1660 files changed, 55466 insertions, 25809 deletions

diff --git a/.clang-format b/.clang-format
index a0a96088c74f..badfc1ba440a 100644
--- a/.clang-format
+++ b/.clang-format
@@ -111,6 +111,7 @@ ForEachMacros:
   - 'css_for_each_descendant_pre'
   - 'device_for_each_child_node'
   - 'dma_fence_chain_for_each'
+  - 'do_for_each_ftrace_op'
   - 'drm_atomic_crtc_for_each_plane'
   - 'drm_atomic_crtc_state_for_each_plane'
   - 'drm_atomic_crtc_state_for_each_plane_state'
@@ -136,6 +137,7 @@ ForEachMacros:
   - 'for_each_active_dev_scope'
   - 'for_each_active_drhd_unit'
   - 'for_each_active_iommu'
+  - 'for_each_aggr_pgid'
   - 'for_each_available_child_of_node'
   - 'for_each_bio'
   - 'for_each_board_func_rsrc'
@@ -234,6 +236,7 @@ ForEachMacros:
   - 'for_each_node_state'
   - 'for_each_node_with_cpus'
   - 'for_each_node_with_property'
+  - 'for_each_nonreserved_multicast_dest_pgid'
   - 'for_each_of_allnodes'
   - 'for_each_of_allnodes_from'
   - 'for_each_of_cpu_node'
@@ -256,6 +259,7 @@ ForEachMacros:
   - 'for_each_pci_dev'
   - 'for_each_pci_msi_entry'
   - 'for_each_pcm_streams'
+  - 'for_each_physmem_range'
   - 'for_each_populated_zone'
   - 'for_each_possible_cpu'
   - 'for_each_present_cpu'
@@ -265,6 +269,8 @@ ForEachMacros:
   - 'for_each_process_thread'
   - 'for_each_property_of_node'
   - 'for_each_registered_fb'
+  - 'for_each_requested_gpio'
+  - 'for_each_requested_gpio_in_range'
   - 'for_each_reserved_mem_region'
   - 'for_each_rtd_codec_dais'
   - 'for_each_rtd_codec_dais_rollback'
@@ -278,12 +284,17 @@ ForEachMacros:
   - 'for_each_sg'
   - 'for_each_sg_dma_page'
   - 'for_each_sg_page'
+  - 'for_each_sgtable_dma_page'
+  - 'for_each_sgtable_dma_sg'
+  - 'for_each_sgtable_page'
+  - 'for_each_sgtable_sg'
   - 'for_each_sibling_event'
   - 'for_each_subelement'
   - 'for_each_subelement_extid'
   - 'for_each_subelement_id'
   - '__for_each_thread'
   - 'for_each_thread'
+  - 'for_each_unicast_dest_pgid'
   - 'for_each_wakeup_source'
   - 'for_each_zone'
   - 'for_each_zone_zonelist'
@@ -464,6 +475,7 @@ ForEachMacros:
   - 'v4l2_m2m_for_each_src_buf'
   - 'v4l2_m2m_for_each_src_buf_safe'
   - 'virtio_device_for_each_vq'
+  - 'while_for_each_ftrace_op'
   - 'xa_for_each'
   - 'xa_for_each_marked'
   - 'xa_for_each_range'
diff --git a/.mailmap b/.mailmap
index 332c7833057f..a780211468e4 100644
--- a/.mailmap
+++ b/.mailmap
@@ -169,6 +169,10 @@ Juha Yrjola <juha.yrjola@solidboot.com>
 Julien Thierry <julien.thierry.kdev@gmail.com> <julien.thierry@arm.com>
 Kamil Konieczny <k.konieczny@samsung.com> <k.konieczny@partner.samsung.com>
 Kay Sievers <kay.sievers@vrfy.org>
+Kees Cook <keescook@chromium.org> <kees.cook@canonical.com>
+Kees Cook <keescook@chromium.org> <keescook@google.com>
+Kees Cook <keescook@chromium.org> <kees@outflux.net>
+Kees Cook <keescook@chromium.org> <kees@ubuntu.com>
 Kenneth W Chen <kenneth.w.chen@intel.com>
 Konstantin Khlebnikov <koct9i@gmail.com> <khlebnikov@yandex-team.ru>
 Konstantin Khlebnikov <koct9i@gmail.com> <k.khlebnikov@samsung.com>
@@ -308,6 +312,7 @@ Tony Luck <tony.luck@intel.com>
 TripleX Chung <xxx.phy@gmail.com> <triplex@zh-kernel.org>
 TripleX Chung <xxx.phy@gmail.com> <zhongyu@18mail.cn>
 Tsuneo Yoshioka <Tsuneo.Yoshioka@f-secure.com>
+Tycho Andersen <tycho@tycho.pizza> <tycho@tycho.ws>
 Uwe Kleine-König <ukleinek@informatik.uni-freiburg.de>
 Uwe Kleine-König <ukl@pengutronix.de>
 Uwe Kleine-König <Uwe.Kleine-Koenig@digi.com>
diff --git a/Documentation/admin-guide/dynamic-debug-howto.rst b/Documentation/admin-guide/dynamic-debug-howto.rst
index e5a8def45f3f..6c04aea8f4cd 100644
--- a/Documentation/admin-guide/dynamic-debug-howto.rst
+++ b/Documentation/admin-guide/dynamic-debug-howto.rst
@@ -156,7 +156,6 @@ against.  Possible keywords are:::
   ``line-range`` cannot contain space, e.g.
   "1-30" is valid range but "1 - 30" is not.
 
-  ``module=foo`` combined keyword=value form is interchangably accepted
 
 The meanings of each keyword are:
 
diff --git a/Documentation/bpf/ringbuf.rst b/Documentation/bpf/ringbuf.rst
index 75f943f0009d..6a615cd62bda 100644
--- a/Documentation/bpf/ringbuf.rst
+++ b/Documentation/bpf/ringbuf.rst
@@ -182,9 +182,6 @@ in the order of reservations, but only after all previous records where
 already committed. It is thus possible for slow producers to temporarily hold
 off submitted records, that were reserved later.
 
-Reservation/commit/consumer protocol is verified by litmus tests in
-Documentation/litmus_tests/bpf-rb/_.
-
 One interesting implementation bit, that significantly simplifies (and thus
 speeds up as well) implementation of both producers and consumers is how data
 area is mapped twice contiguously back-to-back in the virtual memory. This
@@ -200,7 +197,7 @@ a self-pacing notifications of new data being availability.
 being available after commit only if consumer has already caught up right up to
 the record being committed. If not, consumer still has to catch up and thus
 will see new data anyways without needing an extra poll notification.
-Benchmarks (see tools/testing/selftests/bpf/benchs/bench_ringbuf.c_) show that
+Benchmarks (see tools/testing/selftests/bpf/benchs/bench_ringbufs.c) show that
 this allows to achieve a very high throughput without having to resort to
 tricks like "notify only every Nth sample", which are necessary with perf
 buffer. For extreme cases, when BPF program wants more manual control of
diff --git a/Documentation/devicetree/bindings/net/can/microchip,mcp25xxfd.yaml b/Documentation/devicetree/bindings/net/can/microchip,mcp251xfd.yaml
index aa2cad14d6d7..2a884c1fe0e0 100644
--- a/Documentation/devicetree/bindings/net/can/microchip,mcp25xxfd.yaml
+++ b/Documentation/devicetree/bindings/net/can/microchip,mcp251xfd.yaml
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
 %YAML 1.2
 ---
-$id: http://devicetree.org/schemas/net/can/microchip,mcp25xxfd.yaml#
+$id: http://devicetree.org/schemas/net/can/microchip,mcp251xfd.yaml#
 $schema: http://devicetree.org/meta-schemas/core.yaml#
 
 title:
@@ -18,13 +18,13 @@ properties:
         description: for MCP2517FD
       - const: microchip,mcp2518fd
         description: for MCP2518FD
-      - const: microchip,mcp25xxfd
+      - const: microchip,mcp251xfd
         description: to autodetect chip variant
 
   reg:
     maxItems: 1
 
-  interrupts-extended:
+  interrupts:
     maxItems: 1
 
   clocks:
@@ -32,15 +32,13 @@ properties:
 
   vdd-supply:
     description: Regulator that powers the CAN controller.
-    maxItems: 1
 
   xceiver-supply:
     description: Regulator that powers the CAN transceiver.
-    maxItems: 1
 
   microchip,rx-int-gpios:
     description:
-      GPIO phandle of GPIO connected to to INT1 pin of the MCP25XXFD, which
+      GPIO phandle of GPIO connected to to INT1 pin of the MCP251XFD, which
       signals a pending RX interrupt.
     maxItems: 1
 
@@ -52,9 +50,11 @@ properties:
 required:
   - compatible
   - reg
-  - interrupts-extended
+  - interrupts
   - clocks
 
+additionalProperties: false
+
 examples:
   - |
     #include <dt-bindings/gpio/gpio.h>
@@ -65,7 +65,7 @@ examples:
         #size-cells = <0>;
 
         can@0 {
-            compatible = "microchip,mcp25xxfd";
+            compatible = "microchip,mcp251xfd";
             reg = <0>;
             clocks = <&can0_osc>;
             pinctrl-names = "default";
diff --git a/Documentation/devicetree/bindings/net/dsa/b53.txt b/Documentation/devicetree/bindings/net/dsa/b53.txt
index cfd1afdc6e94..f1487a751b1a 100644
--- a/Documentation/devicetree/bindings/net/dsa/b53.txt
+++ b/Documentation/devicetree/bindings/net/dsa/b53.txt
@@ -95,7 +95,7 @@ Ethernet switch connected via MDIO to the host, CPU port wired to eth0:
 
 		fixed-link {
 			speed = <1000>;
-			duplex-full;
+			full-duplex;
 		};
 	};
 
@@ -104,8 +104,9 @@ Ethernet switch connected via MDIO to the host, CPU port wired to eth0:
 		#address-cells = <1>;
 		#size-cells = <0>;
 
-		switch0: ethernet-switch@30 {
+		switch0: ethernet-switch@1e {
 			compatible = "brcm,bcm53125";
+			reg = <30>;
 			#address-cells = <1>;
 			#size-cells = <0>;
 
@@ -128,7 +129,7 @@ Ethernet switch connected via MDIO to the host, CPU port wired to eth0:
 					label = "cable-modem";
 					fixed-link {
 						speed = <1000>;
-						duplex-full;
+						full-duplex;
 					};
 					phy-mode = "rgmii-txid";
 				};
@@ -138,7 +139,7 @@ Ethernet switch connected via MDIO to the host, CPU port wired to eth0:
 					label = "cpu";
 					fixed-link {
 						speed = <1000>;
-						duplex-full;
+						full-duplex;
 					};
 					phy-mode = "rgmii-txid";
 					ethernet = <&eth0>;
diff --git a/Documentation/devicetree/bindings/net/ethernet-controller.yaml b/Documentation/devicetree/bindings/net/ethernet-controller.yaml
index fa2baca8c726..137fbb95c0ea 100644
--- a/Documentation/devicetree/bindings/net/ethernet-controller.yaml
+++ b/Documentation/devicetree/bindings/net/ethernet-controller.yaml
@@ -120,6 +120,13 @@ properties:
       and is useful for determining certain configuration settings
       such as flow control thresholds.
 
+  rx-internal-delay-ps:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    description: |
+      RGMII Receive Clock Delay defined in pico seconds.
+      This is used for controllers that have configurable RX internal delays.
+      If this property is present then the MAC applies the RX delay.
+
   sfp:
     $ref: /schemas/types.yaml#definitions/phandle
     description:
@@ -131,6 +138,13 @@ properties:
       The size of the controller\'s transmit fifo in bytes. This
       is used for components that can have configurable fifo sizes.
 
+  tx-internal-delay-ps:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    description: |
+      RGMII Transmit Clock Delay defined in pico seconds.
+      This is used for controllers that have configurable TX internal delays.
+      If this property is present then the MAC applies the TX delay.
+
   managed:
     description:
       Specifies the PHY management type. If auto is set and fixed-link
diff --git a/Documentation/devicetree/bindings/net/renesas,etheravb.yaml b/Documentation/devicetree/bindings/net/renesas,etheravb.yaml
new file mode 100644
index 000000000000..e13653051b23
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/renesas,etheravb.yaml
@@ -0,0 +1,261 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/net/renesas,etheravb.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Renesas Ethernet AVB
+
+maintainers:
+  - Sergei Shtylyov <sergei.shtylyov@gmail.com>
+
+properties:
+  compatible:
+    oneOf:
+      - items:
+          - enum:
+              - renesas,etheravb-r8a7742      # RZ/G1H
+              - renesas,etheravb-r8a7743      # RZ/G1M
+              - renesas,etheravb-r8a7744      # RZ/G1N
+              - renesas,etheravb-r8a7745      # RZ/G1E
+              - renesas,etheravb-r8a77470     # RZ/G1C
+              - renesas,etheravb-r8a7790      # R-Car H2
+              - renesas,etheravb-r8a7791      # R-Car M2-W
+              - renesas,etheravb-r8a7792      # R-Car V2H
+              - renesas,etheravb-r8a7793      # R-Car M2-N
+              - renesas,etheravb-r8a7794      # R-Car E2
+          - const: renesas,etheravb-rcar-gen2 # R-Car Gen2 and RZ/G1
+
+      - items:
+          - enum:
+              - renesas,etheravb-r8a774a1     # RZ/G2M
+              - renesas,etheravb-r8a774b1     # RZ/G2N
+              - renesas,etheravb-r8a774c0     # RZ/G2E
+              - renesas,etheravb-r8a7795      # R-Car H3
+              - renesas,etheravb-r8a7796      # R-Car M3-W
+              - renesas,etheravb-r8a77961     # R-Car M3-W+
+              - renesas,etheravb-r8a77965     # R-Car M3-N
+              - renesas,etheravb-r8a77970     # R-Car V3M
+              - renesas,etheravb-r8a77980     # R-Car V3H
+              - renesas,etheravb-r8a77990     # R-Car E3
+              - renesas,etheravb-r8a77995     # R-Car D3
+          - const: renesas,etheravb-rcar-gen3 # R-Car Gen3 and RZ/G2
+
+  reg: true
+
+  interrupts: true
+
+  interrupt-names: true
+
+  clocks:
+    maxItems: 1
+
+  iommus:
+    maxItems: 1
+
+  power-domains:
+    maxItems: 1
+
+  resets:
+    maxItems: 1
+
+  phy-mode: true
+
+  phy-handle: true
+
+  '#address-cells':
+    description: Number of address cells for the MDIO bus.
+    const: 1
+
+  '#size-cells':
+    description: Number of size cells on the MDIO bus.
+    const: 0
+
+  renesas,no-ether-link:
+    type: boolean
+    description:
+      Specify when a board does not provide a proper AVB_LINK signal.
+
+  renesas,ether-link-active-low:
+    type: boolean
+    description:
+      Specify when the AVB_LINK signal is active-low instead of normal
+      active-high.
+
+  rx-internal-delay-ps:
+    enum: [0, 1800]
+
+  tx-internal-delay-ps:
+    enum: [0, 2000]
+
+patternProperties:
+  "^ethernet-phy@[0-9a-f]$":
+    type: object
+    $ref: ethernet-phy.yaml#
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - clocks
+  - power-domains
+  - resets
+  - phy-mode
+  - phy-handle
+  - '#address-cells'
+  - '#size-cells'
+
+allOf:
+  - $ref: ethernet-controller.yaml#
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - renesas,etheravb-rcar-gen2
+              - renesas,etheravb-r8a7795
+              - renesas,etheravb-r8a7796
+              - renesas,etheravb-r8a77961
+              - renesas,etheravb-r8a77965
+    then:
+      properties:
+        reg:
+          items:
+            - description: MAC register block
+            - description: Stream buffer
+    else:
+      properties:
+        reg:
+          items:
+            - description: MAC register block
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: renesas,etheravb-rcar-gen2
+    then:
+      properties:
+        interrupts:
+          maxItems: 1
+        interrupt-names:
+          items:
+            - const: mux
+        rx-internal-delay-ps: false
+    else:
+      properties:
+        interrupts:
+          minItems: 25
+          maxItems: 25
+        interrupt-names:
+          items:
+            pattern: '^ch[0-9]+$'
+      required:
+        - interrupt-names
+        - rx-internal-delay-ps
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - renesas,etheravb-r8a774a1
+              - renesas,etheravb-r8a774b1
+              - renesas,etheravb-r8a7795
+              - renesas,etheravb-r8a7796
+              - renesas,etheravb-r8a77961
+              - renesas,etheravb-r8a77965
+              - renesas,etheravb-r8a77970
+              - renesas,etheravb-r8a77980
+    then:
+      required:
+        - tx-internal-delay-ps
+    else:
+      properties:
+        tx-internal-delay-ps: false
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: renesas,etheravb-r8a77995
+    then:
+      properties:
+        rx-internal-delay-ps:
+          const: 1800
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: renesas,etheravb-r8a77980
+    then:
+      properties:
+        tx-internal-delay-ps:
+          const: 2000
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/r8a7795-cpg-mssr.h>
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    #include <dt-bindings/power/r8a7795-sysc.h>
+    #include <dt-bindings/gpio/gpio.h>
+    aliases {
+            ethernet0 = &avb;
+    };
+
+    avb: ethernet@e6800000 {
+            compatible = "renesas,etheravb-r8a7795",
+                         "renesas,etheravb-rcar-gen3";
+            reg = <0xe6800000 0x800>, <0xe6a00000 0x10000>;
+            interrupts = <GIC_SPI 39 IRQ_TYPE_LEVEL_HIGH>,
+                         <GIC_SPI 40 IRQ_TYPE_LEVEL_HIGH>,
+                         <GIC_SPI 41 IRQ_TYPE_LEVEL_HIGH>,
+                         <GIC_SPI 42 IRQ_TYPE_LEVEL_HIGH>,
+                         <GIC_SPI 43 IRQ_TYPE_LEVEL_HIGH>,
+                         <GIC_SPI 44 IRQ_TYPE_LEVEL_HIGH>,
+                         <GIC_SPI 45 IRQ_TYPE_LEVEL_HIGH>,
+                         <GIC_SPI 46 IRQ_TYPE_LEVEL_HIGH>,
+                         <GIC_SPI 47 IRQ_TYPE_LEVEL_HIGH>,
+                         <GIC_SPI 48 IRQ_TYPE_LEVEL_HIGH>,
+                         <GIC_SPI 49 IRQ_TYPE_LEVEL_HIGH>,
+                         <GIC_SPI 50 IRQ_TYPE_LEVEL_HIGH>,
+                         <GIC_SPI 51 IRQ_TYPE_LEVEL_HIGH>,
+                         <GIC_SPI 52 IRQ_TYPE_LEVEL_HIGH>,
+                         <GIC_SPI 53 IRQ_TYPE_LEVEL_HIGH>,
+                         <GIC_SPI 54 IRQ_TYPE_LEVEL_HIGH>,
+                         <GIC_SPI 55 IRQ_TYPE_LEVEL_HIGH>,
+                         <GIC_SPI 56 IRQ_TYPE_LEVEL_HIGH>,
+                         <GIC_SPI 57 IRQ_TYPE_LEVEL_HIGH>,
+                         <GIC_SPI 58 IRQ_TYPE_LEVEL_HIGH>,
+                         <GIC_SPI 59 IRQ_TYPE_LEVEL_HIGH>,
+                         <GIC_SPI 60 IRQ_TYPE_LEVEL_HIGH>,
+                         <GIC_SPI 61 IRQ_TYPE_LEVEL_HIGH>,
+                         <GIC_SPI 62 IRQ_TYPE_LEVEL_HIGH>,
+                         <GIC_SPI 63 IRQ_TYPE_LEVEL_HIGH>;
+            interrupt-names = "ch0", "ch1", "ch2", "ch3", "ch4", "ch5", "ch6",
+                              "ch7", "ch8", "ch9", "ch10", "ch11", "ch12",
+                              "ch13", "ch14", "ch15", "ch16", "ch17", "ch18",
+                              "ch19", "ch20", "ch21", "ch22", "ch23", "ch24";
+            clocks = <&cpg CPG_MOD 812>;
+            iommus = <&ipmmu_ds0 16>;
+            power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
+            resets = <&cpg 812>;
+            phy-mode = "rgmii";
+            phy-handle = <&phy0>;
+            rx-internal-delay-ps = <0>;
+            tx-internal-delay-ps = <2000>;
+            #address-cells = <1>;
+            #size-cells = <0>;
+
+            phy0: ethernet-phy@0 {
+                    rxc-skew-ps = <1500>;
+                    reg = <0>;
+                    interrupt-parent = <&gpio2>;
+                    interrupts = <11 IRQ_TYPE_LEVEL_LOW>;
+                    reset-gpios = <&gpio2 10 GPIO_ACTIVE_LOW>;
+            };
+    };
diff --git a/Documentation/devicetree/bindings/net/renesas,ravb.txt b/Documentation/devicetree/bindings/net/renesas,ravb.txt
deleted file mode 100644
index 032b76f14f4f..000000000000
--- a/Documentation/devicetree/bindings/net/renesas,ravb.txt
+++ /dev/null
@@ -1,134 +0,0 @@
-* Renesas Electronics Ethernet AVB
-
-This file provides information on what the device node for the Ethernet AVB
-interface contains.
-
-Required properties:
-- compatible: Must contain one or more of the following:
-      - "renesas,etheravb-r8a7742" for the R8A7742 SoC.
-      - "renesas,etheravb-r8a7743" for the R8A7743 SoC.
-      - "renesas,etheravb-r8a7744" for the R8A7744 SoC.
-      - "renesas,etheravb-r8a7745" for the R8A7745 SoC.
-      - "renesas,etheravb-r8a77470" for the R8A77470 SoC.
-      - "renesas,etheravb-r8a7790" for the R8A7790 SoC.
-      - "renesas,etheravb-r8a7791" for the R8A7791 SoC.
-      - "renesas,etheravb-r8a7792" for the R8A7792 SoC.
-      - "renesas,etheravb-r8a7793" for the R8A7793 SoC.
-      - "renesas,etheravb-r8a7794" for the R8A7794 SoC.
-      - "renesas,etheravb-rcar-gen2" as a fallback for the above
-		R-Car Gen2 and RZ/G1 devices.
-
-      - "renesas,etheravb-r8a774a1" for the R8A774A1 SoC.
-      - "renesas,etheravb-r8a774b1" for the R8A774B1 SoC.
-      - "renesas,etheravb-r8a774c0" for the R8A774C0 SoC.
-      - "renesas,etheravb-r8a7795" for the R8A7795 SoC.
-      - "renesas,etheravb-r8a7796" for the R8A77960 SoC.
-      - "renesas,etheravb-r8a77961" for the R8A77961 SoC.
-      - "renesas,etheravb-r8a77965" for the R8A77965 SoC.
-      - "renesas,etheravb-r8a77970" for the R8A77970 SoC.
-      - "renesas,etheravb-r8a77980" for the R8A77980 SoC.
-      - "renesas,etheravb-r8a77990" for the R8A77990 SoC.
-      - "renesas,etheravb-r8a77995" for the R8A77995 SoC.
-      - "renesas,etheravb-rcar-gen3" as a fallback for the above
-		R-Car Gen3 and RZ/G2 devices.
-
-	When compatible with the generic version, nodes must list the
-	SoC-specific version corresponding to the platform first followed by
-	the generic version.
-
-- reg: Offset and length of (1) the register block and (2) the stream buffer.
-       The region for the register block is mandatory.
-       The region for the stream buffer is optional, as it is only present on
-       R-Car Gen2 and RZ/G1 SoCs, and on R-Car H3 (R8A7795), M3-W (R8A77960),
-       M3-W+ (R8A77961), and M3-N (R8A77965).
-- interrupts: A list of interrupt-specifiers, one for each entry in
-	      interrupt-names.
-	      If interrupt-names is not present, an interrupt specifier
-	      for a single muxed interrupt.
-- phy-mode: see ethernet.txt file in the same directory.
-- phy-handle: see ethernet.txt file in the same directory.
-- #address-cells: number of address cells for the MDIO bus, must be equal to 1.
-- #size-cells: number of size cells on the MDIO bus, must be equal to 0.
-- clocks: clock phandle and specifier pair.
-- pinctrl-0: phandle, referring to a default pin configuration node.
-
-Optional properties:
-- interrupt-names: A list of interrupt names.
-		   For the R-Car Gen 3 SoCs this property is mandatory;
-		   it should include one entry per channel, named "ch%u",
-		   where %u is the channel number ranging from 0 to 24.
-		   For other SoCs this property is optional; if present
-		   it should contain "mux" for a single muxed interrupt.
-- pinctrl-names: pin configuration state name ("default").
-- renesas,no-ether-link: boolean, specify when a board does not provide a proper
-			 AVB_LINK signal.
-- renesas,ether-link-active-low: boolean, specify when the AVB_LINK signal is
-				 active-low instead of normal active-high.
-
-Example:
-
-	ethernet@e6800000 {
-		compatible = "renesas,etheravb-r8a7795", "renesas,etheravb-rcar-gen3";
-		reg = <0 0xe6800000 0 0x800>, <0 0xe6a00000 0 0x10000>;
-		interrupt-parent = <&gic>;
-		interrupts = <GIC_SPI 39 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 40 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 41 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 42 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 43 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 44 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 45 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 46 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 47 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 48 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 49 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 50 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 51 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 52 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 53 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 54 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 55 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 56 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 57 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 58 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 59 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 60 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 61 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 62 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 63 IRQ_TYPE_LEVEL_HIGH>;
-		interrupt-names = "ch0", "ch1", "ch2", "ch3",
-				  "ch4", "ch5", "ch6", "ch7",
-				  "ch8", "ch9", "ch10", "ch11",
-				  "ch12", "ch13", "ch14", "ch15",
-				  "ch16", "ch17", "ch18", "ch19",
-				  "ch20", "ch21", "ch22", "ch23",
-				  "ch24";
-		clocks = <&cpg CPG_MOD 812>;
-		power-domains = <&cpg>;
-		phy-mode = "rgmii-id";
-		phy-handle = <&phy0>;
-
-		pinctrl-0 = <&ether_pins>;
-		pinctrl-names = "default";
-		renesas,no-ether-link;
-		#address-cells = <1>;
-		#size-cells = <0>;
-
-		phy0: ethernet-phy@0 {
-			rxc-skew-ps = <900>;
-			rxdv-skew-ps = <0>;
-			rxd0-skew-ps = <0>;
-			rxd1-skew-ps = <0>;
-			rxd2-skew-ps = <0>;
-			rxd3-skew-ps = <0>;
-			txc-skew-ps = <900>;
-			txen-skew-ps = <0>;
-			txd0-skew-ps = <0>;
-			txd1-skew-ps = <0>;
-			txd2-skew-ps = <0>;
-			txd3-skew-ps = <0>;
-			reg = <0>;
-			interrupt-parent = <&gpio2>;
-			interrupts = <11 IRQ_TYPE_LEVEL_LOW>;
-		};
-	};
diff --git a/Documentation/devicetree/bindings/spi/brcm,spi-bcm-qspi.txt b/Documentation/devicetree/bindings/spi/brcm,spi-bcm-qspi.txt
index f5e518d099f2..62d4ed2d7fd7 100644
--- a/Documentation/devicetree/bindings/spi/brcm,spi-bcm-qspi.txt
+++ b/Documentation/devicetree/bindings/spi/brcm,spi-bcm-qspi.txt
@@ -23,8 +23,8 @@ Required properties:
 
 - compatible:
     Must be one of :
-    "brcm,spi-bcm-qspi", "brcm,spi-brcmstb-qspi" : MSPI+BSPI on BRCMSTB SoCs
-    "brcm,spi-bcm-qspi", "brcm,spi-brcmstb-mspi" : Second Instance of MSPI
+    "brcm,spi-brcmstb-qspi", "brcm,spi-bcm-qspi" : MSPI+BSPI on BRCMSTB SoCs
+    "brcm,spi-brcmstb-mspi", "brcm,spi-bcm-qspi" : Second Instance of MSPI
 						   BRCMSTB  SoCs
     "brcm,spi-bcm7425-qspi", "brcm,spi-bcm-qspi", "brcm,spi-brcmstb-mspi" : Second Instance of MSPI
     			     			  			    BRCMSTB  SoCs
@@ -36,8 +36,8 @@ Required properties:
     			     			  			    BRCMSTB  SoCs
     "brcm,spi-bcm7278-qspi", "brcm,spi-bcm-qspi", "brcm,spi-brcmstb-mspi" : Second Instance of MSPI
     			     			  			    BRCMSTB  SoCs
-    "brcm,spi-bcm-qspi", "brcm,spi-nsp-qspi"     : MSPI+BSPI on Cygnus, NSP
-    "brcm,spi-bcm-qspi", "brcm,spi-ns2-qspi"     : NS2 SoCs
+    "brcm,spi-nsp-qspi", "brcm,spi-bcm-qspi"     : MSPI+BSPI on Cygnus, NSP
+    "brcm,spi-ns2-qspi", "brcm,spi-bcm-qspi"     : NS2 SoCs
 
 - reg:
     Define the bases and ranges of the associated I/O address spaces.
@@ -86,7 +86,7 @@ BRCMSTB SoC Example:
     spi@f03e3400 {
 		#address-cells = <0x1>;
 		#size-cells = <0x0>;
-		compatible = "brcm,spi-brcmstb-qspi", "brcm,spi-brcmstb-qspi";
+		compatible = "brcm,spi-brcmstb-qspi", "brcm,spi-bcm-qspi";
 		reg = <0xf03e0920 0x4 0xf03e3400 0x188 0xf03e3200 0x50>;
 		reg-names = "cs_reg", "mspi", "bspi";
 		interrupts = <0x6 0x5 0x4 0x3 0x2 0x1 0x0>;
@@ -149,7 +149,7 @@ BRCMSTB SoC Example:
 		#address-cells = <1>;
 		#size-cells = <0>;
 		clocks = <&upg_fixed>;
-		compatible = "brcm,spi-brcmstb-qspi", "brcm,spi-brcmstb-mspi";
+		compatible = "brcm,spi-brcmstb-mspi", "brcm,spi-bcm-qspi";
 		reg = <0xf0416000 0x180>;
 		reg-names = "mspi";
 		interrupts = <0x14>;
@@ -160,7 +160,7 @@ BRCMSTB SoC Example:
 iProc SoC Example:
 
     qspi: spi@18027200 {
-	compatible = "brcm,spi-bcm-qspi", "brcm,spi-nsp-qspi";
+	compatible = "brcm,spi-nsp-qspi", "brcm,spi-bcm-qspi";
 	reg = <0x18027200 0x184>,
 	      <0x18027000 0x124>,
 	      <0x1811c408 0x004>,
@@ -191,7 +191,7 @@ iProc SoC Example:
  NS2 SoC Example:
 
 	       qspi: spi@66470200 {
-		       compatible = "brcm,spi-bcm-qspi", "brcm,spi-ns2-qspi";
+		       compatible = "brcm,spi-ns2-qspi", "brcm,spi-bcm-qspi";
 		       reg = <0x66470200 0x184>,
 			     <0x66470000 0x124>,
 			     <0x67017408 0x004>,
diff --git a/Documentation/driver-api/dma-buf.rst b/Documentation/driver-api/dma-buf.rst
index 100bfd227265..13ea0cc0a3fa 100644
--- a/Documentation/driver-api/dma-buf.rst
+++ b/Documentation/driver-api/dma-buf.rst
@@ -179,7 +179,7 @@ DMA Fence uABI/Sync File
    :internal:
 
 Indefinite DMA Fences
-~~~~~~~~~~~~~~~~~~~~
+~~~~~~~~~~~~~~~~~~~~~
 
 At various times &dma_fence with an indefinite time until dma_fence_wait()
 finishes have been proposed. Examples include:
diff --git a/Documentation/features/debug/debug-vm-pgtable/arch-support.txt b/Documentation/features/debug/debug-vm-pgtable/arch-support.txt
index 53da483c8326..1c49723e7534 100644
--- a/Documentation/features/debug/debug-vm-pgtable/arch-support.txt
+++ b/Documentation/features/debug/debug-vm-pgtable/arch-support.txt
@@ -22,7 +22,7 @@
     |       nios2: | TODO |
     |    openrisc: | TODO |
     |      parisc: | TODO |
-    |     powerpc: |  ok  |
+    |     powerpc: | TODO |
     |       riscv: |  ok  |
     |        s390: |  ok  |
     |          sh: | TODO |
diff --git a/Documentation/networking/caif/index.rst b/Documentation/networking/caif/index.rst
index 86e5b7832ec3..ec29b6f4bdb4 100644
--- a/Documentation/networking/caif/index.rst
+++ b/Documentation/networking/caif/index.rst
@@ -10,4 +10,3 @@ Contents:
 
    linux_caif
    caif
-   spi_porting
diff --git a/Documentation/networking/caif/spi_porting.rst b/Documentation/networking/caif/spi_porting.rst
deleted file mode 100644
index d49f874b20ac..000000000000
--- a/Documentation/networking/caif/spi_porting.rst
+++ /dev/null
@@ -1,229 +0,0 @@
-.. SPDX-License-Identifier: GPL-2.0
-
-================
-CAIF SPI porting
-================
-
-CAIF SPI basics
-===============
-
-Running CAIF over SPI needs some extra setup, owing to the nature of SPI.
-Two extra GPIOs have been added in order to negotiate the transfers
-between the master and the slave. The minimum requirement for running
-CAIF over SPI is a SPI slave chip and two GPIOs (more details below).
-Please note that running as a slave implies that you need to keep up
-with the master clock. An overrun or underrun event is fatal.
-
-CAIF SPI framework
-==================
-
-To make porting as easy as possible, the CAIF SPI has been divided in
-two parts. The first part (called the interface part) deals with all
-generic functionality such as length framing, SPI frame negotiation
-and SPI frame delivery and transmission. The other part is the CAIF
-SPI slave device part, which is the module that you have to write if
-you want to run SPI CAIF on a new hardware. This part takes care of
-the physical hardware, both with regard to SPI and to GPIOs.
-
-- Implementing a CAIF SPI device:
-
-	- Functionality provided by the CAIF SPI slave device:
-
-	In order to implement a SPI device you will, as a minimum,
-	need to implement the following
-	functions:
-
-	::
-
-	    int (*init_xfer) (struct cfspi_xfer * xfer, struct cfspi_dev *dev):
-
-	This function is called by the CAIF SPI interface to give
-	you a chance to set up your hardware to be ready to receive
-	a stream of data from the master. The xfer structure contains
-	both physical and logical addresses, as well as the total length
-	of the transfer in both directions.The dev parameter can be used
-	to map to different CAIF SPI slave devices.
-
-	::
-
-	    void (*sig_xfer) (bool xfer, struct cfspi_dev *dev):
-
-	This function is called by the CAIF SPI interface when the output
-	(SPI_INT) GPIO needs to change state. The boolean value of the xfer
-	variable indicates whether the GPIO should be asserted (HIGH) or
-	deasserted (LOW). The dev parameter can be used to map to different CAIF
-	SPI slave devices.
-
-	- Functionality provided by the CAIF SPI interface:
-
-	::
-
-	    void (*ss_cb) (bool assert, struct cfspi_ifc *ifc);
-
-	This function is called by the CAIF SPI slave device in order to
-	signal a change of state of the input GPIO (SS) to the interface.
-	Only active edges are mandatory to be reported.
-	This function can be called from IRQ context (recommended in order
-	not to introduce latency). The ifc parameter should be the pointer
-	returned from the platform probe function in the SPI device structure.
-
-	::
-
-	    void (*xfer_done_cb) (struct cfspi_ifc *ifc);
-
-	This function is called by the CAIF SPI slave device in order to
-	report that a transfer is completed. This function should only be
-	called once both the transmission and the reception are completed.
-	This function can be called from IRQ context (recommended in order
-	not to introduce latency). The ifc parameter should be the pointer
-	returned from the platform probe function in the SPI device structure.
-
-	- Connecting the bits and pieces:
-
-		- Filling in the SPI slave device structure:
-
-		  Connect the necessary callback functions.
-
-		  Indicate clock speed (used to calculate toggle delays).
-
-		  Chose a suitable name (helps debugging if you use several CAIF
-		  SPI slave devices).
-
-		  Assign your private data (can be used to map to your
-		  structure).
-
-		- Filling in the SPI slave platform device structure:
-
-		  Add name of driver to connect to ("cfspi_sspi").
-
-		  Assign the SPI slave device structure as platform data.
-
-Padding
-=======
-
-In order to optimize throughput, a number of SPI padding options are provided.
-Padding can be enabled independently for uplink and downlink transfers.
-Padding can be enabled for the head, the tail and for the total frame size.
-The padding needs to be correctly configured on both sides of the link.
-The padding can be changed via module parameters in cfspi_sspi.c or via
-the sysfs directory of the cfspi_sspi driver (before device registration).
-
-- CAIF SPI device template::
-
-    /*
-    *	Copyright (C) ST-Ericsson AB 2010
-    *	Author: Daniel Martensson / Daniel.Martensson@stericsson.com
-    *	License terms: GNU General Public License (GPL), version 2.
-    *
-    */
-
-    #include <linux/init.h>
-    #include <linux/module.h>
-    #include <linux/device.h>
-    #include <linux/wait.h>
-    #include <linux/interrupt.h>
-    #include <linux/dma-mapping.h>
-    #include <net/caif/caif_spi.h>
-
-    MODULE_LICENSE("GPL");
-
-    struct sspi_struct {
-	    struct cfspi_dev sdev;
-	    struct cfspi_xfer *xfer;
-    };
-
-    static struct sspi_struct slave;
-    static struct platform_device slave_device;
-
-    static irqreturn_t sspi_irq(int irq, void *arg)
-    {
-	    /* You only need to trigger on an edge to the active state of the
-	    * SS signal. Once a edge is detected, the ss_cb() function should be
-	    * called with the parameter assert set to true. It is OK
-	    * (and even advised) to call the ss_cb() function in IRQ context in
-	    * order not to add any delay. */
-
-	    return IRQ_HANDLED;
-    }
-
-    static void sspi_complete(void *context)
-    {
-	    /* Normally the DMA or the SPI framework will call you back
-	    * in something similar to this. The only thing you need to
-	    * do is to call the xfer_done_cb() function, providing the pointer
-	    * to the CAIF SPI interface. It is OK to call this function
-	    * from IRQ context. */
-    }
-
-    static int sspi_init_xfer(struct cfspi_xfer *xfer, struct cfspi_dev *dev)
-    {
-	    /* Store transfer info. For a normal implementation you should
-	    * set up your DMA here and make sure that you are ready to
-	    * receive the data from the master SPI. */
-
-	    struct sspi_struct *sspi = (struct sspi_struct *)dev->priv;
-
-	    sspi->xfer = xfer;
-
-	    return 0;
-    }
-
-    void sspi_sig_xfer(bool xfer, struct cfspi_dev *dev)
-    {
-	    /* If xfer is true then you should assert the SPI_INT to indicate to
-	    * the master that you are ready to receive the data from the master
-	    * SPI. If xfer is false then you should de-assert SPI_INT to indicate
-	    * that the transfer is done.
-	    */
-
-	    struct sspi_struct *sspi = (struct sspi_struct *)dev->priv;
-    }
-
-    static void sspi_release(struct device *dev)
-    {
-	    /*
-	    * Here you should release your SPI device resources.
-	    */
-    }
-
-    static int __init sspi_init(void)
-    {
-	    /* Here you should initialize your SPI device by providing the
-	    * necessary functions, clock speed, name and private data. Once
-	    * done, you can register your device with the
-	    * platform_device_register() function. This function will return
-	    * with the CAIF SPI interface initialized. This is probably also
-	    * the place where you should set up your GPIOs, interrupts and SPI
-	    * resources. */
-
-	    int res = 0;
-
-	    /* Initialize slave device. */
-	    slave.sdev.init_xfer = sspi_init_xfer;
-	    slave.sdev.sig_xfer = sspi_sig_xfer;
-	    slave.sdev.clk_mhz = 13;
-	    slave.sdev.priv = &slave;
-	    slave.sdev.name = "spi_sspi";
-	    slave_device.dev.release = sspi_release;
-
-	    /* Initialize platform device. */
-	    slave_device.name = "cfspi_sspi";
-	    slave_device.dev.platform_data = &slave.sdev;
-
-	    /* Register platform device. */
-	    res = platform_device_register(&slave_device);
-	    if (res) {
-		    printk(KERN_WARNING "sspi_init: failed to register dev.\n");
-		    return -ENODEV;
-	    }
-
-	    return res;
-    }
-
-    static void __exit sspi_exit(void)
-    {
-	    platform_device_del(&slave_device);
-    }
-
-    module_init(sspi_init);
-    module_exit(sspi_exit);
diff --git a/Documentation/networking/devlink/devlink-flash.rst b/Documentation/networking/devlink/devlink-flash.rst
index 40a87c0222cb..603e732f00cc 100644
--- a/Documentation/networking/devlink/devlink-flash.rst
+++ b/Documentation/networking/devlink/devlink-flash.rst
@@ -16,6 +16,34 @@ Note that the file name is a path relative to the firmware loading path
 (usually ``/lib/firmware/``). Drivers may send status updates to inform
 user space about the progress of the update operation.
 
+Overwrite Mask
+==============
+
+The ``devlink-flash`` command allows optionally specifying a mask indicating
+how the device should handle subsections of flash components when updating.
+This mask indicates the set of sections which are allowed to be overwritten.
+
+.. list-table:: List of overwrite mask bits
+   :widths: 5 95
+
+   * - Name
+     - Description
+   * - ``DEVLINK_FLASH_OVERWRITE_SETTINGS``
+     - Indicates that the device should overwrite settings in the components
+       being updated with the settings found in the provided image.
+   * - ``DEVLINK_FLASH_OVERWRITE_IDENTIFIERS``
+     - Indicates that the device should overwrite identifiers in the
+       components being updated with the identifiers found in the provided
+       image. This includes MAC addresses, serial IDs, and similar device
+       identifiers.
+
+Multiple overwrite bits may be combined and requested together. If no bits
+are provided, it is expected that the device only update firmware binaries
+in the components being updated. Settings and identifiers are expected to be
+preserved across the update. A device may not support every combination and
+the driver for such a device must reject any combination which cannot be
+faithfully implemented.
+
 Firmware Loading
 ================
 
diff --git a/Documentation/networking/devlink/devlink-trap.rst b/Documentation/networking/devlink/devlink-trap.rst
index 7a798352b45d..ef719ceac299 100644
--- a/Documentation/networking/devlink/devlink-trap.rst
+++ b/Documentation/networking/devlink/devlink-trap.rst
@@ -409,6 +409,73 @@ be added to the following table:
      - ``drop``
      - Traps packets dropped due to the RED (Random Early Detection) algorithm
        (i.e., early drops)
+   * - ``vxlan_parsing``
+     - ``drop``
+     - Traps packets dropped due to an error in the VXLAN header parsing which
+       might be because of packet truncation or the I flag is not set.
+   * - ``llc_snap_parsing``
+     - ``drop``
+     - Traps packets dropped due to an error in the LLC+SNAP header parsing
+   * - ``vlan_parsing``
+     - ``drop``
+     - Traps packets dropped due to an error in the VLAN header parsing. Could
+       include unexpected packet truncation.
+   * - ``pppoe_ppp_parsing``
+     - ``drop``
+     - Traps packets dropped due to an error in the PPPoE+PPP header parsing.
+       This could include finding a session ID of 0xFFFF (which is reserved and
+       not for use), a PPPoE length which is larger than the frame received or
+       any common error on this type of header
+   * - ``mpls_parsing``
+     - ``drop``
+     - Traps packets dropped due to an error in the MPLS header parsing which
+       could include unexpected header truncation
+   * - ``arp_parsing``
+     - ``drop``
+     - Traps packets dropped due to an error in the ARP header parsing
+   * - ``ip_1_parsing``
+     - ``drop``
+     - Traps packets dropped due to an error in the first IP header parsing.
+       This packet trap could include packets which do not pass an IP checksum
+       check, a header length check (a minimum of 20 bytes), which might suffer
+       from packet truncation thus the total length field exceeds the received
+       packet length etc
+   * - ``ip_n_parsing``
+     - ``drop``
+     - Traps packets dropped due to an error in the parsing of the last IP
+       header (the inner one in case of an IP over IP tunnel). The same common
+       error checking is performed here as for the ip_1_parsing trap
+   * - ``gre_parsing``
+     - ``drop``
+     - Traps packets dropped due to an error in the GRE header parsing
+   * - ``udp_parsing``
+     - ``drop``
+     - Traps packets dropped due to an error in the UDP header parsing.
+       This packet trap could include checksum errorrs, an improper UDP
+       length detected (smaller than 8 bytes) or detection of header
+       truncation.
+   * - ``tcp_parsing``
+     - ``drop``
+     - Traps packets dropped due to an error in the TCP header parsing.
+       This could include TCP checksum errors, improper combination of SYN, FIN
+       and/or RESET etc.
+   * - ``ipsec_parsing``
+     - ``drop``
+     - Traps packets dropped due to an error in the IPSEC header parsing
+   * - ``sctp_parsing``
+     - ``drop``
+     - Traps packets dropped due to an error in the SCTP header parsing.
+       This would mean that port number 0 was used or that the header is
+       truncated.
+   * - ``dccp_parsing``
+     - ``drop``
+     - Traps packets dropped due to an error in the DCCP header parsing
+   * - ``gtp_parsing``
+     - ``drop``
+     - Traps packets dropped due to an error in the GTP header parsing
+   * - ``esp_parsing``
+     - ``drop``
+     - Traps packets dropped due to an error in the ESP header parsing
 
 Driver-specific Packet Traps
 ============================
@@ -509,6 +576,9 @@ narrow. The description of these groups must be added to the following table:
    * - ``acl_trap``
      - Contains packet traps for packets that were trapped (logged) by the
        device during ACL processing
+   * - ``parser_error_drops``
+     - Contains packet traps for packets that were marked by the device during
+       parsing as erroneous
 
 Packet Trap Policers
 ====================
diff --git a/Documentation/networking/devlink/ice.rst b/Documentation/networking/devlink/ice.rst
index 237848d56f9b..8eb50ba41f1a 100644
--- a/Documentation/networking/devlink/ice.rst
+++ b/Documentation/networking/devlink/ice.rst
@@ -81,6 +81,37 @@ The ``ice`` driver reports the following versions
       - 0xee16ced7
       - The first 4 bytes of the hash of the netlist module contents.
 
+Flash Update
+============
+
+The ``ice`` driver implements support for flash update using the
+``devlink-flash`` interface. It supports updating the device flash using a
+combined flash image that contains the ``fw.mgmt``, ``fw.undi``, and
+``fw.netlist`` components.
+
+.. list-table:: List of supported overwrite modes
+   :widths: 5 95
+
+   * - Bits
+     - Behavior
+   * - ``DEVLINK_FLASH_OVERWRITE_SETTINGS``
+     - Do not preserve settings stored in the flash components being
+       updated. This includes overwriting the port configuration that
+       determines the number of physical functions the device will
+       initialize with.
+   * - ``DEVLINK_FLASH_OVERWRITE_SETTINGS`` and ``DEVLINK_FLASH_OVERWRITE_IDENTIFIERS``
+     - Do not preserve either settings or identifiers. Overwrite everything
+       in the flash with the contents from the provided image, without
+       performing any preservation. This includes overwriting device
+       identifying fields such as the MAC address, VPD area, and device
+       serial number. It is expected that this combination be used with an
+       image customized for the specific device.
+
+The ice hardware does not support overwriting only identifiers while
+preserving settings, and thus ``DEVLINK_FLASH_OVERWRITE_IDENTIFIERS`` on its
+own will be rejected. If no overwrite mask is provided, the firmware will be
+instructed to preserve all settings and identifying fields when updating.
+
 Regions
 =======
 
diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst
index 2c8e0ddf548e..30b98245979f 100644
--- a/Documentation/networking/ethtool-netlink.rst
+++ b/Documentation/networking/ethtool-netlink.rst
@@ -207,6 +207,7 @@ Userspace to kernel:
   ``ETHTOOL_MSG_TSINFO_GET``		get timestamping info
   ``ETHTOOL_MSG_CABLE_TEST_ACT``        action start cable test
   ``ETHTOOL_MSG_CABLE_TEST_TDR_ACT``    action start raw TDR cable test
+  ``ETHTOOL_MSG_TUNNEL_INFO_GET``       get tunnel offload info
   ===================================== ================================
 
 Kernel to userspace:
@@ -240,6 +241,7 @@ Kernel to userspace:
   ``ETHTOOL_MSG_TSINFO_GET_REPLY``	timestamping info
   ``ETHTOOL_MSG_CABLE_TEST_NTF``        Cable test results
   ``ETHTOOL_MSG_CABLE_TEST_TDR_NTF``    Cable test TDR results
+  ``ETHTOOL_MSG_TUNNEL_INFO_GET_REPLY`` tunnel offload info
   ===================================== =================================
 
 ``GET`` requests are sent by userspace applications to retrieve device
@@ -1374,4 +1376,5 @@ are netlink only.
   ``ETHTOOL_SFECPARAM``               n/a
   n/a                                 ''ETHTOOL_MSG_CABLE_TEST_ACT''
   n/a                                 ''ETHTOOL_MSG_CABLE_TEST_TDR_ACT''
+  n/a                                 ``ETHTOOL_MSG_TUNNEL_INFO_GET``
   =================================== =====================================
diff --git a/Documentation/networking/kapi.rst b/Documentation/networking/kapi.rst
index f03ae64be8bc..d198fa5eaacd 100644
--- a/Documentation/networking/kapi.rst
+++ b/Documentation/networking/kapi.rst
@@ -134,6 +134,15 @@ PHY Support
 .. kernel-doc:: drivers/net/phy/phy.c
    :internal:
 
+.. kernel-doc:: drivers/net/phy/phy-core.c
+   :export:
+
+.. kernel-doc:: drivers/net/phy/phy-c45.c
+   :export:
+
+.. kernel-doc:: include/linux/phy.h
+   :internal:
+
 .. kernel-doc:: drivers/net/phy/phy_device.c
    :export:
 
diff --git a/Documentation/networking/vxlan.rst b/Documentation/networking/vxlan.rst
index ce239fa01848..2759dc1cc525 100644
--- a/Documentation/networking/vxlan.rst
+++ b/Documentation/networking/vxlan.rst
@@ -58,3 +58,31 @@ forwarding table using the new bridge command.
 3. Show forwarding table::
 
     # bridge fdb show dev vxlan0
+
+The following NIC features may indicate support for UDP tunnel-related
+offloads (most commonly VXLAN features, but support for a particular
+encapsulation protocol is NIC specific):
+
+ - `tx-udp_tnl-segmentation`
+ - `tx-udp_tnl-csum-segmentation`
+    ability to perform TCP segmentation offload of UDP encapsulated frames
+
+ - `rx-udp_tunnel-port-offload`
+    receive side parsing of UDP encapsulated frames which allows NICs to
+    perform protocol-aware offloads, like checksum validation offload of
+    inner frames (only needed by NICs without protocol-agnostic offloads)
+
+For devices supporting `rx-udp_tunnel-port-offload` the list of currently
+offloaded ports can be interrogated with `ethtool`::
+
+  $ ethtool --show-tunnels eth0
+  Tunnel information for eth0:
+    UDP port table 0:
+      Size: 4
+      Types: vxlan
+      No entries
+    UDP port table 1:
+      Size: 4
+      Types: geneve, vxlan-gpe
+      Entries (1):
+          port 1230, vxlan-gpe
diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index eb3a1316f03e..51191b56e61c 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -6130,7 +6130,7 @@ HvCallSendSyntheticClusterIpi, HvCallSendSyntheticClusterIpiEx.
 8.21 KVM_CAP_HYPERV_DIRECT_TLBFLUSH
 -----------------------------------
 
-:Architecture: x86
+:Architectures: x86
 
 This capability indicates that KVM running on top of Hyper-V hypervisor
 enables Direct TLB flush for its guests meaning that TLB flush
@@ -6143,19 +6143,53 @@ in CPUID and only exposes Hyper-V identification. In this case, guest
 thinks it's running on Hyper-V and only use Hyper-V hypercalls.
 
 8.22 KVM_CAP_S390_VCPU_RESETS
+-----------------------------
 
-Architectures: s390
+:Architectures: s390
 
 This capability indicates that the KVM_S390_NORMAL_RESET and
 KVM_S390_CLEAR_RESET ioctls are available.
 
 8.23 KVM_CAP_S390_PROTECTED
+---------------------------
 
-Architecture: s390
-
+:Architectures: s390
 
 This capability indicates that the Ultravisor has been initialized and
 KVM can therefore start protected VMs.
 This capability governs the KVM_S390_PV_COMMAND ioctl and the
 KVM_MP_STATE_LOAD MP_STATE. KVM_SET_MP_STATE can fail for protected
 guests when the state change is invalid.
+
+8.24 KVM_CAP_STEAL_TIME
+-----------------------
+
+:Architectures: arm64, x86
+
+This capability indicates that KVM supports steal time accounting.
+When steal time accounting is supported it may be enabled with
+architecture-specific interfaces.  This capability and the architecture-
+specific interfaces must be consistent, i.e. if one says the feature
+is supported, than the other should as well and vice versa.  For arm64
+see Documentation/virt/kvm/devices/vcpu.rst "KVM_ARM_VCPU_PVTIME_CTRL".
+For x86 see Documentation/virt/kvm/msr.rst "MSR_KVM_STEAL_TIME".
+
+8.25 KVM_CAP_S390_DIAG318
+-------------------------
+
+:Architectures: s390
+
+This capability enables a guest to set information about its control program
+(i.e. guest kernel type and version). The information is helpful during
+system/firmware service events, providing additional data about the guest
+environments running on the machine.
+
+The information is associated with the DIAGNOSE 0x318 instruction, which sets
+an 8-byte value consisting of a one-byte Control Program Name Code (CPNC) and
+a 7-byte Control Program Version Code (CPVC). The CPNC determines what
+environment the control program is running in (e.g. Linux, z/VM...), and the
+CPVC is used for information specific to OS (e.g. Linux version, Linux
+distribution...)
+
+If this capability is available, then the CPNC and CPVC can be synchronized
+between KVM and userspace via the sync regs mechanism (KVM_SYNC_DIAG318).
diff --git a/MAINTAINERS b/MAINTAINERS
index e3c1c70057e4..c2038d47e47f 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1694,7 +1694,6 @@ F:	arch/arm/mach-cns3xxx/
 
 ARM/CAVIUM THUNDER NETWORK DRIVER
 M:	Sunil Goutham <sgoutham@marvell.com>
-M:	Robert Richter <rrichter@marvell.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Supported
 F:	drivers/net/ethernet/cavium/thunder/
@@ -3948,8 +3947,8 @@ W:	https://wireless.wiki.kernel.org/en/users/Drivers/carl9170
 F:	drivers/net/wireless/ath/carl9170/
 
 CAVIUM I2C DRIVER
-M:	Robert Richter <rrichter@marvell.com>
-S:	Supported
+M:	Robert Richter <rric@kernel.org>
+S:	Odd Fixes
 W:	http://www.marvell.com
 F:	drivers/i2c/busses/i2c-octeon*
 F:	drivers/i2c/busses/i2c-thunderx*
@@ -3964,8 +3963,8 @@ W:	http://www.marvell.com
 F:	drivers/net/ethernet/cavium/liquidio/
 
 CAVIUM MMC DRIVER
-M:	Robert Richter <rrichter@marvell.com>
-S:	Supported
+M:	Robert Richter <rric@kernel.org>
+S:	Odd Fixes
 W:	http://www.marvell.com
 F:	drivers/mmc/host/cavium*
 
@@ -3977,9 +3976,9 @@ W:	http://www.marvell.com
 F:	drivers/crypto/cavium/cpt/
 
 CAVIUM THUNDERX2 ARM64 SOC
-M:	Robert Richter <rrichter@marvell.com>
+M:	Robert Richter <rric@kernel.org>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
-S:	Maintained
+S:	Odd Fixes
 F:	Documentation/devicetree/bindings/arm/cavium-thunder2.txt
 F:	arch/arm64/boot/dts/cavium/thunder2-99xx*
 
@@ -4258,6 +4257,8 @@ S:	Maintained
 F:	.clang-format
 
 CLANG/LLVM BUILD SUPPORT
+M:	Nathan Chancellor <natechancellor@gmail.com>
+M:	Nick Desaulniers <ndesaulniers@google.com>
 L:	clang-built-linux@googlegroups.com
 S:	Supported
 W:	https://clangbuiltlinux.github.io/
@@ -4407,12 +4408,6 @@ T:	git git://git.infradead.org/users/hch/configfs.git
 F:	fs/configfs/
 F:	include/linux/configfs.h
 
-CONNECTOR
-M:	Evgeniy Polyakov <zbr@ioremap.net>
-L:	netdev@vger.kernel.org
-S:	Maintained
-F:	drivers/connector/
-
 CONSOLE SUBSYSTEM
 M:	Greg Kroah-Hartman <gregkh@linuxfoundation.org>
 S:	Supported
@@ -6188,7 +6183,7 @@ F:	Documentation/devicetree/bindings/edac/aspeed-sdram-edac.txt
 F:	drivers/edac/aspeed_edac.c
 
 EDAC-BLUEFIELD
-M:	Shravan Kumar Ramani <sramani@nvidia.com>
+M:	Shravan Kumar Ramani <shravankr@nvidia.com>
 S:	Supported
 F:	drivers/edac/bluefield_edac.c
 
@@ -6200,16 +6195,15 @@ F:	drivers/edac/highbank*
 
 EDAC-CAVIUM OCTEON
 M:	Ralf Baechle <ralf@linux-mips.org>
-M:	Robert Richter <rrichter@marvell.com>
 L:	linux-edac@vger.kernel.org
 L:	linux-mips@vger.kernel.org
 S:	Supported
 F:	drivers/edac/octeon_edac*
 
 EDAC-CAVIUM THUNDERX
-M:	Robert Richter <rrichter@marvell.com>
+M:	Robert Richter <rric@kernel.org>
 L:	linux-edac@vger.kernel.org
-S:	Supported
+S:	Odd Fixes
 F:	drivers/edac/thunderx_edac*
 
 EDAC-CORE
@@ -6217,7 +6211,7 @@ M:	Borislav Petkov <bp@alien8.de>
 M:	Mauro Carvalho Chehab <mchehab@kernel.org>
 M:	Tony Luck <tony.luck@intel.com>
 R:	James Morse <james.morse@arm.com>
-R:	Robert Richter <rrichter@marvell.com>
+R:	Robert Richter <rric@kernel.org>
 L:	linux-edac@vger.kernel.org
 S:	Supported
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/ras/ras.git edac-for-next
@@ -6913,6 +6907,14 @@ L:	linuxppc-dev@lists.ozlabs.org
 S:	Maintained
 F:	drivers/dma/fsldma.*
 
+FREESCALE DSPI DRIVER
+M:	Vladimir Oltean <olteanv@gmail.com>
+L:	linux-spi@vger.kernel.org
+S:	Maintained
+F:	Documentation/devicetree/bindings/spi/spi-fsl-dspi.txt
+F:	drivers/spi/spi-fsl-dspi.c
+F:	include/linux/spi/spi-fsl-dspi.h
+
 FREESCALE ENETC ETHERNET DRIVERS
 M:	Claudiu Manoil <claudiu.manoil@nxp.com>
 L:	netdev@vger.kernel.org
@@ -8284,7 +8286,7 @@ IA64 (Itanium) PLATFORM
 M:	Tony Luck <tony.luck@intel.com>
 M:	Fenghua Yu <fenghua.yu@intel.com>
 L:	linux-ia64@vger.kernel.org
-S:	Maintained
+S:	Odd Fixes
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/aegl/linux.git
 F:	Documentation/ia64/
 F:	arch/ia64/
@@ -8333,8 +8335,9 @@ S:	Supported
 F:	drivers/pci/hotplug/rpaphp*
 
 IBM Power SRIOV Virtual NIC Device Driver
-M:	Thomas Falcon <tlfalcon@linux.ibm.com>
-M:	John Allen <jallen@linux.ibm.com>
+M:	Dany Madden <drt@linux.ibm.com>
+M:	Lijun Pan <ljp@linux.ibm.com>
+M:	Sukadev Bhattiprolu <sukadev@linux.ibm.com>
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	drivers/net/ethernet/ibm/ibmvnic.*
@@ -8348,7 +8351,7 @@ F:	arch/powerpc/platforms/powernv/copy-paste.h
 F:	arch/powerpc/platforms/powernv/vas*
 
 IBM Power Virtual Ethernet Device Driver
-M:	Thomas Falcon <tlfalcon@linux.ibm.com>
+M:	Cristobal Forno <cforno12@linux.ibm.com>
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	drivers/net/ethernet/ibm/ibmveth.*
@@ -9255,7 +9258,7 @@ F:	drivers/firmware/iscsi_ibft*
 
 ISCSI EXTENSIONS FOR RDMA (ISER) INITIATOR
 M:	Sagi Grimberg <sagi@grimberg.me>
-M:	Max Gurtovoy <maxg@nvidia.com>
+M:	Max Gurtovoy <mgurtovoy@nvidia.com>
 L:	linux-rdma@vger.kernel.org
 S:	Supported
 W:	http://www.openfabrics.org
@@ -9804,7 +9807,7 @@ F:	drivers/scsi/53c700*
 
 LEAKING_ADDRESSES
 M:	Tobin C. Harding <me@tobin.cc>
-M:	Tycho Andersen <tycho@tycho.ws>
+M:	Tycho Andersen <tycho@tycho.pizza>
 L:	kernel-hardening@lists.openwall.com
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tobin/leaks.git
@@ -11062,6 +11065,7 @@ F:	drivers/char/hw_random/mtk-rng.c
 
 MEDIATEK SWITCH DRIVER
 M:	Sean Wang <sean.wang@mediatek.com>
+M:	Landen Chao <Landen.Chao@mediatek.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	drivers/net/dsa/mt7530.*
@@ -12061,7 +12065,6 @@ M:	Neil Horman <nhorman@tuxdriver.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
 W:	https://fedorahosted.org/dropwatch/
-F:	include/net/drop_monitor.h
 F:	include/uapi/linux/net_dropmon.h
 F:	net/core/drop_monitor.c
 
@@ -12075,6 +12078,7 @@ Q:	http://patchwork.ozlabs.org/project/netdev/list/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git
 F:	Documentation/devicetree/bindings/net/
+F:	drivers/connector/
 F:	drivers/net/
 F:	include/linux/etherdevice.h
 F:	include/linux/fcdevice.h
@@ -12154,6 +12158,7 @@ F:	net/ipv6/ipcomp6.c
 F:	net/ipv6/xfrm*
 F:	net/key/
 F:	net/xfrm/
+F:	tools/testing/selftests/net/ipsec.c
 
 NETWORKING [IPv4/IPv6]
 M:	"David S. Miller" <davem@davemloft.net>
@@ -12537,6 +12542,7 @@ F:	drivers/net/dsa/ocelot/*
 F:	drivers/net/ethernet/mscc/
 F:	include/soc/mscc/ocelot*
 F:	net/dsa/tag_ocelot.c
+F:	tools/testing/selftests/drivers/net/ocelot/*
 
 OCXL (Open Coherent Accelerator Processor Interface OpenCAPI) DRIVER
 M:	Frederic Barrat <fbarrat@linux.ibm.com>
@@ -13474,10 +13480,10 @@ F:	Documentation/devicetree/bindings/pci/axis,artpec*
 F:	drivers/pci/controller/dwc/*artpec*
 
 PCIE DRIVER FOR CAVIUM THUNDERX
-M:	Robert Richter <rrichter@marvell.com>
+M:	Robert Richter <rric@kernel.org>
 L:	linux-pci@vger.kernel.org
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
-S:	Supported
+S:	Odd Fixes
 F:	drivers/pci/controller/pci-thunder-*
 
 PCIE DRIVER FOR HISILICON
@@ -14416,7 +14422,7 @@ M:	Rob Clark <robdclark@gmail.com>
 L:	iommu@lists.linux-foundation.org
 L:	linux-arm-msm@vger.kernel.org
 S:	Maintained
-F:	drivers/iommu/qcom_iommu.c
+F:	drivers/iommu/arm/arm-smmu/qcom_iommu.c
 
 QUALCOMM IPCC MAILBOX DRIVER
 M:	Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
@@ -15598,6 +15604,7 @@ F:	include/uapi/linux/sed*
 SECURITY CONTACT
 M:	Security Officers <security@kernel.org>
 S:	Supported
+F:	Documentation/admin-guide/security-bugs.rst
 
 SECURITY SUBSYSTEM
 M:	James Morris <jmorris@namei.org>
@@ -17267,8 +17274,8 @@ S:	Maintained
 F:	drivers/net/thunderbolt.c
 
 THUNDERX GPIO DRIVER
-M:	Robert Richter <rrichter@marvell.com>
-S:	Maintained
+M:	Robert Richter <rric@kernel.org>
+S:	Odd Fixes
 F:	drivers/gpio/gpio-thunderx.c
 
 TI AM437X VPFE DRIVER
diff --git a/Makefile b/Makefile
index ff5e0731d26d..d387c5a239b7 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 5
 PATCHLEVEL = 9
 SUBLEVEL = 0
-EXTRAVERSION = -rc3
+EXTRAVERSION = -rc6
 NAME = Kleptomaniac Octopus
 
 # *DOCUMENTATION*
@@ -882,10 +882,6 @@ KBUILD_CFLAGS_KERNEL += -ffunction-sections -fdata-sections
 LDFLAGS_vmlinux += --gc-sections
 endif
 
-ifdef CONFIG_LIVEPATCH
-KBUILD_CFLAGS += $(call cc-option, -flive-patching=inline-clone)
-endif
-
 ifdef CONFIG_SHADOW_CALL_STACK
 CC_FLAGS_SCS	:= -fsanitize=shadow-call-stack
 KBUILD_CFLAGS	+= $(CC_FLAGS_SCS)
@@ -1084,13 +1080,15 @@ ifdef CONFIG_STACK_VALIDATION
   endif
 endif
 
+ifdef CONFIG_BPF
 ifdef CONFIG_DEBUG_INFO_BTF
   ifeq ($(has_libelf),1)
     resolve_btfids_target := tools/bpf/resolve_btfids FORCE
   else
     ERROR_RESOLVE_BTFIDS := 1
   endif
-endif
+endif # CONFIG_DEBUG_INFO_BTF
+endif # CONFIG_BPF
 
 PHONY += prepare0
 
diff --git a/arch/arc/boot/dts/hsdk.dts b/arch/arc/boot/dts/hsdk.dts
index 9acbeba832c0..dcaa44e408ac 100644
--- a/arch/arc/boot/dts/hsdk.dts
+++ b/arch/arc/boot/dts/hsdk.dts
@@ -88,6 +88,8 @@
 
 	arcpct: pct {
 		compatible = "snps,archs-pct";
+		interrupt-parent = <&cpu_intc>;
+		interrupts = <20>;
 	};
 
 	/* TIMER0 with interrupt for clockevent */
@@ -208,7 +210,7 @@
 			reg = <0x8000 0x2000>;
 			interrupts = <10>;
 			interrupt-names = "macirq";
-			phy-mode = "rgmii";
+			phy-mode = "rgmii-id";
 			snps,pbl = <32>;
 			snps,multicast-filter-bins = <256>;
 			clocks = <&gmacclk>;
@@ -226,7 +228,7 @@
 				#address-cells = <1>;
 				#size-cells = <0>;
 				compatible = "snps,dwmac-mdio";
-				phy0: ethernet-phy@0 {
+				phy0: ethernet-phy@0 { /* Micrel KSZ9031 */
 					reg = <0>;
 				};
 			};
diff --git a/arch/arc/include/asm/pgalloc.h b/arch/arc/include/asm/pgalloc.h
index b747f2ec2928..6147db925248 100644
--- a/arch/arc/include/asm/pgalloc.h
+++ b/arch/arc/include/asm/pgalloc.h
@@ -18,10 +18,10 @@
  * vineetg: April 2010
  *  -Switched pgtable_t from being struct page * to unsigned long
  *      =Needed so that Page Table allocator (pte_alloc_one) is not forced to
- *       to deal with struct page. Thay way in future we can make it allocate
+ *       deal with struct page. That way in future we can make it allocate
  *       multiple PG Tbls in one Page Frame
  *      =sweet side effect is avoiding calls to ugly page_address( ) from the
- *       pg-tlb allocator sub-sys (pte_alloc_one, ptr_free, pmd_populate
+ *       pg-tlb allocator sub-sys (pte_alloc_one, ptr_free, pmd_populate)
  *
  *  Amit Bhor, Sameer Dhavale: Codito Technologies 2004
  */
diff --git a/arch/arc/kernel/perf_event.c b/arch/arc/kernel/perf_event.c
index 661fd842ea97..79849f37e782 100644
--- a/arch/arc/kernel/perf_event.c
+++ b/arch/arc/kernel/perf_event.c
@@ -562,7 +562,7 @@ static int arc_pmu_device_probe(struct platform_device *pdev)
 {
 	struct arc_reg_pct_build pct_bcr;
 	struct arc_reg_cc_build cc_bcr;
-	int i, has_interrupts;
+	int i, has_interrupts, irq;
 	int counter_size;	/* in bits */
 
 	union cc_name {
@@ -637,13 +637,7 @@ static int arc_pmu_device_probe(struct platform_device *pdev)
 		.attr_groups	= arc_pmu->attr_groups,
 	};
 
-	if (has_interrupts) {
-		int irq = platform_get_irq(pdev, 0);
-
-		if (irq < 0) {
-			pr_err("Cannot get IRQ number for the platform\n");
-			return -ENODEV;
-		}
+	if (has_interrupts && (irq = platform_get_irq(pdev, 0) >= 0)) {
 
 		arc_pmu->irq = irq;
 
@@ -652,9 +646,9 @@ static int arc_pmu_device_probe(struct platform_device *pdev)
 				   this_cpu_ptr(&arc_pmu_cpu));
 
 		on_each_cpu(arc_cpu_pmu_irq_init, &irq, 1);
-
-	} else
+	} else {
 		arc_pmu->pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
+	}
 
 	/*
 	 * perf parser doesn't really like '-' symbol in events name, so let's
diff --git a/arch/arc/kernel/troubleshoot.c b/arch/arc/kernel/troubleshoot.c
index 28e8bf04b253..a331bb5d8319 100644
--- a/arch/arc/kernel/troubleshoot.c
+++ b/arch/arc/kernel/troubleshoot.c
@@ -18,44 +18,37 @@
 
 #define ARC_PATH_MAX	256
 
-/*
- * Common routine to print scratch regs (r0-r12) or callee regs (r13-r25)
- *   -Prints 3 regs per line and a CR.
- *   -To continue, callee regs right after scratch, special handling of CR
- */
-static noinline void print_reg_file(long *reg_rev, int start_num)
+static noinline void print_regs_scratch(struct pt_regs *regs)
 {
-	unsigned int i;
-	char buf[512];
-	int n = 0, len = sizeof(buf);
-
-	for (i = start_num; i < start_num + 13; i++) {
-		n += scnprintf(buf + n, len - n, "r%02u: 0x%08lx\t",
-			       i, (unsigned long)*reg_rev);
-
-		if (((i + 1) % 3) == 0)
-			n += scnprintf(buf + n, len - n, "\n");
-
-		/* because pt_regs has regs reversed: r12..r0, r25..r13 */
-		if (is_isa_arcv2() && start_num == 0)
-			reg_rev++;
-		else
-			reg_rev--;
-	}
-
-	if (start_num != 0)
-		n += scnprintf(buf + n, len - n, "\n\n");
+	pr_cont("BTA: 0x%08lx\n SP: 0x%08lx  FP: 0x%08lx BLK: %pS\n",
+		regs->bta, regs->sp, regs->fp, (void *)regs->blink);
+	pr_cont("LPS: 0x%08lx\tLPE: 0x%08lx\tLPC: 0x%08lx\n",
+		regs->lp_start, regs->lp_end, regs->lp_count);
 
-	/* To continue printing callee regs on same line as scratch regs */
-	if (start_num == 0)
-		pr_info("%s", buf);
-	else
-		pr_cont("%s\n", buf);
+	pr_info("r00: 0x%08lx\tr01: 0x%08lx\tr02: 0x%08lx\n"	\
+		"r03: 0x%08lx\tr04: 0x%08lx\tr05: 0x%08lx\n"	\
+		"r06: 0x%08lx\tr07: 0x%08lx\tr08: 0x%08lx\n"	\
+		"r09: 0x%08lx\tr10: 0x%08lx\tr11: 0x%08lx\n"	\
+		"r12: 0x%08lx\t",
+		regs->r0, regs->r1, regs->r2,
+		regs->r3, regs->r4, regs->r5,
+		regs->r6, regs->r7, regs->r8,
+		regs->r9, regs->r10, regs->r11,
+		regs->r12);
 }
 
-static void show_callee_regs(struct callee_regs *cregs)
+static void print_regs_callee(struct callee_regs *regs)
 {
-	print_reg_file(&(cregs->r13), 13);
+	pr_cont("r13: 0x%08lx\tr14: 0x%08lx\n"			\
+		"r15: 0x%08lx\tr16: 0x%08lx\tr17: 0x%08lx\n"	\
+		"r18: 0x%08lx\tr19: 0x%08lx\tr20: 0x%08lx\n"	\
+		"r21: 0x%08lx\tr22: 0x%08lx\tr23: 0x%08lx\n"	\
+		"r24: 0x%08lx\tr25: 0x%08lx\n",
+		regs->r13, regs->r14,
+		regs->r15, regs->r16, regs->r17,
+		regs->r18, regs->r19, regs->r20,
+		regs->r21, regs->r22, regs->r23,
+		regs->r24, regs->r25);
 }
 
 static void print_task_path_n_nm(struct task_struct *tsk)
@@ -175,7 +168,7 @@ static void show_ecr_verbose(struct pt_regs *regs)
 void show_regs(struct pt_regs *regs)
 {
 	struct task_struct *tsk = current;
-	struct callee_regs *cregs;
+	struct callee_regs *cregs = (struct callee_regs *)tsk->thread.callee_reg;
 
 	/*
 	 * generic code calls us with preemption disabled, but some calls
@@ -204,25 +197,15 @@ void show_regs(struct pt_regs *regs)
 			STS_BIT(regs, A2), STS_BIT(regs, A1),
 			STS_BIT(regs, E2), STS_BIT(regs, E1));
 #else
-	pr_cont(" [%2s%2s%2s%2s]",
+	pr_cont(" [%2s%2s%2s%2s]   ",
 			STS_BIT(regs, IE),
 			(regs->status32 & STATUS_U_MASK) ? "U " : "K ",
 			STS_BIT(regs, DE), STS_BIT(regs, AE));
 #endif
-	pr_cont("  BTA: 0x%08lx\n  SP: 0x%08lx  FP: 0x%08lx BLK: %pS\n",
-		regs->bta, regs->sp, regs->fp, (void *)regs->blink);
-	pr_info("LPS: 0x%08lx\tLPE: 0x%08lx\tLPC: 0x%08lx\n",
-		regs->lp_start, regs->lp_end, regs->lp_count);
-
-	/* print regs->r0 thru regs->r12
-	 * Sequential printing was generating horrible code
-	 */
-	print_reg_file(&(regs->r0), 0);
 
-	/* If Callee regs were saved, display them too */
-	cregs = (struct callee_regs *)current->thread.callee_reg;
+	print_regs_scratch(regs);
 	if (cregs)
-		show_callee_regs(cregs);
+		print_regs_callee(cregs);
 
 	preempt_disable();
 }
diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c
index f886ac69d8ad..3a35b82a718e 100644
--- a/arch/arc/mm/init.c
+++ b/arch/arc/mm/init.c
@@ -26,8 +26,8 @@ static unsigned long low_mem_sz;
 
 #ifdef CONFIG_HIGHMEM
 static unsigned long min_high_pfn, max_high_pfn;
-static u64 high_mem_start;
-static u64 high_mem_sz;
+static phys_addr_t high_mem_start;
+static phys_addr_t high_mem_sz;
 #endif
 
 #ifdef CONFIG_DISCONTIGMEM
@@ -69,6 +69,7 @@ void __init early_init_dt_add_memory_arch(u64 base, u64 size)
 		high_mem_sz = size;
 		in_use = 1;
 		memblock_add_node(base, size, 1);
+		memblock_reserve(base, size);
 #endif
 	}
 
@@ -157,7 +158,7 @@ void __init setup_arch_memory(void)
 	min_high_pfn = PFN_DOWN(high_mem_start);
 	max_high_pfn = PFN_DOWN(high_mem_start + high_mem_sz);
 
-	max_zone_pfn[ZONE_HIGHMEM] = max_high_pfn;
+	max_zone_pfn[ZONE_HIGHMEM] = min_low_pfn;
 
 	high_memory = (void *)(min_high_pfn << PAGE_SHIFT);
 	kmap_init();
@@ -166,22 +167,26 @@ void __init setup_arch_memory(void)
 	free_area_init(max_zone_pfn);
 }
 
-/*
- * mem_init - initializes memory
- *
- * Frees up bootmem
- * Calculates and displays memory available/used
- */
-void __init mem_init(void)
+static void __init highmem_init(void)
 {
 #ifdef CONFIG_HIGHMEM
 	unsigned long tmp;
 
-	reset_all_zones_managed_pages();
+	memblock_free(high_mem_start, high_mem_sz);
 	for (tmp = min_high_pfn; tmp < max_high_pfn; tmp++)
 		free_highmem_page(pfn_to_page(tmp));
 #endif
+}
 
+/*
+ * mem_init - initializes memory
+ *
+ * Frees up bootmem
+ * Calculates and displays memory available/used
+ */
+void __init mem_init(void)
+{
 	memblock_free_all();
+	highmem_init();
 	mem_init_print_info(NULL);
 }
diff --git a/arch/arc/plat-eznps/include/plat/ctop.h b/arch/arc/plat-eznps/include/plat/ctop.h
index a4a61531c7fb..77712c5ffe84 100644
--- a/arch/arc/plat-eznps/include/plat/ctop.h
+++ b/arch/arc/plat-eznps/include/plat/ctop.h
@@ -33,7 +33,6 @@
 #define CTOP_AUX_DPC				(CTOP_AUX_BASE + 0x02C)
 #define CTOP_AUX_LPC				(CTOP_AUX_BASE + 0x030)
 #define CTOP_AUX_EFLAGS				(CTOP_AUX_BASE + 0x080)
-#define CTOP_AUX_IACK				(CTOP_AUX_BASE + 0x088)
 #define CTOP_AUX_GPA1				(CTOP_AUX_BASE + 0x08C)
 #define CTOP_AUX_UDMC				(CTOP_AUX_BASE + 0x300)
 
diff --git a/arch/arm/boot/dts/at91-sama5d2_icp.dts b/arch/arm/boot/dts/at91-sama5d2_icp.dts
index 8d19925fc09e..6783cf16ff81 100644
--- a/arch/arm/boot/dts/at91-sama5d2_icp.dts
+++ b/arch/arm/boot/dts/at91-sama5d2_icp.dts
@@ -116,7 +116,6 @@
 		switch0: ksz8563@0 {
 			compatible = "microchip,ksz8563";
 			reg = <0>;
-			phy-mode = "mii";
 			reset-gpios = <&pioA PIN_PD4 GPIO_ACTIVE_LOW>;
 
 			spi-max-frequency = <500000>;
@@ -140,6 +139,7 @@
 					reg = <2>;
 					label = "cpu";
 					ethernet = <&macb0>;
+					phy-mode = "mii";
 					fixed-link {
 						speed = <100>;
 						full-duplex;
diff --git a/arch/arm/boot/dts/bcm-hr2.dtsi b/arch/arm/boot/dts/bcm-hr2.dtsi
index cbebed5f050e..e8df458aad39 100644
--- a/arch/arm/boot/dts/bcm-hr2.dtsi
+++ b/arch/arm/boot/dts/bcm-hr2.dtsi
@@ -217,7 +217,7 @@
 		};
 
 		qspi: spi@27200 {
-			compatible = "brcm,spi-bcm-qspi", "brcm,spi-nsp-qspi";
+			compatible = "brcm,spi-nsp-qspi", "brcm,spi-bcm-qspi";
 			reg = <0x027200 0x184>,
 			      <0x027000 0x124>,
 			      <0x11c408 0x004>,
diff --git a/arch/arm/boot/dts/bcm-nsp.dtsi b/arch/arm/boot/dts/bcm-nsp.dtsi
index 0346ea621f0f..c846fa3c244d 100644
--- a/arch/arm/boot/dts/bcm-nsp.dtsi
+++ b/arch/arm/boot/dts/bcm-nsp.dtsi
@@ -284,7 +284,7 @@
 		};
 
 		qspi: spi@27200 {
-			compatible = "brcm,spi-bcm-qspi", "brcm,spi-nsp-qspi";
+			compatible = "brcm,spi-nsp-qspi", "brcm,spi-bcm-qspi";
 			reg = <0x027200 0x184>,
 			      <0x027000 0x124>,
 			      <0x11c408 0x004>,
diff --git a/arch/arm/boot/dts/bcm5301x.dtsi b/arch/arm/boot/dts/bcm5301x.dtsi
index 2d9b4dd05830..0016720ce530 100644
--- a/arch/arm/boot/dts/bcm5301x.dtsi
+++ b/arch/arm/boot/dts/bcm5301x.dtsi
@@ -488,7 +488,7 @@
 	};
 
 	spi@18029200 {
-		compatible = "brcm,spi-bcm-qspi", "brcm,spi-nsp-qspi";
+		compatible = "brcm,spi-nsp-qspi", "brcm,spi-bcm-qspi";
 		reg = <0x18029200 0x184>,
 		      <0x18029000 0x124>,
 		      <0x1811b408 0x004>,
diff --git a/arch/arm/boot/dts/imx6q-logicpd.dts b/arch/arm/boot/dts/imx6q-logicpd.dts
index 7a3d1d3e54a9..8f94364ba484 100644
--- a/arch/arm/boot/dts/imx6q-logicpd.dts
+++ b/arch/arm/boot/dts/imx6q-logicpd.dts
@@ -13,7 +13,7 @@
 
 	backlight: backlight-lvds {
 		compatible = "pwm-backlight";
-		pwms = <&pwm3 0 20000>;
+		pwms = <&pwm3 0 20000 0>;
 		brightness-levels = <0 4 8 16 32 64 128 255>;
 		default-brightness-level = <6>;
 		power-supply = <&reg_lcd>;
diff --git a/arch/arm/boot/dts/imx6q-prtwd2.dts b/arch/arm/boot/dts/imx6q-prtwd2.dts
index dffafbcaa7af..349959d38020 100644
--- a/arch/arm/boot/dts/imx6q-prtwd2.dts
+++ b/arch/arm/boot/dts/imx6q-prtwd2.dts
@@ -30,7 +30,7 @@
 	};
 
 	/* PRTWD2 rev 1 bitbang I2C for Ethernet Switch */
-	i2c@4 {
+	i2c {
 		compatible = "i2c-gpio";
 		pinctrl-names = "default";
 		pinctrl-0 = <&pinctrl_i2c4>;
diff --git a/arch/arm/boot/dts/imx6qdl-gw51xx.dtsi b/arch/arm/boot/dts/imx6qdl-gw51xx.dtsi
index 7705285d9e3c..4d01c3300b97 100644
--- a/arch/arm/boot/dts/imx6qdl-gw51xx.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-gw51xx.dtsi
@@ -22,8 +22,6 @@
 
 	gpio-keys {
 		compatible = "gpio-keys";
-		#address-cells = <1>;
-		#size-cells = <0>;
 
 		user-pb {
 			label = "user_pb";
diff --git a/arch/arm/boot/dts/imx6sx-pinfunc.h b/arch/arm/boot/dts/imx6sx-pinfunc.h
index 0b02c7e60c17..f4dc46207954 100644
--- a/arch/arm/boot/dts/imx6sx-pinfunc.h
+++ b/arch/arm/boot/dts/imx6sx-pinfunc.h
@@ -1026,7 +1026,7 @@
 #define MX6SX_PAD_QSPI1B_DQS__SIM_M_HADDR_15                      0x01B0 0x04F8 0x0000 0x7 0x0
 #define MX6SX_PAD_QSPI1B_SCLK__QSPI1_B_SCLK                       0x01B4 0x04FC 0x0000 0x0 0x0
 #define MX6SX_PAD_QSPI1B_SCLK__UART3_DCE_RX                       0x01B4 0x04FC 0x0840 0x1 0x4
-#define MX6SX_PAD_QSPI1B_SCLK__UART3_DTE_TX                       0x01B4 0x04FC 0x0000 0x0 0x0
+#define MX6SX_PAD_QSPI1B_SCLK__UART3_DTE_TX                       0x01B4 0x04FC 0x0000 0x1 0x0
 #define MX6SX_PAD_QSPI1B_SCLK__ECSPI3_SCLK                        0x01B4 0x04FC 0x0730 0x2 0x1
 #define MX6SX_PAD_QSPI1B_SCLK__ESAI_RX_HF_CLK                     0x01B4 0x04FC 0x0780 0x3 0x2
 #define MX6SX_PAD_QSPI1B_SCLK__CSI1_DATA_16                       0x01B4 0x04FC 0x06DC 0x4 0x1
diff --git a/arch/arm/boot/dts/imx7d-zii-rmu2.dts b/arch/arm/boot/dts/imx7d-zii-rmu2.dts
index e5e20b07f184..7cb6153fc650 100644
--- a/arch/arm/boot/dts/imx7d-zii-rmu2.dts
+++ b/arch/arm/boot/dts/imx7d-zii-rmu2.dts
@@ -58,7 +58,7 @@
 			  <&clks IMX7D_ENET1_TIME_ROOT_CLK>;
 	assigned-clock-parents = <&clks IMX7D_PLL_ENET_MAIN_100M_CLK>;
 	assigned-clock-rates = <0>, <100000000>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 	phy-handle = <&fec1_phy>;
 	status = "okay";
 
diff --git a/arch/arm/boot/dts/imx7ulp.dtsi b/arch/arm/boot/dts/imx7ulp.dtsi
index 367439639da9..b7ea37ad4e55 100644
--- a/arch/arm/boot/dts/imx7ulp.dtsi
+++ b/arch/arm/boot/dts/imx7ulp.dtsi
@@ -394,7 +394,7 @@
 			clocks = <&pcc2 IMX7ULP_CLK_RGPIO2P1>,
 				 <&pcc3 IMX7ULP_CLK_PCTLC>;
 			clock-names = "gpio", "port";
-			gpio-ranges = <&iomuxc1 0 0 32>;
+			gpio-ranges = <&iomuxc1 0 0 20>;
 		};
 
 		gpio_ptd: gpio@40af0000 {
@@ -408,7 +408,7 @@
 			clocks = <&pcc2 IMX7ULP_CLK_RGPIO2P1>,
 				 <&pcc3 IMX7ULP_CLK_PCTLD>;
 			clock-names = "gpio", "port";
-			gpio-ranges = <&iomuxc1 0 32 32>;
+			gpio-ranges = <&iomuxc1 0 32 12>;
 		};
 
 		gpio_pte: gpio@40b00000 {
@@ -422,7 +422,7 @@
 			clocks = <&pcc2 IMX7ULP_CLK_RGPIO2P1>,
 				 <&pcc3 IMX7ULP_CLK_PCTLE>;
 			clock-names = "gpio", "port";
-			gpio-ranges = <&iomuxc1 0 64 32>;
+			gpio-ranges = <&iomuxc1 0 64 16>;
 		};
 
 		gpio_ptf: gpio@40b10000 {
@@ -436,7 +436,7 @@
 			clocks = <&pcc2 IMX7ULP_CLK_RGPIO2P1>,
 				 <&pcc3 IMX7ULP_CLK_PCTLF>;
 			clock-names = "gpio", "port";
-			gpio-ranges = <&iomuxc1 0 96 32>;
+			gpio-ranges = <&iomuxc1 0 96 20>;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/logicpd-som-lv-baseboard.dtsi b/arch/arm/boot/dts/logicpd-som-lv-baseboard.dtsi
index 100396f6c2fe..395e05f10d36 100644
--- a/arch/arm/boot/dts/logicpd-som-lv-baseboard.dtsi
+++ b/arch/arm/boot/dts/logicpd-som-lv-baseboard.dtsi
@@ -51,6 +51,8 @@
 
 &mcbsp2 {
 	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&mcbsp2_pins>;
 };
 
 &charger {
@@ -102,35 +104,18 @@
 		regulator-max-microvolt = <3300000>;
 	};
 
-	lcd0: display@0 {
-		compatible = "panel-dpi";
-		label = "28";
-		status = "okay";
-		/* default-on; */
+	lcd0: display {
+		/* This isn't the exact LCD, but the timings meet spec */
+		compatible = "logicpd,type28";
 		pinctrl-names = "default";
 		pinctrl-0 = <&lcd_enable_pin>;
-		enable-gpios = <&gpio5 27 GPIO_ACTIVE_HIGH>;	/* gpio155, lcd INI */
+		backlight = <&bl>;
+		enable-gpios = <&gpio5 27 GPIO_ACTIVE_HIGH>;
 		port {
 			lcd_in: endpoint {
 				remote-endpoint = <&dpi_out>;
 			};
 		};
-
-		panel-timing {
-			clock-frequency = <9000000>;
-			hactive = <480>;
-			vactive = <272>;
-			hfront-porch = <3>;
-			hback-porch = <2>;
-			hsync-len = <42>;
-			vback-porch = <3>;
-			vfront-porch = <2>;
-			vsync-len = <11>;
-			hsync-active = <1>;
-			vsync-active = <1>;
-			de-active = <1>;
-			pixelclk-active = <0>;
-		};
 	};
 
 	bl: backlight {
diff --git a/arch/arm/boot/dts/logicpd-torpedo-baseboard.dtsi b/arch/arm/boot/dts/logicpd-torpedo-baseboard.dtsi
index 381f0e82bb70..b0f6613e6d54 100644
--- a/arch/arm/boot/dts/logicpd-torpedo-baseboard.dtsi
+++ b/arch/arm/boot/dts/logicpd-torpedo-baseboard.dtsi
@@ -81,6 +81,8 @@
 };
 
 &mcbsp2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&mcbsp2_pins>;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/ls1021a.dtsi b/arch/arm/boot/dts/ls1021a.dtsi
index 069af9a19bb6..827373ef1a54 100644
--- a/arch/arm/boot/dts/ls1021a.dtsi
+++ b/arch/arm/boot/dts/ls1021a.dtsi
@@ -182,7 +182,7 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 			reg = <0x0 0x1550000 0x0 0x10000>,
-			      <0x0 0x40000000 0x0 0x40000000>;
+			      <0x0 0x40000000 0x0 0x20000000>;
 			reg-names = "QuadSPI", "QuadSPI-memory";
 			interrupts = <GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>;
 			clock-names = "qspi_en", "qspi";
diff --git a/arch/arm/boot/dts/omap5.dtsi b/arch/arm/boot/dts/omap5.dtsi
index 5da9cff7a53c..a82c96258a93 100644
--- a/arch/arm/boot/dts/omap5.dtsi
+++ b/arch/arm/boot/dts/omap5.dtsi
@@ -488,11 +488,11 @@
 					};
 				};
 
-				target-module@5000 {
+				target-module@4000 {
 					compatible = "ti,sysc-omap2", "ti,sysc";
-					reg = <0x5000 0x4>,
-					      <0x5010 0x4>,
-					      <0x5014 0x4>;
+					reg = <0x4000 0x4>,
+					      <0x4010 0x4>,
+					      <0x4014 0x4>;
 					reg-names = "rev", "sysc", "syss";
 					ti,sysc-sidle = <SYSC_IDLE_FORCE>,
 							<SYSC_IDLE_NO>,
@@ -504,7 +504,7 @@
 					ti,syss-mask = <1>;
 					#address-cells = <1>;
 					#size-cells = <1>;
-					ranges = <0 0x5000 0x1000>;
+					ranges = <0 0x4000 0x1000>;
 
 					dsi1: encoder@0 {
 						compatible = "ti,omap5-dsi";
@@ -514,8 +514,9 @@
 						reg-names = "proto", "phy", "pll";
 						interrupts = <GIC_SPI 53 IRQ_TYPE_LEVEL_HIGH>;
 						status = "disabled";
-						clocks = <&dss_clkctrl OMAP5_DSS_CORE_CLKCTRL 8>;
-						clock-names = "fck";
+						clocks = <&dss_clkctrl OMAP5_DSS_CORE_CLKCTRL 8>,
+							 <&dss_clkctrl OMAP5_DSS_CORE_CLKCTRL 10>;
+						clock-names = "fck", "sys_clk";
 					};
 				};
 
@@ -545,8 +546,9 @@
 						reg-names = "proto", "phy", "pll";
 						interrupts = <GIC_SPI 55 IRQ_TYPE_LEVEL_HIGH>;
 						status = "disabled";
-						clocks = <&dss_clkctrl OMAP5_DSS_CORE_CLKCTRL 8>;
-						clock-names = "fck";
+						clocks = <&dss_clkctrl OMAP5_DSS_CORE_CLKCTRL 8>,
+							 <&dss_clkctrl OMAP5_DSS_CORE_CLKCTRL 10>;
+						clock-names = "fck", "sys_clk";
 					};
 				};
 
diff --git a/arch/arm/boot/dts/socfpga_arria10.dtsi b/arch/arm/boot/dts/socfpga_arria10.dtsi
index fc4abef143a0..0013ec3463c4 100644
--- a/arch/arm/boot/dts/socfpga_arria10.dtsi
+++ b/arch/arm/boot/dts/socfpga_arria10.dtsi
@@ -821,7 +821,7 @@
 		timer3: timer3@ffd00100 {
 			compatible = "snps,dw-apb-timer";
 			interrupts = <0 118 IRQ_TYPE_LEVEL_HIGH>;
-			reg = <0xffd01000 0x100>;
+			reg = <0xffd00100 0x100>;
 			clocks = <&l4_sys_free_clk>;
 			clock-names = "timer";
 			resets = <&rst L4SYSTIMER1_RESET>;
diff --git a/arch/arm/boot/dts/vfxxx.dtsi b/arch/arm/boot/dts/vfxxx.dtsi
index 0fe03aa0367f..2259d11af721 100644
--- a/arch/arm/boot/dts/vfxxx.dtsi
+++ b/arch/arm/boot/dts/vfxxx.dtsi
@@ -495,7 +495,7 @@
 			};
 
 			ocotp: ocotp@400a5000 {
-				compatible = "fsl,vf610-ocotp";
+				compatible = "fsl,vf610-ocotp", "syscon";
 				reg = <0x400a5000 0x1000>;
 				clocks = <&clks VF610_CLK_OCOTP>;
 			};
diff --git a/arch/arm/configs/integrator_defconfig b/arch/arm/configs/integrator_defconfig
index a9755c501bec..b06e537d5149 100644
--- a/arch/arm/configs/integrator_defconfig
+++ b/arch/arm/configs/integrator_defconfig
@@ -1,13 +1,11 @@
 CONFIG_SYSVIPC=y
 CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
+CONFIG_PREEMPT=y
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_BLK_DEV_INITRD=y
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-CONFIG_PARTITION_ADVANCED=y
 CONFIG_ARCH_MULTI_V4T=y
 CONFIG_ARCH_MULTI_V5=y
 # CONFIG_ARCH_MULTI_V7 is not set
@@ -15,19 +13,17 @@ CONFIG_ARCH_INTEGRATOR=y
 CONFIG_ARCH_INTEGRATOR_AP=y
 CONFIG_INTEGRATOR_IMPD1=y
 CONFIG_ARCH_INTEGRATOR_CP=y
-CONFIG_PCI=y
-CONFIG_PREEMPT=y
 CONFIG_AEABI=y
 # CONFIG_ATAGS is not set
-CONFIG_ZBOOT_ROM_TEXT=0x0
-CONFIG_ZBOOT_ROM_BSS=0x0
 CONFIG_CMDLINE="console=ttyAM0,38400n8 root=/dev/nfs ip=bootp"
 CONFIG_CPU_FREQ=y
 CONFIG_CPU_FREQ_GOV_POWERSAVE=y
 CONFIG_CPU_FREQ_GOV_USERSPACE=y
 CONFIG_CPU_FREQ_GOV_ONDEMAND=y
 CONFIG_CPUFREQ_DT=y
-CONFIG_CMA=y
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_PARTITION_ADVANCED=y
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
@@ -37,6 +33,7 @@ CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
 CONFIG_IP_PNP_BOOTP=y
 # CONFIG_IPV6 is not set
+CONFIG_PCI=y
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
 CONFIG_MTD_AFS_PARTS=y
@@ -52,9 +49,12 @@ CONFIG_BLK_DEV_RAM_SIZE=8192
 CONFIG_NETDEVICES=y
 CONFIG_E100=y
 CONFIG_SMC91X=y
+CONFIG_INPUT_EVDEV=y
 # CONFIG_KEYBOARD_ATKBD is not set
+CONFIG_KEYBOARD_GPIO=y
 # CONFIG_SERIO_SERPORT is not set
 CONFIG_DRM=y
+CONFIG_DRM_DISPLAY_CONNECTOR=y
 CONFIG_DRM_SIMPLE_BRIDGE=y
 CONFIG_DRM_PL111=y
 CONFIG_FB_MODE_HELPERS=y
diff --git a/arch/arm/mach-omap2/omap-iommu.c b/arch/arm/mach-omap2/omap-iommu.c
index 54aff33e55e6..bfa5e1b8dba7 100644
--- a/arch/arm/mach-omap2/omap-iommu.c
+++ b/arch/arm/mach-omap2/omap-iommu.c
@@ -74,7 +74,7 @@ static struct powerdomain *_get_pwrdm(struct device *dev)
 		return pwrdm;
 
 	clk = of_clk_get(dev->of_node->parent, 0);
-	if (!clk) {
+	if (IS_ERR(clk)) {
 		dev_err(dev, "no fck found\n");
 		return NULL;
 	}
diff --git a/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi b/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi
index 15f7b0ed3836..39802066232e 100644
--- a/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi
+++ b/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi
@@ -745,7 +745,7 @@
 		};
 
 		qspi: spi@66470200 {
-			compatible = "brcm,spi-bcm-qspi", "brcm,spi-ns2-qspi";
+			compatible = "brcm,spi-ns2-qspi", "brcm,spi-bcm-qspi";
 			reg = <0x66470200 0x184>,
 				<0x66470000 0x124>,
 				<0x67017408 0x004>,
diff --git a/arch/arm64/boot/dts/freescale/Makefile b/arch/arm64/boot/dts/freescale/Makefile
index a39f0a1723e0..903c0eb61290 100644
--- a/arch/arm64/boot/dts/freescale/Makefile
+++ b/arch/arm64/boot/dts/freescale/Makefile
@@ -28,6 +28,7 @@ dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-lx2160a-honeycomb.dtb
 dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-lx2160a-qds.dtb
 dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-lx2160a-rdb.dtb
 
+dtb-$(CONFIG_ARCH_MXC) += imx8mm-beacon-kit.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mm-evk.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mn-evk.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mn-ddr4-evk.dtb
diff --git a/arch/arm64/boot/dts/freescale/imx8mp.dtsi b/arch/arm64/boot/dts/freescale/imx8mp.dtsi
index 9de2aa1c573c..a5154f13a18e 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp.dtsi
@@ -702,7 +702,7 @@
 				reg = <0x30bd0000 0x10000>;
 				interrupts = <GIC_SPI 2 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clk IMX8MP_CLK_SDMA1_ROOT>,
-					 <&clk IMX8MP_CLK_SDMA1_ROOT>;
+					 <&clk IMX8MP_CLK_AHB>;
 				clock-names = "ipg", "ahb";
 				#dma-cells = <3>;
 				fsl,sdma-ram-script-name = "imx/sdma/sdma-imx7d.bin";
diff --git a/arch/arm64/boot/dts/freescale/imx8mq.dtsi b/arch/arm64/boot/dts/freescale/imx8mq.dtsi
index f70435cf9ad5..561fa792fe5a 100644
--- a/arch/arm64/boot/dts/freescale/imx8mq.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mq.dtsi
@@ -423,7 +423,7 @@
 			tmu: tmu@30260000 {
 				compatible = "fsl,imx8mq-tmu";
 				reg = <0x30260000 0x10000>;
-				interrupt = <GIC_SPI 49 IRQ_TYPE_LEVEL_HIGH>;
+				interrupts = <GIC_SPI 49 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clk IMX8MQ_CLK_TMU_ROOT>;
 				little-endian;
 				fsl,tmu-range = <0xb0000 0xa0026 0x80048 0x70061>;
diff --git a/arch/arm64/boot/dts/xilinx/zynqmp.dtsi b/arch/arm64/boot/dts/xilinx/zynqmp.dtsi
index 9174ddc76bdc..3ec99f13c259 100644
--- a/arch/arm64/boot/dts/xilinx/zynqmp.dtsi
+++ b/arch/arm64/boot/dts/xilinx/zynqmp.dtsi
@@ -13,6 +13,7 @@
  */
 
 #include <dt-bindings/power/xlnx-zynqmp-power.h>
+#include <dt-bindings/reset/xlnx-zynqmp-resets.h>
 
 / {
 	compatible = "xlnx,zynqmp";
@@ -558,6 +559,15 @@
 			};
 		};
 
+		psgtr: phy@fd400000 {
+			compatible = "xlnx,zynqmp-psgtr-v1.1";
+			status = "disabled";
+			reg = <0x0 0xfd400000 0x0 0x40000>,
+			      <0x0 0xfd3d0000 0x0 0x1000>;
+			reg-names = "serdes", "siou";
+			#phy-cells = <4>;
+		};
+
 		rtc: rtc@ffa60000 {
 			compatible = "xlnx,zynqmp-rtc";
 			status = "disabled";
@@ -601,7 +611,7 @@
 			power-domains = <&zynqmp_firmware PD_SD_1>;
 		};
 
-		smmu: smmu@fd800000 {
+		smmu: iommu@fd800000 {
 			compatible = "arm,mmu-500";
 			reg = <0x0 0xfd800000 0x0 0x20000>;
 			status = "disabled";
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index e0f33826819f..6d04b9577b0b 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -724,6 +724,17 @@ CONFIG_USB_GADGET=y
 CONFIG_USB_RENESAS_USBHS_UDC=m
 CONFIG_USB_RENESAS_USB3=m
 CONFIG_USB_TEGRA_XUDC=m
+CONFIG_USB_CONFIGFS=m
+CONFIG_USB_CONFIGFS_SERIAL=y
+CONFIG_USB_CONFIGFS_ACM=y
+CONFIG_USB_CONFIGFS_OBEX=y
+CONFIG_USB_CONFIGFS_NCM=y
+CONFIG_USB_CONFIGFS_ECM=y
+CONFIG_USB_CONFIGFS_ECM_SUBSET=y
+CONFIG_USB_CONFIGFS_RNDIS=y
+CONFIG_USB_CONFIGFS_EEM=y
+CONFIG_USB_CONFIGFS_MASS_STORAGE=y
+CONFIG_USB_CONFIGFS_F_FS=y
 CONFIG_TYPEC=m
 CONFIG_TYPEC_TCPM=m
 CONFIG_TYPEC_FUSB302=m
@@ -914,6 +925,7 @@ CONFIG_ARCH_TEGRA_194_SOC=y
 CONFIG_ARCH_K3_AM6_SOC=y
 CONFIG_ARCH_K3_J721E_SOC=y
 CONFIG_TI_SCI_PM_DOMAINS=y
+CONFIG_EXTCON_PTN5150=m
 CONFIG_EXTCON_USB_GPIO=y
 CONFIG_EXTCON_USBC_CROS_EC=y
 CONFIG_IIO=y
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 49a55be2b9a2..1cc5f5f72d0b 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -298,15 +298,15 @@ static __always_inline int kvm_vcpu_dabt_get_rd(const struct kvm_vcpu *vcpu)
 	return (kvm_vcpu_get_esr(vcpu) & ESR_ELx_SRT_MASK) >> ESR_ELx_SRT_SHIFT;
 }
 
-static __always_inline bool kvm_vcpu_dabt_iss1tw(const struct kvm_vcpu *vcpu)
+static __always_inline bool kvm_vcpu_abt_iss1tw(const struct kvm_vcpu *vcpu)
 {
 	return !!(kvm_vcpu_get_esr(vcpu) & ESR_ELx_S1PTW);
 }
 
+/* Always check for S1PTW *before* using this. */
 static __always_inline bool kvm_vcpu_dabt_iswrite(const struct kvm_vcpu *vcpu)
 {
-	return !!(kvm_vcpu_get_esr(vcpu) & ESR_ELx_WNR) ||
-		kvm_vcpu_dabt_iss1tw(vcpu); /* AF/DBM update */
+	return kvm_vcpu_get_esr(vcpu) & ESR_ELx_WNR;
 }
 
 static inline bool kvm_vcpu_dabt_is_cm(const struct kvm_vcpu *vcpu)
@@ -335,6 +335,11 @@ static inline bool kvm_vcpu_trap_is_iabt(const struct kvm_vcpu *vcpu)
 	return kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_IABT_LOW;
 }
 
+static inline bool kvm_vcpu_trap_is_exec_fault(const struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_trap_is_iabt(vcpu) && !kvm_vcpu_abt_iss1tw(vcpu);
+}
+
 static __always_inline u8 kvm_vcpu_trap_get_fault(const struct kvm_vcpu *vcpu)
 {
 	return kvm_vcpu_get_esr(vcpu) & ESR_ELx_FSC;
@@ -372,6 +377,9 @@ static __always_inline int kvm_vcpu_sys_get_rt(struct kvm_vcpu *vcpu)
 
 static inline bool kvm_is_write_fault(struct kvm_vcpu *vcpu)
 {
+	if (kvm_vcpu_abt_iss1tw(vcpu))
+		return true;
+
 	if (kvm_vcpu_trap_is_iabt(vcpu))
 		return false;
 
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index e52c927aade5..905c2b87e05a 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -368,7 +368,6 @@ struct kvm_vcpu_arch {
 
 	/* Guest PV state */
 	struct {
-		u64 steal;
 		u64 last_steal;
 		gpa_t base;
 	} steal;
@@ -544,6 +543,7 @@ long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu);
 gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu);
 void kvm_update_stolen_time(struct kvm_vcpu *vcpu);
 
+bool kvm_arm_pvtime_supported(void);
 int kvm_arm_pvtime_set_attr(struct kvm_vcpu *vcpu,
 			    struct kvm_device_attr *attr);
 int kvm_arm_pvtime_get_attr(struct kvm_vcpu *vcpu,
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index c332d49780dc..560ba69e13c1 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -910,8 +910,12 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		.desc = "ARM erratum 1418040",
 		.capability = ARM64_WORKAROUND_1418040,
 		ERRATA_MIDR_RANGE_LIST(erratum_1418040_list),
-		.type = (ARM64_CPUCAP_SCOPE_LOCAL_CPU |
-			 ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU),
+		/*
+		 * We need to allow affected CPUs to come in late, but
+		 * also need the non-affected CPUs to be able to come
+		 * in at any point in time. Wonderful.
+		 */
+		.type = ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE,
 	},
 #endif
 #ifdef CONFIG_ARM64_WORKAROUND_SPECULATIVE_AT
diff --git a/arch/arm64/kernel/paravirt.c b/arch/arm64/kernel/paravirt.c
index 295d66490584..c07d7a034941 100644
--- a/arch/arm64/kernel/paravirt.c
+++ b/arch/arm64/kernel/paravirt.c
@@ -50,16 +50,19 @@ static u64 pv_steal_clock(int cpu)
 	struct pv_time_stolen_time_region *reg;
 
 	reg = per_cpu_ptr(&stolen_time_region, cpu);
-	if (!reg->kaddr) {
-		pr_warn_once("stolen time enabled but not configured for cpu %d\n",
-			     cpu);
+
+	/*
+	 * paravirt_steal_clock() may be called before the CPU
+	 * online notification callback runs. Until the callback
+	 * has run we just return zero.
+	 */
+	if (!reg->kaddr)
 		return 0;
-	}
 
 	return le64_to_cpu(READ_ONCE(reg->kaddr->stolen_time));
 }
 
-static int stolen_time_dying_cpu(unsigned int cpu)
+static int stolen_time_cpu_down_prepare(unsigned int cpu)
 {
 	struct pv_time_stolen_time_region *reg;
 
@@ -73,7 +76,7 @@ static int stolen_time_dying_cpu(unsigned int cpu)
 	return 0;
 }
 
-static int init_stolen_time_cpu(unsigned int cpu)
+static int stolen_time_cpu_online(unsigned int cpu)
 {
 	struct pv_time_stolen_time_region *reg;
 	struct arm_smccc_res res;
@@ -103,19 +106,20 @@ static int init_stolen_time_cpu(unsigned int cpu)
 	return 0;
 }
 
-static int pv_time_init_stolen_time(void)
+static int __init pv_time_init_stolen_time(void)
 {
 	int ret;
 
-	ret = cpuhp_setup_state(CPUHP_AP_ARM_KVMPV_STARTING,
-				"hypervisor/arm/pvtime:starting",
-				init_stolen_time_cpu, stolen_time_dying_cpu);
+	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN,
+				"hypervisor/arm/pvtime:online",
+				stolen_time_cpu_online,
+				stolen_time_cpu_down_prepare);
 	if (ret < 0)
 		return ret;
 	return 0;
 }
 
-static bool has_pv_steal_clock(void)
+static bool __init has_pv_steal_clock(void)
 {
 	struct arm_smccc_res res;
 
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 46dc3d75cf13..b588c3b5c2f0 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -206,6 +206,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		 */
 		r = 1;
 		break;
+	case KVM_CAP_STEAL_TIME:
+		r = kvm_arm_pvtime_supported();
+		break;
 	default:
 		r = kvm_arch_vm_ioctl_check_extension(kvm, ext);
 		break;
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index 5b6b8fa00f0a..0261308bf944 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -449,7 +449,7 @@ static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
 			kvm_vcpu_trap_get_fault_type(vcpu) == FSC_FAULT &&
 			kvm_vcpu_dabt_isvalid(vcpu) &&
 			!kvm_vcpu_abt_issea(vcpu) &&
-			!kvm_vcpu_dabt_iss1tw(vcpu);
+			!kvm_vcpu_abt_iss1tw(vcpu);
 
 		if (valid) {
 			int ret = __vgic_v2_perform_cpuif_access(vcpu);
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index ba00bcc0c884..3d26b47a1343 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1849,7 +1849,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	struct kvm_s2_mmu *mmu = vcpu->arch.hw_mmu;
 
 	write_fault = kvm_is_write_fault(vcpu);
-	exec_fault = kvm_vcpu_trap_is_iabt(vcpu);
+	exec_fault = kvm_vcpu_trap_is_exec_fault(vcpu);
 	VM_BUG_ON(write_fault && exec_fault);
 
 	if (fault_status == FSC_PERM && !write_fault && !exec_fault) {
@@ -1877,6 +1877,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	    !fault_supports_stage2_huge_mapping(memslot, hva, vma_pagesize)) {
 		force_pte = true;
 		vma_pagesize = PAGE_SIZE;
+		vma_shift = PAGE_SHIFT;
 	}
 
 	/*
@@ -1970,7 +1971,12 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		(fault_status == FSC_PERM &&
 		 stage2_is_exec(mmu, fault_ipa, vma_pagesize));
 
-	if (vma_pagesize == PUD_SIZE) {
+	/*
+	 * If PUD_SIZE == PMD_SIZE, there is no real PUD level, and
+	 * all we have is a 2-level page table. Trying to map a PUD in
+	 * this case would be fatally wrong.
+	 */
+	if (PUD_SIZE != PMD_SIZE && vma_pagesize == PUD_SIZE) {
 		pud_t new_pud = kvm_pfn_pud(pfn, mem_type);
 
 		new_pud = kvm_pud_mkhuge(new_pud);
@@ -2125,7 +2131,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 			goto out;
 		}
 
-		if (kvm_vcpu_dabt_iss1tw(vcpu)) {
+		if (kvm_vcpu_abt_iss1tw(vcpu)) {
 			kvm_inject_dabt(vcpu, kvm_vcpu_get_hfar(vcpu));
 			ret = 1;
 			goto out_unlock;
diff --git a/arch/arm64/kvm/pvtime.c b/arch/arm64/kvm/pvtime.c
index f7b52ce1557e..920ac43077ad 100644
--- a/arch/arm64/kvm/pvtime.c
+++ b/arch/arm64/kvm/pvtime.c
@@ -13,25 +13,22 @@
 void kvm_update_stolen_time(struct kvm_vcpu *vcpu)
 {
 	struct kvm *kvm = vcpu->kvm;
-	u64 steal;
-	__le64 steal_le;
-	u64 offset;
-	int idx;
 	u64 base = vcpu->arch.steal.base;
+	u64 last_steal = vcpu->arch.steal.last_steal;
+	u64 offset = offsetof(struct pvclock_vcpu_stolen_time, stolen_time);
+	u64 steal = 0;
+	int idx;
 
 	if (base == GPA_INVALID)
 		return;
 
-	/* Let's do the local bookkeeping */
-	steal = vcpu->arch.steal.steal;
-	steal += current->sched_info.run_delay - vcpu->arch.steal.last_steal;
-	vcpu->arch.steal.last_steal = current->sched_info.run_delay;
-	vcpu->arch.steal.steal = steal;
-
-	steal_le = cpu_to_le64(steal);
 	idx = srcu_read_lock(&kvm->srcu);
-	offset = offsetof(struct pvclock_vcpu_stolen_time, stolen_time);
-	kvm_put_guest(kvm, base + offset, steal_le, u64);
+	if (!kvm_get_guest(kvm, base + offset, steal)) {
+		steal = le64_to_cpu(steal);
+		vcpu->arch.steal.last_steal = READ_ONCE(current->sched_info.run_delay);
+		steal += vcpu->arch.steal.last_steal - last_steal;
+		kvm_put_guest(kvm, base + offset, cpu_to_le64(steal));
+	}
 	srcu_read_unlock(&kvm->srcu, idx);
 }
 
@@ -43,7 +40,8 @@ long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu)
 	switch (feature) {
 	case ARM_SMCCC_HV_PV_TIME_FEATURES:
 	case ARM_SMCCC_HV_PV_TIME_ST:
-		val = SMCCC_RET_SUCCESS;
+		if (vcpu->arch.steal.base != GPA_INVALID)
+			val = SMCCC_RET_SUCCESS;
 		break;
 	}
 
@@ -64,7 +62,6 @@ gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu)
 	 * Start counting stolen time from the time the guest requests
 	 * the feature enabled.
 	 */
-	vcpu->arch.steal.steal = 0;
 	vcpu->arch.steal.last_steal = current->sched_info.run_delay;
 
 	idx = srcu_read_lock(&kvm->srcu);
@@ -74,7 +71,7 @@ gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu)
 	return base;
 }
 
-static bool kvm_arm_pvtime_supported(void)
+bool kvm_arm_pvtime_supported(void)
 {
 	return !!sched_info_on();
 }
diff --git a/arch/arm64/kvm/trace_arm.h b/arch/arm64/kvm/trace_arm.h
index 4691053c5ee4..ff0444352bba 100644
--- a/arch/arm64/kvm/trace_arm.h
+++ b/arch/arm64/kvm/trace_arm.h
@@ -23,7 +23,7 @@ TRACE_EVENT(kvm_entry,
 		__entry->vcpu_pc		= vcpu_pc;
 	),
 
-	TP_printk("PC: 0x%08lx", __entry->vcpu_pc)
+	TP_printk("PC: 0x%016lx", __entry->vcpu_pc)
 );
 
 TRACE_EVENT(kvm_exit,
@@ -42,7 +42,7 @@ TRACE_EVENT(kvm_exit,
 		__entry->vcpu_pc		= vcpu_pc;
 	),
 
-	TP_printk("%s: HSR_EC: 0x%04x (%s), PC: 0x%08lx",
+	TP_printk("%s: HSR_EC: 0x%04x (%s), PC: 0x%016lx",
 		  __print_symbolic(__entry->ret, kvm_arm_exception_type),
 		  __entry->esr_ec,
 		  __print_symbolic(__entry->esr_ec, kvm_arm_exception_class),
@@ -69,7 +69,7 @@ TRACE_EVENT(kvm_guest_fault,
 		__entry->ipa			= ipa;
 	),
 
-	TP_printk("ipa %#llx, hsr %#08lx, hxfar %#08lx, pc %#08lx",
+	TP_printk("ipa %#llx, hsr %#08lx, hxfar %#08lx, pc %#016lx",
 		  __entry->ipa, __entry->hsr,
 		  __entry->hxfar, __entry->vcpu_pc)
 );
@@ -131,7 +131,7 @@ TRACE_EVENT(kvm_mmio_emulate,
 		__entry->cpsr			= cpsr;
 	),
 
-	TP_printk("Emulate MMIO at: 0x%08lx (instr: %08lx, cpsr: %08lx)",
+	TP_printk("Emulate MMIO at: 0x%016lx (instr: %08lx, cpsr: %08lx)",
 		  __entry->vcpu_pc, __entry->instr, __entry->cpsr)
 );
 
@@ -149,7 +149,7 @@ TRACE_EVENT(kvm_unmap_hva_range,
 		__entry->end		= end;
 	),
 
-	TP_printk("mmu notifier unmap range: %#08lx -- %#08lx",
+	TP_printk("mmu notifier unmap range: %#016lx -- %#016lx",
 		  __entry->start, __entry->end)
 );
 
@@ -165,7 +165,7 @@ TRACE_EVENT(kvm_set_spte_hva,
 		__entry->hva		= hva;
 	),
 
-	TP_printk("mmu notifier set pte hva: %#08lx", __entry->hva)
+	TP_printk("mmu notifier set pte hva: %#016lx", __entry->hva)
 );
 
 TRACE_EVENT(kvm_age_hva,
@@ -182,7 +182,7 @@ TRACE_EVENT(kvm_age_hva,
 		__entry->end		= end;
 	),
 
-	TP_printk("mmu notifier age hva: %#08lx -- %#08lx",
+	TP_printk("mmu notifier age hva: %#016lx -- %#016lx",
 		  __entry->start, __entry->end)
 );
 
@@ -198,7 +198,7 @@ TRACE_EVENT(kvm_test_age_hva,
 		__entry->hva		= hva;
 	),
 
-	TP_printk("mmu notifier test age hva: %#08lx", __entry->hva)
+	TP_printk("mmu notifier test age hva: %#016lx", __entry->hva)
 );
 
 TRACE_EVENT(kvm_set_way_flush,
diff --git a/arch/arm64/kvm/trace_handle_exit.h b/arch/arm64/kvm/trace_handle_exit.h
index 2c56d1e0f5bd..8d78acc4fba7 100644
--- a/arch/arm64/kvm/trace_handle_exit.h
+++ b/arch/arm64/kvm/trace_handle_exit.h
@@ -22,7 +22,7 @@ TRACE_EVENT(kvm_wfx_arm64,
 		__entry->is_wfe  = is_wfe;
 	),
 
-	TP_printk("guest executed wf%c at: 0x%08lx",
+	TP_printk("guest executed wf%c at: 0x%016lx",
 		  __entry->is_wfe ? 'e' : 'i', __entry->vcpu_pc)
 );
 
@@ -42,7 +42,7 @@ TRACE_EVENT(kvm_hvc_arm64,
 		__entry->imm = imm;
 	),
 
-	TP_printk("HVC at 0x%08lx (r0: 0x%08lx, imm: 0x%lx)",
+	TP_printk("HVC at 0x%016lx (r0: 0x%016lx, imm: 0x%lx)",
 		  __entry->vcpu_pc, __entry->r0, __entry->imm)
 );
 
@@ -135,7 +135,7 @@ TRACE_EVENT(trap_reg,
 		__entry->write_value = write_value;
 	),
 
-	TP_printk("%s %s reg %d (0x%08llx)", __entry->fn,  __entry->is_write?"write to":"read from", __entry->reg, __entry->write_value)
+	TP_printk("%s %s reg %d (0x%016llx)", __entry->fn,  __entry->is_write?"write to":"read from", __entry->reg, __entry->write_value)
 );
 
 TRACE_EVENT(kvm_handle_sys_reg,
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index f8912e45be7a..ef9f1d5e989d 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -143,14 +143,17 @@ static inline void emit_addr_mov_i64(const int reg, const u64 val,
 	}
 }
 
-static inline int bpf2a64_offset(int bpf_to, int bpf_from,
+static inline int bpf2a64_offset(int bpf_insn, int off,
 				 const struct jit_ctx *ctx)
 {
-	int to = ctx->offset[bpf_to];
-	/* -1 to account for the Branch instruction */
-	int from = ctx->offset[bpf_from] - 1;
-
-	return to - from;
+	/* BPF JMP offset is relative to the next instruction */
+	bpf_insn++;
+	/*
+	 * Whereas arm64 branch instructions encode the offset
+	 * from the branch itself, so we must subtract 1 from the
+	 * instruction offset.
+	 */
+	return ctx->offset[bpf_insn + off] - (ctx->offset[bpf_insn] - 1);
 }
 
 static void jit_fill_hole(void *area, unsigned int size)
@@ -642,7 +645,7 @@ emit_bswap_uxt:
 
 	/* JUMP off */
 	case BPF_JMP | BPF_JA:
-		jmp_offset = bpf2a64_offset(i + off, i, ctx);
+		jmp_offset = bpf2a64_offset(i, off, ctx);
 		check_imm26(jmp_offset);
 		emit(A64_B(jmp_offset), ctx);
 		break;
@@ -669,7 +672,7 @@ emit_bswap_uxt:
 	case BPF_JMP32 | BPF_JSLE | BPF_X:
 		emit(A64_CMP(is64, dst, src), ctx);
 emit_cond_jmp:
-		jmp_offset = bpf2a64_offset(i + off, i, ctx);
+		jmp_offset = bpf2a64_offset(i, off, ctx);
 		check_imm19(jmp_offset);
 		switch (BPF_OP(code)) {
 		case BPF_JEQ:
@@ -908,10 +911,21 @@ static int build_body(struct jit_ctx *ctx, bool extra_pass)
 	const struct bpf_prog *prog = ctx->prog;
 	int i;
 
+	/*
+	 * - offset[0] offset of the end of prologue,
+	 *   start of the 1st instruction.
+	 * - offset[1] - offset of the end of 1st instruction,
+	 *   start of the 2nd instruction
+	 * [....]
+	 * - offset[3] - offset of the end of 3rd instruction,
+	 *   start of 4th instruction
+	 */
 	for (i = 0; i < prog->len; i++) {
 		const struct bpf_insn *insn = &prog->insnsi[i];
 		int ret;
 
+		if (ctx->image == NULL)
+			ctx->offset[i] = ctx->idx;
 		ret = build_insn(insn, ctx, extra_pass);
 		if (ret > 0) {
 			i++;
@@ -919,11 +933,16 @@ static int build_body(struct jit_ctx *ctx, bool extra_pass)
 				ctx->offset[i] = ctx->idx;
 			continue;
 		}
-		if (ctx->image == NULL)
-			ctx->offset[i] = ctx->idx;
 		if (ret)
 			return ret;
 	}
+	/*
+	 * offset is allocated with prog->len + 1 so fill in
+	 * the last element with the offset after the last
+	 * instruction (end of program)
+	 */
+	if (ctx->image == NULL)
+		ctx->offset[i] = ctx->idx;
 
 	return 0;
 }
@@ -1002,7 +1021,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	memset(&ctx, 0, sizeof(ctx));
 	ctx.prog = prog;
 
-	ctx.offset = kcalloc(prog->len, sizeof(int), GFP_KERNEL);
+	ctx.offset = kcalloc(prog->len + 1, sizeof(int), GFP_KERNEL);
 	if (ctx.offset == NULL) {
 		prog = orig_prog;
 		goto out_off;
@@ -1089,7 +1108,7 @@ skip_init_ctx:
 	prog->jited_len = prog_size;
 
 	if (!prog->is_func || extra_pass) {
-		bpf_prog_fill_jited_linfo(prog, ctx.offset);
+		bpf_prog_fill_jited_linfo(prog, ctx.offset + 1);
 out_off:
 		kfree(ctx.offset);
 		kfree(jit_data);
diff --git a/arch/ia64/include/asm/acpi.h b/arch/ia64/include/asm/acpi.h
index b66ba907019c..87927eb824cc 100644
--- a/arch/ia64/include/asm/acpi.h
+++ b/arch/ia64/include/asm/acpi.h
@@ -74,8 +74,6 @@ static inline void arch_acpi_set_pdc_bits(u32 *buf)
 	buf[2] |= ACPI_PDC_EST_CAPABILITY_SMP;
 }
 
-#define acpi_unlazy_tlb(x)
-
 #ifdef CONFIG_ACPI_NUMA
 extern cpumask_t early_cpu_possible_map;
 #define for_each_possible_early_cpu(cpu)  \
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index c95fa3a2484c..8f328298f8cc 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -877,6 +877,7 @@ config SNI_RM
 	select I8253
 	select I8259
 	select ISA
+	select MIPS_L1_CACHE_SHIFT_6
 	select SWAP_IO_SPACE if CPU_BIG_ENDIAN
 	select SYS_HAS_CPU_R4X00
 	select SYS_HAS_CPU_R5000
diff --git a/arch/mips/boot/dts/mscc/ocelot.dtsi b/arch/mips/boot/dts/mscc/ocelot.dtsi
index f94e8a02ed06..535a98284dcb 100644
--- a/arch/mips/boot/dts/mscc/ocelot.dtsi
+++ b/arch/mips/boot/dts/mscc/ocelot.dtsi
@@ -134,11 +134,13 @@
 			      <0x1280000 0x100>,
 			      <0x1800000 0x80000>,
 			      <0x1880000 0x10000>,
+			      <0x1040000 0x10000>,
+			      <0x1050000 0x10000>,
 			      <0x1060000 0x10000>;
 			reg-names = "sys", "rew", "qs", "ptp", "port0", "port1",
 				    "port2", "port3", "port4", "port5", "port6",
 				    "port7", "port8", "port9", "port10", "qsys",
-				    "ana", "s2";
+				    "ana", "s0", "s1", "s2";
 			interrupts = <18 21 22>;
 			interrupt-names = "ptp_rdy", "xtr", "inj";
 
diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index 7de85d2253ff..0c50ac444222 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -137,6 +137,8 @@ extern void kvm_init_loongson_ipi(struct kvm *kvm);
 int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 {
 	switch (type) {
+	case KVM_VM_MIPS_AUTO:
+		break;
 #ifdef CONFIG_KVM_MIPS_VZ
 	case KVM_VM_MIPS_VZ:
 #else
diff --git a/arch/mips/sni/a20r.c b/arch/mips/sni/a20r.c
index b09dc844985a..eeeec18c420a 100644
--- a/arch/mips/sni/a20r.c
+++ b/arch/mips/sni/a20r.c
@@ -143,7 +143,10 @@ static struct platform_device sc26xx_pdev = {
 	},
 };
 
-static u32 a20r_ack_hwint(void)
+/*
+ * Trigger chipset to update CPU's CAUSE IP field
+ */
+static u32 a20r_update_cause_ip(void)
 {
 	u32 status = read_c0_status();
 
@@ -205,12 +208,14 @@ static void a20r_hwint(void)
 	int irq;
 
 	clear_c0_status(IE_IRQ0);
-	status = a20r_ack_hwint();
+	status = a20r_update_cause_ip();
 	cause = read_c0_cause();
 
 	irq = ffs(((cause & status) >> 8) & 0xf8);
 	if (likely(irq > 0))
 		do_IRQ(SNI_A20R_IRQ_BASE + irq - 1);
+
+	a20r_update_cause_ip();
 	set_c0_status(IE_IRQ0);
 }
 
diff --git a/arch/openrisc/include/asm/uaccess.h b/arch/openrisc/include/asm/uaccess.h
index f0390211236b..120f5005461b 100644
--- a/arch/openrisc/include/asm/uaccess.h
+++ b/arch/openrisc/include/asm/uaccess.h
@@ -165,19 +165,19 @@ struct __large_struct {
 
 #define __get_user_nocheck(x, ptr, size)			\
 ({								\
-	long __gu_err, __gu_val;				\
-	__get_user_size(__gu_val, (ptr), (size), __gu_err);	\
-	(x) = (__force __typeof__(*(ptr)))__gu_val;		\
+	long __gu_err;						\
+	__get_user_size((x), (ptr), (size), __gu_err);		\
 	__gu_err;						\
 })
 
 #define __get_user_check(x, ptr, size)					\
 ({									\
-	long __gu_err = -EFAULT, __gu_val = 0;				\
+	long __gu_err = -EFAULT;					\
 	const __typeof__(*(ptr)) __user *__gu_addr = (ptr);		\
-	if (access_ok(__gu_addr, size))			\
-		__get_user_size(__gu_val, __gu_addr, (size), __gu_err);	\
-	(x) = (__force __typeof__(*(ptr)))__gu_val;			\
+	if (access_ok(__gu_addr, size))					\
+		__get_user_size((x), __gu_addr, (size), __gu_err);	\
+	else								\
+		(x) = (__typeof__(*(ptr))) 0;				\
 	__gu_err;							\
 })
 
@@ -191,11 +191,13 @@ do {									\
 	case 2: __get_user_asm(x, ptr, retval, "l.lhz"); break;		\
 	case 4: __get_user_asm(x, ptr, retval, "l.lwz"); break;		\
 	case 8: __get_user_asm2(x, ptr, retval); break;			\
-	default: (x) = __get_user_bad();				\
+	default: (x) = (__typeof__(*(ptr)))__get_user_bad();		\
 	}								\
 } while (0)
 
 #define __get_user_asm(x, addr, err, op)		\
+{							\
+	unsigned long __gu_tmp;				\
 	__asm__ __volatile__(				\
 		"1:	"op" %1,0(%2)\n"		\
 		"2:\n"					\
@@ -209,10 +211,14 @@ do {									\
 		"	.align 2\n"			\
 		"	.long 1b,3b\n"			\
 		".previous"				\
-		: "=r"(err), "=r"(x)			\
-		: "r"(addr), "i"(-EFAULT), "0"(err))
+		: "=r"(err), "=r"(__gu_tmp)		\
+		: "r"(addr), "i"(-EFAULT), "0"(err));	\
+	(x) = (__typeof__(*(addr)))__gu_tmp;		\
+}
 
 #define __get_user_asm2(x, addr, err)			\
+{							\
+	unsigned long long __gu_tmp;			\
 	__asm__ __volatile__(				\
 		"1:	l.lwz %1,0(%2)\n"		\
 		"2:	l.lwz %H1,4(%2)\n"		\
@@ -229,8 +235,11 @@ do {									\
 		"	.long 1b,4b\n"			\
 		"	.long 2b,4b\n"			\
 		".previous"				\
-		: "=r"(err), "=&r"(x)			\
-		: "r"(addr), "i"(-EFAULT), "0"(err))
+		: "=r"(err), "=&r"(__gu_tmp)		\
+		: "r"(addr), "i"(-EFAULT), "0"(err));	\
+	(x) = (__typeof__(*(addr)))(			\
+		(__typeof__((x)-(x)))__gu_tmp);		\
+}
 
 /* more complex routines */
 
diff --git a/arch/openrisc/kernel/setup.c b/arch/openrisc/kernel/setup.c
index b18e775f8be3..13c87f1f872b 100644
--- a/arch/openrisc/kernel/setup.c
+++ b/arch/openrisc/kernel/setup.c
@@ -80,6 +80,16 @@ static void __init setup_memory(void)
 	 */
 	memblock_reserve(__pa(_stext), _end - _stext);
 
+#ifdef CONFIG_BLK_DEV_INITRD
+	/* Then reserve the initrd, if any */
+	if (initrd_start && (initrd_end > initrd_start)) {
+		unsigned long aligned_start = ALIGN_DOWN(initrd_start, PAGE_SIZE);
+		unsigned long aligned_end = ALIGN(initrd_end, PAGE_SIZE);
+
+		memblock_reserve(__pa(aligned_start), aligned_end - aligned_start);
+	}
+#endif /* CONFIG_BLK_DEV_INITRD */
+
 	early_init_fdt_reserve_self();
 	early_init_fdt_scan_reserved_mem();
 
diff --git a/arch/openrisc/mm/cache.c b/arch/openrisc/mm/cache.c
index 08f56af387ac..534a52ec5e66 100644
--- a/arch/openrisc/mm/cache.c
+++ b/arch/openrisc/mm/cache.c
@@ -16,7 +16,7 @@
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
 
-static void cache_loop(struct page *page, const unsigned int reg)
+static __always_inline void cache_loop(struct page *page, const unsigned int reg)
 {
 	unsigned long paddr = page_to_pfn(page) << PAGE_SHIFT;
 	unsigned long line = paddr & ~(L1_CACHE_BYTES - 1);
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 65bed1fdeaad..787e829b6f25 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -116,7 +116,6 @@ config PPC
 	#
 	select ARCH_32BIT_OFF_T if PPC32
 	select ARCH_HAS_DEBUG_VIRTUAL
-	select ARCH_HAS_DEBUG_VM_PGTABLE
 	select ARCH_HAS_DEVMEM_IS_ALLOWED
 	select ARCH_HAS_ELF_RANDOMIZE
 	select ARCH_HAS_FORTIFY_SOURCE
diff --git a/arch/powerpc/boot/dts/fsl/t1040rdb.dts b/arch/powerpc/boot/dts/fsl/t1040rdb.dts
index 65ff34c49025..af0c8a6f5613 100644
--- a/arch/powerpc/boot/dts/fsl/t1040rdb.dts
+++ b/arch/powerpc/boot/dts/fsl/t1040rdb.dts
@@ -64,6 +64,40 @@
 				phy_sgmii_2: ethernet-phy@3 {
 					reg = <0x03>;
 				};
+
+				/* VSC8514 QSGMII PHY */
+				phy_qsgmii_0: ethernet-phy@4 {
+					reg = <0x4>;
+				};
+
+				phy_qsgmii_1: ethernet-phy@5 {
+					reg = <0x5>;
+				};
+
+				phy_qsgmii_2: ethernet-phy@6 {
+					reg = <0x6>;
+				};
+
+				phy_qsgmii_3: ethernet-phy@7 {
+					reg = <0x7>;
+				};
+
+				/* VSC8514 QSGMII PHY */
+				phy_qsgmii_4: ethernet-phy@8 {
+					reg = <0x8>;
+				};
+
+				phy_qsgmii_5: ethernet-phy@9 {
+					reg = <0x9>;
+				};
+
+				phy_qsgmii_6: ethernet-phy@a {
+					reg = <0xa>;
+				};
+
+				phy_qsgmii_7: ethernet-phy@b {
+					reg = <0xb>;
+				};
 			};
 		};
 	};
@@ -76,3 +110,76 @@
 };
 
 #include "t1040si-post.dtsi"
+
+&seville_switch {
+	status = "okay";
+};
+
+&seville_port0 {
+	managed = "in-band-status";
+	phy-handle = <&phy_qsgmii_0>;
+	phy-mode = "qsgmii";
+	label = "ETH5";
+	status = "okay";
+};
+
+&seville_port1 {
+	managed = "in-band-status";
+	phy-handle = <&phy_qsgmii_1>;
+	phy-mode = "qsgmii";
+	label = "ETH4";
+	status = "okay";
+};
+
+&seville_port2 {
+	managed = "in-band-status";
+	phy-handle = <&phy_qsgmii_2>;
+	phy-mode = "qsgmii";
+	label = "ETH7";
+	status = "okay";
+};
+
+&seville_port3 {
+	managed = "in-band-status";
+	phy-handle = <&phy_qsgmii_3>;
+	phy-mode = "qsgmii";
+	label = "ETH6";
+	status = "okay";
+};
+
+&seville_port4 {
+	managed = "in-band-status";
+	phy-handle = <&phy_qsgmii_4>;
+	phy-mode = "qsgmii";
+	label = "ETH9";
+	status = "okay";
+};
+
+&seville_port5 {
+	managed = "in-band-status";
+	phy-handle = <&phy_qsgmii_5>;
+	phy-mode = "qsgmii";
+	label = "ETH8";
+	status = "okay";
+};
+
+&seville_port6 {
+	managed = "in-band-status";
+	phy-handle = <&phy_qsgmii_6>;
+	phy-mode = "qsgmii";
+	label = "ETH11";
+	status = "okay";
+};
+
+&seville_port7 {
+	managed = "in-band-status";
+	phy-handle = <&phy_qsgmii_7>;
+	phy-mode = "qsgmii";
+	label = "ETH10";
+	status = "okay";
+};
+
+&seville_port8 {
+	ethernet = <&enet0>;
+	status = "okay";
+};
diff --git a/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi b/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi
index 315d0557eefc..f58eb820eb5e 100644
--- a/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi
@@ -628,6 +628,84 @@
 			status = "disabled";
 		};
 	};
+
+	seville_switch: ethernet-switch@800000 {
+		compatible = "mscc,vsc9953-switch";
+		reg = <0x800000 0x290000>;
+		interrupts = <26 2 0 0>;
+		interrupt-names = "xtr";
+		little-endian;
+		#address-cells = <1>;
+		#size-cells = <0>;
+		status = "disabled";
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			seville_port0: port@0 {
+				reg = <0>;
+				status = "disabled";
+			};
+
+			seville_port1: port@1 {
+				reg = <1>;
+				status = "disabled";
+			};
+
+			seville_port2: port@2 {
+				reg = <2>;
+				status = "disabled";
+			};
+
+			seville_port3: port@3 {
+				reg = <3>;
+				status = "disabled";
+			};
+
+			seville_port4: port@4 {
+				reg = <4>;
+				status = "disabled";
+			};
+
+			seville_port5: port@5 {
+				reg = <5>;
+				status = "disabled";
+			};
+
+			seville_port6: port@6 {
+				reg = <6>;
+				status = "disabled";
+			};
+
+			seville_port7: port@7 {
+				reg = <7>;
+				status = "disabled";
+			};
+
+			seville_port8: port@8 {
+				reg = <8>;
+				phy-mode = "internal";
+				status = "disabled";
+
+				fixed-link {
+					speed = <2500>;
+					full-duplex;
+				};
+			};
+
+			seville_port9: port@9 {
+				reg = <9>;
+				phy-mode = "internal";
+				status = "disabled";
+
+				fixed-link {
+					speed = <2500>;
+					full-duplex;
+				};
+			};
+		};
+	};
 };
 
 &qe {
diff --git a/arch/powerpc/configs/pasemi_defconfig b/arch/powerpc/configs/pasemi_defconfig
index af9af03059e4..15ed8d0aa014 100644
--- a/arch/powerpc/configs/pasemi_defconfig
+++ b/arch/powerpc/configs/pasemi_defconfig
@@ -108,7 +108,6 @@ CONFIG_FB_NVIDIA=y
 CONFIG_FB_NVIDIA_I2C=y
 CONFIG_FB_RADEON=y
 # CONFIG_LCD_CLASS_DEVICE is not set
-CONFIG_VGACON_SOFT_SCROLLBACK=y
 CONFIG_LOGO=y
 CONFIG_SOUND=y
 CONFIG_SND=y
diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig
index 5e6f92ba3210..66e9a0fd64ff 100644
--- a/arch/powerpc/configs/ppc6xx_defconfig
+++ b/arch/powerpc/configs/ppc6xx_defconfig
@@ -743,7 +743,6 @@ CONFIG_FB_TRIDENT=m
 CONFIG_FB_SM501=m
 CONFIG_FB_IBM_GXT4500=y
 CONFIG_LCD_PLATFORM=m
-CONFIG_VGACON_SOFT_SCROLLBACK=y
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_FRAMEBUFFER_CONSOLE_ROTATION=y
 CONFIG_LOGO=y
diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h
index 55442d45c597..b392384a3b15 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu.h
@@ -239,14 +239,14 @@ static inline void early_init_mmu_secondary(void)
 
 extern void hash__setup_initial_memory_limit(phys_addr_t first_memblock_base,
 					 phys_addr_t first_memblock_size);
-extern void radix__setup_initial_memory_limit(phys_addr_t first_memblock_base,
-					 phys_addr_t first_memblock_size);
 static inline void setup_initial_memory_limit(phys_addr_t first_memblock_base,
 					      phys_addr_t first_memblock_size)
 {
-	if (early_radix_enabled())
-		return radix__setup_initial_memory_limit(first_memblock_base,
-						   first_memblock_size);
+	/*
+	 * Hash has more strict restrictions. At this point we don't
+	 * know which translations we will pick. Hence go with hash
+	 * restrictions.
+	 */
 	return hash__setup_initial_memory_limit(first_memblock_base,
 					   first_memblock_size);
 }
diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c
index 569fecd7b5b2..9053fc9d20c7 100644
--- a/arch/powerpc/kernel/dma-iommu.c
+++ b/arch/powerpc/kernel/dma-iommu.c
@@ -120,7 +120,8 @@ u64 dma_iommu_get_required_mask(struct device *dev)
 	if (!tbl)
 		return 0;
 
-	mask = 1ULL < (fls_long(tbl->it_offset + tbl->it_size) - 1);
+	mask = 1ULL << (fls_long(tbl->it_offset + tbl->it_size) +
+			tbl->it_page_shift - 1);
 	mask += mask - 1;
 
 	return mask;
diff --git a/arch/powerpc/kernel/vdso32/Makefile b/arch/powerpc/kernel/vdso32/Makefile
index 87ab1152d5ce..e147bbdc12cd 100644
--- a/arch/powerpc/kernel/vdso32/Makefile
+++ b/arch/powerpc/kernel/vdso32/Makefile
@@ -50,7 +50,7 @@ $(obj-vdso32): %.o: %.S FORCE
 
 # actual build commands
 quiet_cmd_vdso32ld = VDSO32L $@
-      cmd_vdso32ld = $(VDSOCC) $(c_flags) $(CC32FLAGS) -o $@ $(call cc-ldoption, -Wl$(comma)--orphan-handling=warn) -Wl,-T$(filter %.lds,$^) $(filter %.o,$^)
+      cmd_vdso32ld = $(VDSOCC) $(c_flags) $(CC32FLAGS) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^)
 quiet_cmd_vdso32as = VDSO32A $@
       cmd_vdso32as = $(VDSOCC) $(a_flags) $(CC32FLAGS) -c -o $@ $<
 
diff --git a/arch/powerpc/kernel/vdso32/vdso32.lds.S b/arch/powerpc/kernel/vdso32/vdso32.lds.S
index 4c985467a668..5206c2eb2a1d 100644
--- a/arch/powerpc/kernel/vdso32/vdso32.lds.S
+++ b/arch/powerpc/kernel/vdso32/vdso32.lds.S
@@ -111,7 +111,6 @@ SECTIONS
 		*(.note.GNU-stack)
 		*(.data .data.* .gnu.linkonce.d.* .sdata*)
 		*(.bss .sbss .dynbss .dynsbss)
-		*(.glink .iplt .plt .rela*)
 	}
 }
 
diff --git a/arch/powerpc/kernel/vdso64/Makefile b/arch/powerpc/kernel/vdso64/Makefile
index 38c317f25141..32ebb3522ea1 100644
--- a/arch/powerpc/kernel/vdso64/Makefile
+++ b/arch/powerpc/kernel/vdso64/Makefile
@@ -34,7 +34,7 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE
 
 # actual build commands
 quiet_cmd_vdso64ld = VDSO64L $@
-      cmd_vdso64ld = $(CC) $(c_flags) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^) $(call cc-ldoption, -Wl$(comma)--orphan-handling=warn)
+      cmd_vdso64ld = $(CC) $(c_flags) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^)
 
 # install commands for the unstripped file
 quiet_cmd_vdso_install = INSTALL $@
diff --git a/arch/powerpc/kernel/vdso64/vdso64.lds.S b/arch/powerpc/kernel/vdso64/vdso64.lds.S
index 4e3a8d4ee614..256fb9720298 100644
--- a/arch/powerpc/kernel/vdso64/vdso64.lds.S
+++ b/arch/powerpc/kernel/vdso64/vdso64.lds.S
@@ -30,7 +30,7 @@ SECTIONS
 	. = ALIGN(16);
 	.text		: {
 		*(.text .stub .text.* .gnu.linkonce.t.* __ftr_alt_*)
-		*(.sfpr)
+		*(.sfpr .glink)
 	}						:text
 	PROVIDE(__etext = .);
 	PROVIDE(_etext = .);
@@ -111,7 +111,6 @@ SECTIONS
 		*(.branch_lt)
 		*(.data .data.* .gnu.linkonce.d.* .sdata*)
 		*(.bss .sbss .dynbss .dynsbss)
-		*(.glink .iplt .plt .rela*)
 	}
 }
 
diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c
index 28c784976bed..d5f0c10d752a 100644
--- a/arch/powerpc/mm/book3s64/radix_pgtable.c
+++ b/arch/powerpc/mm/book3s64/radix_pgtable.c
@@ -734,21 +734,6 @@ void radix__mmu_cleanup_all(void)
 	}
 }
 
-void radix__setup_initial_memory_limit(phys_addr_t first_memblock_base,
-				phys_addr_t first_memblock_size)
-{
-	/*
-	 * We don't currently support the first MEMBLOCK not mapping 0
-	 * physical on those processors
-	 */
-	BUG_ON(first_memblock_base != 0);
-
-	/*
-	 * Radix mode is not limited by RMA / VRMA addressing.
-	 */
-	ppc64_rma_size = ULONG_MAX;
-}
-
 #ifdef CONFIG_MEMORY_HOTPLUG
 static void free_pte_table(pte_t *pte_start, pmd_t *pmd)
 {
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index 02e127fa5777..8459056cce67 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -433,9 +433,16 @@ void __init mmu_early_init_devtree(void)
 	if (!(mfmsr() & MSR_HV))
 		early_check_vec5();
 
-	if (early_radix_enabled())
+	if (early_radix_enabled()) {
 		radix__early_init_devtree();
-	else
+		/*
+		 * We have finalized the translation we are going to use by now.
+		 * Radix mode is not limited by RMA / VRMA addressing.
+		 * Hence don't limit memblock allocations.
+		 */
+		ppc64_rma_size = ULONG_MAX;
+		memblock_set_current_limit(MEMBLOCK_ALLOC_ANYWHERE);
+	} else
 		hash__early_init_devtree();
 }
 #endif /* CONFIG_PPC_BOOK3S_64 */
diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c
index f439f0dfea7d..a88a707a608a 100644
--- a/arch/powerpc/platforms/pseries/papr_scm.c
+++ b/arch/powerpc/platforms/pseries/papr_scm.c
@@ -822,7 +822,7 @@ free_stats:
 	kfree(stats);
 	return rc ? rc : seq_buf_used(&s);
 }
-DEVICE_ATTR_RO(perf_stats);
+DEVICE_ATTR_ADMIN_RO(perf_stats);
 
 static ssize_t flags_show(struct device *dev,
 			  struct device_attribute *attr, char *buf)
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index df18372861d8..7766e1289468 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -32,6 +32,7 @@ config RISCV
 	select ARCH_WANT_FRAME_POINTERS
 	select ARCH_WANT_HUGE_PMD_SHARE if 64BIT
 	select CLONE_BACKWARDS
+	select CLINT_TIMER if !MMU
 	select COMMON_CLK
 	select EDAC_SUPPORT
 	select GENERIC_ARCH_TOPOLOGY if SMP
diff --git a/arch/riscv/boot/dts/kendryte/k210.dtsi b/arch/riscv/boot/dts/kendryte/k210.dtsi
index c1df56ccb8d5..d2d0ff645632 100644
--- a/arch/riscv/boot/dts/kendryte/k210.dtsi
+++ b/arch/riscv/boot/dts/kendryte/k210.dtsi
@@ -95,10 +95,12 @@
 			#clock-cells = <1>;
 		};
 
-		clint0: interrupt-controller@2000000 {
+		clint0: clint@2000000 {
+			#interrupt-cells = <1>;
 			compatible = "riscv,clint0";
 			reg = <0x2000000 0xC000>;
-			interrupts-extended = <&cpu0_intc 3>,  <&cpu1_intc 3>;
+			interrupts-extended =  <&cpu0_intc 3 &cpu0_intc 7
+						&cpu1_intc 3 &cpu1_intc 7>;
 			clocks = <&sysctl K210_CLK_ACLK>;
 		};
 
diff --git a/arch/riscv/include/asm/clint.h b/arch/riscv/include/asm/clint.h
new file mode 100644
index 000000000000..0789fd37b40a
--- /dev/null
+++ b/arch/riscv/include/asm/clint.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2020 Google, Inc
+ */
+
+#ifndef _ASM_RISCV_CLINT_H
+#define _ASM_RISCV_CLINT_H
+
+#include <linux/types.h>
+#include <asm/mmio.h>
+
+#ifdef CONFIG_RISCV_M_MODE
+/*
+ * This lives in the CLINT driver, but is accessed directly by timex.h to avoid
+ * any overhead when accessing the MMIO timer.
+ *
+ * The ISA defines mtime as a 64-bit memory-mapped register that increments at
+ * a constant frequency, but it doesn't define some other constraints we depend
+ * on (most notably ordering constraints, but also some simpler stuff like the
+ * memory layout).  Thus, this is called "clint_time_val" instead of something
+ * like "riscv_mtime", to signify that these non-ISA assumptions must hold.
+ */
+extern u64 __iomem *clint_time_val;
+#endif
+
+#endif
diff --git a/arch/riscv/include/asm/ftrace.h b/arch/riscv/include/asm/ftrace.h
index ace8a6e2d11d..845002cc2e57 100644
--- a/arch/riscv/include/asm/ftrace.h
+++ b/arch/riscv/include/asm/ftrace.h
@@ -66,6 +66,13 @@ do {									\
  * Let auipc+jalr be the basic *mcount unit*, so we make it 8 bytes here.
  */
 #define MCOUNT_INSN_SIZE 8
+
+#ifndef __ASSEMBLY__
+struct dyn_ftrace;
+int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec);
+#define ftrace_init_nop ftrace_init_nop
+#endif
+
 #endif
 
 #endif /* _ASM_RISCV_FTRACE_H */
diff --git a/arch/riscv/include/asm/timex.h b/arch/riscv/include/asm/timex.h
index a3fb85d505d4..7f659dda0032 100644
--- a/arch/riscv/include/asm/timex.h
+++ b/arch/riscv/include/asm/timex.h
@@ -10,6 +10,31 @@
 
 typedef unsigned long cycles_t;
 
+#ifdef CONFIG_RISCV_M_MODE
+
+#include <asm/clint.h>
+
+#ifdef CONFIG_64BIT
+static inline cycles_t get_cycles(void)
+{
+	return readq_relaxed(clint_time_val);
+}
+#else /* !CONFIG_64BIT */
+static inline u32 get_cycles(void)
+{
+	return readl_relaxed(((u32 *)clint_time_val));
+}
+#define get_cycles get_cycles
+
+static inline u32 get_cycles_hi(void)
+{
+	return readl_relaxed(((u32 *)clint_time_val) + 1);
+}
+#define get_cycles_hi get_cycles_hi
+#endif /* CONFIG_64BIT */
+
+#else /* CONFIG_RISCV_M_MODE */
+
 static inline cycles_t get_cycles(void)
 {
 	return csr_read(CSR_TIME);
@@ -41,6 +66,8 @@ static inline u64 get_cycles64(void)
 }
 #endif /* CONFIG_64BIT */
 
+#endif /* !CONFIG_RISCV_M_MODE */
+
 #define ARCH_HAS_READ_CURRENT_TIMER
 static inline int read_current_timer(unsigned long *timer_val)
 {
diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c
index 2ff63d0cbb50..99e12faa5498 100644
--- a/arch/riscv/kernel/ftrace.c
+++ b/arch/riscv/kernel/ftrace.c
@@ -97,6 +97,25 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec,
 	return __ftrace_modify_call(rec->ip, addr, false);
 }
 
+
+/*
+ * This is called early on, and isn't wrapped by
+ * ftrace_arch_code_modify_{prepare,post_process}() and therefor doesn't hold
+ * text_mutex, which triggers a lockdep failure.  SMP isn't running so we could
+ * just directly poke the text, but it's simpler to just take the lock
+ * ourselves.
+ */
+int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec)
+{
+	int out;
+
+	ftrace_arch_code_modify_prepare();
+	out = ftrace_make_nop(mod, rec, MCOUNT_ADDR);
+	ftrace_arch_code_modify_post_process();
+
+	return out;
+}
+
 int ftrace_update_ftrace_func(ftrace_func_t func)
 {
 	int ret = __ftrace_modify_call((unsigned long)&ftrace_call,
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index 787c75f751a5..ca03762a3733 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -226,12 +226,11 @@ void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t prot)
 
 	ptep = &fixmap_pte[pte_index(addr)];
 
-	if (pgprot_val(prot)) {
+	if (pgprot_val(prot))
 		set_pte(ptep, pfn_pte(phys >> PAGE_SHIFT, prot));
-	} else {
+	else
 		pte_clear(&init_mm, addr, ptep);
-		local_flush_tlb_page(addr);
-	}
+	local_flush_tlb_page(addr);
 }
 
 static pte_t *__init get_pte_virt(phys_addr_t pa)
diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h
index faca269d5f27..a44ddc2f2dec 100644
--- a/arch/s390/kernel/entry.h
+++ b/arch/s390/kernel/entry.h
@@ -26,6 +26,7 @@ void do_protection_exception(struct pt_regs *regs);
 void do_dat_exception(struct pt_regs *regs);
 void do_secure_storage_access(struct pt_regs *regs);
 void do_non_secure_storage_access(struct pt_regs *regs);
+void do_secure_storage_violation(struct pt_regs *regs);
 
 void addressing_exception(struct pt_regs *regs);
 void data_exception(struct pt_regs *regs);
diff --git a/arch/s390/kernel/idle.c b/arch/s390/kernel/idle.c
index c73f50649e7e..f7f1e64e0d98 100644
--- a/arch/s390/kernel/idle.c
+++ b/arch/s390/kernel/idle.c
@@ -39,14 +39,13 @@ void enabled_wait(void)
 	local_irq_restore(flags);
 
 	/* Account time spent with enabled wait psw loaded as idle time. */
-	/* XXX seqcount has tracepoints that require RCU */
-	write_seqcount_begin(&idle->seqcount);
+	raw_write_seqcount_begin(&idle->seqcount);
 	idle_time = idle->clock_idle_exit - idle->clock_idle_enter;
 	idle->clock_idle_enter = idle->clock_idle_exit = 0ULL;
 	idle->idle_time += idle_time;
 	idle->idle_count++;
 	account_idle_time(cputime_to_nsecs(idle_time));
-	write_seqcount_end(&idle->seqcount);
+	raw_write_seqcount_end(&idle->seqcount);
 }
 NOKPROBE_SYMBOL(enabled_wait);
 
diff --git a/arch/s390/kernel/pgm_check.S b/arch/s390/kernel/pgm_check.S
index 2c27907a5ffc..9a92638360ee 100644
--- a/arch/s390/kernel/pgm_check.S
+++ b/arch/s390/kernel/pgm_check.S
@@ -80,7 +80,7 @@ PGM_CHECK(do_dat_exception)		/* 3b */
 PGM_CHECK_DEFAULT			/* 3c */
 PGM_CHECK(do_secure_storage_access)	/* 3d */
 PGM_CHECK(do_non_secure_storage_access)	/* 3e */
-PGM_CHECK_DEFAULT			/* 3f */
+PGM_CHECK(do_secure_storage_violation)	/* 3f */
 PGM_CHECK(monitor_event_exception)	/* 40 */
 PGM_CHECK_DEFAULT			/* 41 */
 PGM_CHECK_DEFAULT			/* 42 */
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index e600f6953d7c..c2c1b4e723ea 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -619,7 +619,7 @@ static struct notifier_block kdump_mem_nb = {
 /*
  * Make sure that the area behind memory_end is protected
  */
-static void reserve_memory_end(void)
+static void __init reserve_memory_end(void)
 {
 	if (memory_end_set)
 		memblock_reserve(memory_end, ULONG_MAX);
@@ -628,7 +628,7 @@ static void reserve_memory_end(void)
 /*
  * Make sure that oldmem, where the dump is stored, is protected
  */
-static void reserve_oldmem(void)
+static void __init reserve_oldmem(void)
 {
 #ifdef CONFIG_CRASH_DUMP
 	if (OLDMEM_BASE)
@@ -640,7 +640,7 @@ static void reserve_oldmem(void)
 /*
  * Make sure that oldmem, where the dump is stored, is protected
  */
-static void remove_oldmem(void)
+static void __init remove_oldmem(void)
 {
 #ifdef CONFIG_CRASH_DUMP
 	if (OLDMEM_BASE)
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index 4c8c063bce5b..996884dcc9fd 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -859,6 +859,21 @@ void do_non_secure_storage_access(struct pt_regs *regs)
 }
 NOKPROBE_SYMBOL(do_non_secure_storage_access);
 
+void do_secure_storage_violation(struct pt_regs *regs)
+{
+	/*
+	 * Either KVM messed up the secure guest mapping or the same
+	 * page is mapped into multiple secure guests.
+	 *
+	 * This exception is only triggered when a guest 2 is running
+	 * and can therefore never occur in kernel context.
+	 */
+	printk_ratelimited(KERN_WARNING
+			   "Secure storage violation in task: %s, pid %d\n",
+			   current->comm, current->pid);
+	send_sig(SIGSEGV, current, 0);
+}
+
 #else
 void do_secure_storage_access(struct pt_regs *regs)
 {
@@ -869,4 +884,9 @@ void do_non_secure_storage_access(struct pt_regs *regs)
 {
 	default_trap_handler(regs);
 }
+
+void do_secure_storage_violation(struct pt_regs *regs)
+{
+	default_trap_handler(regs);
+}
 #endif
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index be4b8532dd3c..0a4182792876 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -50,7 +50,6 @@ struct bpf_jit {
 	int r14_thunk_ip;	/* Address of expoline thunk for 'br %r14' */
 	int tail_call_start;	/* Tail call start offset */
 	int excnt;		/* Number of exception table entries */
-	int labels[1];		/* Labels for local jumps */
 };
 
 #define SEEN_MEM	BIT(0)		/* use mem[] for temporary storage */
@@ -229,18 +228,18 @@ static inline void reg_set_seen(struct bpf_jit *jit, u32 b1)
 	REG_SET_SEEN(b3);					\
 })
 
-#define EMIT6_PCREL_LABEL(op1, op2, b1, b2, label, mask)	\
+#define EMIT6_PCREL_RIEB(op1, op2, b1, b2, mask, target)	\
 ({								\
-	int rel = (jit->labels[label] - jit->prg) >> 1;		\
+	unsigned int rel = (int)((target) - jit->prg) / 2;	\
 	_EMIT6((op1) | reg(b1, b2) << 16 | (rel & 0xffff),	\
 	       (op2) | (mask) << 12);				\
 	REG_SET_SEEN(b1);					\
 	REG_SET_SEEN(b2);					\
 })
 
-#define EMIT6_PCREL_IMM_LABEL(op1, op2, b1, imm, label, mask)	\
+#define EMIT6_PCREL_RIEC(op1, op2, b1, imm, mask, target)	\
 ({								\
-	int rel = (jit->labels[label] - jit->prg) >> 1;		\
+	unsigned int rel = (int)((target) - jit->prg) / 2;	\
 	_EMIT6((op1) | (reg_high(b1) | (mask)) << 16 |		\
 		(rel & 0xffff), (op2) | ((imm) & 0xff) << 8);	\
 	REG_SET_SEEN(b1);					\
@@ -1282,7 +1281,9 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,
 		EMIT4(0xb9040000, BPF_REG_0, REG_2);
 		break;
 	}
-	case BPF_JMP | BPF_TAIL_CALL:
+	case BPF_JMP | BPF_TAIL_CALL: {
+		int patch_1_clrj, patch_2_clij, patch_3_brc;
+
 		/*
 		 * Implicit input:
 		 *  B1: pointer to ctx
@@ -1300,16 +1301,10 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,
 		EMIT6_DISP_LH(0xe3000000, 0x0016, REG_W1, REG_0, BPF_REG_2,
 			      offsetof(struct bpf_array, map.max_entries));
 		/* if ((u32)%b3 >= (u32)%w1) goto out; */
-		if (!is_first_pass(jit) && can_use_rel(jit, jit->labels[0])) {
-			/* clrj %b3,%w1,0xa,label0 */
-			EMIT6_PCREL_LABEL(0xec000000, 0x0077, BPF_REG_3,
-					  REG_W1, 0, 0xa);
-		} else {
-			/* clr %b3,%w1 */
-			EMIT2(0x1500, BPF_REG_3, REG_W1);
-			/* brcl 0xa,label0 */
-			EMIT6_PCREL_RILC(0xc0040000, 0xa, jit->labels[0]);
-		}
+		/* clrj %b3,%w1,0xa,out */
+		patch_1_clrj = jit->prg;
+		EMIT6_PCREL_RIEB(0xec000000, 0x0077, BPF_REG_3, REG_W1, 0xa,
+				 jit->prg);
 
 		/*
 		 * if (tail_call_cnt++ > MAX_TAIL_CALL_CNT)
@@ -1324,16 +1319,10 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,
 		EMIT4_IMM(0xa7080000, REG_W0, 1);
 		/* laal %w1,%w0,off(%r15) */
 		EMIT6_DISP_LH(0xeb000000, 0x00fa, REG_W1, REG_W0, REG_15, off);
-		if (!is_first_pass(jit) && can_use_rel(jit, jit->labels[0])) {
-			/* clij %w1,MAX_TAIL_CALL_CNT,0x2,label0 */
-			EMIT6_PCREL_IMM_LABEL(0xec000000, 0x007f, REG_W1,
-					      MAX_TAIL_CALL_CNT, 0, 0x2);
-		} else {
-			/* clfi %w1,MAX_TAIL_CALL_CNT */
-			EMIT6_IMM(0xc20f0000, REG_W1, MAX_TAIL_CALL_CNT);
-			/* brcl 0x2,label0 */
-			EMIT6_PCREL_RILC(0xc0040000, 0x2, jit->labels[0]);
-		}
+		/* clij %w1,MAX_TAIL_CALL_CNT,0x2,out */
+		patch_2_clij = jit->prg;
+		EMIT6_PCREL_RIEC(0xec000000, 0x007f, REG_W1, MAX_TAIL_CALL_CNT,
+				 2, jit->prg);
 
 		/*
 		 * prog = array->ptrs[index];
@@ -1348,13 +1337,9 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,
 		/* ltg %r1,prog(%b2,%r1) */
 		EMIT6_DISP_LH(0xe3000000, 0x0002, REG_1, BPF_REG_2,
 			      REG_1, offsetof(struct bpf_array, ptrs));
-		if (!is_first_pass(jit) && can_use_rel(jit, jit->labels[0])) {
-			/* brc 0x8,label0 */
-			EMIT4_PCREL_RIC(0xa7040000, 0x8, jit->labels[0]);
-		} else {
-			/* brcl 0x8,label0 */
-			EMIT6_PCREL_RILC(0xc0040000, 0x8, jit->labels[0]);
-		}
+		/* brc 0x8,out */
+		patch_3_brc = jit->prg;
+		EMIT4_PCREL_RIC(0xa7040000, 8, jit->prg);
 
 		/*
 		 * Restore registers before calling function
@@ -1371,8 +1356,16 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,
 		/* bc 0xf,tail_call_start(%r1) */
 		_EMIT4(0x47f01000 + jit->tail_call_start);
 		/* out: */
-		jit->labels[0] = jit->prg;
+		if (jit->prg_buf) {
+			*(u16 *)(jit->prg_buf + patch_1_clrj + 2) =
+				(jit->prg - patch_1_clrj) >> 1;
+			*(u16 *)(jit->prg_buf + patch_2_clij + 2) =
+				(jit->prg - patch_2_clij) >> 1;
+			*(u16 *)(jit->prg_buf + patch_3_brc + 2) =
+				(jit->prg - patch_3_brc) >> 1;
+		}
 		break;
+	}
 	case BPF_JMP | BPF_EXIT: /* return b0 */
 		last = (i == fp->len - 1) ? 1 : 0;
 		if (last)
diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index 4b62d6b55024..1804230dd8d8 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -668,6 +668,10 @@ EXPORT_SYMBOL_GPL(zpci_enable_device);
 int zpci_disable_device(struct zpci_dev *zdev)
 {
 	zpci_dma_exit_device(zdev);
+	/*
+	 * The zPCI function may already be disabled by the platform, this is
+	 * detected in clp_disable_fh() which becomes a no-op.
+	 */
 	return clp_disable_fh(zdev);
 }
 EXPORT_SYMBOL_GPL(zpci_disable_device);
diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c
index 9a3a291cad43..d9ae7456dd4c 100644
--- a/arch/s390/pci/pci_event.c
+++ b/arch/s390/pci/pci_event.c
@@ -143,6 +143,8 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
 			zpci_remove_device(zdev);
 		}
 
+		zdev->fh = ccdf->fh;
+		zpci_disable_device(zdev);
 		zdev->state = ZPCI_FN_STATE_STANDBY;
 		if (!clp_get_state(ccdf->fid, &state) &&
 		    state == ZPCI_FN_STATE_RESERVED) {
diff --git a/arch/sh/include/asm/smp.h b/arch/sh/include/asm/smp.h
index 1a0d7cf71c10..100bf241340b 100644
--- a/arch/sh/include/asm/smp.h
+++ b/arch/sh/include/asm/smp.h
@@ -8,7 +8,6 @@
 
 #ifdef CONFIG_SMP
 
-#include <linux/spinlock.h>
 #include <linux/atomic.h>
 #include <asm/current.h>
 #include <asm/percpu.h>
diff --git a/arch/sh/kernel/entry-common.S b/arch/sh/kernel/entry-common.S
index ad963104d22d..91ab2607a1ff 100644
--- a/arch/sh/kernel/entry-common.S
+++ b/arch/sh/kernel/entry-common.S
@@ -370,7 +370,6 @@ syscall_trace_entry:
 	 nop
 	cmp/eq	#-1, r0
 	bt	syscall_exit
-	mov.l	r0, @(OFF_R0,r15)	! Save return value
 	!			Reload R0-R4 from kernel stack, where the
 	!   	    	    	parent may have modified them using
 	!   	    	    	ptrace(POKEUSR).  (Note that R0-R2 are
diff --git a/arch/sh/kernel/ptrace_32.c b/arch/sh/kernel/ptrace_32.c
index b05bf92f9c32..5281685f6ad1 100644
--- a/arch/sh/kernel/ptrace_32.c
+++ b/arch/sh/kernel/ptrace_32.c
@@ -455,16 +455,11 @@ long arch_ptrace(struct task_struct *child, long request,
 
 asmlinkage long do_syscall_trace_enter(struct pt_regs *regs)
 {
-	long ret = 0;
-
 	if (test_thread_flag(TIF_SYSCALL_TRACE) &&
-	    tracehook_report_syscall_entry(regs))
-		/*
-		 * Tracing decided this syscall should not happen.
-		 * We'll return a bogus call number to get an ENOSYS
-		 * error, but leave the original number in regs->regs[0].
-		 */
-		ret = -1L;
+	    tracehook_report_syscall_entry(regs)) {
+		regs->regs[0] = -ENOSYS;
+		return -1;
+	}
 
 	if (secure_computing() == -1)
 		return -1;
@@ -475,7 +470,7 @@ asmlinkage long do_syscall_trace_enter(struct pt_regs *regs)
 	audit_syscall_entry(regs->regs[3], regs->regs[4], regs->regs[5],
 			    regs->regs[6], regs->regs[7]);
 
-	return ret ?: regs->regs[0];
+	return 0;
 }
 
 asmlinkage void do_syscall_trace_leave(struct pt_regs *regs)
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 3962f592633d..ff7894f39e0e 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -43,6 +43,8 @@ KBUILD_CFLAGS += -Wno-pointer-sign
 KBUILD_CFLAGS += $(call cc-option,-fmacro-prefix-map=$(srctree)/=)
 KBUILD_CFLAGS += -fno-asynchronous-unwind-tables
 KBUILD_CFLAGS += -D__DISABLE_EXPORTS
+# Disable relocation relaxation in case the link is not PIE.
+KBUILD_CFLAGS += $(call as-option,-Wa$(comma)-mrelax-relocations=no)
 
 KBUILD_AFLAGS  := $(KBUILD_CFLAGS) -D__ASSEMBLY__
 GCOV_PROFILE := n
diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig
index d7577fece9eb..78210793d357 100644
--- a/arch/x86/configs/i386_defconfig
+++ b/arch/x86/configs/i386_defconfig
@@ -19,6 +19,7 @@ CONFIG_CGROUP_CPUACCT=y
 CONFIG_BLK_DEV_INITRD=y
 # CONFIG_COMPAT_BRK is not set
 CONFIG_PROFILING=y
+# CONFIG_64BIT is not set
 CONFIG_SMP=y
 CONFIG_X86_GENERIC=y
 CONFIG_HPET_TIMER=y
@@ -186,7 +187,6 @@ CONFIG_DRM_I915=y
 CONFIG_FB_MODE_HELPERS=y
 CONFIG_FB_TILEBLITTING=y
 CONFIG_FB_EFI=y
-CONFIG_VGACON_SOFT_SCROLLBACK=y
 CONFIG_LOGO=y
 # CONFIG_LOGO_LINUX_MONO is not set
 # CONFIG_LOGO_LINUX_VGA16 is not set
diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig
index f85600143747..9936528e1939 100644
--- a/arch/x86/configs/x86_64_defconfig
+++ b/arch/x86/configs/x86_64_defconfig
@@ -181,7 +181,6 @@ CONFIG_DRM_I915=y
 CONFIG_FB_MODE_HELPERS=y
 CONFIG_FB_TILEBLITTING=y
 CONFIG_FB_EFI=y
-CONFIG_VGACON_SOFT_SCROLLBACK=y
 CONFIG_LOGO=y
 # CONFIG_LOGO_LINUX_MONO is not set
 # CONFIG_LOGO_LINUX_VGA16 is not set
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index 48512c7944e7..2f84c7ca74ea 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -60,16 +60,10 @@ __visible noinstr void do_syscall_64(unsigned long nr, struct pt_regs *regs)
 #if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
 static __always_inline unsigned int syscall_32_enter(struct pt_regs *regs)
 {
-	unsigned int nr = (unsigned int)regs->orig_ax;
-
 	if (IS_ENABLED(CONFIG_IA32_EMULATION))
 		current_thread_info()->status |= TS_COMPAT;
-	/*
-	 * Subtlety here: if ptrace pokes something larger than 2^32-1 into
-	 * orig_ax, the unsigned int return value truncates it.  This may
-	 * or may not be necessary, but it matches the old asm behavior.
-	 */
-	return (unsigned int)syscall_enter_from_user_mode(regs, nr);
+
+	return (unsigned int)regs->orig_ax;
 }
 
 /*
@@ -91,15 +85,29 @@ __visible noinstr void do_int80_syscall_32(struct pt_regs *regs)
 {
 	unsigned int nr = syscall_32_enter(regs);
 
+	/*
+	 * Subtlety here: if ptrace pokes something larger than 2^32-1 into
+	 * orig_ax, the unsigned int return value truncates it.  This may
+	 * or may not be necessary, but it matches the old asm behavior.
+	 */
+	nr = (unsigned int)syscall_enter_from_user_mode(regs, nr);
+
 	do_syscall_32_irqs_on(regs, nr);
 	syscall_exit_to_user_mode(regs);
 }
 
 static noinstr bool __do_fast_syscall_32(struct pt_regs *regs)
 {
-	unsigned int nr	= syscall_32_enter(regs);
+	unsigned int nr = syscall_32_enter(regs);
 	int res;
 
+	/*
+	 * This cannot use syscall_enter_from_user_mode() as it has to
+	 * fetch EBP before invoking any of the syscall entry work
+	 * functions.
+	 */
+	syscall_enter_from_user_mode_prepare(regs);
+
 	instrumentation_begin();
 	/* Fetch EBP from where the vDSO stashed it. */
 	if (IS_ENABLED(CONFIG_X86_64)) {
@@ -122,6 +130,9 @@ static noinstr bool __do_fast_syscall_32(struct pt_regs *regs)
 		return false;
 	}
 
+	/* The case truncates any ptrace induced syscall nr > 2^32 -1 */
+	nr = (unsigned int)syscall_enter_from_user_mode_work(regs, nr);
+
 	/* Now this is just like a normal syscall. */
 	do_syscall_32_irqs_on(regs, nr);
 	syscall_exit_to_user_mode(regs);
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index ca0976456a6b..6d2df1ee427b 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -159,8 +159,6 @@ static inline u64 x86_default_get_root_pointer(void)
 extern int x86_acpi_numa_init(void);
 #endif /* CONFIG_ACPI_NUMA */
 
-#define acpi_unlazy_tlb(x)	leave_mm(x)
-
 #ifdef CONFIG_ACPI_APEI
 static inline pgprot_t arch_apei_get_mem_attribute(phys_addr_t addr)
 {
diff --git a/arch/x86/include/asm/entry-common.h b/arch/x86/include/asm/entry-common.h
index a8f9315b9eae..6fe54b2813c1 100644
--- a/arch/x86/include/asm/entry-common.h
+++ b/arch/x86/include/asm/entry-common.h
@@ -18,8 +18,16 @@ static __always_inline void arch_check_user_regs(struct pt_regs *regs)
 		 * state, not the interrupt state as imagined by Xen.
 		 */
 		unsigned long flags = native_save_fl();
-		WARN_ON_ONCE(flags & (X86_EFLAGS_AC | X86_EFLAGS_DF |
-				      X86_EFLAGS_NT));
+		unsigned long mask = X86_EFLAGS_DF | X86_EFLAGS_NT;
+
+		/*
+		 * For !SMAP hardware we patch out CLAC on entry.
+		 */
+		if (boot_cpu_has(X86_FEATURE_SMAP) ||
+		    (IS_ENABLED(CONFIG_64_BIT) && boot_cpu_has(X86_FEATURE_XENPV)))
+			mask |= X86_EFLAGS_AC;
+
+		WARN_ON_ONCE(flags & mask);
 
 		/* We think we came from user mode. Make sure pt_regs agrees. */
 		WARN_ON_ONCE(!user_mode(regs));
diff --git a/arch/x86/include/asm/frame.h b/arch/x86/include/asm/frame.h
index 296b346184b2..fb42659f6e98 100644
--- a/arch/x86/include/asm/frame.h
+++ b/arch/x86/include/asm/frame.h
@@ -60,12 +60,26 @@
 #define FRAME_END "pop %" _ASM_BP "\n"
 
 #ifdef CONFIG_X86_64
+
 #define ENCODE_FRAME_POINTER			\
 	"lea 1(%rsp), %rbp\n\t"
+
+static inline unsigned long encode_frame_pointer(struct pt_regs *regs)
+{
+	return (unsigned long)regs + 1;
+}
+
 #else /* !CONFIG_X86_64 */
+
 #define ENCODE_FRAME_POINTER			\
 	"movl %esp, %ebp\n\t"			\
 	"andl $0x7fffffff, %ebp\n\t"
+
+static inline unsigned long encode_frame_pointer(struct pt_regs *regs)
+{
+	return (unsigned long)regs & 0x7fffffff;
+}
+
 #endif /* CONFIG_X86_64 */
 
 #endif /* __ASSEMBLY__ */
@@ -83,6 +97,11 @@
 
 #define ENCODE_FRAME_POINTER
 
+static inline unsigned long encode_frame_pointer(struct pt_regs *regs)
+{
+	return 0;
+}
+
 #endif
 
 #define FRAME_BEGIN
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index e7752b4038ff..e491c3d9f227 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -314,19 +314,19 @@ static inline void mds_idle_clear_cpu_buffers(void)
  *    lfence
  *    jmp spec_trap
  *  do_rop:
- *    mov %rax,(%rsp) for x86_64
+ *    mov %rcx,(%rsp) for x86_64
  *    mov %edx,(%esp) for x86_32
  *    retq
  *
  * Without retpolines configured:
  *
- *    jmp *%rax for x86_64
+ *    jmp *%rcx for x86_64
  *    jmp *%edx for x86_32
  */
 #ifdef CONFIG_RETPOLINE
 # ifdef CONFIG_X86_64
-#  define RETPOLINE_RAX_BPF_JIT_SIZE	17
-#  define RETPOLINE_RAX_BPF_JIT()				\
+#  define RETPOLINE_RCX_BPF_JIT_SIZE	17
+#  define RETPOLINE_RCX_BPF_JIT()				\
 do {								\
 	EMIT1_off32(0xE8, 7);	 /* callq do_rop */		\
 	/* spec_trap: */					\
@@ -334,7 +334,7 @@ do {								\
 	EMIT3(0x0F, 0xAE, 0xE8); /* lfence */			\
 	EMIT2(0xEB, 0xF9);       /* jmp spec_trap */		\
 	/* do_rop: */						\
-	EMIT4(0x48, 0x89, 0x04, 0x24); /* mov %rax,(%rsp) */	\
+	EMIT4(0x48, 0x89, 0x0C, 0x24); /* mov %rcx,(%rsp) */	\
 	EMIT1(0xC3);             /* retq */			\
 } while (0)
 # else /* !CONFIG_X86_64 */
@@ -352,9 +352,9 @@ do {								\
 # endif
 #else /* !CONFIG_RETPOLINE */
 # ifdef CONFIG_X86_64
-#  define RETPOLINE_RAX_BPF_JIT_SIZE	2
-#  define RETPOLINE_RAX_BPF_JIT()				\
-	EMIT2(0xFF, 0xE0);       /* jmp *%rax */
+#  define RETPOLINE_RCX_BPF_JIT_SIZE	2
+#  define RETPOLINE_RCX_BPF_JIT()				\
+	EMIT2(0xFF, 0xE1);       /* jmp *%rcx */
 # else /* !CONFIG_X86_64 */
 #  define RETPOLINE_EDX_BPF_JIT()				\
 	EMIT2(0xFF, 0xE2)        /* jmp *%edx */
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 40aa69d04862..d8324a236696 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -327,8 +327,8 @@ static inline unsigned long regs_get_kernel_argument(struct pt_regs *regs,
 	static const unsigned int argument_offs[] = {
 #ifdef __i386__
 		offsetof(struct pt_regs, ax),
-		offsetof(struct pt_regs, cx),
 		offsetof(struct pt_regs, dx),
+		offsetof(struct pt_regs, cx),
 #define NR_REG_ARGUMENTS 3
 #else
 		offsetof(struct pt_regs, di),
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 08320b0b2b27..9663ba31347c 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -270,9 +270,8 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_kvm_asyncpf_interrupt)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
 	u32 token;
-	irqentry_state_t state;
 
-	state = irqentry_enter(regs);
+	ack_APIC_irq();
 
 	inc_irq_stat(irq_hv_callback_count);
 
@@ -283,7 +282,6 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_kvm_asyncpf_interrupt)
 		wrmsrl(MSR_KVM_ASYNC_PF_ACK, 1);
 	}
 
-	irqentry_exit(regs, state);
 	set_irq_regs(old_regs);
 }
 
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 13ce616cc7af..ba4593a913fa 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -42,6 +42,7 @@
 #include <asm/spec-ctrl.h>
 #include <asm/io_bitmap.h>
 #include <asm/proto.h>
+#include <asm/frame.h>
 
 #include "process.h"
 
@@ -133,7 +134,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg,
 	fork_frame = container_of(childregs, struct fork_frame, regs);
 	frame = &fork_frame->frame;
 
-	frame->bp = 0;
+	frame->bp = encode_frame_pointer(childregs);
 	frame->ret_addr = (unsigned long) ret_from_fork;
 	p->thread.sp = (unsigned long) fork_frame;
 	p->thread.io_bitmap = NULL;
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 1f66d2d1e998..81a2fb711091 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -729,20 +729,9 @@ static bool is_sysenter_singlestep(struct pt_regs *regs)
 #endif
 }
 
-static __always_inline void debug_enter(unsigned long *dr6, unsigned long *dr7)
+static __always_inline unsigned long debug_read_clear_dr6(void)
 {
-	/*
-	 * Disable breakpoints during exception handling; recursive exceptions
-	 * are exceedingly 'fun'.
-	 *
-	 * Since this function is NOKPROBE, and that also applies to
-	 * HW_BREAKPOINT_X, we can't hit a breakpoint before this (XXX except a
-	 * HW_BREAKPOINT_W on our stack)
-	 *
-	 * Entry text is excluded for HW_BP_X and cpu_entry_area, which
-	 * includes the entry stack is excluded for everything.
-	 */
-	*dr7 = local_db_save();
+	unsigned long dr6;
 
 	/*
 	 * The Intel SDM says:
@@ -755,15 +744,12 @@ static __always_inline void debug_enter(unsigned long *dr6, unsigned long *dr7)
 	 *
 	 * Keep it simple: clear DR6 immediately.
 	 */
-	get_debugreg(*dr6, 6);
+	get_debugreg(dr6, 6);
 	set_debugreg(0, 6);
 	/* Filter out all the reserved bits which are preset to 1 */
-	*dr6 &= ~DR6_RESERVED;
-}
+	dr6 &= ~DR6_RESERVED;
 
-static __always_inline void debug_exit(unsigned long dr7)
-{
-	local_db_restore(dr7);
+	return dr6;
 }
 
 /*
@@ -863,6 +849,18 @@ out:
 static __always_inline void exc_debug_kernel(struct pt_regs *regs,
 					     unsigned long dr6)
 {
+	/*
+	 * Disable breakpoints during exception handling; recursive exceptions
+	 * are exceedingly 'fun'.
+	 *
+	 * Since this function is NOKPROBE, and that also applies to
+	 * HW_BREAKPOINT_X, we can't hit a breakpoint before this (XXX except a
+	 * HW_BREAKPOINT_W on our stack)
+	 *
+	 * Entry text is excluded for HW_BP_X and cpu_entry_area, which
+	 * includes the entry stack is excluded for everything.
+	 */
+	unsigned long dr7 = local_db_save();
 	bool irq_state = idtentry_enter_nmi(regs);
 	instrumentation_begin();
 
@@ -883,6 +881,8 @@ static __always_inline void exc_debug_kernel(struct pt_regs *regs,
 
 	instrumentation_end();
 	idtentry_exit_nmi(regs, irq_state);
+
+	local_db_restore(dr7);
 }
 
 static __always_inline void exc_debug_user(struct pt_regs *regs,
@@ -894,6 +894,15 @@ static __always_inline void exc_debug_user(struct pt_regs *regs,
 	 */
 	WARN_ON_ONCE(!user_mode(regs));
 
+	/*
+	 * NB: We can't easily clear DR7 here because
+	 * idtentry_exit_to_usermode() can invoke ptrace, schedule, access
+	 * user memory, etc.  This means that a recursive #DB is possible.  If
+	 * this happens, that #DB will hit exc_debug_kernel() and clear DR7.
+	 * Since we're not on the IST stack right now, everything will be
+	 * fine.
+	 */
+
 	irqentry_enter_from_user_mode(regs);
 	instrumentation_begin();
 
@@ -907,36 +916,24 @@ static __always_inline void exc_debug_user(struct pt_regs *regs,
 /* IST stack entry */
 DEFINE_IDTENTRY_DEBUG(exc_debug)
 {
-	unsigned long dr6, dr7;
-
-	debug_enter(&dr6, &dr7);
-	exc_debug_kernel(regs, dr6);
-	debug_exit(dr7);
+	exc_debug_kernel(regs, debug_read_clear_dr6());
 }
 
 /* User entry, runs on regular task stack */
 DEFINE_IDTENTRY_DEBUG_USER(exc_debug)
 {
-	unsigned long dr6, dr7;
-
-	debug_enter(&dr6, &dr7);
-	exc_debug_user(regs, dr6);
-	debug_exit(dr7);
+	exc_debug_user(regs, debug_read_clear_dr6());
 }
 #else
 /* 32 bit does not have separate entry points. */
 DEFINE_IDTENTRY_RAW(exc_debug)
 {
-	unsigned long dr6, dr7;
-
-	debug_enter(&dr6, &dr7);
+	unsigned long dr6 = debug_read_clear_dr6();
 
 	if (user_mode(regs))
 		exc_debug_user(regs, dr6);
 	else
 		exc_debug_kernel(regs, dr6);
-
-	debug_exit(dr7);
 }
 #endif
 
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 5299ef5ff18d..2f6510de6b0c 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2505,9 +2505,14 @@ static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt,
 		*reg_write(ctxt, i) = GET_SMSTATE(u32, smstate, 0x7fd0 + i * 4);
 
 	val = GET_SMSTATE(u32, smstate, 0x7fcc);
-	ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1);
+
+	if (ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1))
+		return X86EMUL_UNHANDLEABLE;
+
 	val = GET_SMSTATE(u32, smstate, 0x7fc8);
-	ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1);
+
+	if (ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1))
+		return X86EMUL_UNHANDLEABLE;
 
 	selector =                 GET_SMSTATE(u32, smstate, 0x7fc4);
 	set_desc_base(&desc,       GET_SMSTATE(u32, smstate, 0x7f64));
@@ -2560,16 +2565,23 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt,
 	ctxt->eflags = GET_SMSTATE(u32, smstate, 0x7f70) | X86_EFLAGS_FIXED;
 
 	val = GET_SMSTATE(u32, smstate, 0x7f68);
-	ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1);
+
+	if (ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1))
+		return X86EMUL_UNHANDLEABLE;
+
 	val = GET_SMSTATE(u32, smstate, 0x7f60);
-	ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1);
+
+	if (ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1))
+		return X86EMUL_UNHANDLEABLE;
 
 	cr0 =                       GET_SMSTATE(u64, smstate, 0x7f58);
 	cr3 =                       GET_SMSTATE(u64, smstate, 0x7f50);
 	cr4 =                       GET_SMSTATE(u64, smstate, 0x7f48);
 	ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smstate, 0x7f00));
 	val =                       GET_SMSTATE(u64, smstate, 0x7ed0);
-	ctxt->ops->set_msr(ctxt, MSR_EFER, val & ~EFER_LMA);
+
+	if (ctxt->ops->set_msr(ctxt, MSR_EFER, val & ~EFER_LMA))
+		return X86EMUL_UNHANDLEABLE;
 
 	selector =                  GET_SMSTATE(u32, smstate, 0x7e90);
 	rsm_set_desc_flags(&desc,   GET_SMSTATE(u32, smstate, 0x7e92) << 8);
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 43fdb0c12a5d..71aa3da2a0b7 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -2469,7 +2469,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
 		}
 
 		if (sp->unsync_children)
-			kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu);
+			kvm_make_request(KVM_REQ_MMU_SYNC, vcpu);
 
 		__clear_sp_write_flooding_count(sp);
 
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index fb68467e6049..e90bc436f584 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -586,7 +586,6 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
 	svm->vcpu.arch.mp_state = KVM_MP_STATE_RUNNABLE;
 
 	/* Give the current vmcb to the guest */
-	svm_set_gif(svm, false);
 
 	nested_vmcb->save.es     = vmcb->save.es;
 	nested_vmcb->save.cs     = vmcb->save.cs;
@@ -632,6 +631,9 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
 	/* Restore the original control entries */
 	copy_vmcb_control_area(&vmcb->control, &hsave->control);
 
+	/* On vmexit the  GIF is set to false */
+	svm_set_gif(svm, false);
+
 	svm->vmcb->control.tsc_offset = svm->vcpu.arch.tsc_offset =
 		svm->vcpu.arch.l1_tsc_offset;
 
@@ -1132,6 +1134,9 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu,
 	load_nested_vmcb_control(svm, &ctl);
 	nested_prepare_vmcb_control(svm);
 
+	if (!nested_svm_vmrun_msrpm(svm))
+		return -EINVAL;
+
 out_set_gif:
 	svm_set_gif(svm, !!(kvm_state->flags & KVM_STATE_NESTED_GIF_SET));
 	return 0;
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 402dc4234e39..7bf7bf734979 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -1106,6 +1106,7 @@ void sev_vm_destroy(struct kvm *kvm)
 		list_for_each_safe(pos, q, head) {
 			__unregister_enc_region_locked(kvm,
 				list_entry(pos, struct enc_region, list));
+			cond_resched();
 		}
 	}
 
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 0194336b64a4..c44f3e9140d5 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -2938,8 +2938,6 @@ static int handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
 	if (npt_enabled)
 		vcpu->arch.cr3 = svm->vmcb->save.cr3;
 
-	svm_complete_interrupts(svm);
-
 	if (is_guest_mode(vcpu)) {
 		int vmexit;
 
@@ -3504,7 +3502,6 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu)
 	stgi();
 
 	/* Any pending NMI will happen here */
-	exit_fastpath = svm_exit_handlers_fastpath(vcpu);
 
 	if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI))
 		kvm_after_interrupt(&svm->vcpu);
@@ -3518,6 +3515,7 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu)
 	}
 
 	svm->vmcb->control.tlb_ctl = TLB_CONTROL_DO_NOTHING;
+	vmcb_mark_all_clean(svm->vmcb);
 
 	/* if exit due to PF check for async PF */
 	if (svm->vmcb->control.exit_code == SVM_EXIT_EXCP_BASE + PF_VECTOR)
@@ -3537,7 +3535,8 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu)
 		     SVM_EXIT_EXCP_BASE + MC_VECTOR))
 		svm_handle_mce(svm);
 
-	vmcb_mark_all_clean(svm->vmcb);
+	svm_complete_interrupts(svm);
+	exit_fastpath = svm_exit_handlers_fastpath(vcpu);
 	return exit_fastpath;
 }
 
@@ -3900,21 +3899,28 @@ static int svm_pre_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
 static int svm_pre_leave_smm(struct kvm_vcpu *vcpu, const char *smstate)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
-	struct vmcb *nested_vmcb;
 	struct kvm_host_map map;
-	u64 guest;
-	u64 vmcb;
 	int ret = 0;
 
-	guest = GET_SMSTATE(u64, smstate, 0x7ed8);
-	vmcb = GET_SMSTATE(u64, smstate, 0x7ee0);
+	if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) {
+		u64 saved_efer = GET_SMSTATE(u64, smstate, 0x7ed0);
+		u64 guest = GET_SMSTATE(u64, smstate, 0x7ed8);
+		u64 vmcb = GET_SMSTATE(u64, smstate, 0x7ee0);
 
-	if (guest) {
-		if (kvm_vcpu_map(&svm->vcpu, gpa_to_gfn(vmcb), &map) == -EINVAL)
-			return 1;
-		nested_vmcb = map.hva;
-		ret = enter_svm_guest_mode(svm, vmcb, nested_vmcb);
-		kvm_vcpu_unmap(&svm->vcpu, &map, true);
+		if (guest) {
+			if (!guest_cpuid_has(vcpu, X86_FEATURE_SVM))
+				return 1;
+
+			if (!(saved_efer & EFER_SVME))
+				return 1;
+
+			if (kvm_vcpu_map(&svm->vcpu,
+					 gpa_to_gfn(vmcb), &map) == -EINVAL)
+				return 1;
+
+			ret = enter_svm_guest_mode(svm, vmcb, map.hva);
+			kvm_vcpu_unmap(&svm->vcpu, &map, true);
+		}
 	}
 
 	return ret;
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 23b58c28a1c9..1bb6b31eb646 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -4404,6 +4404,14 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
 	if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu))
 		kvm_vcpu_flush_tlb_current(vcpu);
 
+	/*
+	 * VCPU_EXREG_PDPTR will be clobbered in arch/x86/kvm/vmx/vmx.h between
+	 * now and the new vmentry.  Ensure that the VMCS02 PDPTR fields are
+	 * up-to-date before switching to L1.
+	 */
+	if (enable_ept && is_pae_paging(vcpu))
+		vmx_ept_load_pdptrs(vcpu);
+
 	leave_guest_mode(vcpu);
 
 	if (nested_cpu_has_preemption_timer(vmcs12))
@@ -4668,7 +4676,7 @@ void nested_vmx_pmu_entry_exit_ctls_update(struct kvm_vcpu *vcpu)
 		vmx->nested.msrs.entry_ctls_high &=
 				~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL;
 		vmx->nested.msrs.exit_ctls_high &=
-				~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL;
+				~VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL;
 	}
 }
 
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 819c185adf09..8646a797b7a8 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -2971,7 +2971,7 @@ static void vmx_flush_tlb_guest(struct kvm_vcpu *vcpu)
 	vpid_sync_context(to_vmx(vcpu)->vpid);
 }
 
-static void ept_load_pdptrs(struct kvm_vcpu *vcpu)
+void vmx_ept_load_pdptrs(struct kvm_vcpu *vcpu)
 {
 	struct kvm_mmu *mmu = vcpu->arch.walk_mmu;
 
@@ -3114,7 +3114,7 @@ static void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, unsigned long pgd,
 			guest_cr3 = vcpu->arch.cr3;
 		else /* vmcs01.GUEST_CR3 is already up-to-date. */
 			update_guest_cr3 = false;
-		ept_load_pdptrs(vcpu);
+		vmx_ept_load_pdptrs(vcpu);
 	} else {
 		guest_cr3 = pgd;
 	}
@@ -6054,6 +6054,7 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
 			(exit_reason != EXIT_REASON_EXCEPTION_NMI &&
 			exit_reason != EXIT_REASON_EPT_VIOLATION &&
 			exit_reason != EXIT_REASON_PML_FULL &&
+			exit_reason != EXIT_REASON_APIC_ACCESS &&
 			exit_reason != EXIT_REASON_TASK_SWITCH)) {
 		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
 		vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_DELIVERY_EV;
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 26175a4759fa..a2f82127c170 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -356,6 +356,7 @@ void vmx_update_host_rsp(struct vcpu_vmx *vmx, unsigned long host_rsp);
 int vmx_find_msr_index(struct vmx_msrs *m, u32 msr);
 int vmx_handle_memory_failure(struct kvm_vcpu *vcpu, int r,
 			      struct x86_exception *e);
+void vmx_ept_load_pdptrs(struct kvm_vcpu *vcpu);
 
 #define POSTED_INTR_ON  0
 #define POSTED_INTR_SN  1
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index d39d6cf1d473..1994602a0851 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2731,7 +2731,7 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data)
 		return 1;
 
 	if (!lapic_in_kernel(vcpu))
-		return 1;
+		return data ? 1 : 0;
 
 	vcpu->arch.apf.msr_en_val = data;
 
@@ -3578,6 +3578,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_SMALLER_MAXPHYADDR:
 		r = (int) allow_smaller_maxphyaddr;
 		break;
+	case KVM_CAP_STEAL_TIME:
+		r = sched_info_on();
+		break;
 	default:
 		break;
 	}
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index d46fff11f06f..aa067859a70b 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -24,7 +24,7 @@ ifdef CONFIG_FUNCTION_TRACER
 CFLAGS_REMOVE_cmdline.o = -pg
 endif
 
-CFLAGS_cmdline.o := -fno-stack-protector
+CFLAGS_cmdline.o := -fno-stack-protector -fno-jump-tables
 endif
 
 inat_tables_script = $(srctree)/arch/x86/tools/gen-insn-attr-x86.awk
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 35f1498e9832..6e3e8a124903 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -190,6 +190,53 @@ static inline pmd_t *vmalloc_sync_one(pgd_t *pgd, unsigned long address)
 	return pmd_k;
 }
 
+/*
+ *   Handle a fault on the vmalloc or module mapping area
+ *
+ *   This is needed because there is a race condition between the time
+ *   when the vmalloc mapping code updates the PMD to the point in time
+ *   where it synchronizes this update with the other page-tables in the
+ *   system.
+ *
+ *   In this race window another thread/CPU can map an area on the same
+ *   PMD, finds it already present and does not synchronize it with the
+ *   rest of the system yet. As a result v[mz]alloc might return areas
+ *   which are not mapped in every page-table in the system, causing an
+ *   unhandled page-fault when they are accessed.
+ */
+static noinline int vmalloc_fault(unsigned long address)
+{
+	unsigned long pgd_paddr;
+	pmd_t *pmd_k;
+	pte_t *pte_k;
+
+	/* Make sure we are in vmalloc area: */
+	if (!(address >= VMALLOC_START && address < VMALLOC_END))
+		return -1;
+
+	/*
+	 * Synchronize this task's top level page-table
+	 * with the 'reference' page table.
+	 *
+	 * Do _not_ use "current" here. We might be inside
+	 * an interrupt in the middle of a task switch..
+	 */
+	pgd_paddr = read_cr3_pa();
+	pmd_k = vmalloc_sync_one(__va(pgd_paddr), address);
+	if (!pmd_k)
+		return -1;
+
+	if (pmd_large(*pmd_k))
+		return 0;
+
+	pte_k = pte_offset_kernel(pmd_k, address);
+	if (!pte_present(*pte_k))
+		return -1;
+
+	return 0;
+}
+NOKPROBE_SYMBOL(vmalloc_fault);
+
 void arch_sync_kernel_mappings(unsigned long start, unsigned long end)
 {
 	unsigned long addr;
@@ -1110,6 +1157,37 @@ do_kern_addr_fault(struct pt_regs *regs, unsigned long hw_error_code,
 	 */
 	WARN_ON_ONCE(hw_error_code & X86_PF_PK);
 
+#ifdef CONFIG_X86_32
+	/*
+	 * We can fault-in kernel-space virtual memory on-demand. The
+	 * 'reference' page table is init_mm.pgd.
+	 *
+	 * NOTE! We MUST NOT take any locks for this case. We may
+	 * be in an interrupt or a critical region, and should
+	 * only copy the information from the master page table,
+	 * nothing more.
+	 *
+	 * Before doing this on-demand faulting, ensure that the
+	 * fault is not any of the following:
+	 * 1. A fault on a PTE with a reserved bit set.
+	 * 2. A fault caused by a user-mode access.  (Do not demand-
+	 *    fault kernel memory due to user-mode accesses).
+	 * 3. A fault caused by a page-level protection violation.
+	 *    (A demand fault would be on a non-present page which
+	 *     would have X86_PF_PROT==0).
+	 *
+	 * This is only needed to close a race condition on x86-32 in
+	 * the vmalloc mapping/unmapping code. See the comment above
+	 * vmalloc_fault() for details. On x86-64 the race does not
+	 * exist as the vmalloc mappings don't need to be synchronized
+	 * there.
+	 */
+	if (!(hw_error_code & (X86_PF_RSVD | X86_PF_USER | X86_PF_PROT))) {
+		if (vmalloc_fault(address) >= 0)
+			return;
+	}
+#endif
+
 	/* Was the fault spurious, caused by lazy TLB invalidation? */
 	if (spurious_kernel_fault(hw_error_code, address))
 		return;
diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c
index c5174b4e318b..683cd12f4793 100644
--- a/arch/x86/mm/numa_emulation.c
+++ b/arch/x86/mm/numa_emulation.c
@@ -321,7 +321,7 @@ static int __init split_nodes_size_interleave(struct numa_meminfo *ei,
 					      u64 addr, u64 max_addr, u64 size)
 {
 	return split_nodes_size_interleave_uniform(ei, pi, addr, max_addr, size,
-			0, NULL, NUMA_NO_NODE);
+			0, NULL, 0);
 }
 
 static int __init setup_emu2phys_nid(int *dfl_phys_nid)
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 7d9ea7b41c71..796506dcfc42 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -221,14 +221,48 @@ struct jit_context {
 
 /* Number of bytes emit_patch() needs to generate instructions */
 #define X86_PATCH_SIZE		5
+/* Number of bytes that will be skipped on tailcall */
+#define X86_TAIL_CALL_OFFSET	11
 
-#define PROLOGUE_SIZE		25
+static void push_callee_regs(u8 **pprog, bool *callee_regs_used)
+{
+	u8 *prog = *pprog;
+	int cnt = 0;
+
+	if (callee_regs_used[0])
+		EMIT1(0x53);         /* push rbx */
+	if (callee_regs_used[1])
+		EMIT2(0x41, 0x55);   /* push r13 */
+	if (callee_regs_used[2])
+		EMIT2(0x41, 0x56);   /* push r14 */
+	if (callee_regs_used[3])
+		EMIT2(0x41, 0x57);   /* push r15 */
+	*pprog = prog;
+}
+
+static void pop_callee_regs(u8 **pprog, bool *callee_regs_used)
+{
+	u8 *prog = *pprog;
+	int cnt = 0;
+
+	if (callee_regs_used[3])
+		EMIT2(0x41, 0x5F);   /* pop r15 */
+	if (callee_regs_used[2])
+		EMIT2(0x41, 0x5E);   /* pop r14 */
+	if (callee_regs_used[1])
+		EMIT2(0x41, 0x5D);   /* pop r13 */
+	if (callee_regs_used[0])
+		EMIT1(0x5B);         /* pop rbx */
+	*pprog = prog;
+}
 
 /*
- * Emit x86-64 prologue code for BPF program and check its size.
- * bpf_tail_call helper will skip it while jumping into another program
+ * Emit x86-64 prologue code for BPF program.
+ * bpf_tail_call helper will skip the first X86_TAIL_CALL_OFFSET bytes
+ * while jumping to another program
  */
-static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf)
+static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf,
+			  bool tail_call_reachable, bool is_subprog)
 {
 	u8 *prog = *pprog;
 	int cnt = X86_PATCH_SIZE;
@@ -238,19 +272,19 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf)
 	 */
 	memcpy(prog, ideal_nops[NOP_ATOMIC5], cnt);
 	prog += cnt;
+	if (!ebpf_from_cbpf) {
+		if (tail_call_reachable && !is_subprog)
+			EMIT2(0x31, 0xC0); /* xor eax, eax */
+		else
+			EMIT2(0x66, 0x90); /* nop2 */
+	}
 	EMIT1(0x55);             /* push rbp */
 	EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */
 	/* sub rsp, rounded_stack_depth */
-	EMIT3_off32(0x48, 0x81, 0xEC, round_up(stack_depth, 8));
-	EMIT1(0x53);             /* push rbx */
-	EMIT2(0x41, 0x55);       /* push r13 */
-	EMIT2(0x41, 0x56);       /* push r14 */
-	EMIT2(0x41, 0x57);       /* push r15 */
-	if (!ebpf_from_cbpf) {
-		/* zero init tail_call_cnt */
-		EMIT2(0x6a, 0x00);
-		BUILD_BUG_ON(cnt != PROLOGUE_SIZE);
-	}
+	if (stack_depth)
+		EMIT3_off32(0x48, 0x81, 0xEC, round_up(stack_depth, 8));
+	if (tail_call_reachable)
+		EMIT1(0x50);         /* push rax */
 	*pprog = prog;
 }
 
@@ -314,13 +348,14 @@ static int __bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
 	mutex_lock(&text_mutex);
 	if (memcmp(ip, old_insn, X86_PATCH_SIZE))
 		goto out;
+	ret = 1;
 	if (memcmp(ip, new_insn, X86_PATCH_SIZE)) {
 		if (text_live)
 			text_poke_bp(ip, new_insn, X86_PATCH_SIZE, NULL);
 		else
 			memcpy(ip, new_insn, X86_PATCH_SIZE);
+		ret = 0;
 	}
-	ret = 0;
 out:
 	mutex_unlock(&text_mutex);
 	return ret;
@@ -337,6 +372,22 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
 	return __bpf_arch_text_poke(ip, t, old_addr, new_addr, true);
 }
 
+static int get_pop_bytes(bool *callee_regs_used)
+{
+	int bytes = 0;
+
+	if (callee_regs_used[3])
+		bytes += 2;
+	if (callee_regs_used[2])
+		bytes += 2;
+	if (callee_regs_used[1])
+		bytes += 2;
+	if (callee_regs_used[0])
+		bytes += 1;
+
+	return bytes;
+}
+
 /*
  * Generate the following code:
  *
@@ -351,12 +402,32 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
  *   goto *(prog->bpf_func + prologue_size);
  * out:
  */
-static void emit_bpf_tail_call_indirect(u8 **pprog)
+static void emit_bpf_tail_call_indirect(u8 **pprog, bool *callee_regs_used,
+					u32 stack_depth)
 {
+	int tcc_off = -4 - round_up(stack_depth, 8);
 	u8 *prog = *pprog;
-	int label1, label2, label3;
+	int pop_bytes = 0;
+	int off1 = 42;
+	int off2 = 31;
+	int off3 = 9;
 	int cnt = 0;
 
+	/* count the additional bytes used for popping callee regs from stack
+	 * that need to be taken into account for each of the offsets that
+	 * are used for bailing out of the tail call
+	 */
+	pop_bytes = get_pop_bytes(callee_regs_used);
+	off1 += pop_bytes;
+	off2 += pop_bytes;
+	off3 += pop_bytes;
+
+	if (stack_depth) {
+		off1 += 7;
+		off2 += 7;
+		off3 += 7;
+	}
+
 	/*
 	 * rdi - pointer to ctx
 	 * rsi - pointer to bpf_array
@@ -370,72 +441,112 @@ static void emit_bpf_tail_call_indirect(u8 **pprog)
 	EMIT2(0x89, 0xD2);                        /* mov edx, edx */
 	EMIT3(0x39, 0x56,                         /* cmp dword ptr [rsi + 16], edx */
 	      offsetof(struct bpf_array, map.max_entries));
-#define OFFSET1 (41 + RETPOLINE_RAX_BPF_JIT_SIZE) /* Number of bytes to jump */
+#define OFFSET1 (off1 + RETPOLINE_RCX_BPF_JIT_SIZE) /* Number of bytes to jump */
 	EMIT2(X86_JBE, OFFSET1);                  /* jbe out */
-	label1 = cnt;
 
 	/*
 	 * if (tail_call_cnt > MAX_TAIL_CALL_CNT)
 	 *	goto out;
 	 */
-	EMIT2_off32(0x8B, 0x85, -36 - MAX_BPF_STACK); /* mov eax, dword ptr [rbp - 548] */
+	EMIT2_off32(0x8B, 0x85, tcc_off);         /* mov eax, dword ptr [rbp - tcc_off] */
 	EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT);     /* cmp eax, MAX_TAIL_CALL_CNT */
-#define OFFSET2 (30 + RETPOLINE_RAX_BPF_JIT_SIZE)
+#define OFFSET2 (off2 + RETPOLINE_RCX_BPF_JIT_SIZE)
 	EMIT2(X86_JA, OFFSET2);                   /* ja out */
-	label2 = cnt;
 	EMIT3(0x83, 0xC0, 0x01);                  /* add eax, 1 */
-	EMIT2_off32(0x89, 0x85, -36 - MAX_BPF_STACK); /* mov dword ptr [rbp -548], eax */
+	EMIT2_off32(0x89, 0x85, tcc_off);         /* mov dword ptr [rbp - tcc_off], eax */
 
 	/* prog = array->ptrs[index]; */
-	EMIT4_off32(0x48, 0x8B, 0x84, 0xD6,       /* mov rax, [rsi + rdx * 8 + offsetof(...)] */
+	EMIT4_off32(0x48, 0x8B, 0x8C, 0xD6,       /* mov rcx, [rsi + rdx * 8 + offsetof(...)] */
 		    offsetof(struct bpf_array, ptrs));
 
 	/*
 	 * if (prog == NULL)
 	 *	goto out;
 	 */
-	EMIT3(0x48, 0x85, 0xC0);		  /* test rax,rax */
-#define OFFSET3 (8 + RETPOLINE_RAX_BPF_JIT_SIZE)
+	EMIT3(0x48, 0x85, 0xC9);                  /* test rcx,rcx */
+#define OFFSET3 (off3 + RETPOLINE_RCX_BPF_JIT_SIZE)
 	EMIT2(X86_JE, OFFSET3);                   /* je out */
-	label3 = cnt;
 
-	/* goto *(prog->bpf_func + prologue_size); */
-	EMIT4(0x48, 0x8B, 0x40,                   /* mov rax, qword ptr [rax + 32] */
-	      offsetof(struct bpf_prog, bpf_func));
-	EMIT4(0x48, 0x83, 0xC0, PROLOGUE_SIZE);   /* add rax, prologue_size */
+	*pprog = prog;
+	pop_callee_regs(pprog, callee_regs_used);
+	prog = *pprog;
+
+	EMIT1(0x58);                              /* pop rax */
+	if (stack_depth)
+		EMIT3_off32(0x48, 0x81, 0xC4,     /* add rsp, sd */
+			    round_up(stack_depth, 8));
 
+	/* goto *(prog->bpf_func + X86_TAIL_CALL_OFFSET); */
+	EMIT4(0x48, 0x8B, 0x49,                   /* mov rcx, qword ptr [rcx + 32] */
+	      offsetof(struct bpf_prog, bpf_func));
+	EMIT4(0x48, 0x83, 0xC1,                   /* add rcx, X86_TAIL_CALL_OFFSET */
+	      X86_TAIL_CALL_OFFSET);
 	/*
-	 * Wow we're ready to jump into next BPF program
+	 * Now we're ready to jump into next BPF program
 	 * rdi == ctx (1st arg)
-	 * rax == prog->bpf_func + prologue_size
+	 * rcx == prog->bpf_func + X86_TAIL_CALL_OFFSET
 	 */
-	RETPOLINE_RAX_BPF_JIT();
+	RETPOLINE_RCX_BPF_JIT();
 
 	/* out: */
-	BUILD_BUG_ON(cnt - label1 != OFFSET1);
-	BUILD_BUG_ON(cnt - label2 != OFFSET2);
-	BUILD_BUG_ON(cnt - label3 != OFFSET3);
 	*pprog = prog;
 }
 
 static void emit_bpf_tail_call_direct(struct bpf_jit_poke_descriptor *poke,
-				      u8 **pprog, int addr, u8 *image)
+				      u8 **pprog, int addr, u8 *image,
+				      bool *callee_regs_used, u32 stack_depth)
 {
+	int tcc_off = -4 - round_up(stack_depth, 8);
 	u8 *prog = *pprog;
+	int pop_bytes = 0;
+	int off1 = 20;
+	int poke_off;
 	int cnt = 0;
 
+	/* count the additional bytes used for popping callee regs to stack
+	 * that need to be taken into account for jump offset that is used for
+	 * bailing out from of the tail call when limit is reached
+	 */
+	pop_bytes = get_pop_bytes(callee_regs_used);
+	off1 += pop_bytes;
+
+	/*
+	 * total bytes for:
+	 * - nop5/ jmpq $off
+	 * - pop callee regs
+	 * - sub rsp, $val if depth > 0
+	 * - pop rax
+	 */
+	poke_off = X86_PATCH_SIZE + pop_bytes + 1;
+	if (stack_depth) {
+		poke_off += 7;
+		off1 += 7;
+	}
+
 	/*
 	 * if (tail_call_cnt > MAX_TAIL_CALL_CNT)
 	 *	goto out;
 	 */
-	EMIT2_off32(0x8B, 0x85, -36 - MAX_BPF_STACK); /* mov eax, dword ptr [rbp - 548] */
+	EMIT2_off32(0x8B, 0x85, tcc_off);             /* mov eax, dword ptr [rbp - tcc_off] */
 	EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT);         /* cmp eax, MAX_TAIL_CALL_CNT */
-	EMIT2(X86_JA, 14);                            /* ja out */
+	EMIT2(X86_JA, off1);                          /* ja out */
 	EMIT3(0x83, 0xC0, 0x01);                      /* add eax, 1 */
-	EMIT2_off32(0x89, 0x85, -36 - MAX_BPF_STACK); /* mov dword ptr [rbp -548], eax */
+	EMIT2_off32(0x89, 0x85, tcc_off);             /* mov dword ptr [rbp - tcc_off], eax */
 
-	poke->ip = image + (addr - X86_PATCH_SIZE);
-	poke->adj_off = PROLOGUE_SIZE;
+	poke->tailcall_bypass = image + (addr - poke_off - X86_PATCH_SIZE);
+	poke->adj_off = X86_TAIL_CALL_OFFSET;
+	poke->tailcall_target = image + (addr - X86_PATCH_SIZE);
+	poke->bypass_addr = (u8 *)poke->tailcall_target + X86_PATCH_SIZE;
+
+	emit_jump(&prog, (u8 *)poke->tailcall_target + X86_PATCH_SIZE,
+		  poke->tailcall_bypass);
+
+	*pprog = prog;
+	pop_callee_regs(pprog, callee_regs_used);
+	prog = *pprog;
+	EMIT1(0x58);                                  /* pop rax */
+	if (stack_depth)
+		EMIT3_off32(0x48, 0x81, 0xC4, round_up(stack_depth, 8));
 
 	memcpy(prog, ideal_nops[NOP_ATOMIC5], X86_PATCH_SIZE);
 	prog += X86_PATCH_SIZE;
@@ -453,7 +564,7 @@ static void bpf_tail_call_direct_fixup(struct bpf_prog *prog)
 
 	for (i = 0; i < prog->aux->size_poke_tab; i++) {
 		poke = &prog->aux->poke_tab[i];
-		WARN_ON_ONCE(READ_ONCE(poke->ip_stable));
+		WARN_ON_ONCE(READ_ONCE(poke->tailcall_target_stable));
 
 		if (poke->reason != BPF_POKE_REASON_TAIL_CALL)
 			continue;
@@ -464,18 +575,25 @@ static void bpf_tail_call_direct_fixup(struct bpf_prog *prog)
 		if (target) {
 			/* Plain memcpy is used when image is not live yet
 			 * and still not locked as read-only. Once poke
-			 * location is active (poke->ip_stable), any parallel
-			 * bpf_arch_text_poke() might occur still on the
-			 * read-write image until we finally locked it as
-			 * read-only. Both modifications on the given image
-			 * are under text_mutex to avoid interference.
+			 * location is active (poke->tailcall_target_stable),
+			 * any parallel bpf_arch_text_poke() might occur
+			 * still on the read-write image until we finally
+			 * locked it as read-only. Both modifications on
+			 * the given image are under text_mutex to avoid
+			 * interference.
 			 */
-			ret = __bpf_arch_text_poke(poke->ip, BPF_MOD_JUMP, NULL,
+			ret = __bpf_arch_text_poke(poke->tailcall_target,
+						   BPF_MOD_JUMP, NULL,
 						   (u8 *)target->bpf_func +
 						   poke->adj_off, false);
 			BUG_ON(ret < 0);
+			ret = __bpf_arch_text_poke(poke->tailcall_bypass,
+						   BPF_MOD_JUMP,
+						   (u8 *)poke->tailcall_target +
+						   X86_PATCH_SIZE, NULL, false);
+			BUG_ON(ret < 0);
 		}
-		WRITE_ONCE(poke->ip_stable, true);
+		WRITE_ONCE(poke->tailcall_target_stable, true);
 		mutex_unlock(&array->aux->poke_mutex);
 	}
 }
@@ -652,19 +770,49 @@ static bool ex_handler_bpf(const struct exception_table_entry *x,
 	return true;
 }
 
+static void detect_reg_usage(struct bpf_insn *insn, int insn_cnt,
+			     bool *regs_used, bool *tail_call_seen)
+{
+	int i;
+
+	for (i = 1; i <= insn_cnt; i++, insn++) {
+		if (insn->code == (BPF_JMP | BPF_TAIL_CALL))
+			*tail_call_seen = true;
+		if (insn->dst_reg == BPF_REG_6 || insn->src_reg == BPF_REG_6)
+			regs_used[0] = true;
+		if (insn->dst_reg == BPF_REG_7 || insn->src_reg == BPF_REG_7)
+			regs_used[1] = true;
+		if (insn->dst_reg == BPF_REG_8 || insn->src_reg == BPF_REG_8)
+			regs_used[2] = true;
+		if (insn->dst_reg == BPF_REG_9 || insn->src_reg == BPF_REG_9)
+			regs_used[3] = true;
+	}
+}
+
 static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 		  int oldproglen, struct jit_context *ctx)
 {
+	bool tail_call_reachable = bpf_prog->aux->tail_call_reachable;
 	struct bpf_insn *insn = bpf_prog->insnsi;
+	bool callee_regs_used[4] = {};
 	int insn_cnt = bpf_prog->len;
+	bool tail_call_seen = false;
 	bool seen_exit = false;
 	u8 temp[BPF_MAX_INSN_SIZE + BPF_INSN_SAFETY];
 	int i, cnt = 0, excnt = 0;
 	int proglen = 0;
 	u8 *prog = temp;
 
+	detect_reg_usage(insn, insn_cnt, callee_regs_used,
+			 &tail_call_seen);
+
+	/* tail call's presence in current prog implies it is reachable */
+	tail_call_reachable |= tail_call_seen;
+
 	emit_prologue(&prog, bpf_prog->aux->stack_depth,
-		      bpf_prog_was_classic(bpf_prog));
+		      bpf_prog_was_classic(bpf_prog), tail_call_reachable,
+		      bpf_prog->aux->func_idx != 0);
+	push_callee_regs(&prog, callee_regs_used);
 	addrs[0] = prog - temp;
 
 	for (i = 1; i <= insn_cnt; i++, insn++) {
@@ -1102,16 +1250,27 @@ xadd:			if (is_imm8(insn->off))
 			/* call */
 		case BPF_JMP | BPF_CALL:
 			func = (u8 *) __bpf_call_base + imm32;
-			if (!imm32 || emit_call(&prog, func, image + addrs[i - 1]))
-				return -EINVAL;
+			if (tail_call_reachable) {
+				EMIT3_off32(0x48, 0x8B, 0x85,
+					    -(bpf_prog->aux->stack_depth + 8));
+				if (!imm32 || emit_call(&prog, func, image + addrs[i - 1] + 7))
+					return -EINVAL;
+			} else {
+				if (!imm32 || emit_call(&prog, func, image + addrs[i - 1]))
+					return -EINVAL;
+			}
 			break;
 
 		case BPF_JMP | BPF_TAIL_CALL:
 			if (imm32)
 				emit_bpf_tail_call_direct(&bpf_prog->aux->poke_tab[imm32 - 1],
-							  &prog, addrs[i], image);
+							  &prog, addrs[i], image,
+							  callee_regs_used,
+							  bpf_prog->aux->stack_depth);
 			else
-				emit_bpf_tail_call_indirect(&prog);
+				emit_bpf_tail_call_indirect(&prog,
+							    callee_regs_used,
+							    bpf_prog->aux->stack_depth);
 			break;
 
 			/* cond jump */
@@ -1294,12 +1453,7 @@ emit_jmp:
 			seen_exit = true;
 			/* Update cleanup_addr */
 			ctx->cleanup_addr = proglen;
-			if (!bpf_prog_was_classic(bpf_prog))
-				EMIT1(0x5B); /* get rid of tail_call_cnt */
-			EMIT2(0x41, 0x5F);   /* pop r15 */
-			EMIT2(0x41, 0x5E);   /* pop r14 */
-			EMIT2(0x41, 0x5D);   /* pop r13 */
-			EMIT1(0x5B);         /* pop rbx */
+			pop_callee_regs(&prog, callee_regs_used);
 			EMIT1(0xC9);         /* leave */
 			EMIT1(0xC3);         /* ret */
 			break;
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index c34b090178a9..fa98470df3f0 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -5896,18 +5896,6 @@ static void bfq_finish_requeue_request(struct request *rq)
 	struct bfq_data *bfqd;
 
 	/*
-	 * Requeue and finish hooks are invoked in blk-mq without
-	 * checking whether the involved request is actually still
-	 * referenced in the scheduler. To handle this fact, the
-	 * following two checks make this function exit in case of
-	 * spurious invocations, for which there is nothing to do.
-	 *
-	 * First, check whether rq has nothing to do with an elevator.
-	 */
-	if (unlikely(!(rq->rq_flags & RQF_ELVPRIV)))
-		return;
-
-	/*
 	 * rq either is not associated with any icq, or is an already
 	 * requeued request that has not (yet) been re-inserted into
 	 * a bfq_queue.
diff --git a/block/bio.c b/block/bio.c
index a9931f23d933..e865ea55b9f9 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -879,8 +879,10 @@ bool __bio_try_merge_page(struct bio *bio, struct page *page,
 		struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1];
 
 		if (page_is_mergeable(bv, page, len, off, same_page)) {
-			if (bio->bi_iter.bi_size > UINT_MAX - len)
+			if (bio->bi_iter.bi_size > UINT_MAX - len) {
+				*same_page = false;
 				return false;
+			}
 			bv->bv_len += len;
 			bio->bi_iter.bi_size += len;
 			return true;
diff --git a/block/blk-mq-sched.h b/block/blk-mq-sched.h
index 126021fc3a11..e81ca1bf6e10 100644
--- a/block/blk-mq-sched.h
+++ b/block/blk-mq-sched.h
@@ -66,7 +66,7 @@ static inline void blk_mq_sched_requeue_request(struct request *rq)
 	struct request_queue *q = rq->q;
 	struct elevator_queue *e = q->elevator;
 
-	if (e && e->type->ops.requeue_request)
+	if ((rq->rq_flags & RQF_ELVPRIV) && e && e->type->ops.requeue_request)
 		e->type->ops.requeue_request(rq);
 }
 
diff --git a/block/partitions/core.c b/block/partitions/core.c
index 5b4869c08fb3..722406b841df 100644
--- a/block/partitions/core.c
+++ b/block/partitions/core.c
@@ -537,7 +537,7 @@ int bdev_del_partition(struct block_device *bdev, int partno)
 
 	bdevp = bdget_disk(bdev->bd_disk, partno);
 	if (!bdevp)
-		return -ENOMEM;
+		return -ENXIO;
 
 	mutex_lock(&bdevp->bd_mutex);
 	mutex_lock_nested(&bdev->bd_mutex, 1);
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index 71a30b0d0f05..7ecb90e90afd 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -161,18 +161,10 @@ static void lapic_timer_propagate_broadcast(struct acpi_processor *pr)
 }
 
 /* Power(C) State timer broadcast control */
-static void lapic_timer_state_broadcast(struct acpi_processor *pr,
-				       struct acpi_processor_cx *cx,
-				       int broadcast)
+static bool lapic_timer_needs_broadcast(struct acpi_processor *pr,
+					struct acpi_processor_cx *cx)
 {
-	int state = cx - pr->power.states;
-
-	if (state >= pr->power.timer_broadcast_on_state) {
-		if (broadcast)
-			tick_broadcast_enter();
-		else
-			tick_broadcast_exit();
-	}
+	return cx - pr->power.states >= pr->power.timer_broadcast_on_state;
 }
 
 #else
@@ -180,9 +172,9 @@ static void lapic_timer_state_broadcast(struct acpi_processor *pr,
 static void lapic_timer_check_state(int state, struct acpi_processor *pr,
 				   struct acpi_processor_cx *cstate) { }
 static void lapic_timer_propagate_broadcast(struct acpi_processor *pr) { }
-static void lapic_timer_state_broadcast(struct acpi_processor *pr,
-				       struct acpi_processor_cx *cx,
-				       int broadcast)
+
+static bool lapic_timer_needs_broadcast(struct acpi_processor *pr,
+					struct acpi_processor_cx *cx)
 {
 }
 
@@ -566,32 +558,43 @@ static DEFINE_RAW_SPINLOCK(c3_lock);
 
 /**
  * acpi_idle_enter_bm - enters C3 with proper BM handling
+ * @drv: cpuidle driver
  * @pr: Target processor
  * @cx: Target state context
- * @timer_bc: Whether or not to change timer mode to broadcast
+ * @index: index of target state
  */
-static void acpi_idle_enter_bm(struct acpi_processor *pr,
-			       struct acpi_processor_cx *cx, bool timer_bc)
+static int acpi_idle_enter_bm(struct cpuidle_driver *drv,
+			       struct acpi_processor *pr,
+			       struct acpi_processor_cx *cx,
+			       int index)
 {
-	acpi_unlazy_tlb(smp_processor_id());
-
-	/*
-	 * Must be done before busmaster disable as we might need to
-	 * access HPET !
-	 */
-	if (timer_bc)
-		lapic_timer_state_broadcast(pr, cx, 1);
+	static struct acpi_processor_cx safe_cx = {
+		.entry_method = ACPI_CSTATE_HALT,
+	};
 
 	/*
 	 * disable bus master
 	 * bm_check implies we need ARB_DIS
 	 * bm_control implies whether we can do ARB_DIS
 	 *
-	 * That leaves a case where bm_check is set and bm_control is
-	 * not set. In that case we cannot do much, we enter C3
-	 * without doing anything.
+	 * That leaves a case where bm_check is set and bm_control is not set.
+	 * In that case we cannot do much, we enter C3 without doing anything.
 	 */
-	if (pr->flags.bm_control) {
+	bool dis_bm = pr->flags.bm_control;
+
+	/* If we can skip BM, demote to a safe state. */
+	if (!cx->bm_sts_skip && acpi_idle_bm_check()) {
+		dis_bm = false;
+		index = drv->safe_state_index;
+		if (index >= 0) {
+			cx = this_cpu_read(acpi_cstate[index]);
+		} else {
+			cx = &safe_cx;
+			index = -EBUSY;
+		}
+	}
+
+	if (dis_bm) {
 		raw_spin_lock(&c3_lock);
 		c3_cpu_count++;
 		/* Disable bus master arbitration when all CPUs are in C3 */
@@ -600,18 +603,21 @@ static void acpi_idle_enter_bm(struct acpi_processor *pr,
 		raw_spin_unlock(&c3_lock);
 	}
 
+	rcu_idle_enter();
+
 	acpi_idle_do_entry(cx);
 
+	rcu_idle_exit();
+
 	/* Re-enable bus master arbitration */
-	if (pr->flags.bm_control) {
+	if (dis_bm) {
 		raw_spin_lock(&c3_lock);
 		acpi_write_bit_register(ACPI_BITREG_ARB_DISABLE, 0);
 		c3_cpu_count--;
 		raw_spin_unlock(&c3_lock);
 	}
 
-	if (timer_bc)
-		lapic_timer_state_broadcast(pr, cx, 0);
+	return index;
 }
 
 static int acpi_idle_enter(struct cpuidle_device *dev,
@@ -625,32 +631,21 @@ static int acpi_idle_enter(struct cpuidle_device *dev,
 		return -EINVAL;
 
 	if (cx->type != ACPI_STATE_C1) {
+		if (cx->type == ACPI_STATE_C3 && pr->flags.bm_check)
+			return acpi_idle_enter_bm(drv, pr, cx, index);
+
+		/* C2 to C1 demotion. */
 		if (acpi_idle_fallback_to_c1(pr) && num_online_cpus() > 1) {
 			index = ACPI_IDLE_STATE_START;
 			cx = per_cpu(acpi_cstate[index], dev->cpu);
-		} else if (cx->type == ACPI_STATE_C3 && pr->flags.bm_check) {
-			if (cx->bm_sts_skip || !acpi_idle_bm_check()) {
-				acpi_idle_enter_bm(pr, cx, true);
-				return index;
-			} else if (drv->safe_state_index >= 0) {
-				index = drv->safe_state_index;
-				cx = per_cpu(acpi_cstate[index], dev->cpu);
-			} else {
-				acpi_safe_halt();
-				return -EBUSY;
-			}
 		}
 	}
 
-	lapic_timer_state_broadcast(pr, cx, 1);
-
 	if (cx->type == ACPI_STATE_C3)
 		ACPI_FLUSH_CPU_CACHE();
 
 	acpi_idle_do_entry(cx);
 
-	lapic_timer_state_broadcast(pr, cx, 0);
-
 	return index;
 }
 
@@ -666,7 +661,13 @@ static int acpi_idle_enter_s2idle(struct cpuidle_device *dev,
 			return 0;
 
 		if (pr->flags.bm_check) {
-			acpi_idle_enter_bm(pr, cx, false);
+			u8 bm_sts_skip = cx->bm_sts_skip;
+
+			/* Don't check BM_STS, do an unconditional ARB_DIS for S2IDLE */
+			cx->bm_sts_skip = 1;
+			acpi_idle_enter_bm(drv, pr, cx, index);
+			cx->bm_sts_skip = bm_sts_skip;
+
 			return 0;
 		} else {
 			ACPI_FLUSH_CPU_CACHE();
@@ -682,11 +683,13 @@ static int acpi_processor_setup_cpuidle_cx(struct acpi_processor *pr,
 {
 	int i, count = ACPI_IDLE_STATE_START;
 	struct acpi_processor_cx *cx;
+	struct cpuidle_state *state;
 
 	if (max_cstate == 0)
 		max_cstate = 1;
 
 	for (i = 1; i < ACPI_PROCESSOR_MAX_POWER && i <= max_cstate; i++) {
+		state = &acpi_idle_driver.states[count];
 		cx = &pr->power.states[i];
 
 		if (!cx->valid)
@@ -694,6 +697,15 @@ static int acpi_processor_setup_cpuidle_cx(struct acpi_processor *pr,
 
 		per_cpu(acpi_cstate[count], dev->cpu) = cx;
 
+		if (lapic_timer_needs_broadcast(pr, cx))
+			state->flags |= CPUIDLE_FLAG_TIMER_STOP;
+
+		if (cx->type == ACPI_STATE_C3) {
+			state->flags |= CPUIDLE_FLAG_TLB_FLUSHED;
+			if (pr->flags.bm_check)
+				state->flags |= CPUIDLE_FLAG_RCU_IDLE;
+		}
+
 		count++;
 		if (count == CPUIDLE_STATE_MAX)
 			break;
diff --git a/drivers/atm/atmtcp.c b/drivers/atm/atmtcp.c
index 7f814da3c2d0..96bea1ab1ecc 100644
--- a/drivers/atm/atmtcp.c
+++ b/drivers/atm/atmtcp.c
@@ -327,7 +327,7 @@ done:
  */
 
 
-static struct atmdev_ops atmtcp_v_dev_ops = {
+static const struct atmdev_ops atmtcp_v_dev_ops = {
 	.dev_close	= atmtcp_v_dev_close,
 	.open		= atmtcp_v_open,
 	.close		= atmtcp_v_close,
diff --git a/drivers/atm/eni.c b/drivers/atm/eni.c
index 39be444534d0..316a9947541f 100644
--- a/drivers/atm/eni.c
+++ b/drivers/atm/eni.c
@@ -2224,7 +2224,7 @@ static int eni_init_one(struct pci_dev *pci_dev,
 
 	rc = dma_set_mask_and_coherent(&pci_dev->dev, DMA_BIT_MASK(32));
 	if (rc < 0)
-		goto out;
+		goto err_disable;
 
 	rc = -ENOMEM;
 	eni_dev = kmalloc(sizeof(struct eni_dev), GFP_KERNEL);
diff --git a/drivers/auxdisplay/arm-charlcd.c b/drivers/auxdisplay/arm-charlcd.c
index dea031484cc4..0b1c99cca733 100644
--- a/drivers/auxdisplay/arm-charlcd.c
+++ b/drivers/auxdisplay/arm-charlcd.c
@@ -2,7 +2,7 @@
 /*
  * Driver for the on-board character LCD found on some ARM reference boards
  * This is basically an Hitachi HD44780 LCD with a custom IP block to drive it
- * http://en.wikipedia.org/wiki/HD44780_Character_LCD
+ * https://en.wikipedia.org/wiki/HD44780_Character_LCD
  * Currently it will just display the text "ARM Linux" and the linux version
  *
  * Author: Linus Walleij <triad@df.lth.se>
diff --git a/drivers/base/core.c b/drivers/base/core.c
index f6f620aa9408..bb5806a2bd4c 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -807,9 +807,7 @@ static void device_link_put_kref(struct device_link *link)
 void device_link_del(struct device_link *link)
 {
 	device_links_write_lock();
-	device_pm_lock();
 	device_link_put_kref(link);
-	device_pm_unlock();
 	device_links_write_unlock();
 }
 EXPORT_SYMBOL_GPL(device_link_del);
@@ -830,7 +828,6 @@ void device_link_remove(void *consumer, struct device *supplier)
 		return;
 
 	device_links_write_lock();
-	device_pm_lock();
 
 	list_for_each_entry(link, &supplier->links.consumers, s_node) {
 		if (link->consumer == consumer) {
@@ -839,7 +836,6 @@ void device_link_remove(void *consumer, struct device *supplier)
 		}
 	}
 
-	device_pm_unlock();
 	device_links_write_unlock();
 }
 EXPORT_SYMBOL_GPL(device_link_remove);
@@ -4237,10 +4233,10 @@ int dev_err_probe(const struct device *dev, int err, const char *fmt, ...)
 	vaf.va = &args;
 
 	if (err != -EPROBE_DEFER) {
-		dev_err(dev, "error %d: %pV", err, &vaf);
+		dev_err(dev, "error %pe: %pV", ERR_PTR(err), &vaf);
 	} else {
 		device_set_deferred_probe_reason(dev, &vaf);
-		dev_dbg(dev, "error %d: %pV", err, &vaf);
+		dev_dbg(dev, "error %pe: %pV", ERR_PTR(err), &vaf);
 	}
 
 	va_end(args);
diff --git a/drivers/base/firmware_loader/firmware.h b/drivers/base/firmware_loader/firmware.h
index 933e2192fbe8..d08efc77cf16 100644
--- a/drivers/base/firmware_loader/firmware.h
+++ b/drivers/base/firmware_loader/firmware.h
@@ -142,10 +142,12 @@ int assign_fw(struct firmware *fw, struct device *device, u32 opt_flags);
 void fw_free_paged_buf(struct fw_priv *fw_priv);
 int fw_grow_paged_buf(struct fw_priv *fw_priv, int pages_needed);
 int fw_map_paged_buf(struct fw_priv *fw_priv);
+bool fw_is_paged_buf(struct fw_priv *fw_priv);
 #else
 static inline void fw_free_paged_buf(struct fw_priv *fw_priv) {}
 static inline int fw_grow_paged_buf(struct fw_priv *fw_priv, int pages_needed) { return -ENXIO; }
 static inline int fw_map_paged_buf(struct fw_priv *fw_priv) { return -ENXIO; }
+static inline bool fw_is_paged_buf(struct fw_priv *fw_priv) { return false; }
 #endif
 
 #endif /* __FIRMWARE_LOADER_H */
diff --git a/drivers/base/firmware_loader/main.c b/drivers/base/firmware_loader/main.c
index 9da0c9d5f538..63b9714a0154 100644
--- a/drivers/base/firmware_loader/main.c
+++ b/drivers/base/firmware_loader/main.c
@@ -252,9 +252,11 @@ static void __free_fw_priv(struct kref *ref)
 	list_del(&fw_priv->list);
 	spin_unlock(&fwc->lock);
 
-	fw_free_paged_buf(fw_priv); /* free leftover pages */
-	if (!fw_priv->allocated_size)
+	if (fw_is_paged_buf(fw_priv))
+		fw_free_paged_buf(fw_priv);
+	else if (!fw_priv->allocated_size)
 		vfree(fw_priv->data);
+
 	kfree_const(fw_priv->fw_name);
 	kfree(fw_priv);
 }
@@ -268,6 +270,11 @@ static void free_fw_priv(struct fw_priv *fw_priv)
 }
 
 #ifdef CONFIG_FW_LOADER_PAGED_BUF
+bool fw_is_paged_buf(struct fw_priv *fw_priv)
+{
+	return fw_priv->is_paged_buf;
+}
+
 void fw_free_paged_buf(struct fw_priv *fw_priv)
 {
 	int i;
@@ -275,6 +282,8 @@ void fw_free_paged_buf(struct fw_priv *fw_priv)
 	if (!fw_priv->pages)
 		return;
 
+	vunmap(fw_priv->data);
+
 	for (i = 0; i < fw_priv->nr_pages; i++)
 		__free_page(fw_priv->pages[i]);
 	kvfree(fw_priv->pages);
@@ -328,10 +337,6 @@ int fw_map_paged_buf(struct fw_priv *fw_priv)
 	if (!fw_priv->data)
 		return -ENOMEM;
 
-	/* page table is no longer needed after mapping, let's free */
-	kvfree(fw_priv->pages);
-	fw_priv->pages = NULL;
-
 	return 0;
 }
 #endif
diff --git a/drivers/bcma/driver_pci_host.c b/drivers/bcma/driver_pci_host.c
index 88a93c266c19..6f8fc5f587fe 100644
--- a/drivers/bcma/driver_pci_host.c
+++ b/drivers/bcma/driver_pci_host.c
@@ -419,12 +419,12 @@ void bcma_core_pci_hostmode_init(struct bcma_drv_pci *pc)
 	pc_host->pci_ops.read = bcma_core_pci_hostmode_read_config;
 	pc_host->pci_ops.write = bcma_core_pci_hostmode_write_config;
 
-	pc_host->mem_resource.name = "BCMA PCIcore external memory",
+	pc_host->mem_resource.name = "BCMA PCIcore external memory";
 	pc_host->mem_resource.start = BCMA_SOC_PCI_DMA;
 	pc_host->mem_resource.end = BCMA_SOC_PCI_DMA + BCMA_SOC_PCI_DMA_SZ - 1;
 	pc_host->mem_resource.flags = IORESOURCE_MEM | IORESOURCE_PCI_FIXED;
 
-	pc_host->io_resource.name = "BCMA PCIcore external I/O",
+	pc_host->io_resource.name = "BCMA PCIcore external I/O";
 	pc_host->io_resource.start = 0x100;
 	pc_host->io_resource.end = 0x7FF;
 	pc_host->io_resource.flags = IORESOURCE_IO | IORESOURCE_PCI_FIXED;
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index edf8b632e3d2..ab2bbe2208ef 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -2183,7 +2183,7 @@ out:
 	return ret;
 }
 
-static const struct genl_ops nbd_connect_genl_ops[] = {
+static const struct genl_small_ops nbd_connect_genl_ops[] = {
 	{
 		.cmd	= NBD_CMD_CONNECT,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
@@ -2215,8 +2215,8 @@ static struct genl_family nbd_genl_family __ro_after_init = {
 	.name		= NBD_GENL_FAMILY_NAME,
 	.version	= NBD_GENL_VERSION,
 	.module		= THIS_MODULE,
-	.ops		= nbd_connect_genl_ops,
-	.n_ops		= ARRAY_SIZE(nbd_connect_genl_ops),
+	.small_ops	= nbd_connect_genl_ops,
+	.n_small_ops	= ARRAY_SIZE(nbd_connect_genl_ops),
 	.maxattr	= NBD_ATTR_MAX,
 	.policy = nbd_attr_policy,
 	.mcgrps		= nbd_mcast_grps,
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 011539039693..e77eaab5cf23 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -5120,6 +5120,9 @@ static ssize_t rbd_config_info_show(struct device *dev,
 {
 	struct rbd_device *rbd_dev = dev_to_rbd_dev(dev);
 
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
 	return sprintf(buf, "%s\n", rbd_dev->config_info);
 }
 
@@ -5231,6 +5234,9 @@ static ssize_t rbd_image_refresh(struct device *dev,
 	struct rbd_device *rbd_dev = dev_to_rbd_dev(dev);
 	int ret;
 
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
 	ret = rbd_dev_refresh(rbd_dev);
 	if (ret)
 		return ret;
@@ -7059,6 +7065,9 @@ static ssize_t do_rbd_add(struct bus_type *bus,
 	struct rbd_client *rbdc;
 	int rc;
 
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
 	if (!try_module_get(THIS_MODULE))
 		return -ENODEV;
 
@@ -7209,6 +7218,9 @@ static ssize_t do_rbd_remove(struct bus_type *bus,
 	bool force = false;
 	int ret;
 
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
 	dev_id = -1;
 	opt_buf[0] = '\0';
 	sscanf(buf, "%d %5s", &dev_id, opt_buf);
diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c
index 5fa5be3c5598..88ce5f0ffc4b 100644
--- a/drivers/bluetooth/btintel.c
+++ b/drivers/bluetooth/btintel.c
@@ -18,7 +18,11 @@
 
 #define VERSION "0.1"
 
-#define BDADDR_INTEL (&(bdaddr_t) {{0x00, 0x8b, 0x9e, 0x19, 0x03, 0x00}})
+#define BDADDR_INTEL		(&(bdaddr_t){{0x00, 0x8b, 0x9e, 0x19, 0x03, 0x00}})
+#define RSA_HEADER_LEN		644
+#define CSS_HEADER_OFFSET	8
+#define ECDSA_OFFSET		644
+#define ECDSA_HEADER_LEN	320
 
 int btintel_check_bdaddr(struct hci_dev *hdev)
 {
@@ -360,6 +364,144 @@ int btintel_read_version(struct hci_dev *hdev, struct intel_version *ver)
 }
 EXPORT_SYMBOL_GPL(btintel_read_version);
 
+void btintel_version_info_tlv(struct hci_dev *hdev, struct intel_version_tlv *version)
+{
+	const char *variant;
+
+	switch (version->img_type) {
+	case 0x01:
+		variant = "Bootloader";
+		bt_dev_info(hdev, "Device revision is %u", version->dev_rev_id);
+		bt_dev_info(hdev, "Secure boot is %s",
+			    version->secure_boot ? "enabled" : "disabled");
+		bt_dev_info(hdev, "OTP lock is %s",
+			    version->otp_lock ? "enabled" : "disabled");
+		bt_dev_info(hdev, "API lock is %s",
+			    version->api_lock ? "enabled" : "disabled");
+		bt_dev_info(hdev, "Debug lock is %s",
+			    version->debug_lock ? "enabled" : "disabled");
+		bt_dev_info(hdev, "Minimum firmware build %u week %u %u",
+			    version->min_fw_build_nn, version->min_fw_build_cw,
+			    2000 + version->min_fw_build_yy);
+		break;
+	case 0x03:
+		variant = "Firmware";
+		break;
+	default:
+		bt_dev_err(hdev, "Unsupported image type(%02x)", version->img_type);
+		goto done;
+	}
+
+	bt_dev_info(hdev, "%s timestamp %u.%u buildtype %u build %u", variant,
+		    2000 + (version->timestamp >> 8), version->timestamp & 0xff,
+		    version->build_type, version->build_num);
+
+done:
+	return;
+}
+EXPORT_SYMBOL_GPL(btintel_version_info_tlv);
+
+int btintel_read_version_tlv(struct hci_dev *hdev, struct intel_version_tlv *version)
+{
+	struct sk_buff *skb;
+	const u8 param[1] = { 0xFF };
+
+	if (!version)
+		return -EINVAL;
+
+	skb = __hci_cmd_sync(hdev, 0xfc05, 1, param, HCI_CMD_TIMEOUT);
+	if (IS_ERR(skb)) {
+		bt_dev_err(hdev, "Reading Intel version information failed (%ld)",
+			   PTR_ERR(skb));
+		return PTR_ERR(skb);
+	}
+
+	if (skb->data[0]) {
+		bt_dev_err(hdev, "Intel Read Version command failed (%02x)",
+			   skb->data[0]);
+		kfree_skb(skb);
+		return -EIO;
+	}
+
+	/* Consume Command Complete Status field */
+	skb_pull(skb, 1);
+
+	/* Event parameters contatin multiple TLVs. Read each of them
+	 * and only keep the required data. Also, it use existing legacy
+	 * version field like hw_platform, hw_variant, and fw_variant
+	 * to keep the existing setup flow
+	 */
+	while (skb->len) {
+		struct intel_tlv *tlv;
+
+		tlv = (struct intel_tlv *)skb->data;
+		switch (tlv->type) {
+		case INTEL_TLV_CNVI_TOP:
+			version->cnvi_top = get_unaligned_le32(tlv->val);
+			break;
+		case INTEL_TLV_CNVR_TOP:
+			version->cnvr_top = get_unaligned_le32(tlv->val);
+			break;
+		case INTEL_TLV_CNVI_BT:
+			version->cnvi_bt = get_unaligned_le32(tlv->val);
+			break;
+		case INTEL_TLV_CNVR_BT:
+			version->cnvr_bt = get_unaligned_le32(tlv->val);
+			break;
+		case INTEL_TLV_DEV_REV_ID:
+			version->dev_rev_id = get_unaligned_le16(tlv->val);
+			break;
+		case INTEL_TLV_IMAGE_TYPE:
+			version->img_type = tlv->val[0];
+			break;
+		case INTEL_TLV_TIME_STAMP:
+			version->timestamp = get_unaligned_le16(tlv->val);
+			break;
+		case INTEL_TLV_BUILD_TYPE:
+			version->build_type = tlv->val[0];
+			break;
+		case INTEL_TLV_BUILD_NUM:
+			version->build_num = get_unaligned_le32(tlv->val);
+			break;
+		case INTEL_TLV_SECURE_BOOT:
+			version->secure_boot = tlv->val[0];
+			break;
+		case INTEL_TLV_OTP_LOCK:
+			version->otp_lock = tlv->val[0];
+			break;
+		case INTEL_TLV_API_LOCK:
+			version->api_lock = tlv->val[0];
+			break;
+		case INTEL_TLV_DEBUG_LOCK:
+			version->debug_lock = tlv->val[0];
+			break;
+		case INTEL_TLV_MIN_FW:
+			version->min_fw_build_nn = tlv->val[0];
+			version->min_fw_build_cw = tlv->val[1];
+			version->min_fw_build_yy = tlv->val[2];
+			break;
+		case INTEL_TLV_LIMITED_CCE:
+			version->limited_cce = tlv->val[0];
+			break;
+		case INTEL_TLV_SBE_TYPE:
+			version->sbe_type = tlv->val[0];
+			break;
+		case INTEL_TLV_OTP_BDADDR:
+			memcpy(&version->otp_bd_addr, tlv->val, tlv->len);
+			break;
+		default:
+			/* Ignore rest of information */
+			break;
+		}
+		/* consume the current tlv and move to next*/
+		skb_pull(skb, tlv->len + sizeof(*tlv));
+	}
+
+	kfree_skb(skb);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(btintel_read_version_tlv);
+
 /* ------- REGMAP IBT SUPPORT ------- */
 
 #define IBT_REG_MODE_8BIT  0x00
@@ -626,12 +768,10 @@ int btintel_read_boot_params(struct hci_dev *hdev,
 }
 EXPORT_SYMBOL_GPL(btintel_read_boot_params);
 
-int btintel_download_firmware(struct hci_dev *hdev, const struct firmware *fw,
-			      u32 *boot_param)
+static int btintel_sfi_rsa_header_secure_send(struct hci_dev *hdev,
+					      const struct firmware *fw)
 {
 	int err;
-	const u8 *fw_ptr;
-	u32 frag_len;
 
 	/* Start the firmware download transaction with the Init fragment
 	 * represented by the 128 bytes of CSS header.
@@ -660,8 +800,56 @@ int btintel_download_firmware(struct hci_dev *hdev, const struct firmware *fw,
 		goto done;
 	}
 
-	fw_ptr = fw->data + 644;
+done:
+	return err;
+}
+
+static int btintel_sfi_ecdsa_header_secure_send(struct hci_dev *hdev,
+						const struct firmware *fw)
+{
+	int err;
+
+	/* Start the firmware download transaction with the Init fragment
+	 * represented by the 128 bytes of CSS header.
+	 */
+	err = btintel_secure_send(hdev, 0x00, 128, fw->data + 644);
+	if (err < 0) {
+		bt_dev_err(hdev, "Failed to send firmware header (%d)", err);
+		return err;
+	}
+
+	/* Send the 96 bytes of public key information from the firmware
+	 * as the PKey fragment.
+	 */
+	err = btintel_secure_send(hdev, 0x03, 96, fw->data + 644 + 128);
+	if (err < 0) {
+		bt_dev_err(hdev, "Failed to send firmware pkey (%d)", err);
+		return err;
+	}
+
+	/* Send the 96 bytes of signature information from the firmware
+	 * as the Sign fragment
+	 */
+	err = btintel_secure_send(hdev, 0x02, 96, fw->data + 644 + 224);
+	if (err < 0) {
+		bt_dev_err(hdev, "Failed to send firmware signature (%d)",
+			   err);
+		return err;
+	}
+	return 0;
+}
+
+static int btintel_download_firmware_payload(struct hci_dev *hdev,
+					     const struct firmware *fw,
+					     u32 *boot_param, size_t offset)
+{
+	int err;
+	const u8 *fw_ptr;
+	u32 frag_len;
+
+	fw_ptr = fw->data + offset;
 	frag_len = 0;
+	err = -EINVAL;
 
 	while (fw_ptr - fw->data < fw->size) {
 		struct hci_command_hdr *cmd = (void *)(fw_ptr + frag_len);
@@ -707,8 +895,99 @@ int btintel_download_firmware(struct hci_dev *hdev, const struct firmware *fw,
 done:
 	return err;
 }
+
+int btintel_download_firmware(struct hci_dev *hdev,
+			      const struct firmware *fw,
+			      u32 *boot_param)
+{
+	int err;
+
+	err = btintel_sfi_rsa_header_secure_send(hdev, fw);
+	if (err)
+		return err;
+
+	return btintel_download_firmware_payload(hdev, fw, boot_param,
+						 RSA_HEADER_LEN);
+}
 EXPORT_SYMBOL_GPL(btintel_download_firmware);
 
+int btintel_download_firmware_newgen(struct hci_dev *hdev,
+				     const struct firmware *fw, u32 *boot_param,
+				     u8 hw_variant, u8 sbe_type)
+{
+	int err;
+	u32 css_header_ver;
+
+	/* iBT hardware variants 0x0b, 0x0c, 0x11, 0x12, 0x13, 0x14 support
+	 * only RSA secure boot engine. Hence, the corresponding sfi file will
+	 * have RSA header of 644 bytes followed by Command Buffer.
+	 *
+	 * iBT hardware variants 0x17, 0x18 onwards support both RSA and ECDSA
+	 * secure boot engine. As a result, the corresponding sfi file will
+	 * have RSA header of 644, ECDSA header of 320 bytes followed by
+	 * Command Buffer.
+	 *
+	 * CSS Header byte positions 0x08 to 0x0B represent the CSS Header
+	 * version: RSA(0x00010000) , ECDSA (0x00020000)
+	 */
+	css_header_ver = get_unaligned_le32(fw->data + CSS_HEADER_OFFSET);
+	if (css_header_ver != 0x00010000) {
+		bt_dev_err(hdev, "Invalid CSS Header version");
+		return -EINVAL;
+	}
+
+	if (hw_variant <= 0x14) {
+		if (sbe_type != 0x00) {
+			bt_dev_err(hdev, "Invalid SBE type for hardware variant (%d)",
+				   hw_variant);
+			return -EINVAL;
+		}
+
+		err = btintel_sfi_rsa_header_secure_send(hdev, fw);
+		if (err)
+			return err;
+
+		err = btintel_download_firmware_payload(hdev, fw, boot_param, RSA_HEADER_LEN);
+		if (err)
+			return err;
+	} else if (hw_variant >= 0x17) {
+		/* Check if CSS header for ECDSA follows the RSA header */
+		if (fw->data[ECDSA_OFFSET] != 0x06)
+			return -EINVAL;
+
+		/* Check if the CSS Header version is ECDSA(0x00020000) */
+		css_header_ver = get_unaligned_le32(fw->data + ECDSA_OFFSET + CSS_HEADER_OFFSET);
+		if (css_header_ver != 0x00020000) {
+			bt_dev_err(hdev, "Invalid CSS Header version");
+			return -EINVAL;
+		}
+
+		if (sbe_type == 0x00) {
+			err = btintel_sfi_rsa_header_secure_send(hdev, fw);
+			if (err)
+				return err;
+
+			err = btintel_download_firmware_payload(hdev, fw,
+								boot_param,
+								RSA_HEADER_LEN + ECDSA_HEADER_LEN);
+			if (err)
+				return err;
+		} else if (sbe_type == 0x01) {
+			err = btintel_sfi_ecdsa_header_secure_send(hdev, fw);
+			if (err)
+				return err;
+
+			err = btintel_download_firmware_payload(hdev, fw,
+								boot_param,
+								RSA_HEADER_LEN + ECDSA_HEADER_LEN);
+			if (err)
+				return err;
+		}
+	}
+	return 0;
+}
+EXPORT_SYMBOL_GPL(btintel_download_firmware_newgen);
+
 void btintel_reset_to_bootloader(struct hci_dev *hdev)
 {
 	struct intel_reset params;
diff --git a/drivers/bluetooth/btintel.h b/drivers/bluetooth/btintel.h
index 08e20606fb58..09346ae308eb 100644
--- a/drivers/bluetooth/btintel.h
+++ b/drivers/bluetooth/btintel.h
@@ -6,6 +6,72 @@
  *  Copyright (C) 2015  Intel Corporation
  */
 
+/* List of tlv type */
+enum {
+	INTEL_TLV_CNVI_TOP = 0x10,
+	INTEL_TLV_CNVR_TOP,
+	INTEL_TLV_CNVI_BT,
+	INTEL_TLV_CNVR_BT,
+	INTEL_TLV_CNVI_OTP,
+	INTEL_TLV_CNVR_OTP,
+	INTEL_TLV_DEV_REV_ID,
+	INTEL_TLV_USB_VENDOR_ID,
+	INTEL_TLV_USB_PRODUCT_ID,
+	INTEL_TLV_PCIE_VENDOR_ID,
+	INTEL_TLV_PCIE_DEVICE_ID,
+	INTEL_TLV_PCIE_SUBSYSTEM_ID,
+	INTEL_TLV_IMAGE_TYPE,
+	INTEL_TLV_TIME_STAMP,
+	INTEL_TLV_BUILD_TYPE,
+	INTEL_TLV_BUILD_NUM,
+	INTEL_TLV_FW_BUILD_PRODUCT,
+	INTEL_TLV_FW_BUILD_HW,
+	INTEL_TLV_FW_STEP,
+	INTEL_TLV_BT_SPEC,
+	INTEL_TLV_MFG_NAME,
+	INTEL_TLV_HCI_REV,
+	INTEL_TLV_LMP_SUBVER,
+	INTEL_TLV_OTP_PATCH_VER,
+	INTEL_TLV_SECURE_BOOT,
+	INTEL_TLV_KEY_FROM_HDR,
+	INTEL_TLV_OTP_LOCK,
+	INTEL_TLV_API_LOCK,
+	INTEL_TLV_DEBUG_LOCK,
+	INTEL_TLV_MIN_FW,
+	INTEL_TLV_LIMITED_CCE,
+	INTEL_TLV_SBE_TYPE,
+	INTEL_TLV_OTP_BDADDR,
+	INTEL_TLV_UNLOCKED_STATE
+};
+
+struct intel_tlv {
+	u8 type;
+	u8 len;
+	u8 val[0];
+} __packed;
+
+struct intel_version_tlv {
+	u32	cnvi_top;
+	u32	cnvr_top;
+	u32	cnvi_bt;
+	u32	cnvr_bt;
+	u16	dev_rev_id;
+	u8	img_type;
+	u16	timestamp;
+	u8	build_type;
+	u32	build_num;
+	u8	secure_boot;
+	u8	otp_lock;
+	u8	api_lock;
+	u8	debug_lock;
+	u8	min_fw_build_nn;
+	u8	min_fw_build_cw;
+	u8	min_fw_build_yy;
+	u8	limited_cce;
+	u8	sbe_type;
+	bdaddr_t otp_bd_addr;
+};
+
 struct intel_version {
 	u8 status;
 	u8 hw_platform;
@@ -77,12 +143,14 @@ int btintel_set_diag_mfg(struct hci_dev *hdev, bool enable);
 void btintel_hw_error(struct hci_dev *hdev, u8 code);
 
 void btintel_version_info(struct hci_dev *hdev, struct intel_version *ver);
+void btintel_version_info_tlv(struct hci_dev *hdev, struct intel_version_tlv *version);
 int btintel_secure_send(struct hci_dev *hdev, u8 fragment_type, u32 plen,
 			const void *param);
 int btintel_load_ddc_config(struct hci_dev *hdev, const char *ddc_name);
 int btintel_set_event_mask(struct hci_dev *hdev, bool debug);
 int btintel_set_event_mask_mfg(struct hci_dev *hdev, bool debug);
 int btintel_read_version(struct hci_dev *hdev, struct intel_version *ver);
+int btintel_read_version_tlv(struct hci_dev *hdev, struct intel_version_tlv *ver);
 
 struct regmap *btintel_regmap_init(struct hci_dev *hdev, u16 opcode_read,
 				   u16 opcode_write);
@@ -91,6 +159,10 @@ int btintel_read_boot_params(struct hci_dev *hdev,
 			     struct intel_boot_params *params);
 int btintel_download_firmware(struct hci_dev *dev, const struct firmware *fw,
 			      u32 *boot_param);
+int btintel_download_firmware_newgen(struct hci_dev *hdev,
+				     const struct firmware *fw,
+				     u32 *boot_param, u8 hw_variant,
+				     u8 sbe_type);
 void btintel_reset_to_bootloader(struct hci_dev *hdev);
 int btintel_read_debug_features(struct hci_dev *hdev,
 				struct intel_debug_features *features);
@@ -137,6 +209,11 @@ static inline void btintel_version_info(struct hci_dev *hdev,
 {
 }
 
+static inline void btintel_version_info_tlv(struct hci_dev *hdev,
+					    struct intel_version_tlv *version)
+{
+}
+
 static inline int btintel_secure_send(struct hci_dev *hdev, u8 fragment_type,
 				      u32 plen, const void *param)
 {
@@ -165,6 +242,12 @@ static inline int btintel_read_version(struct hci_dev *hdev,
 	return -EOPNOTSUPP;
 }
 
+static inline int btintel_read_version_tlv(struct hci_dev *hdev,
+					   struct intel_version_tlv *ver)
+{
+	return -EOPNOTSUPP;
+}
+
 static inline struct regmap *btintel_regmap_init(struct hci_dev *hdev,
 						 u16 opcode_read,
 						 u16 opcode_write)
@@ -191,6 +274,14 @@ static inline int btintel_download_firmware(struct hci_dev *dev,
 	return -EOPNOTSUPP;
 }
 
+static inline int btintel_download_firmware_newgen(struct hci_dev *hdev,
+						   const struct firmware *fw,
+						   u32 *boot_param,
+						   u8 hw_variant, u8 sbe_type)
+{
+	return -EOPNOTSUPP;
+}
+
 static inline void btintel_reset_to_bootloader(struct hci_dev *hdev)
 {
 }
diff --git a/drivers/bluetooth/btmrvl_sdio.c b/drivers/bluetooth/btmrvl_sdio.c
index d15fd5be0216..33d58b30c5ac 100644
--- a/drivers/bluetooth/btmrvl_sdio.c
+++ b/drivers/bluetooth/btmrvl_sdio.c
@@ -215,30 +215,7 @@ static const struct btmrvl_sdio_card_reg btmrvl_reg_8897 = {
 	.fw_dump_end = 0xea,
 };
 
-static const struct btmrvl_sdio_card_reg btmrvl_reg_8977 = {
-	.cfg = 0x00,
-	.host_int_mask = 0x08,
-	.host_intstatus = 0x0c,
-	.card_status = 0x5c,
-	.sq_read_base_addr_a0 = 0xf8,
-	.sq_read_base_addr_a1 = 0xf9,
-	.card_revision = 0xc8,
-	.card_fw_status0 = 0xe8,
-	.card_fw_status1 = 0xe9,
-	.card_rx_len = 0xea,
-	.card_rx_unit = 0xeb,
-	.io_port_0 = 0xe4,
-	.io_port_1 = 0xe5,
-	.io_port_2 = 0xe6,
-	.int_read_to_clear = true,
-	.host_int_rsr = 0x04,
-	.card_misc_cfg = 0xD8,
-	.fw_dump_ctrl = 0xf0,
-	.fw_dump_start = 0xf1,
-	.fw_dump_end = 0xf8,
-};
-
-static const struct btmrvl_sdio_card_reg btmrvl_reg_8987 = {
+static const struct btmrvl_sdio_card_reg btmrvl_reg_89xx = {
 	.cfg = 0x00,
 	.host_int_mask = 0x08,
 	.host_intstatus = 0x0c,
@@ -261,29 +238,6 @@ static const struct btmrvl_sdio_card_reg btmrvl_reg_8987 = {
 	.fw_dump_end = 0xf8,
 };
 
-static const struct btmrvl_sdio_card_reg btmrvl_reg_8997 = {
-	.cfg = 0x00,
-	.host_int_mask = 0x08,
-	.host_intstatus = 0x0c,
-	.card_status = 0x5c,
-	.sq_read_base_addr_a0 = 0xf8,
-	.sq_read_base_addr_a1 = 0xf9,
-	.card_revision = 0xc8,
-	.card_fw_status0 = 0xe8,
-	.card_fw_status1 = 0xe9,
-	.card_rx_len = 0xea,
-	.card_rx_unit = 0xeb,
-	.io_port_0 = 0xe4,
-	.io_port_1 = 0xe5,
-	.io_port_2 = 0xe6,
-	.int_read_to_clear = true,
-	.host_int_rsr = 0x04,
-	.card_misc_cfg = 0xD8,
-	.fw_dump_ctrl = 0xf0,
-	.fw_dump_start = 0xf1,
-	.fw_dump_end = 0xf8,
-};
-
 static const struct btmrvl_sdio_device btmrvl_sdio_sd8688 = {
 	.helper		= "mrvl/sd8688_helper.bin",
 	.firmware	= "mrvl/sd8688.bin",
@@ -332,7 +286,7 @@ static const struct btmrvl_sdio_device btmrvl_sdio_sd8897 = {
 static const struct btmrvl_sdio_device btmrvl_sdio_sd8977 = {
 	.helper         = NULL,
 	.firmware       = "mrvl/sdsd8977_combo_v2.bin",
-	.reg            = &btmrvl_reg_8977,
+	.reg            = &btmrvl_reg_89xx,
 	.support_pscan_win_report = true,
 	.sd_blksz_fw_dl = 256,
 	.supports_fw_dump = true,
@@ -341,7 +295,7 @@ static const struct btmrvl_sdio_device btmrvl_sdio_sd8977 = {
 static const struct btmrvl_sdio_device btmrvl_sdio_sd8987 = {
 	.helper		= NULL,
 	.firmware	= "mrvl/sd8987_uapsta.bin",
-	.reg		= &btmrvl_reg_8987,
+	.reg		= &btmrvl_reg_89xx,
 	.support_pscan_win_report = true,
 	.sd_blksz_fw_dl	= 256,
 	.supports_fw_dump = true,
@@ -350,7 +304,7 @@ static const struct btmrvl_sdio_device btmrvl_sdio_sd8987 = {
 static const struct btmrvl_sdio_device btmrvl_sdio_sd8997 = {
 	.helper         = NULL,
 	.firmware       = "mrvl/sdsd8997_combo_v4.bin",
-	.reg            = &btmrvl_reg_8997,
+	.reg            = &btmrvl_reg_89xx,
 	.support_pscan_win_report = true,
 	.sd_blksz_fw_dl = 256,
 	.supports_fw_dump = true,
diff --git a/drivers/bluetooth/btmtksdio.c b/drivers/bluetooth/btmtksdio.c
index c7ab7a23bd67..ba45c59bd9f3 100644
--- a/drivers/bluetooth/btmtksdio.c
+++ b/drivers/bluetooth/btmtksdio.c
@@ -496,7 +496,7 @@ static void btmtksdio_interrupt(struct sdio_func *func)
 	sdio_claim_host(bdev->func);
 
 	/* Disable interrupt */
-	sdio_writel(func, C_INT_EN_CLR, MTK_REG_CHLPCR, 0);
+	sdio_writel(func, C_INT_EN_CLR, MTK_REG_CHLPCR, NULL);
 
 	int_status = sdio_readl(func, MTK_REG_CHISR, NULL);
 
@@ -530,7 +530,7 @@ static void btmtksdio_interrupt(struct sdio_func *func)
 	}
 
 	/* Enable interrupt */
-	sdio_writel(func, C_INT_EN_SET, MTK_REG_CHLPCR, 0);
+	sdio_writel(func, C_INT_EN_SET, MTK_REG_CHLPCR, NULL);
 
 	pm_runtime_mark_last_busy(bdev->dev);
 	pm_runtime_put_autosuspend(bdev->dev);
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index 8d2608ddfd08..1005b6e8ff74 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -59,6 +59,7 @@ static struct usb_driver btusb_driver;
 #define BTUSB_MEDIATEK		0x200000
 #define BTUSB_WIDEBAND_SPEECH	0x400000
 #define BTUSB_VALID_LE_STATES   0x800000
+#define BTUSB_QCA_WCN6855	0x1000000
 
 static const struct usb_device_id btusb_table[] = {
 	/* Generic Bluetooth USB device */
@@ -254,24 +255,46 @@ static const struct usb_device_id blacklist_table[] = {
 	{ USB_DEVICE(0x0489, 0xe03c), .driver_info = BTUSB_ATH3012 },
 
 	/* QCA ROME chipset */
-	{ USB_DEVICE(0x0cf3, 0x535b), .driver_info = BTUSB_QCA_ROME },
-	{ USB_DEVICE(0x0cf3, 0xe007), .driver_info = BTUSB_QCA_ROME },
-	{ USB_DEVICE(0x0cf3, 0xe009), .driver_info = BTUSB_QCA_ROME },
-	{ USB_DEVICE(0x0cf3, 0xe010), .driver_info = BTUSB_QCA_ROME },
-	{ USB_DEVICE(0x0cf3, 0xe300), .driver_info = BTUSB_QCA_ROME },
-	{ USB_DEVICE(0x0cf3, 0xe301), .driver_info = BTUSB_QCA_ROME },
-	{ USB_DEVICE(0x0cf3, 0xe360), .driver_info = BTUSB_QCA_ROME },
-	{ USB_DEVICE(0x0489, 0xe092), .driver_info = BTUSB_QCA_ROME },
-	{ USB_DEVICE(0x0489, 0xe09f), .driver_info = BTUSB_QCA_ROME },
-	{ USB_DEVICE(0x0489, 0xe0a2), .driver_info = BTUSB_QCA_ROME },
-	{ USB_DEVICE(0x04ca, 0x3011), .driver_info = BTUSB_QCA_ROME },
-	{ USB_DEVICE(0x04ca, 0x3015), .driver_info = BTUSB_QCA_ROME },
-	{ USB_DEVICE(0x04ca, 0x3016), .driver_info = BTUSB_QCA_ROME },
-	{ USB_DEVICE(0x04ca, 0x301a), .driver_info = BTUSB_QCA_ROME },
-	{ USB_DEVICE(0x04ca, 0x3021), .driver_info = BTUSB_QCA_ROME },
-	{ USB_DEVICE(0x13d3, 0x3491), .driver_info = BTUSB_QCA_ROME },
-	{ USB_DEVICE(0x13d3, 0x3496), .driver_info = BTUSB_QCA_ROME },
-	{ USB_DEVICE(0x13d3, 0x3501), .driver_info = BTUSB_QCA_ROME },
+	{ USB_DEVICE(0x0cf3, 0x535b), .driver_info = BTUSB_QCA_ROME |
+						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x0cf3, 0xe007), .driver_info = BTUSB_QCA_ROME |
+						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x0cf3, 0xe009), .driver_info = BTUSB_QCA_ROME |
+						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x0cf3, 0xe010), .driver_info = BTUSB_QCA_ROME |
+						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x0cf3, 0xe300), .driver_info = BTUSB_QCA_ROME |
+						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x0cf3, 0xe301), .driver_info = BTUSB_QCA_ROME |
+						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x0cf3, 0xe360), .driver_info = BTUSB_QCA_ROME |
+						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x0489, 0xe092), .driver_info = BTUSB_QCA_ROME |
+						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x0489, 0xe09f), .driver_info = BTUSB_QCA_ROME |
+						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x0489, 0xe0a2), .driver_info = BTUSB_QCA_ROME |
+						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x04ca, 0x3011), .driver_info = BTUSB_QCA_ROME |
+						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x04ca, 0x3015), .driver_info = BTUSB_QCA_ROME |
+						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x04ca, 0x3016), .driver_info = BTUSB_QCA_ROME |
+						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x04ca, 0x301a), .driver_info = BTUSB_QCA_ROME |
+						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x04ca, 0x3021), .driver_info = BTUSB_QCA_ROME |
+						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x13d3, 0x3491), .driver_info = BTUSB_QCA_ROME |
+						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x13d3, 0x3496), .driver_info = BTUSB_QCA_ROME |
+						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x13d3, 0x3501), .driver_info = BTUSB_QCA_ROME |
+						     BTUSB_WIDEBAND_SPEECH },
+
+	/* QCA WCN6855 chipset */
+	{ USB_DEVICE(0x0cf3, 0xe600), .driver_info = BTUSB_QCA_WCN6855 |
+						     BTUSB_WIDEBAND_SPEECH },
 
 	/* Broadcom BCM2035 */
 	{ USB_DEVICE(0x0a5c, 0x2009), .driver_info = BTUSB_BCM92035 },
@@ -2338,10 +2361,10 @@ static bool btusb_setup_intel_new_get_fw_name(struct intel_version *ver,
 
 static int btusb_intel_download_firmware(struct hci_dev *hdev,
 					 struct intel_version *ver,
-					 struct intel_boot_params *params)
+					 struct intel_boot_params *params,
+					 u32 *boot_param)
 {
 	const struct firmware *fw;
-	u32 boot_param;
 	char fwname[64];
 	int err;
 	struct btusb_data *data = hci_get_drvdata(hdev);
@@ -2479,7 +2502,7 @@ static int btusb_intel_download_firmware(struct hci_dev *hdev,
 	set_bit(BTUSB_DOWNLOADING, &data->flags);
 
 	/* Start firmware downloading and get boot parameter */
-	err = btintel_download_firmware(hdev, fw, &boot_param);
+	err = btintel_download_firmware(hdev, fw, boot_param);
 	if (err < 0) {
 		/* When FW download fails, send Intel Reset to retry
 		 * FW download.
@@ -2561,7 +2584,7 @@ static int btusb_setup_intel_new(struct hci_dev *hdev)
 		return err;
 	}
 
-	err = btusb_intel_download_firmware(hdev, &ver, &params);
+	err = btusb_intel_download_firmware(hdev, &ver, &params, &boot_param);
 	if (err)
 		return err;
 
@@ -2896,6 +2919,7 @@ static int btusb_mtk_submit_wmt_recv_urb(struct hci_dev *hdev)
 	buf = kmalloc(size, GFP_KERNEL);
 	if (!buf) {
 		kfree(dr);
+		usb_free_urb(urb);
 		return -ENOMEM;
 	}
 
@@ -3390,6 +3414,27 @@ static int btusb_set_bdaddr_ath3012(struct hci_dev *hdev,
 	return 0;
 }
 
+static int btusb_set_bdaddr_wcn6855(struct hci_dev *hdev,
+				const bdaddr_t *bdaddr)
+{
+	struct sk_buff *skb;
+	u8 buf[6];
+	long ret;
+
+	memcpy(buf, bdaddr, sizeof(bdaddr_t));
+
+	skb = __hci_cmd_sync_ev(hdev, 0xfc14, sizeof(buf), buf,
+				HCI_EV_CMD_COMPLETE, HCI_INIT_TIMEOUT);
+	if (IS_ERR(skb)) {
+		ret = PTR_ERR(skb);
+		bt_dev_err(hdev, "Change address command failed (%ld)", ret);
+		return ret;
+	}
+	kfree_skb(skb);
+
+	return 0;
+}
+
 #define QCA_DFU_PACKET_LEN	4096
 
 #define QCA_GET_TARGET_VERSION	0x09
@@ -3409,7 +3454,8 @@ struct qca_version {
 } __packed;
 
 struct qca_rampatch_version {
-	__le16	rom_version;
+	__le16	rom_version_high;
+	__le16  rom_version_low;
 	__le16	patch_version;
 } __packed;
 
@@ -3421,12 +3467,14 @@ struct qca_device_info {
 };
 
 static const struct qca_device_info qca_devices_table[] = {
-	{ 0x00000100, 20, 4, 10 }, /* Rome 1.0 */
-	{ 0x00000101, 20, 4, 10 }, /* Rome 1.1 */
-	{ 0x00000200, 28, 4, 18 }, /* Rome 2.0 */
-	{ 0x00000201, 28, 4, 18 }, /* Rome 2.1 */
-	{ 0x00000300, 28, 4, 18 }, /* Rome 3.0 */
-	{ 0x00000302, 28, 4, 18 }, /* Rome 3.2 */
+	{ 0x00000100, 20, 4,  8 }, /* Rome 1.0 */
+	{ 0x00000101, 20, 4,  8 }, /* Rome 1.1 */
+	{ 0x00000200, 28, 4, 16 }, /* Rome 2.0 */
+	{ 0x00000201, 28, 4, 16 }, /* Rome 2.1 */
+	{ 0x00000300, 28, 4, 16 }, /* Rome 3.0 */
+	{ 0x00000302, 28, 4, 16 }, /* Rome 3.2 */
+	{ 0x00130100, 40, 4, 16 }, /* WCN6855 1.0 */
+	{ 0x00130200, 40, 4, 16 }, /* WCN6855 2.0 */
 };
 
 static int btusb_qca_send_vendor_req(struct usb_device *udev, u8 request,
@@ -3528,8 +3576,8 @@ static int btusb_setup_qca_load_rampatch(struct hci_dev *hdev,
 {
 	struct qca_rampatch_version *rver;
 	const struct firmware *fw;
-	u32 ver_rom, ver_patch;
-	u16 rver_rom, rver_patch;
+	u32 ver_rom, ver_patch, rver_rom;
+	u16 rver_rom_low, rver_rom_high, rver_patch;
 	char fwname[64];
 	int err;
 
@@ -3548,9 +3596,16 @@ static int btusb_setup_qca_load_rampatch(struct hci_dev *hdev,
 	bt_dev_info(hdev, "using rampatch file: %s", fwname);
 
 	rver = (struct qca_rampatch_version *)(fw->data + info->ver_offset);
-	rver_rom = le16_to_cpu(rver->rom_version);
+	rver_rom_low = le16_to_cpu(rver->rom_version_low);
 	rver_patch = le16_to_cpu(rver->patch_version);
 
+	if (ver_rom & ~0xffffU) {
+		rver_rom_high = le16_to_cpu(rver->rom_version_high);
+		rver_rom = le32_to_cpu(rver_rom_high << 16 | rver_rom_low);
+	} else {
+		rver_rom = rver_rom_low;
+	}
+
 	bt_dev_info(hdev, "QCA: patch rome 0x%x build 0x%x, "
 		    "firmware rome 0x%x build 0x%x",
 		    rver_rom, rver_patch, ver_rom, ver_patch);
@@ -3624,9 +3679,6 @@ static int btusb_setup_qca(struct hci_dev *hdev)
 		return err;
 
 	ver_rom = le32_to_cpu(ver.rom_version);
-	/* Don't care about high ROM versions */
-	if (ver_rom & ~0xffffU)
-		return 0;
 
 	for (i = 0; i < ARRAY_SIZE(qca_devices_table); i++) {
 		if (ver_rom == qca_devices_table[i].rom_version)
@@ -4062,6 +4114,13 @@ static int btusb_probe(struct usb_interface *intf,
 		btusb_check_needs_reset_resume(intf);
 	}
 
+	if (id->driver_info & BTUSB_QCA_WCN6855) {
+		data->setup_on_usb = btusb_setup_qca;
+		hdev->set_bdaddr = btusb_set_bdaddr_wcn6855;
+		hdev->cmd_timeout = btusb_qca_cmd_timeout;
+		set_bit(HCI_QUIRK_SIMULTANEOUS_DISCOVERY, &hdev->quirks);
+	}
+
 	if (id->driver_info & BTUSB_AMP) {
 		/* AMP controllers do not support SCO packets */
 		data->isoc = NULL;
diff --git a/drivers/bluetooth/hci_h5.c b/drivers/bluetooth/hci_h5.c
index e41854e0d79a..981d96cc7695 100644
--- a/drivers/bluetooth/hci_h5.c
+++ b/drivers/bluetooth/hci_h5.c
@@ -793,8 +793,6 @@ static int h5_serdev_probe(struct serdev_device *serdev)
 	if (!h5)
 		return -ENOMEM;
 
-	set_bit(HCI_UART_RESET_ON_INIT, &h5->serdev_hu.hdev_flags);
-
 	h5->hu = &h5->serdev_hu;
 	h5->serdev_hu.serdev = serdev;
 	serdev_device_set_drvdata(serdev, h5);
diff --git a/drivers/bluetooth/hci_intel.c b/drivers/bluetooth/hci_intel.c
index f1299da6eed8..b20a40fab83e 100644
--- a/drivers/bluetooth/hci_intel.c
+++ b/drivers/bluetooth/hci_intel.c
@@ -288,7 +288,7 @@ static irqreturn_t intel_irq(int irq, void *dev_id)
 
 static int intel_set_power(struct hci_uart *hu, bool powered)
 {
-	struct list_head *p;
+	struct intel_device *idev;
 	int err = -ENODEV;
 
 	if (!hu->tty->dev)
@@ -296,10 +296,7 @@ static int intel_set_power(struct hci_uart *hu, bool powered)
 
 	mutex_lock(&intel_device_list_lock);
 
-	list_for_each(p, &intel_device_list) {
-		struct intel_device *idev = list_entry(p, struct intel_device,
-						       list);
-
+	list_for_each_entry(idev, &intel_device_list, list) {
 		/* tty device and pdev device should share the same parent
 		 * which is the UART port.
 		 */
@@ -362,19 +359,16 @@ static int intel_set_power(struct hci_uart *hu, bool powered)
 
 static void intel_busy_work(struct work_struct *work)
 {
-	struct list_head *p;
 	struct intel_data *intel = container_of(work, struct intel_data,
 						busy_work);
+	struct intel_device *idev;
 
 	if (!intel->hu->tty->dev)
 		return;
 
 	/* Link is busy, delay the suspend */
 	mutex_lock(&intel_device_list_lock);
-	list_for_each(p, &intel_device_list) {
-		struct intel_device *idev = list_entry(p, struct intel_device,
-						       list);
-
+	list_for_each_entry(idev, &intel_device_list, list) {
 		if (intel->hu->tty->dev->parent == idev->pdev->dev.parent) {
 			pm_runtime_get(&idev->pdev->dev);
 			pm_runtime_mark_last_busy(&idev->pdev->dev);
@@ -533,7 +527,7 @@ static int intel_setup(struct hci_uart *hu)
 	struct sk_buff *skb;
 	struct intel_version ver;
 	struct intel_boot_params params;
-	struct list_head *p;
+	struct intel_device *idev;
 	const struct firmware *fw;
 	char fwname[64];
 	u32 boot_param;
@@ -693,14 +687,11 @@ static int intel_setup(struct hci_uart *hu)
 	case 0x0b:      /* SfP */
 	case 0x0c:      /* WsP */
 		snprintf(fwname, sizeof(fwname), "intel/ibt-%u-%u.sfi",
-			 le16_to_cpu(ver.hw_variant),
-			 le16_to_cpu(params.dev_revid));
+			 ver.hw_variant, le16_to_cpu(params.dev_revid));
 		break;
 	case 0x12:      /* ThP */
 		snprintf(fwname, sizeof(fwname), "intel/ibt-%u-%u-%u.sfi",
-			 le16_to_cpu(ver.hw_variant),
-			 le16_to_cpu(ver.hw_revision),
-			 le16_to_cpu(ver.fw_revision));
+			 ver.hw_variant, ver.hw_revision, ver.fw_revision);
 		break;
 	default:
 		bt_dev_err(hdev, "Unsupported Intel hardware variant (%u)",
@@ -722,14 +713,11 @@ static int intel_setup(struct hci_uart *hu)
 	case 0x0b:      /* SfP */
 	case 0x0c:      /* WsP */
 		snprintf(fwname, sizeof(fwname), "intel/ibt-%u-%u.ddc",
-			 le16_to_cpu(ver.hw_variant),
-			 le16_to_cpu(params.dev_revid));
+			 ver.hw_variant, le16_to_cpu(params.dev_revid));
 		break;
 	case 0x12:      /* ThP */
 		snprintf(fwname, sizeof(fwname), "intel/ibt-%u-%u-%u.ddc",
-			 le16_to_cpu(ver.hw_variant),
-			 le16_to_cpu(ver.hw_revision),
-			 le16_to_cpu(ver.fw_revision));
+			 ver.hw_variant, ver.hw_revision, ver.fw_revision);
 		break;
 	default:
 		bt_dev_err(hdev, "Unsupported Intel hardware variant (%u)",
@@ -839,13 +827,11 @@ done:
 	 * until further LPM TX notification.
 	 */
 	mutex_lock(&intel_device_list_lock);
-	list_for_each(p, &intel_device_list) {
-		struct intel_device *dev = list_entry(p, struct intel_device,
-						      list);
+	list_for_each_entry(idev, &intel_device_list, list) {
 		if (!hu->tty->dev)
 			break;
-		if (hu->tty->dev->parent == dev->pdev->dev.parent) {
-			if (device_may_wakeup(&dev->pdev->dev)) {
+		if (hu->tty->dev->parent == idev->pdev->dev.parent) {
+			if (device_may_wakeup(&idev->pdev->dev)) {
 				set_bit(STATE_LPM_ENABLED, &intel->flags);
 				set_bit(STATE_TX_ACTIVE, &intel->flags);
 			}
@@ -999,7 +985,7 @@ static int intel_recv(struct hci_uart *hu, const void *data, int count)
 static int intel_enqueue(struct hci_uart *hu, struct sk_buff *skb)
 {
 	struct intel_data *intel = hu->priv;
-	struct list_head *p;
+	struct intel_device *idev;
 
 	BT_DBG("hu %p skb %p", hu, skb);
 
@@ -1010,10 +996,7 @@ static int intel_enqueue(struct hci_uart *hu, struct sk_buff *skb)
 	 * completed before enqueuing any packet.
 	 */
 	mutex_lock(&intel_device_list_lock);
-	list_for_each(p, &intel_device_list) {
-		struct intel_device *idev = list_entry(p, struct intel_device,
-						       list);
-
+	list_for_each_entry(idev, &intel_device_list, list) {
 		if (hu->tty->dev->parent == idev->pdev->dev.parent) {
 			pm_runtime_get_sync(&idev->pdev->dev);
 			pm_runtime_mark_last_busy(&idev->pdev->dev);
@@ -1076,7 +1059,8 @@ static const struct hci_uart_proto intel_proto = {
 #ifdef CONFIG_ACPI
 static const struct acpi_device_id intel_acpi_match[] = {
 	{ "INT33E1", 0 },
-	{ },
+	{ "INT33E3", 0 },
+	{ }
 };
 MODULE_DEVICE_TABLE(acpi, intel_acpi_match);
 #endif
@@ -1138,9 +1122,9 @@ static const struct acpi_gpio_params reset_gpios = { 0, 0, false };
 static const struct acpi_gpio_params host_wake_gpios = { 1, 0, false };
 
 static const struct acpi_gpio_mapping acpi_hci_intel_gpios[] = {
-	{ "reset-gpios", &reset_gpios, 1 },
-	{ "host-wake-gpios", &host_wake_gpios, 1 },
-	{ },
+	{ "reset-gpios", &reset_gpios, 1, ACPI_GPIO_QUIRK_ONLY_GPIOIO },
+	{ "host-wake-gpios", &host_wake_gpios, 1, ACPI_GPIO_QUIRK_ONLY_GPIOIO },
+	{ }
 };
 
 static int intel_probe(struct platform_device *pdev)
diff --git a/drivers/bluetooth/hci_ldisc.c b/drivers/bluetooth/hci_ldisc.c
index 85a30fb9177b..f83d67eafc9f 100644
--- a/drivers/bluetooth/hci_ldisc.c
+++ b/drivers/bluetooth/hci_ldisc.c
@@ -538,6 +538,7 @@ static void hci_uart_tty_close(struct tty_struct *tty)
 		clear_bit(HCI_UART_PROTO_READY, &hu->flags);
 		percpu_up_write(&hu->proto_lock);
 
+		cancel_work_sync(&hu->init_ready);
 		cancel_work_sync(&hu->write_work);
 
 		if (hdev) {
diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c
index 20e1dedbc58c..244b8feba523 100644
--- a/drivers/bluetooth/hci_qca.c
+++ b/drivers/bluetooth/hci_qca.c
@@ -693,8 +693,6 @@ static int qca_close(struct hci_uart *hu)
 	destroy_workqueue(qca->workqueue);
 	qca->hu = NULL;
 
-	qca_power_shutdown(hu);
-
 	kfree_skb(qca->rx_skb);
 
 	hu->priv = NULL;
@@ -2007,8 +2005,7 @@ static int qca_serdev_probe(struct serdev_device *serdev)
 		err = hci_uart_register_device(&qcadev->serdev_hu, &qca_proto);
 		if (err) {
 			BT_ERR("Rome serdev registration failed");
-			if (qcadev->susclk)
-				clk_disable_unprepare(qcadev->susclk);
+			clk_disable_unprepare(qcadev->susclk);
 			return err;
 		}
 	}
@@ -2032,8 +2029,9 @@ static int qca_serdev_probe(struct serdev_device *serdev)
 static void qca_serdev_remove(struct serdev_device *serdev)
 {
 	struct qca_serdev *qcadev = serdev_device_get_drvdata(serdev);
+	struct qca_power *power = qcadev->bt_power;
 
-	if (qca_is_wcn399x(qcadev->btsoc_type))
+	if (qca_is_wcn399x(qcadev->btsoc_type) && power->vregs_on)
 		qca_power_shutdown(&qcadev->serdev_hu);
 	else if (qcadev->susclk)
 		clk_disable_unprepare(qcadev->susclk);
diff --git a/drivers/bluetooth/hci_serdev.c b/drivers/bluetooth/hci_serdev.c
index 7b233312e723..ef96ad06fa54 100644
--- a/drivers/bluetooth/hci_serdev.c
+++ b/drivers/bluetooth/hci_serdev.c
@@ -113,8 +113,22 @@ static int hci_uart_flush(struct hci_dev *hdev)
 /* Initialize device */
 static int hci_uart_open(struct hci_dev *hdev)
 {
+	struct hci_uart *hu = hci_get_drvdata(hdev);
+	int err;
+
 	BT_DBG("%s %p", hdev->name, hdev);
 
+	/* When Quirk HCI_QUIRK_NON_PERSISTENT_SETUP is set by
+	 * driver, BT SoC is completely turned OFF during
+	 * BT OFF. Upon next BT ON UART port should be opened.
+	 */
+	if (!test_bit(HCI_UART_PROTO_READY, &hu->flags)) {
+		err = serdev_device_open(hu->serdev);
+		if (err)
+			return err;
+		set_bit(HCI_UART_PROTO_READY, &hu->flags);
+	}
+
 	/* Undo clearing this from hci_uart_close() */
 	hdev->flush = hci_uart_flush;
 
@@ -124,11 +138,25 @@ static int hci_uart_open(struct hci_dev *hdev)
 /* Close device */
 static int hci_uart_close(struct hci_dev *hdev)
 {
+	struct hci_uart *hu = hci_get_drvdata(hdev);
+
 	BT_DBG("hdev %p", hdev);
 
+	if (!test_bit(HCI_UART_PROTO_READY, &hu->flags))
+		return 0;
+
 	hci_uart_flush(hdev);
 	hdev->flush = NULL;
 
+	/* When QUIRK HCI_QUIRK_NON_PERSISTENT_SETUP is set by driver,
+	 * BT SOC is completely powered OFF during BT OFF, holding port
+	 * open may drain the battery.
+	 */
+	if (test_bit(HCI_QUIRK_NON_PERSISTENT_SETUP, &hdev->quirks)) {
+		clear_bit(HCI_UART_PROTO_READY, &hu->flags);
+		serdev_device_close(hu->serdev);
+	}
+
 	return 0;
 }
 
@@ -354,7 +382,7 @@ void hci_uart_unregister_device(struct hci_uart *hu)
 {
 	struct hci_dev *hdev = hu->hdev;
 
-	clear_bit(HCI_UART_PROTO_READY, &hu->flags);
+	cancel_work_sync(&hu->init_ready);
 	if (test_bit(HCI_UART_REGISTERED, &hu->flags))
 		hci_unregister_dev(hdev);
 	hci_free_dev(hdev);
@@ -362,6 +390,10 @@ void hci_uart_unregister_device(struct hci_uart *hu)
 	cancel_work_sync(&hu->write_work);
 
 	hu->proto->close(hu);
-	serdev_device_close(hu->serdev);
+
+	if (test_bit(HCI_UART_PROTO_READY, &hu->flags)) {
+		clear_bit(HCI_UART_PROTO_READY, &hu->flags);
+		serdev_device_close(hu->serdev);
+	}
 }
 EXPORT_SYMBOL_GPL(hci_uart_unregister_device);
diff --git a/drivers/clk/bcm/Kconfig b/drivers/clk/bcm/Kconfig
index 784f12c72365..ec738f74a026 100644
--- a/drivers/clk/bcm/Kconfig
+++ b/drivers/clk/bcm/Kconfig
@@ -5,6 +5,7 @@ config CLK_BCM2711_DVP
 	depends on ARCH_BCM2835 ||COMPILE_TEST
 	depends on COMMON_CLK
 	default ARCH_BCM2835
+	select RESET_CONTROLLER
 	select RESET_SIMPLE
 	help
 	  Enable common clock framework support for the Broadcom BCM2711
diff --git a/drivers/clk/davinci/pll.c b/drivers/clk/davinci/pll.c
index 6c35e4bb7940..0d750433eb42 100644
--- a/drivers/clk/davinci/pll.c
+++ b/drivers/clk/davinci/pll.c
@@ -491,7 +491,7 @@ struct clk *davinci_pll_clk_register(struct device *dev,
 		parent_name = postdiv_name;
 	}
 
-	pllen = kzalloc(sizeof(*pllout), GFP_KERNEL);
+	pllen = kzalloc(sizeof(*pllen), GFP_KERNEL);
 	if (!pllen) {
 		ret = -ENOMEM;
 		goto err_unregister_postdiv;
diff --git a/drivers/clk/qcom/lpasscorecc-sc7180.c b/drivers/clk/qcom/lpasscorecc-sc7180.c
index d4c1864e1ee9..228d08f5d26f 100644
--- a/drivers/clk/qcom/lpasscorecc-sc7180.c
+++ b/drivers/clk/qcom/lpasscorecc-sc7180.c
@@ -420,17 +420,18 @@ static int lpass_core_sc7180_probe(struct platform_device *pdev)
 	pm_runtime_enable(&pdev->dev);
 	ret = pm_clk_create(&pdev->dev);
 	if (ret)
-		return ret;
+		goto disable_pm_runtime;
 
 	ret = pm_clk_add(&pdev->dev, "iface");
 	if (ret < 0) {
 		dev_err(&pdev->dev, "failed to acquire iface clock\n");
-		goto disable_pm_runtime;
+		goto destroy_pm_clk;
 	}
 
+	ret = -EINVAL;
 	clk_probe = of_device_get_match_data(&pdev->dev);
 	if (!clk_probe)
-		return -EINVAL;
+		goto destroy_pm_clk;
 
 	ret = clk_probe(pdev);
 	if (ret)
diff --git a/drivers/clk/rockchip/clk-rk3228.c b/drivers/clk/rockchip/clk-rk3228.c
index d7243c09cc84..47d6482dda9d 100644
--- a/drivers/clk/rockchip/clk-rk3228.c
+++ b/drivers/clk/rockchip/clk-rk3228.c
@@ -137,7 +137,7 @@ PNAME(mux_usb480m_p)		= { "usb480m_phy", "xin24m" };
 PNAME(mux_hdmiphy_p)		= { "hdmiphy_phy", "xin24m" };
 PNAME(mux_aclk_cpu_src_p)	= { "cpll_aclk_cpu", "gpll_aclk_cpu", "hdmiphy_aclk_cpu" };
 
-PNAME(mux_pll_src_4plls_p)	= { "cpll", "gpll", "hdmiphy" "usb480m" };
+PNAME(mux_pll_src_4plls_p)	= { "cpll", "gpll", "hdmiphy", "usb480m" };
 PNAME(mux_pll_src_3plls_p)	= { "cpll", "gpll", "hdmiphy" };
 PNAME(mux_pll_src_2plls_p)	= { "cpll", "gpll" };
 PNAME(mux_sclk_hdmi_cec_p)	= { "cpll", "gpll", "xin24m" };
diff --git a/drivers/clk/versatile/clk-impd1.c b/drivers/clk/versatile/clk-impd1.c
index ca798249544d..85c395df9c00 100644
--- a/drivers/clk/versatile/clk-impd1.c
+++ b/drivers/clk/versatile/clk-impd1.c
@@ -109,8 +109,10 @@ static int integrator_impd1_clk_probe(struct platform_device *pdev)
 
 	for_each_available_child_of_node(np, child) {
 		ret = integrator_impd1_clk_spawn(dev, np, child);
-		if (ret)
+		if (ret) {
+			of_node_put(child);
 			break;
+		}
 	}
 
 	return ret;
diff --git a/drivers/clocksource/timer-clint.c b/drivers/clocksource/timer-clint.c
index 8eeafa82c03d..d17367dee02c 100644
--- a/drivers/clocksource/timer-clint.c
+++ b/drivers/clocksource/timer-clint.c
@@ -19,6 +19,11 @@
 #include <linux/interrupt.h>
 #include <linux/of_irq.h>
 #include <linux/smp.h>
+#include <linux/timex.h>
+
+#ifndef CONFIG_RISCV_M_MODE
+#include <asm/clint.h>
+#endif
 
 #define CLINT_IPI_OFF		0
 #define CLINT_TIMER_CMP_OFF	0x4000
@@ -31,6 +36,10 @@ static u64 __iomem *clint_timer_val;
 static unsigned long clint_timer_freq;
 static unsigned int clint_timer_irq;
 
+#ifdef CONFIG_RISCV_M_MODE
+u64 __iomem *clint_time_val;
+#endif
+
 static void clint_send_ipi(const struct cpumask *target)
 {
 	unsigned int cpu;
@@ -184,6 +193,14 @@ static int __init clint_timer_init_dt(struct device_node *np)
 	clint_timer_val = base + CLINT_TIMER_VAL_OFF;
 	clint_timer_freq = riscv_timebase;
 
+#ifdef CONFIG_RISCV_M_MODE
+	/*
+	 * Yes, that's an odd naming scheme.  time_val is public, but hopefully
+	 * will die in favor of something cleaner.
+	 */
+	clint_time_val = clint_timer_val;
+#endif
+
 	pr_info("%pOFP: timer running at %ld Hz\n", np, clint_timer_freq);
 
 	rc = clocksource_register_hz(&clint_clocksource, clint_timer_freq);
diff --git a/drivers/counter/microchip-tcb-capture.c b/drivers/counter/microchip-tcb-capture.c
index f7b7743ddb94..b7b252c5addf 100644
--- a/drivers/counter/microchip-tcb-capture.c
+++ b/drivers/counter/microchip-tcb-capture.c
@@ -320,8 +320,8 @@ static int mchp_tc_probe(struct platform_device *pdev)
 	}
 
 	regmap = syscon_node_to_regmap(np->parent);
-	if (IS_ERR(priv->regmap))
-		return PTR_ERR(priv->regmap);
+	if (IS_ERR(regmap))
+		return PTR_ERR(regmap);
 
 	/* max. channels number is 2 when in QDEC mode */
 	priv->num_channels = of_property_count_u32_elems(np, "reg");
diff --git a/drivers/cpuidle/cpuidle-pseries.c b/drivers/cpuidle/cpuidle-pseries.c
index ff6d99e923a4..a2b5c6f60cf0 100644
--- a/drivers/cpuidle/cpuidle-pseries.c
+++ b/drivers/cpuidle/cpuidle-pseries.c
@@ -361,7 +361,10 @@ static void __init fixup_cede0_latency(void)
 	for (i = 0; i < nr_xcede_records; i++) {
 		struct xcede_latency_record *record = &payload->records[i];
 		u64 latency_tb = be64_to_cpu(record->latency_ticks);
-		u64 latency_us = tb_to_ns(latency_tb) / NSEC_PER_USEC;
+		u64 latency_us = DIV_ROUND_UP_ULL(tb_to_ns(latency_tb), NSEC_PER_USEC);
+
+		if (latency_us == 0)
+			pr_warn("cpuidle: xcede record %d has an unrealistic latency of 0us.\n", i);
 
 		if (latency_us < min_latency_us)
 			min_latency_us = latency_us;
@@ -378,10 +381,14 @@ static void __init fixup_cede0_latency(void)
 	 * Perform the fix-up.
 	 */
 	if (min_latency_us < dedicated_states[1].exit_latency) {
-		u64 cede0_latency = min_latency_us - 1;
+		/*
+		 * We set a minimum of 1us wakeup latency for cede0 to
+		 * distinguish it from snooze
+		 */
+		u64 cede0_latency = 1;
 
-		if (cede0_latency <= 0)
-			cede0_latency = min_latency_us;
+		if (min_latency_us > cede0_latency)
+			cede0_latency = min_latency_us - 1;
 
 		dedicated_states[1].exit_latency = cede0_latency;
 		dedicated_states[1].target_residency = 10 * (cede0_latency);
diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index 04becd70cc41..6c7e5621cf9a 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -138,6 +138,7 @@ static void enter_s2idle_proper(struct cpuidle_driver *drv,
 				struct cpuidle_device *dev, int index)
 {
 	ktime_t time_start, time_end;
+	struct cpuidle_state *target_state = &drv->states[index];
 
 	time_start = ns_to_ktime(local_clock());
 
@@ -153,8 +154,9 @@ static void enter_s2idle_proper(struct cpuidle_driver *drv,
 	 * suspended is generally unsafe.
 	 */
 	stop_critical_timings();
-	rcu_idle_enter();
-	drv->states[index].enter_s2idle(dev, drv, index);
+	if (!(target_state->flags & CPUIDLE_FLAG_RCU_IDLE))
+		rcu_idle_enter();
+	target_state->enter_s2idle(dev, drv, index);
 	if (WARN_ON_ONCE(!irqs_disabled()))
 		local_irq_disable();
 	/*
@@ -162,7 +164,8 @@ static void enter_s2idle_proper(struct cpuidle_driver *drv,
 	 * first CPU executing it calls functions containing RCU read-side
 	 * critical sections, so tell RCU about that.
 	 */
-	rcu_idle_exit();
+	if (!(target_state->flags & CPUIDLE_FLAG_RCU_IDLE))
+		rcu_idle_exit();
 	tick_unfreeze();
 	start_critical_timings();
 
@@ -239,9 +242,11 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
 	time_start = ns_to_ktime(local_clock());
 
 	stop_critical_timings();
-	rcu_idle_enter();
+	if (!(target_state->flags & CPUIDLE_FLAG_RCU_IDLE))
+		rcu_idle_enter();
 	entered_state = target_state->enter(dev, drv, index);
-	rcu_idle_exit();
+	if (!(target_state->flags & CPUIDLE_FLAG_RCU_IDLE))
+		rcu_idle_exit();
 	start_critical_timings();
 
 	sched_clock_idle_wakeup_event();
diff --git a/drivers/dax/device.c b/drivers/dax/device.c
index 4c0af2eb7e19..1e89513f3c59 100644
--- a/drivers/dax/device.c
+++ b/drivers/dax/device.c
@@ -429,7 +429,7 @@ int dev_dax_probe(struct device *dev)
 		return -EBUSY;
 	}
 
-	dev_dax->pgmap.type = MEMORY_DEVICE_DEVDAX;
+	dev_dax->pgmap.type = MEMORY_DEVICE_GENERIC;
 	addr = devm_memremap_pages(dev, &dev_dax->pgmap);
 	if (IS_ERR(addr))
 		return PTR_ERR(addr);
diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index 32642634c1bb..e84070b55463 100644
--- a/drivers/dax/super.c
+++ b/drivers/dax/super.c
@@ -85,6 +85,12 @@ bool __generic_fsdax_supported(struct dax_device *dax_dev,
 		return false;
 	}
 
+	if (!dax_dev) {
+		pr_debug("%s: error: dax unsupported by block device\n",
+				bdevname(bdev, buf));
+		return false;
+	}
+
 	err = bdev_dax_pgoff(bdev, start, PAGE_SIZE, &pgoff);
 	if (err) {
 		pr_info("%s: error: unaligned partition for dax\n",
@@ -100,12 +106,6 @@ bool __generic_fsdax_supported(struct dax_device *dax_dev,
 		return false;
 	}
 
-	if (!dax_dev && !bdev_dax_supported(bdev, blocksize)) {
-		pr_debug("%s: error: dax unsupported by block device\n",
-				bdevname(bdev, buf));
-		return false;
-	}
-
 	id = dax_read_lock();
 	len = dax_direct_access(dax_dev, pgoff, 1, &kaddr, &pfn);
 	len2 = dax_direct_access(dax_dev, pgoff_end, 1, &end_kaddr, &end_pfn);
@@ -325,11 +325,15 @@ EXPORT_SYMBOL_GPL(dax_direct_access);
 bool dax_supported(struct dax_device *dax_dev, struct block_device *bdev,
 		int blocksize, sector_t start, sector_t len)
 {
+	if (!dax_dev)
+		return false;
+
 	if (!dax_alive(dax_dev))
 		return false;
 
 	return dax_dev->ops->dax_supported(dax_dev, bdev, blocksize, start, len);
 }
+EXPORT_SYMBOL_GPL(dax_supported);
 
 size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
 		size_t bytes, struct iov_iter *i)
diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c
index 1699a8e309ef..58564d82a3a2 100644
--- a/drivers/dma-buf/dma-buf.c
+++ b/drivers/dma-buf/dma-buf.c
@@ -316,9 +316,9 @@ out:
  * name of the dma-buf if the same piece of memory is used for multiple
  * purpose between different devices.
  *
- * @dmabuf [in]     dmabuf buffer that will be renamed.
- * @buf:   [in]     A piece of userspace memory that contains the name of
- *                  the dma-buf.
+ * @dmabuf: [in]     dmabuf buffer that will be renamed.
+ * @buf:    [in]     A piece of userspace memory that contains the name of
+ *                   the dma-buf.
  *
  * Returns 0 on success. If the dma-buf buffer is already attached to
  * devices, return -EBUSY.
diff --git a/drivers/dma-buf/dma-fence-chain.c b/drivers/dma-buf/dma-fence-chain.c
index 3d123502ff12..7d129e68ac70 100644
--- a/drivers/dma-buf/dma-fence-chain.c
+++ b/drivers/dma-buf/dma-fence-chain.c
@@ -222,6 +222,7 @@ EXPORT_SYMBOL(dma_fence_chain_ops);
  * @chain: the chain node to initialize
  * @prev: the previous fence
  * @fence: the current fence
+ * @seqno: the sequence number to use for the fence chain
  *
  * Initialize a new chain node and either start a new chain or add the node to
  * the existing chain of the previous fence.
diff --git a/drivers/edac/ghes_edac.c b/drivers/edac/ghes_edac.c
index 54ebc8afc6b1..94d1e3165052 100644
--- a/drivers/edac/ghes_edac.c
+++ b/drivers/edac/ghes_edac.c
@@ -508,6 +508,7 @@ int ghes_edac_register(struct ghes *ghes, struct device *dev)
 		if (!force_load && idx < 0)
 			return -ENODEV;
 	} else {
+		force_load = true;
 		idx = 0;
 	}
 
@@ -629,9 +630,13 @@ void ghes_edac_unregister(struct ghes *ghes)
 	struct mem_ctl_info *mci;
 	unsigned long flags;
 
+	if (!force_load)
+		return;
+
 	mutex_lock(&ghes_reg_mutex);
 
 	system_scanned = false;
+	memset(&ghes_hw, 0, sizeof(struct ghes_hw_desc));
 
 	if (!refcount_dec_and_test(&ghes_refcount))
 		goto unlock;
diff --git a/drivers/firmware/efi/efibc.c b/drivers/firmware/efi/efibc.c
index 35dccc88ac0a..15a47539dc56 100644
--- a/drivers/firmware/efi/efibc.c
+++ b/drivers/firmware/efi/efibc.c
@@ -84,7 +84,7 @@ static int __init efibc_init(void)
 {
 	int ret;
 
-	if (!efi_enabled(EFI_RUNTIME_SERVICES))
+	if (!efivars_kobject() || !efivar_supports_writes())
 		return -ENODEV;
 
 	ret = register_reboot_notifier(&efibc_reboot_notifier);
diff --git a/drivers/firmware/efi/embedded-firmware.c b/drivers/firmware/efi/embedded-firmware.c
index e97a9c9d010c..21ae0c48232a 100644
--- a/drivers/firmware/efi/embedded-firmware.c
+++ b/drivers/firmware/efi/embedded-firmware.c
@@ -16,9 +16,9 @@
 
 /* Exported for use by lib/test_firmware.c only */
 LIST_HEAD(efi_embedded_fw_list);
-EXPORT_SYMBOL_GPL(efi_embedded_fw_list);
-
-static bool checked_for_fw;
+EXPORT_SYMBOL_NS_GPL(efi_embedded_fw_list, TEST_FIRMWARE);
+bool efi_embedded_fw_checked;
+EXPORT_SYMBOL_NS_GPL(efi_embedded_fw_checked, TEST_FIRMWARE);
 
 static const struct dmi_system_id * const embedded_fw_table[] = {
 #ifdef CONFIG_TOUCHSCREEN_DMI
@@ -116,14 +116,14 @@ void __init efi_check_for_embedded_firmwares(void)
 		}
 	}
 
-	checked_for_fw = true;
+	efi_embedded_fw_checked = true;
 }
 
 int efi_get_embedded_fw(const char *name, const u8 **data, size_t *size)
 {
 	struct efi_embedded_fw *iter, *fw = NULL;
 
-	if (!checked_for_fw) {
+	if (!efi_embedded_fw_checked) {
 		pr_warn("Warning %s called while we did not check for embedded fw\n",
 			__func__);
 		return -ENOENT;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index d8c6520ff74a..06757681b2ce 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -178,7 +178,7 @@ static int psp_sw_init(void *handle)
 		return ret;
 	}
 
-	if (adev->asic_type == CHIP_NAVI10) {
+	if (adev->asic_type == CHIP_NAVI10 || adev->asic_type == CHIP_SIENNA_CICHLID) {
 		ret= psp_sysfs_init(adev);
 		if (ret) {
 			return ret;
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
index e16874f30d5d..6c5d9612abcb 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
@@ -58,7 +58,7 @@ MODULE_FIRMWARE("amdgpu/arcturus_ta.bin");
 MODULE_FIRMWARE("amdgpu/sienna_cichlid_sos.bin");
 MODULE_FIRMWARE("amdgpu/sienna_cichlid_ta.bin");
 MODULE_FIRMWARE("amdgpu/navy_flounder_sos.bin");
-MODULE_FIRMWARE("amdgpu/navy_flounder_asd.bin");
+MODULE_FIRMWARE("amdgpu/navy_flounder_ta.bin");
 
 /* address block */
 #define smnMP1_FIRMWARE_FLAGS		0x3010024
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index e0e60b0d0669..0f4508b4903e 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -1216,6 +1216,8 @@ static int stop_cpsch(struct device_queue_manager *dqm)
 	dqm->sched_running = false;
 	dqm_unlock(dqm);
 
+	pm_release_ib(&dqm->packets);
+
 	kfd_gtt_sa_free(dqm->dev, dqm->fence_mem);
 	pm_uninit(&dqm->packets, hanging);
 
@@ -1326,7 +1328,7 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
 	if (q->properties.is_active) {
 		increment_queue_count(dqm, q->properties.type);
 
-		retval = execute_queues_cpsch(dqm,
+		execute_queues_cpsch(dqm,
 				KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0);
 	}
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index b51c527a3f0d..4ba8b54a2695 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -5278,19 +5278,6 @@ static void dm_crtc_helper_disable(struct drm_crtc *crtc)
 {
 }
 
-static bool does_crtc_have_active_cursor(struct drm_crtc_state *new_crtc_state)
-{
-	struct drm_device *dev = new_crtc_state->crtc->dev;
-	struct drm_plane *plane;
-
-	drm_for_each_plane_mask(plane, dev, new_crtc_state->plane_mask) {
-		if (plane->type == DRM_PLANE_TYPE_CURSOR)
-			return true;
-	}
-
-	return false;
-}
-
 static int count_crtc_active_planes(struct drm_crtc_state *new_crtc_state)
 {
 	struct drm_atomic_state *state = new_crtc_state->state;
@@ -5354,19 +5341,20 @@ static int dm_crtc_helper_atomic_check(struct drm_crtc *crtc,
 		return ret;
 	}
 
-	/* In some use cases, like reset, no stream is attached */
-	if (!dm_crtc_state->stream)
-		return 0;
-
 	/*
-	 * We want at least one hardware plane enabled to use
-	 * the stream with a cursor enabled.
+	 * We require the primary plane to be enabled whenever the CRTC is, otherwise
+	 * drm_mode_cursor_universal may end up trying to enable the cursor plane while all other
+	 * planes are disabled, which is not supported by the hardware. And there is legacy
+	 * userspace which stops using the HW cursor altogether in response to the resulting EINVAL.
 	 */
-	if (state->enable && state->active &&
-	    does_crtc_have_active_cursor(state) &&
-	    dm_crtc_state->active_planes == 0)
+	if (state->enable &&
+	    !(state->plane_mask & drm_plane_mask(crtc->primary)))
 		return -EINVAL;
 
+	/* In some use cases, like reset, no stream is attached */
+	if (!dm_crtc_state->stream)
+		return 0;
+
 	if (dc_validate_stream(dc, dm_crtc_state->stream) == DC_OK)
 		return 0;
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
index 9140b3fc767a..f31f48dd0da2 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
@@ -409,8 +409,8 @@ static struct _vcs_dpi_soc_bounding_box_st dcn2_0_nv14_soc = {
 			},
 		},
 	.num_states = 5,
-	.sr_exit_time_us = 8.6,
-	.sr_enter_plus_exit_time_us = 10.9,
+	.sr_exit_time_us = 11.6,
+	.sr_enter_plus_exit_time_us = 13.9,
 	.urgent_latency_us = 4.0,
 	.urgent_latency_pixel_data_only_us = 4.0,
 	.urgent_latency_pixel_mixed_with_vm_data_us = 4.0,
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.h b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.h
index d3192b9d0c3d..47f8ee2832ff 100644
--- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.h
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.h
@@ -27,7 +27,7 @@
 #define MOD_HDCP_LOG_H_
 
 #ifdef CONFIG_DRM_AMD_DC_HDCP
-#define HDCP_LOG_ERR(hdcp, ...) DRM_WARN(__VA_ARGS__)
+#define HDCP_LOG_ERR(hdcp, ...) DRM_DEBUG_KMS(__VA_ARGS__)
 #define HDCP_LOG_VER(hdcp, ...) DRM_DEBUG_KMS(__VA_ARGS__)
 #define HDCP_LOG_FSM(hdcp, ...) DRM_DEBUG_KMS(__VA_ARGS__)
 #define HDCP_LOG_TOP(hdcp, ...) pr_debug("[HDCP_TOP]:"__VA_ARGS__)
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c
index fb1161dd7ea8..3a367a5968ae 100644
--- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c
@@ -88,7 +88,7 @@ enum mod_hdcp_status mod_hdcp_add_display_to_topology(struct mod_hdcp *hdcp,
 	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
 
 	if (!psp->dtm_context.dtm_initialized) {
-		DRM_ERROR("Failed to add display topology, DTM TA is not initialized.");
+		DRM_INFO("Failed to add display topology, DTM TA is not initialized.");
 		display->state = MOD_HDCP_DISPLAY_INACTIVE;
 		return MOD_HDCP_STATUS_FAILURE;
 	}
diff --git a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
index 0826625573dc..63f945f9f331 100644
--- a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
@@ -1126,7 +1126,7 @@ static int smu_disable_dpms(struct smu_context *smu)
 	 */
 	if (smu->uploading_custom_pp_table &&
 	    (adev->asic_type >= CHIP_NAVI10) &&
-	    (adev->asic_type <= CHIP_NAVI12))
+	    (adev->asic_type <= CHIP_NAVY_FLOUNDER))
 		return 0;
 
 	/*
@@ -1211,7 +1211,9 @@ static int smu_hw_fini(void *handle)
 int smu_reset(struct smu_context *smu)
 {
 	struct amdgpu_device *adev = smu->adev;
-	int ret = 0;
+	int ret;
+
+	amdgpu_gfx_off_ctrl(smu->adev, false);
 
 	ret = smu_hw_fini(adev);
 	if (ret)
@@ -1222,8 +1224,12 @@ int smu_reset(struct smu_context *smu)
 		return ret;
 
 	ret = smu_late_init(adev);
+	if (ret)
+		return ret;
 
-	return ret;
+	amdgpu_gfx_off_ctrl(smu->adev, true);
+
+	return 0;
 }
 
 static int smu_suspend(void *handle)
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 68325678f5ef..b18c5ac2934d 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -14956,12 +14956,6 @@ static int intel_atomic_check(struct drm_device *dev,
 	if (dev_priv->wm.distrust_bios_wm)
 		any_ms = true;
 
-	if (any_ms) {
-		ret = intel_modeset_checks(state);
-		if (ret)
-			goto fail;
-	}
-
 	intel_fbc_choose_crtc(dev_priv, state);
 	ret = calc_watermark_data(state);
 	if (ret)
@@ -14976,6 +14970,10 @@ static int intel_atomic_check(struct drm_device *dev,
 		goto fail;
 
 	if (any_ms) {
+		ret = intel_modeset_checks(state);
+		if (ret)
+			goto fail;
+
 		ret = intel_modeset_calc_cdclk(state);
 		if (ret)
 			return ret;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index d0bdb6d447ed..ef755dd5e68f 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -439,29 +439,36 @@ static bool __cancel_engine(struct intel_engine_cs *engine)
 	return __reset_engine(engine);
 }
 
-static struct intel_engine_cs *__active_engine(struct i915_request *rq)
+static bool
+__active_engine(struct i915_request *rq, struct intel_engine_cs **active)
 {
 	struct intel_engine_cs *engine, *locked;
+	bool ret = false;
 
 	/*
 	 * Serialise with __i915_request_submit() so that it sees
 	 * is-banned?, or we know the request is already inflight.
+	 *
+	 * Note that rq->engine is unstable, and so we double
+	 * check that we have acquired the lock on the final engine.
 	 */
 	locked = READ_ONCE(rq->engine);
 	spin_lock_irq(&locked->active.lock);
 	while (unlikely(locked != (engine = READ_ONCE(rq->engine)))) {
 		spin_unlock(&locked->active.lock);
-		spin_lock(&engine->active.lock);
 		locked = engine;
+		spin_lock(&locked->active.lock);
 	}
 
-	engine = NULL;
-	if (i915_request_is_active(rq) && rq->fence.error != -EIO)
-		engine = rq->engine;
+	if (!i915_request_completed(rq)) {
+		if (i915_request_is_active(rq) && rq->fence.error != -EIO)
+			*active = locked;
+		ret = true;
+	}
 
 	spin_unlock_irq(&locked->active.lock);
 
-	return engine;
+	return ret;
 }
 
 static struct intel_engine_cs *active_engine(struct intel_context *ce)
@@ -472,17 +479,16 @@ static struct intel_engine_cs *active_engine(struct intel_context *ce)
 	if (!ce->timeline)
 		return NULL;
 
-	mutex_lock(&ce->timeline->mutex);
-	list_for_each_entry_reverse(rq, &ce->timeline->requests, link) {
-		if (i915_request_completed(rq))
-			break;
+	rcu_read_lock();
+	list_for_each_entry_rcu(rq, &ce->timeline->requests, link) {
+		if (i915_request_is_active(rq) && i915_request_completed(rq))
+			continue;
 
 		/* Check with the backend if the request is inflight */
-		engine = __active_engine(rq);
-		if (engine)
+		if (__active_engine(rq, &engine))
 			break;
 	}
-	mutex_unlock(&ce->timeline->mutex);
+	rcu_read_unlock();
 
 	return engine;
 }
@@ -713,6 +719,7 @@ __create_context(struct drm_i915_private *i915)
 	ctx->i915 = i915;
 	ctx->sched.priority = I915_USER_PRIORITY(I915_PRIORITY_NORMAL);
 	mutex_init(&ctx->mutex);
+	INIT_LIST_HEAD(&ctx->link);
 
 	spin_lock_init(&ctx->stale.lock);
 	INIT_LIST_HEAD(&ctx->stale.engines);
@@ -740,10 +747,6 @@ __create_context(struct drm_i915_private *i915)
 	for (i = 0; i < ARRAY_SIZE(ctx->hang_timestamp); i++)
 		ctx->hang_timestamp[i] = jiffies - CONTEXT_FAST_HANG_JIFFIES;
 
-	spin_lock(&i915->gem.contexts.lock);
-	list_add_tail(&ctx->link, &i915->gem.contexts.list);
-	spin_unlock(&i915->gem.contexts.lock);
-
 	return ctx;
 
 err_free:
@@ -931,6 +934,7 @@ static int gem_context_register(struct i915_gem_context *ctx,
 				struct drm_i915_file_private *fpriv,
 				u32 *id)
 {
+	struct drm_i915_private *i915 = ctx->i915;
 	struct i915_address_space *vm;
 	int ret;
 
@@ -949,8 +953,16 @@ static int gem_context_register(struct i915_gem_context *ctx,
 	/* And finally expose ourselves to userspace via the idr */
 	ret = xa_alloc(&fpriv->context_xa, id, ctx, xa_limit_32b, GFP_KERNEL);
 	if (ret)
-		put_pid(fetch_and_zero(&ctx->pid));
+		goto err_pid;
+
+	spin_lock(&i915->gem.contexts.lock);
+	list_add_tail(&ctx->link, &i915->gem.contexts.list);
+	spin_unlock(&i915->gem.contexts.lock);
+
+	return 0;
 
+err_pid:
+	put_pid(fetch_and_zero(&ctx->pid));
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index 6b4ec66cb558..446e76e95c38 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -45,6 +45,13 @@ struct eb_vma_array {
 	struct eb_vma vma[];
 };
 
+enum {
+	FORCE_CPU_RELOC = 1,
+	FORCE_GTT_RELOC,
+	FORCE_GPU_RELOC,
+#define DBG_FORCE_RELOC 0 /* choose one of the above! */
+};
+
 #define __EXEC_OBJECT_HAS_PIN		BIT(31)
 #define __EXEC_OBJECT_HAS_FENCE		BIT(30)
 #define __EXEC_OBJECT_NEEDS_MAP		BIT(29)
@@ -253,6 +260,8 @@ struct i915_execbuffer {
 	 */
 	struct reloc_cache {
 		struct drm_mm_node node; /** temporary GTT binding */
+		unsigned long vaddr; /** Current kmap address */
+		unsigned long page; /** Currently mapped page index */
 		unsigned int gen; /** Cached value of INTEL_GEN */
 		bool use_64bit_reloc : 1;
 		bool has_llc : 1;
@@ -596,6 +605,23 @@ eb_add_vma(struct i915_execbuffer *eb,
 	}
 }
 
+static inline int use_cpu_reloc(const struct reloc_cache *cache,
+				const struct drm_i915_gem_object *obj)
+{
+	if (!i915_gem_object_has_struct_page(obj))
+		return false;
+
+	if (DBG_FORCE_RELOC == FORCE_CPU_RELOC)
+		return true;
+
+	if (DBG_FORCE_RELOC == FORCE_GTT_RELOC)
+		return false;
+
+	return (cache->has_llc ||
+		obj->cache_dirty ||
+		obj->cache_level != I915_CACHE_NONE);
+}
+
 static int eb_reserve_vma(const struct i915_execbuffer *eb,
 			  struct eb_vma *ev,
 			  u64 pin_flags)
@@ -926,6 +952,8 @@ relocation_target(const struct drm_i915_gem_relocation_entry *reloc,
 static void reloc_cache_init(struct reloc_cache *cache,
 			     struct drm_i915_private *i915)
 {
+	cache->page = -1;
+	cache->vaddr = 0;
 	/* Must be a variable in the struct to allow GCC to unroll. */
 	cache->gen = INTEL_GEN(i915);
 	cache->has_llc = HAS_LLC(i915);
@@ -937,6 +965,25 @@ static void reloc_cache_init(struct reloc_cache *cache,
 	cache->target = NULL;
 }
 
+static inline void *unmask_page(unsigned long p)
+{
+	return (void *)(uintptr_t)(p & PAGE_MASK);
+}
+
+static inline unsigned int unmask_flags(unsigned long p)
+{
+	return p & ~PAGE_MASK;
+}
+
+#define KMAP 0x4 /* after CLFLUSH_FLAGS */
+
+static inline struct i915_ggtt *cache_to_ggtt(struct reloc_cache *cache)
+{
+	struct drm_i915_private *i915 =
+		container_of(cache, struct i915_execbuffer, reloc_cache)->i915;
+	return &i915->ggtt;
+}
+
 #define RELOC_TAIL 4
 
 static int reloc_gpu_chain(struct reloc_cache *cache)
@@ -1049,6 +1096,181 @@ static int reloc_gpu_flush(struct reloc_cache *cache)
 	return err;
 }
 
+static void reloc_cache_reset(struct reloc_cache *cache)
+{
+	void *vaddr;
+
+	if (!cache->vaddr)
+		return;
+
+	vaddr = unmask_page(cache->vaddr);
+	if (cache->vaddr & KMAP) {
+		if (cache->vaddr & CLFLUSH_AFTER)
+			mb();
+
+		kunmap_atomic(vaddr);
+		i915_gem_object_finish_access((struct drm_i915_gem_object *)cache->node.mm);
+	} else {
+		struct i915_ggtt *ggtt = cache_to_ggtt(cache);
+
+		intel_gt_flush_ggtt_writes(ggtt->vm.gt);
+		io_mapping_unmap_atomic((void __iomem *)vaddr);
+
+		if (drm_mm_node_allocated(&cache->node)) {
+			ggtt->vm.clear_range(&ggtt->vm,
+					     cache->node.start,
+					     cache->node.size);
+			mutex_lock(&ggtt->vm.mutex);
+			drm_mm_remove_node(&cache->node);
+			mutex_unlock(&ggtt->vm.mutex);
+		} else {
+			i915_vma_unpin((struct i915_vma *)cache->node.mm);
+		}
+	}
+
+	cache->vaddr = 0;
+	cache->page = -1;
+}
+
+static void *reloc_kmap(struct drm_i915_gem_object *obj,
+			struct reloc_cache *cache,
+			unsigned long page)
+{
+	void *vaddr;
+
+	if (cache->vaddr) {
+		kunmap_atomic(unmask_page(cache->vaddr));
+	} else {
+		unsigned int flushes;
+		int err;
+
+		err = i915_gem_object_prepare_write(obj, &flushes);
+		if (err)
+			return ERR_PTR(err);
+
+		BUILD_BUG_ON(KMAP & CLFLUSH_FLAGS);
+		BUILD_BUG_ON((KMAP | CLFLUSH_FLAGS) & PAGE_MASK);
+
+		cache->vaddr = flushes | KMAP;
+		cache->node.mm = (void *)obj;
+		if (flushes)
+			mb();
+	}
+
+	vaddr = kmap_atomic(i915_gem_object_get_dirty_page(obj, page));
+	cache->vaddr = unmask_flags(cache->vaddr) | (unsigned long)vaddr;
+	cache->page = page;
+
+	return vaddr;
+}
+
+static void *reloc_iomap(struct drm_i915_gem_object *obj,
+			 struct reloc_cache *cache,
+			 unsigned long page)
+{
+	struct i915_ggtt *ggtt = cache_to_ggtt(cache);
+	unsigned long offset;
+	void *vaddr;
+
+	if (cache->vaddr) {
+		intel_gt_flush_ggtt_writes(ggtt->vm.gt);
+		io_mapping_unmap_atomic((void __force __iomem *) unmask_page(cache->vaddr));
+	} else {
+		struct i915_vma *vma;
+		int err;
+
+		if (i915_gem_object_is_tiled(obj))
+			return ERR_PTR(-EINVAL);
+
+		if (use_cpu_reloc(cache, obj))
+			return NULL;
+
+		i915_gem_object_lock(obj);
+		err = i915_gem_object_set_to_gtt_domain(obj, true);
+		i915_gem_object_unlock(obj);
+		if (err)
+			return ERR_PTR(err);
+
+		vma = i915_gem_object_ggtt_pin(obj, NULL, 0, 0,
+					       PIN_MAPPABLE |
+					       PIN_NONBLOCK /* NOWARN */ |
+					       PIN_NOEVICT);
+		if (IS_ERR(vma)) {
+			memset(&cache->node, 0, sizeof(cache->node));
+			mutex_lock(&ggtt->vm.mutex);
+			err = drm_mm_insert_node_in_range
+				(&ggtt->vm.mm, &cache->node,
+				 PAGE_SIZE, 0, I915_COLOR_UNEVICTABLE,
+				 0, ggtt->mappable_end,
+				 DRM_MM_INSERT_LOW);
+			mutex_unlock(&ggtt->vm.mutex);
+			if (err) /* no inactive aperture space, use cpu reloc */
+				return NULL;
+		} else {
+			cache->node.start = vma->node.start;
+			cache->node.mm = (void *)vma;
+		}
+	}
+
+	offset = cache->node.start;
+	if (drm_mm_node_allocated(&cache->node)) {
+		ggtt->vm.insert_page(&ggtt->vm,
+				     i915_gem_object_get_dma_address(obj, page),
+				     offset, I915_CACHE_NONE, 0);
+	} else {
+		offset += page << PAGE_SHIFT;
+	}
+
+	vaddr = (void __force *)io_mapping_map_atomic_wc(&ggtt->iomap,
+							 offset);
+	cache->page = page;
+	cache->vaddr = (unsigned long)vaddr;
+
+	return vaddr;
+}
+
+static void *reloc_vaddr(struct drm_i915_gem_object *obj,
+			 struct reloc_cache *cache,
+			 unsigned long page)
+{
+	void *vaddr;
+
+	if (cache->page == page) {
+		vaddr = unmask_page(cache->vaddr);
+	} else {
+		vaddr = NULL;
+		if ((cache->vaddr & KMAP) == 0)
+			vaddr = reloc_iomap(obj, cache, page);
+		if (!vaddr)
+			vaddr = reloc_kmap(obj, cache, page);
+	}
+
+	return vaddr;
+}
+
+static void clflush_write32(u32 *addr, u32 value, unsigned int flushes)
+{
+	if (unlikely(flushes & (CLFLUSH_BEFORE | CLFLUSH_AFTER))) {
+		if (flushes & CLFLUSH_BEFORE) {
+			clflushopt(addr);
+			mb();
+		}
+
+		*addr = value;
+
+		/*
+		 * Writes to the same cacheline are serialised by the CPU
+		 * (including clflush). On the write path, we only require
+		 * that it hits memory in an orderly fashion and place
+		 * mb barriers at the start and end of the relocation phase
+		 * to ensure ordering of clflush wrt to the system.
+		 */
+		if (flushes & CLFLUSH_AFTER)
+			clflushopt(addr);
+	} else
+		*addr = value;
+}
+
 static int reloc_move_to_gpu(struct i915_request *rq, struct i915_vma *vma)
 {
 	struct drm_i915_gem_object *obj = vma->obj;
@@ -1214,6 +1436,17 @@ static u32 *reloc_gpu(struct i915_execbuffer *eb,
 	return cmd;
 }
 
+static inline bool use_reloc_gpu(struct i915_vma *vma)
+{
+	if (DBG_FORCE_RELOC == FORCE_GPU_RELOC)
+		return true;
+
+	if (DBG_FORCE_RELOC)
+		return false;
+
+	return !dma_resv_test_signaled_rcu(vma->resv, true);
+}
+
 static unsigned long vma_phys_addr(struct i915_vma *vma, u32 offset)
 {
 	struct page *page;
@@ -1228,10 +1461,10 @@ static unsigned long vma_phys_addr(struct i915_vma *vma, u32 offset)
 	return addr + offset_in_page(offset);
 }
 
-static int __reloc_entry_gpu(struct i915_execbuffer *eb,
-			     struct i915_vma *vma,
-			     u64 offset,
-			     u64 target_addr)
+static bool __reloc_entry_gpu(struct i915_execbuffer *eb,
+			      struct i915_vma *vma,
+			      u64 offset,
+			      u64 target_addr)
 {
 	const unsigned int gen = eb->reloc_cache.gen;
 	unsigned int len;
@@ -1247,7 +1480,7 @@ static int __reloc_entry_gpu(struct i915_execbuffer *eb,
 
 	batch = reloc_gpu(eb, vma, len);
 	if (IS_ERR(batch))
-		return PTR_ERR(batch);
+		return false;
 
 	addr = gen8_canonical_addr(vma->node.start + offset);
 	if (gen >= 8) {
@@ -1296,21 +1529,55 @@ static int __reloc_entry_gpu(struct i915_execbuffer *eb,
 		*batch++ = target_addr;
 	}
 
-	return 0;
+	return true;
+}
+
+static bool reloc_entry_gpu(struct i915_execbuffer *eb,
+			    struct i915_vma *vma,
+			    u64 offset,
+			    u64 target_addr)
+{
+	if (eb->reloc_cache.vaddr)
+		return false;
+
+	if (!use_reloc_gpu(vma))
+		return false;
+
+	return __reloc_entry_gpu(eb, vma, offset, target_addr);
 }
 
 static u64
-relocate_entry(struct i915_execbuffer *eb,
-	       struct i915_vma *vma,
+relocate_entry(struct i915_vma *vma,
 	       const struct drm_i915_gem_relocation_entry *reloc,
+	       struct i915_execbuffer *eb,
 	       const struct i915_vma *target)
 {
 	u64 target_addr = relocation_target(reloc, target);
-	int err;
-
-	err = __reloc_entry_gpu(eb, vma, reloc->offset, target_addr);
-	if (err)
-		return err;
+	u64 offset = reloc->offset;
+
+	if (!reloc_entry_gpu(eb, vma, offset, target_addr)) {
+		bool wide = eb->reloc_cache.use_64bit_reloc;
+		void *vaddr;
+
+repeat:
+		vaddr = reloc_vaddr(vma->obj,
+				    &eb->reloc_cache,
+				    offset >> PAGE_SHIFT);
+		if (IS_ERR(vaddr))
+			return PTR_ERR(vaddr);
+
+		GEM_BUG_ON(!IS_ALIGNED(offset, sizeof(u32)));
+		clflush_write32(vaddr + offset_in_page(offset),
+				lower_32_bits(target_addr),
+				eb->reloc_cache.vaddr);
+
+		if (wide) {
+			offset += sizeof(u32);
+			target_addr >>= 32;
+			wide = false;
+			goto repeat;
+		}
+	}
 
 	return target->node.start | UPDATE;
 }
@@ -1375,7 +1642,8 @@ eb_relocate_entry(struct i915_execbuffer *eb,
 	 * If the relocation already has the right value in it, no
 	 * more work needs to be done.
 	 */
-	if (gen8_canonical_addr(target->vma->node.start) == reloc->presumed_offset)
+	if (!DBG_FORCE_RELOC &&
+	    gen8_canonical_addr(target->vma->node.start) == reloc->presumed_offset)
 		return 0;
 
 	/* Check that the relocation address is valid... */
@@ -1407,7 +1675,7 @@ eb_relocate_entry(struct i915_execbuffer *eb,
 	ev->flags &= ~EXEC_OBJECT_ASYNC;
 
 	/* and update the user's relocation entry */
-	return relocate_entry(eb, ev->vma, reloc, target->vma);
+	return relocate_entry(ev->vma, reloc, eb, target->vma);
 }
 
 static int eb_relocate_vma(struct i915_execbuffer *eb, struct eb_vma *ev)
@@ -1445,8 +1713,10 @@ static int eb_relocate_vma(struct i915_execbuffer *eb, struct eb_vma *ev)
 		 * this is bad and so lockdep complains vehemently.
 		 */
 		copied = __copy_from_user(r, urelocs, count * sizeof(r[0]));
-		if (unlikely(copied))
-			return -EFAULT;
+		if (unlikely(copied)) {
+			remain = -EFAULT;
+			goto out;
+		}
 
 		remain -= count;
 		do {
@@ -1454,7 +1724,8 @@ static int eb_relocate_vma(struct i915_execbuffer *eb, struct eb_vma *ev)
 
 			if (likely(offset == 0)) {
 			} else if ((s64)offset < 0) {
-				return (int)offset;
+				remain = (int)offset;
+				goto out;
 			} else {
 				/*
 				 * Note that reporting an error now
@@ -1484,8 +1755,9 @@ static int eb_relocate_vma(struct i915_execbuffer *eb, struct eb_vma *ev)
 		} while (r++, --count);
 		urelocs += ARRAY_SIZE(stack);
 	} while (remain);
-
-	return 0;
+out:
+	reloc_cache_reset(&eb->reloc_cache);
+	return remain;
 }
 
 static int eb_relocate(struct i915_execbuffer *eb)
@@ -2392,7 +2664,7 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 	eb.i915 = i915;
 	eb.file = file;
 	eb.args = args;
-	if (!(args->flags & I915_EXEC_NO_RELOC))
+	if (DBG_FORCE_RELOC || !(args->flags & I915_EXEC_NO_RELOC))
 		args->flags |= __EXEC_HAS_RELOC;
 
 	eb.exec = exec;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h
index e5b9276d254c..9cf4ad78ece6 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h
@@ -258,6 +258,10 @@ struct page *
 i915_gem_object_get_page(struct drm_i915_gem_object *obj,
 			 unsigned int n);
 
+struct page *
+i915_gem_object_get_dirty_page(struct drm_i915_gem_object *obj,
+			       unsigned int n);
+
 dma_addr_t
 i915_gem_object_get_dma_address_len(struct drm_i915_gem_object *obj,
 				    unsigned long n,
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c b/drivers/gpu/drm/i915/gem/i915_gem_pages.c
index d15ff6748a50..e8a083743e09 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_pages.c
@@ -548,6 +548,20 @@ i915_gem_object_get_page(struct drm_i915_gem_object *obj, unsigned int n)
 	return nth_page(sg_page(sg), offset);
 }
 
+/* Like i915_gem_object_get_page(), but mark the returned page dirty */
+struct page *
+i915_gem_object_get_dirty_page(struct drm_i915_gem_object *obj,
+			       unsigned int n)
+{
+	struct page *page;
+
+	page = i915_gem_object_get_page(obj, n);
+	if (!obj->mm.dirty)
+		set_page_dirty(page);
+
+	return page;
+}
+
 dma_addr_t
 i915_gem_object_get_dma_address_len(struct drm_i915_gem_object *obj,
 				    unsigned long n,
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c
index 57c14d3340cd..a49016f8ee0d 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c
@@ -37,14 +37,20 @@ static int __igt_gpu_reloc(struct i915_execbuffer *eb,
 		return err;
 
 	/* 8-Byte aligned */
-	err = __reloc_entry_gpu(eb, vma, offsets[0] * sizeof(u32), 0);
-	if (err)
+	if (!__reloc_entry_gpu(eb, vma,
+			       offsets[0] * sizeof(u32),
+			       0)) {
+		err = -EIO;
 		goto unpin_vma;
+	}
 
 	/* !8-Byte aligned */
-	err = __reloc_entry_gpu(eb, vma, offsets[1] * sizeof(u32), 1);
-	if (err)
+	if (!__reloc_entry_gpu(eb, vma,
+			       offsets[1] * sizeof(u32),
+			       1)) {
+		err = -EIO;
 		goto unpin_vma;
+	}
 
 	/* Skip to the end of the cmd page */
 	i = PAGE_SIZE / sizeof(u32) - RELOC_TAIL - 1;
@@ -54,9 +60,12 @@ static int __igt_gpu_reloc(struct i915_execbuffer *eb,
 	eb->reloc_cache.rq_size += i;
 
 	/* Force batch chaining */
-	err = __reloc_entry_gpu(eb, vma, offsets[2] * sizeof(u32), 2);
-	if (err)
+	if (!__reloc_entry_gpu(eb, vma,
+			       offsets[2] * sizeof(u32),
+			       2)) {
+		err = -EIO;
 		goto unpin_vma;
+	}
 
 	GEM_BUG_ON(!eb->reloc_cache.rq);
 	rq = i915_request_get(eb->reloc_cache.rq);
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 24322ef08aa4..9eeaca957a7e 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -2060,6 +2060,14 @@ static inline void clear_ports(struct i915_request **ports, int count)
 	memset_p((void **)ports, NULL, count);
 }
 
+static inline void
+copy_ports(struct i915_request **dst, struct i915_request **src, int count)
+{
+	/* A memcpy_p() would be very useful here! */
+	while (count--)
+		WRITE_ONCE(*dst++, *src++); /* avoid write tearing */
+}
+
 static void execlists_dequeue(struct intel_engine_cs *engine)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
@@ -2648,10 +2656,9 @@ static void process_csb(struct intel_engine_cs *engine)
 
 			/* switch pending to inflight */
 			GEM_BUG_ON(!assert_pending_valid(execlists, "promote"));
-			memcpy(execlists->inflight,
-			       execlists->pending,
-			       execlists_num_ports(execlists) *
-			       sizeof(*execlists->pending));
+			copy_ports(execlists->inflight,
+				   execlists->pending,
+				   execlists_num_ports(execlists));
 			smp_wmb(); /* complete the seqlock */
 			WRITE_ONCE(execlists->active, execlists->inflight);
 
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 0b2fe55e6194..781a6783affe 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -388,17 +388,38 @@ static bool __request_in_flight(const struct i915_request *signal)
 	 * As we know that there are always preemption points between
 	 * requests, we know that only the currently executing request
 	 * may be still active even though we have cleared the flag.
-	 * However, we can't rely on our tracking of ELSP[0] to known
+	 * However, we can't rely on our tracking of ELSP[0] to know
 	 * which request is currently active and so maybe stuck, as
 	 * the tracking maybe an event behind. Instead assume that
 	 * if the context is still inflight, then it is still active
 	 * even if the active flag has been cleared.
+	 *
+	 * To further complicate matters, if there a pending promotion, the HW
+	 * may either perform a context switch to the second inflight execlists,
+	 * or it may switch to the pending set of execlists. In the case of the
+	 * latter, it may send the ACK and we process the event copying the
+	 * pending[] over top of inflight[], _overwriting_ our *active. Since
+	 * this implies the HW is arbitrating and not struck in *active, we do
+	 * not worry about complete accuracy, but we do require no read/write
+	 * tearing of the pointer [the read of the pointer must be valid, even
+	 * as the array is being overwritten, for which we require the writes
+	 * to avoid tearing.]
+	 *
+	 * Note that the read of *execlists->active may race with the promotion
+	 * of execlists->pending[] to execlists->inflight[], overwritting
+	 * the value at *execlists->active. This is fine. The promotion implies
+	 * that we received an ACK from the HW, and so the context is not
+	 * stuck -- if we do not see ourselves in *active, the inflight status
+	 * is valid. If instead we see ourselves being copied into *active,
+	 * we are inflight and may signal the callback.
 	 */
 	if (!intel_context_inflight(signal->context))
 		return false;
 
 	rcu_read_lock();
-	for (port = __engine_active(signal->engine); (rq = *port); port++) {
+	for (port = __engine_active(signal->engine);
+	     (rq = READ_ONCE(*port)); /* may race with promotion of pending[] */
+	     port++) {
 		if (rq->context == signal->context) {
 			inflight = i915_seqno_passed(rq->fence.seqno,
 						     signal->fence.seqno);
diff --git a/drivers/gpu/drm/i915/i915_sw_fence.c b/drivers/gpu/drm/i915/i915_sw_fence.c
index 295b9829e2da..4cd2038cbe35 100644
--- a/drivers/gpu/drm/i915/i915_sw_fence.c
+++ b/drivers/gpu/drm/i915/i915_sw_fence.c
@@ -164,9 +164,13 @@ static void __i915_sw_fence_wake_up_all(struct i915_sw_fence *fence,
 
 		do {
 			list_for_each_entry_safe(pos, next, &x->head, entry) {
-				pos->func(pos,
-					  TASK_NORMAL, fence->error,
-					  &extra);
+				int wake_flags;
+
+				wake_flags = fence->error;
+				if (pos->func == autoremove_wake_function)
+					wake_flags = 0;
+
+				pos->func(pos, TASK_NORMAL, wake_flags, &extra);
 			}
 
 			if (list_empty(&extra))
diff --git a/drivers/gpu/drm/ingenic/ingenic-drm-drv.c b/drivers/gpu/drm/ingenic/ingenic-drm-drv.c
index ada990a7f911..b7074161ccf0 100644
--- a/drivers/gpu/drm/ingenic/ingenic-drm-drv.c
+++ b/drivers/gpu/drm/ingenic/ingenic-drm-drv.c
@@ -673,7 +673,7 @@ static void ingenic_drm_unbind_all(void *d)
 	component_unbind_all(priv->dev, &priv->drm);
 }
 
-static int ingenic_drm_bind(struct device *dev)
+static int ingenic_drm_bind(struct device *dev, bool has_components)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	const struct jz_soc_info *soc_info;
@@ -808,7 +808,7 @@ static int ingenic_drm_bind(struct device *dev)
 			return ret;
 		}
 
-		if (IS_ENABLED(CONFIG_DRM_INGENIC_IPU)) {
+		if (IS_ENABLED(CONFIG_DRM_INGENIC_IPU) && has_components) {
 			ret = component_bind_all(dev, drm);
 			if (ret) {
 				if (ret != -EPROBE_DEFER)
@@ -939,6 +939,11 @@ err_pixclk_disable:
 	return ret;
 }
 
+static int ingenic_drm_bind_with_components(struct device *dev)
+{
+	return ingenic_drm_bind(dev, true);
+}
+
 static int compare_of(struct device *dev, void *data)
 {
 	return dev->of_node == data;
@@ -957,7 +962,7 @@ static void ingenic_drm_unbind(struct device *dev)
 }
 
 static const struct component_master_ops ingenic_master_ops = {
-	.bind = ingenic_drm_bind,
+	.bind = ingenic_drm_bind_with_components,
 	.unbind = ingenic_drm_unbind,
 };
 
@@ -968,16 +973,15 @@ static int ingenic_drm_probe(struct platform_device *pdev)
 	struct device_node *np;
 
 	if (!IS_ENABLED(CONFIG_DRM_INGENIC_IPU))
-		return ingenic_drm_bind(dev);
+		return ingenic_drm_bind(dev, false);
 
 	/* IPU is at port address 8 */
 	np = of_graph_get_remote_node(dev->of_node, 8, 0);
-	if (!np) {
-		dev_err(dev, "Unable to get IPU node\n");
-		return -EINVAL;
-	}
+	if (!np)
+		return ingenic_drm_bind(dev, false);
 
 	drm_of_component_match_add(dev, &match, compare_of, np);
+	of_node_put(np);
 
 	return component_master_add_with_match(dev, &ingenic_master_ops, match);
 }
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
index 3fc5511330b9..4d29568be3f5 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
@@ -831,13 +831,19 @@ int mtk_drm_crtc_create(struct drm_device *drm_dev,
 			drm_crtc_index(&mtk_crtc->base));
 		mtk_crtc->cmdq_client = NULL;
 	}
-	ret = of_property_read_u32_index(priv->mutex_node,
-					 "mediatek,gce-events",
-					 drm_crtc_index(&mtk_crtc->base),
-					 &mtk_crtc->cmdq_event);
-	if (ret)
-		dev_dbg(dev, "mtk_crtc %d failed to get mediatek,gce-events property\n",
-			drm_crtc_index(&mtk_crtc->base));
+
+	if (mtk_crtc->cmdq_client) {
+		ret = of_property_read_u32_index(priv->mutex_node,
+						 "mediatek,gce-events",
+						 drm_crtc_index(&mtk_crtc->base),
+						 &mtk_crtc->cmdq_event);
+		if (ret) {
+			dev_dbg(dev, "mtk_crtc %d failed to get mediatek,gce-events property\n",
+				drm_crtc_index(&mtk_crtc->base));
+			cmdq_mbox_destroy(mtk_crtc->cmdq_client);
+			mtk_crtc->cmdq_client = NULL;
+		}
+	}
 #endif
 	return 0;
 }
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
index 57c88de9a329..526648885b97 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
@@ -496,6 +496,7 @@ int mtk_ddp_comp_init(struct device *dev, struct device_node *node,
 #if IS_REACHABLE(CONFIG_MTK_CMDQ)
 	if (of_address_to_resource(node, 0, &res) != 0) {
 		dev_err(dev, "Missing reg in %s node\n", node->full_name);
+		put_device(&larb_pdev->dev);
 		return -EINVAL;
 	}
 	comp->regs_pa = res.start;
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
index 040a8f393fe2..2d982740b1a4 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
@@ -27,7 +27,6 @@
 
 #include "mtk_drm_crtc.h"
 #include "mtk_drm_ddp.h"
-#include "mtk_drm_ddp.h"
 #include "mtk_drm_ddp_comp.h"
 #include "mtk_drm_drv.h"
 #include "mtk_drm_gem.h"
@@ -165,7 +164,7 @@ static int mtk_drm_kms_init(struct drm_device *drm)
 
 	ret = drmm_mode_config_init(drm);
 	if (ret)
-		return ret;
+		goto put_mutex_dev;
 
 	drm->mode_config.min_width = 64;
 	drm->mode_config.min_height = 64;
@@ -182,7 +181,7 @@ static int mtk_drm_kms_init(struct drm_device *drm)
 
 	ret = component_bind_all(drm->dev, drm);
 	if (ret)
-		return ret;
+		goto put_mutex_dev;
 
 	/*
 	 * We currently support two fixed data streams, each optional,
@@ -229,7 +228,7 @@ static int mtk_drm_kms_init(struct drm_device *drm)
 	}
 	if (!dma_dev->dma_parms) {
 		ret = -ENOMEM;
-		goto err_component_unbind;
+		goto put_dma_dev;
 	}
 
 	ret = dma_set_max_seg_size(dma_dev, (unsigned int)DMA_BIT_MASK(32));
@@ -256,9 +255,12 @@ static int mtk_drm_kms_init(struct drm_device *drm)
 err_unset_dma_parms:
 	if (private->dma_parms_allocated)
 		dma_dev->dma_parms = NULL;
+put_dma_dev:
+	put_device(private->dma_dev);
 err_component_unbind:
 	component_unbind_all(drm->dev, drm);
-
+put_mutex_dev:
+	put_device(private->mutex_dev);
 	return ret;
 }
 
@@ -544,8 +546,13 @@ err_pm:
 	pm_runtime_disable(dev);
 err_node:
 	of_node_put(private->mutex_node);
-	for (i = 0; i < DDP_COMPONENT_ID_MAX; i++)
+	for (i = 0; i < DDP_COMPONENT_ID_MAX; i++) {
 		of_node_put(private->comp_node[i]);
+		if (private->ddp_comp[i]) {
+			put_device(private->ddp_comp[i]->larb_dev);
+			private->ddp_comp[i] = NULL;
+		}
+	}
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c
index 16fd99dcdacf..80b7a082e874 100644
--- a/drivers/gpu/drm/mediatek/mtk_dsi.c
+++ b/drivers/gpu/drm/mediatek/mtk_dsi.c
@@ -466,14 +466,13 @@ static void mtk_dsi_config_vdo_timing(struct mtk_dsi *dsi)
 	horizontal_sync_active_byte = (vm->hsync_len * dsi_tmp_buf_bpp - 10);
 
 	if (dsi->mode_flags & MIPI_DSI_MODE_VIDEO_SYNC_PULSE)
-		horizontal_backporch_byte =
-			(vm->hback_porch * dsi_tmp_buf_bpp - 10);
+		horizontal_backporch_byte = vm->hback_porch * dsi_tmp_buf_bpp;
 	else
-		horizontal_backporch_byte = ((vm->hback_porch + vm->hsync_len) *
-			dsi_tmp_buf_bpp - 10);
+		horizontal_backporch_byte = (vm->hback_porch + vm->hsync_len) *
+					    dsi_tmp_buf_bpp;
 
 	data_phy_cycles = timing->lpx + timing->da_hs_prepare +
-			  timing->da_hs_zero + timing->da_hs_exit + 3;
+			  timing->da_hs_zero + timing->da_hs_exit;
 
 	if (dsi->mode_flags & MIPI_DSI_MODE_VIDEO_BURST) {
 		if ((vm->hfront_porch + vm->hback_porch) * dsi_tmp_buf_bpp >
diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi.c b/drivers/gpu/drm/mediatek/mtk_hdmi.c
index f2e9b429960b..a97725680d4e 100644
--- a/drivers/gpu/drm/mediatek/mtk_hdmi.c
+++ b/drivers/gpu/drm/mediatek/mtk_hdmi.c
@@ -1507,25 +1507,30 @@ static int mtk_hdmi_dt_parse_pdata(struct mtk_hdmi *hdmi,
 		dev_err(dev,
 			"Failed to get system configuration registers: %d\n",
 			ret);
-		return ret;
+		goto put_device;
 	}
 	hdmi->sys_regmap = regmap;
 
 	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	hdmi->regs = devm_ioremap_resource(dev, mem);
-	if (IS_ERR(hdmi->regs))
-		return PTR_ERR(hdmi->regs);
+	if (IS_ERR(hdmi->regs)) {
+		ret = PTR_ERR(hdmi->regs);
+		goto put_device;
+	}
 
 	remote = of_graph_get_remote_node(np, 1, 0);
-	if (!remote)
-		return -EINVAL;
+	if (!remote) {
+		ret = -EINVAL;
+		goto put_device;
+	}
 
 	if (!of_device_is_compatible(remote, "hdmi-connector")) {
 		hdmi->next_bridge = of_drm_find_bridge(remote);
 		if (!hdmi->next_bridge) {
 			dev_err(dev, "Waiting for external bridge\n");
 			of_node_put(remote);
-			return -EPROBE_DEFER;
+			ret = -EPROBE_DEFER;
+			goto put_device;
 		}
 	}
 
@@ -1534,7 +1539,8 @@ static int mtk_hdmi_dt_parse_pdata(struct mtk_hdmi *hdmi,
 		dev_err(dev, "Failed to find ddc-i2c-bus node in %pOF\n",
 			remote);
 		of_node_put(remote);
-		return -EINVAL;
+		ret = -EINVAL;
+		goto put_device;
 	}
 	of_node_put(remote);
 
@@ -1542,10 +1548,14 @@ static int mtk_hdmi_dt_parse_pdata(struct mtk_hdmi *hdmi,
 	of_node_put(i2c_np);
 	if (!hdmi->ddc_adpt) {
 		dev_err(dev, "Failed to get ddc i2c adapter by node\n");
-		return -EINVAL;
+		ret = -EINVAL;
+		goto put_device;
 	}
 
 	return 0;
+put_device:
+	put_device(hdmi->cec_dev);
+	return ret;
 }
 
 /*
diff --git a/drivers/gpu/drm/msm/adreno/a2xx_gpu.c b/drivers/gpu/drm/msm/adreno/a2xx_gpu.c
index 6021f8d9efd1..48fa49f69d6d 100644
--- a/drivers/gpu/drm/msm/adreno/a2xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a2xx_gpu.c
@@ -164,6 +164,11 @@ static int a2xx_hw_init(struct msm_gpu *gpu)
 	if (ret)
 		return ret;
 
+	gpu_write(gpu, REG_AXXX_CP_RB_CNTL,
+		MSM_GPU_RB_CNTL_DEFAULT | AXXX_CP_RB_CNTL_NO_UPDATE);
+
+	gpu_write(gpu, REG_AXXX_CP_RB_BASE, lower_32_bits(gpu->rb[0]->iova));
+
 	/* NOTE: PM4/micro-engine firmware registers look to be the same
 	 * for a2xx and a3xx.. we could possibly push that part down to
 	 * adreno_gpu base class.  Or push both PM4 and PFP but
diff --git a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
index 0a5ea9f56cb8..f6471145a7a6 100644
--- a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
@@ -211,6 +211,16 @@ static int a3xx_hw_init(struct msm_gpu *gpu)
 	if (ret)
 		return ret;
 
+	/*
+	 * Use the default ringbuffer size and block size but disable the RPTR
+	 * shadow
+	 */
+	gpu_write(gpu, REG_AXXX_CP_RB_CNTL,
+		MSM_GPU_RB_CNTL_DEFAULT | AXXX_CP_RB_CNTL_NO_UPDATE);
+
+	/* Set the ringbuffer address */
+	gpu_write(gpu, REG_AXXX_CP_RB_BASE, lower_32_bits(gpu->rb[0]->iova));
+
 	/* setup access protection: */
 	gpu_write(gpu, REG_A3XX_CP_PROTECT_CTRL, 0x00000007);
 
diff --git a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
index b9b26b2bf9c5..954753600625 100644
--- a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
@@ -267,6 +267,16 @@ static int a4xx_hw_init(struct msm_gpu *gpu)
 	if (ret)
 		return ret;
 
+	/*
+	 * Use the default ringbuffer size and block size but disable the RPTR
+	 * shadow
+	 */
+	gpu_write(gpu, REG_A4XX_CP_RB_CNTL,
+		MSM_GPU_RB_CNTL_DEFAULT | AXXX_CP_RB_CNTL_NO_UPDATE);
+
+	/* Set the ringbuffer address */
+	gpu_write(gpu, REG_A4XX_CP_RB_BASE, lower_32_bits(gpu->rb[0]->iova));
+
 	/* Load PM4: */
 	ptr = (uint32_t *)(adreno_gpu->fw[ADRENO_FW_PM4]->data);
 	len = adreno_gpu->fw[ADRENO_FW_PM4]->size / 4;
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
index 84a5d9c1f2a2..91726da82ed6 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
@@ -703,8 +703,6 @@ static int a5xx_hw_init(struct msm_gpu *gpu)
 	if (ret)
 		return ret;
 
-	a5xx_preempt_hw_init(gpu);
-
 	if (!adreno_is_a510(adreno_gpu))
 		a5xx_gpmu_ucode_init(gpu);
 
@@ -712,6 +710,15 @@ static int a5xx_hw_init(struct msm_gpu *gpu)
 	if (ret)
 		return ret;
 
+	/* Set the ringbuffer address */
+	gpu_write64(gpu, REG_A5XX_CP_RB_BASE, REG_A5XX_CP_RB_BASE_HI,
+		gpu->rb[0]->iova);
+
+	gpu_write(gpu, REG_A5XX_CP_RB_CNTL,
+		MSM_GPU_RB_CNTL_DEFAULT | AXXX_CP_RB_CNTL_NO_UPDATE);
+
+	a5xx_preempt_hw_init(gpu);
+
 	/* Disable the interrupts through the initial bringup stage */
 	gpu_write(gpu, REG_A5XX_RBBM_INT_0_MASK, A5XX_INT_MASK);
 
@@ -1511,7 +1518,8 @@ struct msm_gpu *a5xx_gpu_init(struct drm_device *dev)
 
 	check_speed_bin(&pdev->dev);
 
-	ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, 4);
+	/* Restricting nr_rings to 1 to temporarily disable preemption */
+	ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, 1);
 	if (ret) {
 		a5xx_destroy(&(a5xx_gpu->base.base));
 		return ERR_PTR(ret);
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.h b/drivers/gpu/drm/msm/adreno/a5xx_gpu.h
index 54868d4e3958..1e5b1a15a70f 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.h
@@ -31,6 +31,7 @@ struct a5xx_gpu {
 	struct msm_ringbuffer *next_ring;
 
 	struct drm_gem_object *preempt_bo[MSM_GPU_MAX_RINGS];
+	struct drm_gem_object *preempt_counters_bo[MSM_GPU_MAX_RINGS];
 	struct a5xx_preempt_record *preempt[MSM_GPU_MAX_RINGS];
 	uint64_t preempt_iova[MSM_GPU_MAX_RINGS];
 
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_preempt.c b/drivers/gpu/drm/msm/adreno/a5xx_preempt.c
index 9cf9353a7ff1..9f3fe177b00e 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_preempt.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_preempt.c
@@ -226,19 +226,31 @@ static int preempt_init_ring(struct a5xx_gpu *a5xx_gpu,
 	struct adreno_gpu *adreno_gpu = &a5xx_gpu->base;
 	struct msm_gpu *gpu = &adreno_gpu->base;
 	struct a5xx_preempt_record *ptr;
-	struct drm_gem_object *bo = NULL;
-	u64 iova = 0;
+	void *counters;
+	struct drm_gem_object *bo = NULL, *counters_bo = NULL;
+	u64 iova = 0, counters_iova = 0;
 
 	ptr = msm_gem_kernel_new(gpu->dev,
 		A5XX_PREEMPT_RECORD_SIZE + A5XX_PREEMPT_COUNTER_SIZE,
-		MSM_BO_UNCACHED, gpu->aspace, &bo, &iova);
+		MSM_BO_UNCACHED | MSM_BO_MAP_PRIV, gpu->aspace, &bo, &iova);
 
 	if (IS_ERR(ptr))
 		return PTR_ERR(ptr);
 
+	/* The buffer to store counters needs to be unprivileged */
+	counters = msm_gem_kernel_new(gpu->dev,
+		A5XX_PREEMPT_COUNTER_SIZE,
+		MSM_BO_UNCACHED, gpu->aspace, &counters_bo, &counters_iova);
+	if (IS_ERR(counters)) {
+		msm_gem_kernel_put(bo, gpu->aspace, true);
+		return PTR_ERR(counters);
+	}
+
 	msm_gem_object_set_name(bo, "preempt");
+	msm_gem_object_set_name(counters_bo, "preempt_counters");
 
 	a5xx_gpu->preempt_bo[ring->id] = bo;
+	a5xx_gpu->preempt_counters_bo[ring->id] = counters_bo;
 	a5xx_gpu->preempt_iova[ring->id] = iova;
 	a5xx_gpu->preempt[ring->id] = ptr;
 
@@ -249,7 +261,7 @@ static int preempt_init_ring(struct a5xx_gpu *a5xx_gpu,
 	ptr->data = 0;
 	ptr->cntl = MSM_GPU_RB_CNTL_DEFAULT;
 	ptr->rptr_addr = rbmemptr(ring, rptr);
-	ptr->counter = iova + A5XX_PREEMPT_RECORD_SIZE;
+	ptr->counter = counters_iova;
 
 	return 0;
 }
@@ -260,8 +272,11 @@ void a5xx_preempt_fini(struct msm_gpu *gpu)
 	struct a5xx_gpu *a5xx_gpu = to_a5xx_gpu(adreno_gpu);
 	int i;
 
-	for (i = 0; i < gpu->nr_rings; i++)
+	for (i = 0; i < gpu->nr_rings; i++) {
 		msm_gem_kernel_put(a5xx_gpu->preempt_bo[i], gpu->aspace, true);
+		msm_gem_kernel_put(a5xx_gpu->preempt_counters_bo[i],
+			gpu->aspace, true);
+	}
 }
 
 void a5xx_preempt_init(struct msm_gpu *gpu)
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index 3966abd523cc..66a95e22b7b3 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -678,7 +678,8 @@ static int a6xx_hw_init(struct msm_gpu *gpu)
 			A6XX_PROTECT_RDONLY(0x980, 0x4));
 	gpu_write(gpu, REG_A6XX_CP_PROTECT(25), A6XX_PROTECT_RW(0xa630, 0x0));
 
-	if (adreno_is_a650(adreno_gpu)) {
+	/* Enable expanded apriv for targets that support it */
+	if (gpu->hw_apriv) {
 		gpu_write(gpu, REG_A6XX_CP_APRIV_CNTL,
 			(1 << 6) | (1 << 5) | (1 << 3) | (1 << 2) | (1 << 1));
 	}
@@ -694,6 +695,13 @@ static int a6xx_hw_init(struct msm_gpu *gpu)
 	if (ret)
 		goto out;
 
+	/* Set the ringbuffer address */
+	gpu_write64(gpu, REG_A6XX_CP_RB_BASE, REG_A6XX_CP_RB_BASE_HI,
+		gpu->rb[0]->iova);
+
+	gpu_write(gpu, REG_A6XX_CP_RB_CNTL,
+		MSM_GPU_RB_CNTL_DEFAULT | AXXX_CP_RB_CNTL_NO_UPDATE);
+
 	/* Always come up on rb 0 */
 	a6xx_gpu->cur_ring = gpu->rb[0];
 
@@ -1056,6 +1064,9 @@ struct msm_gpu *a6xx_gpu_init(struct drm_device *dev)
 	adreno_gpu->registers = NULL;
 	adreno_gpu->reg_offsets = a6xx_register_offsets;
 
+	if (adreno_is_a650(adreno_gpu))
+		adreno_gpu->base.hw_apriv = true;
+
 	ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, 1);
 	if (ret) {
 		a6xx_destroy(&(a6xx_gpu->base.base));
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index 288141fe4c58..862dd35b27d3 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -400,26 +400,6 @@ int adreno_hw_init(struct msm_gpu *gpu)
 		ring->memptrs->rptr = 0;
 	}
 
-	/*
-	 * Setup REG_CP_RB_CNTL.  The same value is used across targets (with
-	 * the excpetion of A430 that disables the RPTR shadow) - the cacluation
-	 * for the ringbuffer size and block size is moved to msm_gpu.h for the
-	 * pre-processor to deal with and the A430 variant is ORed in here
-	 */
-	adreno_gpu_write(adreno_gpu, REG_ADRENO_CP_RB_CNTL,
-		MSM_GPU_RB_CNTL_DEFAULT |
-		(adreno_is_a430(adreno_gpu) ? AXXX_CP_RB_CNTL_NO_UPDATE : 0));
-
-	/* Setup ringbuffer address - use ringbuffer[0] for GPU init */
-	adreno_gpu_write64(adreno_gpu, REG_ADRENO_CP_RB_BASE,
-		REG_ADRENO_CP_RB_BASE_HI, gpu->rb[0]->iova);
-
-	if (!adreno_is_a430(adreno_gpu)) {
-		adreno_gpu_write64(adreno_gpu, REG_ADRENO_CP_RB_RPTR_ADDR,
-			REG_ADRENO_CP_RB_RPTR_ADDR_HI,
-			rbmemptr(gpu->rb[0], rptr));
-	}
-
 	return 0;
 }
 
@@ -427,11 +407,8 @@ int adreno_hw_init(struct msm_gpu *gpu)
 static uint32_t get_rptr(struct adreno_gpu *adreno_gpu,
 		struct msm_ringbuffer *ring)
 {
-	if (adreno_is_a430(adreno_gpu))
-		return ring->memptrs->rptr = adreno_gpu_read(
-			adreno_gpu, REG_ADRENO_CP_RB_RPTR);
-	else
-		return ring->memptrs->rptr;
+	return ring->memptrs->rptr = adreno_gpu_read(
+		adreno_gpu, REG_ADRENO_CP_RB_RPTR);
 }
 
 struct msm_ringbuffer *adreno_active_ring(struct msm_gpu *gpu)
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index d5645472b25d..57ddc9438351 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -908,7 +908,7 @@ int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 
 	memptrs = msm_gem_kernel_new(drm,
 		sizeof(struct msm_rbmemptrs) * nr_rings,
-		MSM_BO_UNCACHED, gpu->aspace, &gpu->memptrs_bo,
+		check_apriv(gpu, MSM_BO_UNCACHED), gpu->aspace, &gpu->memptrs_bo,
 		&memptrs_iova);
 
 	if (IS_ERR(memptrs)) {
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
index 0db117a7339b..37cffac4cbe3 100644
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -15,6 +15,7 @@
 #include "msm_drv.h"
 #include "msm_fence.h"
 #include "msm_ringbuffer.h"
+#include "msm_gem.h"
 
 struct msm_gem_submit;
 struct msm_gpu_perfcntr;
@@ -139,6 +140,8 @@ struct msm_gpu {
 	} devfreq;
 
 	struct msm_gpu_state *crashstate;
+	/* True if the hardware supports expanded apriv (a650 and newer) */
+	bool hw_apriv;
 };
 
 /* It turns out that all targets use the same ringbuffer size */
@@ -327,4 +330,12 @@ static inline void msm_gpu_crashstate_put(struct msm_gpu *gpu)
 	mutex_unlock(&gpu->dev->struct_mutex);
 }
 
+/*
+ * Simple macro to semi-cleanly add the MAP_PRIV flag for targets that can
+ * support expanded privileges
+ */
+#define check_apriv(gpu, flags) \
+	(((gpu)->hw_apriv ? MSM_BO_MAP_PRIV : 0) | (flags))
+
+
 #endif /* __MSM_GPU_H__ */
diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.c b/drivers/gpu/drm/msm/msm_ringbuffer.c
index 39ecb5a18431..935bf9b1d941 100644
--- a/drivers/gpu/drm/msm/msm_ringbuffer.c
+++ b/drivers/gpu/drm/msm/msm_ringbuffer.c
@@ -27,8 +27,8 @@ struct msm_ringbuffer *msm_ringbuffer_new(struct msm_gpu *gpu, int id,
 	ring->id = id;
 
 	ring->start = msm_gem_kernel_new(gpu->dev, MSM_GPU_RINGBUFFER_SZ,
-		MSM_BO_WC | MSM_BO_GPU_READONLY, gpu->aspace, &ring->bo,
-		&ring->iova);
+		check_apriv(gpu, MSM_BO_WC | MSM_BO_GPU_READONLY),
+		gpu->aspace, &ring->bo, &ring->iova);
 
 	if (IS_ERR(ring->start)) {
 		ret = PTR_ERR(ring->start);
diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c
index 7b69d6dfe44a..e0ae911ef427 100644
--- a/drivers/gpu/drm/radeon/radeon_display.c
+++ b/drivers/gpu/drm/radeon/radeon_display.c
@@ -933,7 +933,7 @@ static void avivo_get_fb_ref_div(unsigned nom, unsigned den, unsigned post_div,
 
 	/* get matching reference and feedback divider */
 	*ref_div = min(max(den/post_div, 1u), ref_div_max);
-	*fb_div = max(nom * *ref_div * post_div / den, 1u);
+	*fb_div = DIV_ROUND_CLOSEST(nom * *ref_div * post_div, den);
 
 	/* limit fb divider to its maximum */
 	if (*fb_div > fb_div_max) {
diff --git a/drivers/gpu/drm/sun4i/sun4i_backend.c b/drivers/gpu/drm/sun4i/sun4i_backend.c
index 072ea113e6be..ed5d86617802 100644
--- a/drivers/gpu/drm/sun4i/sun4i_backend.c
+++ b/drivers/gpu/drm/sun4i/sun4i_backend.c
@@ -589,8 +589,7 @@ static int sun4i_backend_atomic_check(struct sunxi_engine *engine,
 
 	/* We can't have an alpha plane at the lowest position */
 	if (!backend->quirks->supports_lowest_plane_alpha &&
-	    (plane_states[0]->fb->format->has_alpha ||
-	    (plane_states[0]->alpha != DRM_BLEND_ALPHA_OPAQUE)))
+	    (plane_states[0]->alpha != DRM_BLEND_ALPHA_OPAQUE))
 		return -EINVAL;
 
 	for (i = 1; i < num_planes; i++) {
@@ -995,7 +994,6 @@ static const struct sun4i_backend_quirks sun6i_backend_quirks = {
 
 static const struct sun4i_backend_quirks sun7i_backend_quirks = {
 	.needs_output_muxing = true,
-	.supports_lowest_plane_alpha = true,
 };
 
 static const struct sun4i_backend_quirks sun8i_a33_backend_quirks = {
diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.c b/drivers/gpu/drm/sun4i/sun4i_tcon.c
index ced9a8287dd8..e40c542254f6 100644
--- a/drivers/gpu/drm/sun4i/sun4i_tcon.c
+++ b/drivers/gpu/drm/sun4i/sun4i_tcon.c
@@ -1433,14 +1433,18 @@ static int sun8i_r40_tcon_tv_set_mux(struct sun4i_tcon *tcon,
 	if (IS_ENABLED(CONFIG_DRM_SUN8I_TCON_TOP) &&
 	    encoder->encoder_type == DRM_MODE_ENCODER_TMDS) {
 		ret = sun8i_tcon_top_set_hdmi_src(&pdev->dev, id);
-		if (ret)
+		if (ret) {
+			put_device(&pdev->dev);
 			return ret;
+		}
 	}
 
 	if (IS_ENABLED(CONFIG_DRM_SUN8I_TCON_TOP)) {
 		ret = sun8i_tcon_top_de_config(&pdev->dev, tcon->id, id);
-		if (ret)
+		if (ret) {
+			put_device(&pdev->dev);
 			return ret;
+		}
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
index 7f13f4d715bf..de8a11abd66a 100644
--- a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
+++ b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
@@ -889,7 +889,7 @@ static int sun6i_dsi_dcs_write_long(struct sun6i_dsi *dsi,
 	regmap_write(dsi->regs, SUN6I_DSI_CMD_TX_REG(0),
 		     sun6i_dsi_dcs_build_pkt_hdr(dsi, msg));
 
-	bounce = kzalloc(msg->tx_len + sizeof(crc), GFP_KERNEL);
+	bounce = kzalloc(ALIGN(msg->tx_len + sizeof(crc), 4), GFP_KERNEL);
 	if (!bounce)
 		return -ENOMEM;
 
@@ -900,7 +900,7 @@ static int sun6i_dsi_dcs_write_long(struct sun6i_dsi *dsi,
 	memcpy((u8 *)bounce + msg->tx_len, &crc, sizeof(crc));
 	len += sizeof(crc);
 
-	regmap_bulk_write(dsi->regs, SUN6I_DSI_CMD_TX_REG(1), bounce, len);
+	regmap_bulk_write(dsi->regs, SUN6I_DSI_CMD_TX_REG(1), bounce, DIV_ROUND_UP(len, 4));
 	regmap_write(dsi->regs, SUN6I_DSI_CMD_CTL_REG, len + 4 - 1);
 	kfree(bounce);
 
diff --git a/drivers/gpu/drm/sun4i/sun8i_vi_layer.c b/drivers/gpu/drm/sun4i/sun8i_vi_layer.c
index 22c8c5375d0d..c0147af6a840 100644
--- a/drivers/gpu/drm/sun4i/sun8i_vi_layer.c
+++ b/drivers/gpu/drm/sun4i/sun8i_vi_layer.c
@@ -211,7 +211,7 @@ static int sun8i_vi_layer_update_coord(struct sun8i_mixer *mixer, int channel,
 	return 0;
 }
 
-static bool sun8i_vi_layer_get_csc_mode(const struct drm_format_info *format)
+static u32 sun8i_vi_layer_get_csc_mode(const struct drm_format_info *format)
 {
 	if (!format->is_yuv)
 		return SUN8I_CSC_MODE_OFF;
diff --git a/drivers/gpu/drm/tve200/tve200_display.c b/drivers/gpu/drm/tve200/tve200_display.c
index d733bbc4ac0e..17ff24d999d1 100644
--- a/drivers/gpu/drm/tve200/tve200_display.c
+++ b/drivers/gpu/drm/tve200/tve200_display.c
@@ -14,6 +14,7 @@
 #include <linux/version.h>
 #include <linux/dma-buf.h>
 #include <linux/of_graph.h>
+#include <linux/delay.h>
 
 #include <drm/drm_fb_cma_helper.h>
 #include <drm/drm_fourcc.h>
@@ -130,9 +131,25 @@ static void tve200_display_enable(struct drm_simple_display_pipe *pipe,
 	struct drm_connector *connector = priv->connector;
 	u32 format = fb->format->format;
 	u32 ctrl1 = 0;
+	int retries;
 
 	clk_prepare_enable(priv->clk);
 
+	/* Reset the TVE200 and wait for it to come back online */
+	writel(TVE200_CTRL_4_RESET, priv->regs + TVE200_CTRL_4);
+	for (retries = 0; retries < 5; retries++) {
+		usleep_range(30000, 50000);
+		if (readl(priv->regs + TVE200_CTRL_4) & TVE200_CTRL_4_RESET)
+			continue;
+		else
+			break;
+	}
+	if (retries == 5 &&
+	    readl(priv->regs + TVE200_CTRL_4) & TVE200_CTRL_4_RESET) {
+		dev_err(drm->dev, "can't get hardware out of reset\n");
+		return;
+	}
+
 	/* Function 1 */
 	ctrl1 |= TVE200_CTRL_CSMODE;
 	/* Interlace mode for CCIR656: parameterize? */
@@ -230,8 +247,9 @@ static void tve200_display_disable(struct drm_simple_display_pipe *pipe)
 
 	drm_crtc_vblank_off(crtc);
 
-	/* Disable and Power Down */
+	/* Disable put into reset and Power Down */
 	writel(0, priv->regs + TVE200_CTRL);
+	writel(TVE200_CTRL_4_RESET, priv->regs + TVE200_CTRL_4);
 
 	clk_disable_unprepare(priv->clk);
 }
@@ -279,6 +297,8 @@ static int tve200_display_enable_vblank(struct drm_simple_display_pipe *pipe)
 	struct drm_device *drm = crtc->dev;
 	struct tve200_drm_dev_private *priv = drm->dev_private;
 
+	/* Clear any IRQs and enable */
+	writel(0xFF, priv->regs + TVE200_INT_CLR);
 	writel(TVE200_INT_V_STATUS, priv->regs + TVE200_INT_EN);
 	return 0;
 }
diff --git a/drivers/gpu/drm/virtio/virtgpu_display.c b/drivers/gpu/drm/virtio/virtgpu_display.c
index af55b334be2f..afd0f9200f90 100644
--- a/drivers/gpu/drm/virtio/virtgpu_display.c
+++ b/drivers/gpu/drm/virtio/virtgpu_display.c
@@ -97,9 +97,6 @@ static void virtio_gpu_crtc_mode_set_nofb(struct drm_crtc *crtc)
 static void virtio_gpu_crtc_atomic_enable(struct drm_crtc *crtc,
 					  struct drm_crtc_state *old_state)
 {
-	struct virtio_gpu_output *output = drm_crtc_to_virtio_gpu_output(crtc);
-
-	output->enabled = true;
 }
 
 static void virtio_gpu_crtc_atomic_disable(struct drm_crtc *crtc,
@@ -111,7 +108,6 @@ static void virtio_gpu_crtc_atomic_disable(struct drm_crtc *crtc,
 
 	virtio_gpu_cmd_set_scanout(vgdev, output->index, 0, 0, 0, 0, 0);
 	virtio_gpu_notify(vgdev);
-	output->enabled = false;
 }
 
 static int virtio_gpu_crtc_atomic_check(struct drm_crtc *crtc,
@@ -123,6 +119,17 @@ static int virtio_gpu_crtc_atomic_check(struct drm_crtc *crtc,
 static void virtio_gpu_crtc_atomic_flush(struct drm_crtc *crtc,
 					 struct drm_crtc_state *old_state)
 {
+	struct virtio_gpu_output *output = drm_crtc_to_virtio_gpu_output(crtc);
+
+	/*
+	 * virtio-gpu can't do modeset and plane update operations
+	 * independent from each other.  So the actual modeset happens
+	 * in the plane update callback, and here we just check
+	 * whenever we must force the modeset.
+	 */
+	if (drm_atomic_crtc_needs_modeset(crtc->state)) {
+		output->needs_modeset = true;
+	}
 }
 
 static const struct drm_crtc_helper_funcs virtio_gpu_crtc_helper_funcs = {
diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.h b/drivers/gpu/drm/virtio/virtgpu_drv.h
index 9ff9f4ac0522..fbc04272db4f 100644
--- a/drivers/gpu/drm/virtio/virtgpu_drv.h
+++ b/drivers/gpu/drm/virtio/virtgpu_drv.h
@@ -137,7 +137,7 @@ struct virtio_gpu_output {
 	struct edid *edid;
 	int cur_x;
 	int cur_y;
-	bool enabled;
+	bool needs_modeset;
 };
 #define drm_crtc_to_virtio_gpu_output(x) \
 	container_of(x, struct virtio_gpu_output, crtc)
diff --git a/drivers/gpu/drm/virtio/virtgpu_object.c b/drivers/gpu/drm/virtio/virtgpu_object.c
index e83651b7747d..842f8b61aa89 100644
--- a/drivers/gpu/drm/virtio/virtgpu_object.c
+++ b/drivers/gpu/drm/virtio/virtgpu_object.c
@@ -151,7 +151,13 @@ static int virtio_gpu_object_shmem_init(struct virtio_gpu_device *vgdev,
 	if (ret < 0)
 		return -EINVAL;
 
-	shmem->pages = drm_gem_shmem_get_pages_sgt(&bo->base.base);
+	/*
+	 * virtio_gpu uses drm_gem_shmem_get_sg_table instead of
+	 * drm_gem_shmem_get_pages_sgt because virtio has it's own set of
+	 * dma-ops. This is discouraged for other drivers, but should be fine
+	 * since virtio_gpu doesn't support dma-buf import from other devices.
+	 */
+	shmem->pages = drm_gem_shmem_get_sg_table(&bo->base.base);
 	if (!shmem->pages) {
 		drm_gem_shmem_unpin(&bo->base.base);
 		return -EINVAL;
diff --git a/drivers/gpu/drm/virtio/virtgpu_plane.c b/drivers/gpu/drm/virtio/virtgpu_plane.c
index 52d24179bcec..6a311cd93440 100644
--- a/drivers/gpu/drm/virtio/virtgpu_plane.c
+++ b/drivers/gpu/drm/virtio/virtgpu_plane.c
@@ -142,7 +142,7 @@ static void virtio_gpu_primary_plane_update(struct drm_plane *plane,
 	if (WARN_ON(!output))
 		return;
 
-	if (!plane->state->fb || !output->enabled) {
+	if (!plane->state->fb || !output->crtc.state->active) {
 		DRM_DEBUG("nofb\n");
 		virtio_gpu_cmd_set_scanout(vgdev, output->index, 0,
 					   plane->state->src_w >> 16,
@@ -163,7 +163,9 @@ static void virtio_gpu_primary_plane_update(struct drm_plane *plane,
 	    plane->state->src_w != old_state->src_w ||
 	    plane->state->src_h != old_state->src_h ||
 	    plane->state->src_x != old_state->src_x ||
-	    plane->state->src_y != old_state->src_y) {
+	    plane->state->src_y != old_state->src_y ||
+	    output->needs_modeset) {
+		output->needs_modeset = false;
 		DRM_DEBUG("handle 0x%x, crtc %dx%d+%d+%d, src %dx%d+%d+%d\n",
 			  bo->hw_res_handle,
 			  plane->state->crtc_w, plane->state->crtc_h,
diff --git a/drivers/gpu/drm/xen/xen_drm_front_gem.c b/drivers/gpu/drm/xen/xen_drm_front_gem.c
index 39ff95b75357..534daf37c97e 100644
--- a/drivers/gpu/drm/xen/xen_drm_front_gem.c
+++ b/drivers/gpu/drm/xen/xen_drm_front_gem.c
@@ -18,6 +18,7 @@
 #include <drm/drm_probe_helper.h>
 
 #include <xen/balloon.h>
+#include <xen/xen.h>
 
 #include "xen_drm_front.h"
 #include "xen_drm_front_gem.h"
@@ -99,8 +100,8 @@ static struct xen_gem_object *gem_create(struct drm_device *dev, size_t size)
 		 * allocate ballooned pages which will be used to map
 		 * grant references provided by the backend
 		 */
-		ret = alloc_xenballooned_pages(xen_obj->num_pages,
-					       xen_obj->pages);
+		ret = xen_alloc_unpopulated_pages(xen_obj->num_pages,
+					          xen_obj->pages);
 		if (ret < 0) {
 			DRM_ERROR("Cannot allocate %zu ballooned pages: %d\n",
 				  xen_obj->num_pages, ret);
@@ -152,8 +153,8 @@ void xen_drm_front_gem_free_object_unlocked(struct drm_gem_object *gem_obj)
 	} else {
 		if (xen_obj->pages) {
 			if (xen_obj->be_alloc) {
-				free_xenballooned_pages(xen_obj->num_pages,
-							xen_obj->pages);
+				xen_free_unpopulated_pages(xen_obj->num_pages,
+							   xen_obj->pages);
 				gem_free_pages_array(xen_obj);
 			} else {
 				drm_gem_put_pages(&xen_obj->base,
diff --git a/drivers/gpu/drm/xlnx/Kconfig b/drivers/gpu/drm/xlnx/Kconfig
index aa6cd889bd11..b52c6cdfc0b8 100644
--- a/drivers/gpu/drm/xlnx/Kconfig
+++ b/drivers/gpu/drm/xlnx/Kconfig
@@ -2,6 +2,7 @@ config DRM_ZYNQMP_DPSUB
 	tristate "ZynqMP DisplayPort Controller Driver"
 	depends on ARCH_ZYNQMP || COMPILE_TEST
 	depends on COMMON_CLK && DRM && OF
+	depends on DMADEVICES
 	select DMA_ENGINE
 	select DRM_GEM_CMA_HELPER
 	select DRM_KMS_CMA_HELPER
diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index 591106cf58fc..1d44bb635bb8 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -731,7 +731,7 @@ static void vmbus_wait_for_unload(void)
 	void *page_addr;
 	struct hv_message *msg;
 	struct vmbus_channel_message_header *hdr;
-	u32 message_type;
+	u32 message_type, i;
 
 	/*
 	 * CHANNELMSG_UNLOAD_RESPONSE is always delivered to the CPU which was
@@ -741,8 +741,11 @@ static void vmbus_wait_for_unload(void)
 	 * functional and vmbus_unload_response() will complete
 	 * vmbus_connection.unload_event. If not, the last thing we can do is
 	 * read message pages for all CPUs directly.
+	 *
+	 * Wait no more than 10 seconds so that the panic path can't get
+	 * hung forever in case the response message isn't seen.
 	 */
-	while (1) {
+	for (i = 0; i < 1000; i++) {
 		if (completion_done(&vmbus_connection.unload_event))
 			break;
 
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 910b6e90866c..946d0aba101f 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -2382,7 +2382,10 @@ static int vmbus_bus_suspend(struct device *dev)
 	if (atomic_read(&vmbus_connection.nr_chan_close_on_suspend) > 0)
 		wait_for_completion(&vmbus_connection.ready_for_suspend_event);
 
-	WARN_ON(atomic_read(&vmbus_connection.nr_chan_fixup_on_resume) != 0);
+	if (atomic_read(&vmbus_connection.nr_chan_fixup_on_resume) != 0) {
+		pr_err("Can not suspend due to a previous failed resuming\n");
+		return -EBUSY;
+	}
 
 	mutex_lock(&vmbus_connection.channel_mutex);
 
@@ -2456,7 +2459,9 @@ static int vmbus_bus_resume(struct device *dev)
 
 	vmbus_request_offers();
 
-	wait_for_completion(&vmbus_connection.ready_for_resume_event);
+	if (wait_for_completion_timeout(
+		&vmbus_connection.ready_for_resume_event, 10 * HZ) == 0)
+		pr_err("Some vmbus device is missing after suspending?\n");
 
 	/* Reset the event for the next suspend. */
 	reinit_completion(&vmbus_connection.ready_for_suspend_event);
diff --git a/drivers/i2c/algos/i2c-algo-pca.c b/drivers/i2c/algos/i2c-algo-pca.c
index 710fbef9a9c2..384af88e58ad 100644
--- a/drivers/i2c/algos/i2c-algo-pca.c
+++ b/drivers/i2c/algos/i2c-algo-pca.c
@@ -41,8 +41,22 @@ static void pca_reset(struct i2c_algo_pca_data *adap)
 		pca_outw(adap, I2C_PCA_INDPTR, I2C_PCA_IPRESET);
 		pca_outw(adap, I2C_PCA_IND, 0xA5);
 		pca_outw(adap, I2C_PCA_IND, 0x5A);
+
+		/*
+		 * After a reset we need to re-apply any configuration
+		 * (calculated in pca_init) to get the bus in a working state.
+		 */
+		pca_outw(adap, I2C_PCA_INDPTR, I2C_PCA_IMODE);
+		pca_outw(adap, I2C_PCA_IND, adap->bus_settings.mode);
+		pca_outw(adap, I2C_PCA_INDPTR, I2C_PCA_ISCLL);
+		pca_outw(adap, I2C_PCA_IND, adap->bus_settings.tlow);
+		pca_outw(adap, I2C_PCA_INDPTR, I2C_PCA_ISCLH);
+		pca_outw(adap, I2C_PCA_IND, adap->bus_settings.thi);
+
+		pca_set_con(adap, I2C_PCA_CON_ENSIO);
 	} else {
 		adap->reset_chip(adap->data);
+		pca_set_con(adap, I2C_PCA_CON_ENSIO | adap->bus_settings.clock_freq);
 	}
 }
 
@@ -423,13 +437,14 @@ static int pca_init(struct i2c_adapter *adap)
 				" Use the nominal frequency.\n", adap->name);
 		}
 
-		pca_reset(pca_data);
-
 		clock = pca_clock(pca_data);
 		printk(KERN_INFO "%s: Clock frequency is %dkHz\n",
 		     adap->name, freqs[clock]);
 
-		pca_set_con(pca_data, I2C_PCA_CON_ENSIO | clock);
+		/* Store settings as these will be needed when the PCA chip is reset */
+		pca_data->bus_settings.clock_freq = clock;
+
+		pca_reset(pca_data);
 	} else {
 		int clock;
 		int mode;
@@ -496,19 +511,15 @@ static int pca_init(struct i2c_adapter *adap)
 			thi = tlow * min_thi / min_tlow;
 		}
 
+		/* Store settings as these will be needed when the PCA chip is reset */
+		pca_data->bus_settings.mode = mode;
+		pca_data->bus_settings.tlow = tlow;
+		pca_data->bus_settings.thi = thi;
+
 		pca_reset(pca_data);
 
 		printk(KERN_INFO
 		     "%s: Clock frequency is %dHz\n", adap->name, clock * 100);
-
-		pca_outw(pca_data, I2C_PCA_INDPTR, I2C_PCA_IMODE);
-		pca_outw(pca_data, I2C_PCA_IND, mode);
-		pca_outw(pca_data, I2C_PCA_INDPTR, I2C_PCA_ISCLL);
-		pca_outw(pca_data, I2C_PCA_IND, tlow);
-		pca_outw(pca_data, I2C_PCA_INDPTR, I2C_PCA_ISCLH);
-		pca_outw(pca_data, I2C_PCA_IND, thi);
-
-		pca_set_con(pca_data, I2C_PCA_CON_ENSIO);
 	}
 	udelay(500); /* 500 us for oscillator to stabilise */
 
diff --git a/drivers/i2c/busses/i2c-aspeed.c b/drivers/i2c/busses/i2c-aspeed.c
index 31268074c422..724bf30600d6 100644
--- a/drivers/i2c/busses/i2c-aspeed.c
+++ b/drivers/i2c/busses/i2c-aspeed.c
@@ -69,6 +69,7 @@
  * These share bit definitions, so use the same values for the enable &
  * status bits.
  */
+#define ASPEED_I2CD_INTR_RECV_MASK			0xf000ffff
 #define ASPEED_I2CD_INTR_SDA_DL_TIMEOUT			BIT(14)
 #define ASPEED_I2CD_INTR_BUS_RECOVER_DONE		BIT(13)
 #define ASPEED_I2CD_INTR_SLAVE_MATCH			BIT(7)
@@ -604,6 +605,7 @@ static irqreturn_t aspeed_i2c_bus_irq(int irq, void *dev_id)
 	writel(irq_received & ~ASPEED_I2CD_INTR_RX_DONE,
 	       bus->base + ASPEED_I2C_INTR_STS_REG);
 	readl(bus->base + ASPEED_I2C_INTR_STS_REG);
+	irq_received &= ASPEED_I2CD_INTR_RECV_MASK;
 	irq_remaining = irq_received;
 
 #if IS_ENABLED(CONFIG_I2C_SLAVE)
diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c
index e32ef3f01fe8..ebb4c0b03057 100644
--- a/drivers/i2c/busses/i2c-i801.c
+++ b/drivers/i2c/busses/i2c-i801.c
@@ -1709,6 +1709,16 @@ static inline int i801_acpi_probe(struct i801_priv *priv) { return 0; }
 static inline void i801_acpi_remove(struct i801_priv *priv) { }
 #endif
 
+static unsigned char i801_setup_hstcfg(struct i801_priv *priv)
+{
+	unsigned char hstcfg = priv->original_hstcfg;
+
+	hstcfg &= ~SMBHSTCFG_I2C_EN;	/* SMBus timing */
+	hstcfg |= SMBHSTCFG_HST_EN;
+	pci_write_config_byte(priv->pci_dev, SMBHSTCFG, hstcfg);
+	return hstcfg;
+}
+
 static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id)
 {
 	unsigned char temp;
@@ -1830,14 +1840,10 @@ static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id)
 		return err;
 	}
 
-	pci_read_config_byte(priv->pci_dev, SMBHSTCFG, &temp);
-	priv->original_hstcfg = temp;
-	temp &= ~SMBHSTCFG_I2C_EN;	/* SMBus timing */
-	if (!(temp & SMBHSTCFG_HST_EN)) {
+	pci_read_config_byte(priv->pci_dev, SMBHSTCFG, &priv->original_hstcfg);
+	temp = i801_setup_hstcfg(priv);
+	if (!(priv->original_hstcfg & SMBHSTCFG_HST_EN))
 		dev_info(&dev->dev, "Enabling SMBus device\n");
-		temp |= SMBHSTCFG_HST_EN;
-	}
-	pci_write_config_byte(priv->pci_dev, SMBHSTCFG, temp);
 
 	if (temp & SMBHSTCFG_SMB_SMI_EN) {
 		dev_dbg(&dev->dev, "SMBus using interrupt SMI#\n");
@@ -1952,10 +1958,9 @@ static void i801_shutdown(struct pci_dev *dev)
 #ifdef CONFIG_PM_SLEEP
 static int i801_suspend(struct device *dev)
 {
-	struct pci_dev *pci_dev = to_pci_dev(dev);
-	struct i801_priv *priv = pci_get_drvdata(pci_dev);
+	struct i801_priv *priv = dev_get_drvdata(dev);
 
-	pci_write_config_byte(pci_dev, SMBHSTCFG, priv->original_hstcfg);
+	pci_write_config_byte(priv->pci_dev, SMBHSTCFG, priv->original_hstcfg);
 	return 0;
 }
 
@@ -1963,6 +1968,7 @@ static int i801_resume(struct device *dev)
 {
 	struct i801_priv *priv = dev_get_drvdata(dev);
 
+	i801_setup_hstcfg(priv);
 	i801_enable_host_notify(&priv->adapter);
 
 	return 0;
diff --git a/drivers/i2c/busses/i2c-mt65xx.c b/drivers/i2c/busses/i2c-mt65xx.c
index efc14041d45b..0cbdfbe605b5 100644
--- a/drivers/i2c/busses/i2c-mt65xx.c
+++ b/drivers/i2c/busses/i2c-mt65xx.c
@@ -681,8 +681,8 @@ static int mtk_i2c_calculate_speed(struct mtk_i2c *i2c, unsigned int clk_src,
 	unsigned int cnt_mul;
 	int ret = -EINVAL;
 
-	if (target_speed > I2C_MAX_FAST_MODE_PLUS_FREQ)
-		target_speed = I2C_MAX_FAST_MODE_PLUS_FREQ;
+	if (target_speed > I2C_MAX_HIGH_SPEED_MODE_FREQ)
+		target_speed = I2C_MAX_HIGH_SPEED_MODE_FREQ;
 
 	max_step_cnt = mtk_i2c_max_step_cnt(target_speed);
 	base_step_cnt = max_step_cnt;
@@ -759,7 +759,7 @@ static int mtk_i2c_set_speed(struct mtk_i2c *i2c, unsigned int parent_clk)
 	for (clk_div = 1; clk_div <= max_clk_div; clk_div++) {
 		clk_src = parent_clk / clk_div;
 
-		if (target_speed > I2C_MAX_FAST_MODE_FREQ) {
+		if (target_speed > I2C_MAX_FAST_MODE_PLUS_FREQ) {
 			/* Set master code speed register */
 			ret = mtk_i2c_calculate_speed(i2c, clk_src,
 						      I2C_MAX_FAST_MODE_FREQ,
diff --git a/drivers/i2c/busses/i2c-mxs.c b/drivers/i2c/busses/i2c-mxs.c
index 9587347447f0..c4b08a924461 100644
--- a/drivers/i2c/busses/i2c-mxs.c
+++ b/drivers/i2c/busses/i2c-mxs.c
@@ -25,6 +25,7 @@
 #include <linux/of_device.h>
 #include <linux/dma-mapping.h>
 #include <linux/dmaengine.h>
+#include <linux/dma/mxs-dma.h>
 
 #define DRIVER_NAME "mxs-i2c"
 
@@ -200,7 +201,8 @@ static int mxs_i2c_dma_setup_xfer(struct i2c_adapter *adap,
 		dma_map_sg(i2c->dev, &i2c->sg_io[0], 1, DMA_TO_DEVICE);
 		desc = dmaengine_prep_slave_sg(i2c->dmach, &i2c->sg_io[0], 1,
 					DMA_MEM_TO_DEV,
-					DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+					DMA_PREP_INTERRUPT |
+					MXS_DMA_CTRL_WAIT4END);
 		if (!desc) {
 			dev_err(i2c->dev,
 				"Failed to get DMA data write descriptor.\n");
@@ -228,7 +230,8 @@ static int mxs_i2c_dma_setup_xfer(struct i2c_adapter *adap,
 		dma_map_sg(i2c->dev, &i2c->sg_io[1], 1, DMA_FROM_DEVICE);
 		desc = dmaengine_prep_slave_sg(i2c->dmach, &i2c->sg_io[1], 1,
 					DMA_DEV_TO_MEM,
-					DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+					DMA_PREP_INTERRUPT |
+					MXS_DMA_CTRL_WAIT4END);
 		if (!desc) {
 			dev_err(i2c->dev,
 				"Failed to get DMA data write descriptor.\n");
@@ -260,7 +263,8 @@ static int mxs_i2c_dma_setup_xfer(struct i2c_adapter *adap,
 		dma_map_sg(i2c->dev, i2c->sg_io, 2, DMA_TO_DEVICE);
 		desc = dmaengine_prep_slave_sg(i2c->dmach, i2c->sg_io, 2,
 					DMA_MEM_TO_DEV,
-					DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+					DMA_PREP_INTERRUPT |
+					MXS_DMA_CTRL_WAIT4END);
 		if (!desc) {
 			dev_err(i2c->dev,
 				"Failed to get DMA data write descriptor.\n");
diff --git a/drivers/i2c/busses/i2c-npcm7xx.c b/drivers/i2c/busses/i2c-npcm7xx.c
index 75f07138a6fa..dfcf04e1967f 100644
--- a/drivers/i2c/busses/i2c-npcm7xx.c
+++ b/drivers/i2c/busses/i2c-npcm7xx.c
@@ -2093,8 +2093,12 @@ static int npcm_i2c_master_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs,
 		}
 	}
 
-	/* Adaptive TimeOut: astimated time in usec + 100% margin */
-	timeout_usec = (2 * 10000 / bus->bus_freq) * (2 + nread + nwrite);
+	/*
+	 * Adaptive TimeOut: estimated time in usec + 100% margin:
+	 * 2: double the timeout for clock stretching case
+	 * 9: bits per transaction (including the ack/nack)
+	 */
+	timeout_usec = (2 * 9 * USEC_PER_SEC / bus->bus_freq) * (2 + nread + nwrite);
 	timeout = max(msecs_to_jiffies(35), usecs_to_jiffies(timeout_usec));
 	if (nwrite >= 32 * 1024 || nread >= 32 * 1024) {
 		dev_err(bus->dev, "i2c%d buffer too big\n", bus->num);
diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c
index 5ec082e2039d..573b5da145d1 100644
--- a/drivers/i2c/i2c-core-base.c
+++ b/drivers/i2c/i2c-core-base.c
@@ -1464,8 +1464,8 @@ static int i2c_register_adapter(struct i2c_adapter *adap)
 
 	/* create pre-declared device nodes */
 	of_i2c_register_devices(adap);
-	i2c_acpi_register_devices(adap);
 	i2c_acpi_install_space_handler(adap);
+	i2c_acpi_register_devices(adap);
 
 	if (adap->nr < __i2c_first_dynamic_bus_num)
 		i2c_scan_static_board_info(adap);
diff --git a/drivers/iio/accel/bmc150-accel-core.c b/drivers/iio/accel/bmc150-accel-core.c
index 24864d9dfab5..48435865fdaf 100644
--- a/drivers/iio/accel/bmc150-accel-core.c
+++ b/drivers/iio/accel/bmc150-accel-core.c
@@ -189,6 +189,14 @@ struct bmc150_accel_data {
 	struct mutex mutex;
 	u8 fifo_mode, watermark;
 	s16 buffer[8];
+	/*
+	 * Ensure there is sufficient space and correct alignment for
+	 * the timestamp if enabled
+	 */
+	struct {
+		__le16 channels[3];
+		s64 ts __aligned(8);
+	} scan;
 	u8 bw_bits;
 	u32 slope_dur;
 	u32 slope_thres;
@@ -922,15 +930,16 @@ static int __bmc150_accel_fifo_flush(struct iio_dev *indio_dev,
 	 * now.
 	 */
 	for (i = 0; i < count; i++) {
-		u16 sample[8];
 		int j, bit;
 
 		j = 0;
 		for_each_set_bit(bit, indio_dev->active_scan_mask,
 				 indio_dev->masklength)
-			memcpy(&sample[j++], &buffer[i * 3 + bit], 2);
+			memcpy(&data->scan.channels[j++], &buffer[i * 3 + bit],
+			       sizeof(data->scan.channels[0]));
 
-		iio_push_to_buffers_with_timestamp(indio_dev, sample, tstamp);
+		iio_push_to_buffers_with_timestamp(indio_dev, &data->scan,
+						   tstamp);
 
 		tstamp += sample_period;
 	}
diff --git a/drivers/iio/accel/kxsd9.c b/drivers/iio/accel/kxsd9.c
index 66b2e4cf24cf..0e18b92e2099 100644
--- a/drivers/iio/accel/kxsd9.c
+++ b/drivers/iio/accel/kxsd9.c
@@ -209,14 +209,20 @@ static irqreturn_t kxsd9_trigger_handler(int irq, void *p)
 	const struct iio_poll_func *pf = p;
 	struct iio_dev *indio_dev = pf->indio_dev;
 	struct kxsd9_state *st = iio_priv(indio_dev);
+	/*
+	 * Ensure correct positioning and alignment of timestamp.
+	 * No need to zero initialize as all elements written.
+	 */
+	struct {
+		__be16 chan[4];
+		s64 ts __aligned(8);
+	} hw_values;
 	int ret;
-	/* 4 * 16bit values AND timestamp */
-	__be16 hw_values[8];
 
 	ret = regmap_bulk_read(st->map,
 			       KXSD9_REG_X,
-			       &hw_values,
-			       8);
+			       hw_values.chan,
+			       sizeof(hw_values.chan));
 	if (ret) {
 		dev_err(st->dev,
 			"error reading data\n");
@@ -224,7 +230,7 @@ static irqreturn_t kxsd9_trigger_handler(int irq, void *p)
 	}
 
 	iio_push_to_buffers_with_timestamp(indio_dev,
-					   hw_values,
+					   &hw_values,
 					   iio_get_time_ns(indio_dev));
 	iio_trigger_notify_done(indio_dev->trig);
 
diff --git a/drivers/iio/accel/mma7455_core.c b/drivers/iio/accel/mma7455_core.c
index 7e99bcb3398d..922bd38ff6ea 100644
--- a/drivers/iio/accel/mma7455_core.c
+++ b/drivers/iio/accel/mma7455_core.c
@@ -52,6 +52,14 @@
 
 struct mma7455_data {
 	struct regmap *regmap;
+	/*
+	 * Used to reorganize data.  Will ensure correct alignment of
+	 * the timestamp if present
+	 */
+	struct {
+		__le16 channels[3];
+		s64 ts __aligned(8);
+	} scan;
 };
 
 static int mma7455_drdy(struct mma7455_data *mma7455)
@@ -82,19 +90,19 @@ static irqreturn_t mma7455_trigger_handler(int irq, void *p)
 	struct iio_poll_func *pf = p;
 	struct iio_dev *indio_dev = pf->indio_dev;
 	struct mma7455_data *mma7455 = iio_priv(indio_dev);
-	u8 buf[16]; /* 3 x 16-bit channels + padding + ts */
 	int ret;
 
 	ret = mma7455_drdy(mma7455);
 	if (ret)
 		goto done;
 
-	ret = regmap_bulk_read(mma7455->regmap, MMA7455_REG_XOUTL, buf,
-			       sizeof(__le16) * 3);
+	ret = regmap_bulk_read(mma7455->regmap, MMA7455_REG_XOUTL,
+			       mma7455->scan.channels,
+			       sizeof(mma7455->scan.channels));
 	if (ret)
 		goto done;
 
-	iio_push_to_buffers_with_timestamp(indio_dev, buf,
+	iio_push_to_buffers_with_timestamp(indio_dev, &mma7455->scan,
 					   iio_get_time_ns(indio_dev));
 
 done:
diff --git a/drivers/iio/accel/mma8452.c b/drivers/iio/accel/mma8452.c
index 4e6e70250048..853febc29488 100644
--- a/drivers/iio/accel/mma8452.c
+++ b/drivers/iio/accel/mma8452.c
@@ -110,6 +110,12 @@ struct mma8452_data {
 	int sleep_val;
 	struct regulator *vdd_reg;
 	struct regulator *vddio_reg;
+
+	/* Ensure correct alignment of time stamp when present */
+	struct {
+		__be16 channels[3];
+		s64 ts __aligned(8);
+	} buffer;
 };
 
  /**
@@ -1091,14 +1097,13 @@ static irqreturn_t mma8452_trigger_handler(int irq, void *p)
 	struct iio_poll_func *pf = p;
 	struct iio_dev *indio_dev = pf->indio_dev;
 	struct mma8452_data *data = iio_priv(indio_dev);
-	u8 buffer[16]; /* 3 16-bit channels + padding + ts */
 	int ret;
 
-	ret = mma8452_read(data, (__be16 *)buffer);
+	ret = mma8452_read(data, data->buffer.channels);
 	if (ret < 0)
 		goto done;
 
-	iio_push_to_buffers_with_timestamp(indio_dev, buffer,
+	iio_push_to_buffers_with_timestamp(indio_dev, &data->buffer,
 					   iio_get_time_ns(indio_dev));
 
 done:
diff --git a/drivers/iio/adc/Kconfig b/drivers/iio/adc/Kconfig
index 66d9cc073157..d94dc800b842 100644
--- a/drivers/iio/adc/Kconfig
+++ b/drivers/iio/adc/Kconfig
@@ -865,6 +865,8 @@ config ROCKCHIP_SARADC
 	tristate "Rockchip SARADC driver"
 	depends on ARCH_ROCKCHIP || (ARM && COMPILE_TEST)
 	depends on RESET_CONTROLLER
+	select IIO_BUFFER
+	select IIO_TRIGGERED_BUFFER
 	help
 	  Say yes here to build support for the SARADC found in SoCs from
 	  Rockchip.
diff --git a/drivers/iio/adc/ina2xx-adc.c b/drivers/iio/adc/ina2xx-adc.c
index 5ed63e874292..b573ec60a8b8 100644
--- a/drivers/iio/adc/ina2xx-adc.c
+++ b/drivers/iio/adc/ina2xx-adc.c
@@ -146,6 +146,11 @@ struct ina2xx_chip_info {
 	int range_vbus; /* Bus voltage maximum in V */
 	int pga_gain_vshunt; /* Shunt voltage PGA gain */
 	bool allow_async_readout;
+	/* data buffer needs space for channel data and timestamp */
+	struct {
+		u16 chan[4];
+		u64 ts __aligned(8);
+	} scan;
 };
 
 static const struct ina2xx_config ina2xx_config[] = {
@@ -738,8 +743,6 @@ static int ina2xx_conversion_ready(struct iio_dev *indio_dev)
 static int ina2xx_work_buffer(struct iio_dev *indio_dev)
 {
 	struct ina2xx_chip_info *chip = iio_priv(indio_dev);
-	/* data buffer needs space for channel data and timestap */
-	unsigned short data[4 + sizeof(s64)/sizeof(short)];
 	int bit, ret, i = 0;
 	s64 time;
 
@@ -758,10 +761,10 @@ static int ina2xx_work_buffer(struct iio_dev *indio_dev)
 		if (ret < 0)
 			return ret;
 
-		data[i++] = val;
+		chip->scan.chan[i++] = val;
 	}
 
-	iio_push_to_buffers_with_timestamp(indio_dev, data, time);
+	iio_push_to_buffers_with_timestamp(indio_dev, &chip->scan, time);
 
 	return 0;
 };
diff --git a/drivers/iio/adc/max1118.c b/drivers/iio/adc/max1118.c
index 01b20e420ac4..6efb0b43d938 100644
--- a/drivers/iio/adc/max1118.c
+++ b/drivers/iio/adc/max1118.c
@@ -36,6 +36,11 @@ struct max1118 {
 	struct spi_device *spi;
 	struct mutex lock;
 	struct regulator *reg;
+	/* Ensure natural alignment of buffer elements */
+	struct {
+		u8 channels[2];
+		s64 ts __aligned(8);
+	} scan;
 
 	u8 data ____cacheline_aligned;
 };
@@ -166,7 +171,6 @@ static irqreturn_t max1118_trigger_handler(int irq, void *p)
 	struct iio_poll_func *pf = p;
 	struct iio_dev *indio_dev = pf->indio_dev;
 	struct max1118 *adc = iio_priv(indio_dev);
-	u8 data[16] = { }; /* 2x 8-bit ADC data + padding + 8 bytes timestamp */
 	int scan_index;
 	int i = 0;
 
@@ -184,10 +188,10 @@ static irqreturn_t max1118_trigger_handler(int irq, void *p)
 			goto out;
 		}
 
-		data[i] = ret;
+		adc->scan.channels[i] = ret;
 		i++;
 	}
-	iio_push_to_buffers_with_timestamp(indio_dev, data,
+	iio_push_to_buffers_with_timestamp(indio_dev, &adc->scan,
 					   iio_get_time_ns(indio_dev));
 out:
 	mutex_unlock(&adc->lock);
diff --git a/drivers/iio/adc/mcp3422.c b/drivers/iio/adc/mcp3422.c
index 5f1706d1c3c0..da353dcb1e9d 100644
--- a/drivers/iio/adc/mcp3422.c
+++ b/drivers/iio/adc/mcp3422.c
@@ -96,16 +96,12 @@ static int mcp3422_update_config(struct mcp3422 *adc, u8 newconfig)
 {
 	int ret;
 
-	mutex_lock(&adc->lock);
-
 	ret = i2c_master_send(adc->i2c, &newconfig, 1);
 	if (ret > 0) {
 		adc->config = newconfig;
 		ret = 0;
 	}
 
-	mutex_unlock(&adc->lock);
-
 	return ret;
 }
 
@@ -138,6 +134,8 @@ static int mcp3422_read_channel(struct mcp3422 *adc,
 	u8 config;
 	u8 req_channel = channel->channel;
 
+	mutex_lock(&adc->lock);
+
 	if (req_channel != MCP3422_CHANNEL(adc->config)) {
 		config = adc->config;
 		config &= ~MCP3422_CHANNEL_MASK;
@@ -145,12 +143,18 @@ static int mcp3422_read_channel(struct mcp3422 *adc,
 		config &= ~MCP3422_PGA_MASK;
 		config |= MCP3422_PGA_VALUE(adc->pga[req_channel]);
 		ret = mcp3422_update_config(adc, config);
-		if (ret < 0)
+		if (ret < 0) {
+			mutex_unlock(&adc->lock);
 			return ret;
+		}
 		msleep(mcp3422_read_times[MCP3422_SAMPLE_RATE(adc->config)]);
 	}
 
-	return mcp3422_read(adc, value, &config);
+	ret = mcp3422_read(adc, value, &config);
+
+	mutex_unlock(&adc->lock);
+
+	return ret;
 }
 
 static int mcp3422_read_raw(struct iio_dev *iio,
diff --git a/drivers/iio/adc/meson_saradc.c b/drivers/iio/adc/meson_saradc.c
index 93c2252c0b89..1a9189ba69ae 100644
--- a/drivers/iio/adc/meson_saradc.c
+++ b/drivers/iio/adc/meson_saradc.c
@@ -707,7 +707,7 @@ static int meson_sar_adc_temp_sensor_init(struct iio_dev *indio_dev)
 	size_t read_len;
 	int ret;
 
-	temperature_calib = devm_nvmem_cell_get(&indio_dev->dev,
+	temperature_calib = devm_nvmem_cell_get(indio_dev->dev.parent,
 						"temperature_calib");
 	if (IS_ERR(temperature_calib)) {
 		ret = PTR_ERR(temperature_calib);
diff --git a/drivers/iio/adc/ti-adc081c.c b/drivers/iio/adc/ti-adc081c.c
index 9426f70a8005..cf63983a54d9 100644
--- a/drivers/iio/adc/ti-adc081c.c
+++ b/drivers/iio/adc/ti-adc081c.c
@@ -33,6 +33,12 @@ struct adc081c {
 
 	/* 8, 10 or 12 */
 	int bits;
+
+	/* Ensure natural alignment of buffer elements */
+	struct {
+		u16 channel;
+		s64 ts __aligned(8);
+	} scan;
 };
 
 #define REG_CONV_RES 0x00
@@ -128,14 +134,13 @@ static irqreturn_t adc081c_trigger_handler(int irq, void *p)
 	struct iio_poll_func *pf = p;
 	struct iio_dev *indio_dev = pf->indio_dev;
 	struct adc081c *data = iio_priv(indio_dev);
-	u16 buf[8]; /* 2 bytes data + 6 bytes padding + 8 bytes timestamp */
 	int ret;
 
 	ret = i2c_smbus_read_word_swapped(data->i2c, REG_CONV_RES);
 	if (ret < 0)
 		goto out;
-	buf[0] = ret;
-	iio_push_to_buffers_with_timestamp(indio_dev, buf,
+	data->scan.channel = ret;
+	iio_push_to_buffers_with_timestamp(indio_dev, &data->scan,
 					   iio_get_time_ns(indio_dev));
 out:
 	iio_trigger_notify_done(indio_dev->trig);
diff --git a/drivers/iio/adc/ti-adc084s021.c b/drivers/iio/adc/ti-adc084s021.c
index 9017e1e24273..dfba34834a57 100644
--- a/drivers/iio/adc/ti-adc084s021.c
+++ b/drivers/iio/adc/ti-adc084s021.c
@@ -26,6 +26,11 @@ struct adc084s021 {
 	struct spi_transfer spi_trans;
 	struct regulator *reg;
 	struct mutex lock;
+	/* Buffer used to align data */
+	struct {
+		__be16 channels[4];
+		s64 ts __aligned(8);
+	} scan;
 	/*
 	 * DMA (thus cache coherency maintenance) requires the
 	 * transfer buffers to live in their own cache line.
@@ -141,14 +146,13 @@ static irqreturn_t adc084s021_buffer_trigger_handler(int irq, void *pollfunc)
 	struct iio_poll_func *pf = pollfunc;
 	struct iio_dev *indio_dev = pf->indio_dev;
 	struct adc084s021 *adc = iio_priv(indio_dev);
-	__be16 data[8] = {0}; /* 4 * 16-bit words of data + 8 bytes timestamp */
 
 	mutex_lock(&adc->lock);
 
-	if (adc084s021_adc_conversion(adc, &data) < 0)
+	if (adc084s021_adc_conversion(adc, adc->scan.channels) < 0)
 		dev_err(&adc->spi->dev, "Failed to read data\n");
 
-	iio_push_to_buffers_with_timestamp(indio_dev, data,
+	iio_push_to_buffers_with_timestamp(indio_dev, &adc->scan,
 					   iio_get_time_ns(indio_dev));
 	mutex_unlock(&adc->lock);
 	iio_trigger_notify_done(indio_dev->trig);
diff --git a/drivers/iio/adc/ti-ads1015.c b/drivers/iio/adc/ti-ads1015.c
index f42ab112986e..9fef39bcf997 100644
--- a/drivers/iio/adc/ti-ads1015.c
+++ b/drivers/iio/adc/ti-ads1015.c
@@ -316,6 +316,7 @@ static const struct iio_chan_spec ads1115_channels[] = {
 	IIO_CHAN_SOFT_TIMESTAMP(ADS1015_TIMESTAMP),
 };
 
+#ifdef CONFIG_PM
 static int ads1015_set_power_state(struct ads1015_data *data, bool on)
 {
 	int ret;
@@ -333,6 +334,15 @@ static int ads1015_set_power_state(struct ads1015_data *data, bool on)
 	return ret < 0 ? ret : 0;
 }
 
+#else /* !CONFIG_PM */
+
+static int ads1015_set_power_state(struct ads1015_data *data, bool on)
+{
+	return 0;
+}
+
+#endif /* !CONFIG_PM */
+
 static
 int ads1015_get_adc_result(struct ads1015_data *data, int chan, int *val)
 {
diff --git a/drivers/iio/chemical/ccs811.c b/drivers/iio/chemical/ccs811.c
index 2b007e7568b2..60dd87e96f5f 100644
--- a/drivers/iio/chemical/ccs811.c
+++ b/drivers/iio/chemical/ccs811.c
@@ -78,6 +78,11 @@ struct ccs811_data {
 	struct iio_trigger *drdy_trig;
 	struct gpio_desc *wakeup_gpio;
 	bool drdy_trig_on;
+	/* Ensures correct alignment of timestamp if present */
+	struct {
+		s16 channels[2];
+		s64 ts __aligned(8);
+	} scan;
 };
 
 static const struct iio_chan_spec ccs811_channels[] = {
@@ -327,17 +332,17 @@ static irqreturn_t ccs811_trigger_handler(int irq, void *p)
 	struct iio_dev *indio_dev = pf->indio_dev;
 	struct ccs811_data *data = iio_priv(indio_dev);
 	struct i2c_client *client = data->client;
-	s16 buf[8]; /* s16 eCO2 + s16 TVOC + padding + 8 byte timestamp */
 	int ret;
 
-	ret = i2c_smbus_read_i2c_block_data(client, CCS811_ALG_RESULT_DATA, 4,
-					    (u8 *)&buf);
+	ret = i2c_smbus_read_i2c_block_data(client, CCS811_ALG_RESULT_DATA,
+					    sizeof(data->scan.channels),
+					    (u8 *)data->scan.channels);
 	if (ret != 4) {
 		dev_err(&client->dev, "cannot read sensor data\n");
 		goto err;
 	}
 
-	iio_push_to_buffers_with_timestamp(indio_dev, buf,
+	iio_push_to_buffers_with_timestamp(indio_dev, &data->scan,
 					   iio_get_time_ns(indio_dev));
 
 err:
diff --git a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c
index ea480c1d4349..1bc6efa47316 100644
--- a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c
+++ b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c
@@ -72,10 +72,13 @@ static void get_default_min_max_freq(enum motionsensor_type type,
 
 	switch (type) {
 	case MOTIONSENSE_TYPE_ACCEL:
-	case MOTIONSENSE_TYPE_GYRO:
 		*min_freq = 12500;
 		*max_freq = 100000;
 		break;
+	case MOTIONSENSE_TYPE_GYRO:
+		*min_freq = 25000;
+		*max_freq = 100000;
+		break;
 	case MOTIONSENSE_TYPE_MAG:
 		*min_freq = 5000;
 		*max_freq = 25000;
diff --git a/drivers/iio/light/ltr501.c b/drivers/iio/light/ltr501.c
index 4bac0646398d..b4323d2db0b1 100644
--- a/drivers/iio/light/ltr501.c
+++ b/drivers/iio/light/ltr501.c
@@ -1243,13 +1243,16 @@ static irqreturn_t ltr501_trigger_handler(int irq, void *p)
 	struct iio_poll_func *pf = p;
 	struct iio_dev *indio_dev = pf->indio_dev;
 	struct ltr501_data *data = iio_priv(indio_dev);
-	u16 buf[8];
+	struct {
+		u16 channels[3];
+		s64 ts __aligned(8);
+	} scan;
 	__le16 als_buf[2];
 	u8 mask = 0;
 	int j = 0;
 	int ret, psdata;
 
-	memset(buf, 0, sizeof(buf));
+	memset(&scan, 0, sizeof(scan));
 
 	/* figure out which data needs to be ready */
 	if (test_bit(0, indio_dev->active_scan_mask) ||
@@ -1268,9 +1271,9 @@ static irqreturn_t ltr501_trigger_handler(int irq, void *p)
 		if (ret < 0)
 			return ret;
 		if (test_bit(0, indio_dev->active_scan_mask))
-			buf[j++] = le16_to_cpu(als_buf[1]);
+			scan.channels[j++] = le16_to_cpu(als_buf[1]);
 		if (test_bit(1, indio_dev->active_scan_mask))
-			buf[j++] = le16_to_cpu(als_buf[0]);
+			scan.channels[j++] = le16_to_cpu(als_buf[0]);
 	}
 
 	if (mask & LTR501_STATUS_PS_RDY) {
@@ -1278,10 +1281,10 @@ static irqreturn_t ltr501_trigger_handler(int irq, void *p)
 				       &psdata, 2);
 		if (ret < 0)
 			goto done;
-		buf[j++] = psdata & LTR501_PS_DATA_MASK;
+		scan.channels[j++] = psdata & LTR501_PS_DATA_MASK;
 	}
 
-	iio_push_to_buffers_with_timestamp(indio_dev, buf,
+	iio_push_to_buffers_with_timestamp(indio_dev, &scan,
 					   iio_get_time_ns(indio_dev));
 
 done:
diff --git a/drivers/iio/light/max44000.c b/drivers/iio/light/max44000.c
index aa8ed1e3e89a..b8e721bced5b 100644
--- a/drivers/iio/light/max44000.c
+++ b/drivers/iio/light/max44000.c
@@ -75,6 +75,11 @@
 struct max44000_data {
 	struct mutex lock;
 	struct regmap *regmap;
+	/* Ensure naturally aligned timestamp */
+	struct {
+		u16 channels[2];
+		s64 ts __aligned(8);
+	} scan;
 };
 
 /* Default scale is set to the minimum of 0.03125 or 1 / (1 << 5) lux */
@@ -488,7 +493,6 @@ static irqreturn_t max44000_trigger_handler(int irq, void *p)
 	struct iio_poll_func *pf = p;
 	struct iio_dev *indio_dev = pf->indio_dev;
 	struct max44000_data *data = iio_priv(indio_dev);
-	u16 buf[8]; /* 2x u16 + padding + 8 bytes timestamp */
 	int index = 0;
 	unsigned int regval;
 	int ret;
@@ -498,17 +502,17 @@ static irqreturn_t max44000_trigger_handler(int irq, void *p)
 		ret = max44000_read_alsval(data);
 		if (ret < 0)
 			goto out_unlock;
-		buf[index++] = ret;
+		data->scan.channels[index++] = ret;
 	}
 	if (test_bit(MAX44000_SCAN_INDEX_PRX, indio_dev->active_scan_mask)) {
 		ret = regmap_read(data->regmap, MAX44000_REG_PRX_DATA, &regval);
 		if (ret < 0)
 			goto out_unlock;
-		buf[index] = regval;
+		data->scan.channels[index] = regval;
 	}
 	mutex_unlock(&data->lock);
 
-	iio_push_to_buffers_with_timestamp(indio_dev, buf,
+	iio_push_to_buffers_with_timestamp(indio_dev, &data->scan,
 					   iio_get_time_ns(indio_dev));
 	iio_trigger_notify_done(indio_dev->trig);
 	return IRQ_HANDLED;
diff --git a/drivers/iio/magnetometer/ak8975.c b/drivers/iio/magnetometer/ak8975.c
index 03d71f796177..623766ff800b 100644
--- a/drivers/iio/magnetometer/ak8975.c
+++ b/drivers/iio/magnetometer/ak8975.c
@@ -366,6 +366,12 @@ struct ak8975_data {
 	struct iio_mount_matrix orientation;
 	struct regulator	*vdd;
 	struct regulator	*vid;
+
+	/* Ensure natural alignment of timestamp */
+	struct {
+		s16 channels[3];
+		s64 ts __aligned(8);
+	} scan;
 };
 
 /* Enable attached power regulator if any. */
@@ -793,7 +799,6 @@ static void ak8975_fill_buffer(struct iio_dev *indio_dev)
 	const struct i2c_client *client = data->client;
 	const struct ak_def *def = data->def;
 	int ret;
-	s16 buff[8]; /* 3 x 16 bits axis values + 1 aligned 64 bits timestamp */
 	__le16 fval[3];
 
 	mutex_lock(&data->lock);
@@ -816,12 +821,13 @@ static void ak8975_fill_buffer(struct iio_dev *indio_dev)
 	mutex_unlock(&data->lock);
 
 	/* Clamp to valid range. */
-	buff[0] = clamp_t(s16, le16_to_cpu(fval[0]), -def->range, def->range);
-	buff[1] = clamp_t(s16, le16_to_cpu(fval[1]), -def->range, def->range);
-	buff[2] = clamp_t(s16, le16_to_cpu(fval[2]), -def->range, def->range);
+	data->scan.channels[0] = clamp_t(s16, le16_to_cpu(fval[0]), -def->range, def->range);
+	data->scan.channels[1] = clamp_t(s16, le16_to_cpu(fval[1]), -def->range, def->range);
+	data->scan.channels[2] = clamp_t(s16, le16_to_cpu(fval[2]), -def->range, def->range);
 
-	iio_push_to_buffers_with_timestamp(indio_dev, buff,
+	iio_push_to_buffers_with_timestamp(indio_dev, &data->scan,
 					   iio_get_time_ns(indio_dev));
+
 	return;
 
 unlock:
diff --git a/drivers/iio/proximity/mb1232.c b/drivers/iio/proximity/mb1232.c
index 654564c45248..ad4b1fb2607a 100644
--- a/drivers/iio/proximity/mb1232.c
+++ b/drivers/iio/proximity/mb1232.c
@@ -40,6 +40,11 @@ struct mb1232_data {
 	 */
 	struct completion	ranging;
 	int			irqnr;
+	/* Ensure correct alignment of data to push to IIO buffer */
+	struct {
+		s16 distance;
+		s64 ts __aligned(8);
+	} scan;
 };
 
 static irqreturn_t mb1232_handle_irq(int irq, void *dev_id)
@@ -113,17 +118,13 @@ static irqreturn_t mb1232_trigger_handler(int irq, void *p)
 	struct iio_poll_func *pf = p;
 	struct iio_dev *indio_dev = pf->indio_dev;
 	struct mb1232_data *data = iio_priv(indio_dev);
-	/*
-	 * triggered buffer
-	 * 16-bit channel + 48-bit padding + 64-bit timestamp
-	 */
-	s16 buffer[8] = { 0 };
 
-	buffer[0] = mb1232_read_distance(data);
-	if (buffer[0] < 0)
+	data->scan.distance = mb1232_read_distance(data);
+	if (data->scan.distance < 0)
 		goto err;
 
-	iio_push_to_buffers_with_timestamp(indio_dev, buffer, pf->timestamp);
+	iio_push_to_buffers_with_timestamp(indio_dev, &data->scan,
+					   pf->timestamp);
 
 err:
 	iio_trigger_notify_done(indio_dev->trig);
diff --git a/drivers/infiniband/core/cq.c b/drivers/infiniband/core/cq.c
index 513825e424bf..a92fc3f90bb5 100644
--- a/drivers/infiniband/core/cq.c
+++ b/drivers/infiniband/core/cq.c
@@ -379,7 +379,7 @@ static int ib_alloc_cqs(struct ib_device *dev, unsigned int nr_cqes,
 {
 	LIST_HEAD(tmp_list);
 	unsigned int nr_cqs, i;
-	struct ib_cq *cq;
+	struct ib_cq *cq, *n;
 	int ret;
 
 	if (poll_ctx > IB_POLL_LAST_POOL_TYPE) {
@@ -412,7 +412,7 @@ static int ib_alloc_cqs(struct ib_device *dev, unsigned int nr_cqes,
 	return 0;
 
 out_free_cqs:
-	list_for_each_entry(cq, &tmp_list, pool_entry) {
+	list_for_each_entry_safe(cq, n, &tmp_list, pool_entry) {
 		cq->shared = false;
 		ib_free_cq(cq);
 	}
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index 3096e73797b7..307886737646 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -1801,7 +1801,7 @@ int ib_get_eth_speed(struct ib_device *dev, u8 port_num, u8 *speed, u8 *width)
 
 	dev_put(netdev);
 
-	if (!rc) {
+	if (!rc && lksettings.base.speed != (u32)SPEED_UNKNOWN) {
 		netdev_speed = lksettings.base.speed;
 	} else {
 		netdev_speed = SPEED_1000;
diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
index 5ee272d27aaa..1d7a9ca5240c 100644
--- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
@@ -752,12 +752,6 @@ static int bnxt_re_destroy_gsi_sqp(struct bnxt_re_qp *qp)
 	gsi_sqp = rdev->gsi_ctx.gsi_sqp;
 	gsi_sah = rdev->gsi_ctx.gsi_sah;
 
-	/* remove from active qp list */
-	mutex_lock(&rdev->qp_lock);
-	list_del(&gsi_sqp->list);
-	mutex_unlock(&rdev->qp_lock);
-	atomic_dec(&rdev->qp_count);
-
 	ibdev_dbg(&rdev->ibdev, "Destroy the shadow AH\n");
 	bnxt_qplib_destroy_ah(&rdev->qplib_res,
 			      &gsi_sah->qplib_ah,
@@ -772,6 +766,12 @@ static int bnxt_re_destroy_gsi_sqp(struct bnxt_re_qp *qp)
 	}
 	bnxt_qplib_free_qp_res(&rdev->qplib_res, &gsi_sqp->qplib_qp);
 
+	/* remove from active qp list */
+	mutex_lock(&rdev->qp_lock);
+	list_del(&gsi_sqp->list);
+	mutex_unlock(&rdev->qp_lock);
+	atomic_dec(&rdev->qp_count);
+
 	kfree(rdev->gsi_ctx.sqp_tbl);
 	kfree(gsi_sah);
 	kfree(gsi_sqp);
@@ -792,11 +792,6 @@ int bnxt_re_destroy_qp(struct ib_qp *ib_qp, struct ib_udata *udata)
 	unsigned int flags;
 	int rc;
 
-	mutex_lock(&rdev->qp_lock);
-	list_del(&qp->list);
-	mutex_unlock(&rdev->qp_lock);
-	atomic_dec(&rdev->qp_count);
-
 	bnxt_qplib_flush_cqn_wq(&qp->qplib_qp);
 
 	rc = bnxt_qplib_destroy_qp(&rdev->qplib_res, &qp->qplib_qp);
@@ -819,6 +814,11 @@ int bnxt_re_destroy_qp(struct ib_qp *ib_qp, struct ib_udata *udata)
 			goto sh_fail;
 	}
 
+	mutex_lock(&rdev->qp_lock);
+	list_del(&qp->list);
+	mutex_unlock(&rdev->qp_lock);
+	atomic_dec(&rdev->qp_count);
+
 	ib_umem_release(qp->rumem);
 	ib_umem_release(qp->sumem);
 
@@ -3264,6 +3264,19 @@ static void bnxt_re_process_res_rawqp1_wc(struct ib_wc *wc,
 	wc->wc_flags |= IB_WC_GRH;
 }
 
+static bool bnxt_re_check_if_vlan_valid(struct bnxt_re_dev *rdev,
+					u16 vlan_id)
+{
+	/*
+	 * Check if the vlan is configured in the host.  If not configured, it
+	 * can be a transparent VLAN. So dont report the vlan id.
+	 */
+	if (!__vlan_find_dev_deep_rcu(rdev->netdev,
+				      htons(ETH_P_8021Q), vlan_id))
+		return false;
+	return true;
+}
+
 static bool bnxt_re_is_vlan_pkt(struct bnxt_qplib_cqe *orig_cqe,
 				u16 *vid, u8 *sl)
 {
@@ -3332,9 +3345,11 @@ static void bnxt_re_process_res_shadow_qp_wc(struct bnxt_re_qp *gsi_sqp,
 	wc->src_qp = orig_cqe->src_qp;
 	memcpy(wc->smac, orig_cqe->smac, ETH_ALEN);
 	if (bnxt_re_is_vlan_pkt(orig_cqe, &vlan_id, &sl)) {
-		wc->vlan_id = vlan_id;
-		wc->sl = sl;
-		wc->wc_flags |= IB_WC_WITH_VLAN;
+		if (bnxt_re_check_if_vlan_valid(rdev, vlan_id)) {
+			wc->vlan_id = vlan_id;
+			wc->sl = sl;
+			wc->wc_flags |= IB_WC_WITH_VLAN;
+		}
 	}
 	wc->port_num = 1;
 	wc->vendor_err = orig_cqe->status;
diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c
index 17ac8b7c5710..53aee5a42ab8 100644
--- a/drivers/infiniband/hw/bnxt_re/main.c
+++ b/drivers/infiniband/hw/bnxt_re/main.c
@@ -1009,7 +1009,6 @@ static void bnxt_re_free_res(struct bnxt_re_dev *rdev)
 static int bnxt_re_alloc_res(struct bnxt_re_dev *rdev)
 {
 	struct bnxt_re_ring_attr rattr = {};
-	struct bnxt_qplib_ctx *qplib_ctx;
 	int num_vec_created = 0;
 	int rc = 0, i;
 	u8 type;
@@ -1032,13 +1031,11 @@ static int bnxt_re_alloc_res(struct bnxt_re_dev *rdev)
 	if (rc)
 		goto dealloc_res;
 
-	qplib_ctx = &rdev->qplib_ctx;
 	for (i = 0; i < rdev->num_msix - 1; i++) {
 		struct bnxt_qplib_nq *nq;
 
 		nq = &rdev->nq[i];
-		nq->hwq.max_elements = (qplib_ctx->cq_count +
-					qplib_ctx->srqc_count + 2);
+		nq->hwq.max_elements = BNXT_QPLIB_NQE_MAX_CNT;
 		rc = bnxt_qplib_alloc_nq(&rdev->qplib_res, &rdev->nq[i]);
 		if (rc) {
 			ibdev_err(&rdev->ibdev, "Alloc Failed NQ%d rc:%#x",
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c
index d60e3dcea087..f78da54a0bc5 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c
@@ -818,6 +818,7 @@ int bnxt_qplib_create_qp1(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp)
 	u16 cmd_flags = 0;
 	u32 qp_flags = 0;
 	u8 pg_sz_lvl;
+	u32 tbl_indx;
 	int rc;
 
 	RCFW_CMD_PREP(req, CREATE_QP1, cmd_flags);
@@ -907,8 +908,9 @@ int bnxt_qplib_create_qp1(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp)
 		rq->dbinfo.db = qp->dpi->dbr;
 		rq->dbinfo.max_slot = bnxt_qplib_set_rq_max_slot(rq->wqe_size);
 	}
-	rcfw->qp_tbl[qp->id].qp_id = qp->id;
-	rcfw->qp_tbl[qp->id].qp_handle = (void *)qp;
+	tbl_indx = map_qp_id_to_tbl_indx(qp->id, rcfw);
+	rcfw->qp_tbl[tbl_indx].qp_id = qp->id;
+	rcfw->qp_tbl[tbl_indx].qp_handle = (void *)qp;
 
 	return 0;
 
@@ -935,10 +937,10 @@ static void bnxt_qplib_init_psn_ptr(struct bnxt_qplib_qp *qp, int size)
 
 	sq = &qp->sq;
 	hwq = &sq->hwq;
+	/* First psn entry */
 	fpsne = (u64)bnxt_qplib_get_qe(hwq, hwq->depth, &psn_pg);
 	if (!IS_ALIGNED(fpsne, PAGE_SIZE))
-		indx_pad = ALIGN(fpsne, PAGE_SIZE) / size;
-
+		indx_pad = (fpsne & ~PAGE_MASK) / size;
 	hwq->pad_pgofft = indx_pad;
 	hwq->pad_pg = (u64 *)psn_pg;
 	hwq->pad_stride = size;
@@ -959,6 +961,7 @@ int bnxt_qplib_create_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp)
 	u16 cmd_flags = 0;
 	u32 qp_flags = 0;
 	u8 pg_sz_lvl;
+	u32 tbl_indx;
 	u16 nsge;
 
 	RCFW_CMD_PREP(req, CREATE_QP, cmd_flags);
@@ -1111,8 +1114,9 @@ int bnxt_qplib_create_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp)
 		rq->dbinfo.db = qp->dpi->dbr;
 		rq->dbinfo.max_slot = bnxt_qplib_set_rq_max_slot(rq->wqe_size);
 	}
-	rcfw->qp_tbl[qp->id].qp_id = qp->id;
-	rcfw->qp_tbl[qp->id].qp_handle = (void *)qp;
+	tbl_indx = map_qp_id_to_tbl_indx(qp->id, rcfw);
+	rcfw->qp_tbl[tbl_indx].qp_id = qp->id;
+	rcfw->qp_tbl[tbl_indx].qp_handle = (void *)qp;
 
 	return 0;
 fail:
@@ -1457,10 +1461,12 @@ int bnxt_qplib_destroy_qp(struct bnxt_qplib_res *res,
 	struct cmdq_destroy_qp req;
 	struct creq_destroy_qp_resp resp;
 	u16 cmd_flags = 0;
+	u32 tbl_indx;
 	int rc;
 
-	rcfw->qp_tbl[qp->id].qp_id = BNXT_QPLIB_QP_ID_INVALID;
-	rcfw->qp_tbl[qp->id].qp_handle = NULL;
+	tbl_indx = map_qp_id_to_tbl_indx(qp->id, rcfw);
+	rcfw->qp_tbl[tbl_indx].qp_id = BNXT_QPLIB_QP_ID_INVALID;
+	rcfw->qp_tbl[tbl_indx].qp_handle = NULL;
 
 	RCFW_CMD_PREP(req, DESTROY_QP, cmd_flags);
 
@@ -1468,8 +1474,8 @@ int bnxt_qplib_destroy_qp(struct bnxt_qplib_res *res,
 	rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req,
 					  (void *)&resp, NULL, 0);
 	if (rc) {
-		rcfw->qp_tbl[qp->id].qp_id = qp->id;
-		rcfw->qp_tbl[qp->id].qp_handle = qp;
+		rcfw->qp_tbl[tbl_indx].qp_id = qp->id;
+		rcfw->qp_tbl[tbl_indx].qp_handle = qp;
 		return rc;
 	}
 
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c
index 4e211162acee..f7736e34ac64 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c
@@ -307,14 +307,15 @@ static int bnxt_qplib_process_qp_event(struct bnxt_qplib_rcfw *rcfw,
 	__le16  mcookie;
 	u16 cookie;
 	int rc = 0;
-	u32 qp_id;
+	u32 qp_id, tbl_indx;
 
 	pdev = rcfw->pdev;
 	switch (qp_event->event) {
 	case CREQ_QP_EVENT_EVENT_QP_ERROR_NOTIFICATION:
 		err_event = (struct creq_qp_error_notification *)qp_event;
 		qp_id = le32_to_cpu(err_event->xid);
-		qp = rcfw->qp_tbl[qp_id].qp_handle;
+		tbl_indx = map_qp_id_to_tbl_indx(qp_id, rcfw);
+		qp = rcfw->qp_tbl[tbl_indx].qp_handle;
 		dev_dbg(&pdev->dev, "Received QP error notification\n");
 		dev_dbg(&pdev->dev,
 			"qpid 0x%x, req_err=0x%x, resp_err=0x%x\n",
@@ -615,8 +616,9 @@ int bnxt_qplib_alloc_rcfw_channel(struct bnxt_qplib_res *res,
 
 	cmdq->bmap_size = bmap_size;
 
-	rcfw->qp_tbl_size = qp_tbl_sz;
-	rcfw->qp_tbl = kcalloc(qp_tbl_sz, sizeof(struct bnxt_qplib_qp_node),
+	/* Allocate one extra to hold the QP1 entries */
+	rcfw->qp_tbl_size = qp_tbl_sz + 1;
+	rcfw->qp_tbl = kcalloc(rcfw->qp_tbl_size, sizeof(struct bnxt_qplib_qp_node),
 			       GFP_KERNEL);
 	if (!rcfw->qp_tbl)
 		goto fail;
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h
index 157387636d00..5f2f0a5a3560 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h
+++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h
@@ -216,4 +216,9 @@ int bnxt_qplib_deinit_rcfw(struct bnxt_qplib_rcfw *rcfw);
 int bnxt_qplib_init_rcfw(struct bnxt_qplib_rcfw *rcfw,
 			 struct bnxt_qplib_ctx *ctx, int is_virtfn);
 void bnxt_qplib_mark_qp_error(void *qp_handle);
+static inline u32 map_qp_id_to_tbl_indx(u32 qid, struct bnxt_qplib_rcfw *rcfw)
+{
+	/* Last index of the qp_tbl is for QP1 ie. qp_tbl_size - 1*/
+	return (qid == 1) ? rcfw->qp_tbl_size - 1 : qid % rcfw->qp_tbl_size - 2;
+}
 #endif /* __BNXT_QPLIB_RCFW_H__ */
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_sp.c b/drivers/infiniband/hw/bnxt_re/qplib_sp.c
index 4cd475ea97a2..64d44f51db4b 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_sp.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.c
@@ -149,7 +149,7 @@ int bnxt_qplib_get_dev_attr(struct bnxt_qplib_rcfw *rcfw,
 	attr->max_inline_data = le32_to_cpu(sb->max_inline_data);
 	attr->l2_db_size = (sb->l2_db_space_size + 1) *
 			    (0x01 << RCFW_DBR_BASE_PAGE_SHIFT);
-	attr->max_sgid = le32_to_cpu(sb->max_gid);
+	attr->max_sgid = BNXT_QPLIB_NUM_GIDS_SUPPORTED;
 
 	bnxt_qplib_query_version(rcfw, attr->fw_ver);
 
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_sp.h b/drivers/infiniband/hw/bnxt_re/qplib_sp.h
index 6404f0da1051..967890cd81f2 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_sp.h
+++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.h
@@ -47,6 +47,7 @@
 struct bnxt_qplib_dev_attr {
 #define FW_VER_ARR_LEN			4
 	u8				fw_ver[FW_VER_ARR_LEN];
+#define BNXT_QPLIB_NUM_GIDS_SUPPORTED	256
 	u16				max_sgid;
 	u16				max_mrw;
 	u32				max_qp;
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 5e7910a517da..bd4f975e7f9a 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -784,7 +784,8 @@ static int eth_link_query_port(struct ib_device *ibdev, u8 port,
 	props->ip_gids = true;
 	props->gid_tbl_len	= mdev->dev->caps.gid_table_len[port];
 	props->max_msg_sz	= mdev->dev->caps.max_msg_sz;
-	props->pkey_tbl_len	= 1;
+	if (mdev->dev->caps.pkey_table_len[port])
+		props->pkey_tbl_len = 1;
 	props->max_mtu		= IB_MTU_4096;
 	props->max_vl_num	= 2;
 	props->state		= IB_PORT_DOWN;
diff --git a/drivers/infiniband/sw/rxe/rxe.c b/drivers/infiniband/sw/rxe/rxe.c
index 907203afbd99..77f2c7cd1216 100644
--- a/drivers/infiniband/sw/rxe/rxe.c
+++ b/drivers/infiniband/sw/rxe/rxe.c
@@ -40,6 +40,8 @@ MODULE_AUTHOR("Bob Pearson, Frank Zago, John Groves, Kamal Heib");
 MODULE_DESCRIPTION("Soft RDMA transport");
 MODULE_LICENSE("Dual BSD/GPL");
 
+bool rxe_initialized;
+
 /* free resources for a rxe device all objects created for this device must
  * have been destroyed
  */
@@ -315,6 +317,7 @@ static int __init rxe_module_init(void)
 		return err;
 
 	rdma_link_register(&rxe_link_ops);
+	rxe_initialized = true;
 	pr_info("loaded\n");
 	return 0;
 }
@@ -326,6 +329,7 @@ static void __exit rxe_module_exit(void)
 	rxe_net_exit();
 	rxe_cache_exit();
 
+	rxe_initialized = false;
 	pr_info("unloaded\n");
 }
 
diff --git a/drivers/infiniband/sw/rxe/rxe.h b/drivers/infiniband/sw/rxe/rxe.h
index fb07eed9e402..cae1b0a24c85 100644
--- a/drivers/infiniband/sw/rxe/rxe.h
+++ b/drivers/infiniband/sw/rxe/rxe.h
@@ -67,6 +67,8 @@
 
 #define RXE_ROCE_V2_SPORT		(0xc000)
 
+extern bool rxe_initialized;
+
 static inline u32 rxe_crc32(struct rxe_dev *rxe,
 			    u32 crc, void *next, size_t len)
 {
diff --git a/drivers/infiniband/sw/rxe/rxe_mr.c b/drivers/infiniband/sw/rxe/rxe_mr.c
index cdd811a45120..ce24144de16a 100644
--- a/drivers/infiniband/sw/rxe/rxe_mr.c
+++ b/drivers/infiniband/sw/rxe/rxe_mr.c
@@ -205,6 +205,7 @@ int rxe_mem_init_user(struct rxe_pd *pd, u64 start,
 			vaddr = page_address(sg_page_iter_page(&sg_iter));
 			if (!vaddr) {
 				pr_warn("null vaddr\n");
+				ib_umem_release(umem);
 				err = -ENOMEM;
 				goto err1;
 			}
diff --git a/drivers/infiniband/sw/rxe/rxe_sysfs.c b/drivers/infiniband/sw/rxe/rxe_sysfs.c
index ccda5f5a3bc0..2af31d421bfc 100644
--- a/drivers/infiniband/sw/rxe/rxe_sysfs.c
+++ b/drivers/infiniband/sw/rxe/rxe_sysfs.c
@@ -61,6 +61,11 @@ static int rxe_param_set_add(const char *val, const struct kernel_param *kp)
 	struct net_device *ndev;
 	struct rxe_dev *exists;
 
+	if (!rxe_initialized) {
+		pr_err("Module parameters are not supported, use rdma link add or rxe_cfg\n");
+		return -EAGAIN;
+	}
+
 	len = sanitize_arg(val, intf, sizeof(intf));
 	if (!len) {
 		pr_err("add: invalid interface name\n");
diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c
index 658939e5c34a..8522e9a3e914 100644
--- a/drivers/infiniband/sw/rxe/rxe_verbs.c
+++ b/drivers/infiniband/sw/rxe/rxe_verbs.c
@@ -1056,7 +1056,7 @@ static ssize_t parent_show(struct device *device,
 	struct rxe_dev *rxe =
 		rdma_device_to_drv_device(device, struct rxe_dev, ib_dev);
 
-	return snprintf(buf, 16, "%s\n", rxe_parent_name(rxe, 1));
+	return scnprintf(buf, PAGE_SIZE, "%s\n", rxe_parent_name(rxe, 1));
 }
 
 static DEVICE_ATTR_RO(parent);
diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c
index e86acda3cf8c..695f701dc43d 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.c
+++ b/drivers/infiniband/ulp/isert/ib_isert.c
@@ -140,15 +140,15 @@ isert_alloc_rx_descriptors(struct isert_conn *isert_conn)
 	rx_desc = isert_conn->rx_descs;
 
 	for (i = 0; i < ISERT_QP_MAX_RECV_DTOS; i++, rx_desc++)  {
-		dma_addr = ib_dma_map_single(ib_dev, (void *)rx_desc,
-					ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE);
+		dma_addr = ib_dma_map_single(ib_dev, rx_desc->buf,
+					ISER_RX_SIZE, DMA_FROM_DEVICE);
 		if (ib_dma_mapping_error(ib_dev, dma_addr))
 			goto dma_map_fail;
 
 		rx_desc->dma_addr = dma_addr;
 
 		rx_sg = &rx_desc->rx_sg;
-		rx_sg->addr = rx_desc->dma_addr;
+		rx_sg->addr = rx_desc->dma_addr + isert_get_hdr_offset(rx_desc);
 		rx_sg->length = ISER_RX_PAYLOAD_SIZE;
 		rx_sg->lkey = device->pd->local_dma_lkey;
 		rx_desc->rx_cqe.done = isert_recv_done;
@@ -160,7 +160,7 @@ dma_map_fail:
 	rx_desc = isert_conn->rx_descs;
 	for (j = 0; j < i; j++, rx_desc++) {
 		ib_dma_unmap_single(ib_dev, rx_desc->dma_addr,
-				    ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE);
+				    ISER_RX_SIZE, DMA_FROM_DEVICE);
 	}
 	kfree(isert_conn->rx_descs);
 	isert_conn->rx_descs = NULL;
@@ -181,7 +181,7 @@ isert_free_rx_descriptors(struct isert_conn *isert_conn)
 	rx_desc = isert_conn->rx_descs;
 	for (i = 0; i < ISERT_QP_MAX_RECV_DTOS; i++, rx_desc++)  {
 		ib_dma_unmap_single(ib_dev, rx_desc->dma_addr,
-				    ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE);
+				    ISER_RX_SIZE, DMA_FROM_DEVICE);
 	}
 
 	kfree(isert_conn->rx_descs);
@@ -299,10 +299,9 @@ isert_free_login_buf(struct isert_conn *isert_conn)
 			    ISER_RX_PAYLOAD_SIZE, DMA_TO_DEVICE);
 	kfree(isert_conn->login_rsp_buf);
 
-	ib_dma_unmap_single(ib_dev, isert_conn->login_req_dma,
-			    ISER_RX_PAYLOAD_SIZE,
-			    DMA_FROM_DEVICE);
-	kfree(isert_conn->login_req_buf);
+	ib_dma_unmap_single(ib_dev, isert_conn->login_desc->dma_addr,
+			    ISER_RX_SIZE, DMA_FROM_DEVICE);
+	kfree(isert_conn->login_desc);
 }
 
 static int
@@ -311,25 +310,25 @@ isert_alloc_login_buf(struct isert_conn *isert_conn,
 {
 	int ret;
 
-	isert_conn->login_req_buf = kzalloc(sizeof(*isert_conn->login_req_buf),
+	isert_conn->login_desc = kzalloc(sizeof(*isert_conn->login_desc),
 			GFP_KERNEL);
-	if (!isert_conn->login_req_buf)
+	if (!isert_conn->login_desc)
 		return -ENOMEM;
 
-	isert_conn->login_req_dma = ib_dma_map_single(ib_dev,
-				isert_conn->login_req_buf,
-				ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE);
-	ret = ib_dma_mapping_error(ib_dev, isert_conn->login_req_dma);
+	isert_conn->login_desc->dma_addr = ib_dma_map_single(ib_dev,
+				isert_conn->login_desc->buf,
+				ISER_RX_SIZE, DMA_FROM_DEVICE);
+	ret = ib_dma_mapping_error(ib_dev, isert_conn->login_desc->dma_addr);
 	if (ret) {
-		isert_err("login_req_dma mapping error: %d\n", ret);
-		isert_conn->login_req_dma = 0;
-		goto out_free_login_req_buf;
+		isert_err("login_desc dma mapping error: %d\n", ret);
+		isert_conn->login_desc->dma_addr = 0;
+		goto out_free_login_desc;
 	}
 
 	isert_conn->login_rsp_buf = kzalloc(ISER_RX_PAYLOAD_SIZE, GFP_KERNEL);
 	if (!isert_conn->login_rsp_buf) {
 		ret = -ENOMEM;
-		goto out_unmap_login_req_buf;
+		goto out_unmap_login_desc;
 	}
 
 	isert_conn->login_rsp_dma = ib_dma_map_single(ib_dev,
@@ -346,11 +345,11 @@ isert_alloc_login_buf(struct isert_conn *isert_conn,
 
 out_free_login_rsp_buf:
 	kfree(isert_conn->login_rsp_buf);
-out_unmap_login_req_buf:
-	ib_dma_unmap_single(ib_dev, isert_conn->login_req_dma,
-			    ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE);
-out_free_login_req_buf:
-	kfree(isert_conn->login_req_buf);
+out_unmap_login_desc:
+	ib_dma_unmap_single(ib_dev, isert_conn->login_desc->dma_addr,
+			    ISER_RX_SIZE, DMA_FROM_DEVICE);
+out_free_login_desc:
+	kfree(isert_conn->login_desc);
 	return ret;
 }
 
@@ -476,7 +475,7 @@ isert_connect_release(struct isert_conn *isert_conn)
 	if (isert_conn->qp)
 		isert_destroy_qp(isert_conn);
 
-	if (isert_conn->login_req_buf)
+	if (isert_conn->login_desc)
 		isert_free_login_buf(isert_conn);
 
 	isert_device_put(device);
@@ -862,17 +861,18 @@ isert_login_post_recv(struct isert_conn *isert_conn)
 	int ret;
 
 	memset(&sge, 0, sizeof(struct ib_sge));
-	sge.addr = isert_conn->login_req_dma;
+	sge.addr = isert_conn->login_desc->dma_addr +
+		isert_get_hdr_offset(isert_conn->login_desc);
 	sge.length = ISER_RX_PAYLOAD_SIZE;
 	sge.lkey = isert_conn->device->pd->local_dma_lkey;
 
 	isert_dbg("Setup sge: addr: %llx length: %d 0x%08x\n",
 		sge.addr, sge.length, sge.lkey);
 
-	isert_conn->login_req_buf->rx_cqe.done = isert_login_recv_done;
+	isert_conn->login_desc->rx_cqe.done = isert_login_recv_done;
 
 	memset(&rx_wr, 0, sizeof(struct ib_recv_wr));
-	rx_wr.wr_cqe = &isert_conn->login_req_buf->rx_cqe;
+	rx_wr.wr_cqe = &isert_conn->login_desc->rx_cqe;
 	rx_wr.sg_list = &sge;
 	rx_wr.num_sge = 1;
 
@@ -949,7 +949,7 @@ post_send:
 static void
 isert_rx_login_req(struct isert_conn *isert_conn)
 {
-	struct iser_rx_desc *rx_desc = isert_conn->login_req_buf;
+	struct iser_rx_desc *rx_desc = isert_conn->login_desc;
 	int rx_buflen = isert_conn->login_req_len;
 	struct iscsi_conn *conn = isert_conn->conn;
 	struct iscsi_login *login = conn->conn_login;
@@ -961,7 +961,7 @@ isert_rx_login_req(struct isert_conn *isert_conn)
 
 	if (login->first_request) {
 		struct iscsi_login_req *login_req =
-			(struct iscsi_login_req *)&rx_desc->iscsi_header;
+			(struct iscsi_login_req *)isert_get_iscsi_hdr(rx_desc);
 		/*
 		 * Setup the initial iscsi_login values from the leading
 		 * login request PDU.
@@ -980,13 +980,13 @@ isert_rx_login_req(struct isert_conn *isert_conn)
 		login->tsih		= be16_to_cpu(login_req->tsih);
 	}
 
-	memcpy(&login->req[0], (void *)&rx_desc->iscsi_header, ISCSI_HDR_LEN);
+	memcpy(&login->req[0], isert_get_iscsi_hdr(rx_desc), ISCSI_HDR_LEN);
 
 	size = min(rx_buflen, MAX_KEY_VALUE_PAIRS);
 	isert_dbg("Using login payload size: %d, rx_buflen: %d "
 		  "MAX_KEY_VALUE_PAIRS: %d\n", size, rx_buflen,
 		  MAX_KEY_VALUE_PAIRS);
-	memcpy(login->req_buf, &rx_desc->data[0], size);
+	memcpy(login->req_buf, isert_get_data(rx_desc), size);
 
 	if (login->first_request) {
 		complete(&isert_conn->login_comp);
@@ -1051,14 +1051,15 @@ isert_handle_scsi_cmd(struct isert_conn *isert_conn,
 	if (imm_data_len != data_len) {
 		sg_nents = max(1UL, DIV_ROUND_UP(imm_data_len, PAGE_SIZE));
 		sg_copy_from_buffer(cmd->se_cmd.t_data_sg, sg_nents,
-				    &rx_desc->data[0], imm_data_len);
+				    isert_get_data(rx_desc), imm_data_len);
 		isert_dbg("Copy Immediate sg_nents: %u imm_data_len: %d\n",
 			  sg_nents, imm_data_len);
 	} else {
 		sg_init_table(&isert_cmd->sg, 1);
 		cmd->se_cmd.t_data_sg = &isert_cmd->sg;
 		cmd->se_cmd.t_data_nents = 1;
-		sg_set_buf(&isert_cmd->sg, &rx_desc->data[0], imm_data_len);
+		sg_set_buf(&isert_cmd->sg, isert_get_data(rx_desc),
+				imm_data_len);
 		isert_dbg("Transfer Immediate imm_data_len: %d\n",
 			  imm_data_len);
 	}
@@ -1127,9 +1128,9 @@ isert_handle_iscsi_dataout(struct isert_conn *isert_conn,
 	}
 	isert_dbg("Copying DataOut: sg_start: %p, sg_off: %u "
 		  "sg_nents: %u from %p %u\n", sg_start, sg_off,
-		  sg_nents, &rx_desc->data[0], unsol_data_len);
+		  sg_nents, isert_get_data(rx_desc), unsol_data_len);
 
-	sg_copy_from_buffer(sg_start, sg_nents, &rx_desc->data[0],
+	sg_copy_from_buffer(sg_start, sg_nents, isert_get_data(rx_desc),
 			    unsol_data_len);
 
 	rc = iscsit_check_dataout_payload(cmd, hdr, false);
@@ -1188,7 +1189,7 @@ isert_handle_text_cmd(struct isert_conn *isert_conn, struct isert_cmd *isert_cmd
 	}
 	cmd->text_in_ptr = text_in;
 
-	memcpy(cmd->text_in_ptr, &rx_desc->data[0], payload_length);
+	memcpy(cmd->text_in_ptr, isert_get_data(rx_desc), payload_length);
 
 	return iscsit_process_text_cmd(conn, cmd, hdr);
 }
@@ -1198,7 +1199,7 @@ isert_rx_opcode(struct isert_conn *isert_conn, struct iser_rx_desc *rx_desc,
 		uint32_t read_stag, uint64_t read_va,
 		uint32_t write_stag, uint64_t write_va)
 {
-	struct iscsi_hdr *hdr = &rx_desc->iscsi_header;
+	struct iscsi_hdr *hdr = isert_get_iscsi_hdr(rx_desc);
 	struct iscsi_conn *conn = isert_conn->conn;
 	struct iscsi_cmd *cmd;
 	struct isert_cmd *isert_cmd;
@@ -1296,8 +1297,8 @@ isert_recv_done(struct ib_cq *cq, struct ib_wc *wc)
 	struct isert_conn *isert_conn = wc->qp->qp_context;
 	struct ib_device *ib_dev = isert_conn->cm_id->device;
 	struct iser_rx_desc *rx_desc = cqe_to_rx_desc(wc->wr_cqe);
-	struct iscsi_hdr *hdr = &rx_desc->iscsi_header;
-	struct iser_ctrl *iser_ctrl = &rx_desc->iser_header;
+	struct iscsi_hdr *hdr = isert_get_iscsi_hdr(rx_desc);
+	struct iser_ctrl *iser_ctrl = isert_get_iser_hdr(rx_desc);
 	uint64_t read_va = 0, write_va = 0;
 	uint32_t read_stag = 0, write_stag = 0;
 
@@ -1311,7 +1312,7 @@ isert_recv_done(struct ib_cq *cq, struct ib_wc *wc)
 	rx_desc->in_use = true;
 
 	ib_dma_sync_single_for_cpu(ib_dev, rx_desc->dma_addr,
-			ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE);
+			ISER_RX_SIZE, DMA_FROM_DEVICE);
 
 	isert_dbg("DMA: 0x%llx, iSCSI opcode: 0x%02x, ITT: 0x%08x, flags: 0x%02x dlen: %d\n",
 		 rx_desc->dma_addr, hdr->opcode, hdr->itt, hdr->flags,
@@ -1346,7 +1347,7 @@ isert_recv_done(struct ib_cq *cq, struct ib_wc *wc)
 			read_stag, read_va, write_stag, write_va);
 
 	ib_dma_sync_single_for_device(ib_dev, rx_desc->dma_addr,
-			ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE);
+			ISER_RX_SIZE, DMA_FROM_DEVICE);
 }
 
 static void
@@ -1360,8 +1361,8 @@ isert_login_recv_done(struct ib_cq *cq, struct ib_wc *wc)
 		return;
 	}
 
-	ib_dma_sync_single_for_cpu(ib_dev, isert_conn->login_req_dma,
-			ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE);
+	ib_dma_sync_single_for_cpu(ib_dev, isert_conn->login_desc->dma_addr,
+			ISER_RX_SIZE, DMA_FROM_DEVICE);
 
 	isert_conn->login_req_len = wc->byte_len - ISER_HEADERS_LEN;
 
@@ -1376,8 +1377,8 @@ isert_login_recv_done(struct ib_cq *cq, struct ib_wc *wc)
 	complete(&isert_conn->login_req_comp);
 	mutex_unlock(&isert_conn->mutex);
 
-	ib_dma_sync_single_for_device(ib_dev, isert_conn->login_req_dma,
-				ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE);
+	ib_dma_sync_single_for_device(ib_dev, isert_conn->login_desc->dma_addr,
+				ISER_RX_SIZE, DMA_FROM_DEVICE);
 }
 
 static void
diff --git a/drivers/infiniband/ulp/isert/ib_isert.h b/drivers/infiniband/ulp/isert/ib_isert.h
index c55f7d9bfced..7fee4a65e181 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.h
+++ b/drivers/infiniband/ulp/isert/ib_isert.h
@@ -59,9 +59,11 @@
 				ISERT_MAX_TX_MISC_PDUS	+ \
 				ISERT_MAX_RX_MISC_PDUS)
 
-#define ISER_RX_PAD_SIZE	(ISCSI_DEF_MAX_RECV_SEG_LEN + 4096 - \
-		(ISER_RX_PAYLOAD_SIZE + sizeof(u64) + sizeof(struct ib_sge) + \
-		 sizeof(struct ib_cqe) + sizeof(bool)))
+/*
+ * RX size is default of 8k plus headers, but data needs to align to
+ * 512 boundary, so use 1024 to have the extra space for alignment.
+ */
+#define ISER_RX_SIZE		(ISCSI_DEF_MAX_RECV_SEG_LEN + 1024)
 
 /* Maximum support is 16MB I/O size */
 #define ISCSI_ISER_MAX_SG_TABLESIZE	4096
@@ -81,21 +83,41 @@ enum iser_conn_state {
 };
 
 struct iser_rx_desc {
-	struct iser_ctrl iser_header;
-	struct iscsi_hdr iscsi_header;
-	char		data[ISCSI_DEF_MAX_RECV_SEG_LEN];
+	char		buf[ISER_RX_SIZE];
 	u64		dma_addr;
 	struct ib_sge	rx_sg;
 	struct ib_cqe	rx_cqe;
 	bool		in_use;
-	char		pad[ISER_RX_PAD_SIZE];
-} __packed;
+};
 
 static inline struct iser_rx_desc *cqe_to_rx_desc(struct ib_cqe *cqe)
 {
 	return container_of(cqe, struct iser_rx_desc, rx_cqe);
 }
 
+static void *isert_get_iser_hdr(struct iser_rx_desc *desc)
+{
+	return PTR_ALIGN(desc->buf + ISER_HEADERS_LEN, 512) - ISER_HEADERS_LEN;
+}
+
+static size_t isert_get_hdr_offset(struct iser_rx_desc *desc)
+{
+	return isert_get_iser_hdr(desc) - (void *)desc->buf;
+}
+
+static void *isert_get_iscsi_hdr(struct iser_rx_desc *desc)
+{
+	return isert_get_iser_hdr(desc) + sizeof(struct iser_ctrl);
+}
+
+static void *isert_get_data(struct iser_rx_desc *desc)
+{
+	void *data = isert_get_iser_hdr(desc) + ISER_HEADERS_LEN;
+
+	WARN_ON((uintptr_t)data & 511);
+	return data;
+}
+
 struct iser_tx_desc {
 	struct iser_ctrl iser_header;
 	struct iscsi_hdr iscsi_header;
@@ -142,9 +164,8 @@ struct isert_conn {
 	u32			responder_resources;
 	u32			initiator_depth;
 	bool			pi_support;
-	struct iser_rx_desc	*login_req_buf;
+	struct iser_rx_desc	*login_desc;
 	char			*login_rsp_buf;
-	u64			login_req_dma;
 	int			login_req_len;
 	u64			login_rsp_dma;
 	struct iser_rx_desc	*rx_descs;
diff --git a/drivers/infiniband/ulp/rtrs/rtrs-srv-sysfs.c b/drivers/infiniband/ulp/rtrs/rtrs-srv-sysfs.c
index 3d7877534bcc..cf6a2be61695 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-srv-sysfs.c
+++ b/drivers/infiniband/ulp/rtrs/rtrs-srv-sysfs.c
@@ -152,13 +152,6 @@ static struct attribute_group rtrs_srv_stats_attr_group = {
 	.attrs = rtrs_srv_stats_attrs,
 };
 
-static void rtrs_srv_dev_release(struct device *dev)
-{
-	struct rtrs_srv *srv = container_of(dev, struct rtrs_srv, dev);
-
-	kfree(srv);
-}
-
 static int rtrs_srv_create_once_sysfs_root_folders(struct rtrs_srv_sess *sess)
 {
 	struct rtrs_srv *srv = sess->srv;
@@ -172,7 +165,6 @@ static int rtrs_srv_create_once_sysfs_root_folders(struct rtrs_srv_sess *sess)
 		goto unlock;
 	}
 	srv->dev.class = rtrs_dev_class;
-	srv->dev.release = rtrs_srv_dev_release;
 	err = dev_set_name(&srv->dev, "%s", sess->s.sessname);
 	if (err)
 		goto unlock;
@@ -182,16 +174,16 @@ static int rtrs_srv_create_once_sysfs_root_folders(struct rtrs_srv_sess *sess)
 	 * sysfs files are created
 	 */
 	dev_set_uevent_suppress(&srv->dev, true);
-	err = device_register(&srv->dev);
+	err = device_add(&srv->dev);
 	if (err) {
-		pr_err("device_register(): %d\n", err);
+		pr_err("device_add(): %d\n", err);
 		goto put;
 	}
 	srv->kobj_paths = kobject_create_and_add("paths", &srv->dev.kobj);
 	if (!srv->kobj_paths) {
 		err = -ENOMEM;
 		pr_err("kobject_create_and_add(): %d\n", err);
-		device_unregister(&srv->dev);
+		device_del(&srv->dev);
 		goto unlock;
 	}
 	dev_set_uevent_suppress(&srv->dev, false);
@@ -216,7 +208,7 @@ rtrs_srv_destroy_once_sysfs_root_folders(struct rtrs_srv_sess *sess)
 		kobject_del(srv->kobj_paths);
 		kobject_put(srv->kobj_paths);
 		mutex_unlock(&srv->paths_mutex);
-		device_unregister(&srv->dev);
+		device_del(&srv->dev);
 	} else {
 		mutex_unlock(&srv->paths_mutex);
 	}
diff --git a/drivers/infiniband/ulp/rtrs/rtrs-srv.c b/drivers/infiniband/ulp/rtrs/rtrs-srv.c
index a219bd1bdbc2..28f6414dfa3d 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-srv.c
+++ b/drivers/infiniband/ulp/rtrs/rtrs-srv.c
@@ -1319,6 +1319,13 @@ static int rtrs_srv_get_next_cq_vector(struct rtrs_srv_sess *sess)
 	return sess->cur_cq_vector;
 }
 
+static void rtrs_srv_dev_release(struct device *dev)
+{
+	struct rtrs_srv *srv = container_of(dev, struct rtrs_srv, dev);
+
+	kfree(srv);
+}
+
 static struct rtrs_srv *__alloc_srv(struct rtrs_srv_ctx *ctx,
 				     const uuid_t *paths_uuid)
 {
@@ -1336,6 +1343,8 @@ static struct rtrs_srv *__alloc_srv(struct rtrs_srv_ctx *ctx,
 	uuid_copy(&srv->paths_uuid, paths_uuid);
 	srv->queue_depth = sess_queue_depth;
 	srv->ctx = ctx;
+	device_initialize(&srv->dev);
+	srv->dev.release = rtrs_srv_dev_release;
 
 	srv->chunks = kcalloc(srv->queue_depth, sizeof(*srv->chunks),
 			      GFP_KERNEL);
diff --git a/drivers/input/mouse/trackpoint.c b/drivers/input/mouse/trackpoint.c
index 3eefee2ee2a1..854d5e758724 100644
--- a/drivers/input/mouse/trackpoint.c
+++ b/drivers/input/mouse/trackpoint.c
@@ -17,10 +17,12 @@
 #include "trackpoint.h"
 
 static const char * const trackpoint_variants[] = {
-	[TP_VARIANT_IBM]	= "IBM",
-	[TP_VARIANT_ALPS]	= "ALPS",
-	[TP_VARIANT_ELAN]	= "Elan",
-	[TP_VARIANT_NXP]	= "NXP",
+	[TP_VARIANT_IBM]		= "IBM",
+	[TP_VARIANT_ALPS]		= "ALPS",
+	[TP_VARIANT_ELAN]		= "Elan",
+	[TP_VARIANT_NXP]		= "NXP",
+	[TP_VARIANT_JYT_SYNAPTICS]	= "JYT_Synaptics",
+	[TP_VARIANT_SYNAPTICS]		= "Synaptics",
 };
 
 /*
diff --git a/drivers/input/mouse/trackpoint.h b/drivers/input/mouse/trackpoint.h
index 5cb93ed26085..eb5412904fe0 100644
--- a/drivers/input/mouse/trackpoint.h
+++ b/drivers/input/mouse/trackpoint.h
@@ -24,10 +24,12 @@
  * 0x01 was the original IBM trackpoint, others implement very limited
  * subset of trackpoint features.
  */
-#define TP_VARIANT_IBM		0x01
-#define TP_VARIANT_ALPS		0x02
-#define TP_VARIANT_ELAN		0x03
-#define TP_VARIANT_NXP		0x04
+#define TP_VARIANT_IBM			0x01
+#define TP_VARIANT_ALPS			0x02
+#define TP_VARIANT_ELAN			0x03
+#define TP_VARIANT_NXP			0x04
+#define TP_VARIANT_JYT_SYNAPTICS	0x05
+#define TP_VARIANT_SYNAPTICS		0x06
 
 /*
  * Commands
diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h
index 7d7f73702726..37fb9aa88f9c 100644
--- a/drivers/input/serio/i8042-x86ia64io.h
+++ b/drivers/input/serio/i8042-x86ia64io.h
@@ -548,6 +548,14 @@ static const struct dmi_system_id __initconst i8042_dmi_nomux_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5738"),
 		},
 	},
+	{
+		/* Entroware Proteus */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Entroware"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Proteus"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "EL07R4"),
+		},
+	},
 	{ }
 };
 
@@ -676,6 +684,14 @@ static const struct dmi_system_id __initconst i8042_dmi_reset_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "33474HU"),
 		},
 	},
+	{
+		/* Entroware Proteus */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Entroware"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Proteus"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "EL07R4"),
+		},
+	},
 	{ }
 };
 
diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c
index befd111049c0..cf07491b7415 100644
--- a/drivers/interconnect/core.c
+++ b/drivers/interconnect/core.c
@@ -55,12 +55,18 @@ static int icc_summary_show(struct seq_file *s, void *data)
 
 			icc_summary_show_one(s, n);
 			hlist_for_each_entry(r, &n->req_list, req_node) {
+				u32 avg_bw = 0, peak_bw = 0;
+
 				if (!r->dev)
 					continue;
 
+				if (r->enabled) {
+					avg_bw = r->avg_bw;
+					peak_bw = r->peak_bw;
+				}
+
 				seq_printf(s, "  %-27s %12u %12u %12u\n",
-					   dev_name(r->dev), r->tag, r->avg_bw,
-					   r->peak_bw);
+					   dev_name(r->dev), r->tag, avg_bw, peak_bw);
 			}
 		}
 	}
diff --git a/drivers/interconnect/qcom/bcm-voter.c b/drivers/interconnect/qcom/bcm-voter.c
index a3d2ef1d9903..609db9c95fd7 100644
--- a/drivers/interconnect/qcom/bcm-voter.c
+++ b/drivers/interconnect/qcom/bcm-voter.c
@@ -52,8 +52,20 @@ static int cmp_vcd(void *priv, struct list_head *a, struct list_head *b)
 		return 1;
 }
 
+static u64 bcm_div(u64 num, u32 base)
+{
+	/* Ensure that small votes aren't lost. */
+	if (num && num < base)
+		return 1;
+
+	do_div(num, base);
+
+	return num;
+}
+
 static void bcm_aggregate(struct qcom_icc_bcm *bcm)
 {
+	struct qcom_icc_node *node;
 	size_t i, bucket;
 	u64 agg_avg[QCOM_ICC_NUM_BUCKETS] = {0};
 	u64 agg_peak[QCOM_ICC_NUM_BUCKETS] = {0};
@@ -61,22 +73,21 @@ static void bcm_aggregate(struct qcom_icc_bcm *bcm)
 
 	for (bucket = 0; bucket < QCOM_ICC_NUM_BUCKETS; bucket++) {
 		for (i = 0; i < bcm->num_nodes; i++) {
-			temp = bcm->nodes[i]->sum_avg[bucket] * bcm->aux_data.width;
-			do_div(temp, bcm->nodes[i]->buswidth * bcm->nodes[i]->channels);
+			node = bcm->nodes[i];
+			temp = bcm_div(node->sum_avg[bucket] * bcm->aux_data.width,
+				       node->buswidth * node->channels);
 			agg_avg[bucket] = max(agg_avg[bucket], temp);
 
-			temp = bcm->nodes[i]->max_peak[bucket] * bcm->aux_data.width;
-			do_div(temp, bcm->nodes[i]->buswidth);
+			temp = bcm_div(node->max_peak[bucket] * bcm->aux_data.width,
+				       node->buswidth);
 			agg_peak[bucket] = max(agg_peak[bucket], temp);
 		}
 
 		temp = agg_avg[bucket] * 1000ULL;
-		do_div(temp, bcm->aux_data.unit);
-		bcm->vote_x[bucket] = temp;
+		bcm->vote_x[bucket] = bcm_div(temp, bcm->aux_data.unit);
 
 		temp = agg_peak[bucket] * 1000ULL;
-		do_div(temp, bcm->aux_data.unit);
-		bcm->vote_y[bucket] = temp;
+		bcm->vote_y[bucket] = bcm_div(temp, bcm->aux_data.unit);
 	}
 
 	if (bcm->keepalive && bcm->vote_x[QCOM_ICC_BUCKET_AMC] == 0 &&
diff --git a/drivers/iommu/amd/Kconfig b/drivers/iommu/amd/Kconfig
index 1f061d91e0b8..626b97d0dd21 100644
--- a/drivers/iommu/amd/Kconfig
+++ b/drivers/iommu/amd/Kconfig
@@ -10,7 +10,7 @@ config AMD_IOMMU
 	select IOMMU_API
 	select IOMMU_IOVA
 	select IOMMU_DMA
-	depends on X86_64 && PCI && ACPI
+	depends on X86_64 && PCI && ACPI && HAVE_CMPXCHG_DOUBLE
 	help
 	  With this option you can enable support for AMD IOMMU hardware in
 	  your system. An IOMMU is a hardware component which provides
diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c
index c652f16eb702..445a08d23fed 100644
--- a/drivers/iommu/amd/init.c
+++ b/drivers/iommu/amd/init.c
@@ -1511,7 +1511,14 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h)
 			iommu->mmio_phys_end = MMIO_REG_END_OFFSET;
 		else
 			iommu->mmio_phys_end = MMIO_CNTR_CONF_OFFSET;
-		if (((h->efr_attr & (0x1 << IOMMU_FEAT_GASUP_SHIFT)) == 0))
+
+		/*
+		 * Note: GA (128-bit IRTE) mode requires cmpxchg16b supports.
+		 * GAM also requires GA mode. Therefore, we need to
+		 * check cmpxchg16b support before enabling it.
+		 */
+		if (!boot_cpu_has(X86_FEATURE_CX16) ||
+		    ((h->efr_attr & (0x1 << IOMMU_FEAT_GASUP_SHIFT)) == 0))
 			amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_LEGACY;
 		break;
 	case 0x11:
@@ -1520,8 +1527,18 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h)
 			iommu->mmio_phys_end = MMIO_REG_END_OFFSET;
 		else
 			iommu->mmio_phys_end = MMIO_CNTR_CONF_OFFSET;
-		if (((h->efr_reg & (0x1 << IOMMU_EFR_GASUP_SHIFT)) == 0))
+
+		/*
+		 * Note: GA (128-bit IRTE) mode requires cmpxchg16b supports.
+		 * XT, GAM also requires GA mode. Therefore, we need to
+		 * check cmpxchg16b support before enabling them.
+		 */
+		if (!boot_cpu_has(X86_FEATURE_CX16) ||
+		    ((h->efr_reg & (0x1 << IOMMU_EFR_GASUP_SHIFT)) == 0)) {
 			amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_LEGACY;
+			break;
+		}
+
 		/*
 		 * Note: Since iommu_update_intcapxt() leverages
 		 * the IOMMU MMIO access to MSI capability block registers
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index ba9f3dbc5b94..10e4200d3552 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -2659,7 +2659,12 @@ static int amd_iommu_def_domain_type(struct device *dev)
 	if (!dev_data)
 		return 0;
 
-	if (dev_data->iommu_v2)
+	/*
+	 * Do not identity map IOMMUv2 capable devices when memory encryption is
+	 * active, because some of those devices (AMD GPUs) don't have the
+	 * encryption bit in their DMA-mask and require remapping.
+	 */
+	if (!mem_encrypt_active() && dev_data->iommu_v2)
 		return IOMMU_DOMAIN_IDENTITY;
 
 	return 0;
@@ -3292,6 +3297,7 @@ out:
 static int modify_irte_ga(u16 devid, int index, struct irte_ga *irte,
 			  struct amd_ir_data *data)
 {
+	bool ret;
 	struct irq_remap_table *table;
 	struct amd_iommu *iommu;
 	unsigned long flags;
@@ -3309,10 +3315,18 @@ static int modify_irte_ga(u16 devid, int index, struct irte_ga *irte,
 
 	entry = (struct irte_ga *)table->table;
 	entry = &entry[index];
-	entry->lo.fields_remap.valid = 0;
-	entry->hi.val = irte->hi.val;
-	entry->lo.val = irte->lo.val;
-	entry->lo.fields_remap.valid = 1;
+
+	ret = cmpxchg_double(&entry->lo.val, &entry->hi.val,
+			     entry->lo.val, entry->hi.val,
+			     irte->lo.val, irte->hi.val);
+	/*
+	 * We use cmpxchg16 to atomically update the 128-bit IRTE,
+	 * and it cannot be updated by the hardware or other processors
+	 * behind us, so the return value of cmpxchg16 should be the
+	 * same as the old value.
+	 */
+	WARN_ON(!ret);
+
 	if (data)
 		data->ref = entry;
 
@@ -3826,14 +3840,18 @@ int amd_iommu_activate_guest_mode(void *data)
 {
 	struct amd_ir_data *ir_data = (struct amd_ir_data *)data;
 	struct irte_ga *entry = (struct irte_ga *) ir_data->entry;
+	u64 valid;
 
 	if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) ||
 	    !entry || entry->lo.fields_vapic.guest_mode)
 		return 0;
 
+	valid = entry->lo.fields_vapic.valid;
+
 	entry->lo.val = 0;
 	entry->hi.val = 0;
 
+	entry->lo.fields_vapic.valid       = valid;
 	entry->lo.fields_vapic.guest_mode  = 1;
 	entry->lo.fields_vapic.ga_log_intr = 1;
 	entry->hi.fields.ga_root_ptr       = ir_data->ga_root_ptr;
@@ -3850,14 +3868,18 @@ int amd_iommu_deactivate_guest_mode(void *data)
 	struct amd_ir_data *ir_data = (struct amd_ir_data *)data;
 	struct irte_ga *entry = (struct irte_ga *) ir_data->entry;
 	struct irq_cfg *cfg = ir_data->cfg;
+	u64 valid;
 
 	if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) ||
 	    !entry || !entry->lo.fields_vapic.guest_mode)
 		return 0;
 
+	valid = entry->lo.fields_remap.valid;
+
 	entry->lo.val = 0;
 	entry->hi.val = 0;
 
+	entry->lo.fields_remap.valid       = valid;
 	entry->lo.fields_remap.dm          = apic->irq_dest_mode;
 	entry->lo.fields_remap.int_type    = apic->irq_delivery_mode;
 	entry->hi.fields.vector            = cfg->vector;
diff --git a/drivers/iommu/amd/iommu_v2.c b/drivers/iommu/amd/iommu_v2.c
index c259108ab6dd..0d175aed1d92 100644
--- a/drivers/iommu/amd/iommu_v2.c
+++ b/drivers/iommu/amd/iommu_v2.c
@@ -737,6 +737,13 @@ int amd_iommu_init_device(struct pci_dev *pdev, int pasids)
 
 	might_sleep();
 
+	/*
+	 * When memory encryption is active the device is likely not in a
+	 * direct-mapped domain. Forbid using IOMMUv2 functionality for now.
+	 */
+	if (mem_encrypt_active())
+		return -ENODEV;
+
 	if (!amd_iommu_v2_supported())
 		return -ENODEV;
 
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index f8177c59d229..87b17bac04c2 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -123,29 +123,29 @@ static inline unsigned int level_to_offset_bits(int level)
 	return (level - 1) * LEVEL_STRIDE;
 }
 
-static inline int pfn_level_offset(unsigned long pfn, int level)
+static inline int pfn_level_offset(u64 pfn, int level)
 {
 	return (pfn >> level_to_offset_bits(level)) & LEVEL_MASK;
 }
 
-static inline unsigned long level_mask(int level)
+static inline u64 level_mask(int level)
 {
-	return -1UL << level_to_offset_bits(level);
+	return -1ULL << level_to_offset_bits(level);
 }
 
-static inline unsigned long level_size(int level)
+static inline u64 level_size(int level)
 {
-	return 1UL << level_to_offset_bits(level);
+	return 1ULL << level_to_offset_bits(level);
 }
 
-static inline unsigned long align_to_level(unsigned long pfn, int level)
+static inline u64 align_to_level(u64 pfn, int level)
 {
 	return (pfn + level_size(level) - 1) & level_mask(level);
 }
 
 static inline unsigned long lvl_to_nr_pages(unsigned int lvl)
 {
-	return  1 << min_t(int, (lvl - 1) * LEVEL_STRIDE, MAX_AGAW_PFN_WIDTH);
+	return 1UL << min_t(int, (lvl - 1) * LEVEL_STRIDE, MAX_AGAW_PFN_WIDTH);
 }
 
 /* VT-d pages must always be _smaller_ than MM pages. Otherwise things
@@ -364,7 +364,6 @@ static int iommu_skip_te_disable;
 int intel_iommu_gfx_mapped;
 EXPORT_SYMBOL_GPL(intel_iommu_gfx_mapped);
 
-#define DUMMY_DEVICE_DOMAIN_INFO ((struct device_domain_info *)(-1))
 #define DEFER_DEVICE_DOMAIN_INFO ((struct device_domain_info *)(-2))
 struct device_domain_info *get_domain_info(struct device *dev)
 {
@@ -374,8 +373,7 @@ struct device_domain_info *get_domain_info(struct device *dev)
 		return NULL;
 
 	info = dev_iommu_priv_get(dev);
-	if (unlikely(info == DUMMY_DEVICE_DOMAIN_INFO ||
-		     info == DEFER_DEVICE_DOMAIN_INFO))
+	if (unlikely(info == DEFER_DEVICE_DOMAIN_INFO))
 		return NULL;
 
 	return info;
@@ -742,11 +740,6 @@ struct context_entry *iommu_context_addr(struct intel_iommu *iommu, u8 bus,
 	return &context[devfn];
 }
 
-static int iommu_dummy(struct device *dev)
-{
-	return dev_iommu_priv_get(dev) == DUMMY_DEVICE_DOMAIN_INFO;
-}
-
 static bool attach_deferred(struct device *dev)
 {
 	return dev_iommu_priv_get(dev) == DEFER_DEVICE_DOMAIN_INFO;
@@ -779,6 +772,53 @@ is_downstream_to_pci_bridge(struct device *dev, struct device *bridge)
 	return false;
 }
 
+static bool quirk_ioat_snb_local_iommu(struct pci_dev *pdev)
+{
+	struct dmar_drhd_unit *drhd;
+	u32 vtbar;
+	int rc;
+
+	/* We know that this device on this chipset has its own IOMMU.
+	 * If we find it under a different IOMMU, then the BIOS is lying
+	 * to us. Hope that the IOMMU for this device is actually
+	 * disabled, and it needs no translation...
+	 */
+	rc = pci_bus_read_config_dword(pdev->bus, PCI_DEVFN(0, 0), 0xb0, &vtbar);
+	if (rc) {
+		/* "can't" happen */
+		dev_info(&pdev->dev, "failed to run vt-d quirk\n");
+		return false;
+	}
+	vtbar &= 0xffff0000;
+
+	/* we know that the this iommu should be at offset 0xa000 from vtbar */
+	drhd = dmar_find_matched_drhd_unit(pdev);
+	if (!drhd || drhd->reg_base_addr - vtbar != 0xa000) {
+		pr_warn_once(FW_BUG "BIOS assigned incorrect VT-d unit for Intel(R) QuickData Technology device\n");
+		add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK);
+		return true;
+	}
+
+	return false;
+}
+
+static bool iommu_is_dummy(struct intel_iommu *iommu, struct device *dev)
+{
+	if (!iommu || iommu->drhd->ignored)
+		return true;
+
+	if (dev_is_pci(dev)) {
+		struct pci_dev *pdev = to_pci_dev(dev);
+
+		if (pdev->vendor == PCI_VENDOR_ID_INTEL &&
+		    pdev->device == PCI_DEVICE_ID_INTEL_IOAT_SNB &&
+		    quirk_ioat_snb_local_iommu(pdev))
+			return true;
+	}
+
+	return false;
+}
+
 struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devfn)
 {
 	struct dmar_drhd_unit *drhd = NULL;
@@ -788,7 +828,7 @@ struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devfn)
 	u16 segment = 0;
 	int i;
 
-	if (!dev || iommu_dummy(dev))
+	if (!dev)
 		return NULL;
 
 	if (dev_is_pci(dev)) {
@@ -805,7 +845,7 @@ struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devfn)
 		dev = &ACPI_COMPANION(dev)->dev;
 
 	rcu_read_lock();
-	for_each_active_iommu(iommu, drhd) {
+	for_each_iommu(iommu, drhd) {
 		if (pdev && segment != drhd->segment)
 			continue;
 
@@ -841,6 +881,9 @@ struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devfn)
 	}
 	iommu = NULL;
  out:
+	if (iommu_is_dummy(iommu, dev))
+		iommu = NULL;
+
 	rcu_read_unlock();
 
 	return iommu;
@@ -2447,7 +2490,7 @@ struct dmar_domain *find_domain(struct device *dev)
 {
 	struct device_domain_info *info;
 
-	if (unlikely(attach_deferred(dev) || iommu_dummy(dev)))
+	if (unlikely(attach_deferred(dev)))
 		return NULL;
 
 	/* No lock here, assumes no domain exit in normal case */
@@ -3989,35 +4032,6 @@ static void __init iommu_exit_mempool(void)
 	iova_cache_put();
 }
 
-static void quirk_ioat_snb_local_iommu(struct pci_dev *pdev)
-{
-	struct dmar_drhd_unit *drhd;
-	u32 vtbar;
-	int rc;
-
-	/* We know that this device on this chipset has its own IOMMU.
-	 * If we find it under a different IOMMU, then the BIOS is lying
-	 * to us. Hope that the IOMMU for this device is actually
-	 * disabled, and it needs no translation...
-	 */
-	rc = pci_bus_read_config_dword(pdev->bus, PCI_DEVFN(0, 0), 0xb0, &vtbar);
-	if (rc) {
-		/* "can't" happen */
-		dev_info(&pdev->dev, "failed to run vt-d quirk\n");
-		return;
-	}
-	vtbar &= 0xffff0000;
-
-	/* we know that the this iommu should be at offset 0xa000 from vtbar */
-	drhd = dmar_find_matched_drhd_unit(pdev);
-	if (!drhd || drhd->reg_base_addr - vtbar != 0xa000) {
-		pr_warn_once(FW_BUG "BIOS assigned incorrect VT-d unit for Intel(R) QuickData Technology device\n");
-		add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK);
-		dev_iommu_priv_set(&pdev->dev, DUMMY_DEVICE_DOMAIN_INFO);
-	}
-}
-DECLARE_PCI_FIXUP_ENABLE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IOAT_SNB, quirk_ioat_snb_local_iommu);
-
 static void __init init_no_remapping_devices(void)
 {
 	struct dmar_drhd_unit *drhd;
@@ -4049,12 +4063,8 @@ static void __init init_no_remapping_devices(void)
 		/* This IOMMU has *only* gfx devices. Either bypass it or
 		   set the gfx_mapped flag, as appropriate */
 		drhd->gfx_dedicated = 1;
-		if (!dmar_map_gfx) {
+		if (!dmar_map_gfx)
 			drhd->ignored = 1;
-			for_each_active_dev_scope(drhd->devices,
-						  drhd->devices_cnt, i, dev)
-				dev_iommu_priv_set(dev, DUMMY_DEVICE_DOMAIN_INFO);
-		}
 	}
 }
 
diff --git a/drivers/iommu/intel/irq_remapping.c b/drivers/iommu/intel/irq_remapping.c
index 23583b0e66a5..8f4ce72570ce 100644
--- a/drivers/iommu/intel/irq_remapping.c
+++ b/drivers/iommu/intel/irq_remapping.c
@@ -508,12 +508,18 @@ static void iommu_enable_irq_remapping(struct intel_iommu *iommu)
 
 	/* Enable interrupt-remapping */
 	iommu->gcmd |= DMA_GCMD_IRE;
-	iommu->gcmd &= ~DMA_GCMD_CFI;  /* Block compatibility-format MSIs */
 	writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG);
-
 	IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
 		      readl, (sts & DMA_GSTS_IRES), sts);
 
+	/* Block compatibility-format MSIs */
+	if (sts & DMA_GSTS_CFIS) {
+		iommu->gcmd &= ~DMA_GCMD_CFI;
+		writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG);
+		IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
+			      readl, !(sts & DMA_GSTS_CFIS), sts);
+	}
+
 	/*
 	 * With CFI clear in the Global Command register, we should be
 	 * protected from dangerous (i.e. compatibility) interrupts
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 5edc3079e7c1..229f461e7def 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -860,10 +860,14 @@ EXPORT_SYMBOL_GPL(dm_table_set_type);
 int device_supports_dax(struct dm_target *ti, struct dm_dev *dev,
 			sector_t start, sector_t len, void *data)
 {
-	int blocksize = *(int *) data;
+	int blocksize = *(int *) data, id;
+	bool rc;
 
-	return generic_fsdax_supported(dev->dax_dev, dev->bdev, blocksize,
-				       start, len);
+	id = dax_read_lock();
+	rc = dax_supported(dev->dax_dev, dev->bdev, blocksize, start, len);
+	dax_read_unlock(id);
+
+	return rc;
 }
 
 /* Check devices support synchronous DAX */
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index fb0255d25e4b..4a40df8af7d3 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1136,15 +1136,16 @@ static bool dm_dax_supported(struct dax_device *dax_dev, struct block_device *bd
 {
 	struct mapped_device *md = dax_get_private(dax_dev);
 	struct dm_table *map;
+	bool ret = false;
 	int srcu_idx;
-	bool ret;
 
 	map = dm_get_live_table(md, &srcu_idx);
 	if (!map)
-		return false;
+		goto out;
 
 	ret = dm_table_supports_dax(map, device_supports_dax, &blocksize);
 
+out:
 	dm_put_live_table(md, srcu_idx);
 
 	return ret;
diff --git a/drivers/misc/eeprom/at24.c b/drivers/misc/eeprom/at24.c
index 2591c21b2b5d..26a23abc053d 100644
--- a/drivers/misc/eeprom/at24.c
+++ b/drivers/misc/eeprom/at24.c
@@ -692,10 +692,6 @@ static int at24_probe(struct i2c_client *client)
 	nvmem_config.word_size = 1;
 	nvmem_config.size = byte_len;
 
-	at24->nvmem = devm_nvmem_register(dev, &nvmem_config);
-	if (IS_ERR(at24->nvmem))
-		return PTR_ERR(at24->nvmem);
-
 	i2c_set_clientdata(client, at24);
 
 	err = regulator_enable(at24->vcc_reg);
@@ -708,6 +704,13 @@ static int at24_probe(struct i2c_client *client)
 	pm_runtime_set_active(dev);
 	pm_runtime_enable(dev);
 
+	at24->nvmem = devm_nvmem_register(dev, &nvmem_config);
+	if (IS_ERR(at24->nvmem)) {
+		pm_runtime_disable(dev);
+		regulator_disable(at24->vcc_reg);
+		return PTR_ERR(at24->nvmem);
+	}
+
 	/*
 	 * Perform a one-byte test read to verify that the
 	 * chip is functional.
diff --git a/drivers/misc/habanalabs/common/debugfs.c b/drivers/misc/habanalabs/common/debugfs.c
index 37701e4f9d5a..aa77771635d3 100644
--- a/drivers/misc/habanalabs/common/debugfs.c
+++ b/drivers/misc/habanalabs/common/debugfs.c
@@ -982,7 +982,7 @@ static ssize_t hl_clk_gate_read(struct file *f, char __user *buf,
 		return 0;
 
 	sprintf(tmp_buf, "0x%llx\n", hdev->clock_gating_mask);
-	rc = simple_read_from_buffer(buf, strlen(tmp_buf) + 1, ppos, tmp_buf,
+	rc = simple_read_from_buffer(buf, count, ppos, tmp_buf,
 			strlen(tmp_buf) + 1);
 
 	return rc;
diff --git a/drivers/misc/habanalabs/include/gaudi/gaudi_masks.h b/drivers/misc/habanalabs/include/gaudi/gaudi_masks.h
index 13ef6b2887fd..3510c42d24e3 100644
--- a/drivers/misc/habanalabs/include/gaudi/gaudi_masks.h
+++ b/drivers/misc/habanalabs/include/gaudi/gaudi_masks.h
@@ -378,15 +378,15 @@ enum axi_id {
 	((((y) & RAZWI_INITIATOR_Y_MASK) << RAZWI_INITIATOR_Y_SHIFT) | \
 		(((x) & RAZWI_INITIATOR_X_MASK) << RAZWI_INITIATOR_X_SHIFT))
 
-#define RAZWI_INITIATOR_ID_X_Y_TPC0_NIC0	RAZWI_INITIATOR_ID_X_Y(1, 0)
-#define RAZWI_INITIATOR_ID_X_Y_TPC1		RAZWI_INITIATOR_ID_X_Y(2, 0)
-#define RAZWI_INITIATOR_ID_X_Y_MME0_0		RAZWI_INITIATOR_ID_X_Y(3, 0)
-#define RAZWI_INITIATOR_ID_X_Y_MME0_1		RAZWI_INITIATOR_ID_X_Y(4, 0)
-#define RAZWI_INITIATOR_ID_X_Y_MME1_0		RAZWI_INITIATOR_ID_X_Y(5, 0)
-#define RAZWI_INITIATOR_ID_X_Y_MME1_1		RAZWI_INITIATOR_ID_X_Y(6, 0)
-#define RAZWI_INITIATOR_ID_X_Y_TPC2		RAZWI_INITIATOR_ID_X_Y(7, 0)
+#define RAZWI_INITIATOR_ID_X_Y_TPC0_NIC0	RAZWI_INITIATOR_ID_X_Y(1, 1)
+#define RAZWI_INITIATOR_ID_X_Y_TPC1		RAZWI_INITIATOR_ID_X_Y(2, 1)
+#define RAZWI_INITIATOR_ID_X_Y_MME0_0		RAZWI_INITIATOR_ID_X_Y(3, 1)
+#define RAZWI_INITIATOR_ID_X_Y_MME0_1		RAZWI_INITIATOR_ID_X_Y(4, 1)
+#define RAZWI_INITIATOR_ID_X_Y_MME1_0		RAZWI_INITIATOR_ID_X_Y(5, 1)
+#define RAZWI_INITIATOR_ID_X_Y_MME1_1		RAZWI_INITIATOR_ID_X_Y(6, 1)
+#define RAZWI_INITIATOR_ID_X_Y_TPC2		RAZWI_INITIATOR_ID_X_Y(7, 1)
 #define RAZWI_INITIATOR_ID_X_Y_TPC3_PCI_CPU_PSOC \
-						RAZWI_INITIATOR_ID_X_Y(8, 0)
+						RAZWI_INITIATOR_ID_X_Y(8, 1)
 #define RAZWI_INITIATOR_ID_X_Y_DMA_IF_W_S_0	RAZWI_INITIATOR_ID_X_Y(0, 1)
 #define RAZWI_INITIATOR_ID_X_Y_DMA_IF_E_S_0	RAZWI_INITIATOR_ID_X_Y(9, 1)
 #define RAZWI_INITIATOR_ID_X_Y_DMA_IF_W_S_1	RAZWI_INITIATOR_ID_X_Y(0, 2)
@@ -395,14 +395,14 @@ enum axi_id {
 #define RAZWI_INITIATOR_ID_X_Y_DMA_IF_E_N_0	RAZWI_INITIATOR_ID_X_Y(9, 3)
 #define RAZWI_INITIATOR_ID_X_Y_DMA_IF_W_N_1	RAZWI_INITIATOR_ID_X_Y(0, 4)
 #define RAZWI_INITIATOR_ID_X_Y_DMA_IF_E_N_1	RAZWI_INITIATOR_ID_X_Y(9, 4)
-#define RAZWI_INITIATOR_ID_X_Y_TPC4_NIC1_NIC2	RAZWI_INITIATOR_ID_X_Y(1, 5)
-#define RAZWI_INITIATOR_ID_X_Y_TPC5		RAZWI_INITIATOR_ID_X_Y(2, 5)
-#define RAZWI_INITIATOR_ID_X_Y_MME2_0		RAZWI_INITIATOR_ID_X_Y(3, 5)
-#define RAZWI_INITIATOR_ID_X_Y_MME2_1		RAZWI_INITIATOR_ID_X_Y(4, 5)
-#define RAZWI_INITIATOR_ID_X_Y_MME3_0		RAZWI_INITIATOR_ID_X_Y(5, 5)
-#define RAZWI_INITIATOR_ID_X_Y_MME3_1		RAZWI_INITIATOR_ID_X_Y(6, 5)
-#define RAZWI_INITIATOR_ID_X_Y_TPC6		RAZWI_INITIATOR_ID_X_Y(7, 5)
-#define RAZWI_INITIATOR_ID_X_Y_TPC7_NIC4_NIC5	RAZWI_INITIATOR_ID_X_Y(8, 5)
+#define RAZWI_INITIATOR_ID_X_Y_TPC4_NIC1_NIC2	RAZWI_INITIATOR_ID_X_Y(1, 6)
+#define RAZWI_INITIATOR_ID_X_Y_TPC5		RAZWI_INITIATOR_ID_X_Y(2, 6)
+#define RAZWI_INITIATOR_ID_X_Y_MME2_0		RAZWI_INITIATOR_ID_X_Y(3, 6)
+#define RAZWI_INITIATOR_ID_X_Y_MME2_1		RAZWI_INITIATOR_ID_X_Y(4, 6)
+#define RAZWI_INITIATOR_ID_X_Y_MME3_0		RAZWI_INITIATOR_ID_X_Y(5, 6)
+#define RAZWI_INITIATOR_ID_X_Y_MME3_1		RAZWI_INITIATOR_ID_X_Y(6, 6)
+#define RAZWI_INITIATOR_ID_X_Y_TPC6		RAZWI_INITIATOR_ID_X_Y(7, 6)
+#define RAZWI_INITIATOR_ID_X_Y_TPC7_NIC4_NIC5	RAZWI_INITIATOR_ID_X_Y(8, 6)
 
 #define PSOC_ETR_AXICTL_PROTCTRLBIT1_SHIFT                           1
 
diff --git a/drivers/mmc/core/sdio_ops.c b/drivers/mmc/core/sdio_ops.c
index 93d346c01110..4c229dd2b6e5 100644
--- a/drivers/mmc/core/sdio_ops.c
+++ b/drivers/mmc/core/sdio_ops.c
@@ -121,6 +121,7 @@ int mmc_io_rw_extended(struct mmc_card *card, int write, unsigned fn,
 	struct sg_table sgtable;
 	unsigned int nents, left_size, i;
 	unsigned int seg_size = card->host->max_seg_size;
+	int err;
 
 	WARN_ON(blksz == 0);
 
@@ -170,28 +171,32 @@ int mmc_io_rw_extended(struct mmc_card *card, int write, unsigned fn,
 
 	mmc_set_data_timeout(&data, card);
 
-	mmc_wait_for_req(card->host, &mrq);
+	mmc_pre_req(card->host, &mrq);
 
-	if (nents > 1)
-		sg_free_table(&sgtable);
+	mmc_wait_for_req(card->host, &mrq);
 
 	if (cmd.error)
-		return cmd.error;
-	if (data.error)
-		return data.error;
-
-	if (mmc_host_is_spi(card->host)) {
+		err = cmd.error;
+	else if (data.error)
+		err = data.error;
+	else if (mmc_host_is_spi(card->host))
 		/* host driver already reported errors */
-	} else {
-		if (cmd.resp[0] & R5_ERROR)
-			return -EIO;
-		if (cmd.resp[0] & R5_FUNCTION_NUMBER)
-			return -EINVAL;
-		if (cmd.resp[0] & R5_OUT_OF_RANGE)
-			return -ERANGE;
-	}
+		err = 0;
+	else if (cmd.resp[0] & R5_ERROR)
+		err = -EIO;
+	else if (cmd.resp[0] & R5_FUNCTION_NUMBER)
+		err = -EINVAL;
+	else if (cmd.resp[0] & R5_OUT_OF_RANGE)
+		err = -ERANGE;
+	else
+		err = 0;
 
-	return 0;
+	mmc_post_req(card->host, &mrq, err);
+
+	if (nents > 1)
+		sg_free_table(&sgtable);
+
+	return err;
 }
 
 int sdio_reset(struct mmc_host *host)
diff --git a/drivers/mmc/host/Kconfig b/drivers/mmc/host/Kconfig
index 9c89a5b780e8..9a34c827c96e 100644
--- a/drivers/mmc/host/Kconfig
+++ b/drivers/mmc/host/Kconfig
@@ -602,7 +602,7 @@ config MMC_GOLDFISH
 
 config MMC_SPI
 	tristate "MMC/SD/SDIO over SPI"
-	depends on SPI_MASTER && HAS_DMA
+	depends on SPI_MASTER
 	select CRC7
 	select CRC_ITU_T
 	help
diff --git a/drivers/mmc/host/mmc_spi.c b/drivers/mmc/host/mmc_spi.c
index 39bb1e30c2d7..5055a7eb134a 100644
--- a/drivers/mmc/host/mmc_spi.c
+++ b/drivers/mmc/host/mmc_spi.c
@@ -1278,6 +1278,52 @@ mmc_spi_detect_irq(int irq, void *mmc)
 	return IRQ_HANDLED;
 }
 
+#ifdef CONFIG_HAS_DMA
+static int mmc_spi_dma_alloc(struct mmc_spi_host *host)
+{
+	struct spi_device *spi = host->spi;
+	struct device *dev;
+
+	if (!spi->master->dev.parent->dma_mask)
+		return 0;
+
+	dev = spi->master->dev.parent;
+
+	host->ones_dma = dma_map_single(dev, host->ones, MMC_SPI_BLOCKSIZE,
+					DMA_TO_DEVICE);
+	if (dma_mapping_error(dev, host->ones_dma))
+		return -ENOMEM;
+
+	host->data_dma = dma_map_single(dev, host->data, sizeof(*host->data),
+					DMA_BIDIRECTIONAL);
+	if (dma_mapping_error(dev, host->data_dma)) {
+		dma_unmap_single(dev, host->ones_dma, MMC_SPI_BLOCKSIZE,
+				 DMA_TO_DEVICE);
+		return -ENOMEM;
+	}
+
+	dma_sync_single_for_cpu(dev, host->data_dma, sizeof(*host->data),
+				DMA_BIDIRECTIONAL);
+
+	host->dma_dev = dev;
+	return 0;
+}
+
+static void mmc_spi_dma_free(struct mmc_spi_host *host)
+{
+	if (!host->dma_dev)
+		return;
+
+	dma_unmap_single(host->dma_dev, host->ones_dma, MMC_SPI_BLOCKSIZE,
+			 DMA_TO_DEVICE);
+	dma_unmap_single(host->dma_dev, host->data_dma,	sizeof(*host->data),
+			 DMA_BIDIRECTIONAL);
+}
+#else
+static inline mmc_spi_dma_alloc(struct mmc_spi_host *host) { return 0; }
+static inline void mmc_spi_dma_free(struct mmc_spi_host *host) {}
+#endif
+
 static int mmc_spi_probe(struct spi_device *spi)
 {
 	void			*ones;
@@ -1374,23 +1420,9 @@ static int mmc_spi_probe(struct spi_device *spi)
 	if (!host->data)
 		goto fail_nobuf1;
 
-	if (spi->master->dev.parent->dma_mask) {
-		struct device	*dev = spi->master->dev.parent;
-
-		host->dma_dev = dev;
-		host->ones_dma = dma_map_single(dev, ones,
-				MMC_SPI_BLOCKSIZE, DMA_TO_DEVICE);
-		if (dma_mapping_error(dev, host->ones_dma))
-			goto fail_ones_dma;
-		host->data_dma = dma_map_single(dev, host->data,
-				sizeof(*host->data), DMA_BIDIRECTIONAL);
-		if (dma_mapping_error(dev, host->data_dma))
-			goto fail_data_dma;
-
-		dma_sync_single_for_cpu(host->dma_dev,
-				host->data_dma, sizeof(*host->data),
-				DMA_BIDIRECTIONAL);
-	}
+	status = mmc_spi_dma_alloc(host);
+	if (status)
+		goto fail_dma;
 
 	/* setup message for status/busy readback */
 	spi_message_init(&host->readback);
@@ -1458,20 +1490,12 @@ static int mmc_spi_probe(struct spi_device *spi)
 fail_add_host:
 	mmc_remove_host(mmc);
 fail_glue_init:
-	if (host->dma_dev)
-		dma_unmap_single(host->dma_dev, host->data_dma,
-				sizeof(*host->data), DMA_BIDIRECTIONAL);
-fail_data_dma:
-	if (host->dma_dev)
-		dma_unmap_single(host->dma_dev, host->ones_dma,
-				MMC_SPI_BLOCKSIZE, DMA_TO_DEVICE);
-fail_ones_dma:
+	mmc_spi_dma_free(host);
+fail_dma:
 	kfree(host->data);
-
 fail_nobuf1:
 	mmc_free_host(mmc);
 	mmc_spi_put_pdata(spi);
-
 nomem:
 	kfree(ones);
 	return status;
@@ -1489,13 +1513,7 @@ static int mmc_spi_remove(struct spi_device *spi)
 
 	mmc_remove_host(mmc);
 
-	if (host->dma_dev) {
-		dma_unmap_single(host->dma_dev, host->ones_dma,
-			MMC_SPI_BLOCKSIZE, DMA_TO_DEVICE);
-		dma_unmap_single(host->dma_dev, host->data_dma,
-			sizeof(*host->data), DMA_BIDIRECTIONAL);
-	}
-
+	mmc_spi_dma_free(host);
 	kfree(host->data);
 	kfree(host->ones);
 
diff --git a/drivers/mmc/host/sdhci-acpi.c b/drivers/mmc/host/sdhci-acpi.c
index 962f074ca174..284cba11e279 100644
--- a/drivers/mmc/host/sdhci-acpi.c
+++ b/drivers/mmc/host/sdhci-acpi.c
@@ -551,12 +551,18 @@ static int amd_select_drive_strength(struct mmc_card *card,
 	return MMC_SET_DRIVER_TYPE_A;
 }
 
-static void sdhci_acpi_amd_hs400_dll(struct sdhci_host *host)
+static void sdhci_acpi_amd_hs400_dll(struct sdhci_host *host, bool enable)
 {
+	struct sdhci_acpi_host *acpi_host = sdhci_priv(host);
+	struct amd_sdhci_host *amd_host = sdhci_acpi_priv(acpi_host);
+
 	/* AMD Platform requires dll setting */
 	sdhci_writel(host, 0x40003210, SDHCI_AMD_RESET_DLL_REGISTER);
 	usleep_range(10, 20);
-	sdhci_writel(host, 0x40033210, SDHCI_AMD_RESET_DLL_REGISTER);
+	if (enable)
+		sdhci_writel(host, 0x40033210, SDHCI_AMD_RESET_DLL_REGISTER);
+
+	amd_host->dll_enabled = enable;
 }
 
 /*
@@ -596,10 +602,8 @@ static void amd_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 
 		/* DLL is only required for HS400 */
 		if (host->timing == MMC_TIMING_MMC_HS400 &&
-		    !amd_host->dll_enabled) {
-			sdhci_acpi_amd_hs400_dll(host);
-			amd_host->dll_enabled = true;
-		}
+		    !amd_host->dll_enabled)
+			sdhci_acpi_amd_hs400_dll(host, true);
 	}
 }
 
@@ -620,10 +624,23 @@ static int amd_sdhci_execute_tuning(struct mmc_host *mmc, u32 opcode)
 	return err;
 }
 
+static void amd_sdhci_reset(struct sdhci_host *host, u8 mask)
+{
+	struct sdhci_acpi_host *acpi_host = sdhci_priv(host);
+	struct amd_sdhci_host *amd_host = sdhci_acpi_priv(acpi_host);
+
+	if (mask & SDHCI_RESET_ALL) {
+		amd_host->tuned_clock = false;
+		sdhci_acpi_amd_hs400_dll(host, false);
+	}
+
+	sdhci_reset(host, mask);
+}
+
 static const struct sdhci_ops sdhci_acpi_ops_amd = {
 	.set_clock	= sdhci_set_clock,
 	.set_bus_width	= sdhci_set_bus_width,
-	.reset		= sdhci_reset,
+	.reset		= amd_sdhci_reset,
 	.set_uhs_signaling = sdhci_set_uhs_signaling,
 };
 
diff --git a/drivers/mmc/host/sdhci-msm.c b/drivers/mmc/host/sdhci-msm.c
index 5a33389037cd..729868abd2db 100644
--- a/drivers/mmc/host/sdhci-msm.c
+++ b/drivers/mmc/host/sdhci-msm.c
@@ -1166,7 +1166,7 @@ static void sdhci_msm_set_cdr(struct sdhci_host *host, bool enable)
 static int sdhci_msm_execute_tuning(struct mmc_host *mmc, u32 opcode)
 {
 	struct sdhci_host *host = mmc_priv(mmc);
-	int tuning_seq_cnt = 3;
+	int tuning_seq_cnt = 10;
 	u8 phase, tuned_phases[16], tuned_phase_cnt = 0;
 	int rc;
 	struct mmc_ios ios = host->mmc->ios;
@@ -1222,6 +1222,22 @@ retry:
 	} while (++phase < ARRAY_SIZE(tuned_phases));
 
 	if (tuned_phase_cnt) {
+		if (tuned_phase_cnt == ARRAY_SIZE(tuned_phases)) {
+			/*
+			 * All phases valid is _almost_ as bad as no phases
+			 * valid.  Probably all phases are not really reliable
+			 * but we didn't detect where the unreliable place is.
+			 * That means we'll essentially be guessing and hoping
+			 * we get a good phase.  Better to try a few times.
+			 */
+			dev_dbg(mmc_dev(mmc), "%s: All phases valid; try again\n",
+				mmc_hostname(mmc));
+			if (--tuning_seq_cnt) {
+				tuned_phase_cnt = 0;
+				goto retry;
+			}
+		}
+
 		rc = msm_find_most_appropriate_phase(host, tuned_phases,
 						     tuned_phase_cnt);
 		if (rc < 0)
diff --git a/drivers/mmc/host/sdhci-of-esdhc.c b/drivers/mmc/host/sdhci-of-esdhc.c
index 7c73d243dc6c..45881b309956 100644
--- a/drivers/mmc/host/sdhci-of-esdhc.c
+++ b/drivers/mmc/host/sdhci-of-esdhc.c
@@ -81,6 +81,7 @@ struct sdhci_esdhc {
 	bool quirk_tuning_erratum_type2;
 	bool quirk_ignore_data_inhibit;
 	bool quirk_delay_before_data_reset;
+	bool quirk_trans_complete_erratum;
 	bool in_sw_tuning;
 	unsigned int peripheral_clock;
 	const struct esdhc_clk_fixup *clk_fixup;
@@ -1177,10 +1178,11 @@ static void esdhc_set_uhs_signaling(struct sdhci_host *host,
 
 static u32 esdhc_irq(struct sdhci_host *host, u32 intmask)
 {
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct sdhci_esdhc *esdhc = sdhci_pltfm_priv(pltfm_host);
 	u32 command;
 
-	if (of_find_compatible_node(NULL, NULL,
-				"fsl,p2020-esdhc")) {
+	if (esdhc->quirk_trans_complete_erratum) {
 		command = SDHCI_GET_CMD(sdhci_readw(host,
 					SDHCI_COMMAND));
 		if (command == MMC_WRITE_MULTIPLE_BLOCK &&
@@ -1334,8 +1336,10 @@ static void esdhc_init(struct platform_device *pdev, struct sdhci_host *host)
 		esdhc->clk_fixup = match->data;
 	np = pdev->dev.of_node;
 
-	if (of_device_is_compatible(np, "fsl,p2020-esdhc"))
+	if (of_device_is_compatible(np, "fsl,p2020-esdhc")) {
 		esdhc->quirk_delay_before_data_reset = true;
+		esdhc->quirk_trans_complete_erratum = true;
+	}
 
 	clk = of_clk_get(np, 0);
 	if (!IS_ERR(clk)) {
diff --git a/drivers/mtd/spi-nor/core.c b/drivers/mtd/spi-nor/core.c
index 65eff4ce6ab1..0369d98b2d12 100644
--- a/drivers/mtd/spi-nor/core.c
+++ b/drivers/mtd/spi-nor/core.c
@@ -1907,16 +1907,15 @@ static int spi_nor_is_locked(struct mtd_info *mtd, loff_t ofs, uint64_t len)
 }
 
 /**
- * spi_nor_sr1_bit6_quad_enable() - Set/Unset the Quad Enable BIT(6) in the
- *                                  Status Register 1.
+ * spi_nor_sr1_bit6_quad_enable() - Set the Quad Enable BIT(6) in the Status
+ * Register 1.
  * @nor:	pointer to a 'struct spi_nor'
- * @enable:	true to enable Quad mode, false to disable Quad mode.
  *
  * Bit 6 of the Status Register 1 is the QE bit for Macronix like QSPI memories.
  *
  * Return: 0 on success, -errno otherwise.
  */
-int spi_nor_sr1_bit6_quad_enable(struct spi_nor *nor, bool enable)
+int spi_nor_sr1_bit6_quad_enable(struct spi_nor *nor)
 {
 	int ret;
 
@@ -1924,56 +1923,45 @@ int spi_nor_sr1_bit6_quad_enable(struct spi_nor *nor, bool enable)
 	if (ret)
 		return ret;
 
-	if ((enable && (nor->bouncebuf[0] & SR1_QUAD_EN_BIT6)) ||
-	    (!enable && !(nor->bouncebuf[0] & SR1_QUAD_EN_BIT6)))
+	if (nor->bouncebuf[0] & SR1_QUAD_EN_BIT6)
 		return 0;
 
-	if (enable)
-		nor->bouncebuf[0] |= SR1_QUAD_EN_BIT6;
-	else
-		nor->bouncebuf[0] &= ~SR1_QUAD_EN_BIT6;
+	nor->bouncebuf[0] |= SR1_QUAD_EN_BIT6;
 
 	return spi_nor_write_sr1_and_check(nor, nor->bouncebuf[0]);
 }
 
 /**
- * spi_nor_sr2_bit1_quad_enable() - set/unset the Quad Enable BIT(1) in the
- *                                  Status Register 2.
+ * spi_nor_sr2_bit1_quad_enable() - set the Quad Enable BIT(1) in the Status
+ * Register 2.
  * @nor:       pointer to a 'struct spi_nor'.
- * @enable:	true to enable Quad mode, false to disable Quad mode.
  *
  * Bit 1 of the Status Register 2 is the QE bit for Spansion like QSPI memories.
  *
  * Return: 0 on success, -errno otherwise.
  */
-int spi_nor_sr2_bit1_quad_enable(struct spi_nor *nor, bool enable)
+int spi_nor_sr2_bit1_quad_enable(struct spi_nor *nor)
 {
 	int ret;
 
 	if (nor->flags & SNOR_F_NO_READ_CR)
-		return spi_nor_write_16bit_cr_and_check(nor,
-						enable ? SR2_QUAD_EN_BIT1 : 0);
+		return spi_nor_write_16bit_cr_and_check(nor, SR2_QUAD_EN_BIT1);
 
 	ret = spi_nor_read_cr(nor, nor->bouncebuf);
 	if (ret)
 		return ret;
 
-	if ((enable && (nor->bouncebuf[0] & SR2_QUAD_EN_BIT1)) ||
-	    (!enable && !(nor->bouncebuf[0] & SR2_QUAD_EN_BIT1)))
+	if (nor->bouncebuf[0] & SR2_QUAD_EN_BIT1)
 		return 0;
 
-	if (enable)
-		nor->bouncebuf[0] |= SR2_QUAD_EN_BIT1;
-	else
-		nor->bouncebuf[0] &= ~SR2_QUAD_EN_BIT1;
+	nor->bouncebuf[0] |= SR2_QUAD_EN_BIT1;
 
 	return spi_nor_write_16bit_cr_and_check(nor, nor->bouncebuf[0]);
 }
 
 /**
- * spi_nor_sr2_bit7_quad_enable() - set/unset QE bit in Status Register 2.
+ * spi_nor_sr2_bit7_quad_enable() - set QE bit in Status Register 2.
  * @nor:	pointer to a 'struct spi_nor'
- * @enable:	true to enable Quad mode, false to disable Quad mode.
  *
  * Set the Quad Enable (QE) bit in the Status Register 2.
  *
@@ -1983,7 +1971,7 @@ int spi_nor_sr2_bit1_quad_enable(struct spi_nor *nor, bool enable)
  *
  * Return: 0 on success, -errno otherwise.
  */
-int spi_nor_sr2_bit7_quad_enable(struct spi_nor *nor, bool enable)
+int spi_nor_sr2_bit7_quad_enable(struct spi_nor *nor)
 {
 	u8 *sr2 = nor->bouncebuf;
 	int ret;
@@ -1993,15 +1981,11 @@ int spi_nor_sr2_bit7_quad_enable(struct spi_nor *nor, bool enable)
 	ret = spi_nor_read_sr2(nor, sr2);
 	if (ret)
 		return ret;
-	if ((enable && (*sr2 & SR2_QUAD_EN_BIT7)) ||
-	    (!enable && !(*sr2 & SR2_QUAD_EN_BIT7)))
+	if (*sr2 & SR2_QUAD_EN_BIT7)
 		return 0;
 
 	/* Update the Quad Enable bit. */
-	if (enable)
-		*sr2 |= SR2_QUAD_EN_BIT7;
-	else
-		*sr2 &= ~SR2_QUAD_EN_BIT7;
+	*sr2 |= SR2_QUAD_EN_BIT7;
 
 	ret = spi_nor_write_sr2(nor, sr2);
 	if (ret)
@@ -2914,13 +2898,12 @@ static int spi_nor_init_params(struct spi_nor *nor)
 }
 
 /**
- * spi_nor_quad_enable() - enable/disable Quad I/O if needed.
+ * spi_nor_quad_enable() - enable Quad I/O if needed.
  * @nor:                pointer to a 'struct spi_nor'
- * @enable:             true to enable Quad mode. false to disable Quad mode.
  *
  * Return: 0 on success, -errno otherwise.
  */
-static int spi_nor_quad_enable(struct spi_nor *nor, bool enable)
+static int spi_nor_quad_enable(struct spi_nor *nor)
 {
 	if (!nor->params->quad_enable)
 		return 0;
@@ -2929,7 +2912,7 @@ static int spi_nor_quad_enable(struct spi_nor *nor, bool enable)
 	      spi_nor_get_protocol_width(nor->write_proto) == 4))
 		return 0;
 
-	return nor->params->quad_enable(nor, enable);
+	return nor->params->quad_enable(nor);
 }
 
 /**
@@ -2953,7 +2936,7 @@ static int spi_nor_init(struct spi_nor *nor)
 {
 	int err;
 
-	err = spi_nor_quad_enable(nor, true);
+	err = spi_nor_quad_enable(nor);
 	if (err) {
 		dev_dbg(nor->dev, "quad mode not supported\n");
 		return err;
@@ -3000,8 +2983,6 @@ void spi_nor_restore(struct spi_nor *nor)
 	if (nor->addr_width == 4 && !(nor->flags & SNOR_F_4B_OPCODES) &&
 	    nor->flags & SNOR_F_BROKEN_RESET)
 		nor->params->set_4byte_addr_mode(nor, false);
-
-	spi_nor_quad_enable(nor, false);
 }
 EXPORT_SYMBOL_GPL(spi_nor_restore);
 
diff --git a/drivers/mtd/spi-nor/core.h b/drivers/mtd/spi-nor/core.h
index 95aa32f3ceb1..6f2f6b27173f 100644
--- a/drivers/mtd/spi-nor/core.h
+++ b/drivers/mtd/spi-nor/core.h
@@ -198,7 +198,7 @@ struct spi_nor_locking_ops {
  *                      higher index in the array, the higher priority.
  * @erase_map:		the erase map parsed from the SFDP Sector Map Parameter
  *                      Table.
- * @quad_enable:	enables/disables SPI NOR Quad mode.
+ * @quad_enable:	enables SPI NOR quad mode.
  * @set_4byte_addr_mode: puts the SPI NOR in 4 byte addressing mode.
  * @convert_addr:	converts an absolute address into something the flash
  *                      will understand. Particularly useful when pagesize is
@@ -219,7 +219,7 @@ struct spi_nor_flash_parameter {
 
 	struct spi_nor_erase_map        erase_map;
 
-	int (*quad_enable)(struct spi_nor *nor, bool enable);
+	int (*quad_enable)(struct spi_nor *nor);
 	int (*set_4byte_addr_mode)(struct spi_nor *nor, bool enable);
 	u32 (*convert_addr)(struct spi_nor *nor, u32 addr);
 	int (*setup)(struct spi_nor *nor, const struct spi_nor_hwcaps *hwcaps);
@@ -406,9 +406,9 @@ int spi_nor_write_ear(struct spi_nor *nor, u8 ear);
 int spi_nor_wait_till_ready(struct spi_nor *nor);
 int spi_nor_lock_and_prep(struct spi_nor *nor);
 void spi_nor_unlock_and_unprep(struct spi_nor *nor);
-int spi_nor_sr1_bit6_quad_enable(struct spi_nor *nor, bool enable);
-int spi_nor_sr2_bit1_quad_enable(struct spi_nor *nor, bool enable);
-int spi_nor_sr2_bit7_quad_enable(struct spi_nor *nor, bool enable);
+int spi_nor_sr1_bit6_quad_enable(struct spi_nor *nor);
+int spi_nor_sr2_bit1_quad_enable(struct spi_nor *nor);
+int spi_nor_sr2_bit7_quad_enable(struct spi_nor *nor);
 
 int spi_nor_xread_sr(struct spi_nor *nor, u8 *sr);
 ssize_t spi_nor_read_data(struct spi_nor *nor, loff_t from, size_t len,
diff --git a/drivers/net/caif/Kconfig b/drivers/net/caif/Kconfig
index c245edddb48b..a77124bc1f4b 100644
--- a/drivers/net/caif/Kconfig
+++ b/drivers/net/caif/Kconfig
@@ -20,25 +20,6 @@ config CAIF_TTY
 	  identified as N_CAIF. When this ldisc is opened from user space
 	  it will redirect the TTY's traffic into the CAIF stack.
 
-config CAIF_SPI_SLAVE
-	tristate "CAIF SPI transport driver for slave interface"
-	depends on CAIF && HAS_DMA
-	default n
-	help
-	  The CAIF Link layer SPI Protocol driver for Slave SPI interface.
-	  This driver implements a platform driver to accommodate for a
-	  platform specific SPI device. A sample CAIF SPI Platform device is
-	  provided in <file:Documentation/networking/caif/spi_porting.rst>.
-
-config CAIF_SPI_SYNC
-	bool "Next command and length in start of frame"
-	depends on CAIF_SPI_SLAVE
-	default n
-	help
-	  Putting the next command and length in the start of the frame can
-	  help to synchronize to the next transfer in case of over or under-runs.
-	  This option also needs to be enabled on the modem.
-
 config CAIF_HSI
 	tristate "CAIF HSI transport driver"
 	depends on CAIF
diff --git a/drivers/net/caif/Makefile b/drivers/net/caif/Makefile
index 54ae1165d60a..b1918c8c126c 100644
--- a/drivers/net/caif/Makefile
+++ b/drivers/net/caif/Makefile
@@ -4,10 +4,6 @@ ccflags-$(CONFIG_CAIF_DEBUG) := -DDEBUG
 # Serial interface
 obj-$(CONFIG_CAIF_TTY) += caif_serial.o
 
-# SPI slave physical interfaces module
-cfspi_slave-objs := caif_spi.o caif_spi_slave.o
-obj-$(CONFIG_CAIF_SPI_SLAVE) += cfspi_slave.o
-
 # HSI interface
 obj-$(CONFIG_CAIF_HSI) += caif_hsi.o
 
diff --git a/drivers/net/caif/caif_hsi.c b/drivers/net/caif/caif_hsi.c
index 4a33ec4fc089..3d63b15bbaa1 100644
--- a/drivers/net/caif/caif_hsi.c
+++ b/drivers/net/caif/caif_hsi.c
@@ -458,15 +458,7 @@ static int cfhsi_rx_desc(struct cfhsi_desc *desc, struct cfhsi *cfhsi)
 		skb_reset_mac_header(skb);
 		skb->dev = cfhsi->ndev;
 
-		/*
-		 * We are in a callback handler and
-		 * unfortunately we don't know what context we're
-		 * running in.
-		 */
-		if (in_interrupt())
-			netif_rx(skb);
-		else
-			netif_rx_ni(skb);
+		netif_rx_any_context(skb);
 
 		/* Update network statistics. */
 		cfhsi->ndev->stats.rx_packets++;
@@ -587,14 +579,7 @@ static int cfhsi_rx_pld(struct cfhsi_desc *desc, struct cfhsi *cfhsi)
 		skb_reset_mac_header(skb);
 		skb->dev = cfhsi->ndev;
 
-		/*
-		 * We're called in callback from HSI
-		 * and don't know the context we're running in.
-		 */
-		if (in_interrupt())
-			netif_rx(skb);
-		else
-			netif_rx_ni(skb);
+		netif_rx_any_context(skb);
 
 		/* Update network statistics. */
 		cfhsi->ndev->stats.rx_packets++;
diff --git a/drivers/net/caif/caif_spi.c b/drivers/net/caif/caif_spi.c
deleted file mode 100644
index 7d5899626130..000000000000
--- a/drivers/net/caif/caif_spi.c
+++ /dev/null
@@ -1,874 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Copyright (C) ST-Ericsson AB 2010
- * Author:  Daniel Martensson
- */
-
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/device.h>
-#include <linux/platform_device.h>
-#include <linux/string.h>
-#include <linux/workqueue.h>
-#include <linux/completion.h>
-#include <linux/list.h>
-#include <linux/interrupt.h>
-#include <linux/dma-mapping.h>
-#include <linux/delay.h>
-#include <linux/sched.h>
-#include <linux/debugfs.h>
-#include <linux/if_arp.h>
-#include <net/caif/caif_layer.h>
-#include <net/caif/caif_spi.h>
-
-#ifndef CONFIG_CAIF_SPI_SYNC
-#define FLAVOR "Flavour: Vanilla.\n"
-#else
-#define FLAVOR "Flavour: Master CMD&LEN at start.\n"
-#endif /* CONFIG_CAIF_SPI_SYNC */
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Daniel Martensson");
-MODULE_DESCRIPTION("CAIF SPI driver");
-
-/* Returns the number of padding bytes for alignment. */
-#define PAD_POW2(x, pow) ((((x)&((pow)-1))==0) ? 0 : (((pow)-((x)&((pow)-1)))))
-
-static bool spi_loop;
-module_param(spi_loop, bool, 0444);
-MODULE_PARM_DESC(spi_loop, "SPI running in loopback mode.");
-
-/* SPI frame alignment. */
-module_param(spi_frm_align, int, 0444);
-MODULE_PARM_DESC(spi_frm_align, "SPI frame alignment.");
-
-/*
- * SPI padding options.
- * Warning: must be a base of 2 (& operation used) and can not be zero !
- */
-module_param(spi_up_head_align, int, 0444);
-MODULE_PARM_DESC(spi_up_head_align, "SPI uplink head alignment.");
-
-module_param(spi_up_tail_align, int, 0444);
-MODULE_PARM_DESC(spi_up_tail_align, "SPI uplink tail alignment.");
-
-module_param(spi_down_head_align, int, 0444);
-MODULE_PARM_DESC(spi_down_head_align, "SPI downlink head alignment.");
-
-module_param(spi_down_tail_align, int, 0444);
-MODULE_PARM_DESC(spi_down_tail_align, "SPI downlink tail alignment.");
-
-#ifdef CONFIG_ARM
-#define BYTE_HEX_FMT "%02X"
-#else
-#define BYTE_HEX_FMT "%02hhX"
-#endif
-
-#define SPI_MAX_PAYLOAD_SIZE 4096
-/*
- * Threshold values for the SPI packet queue. Flowcontrol will be asserted
- * when the number of packets exceeds HIGH_WATER_MARK. It will not be
- * deasserted before the number of packets drops below LOW_WATER_MARK.
- */
-#define LOW_WATER_MARK   100
-#define HIGH_WATER_MARK  (LOW_WATER_MARK*5)
-
-#ifndef CONFIG_HAS_DMA
-
-/*
- * We sometimes use UML for debugging, but it cannot handle
- * dma_alloc_coherent so we have to wrap it.
- */
-static inline void *dma_alloc(struct cfspi *cfspi, dma_addr_t *daddr)
-{
-	return kmalloc(SPI_DMA_BUF_LEN, GFP_KERNEL);
-}
-
-static inline void dma_free(struct cfspi *cfspi, void *cpu_addr,
-		dma_addr_t handle)
-{
-	kfree(cpu_addr);
-}
-
-#else
-
-static inline void *dma_alloc(struct cfspi *cfspi, dma_addr_t *daddr)
-{
-	return dma_alloc_coherent(&cfspi->pdev->dev, SPI_DMA_BUF_LEN, daddr,
-				GFP_KERNEL);
-}
-
-static inline void dma_free(struct cfspi *cfspi, void *cpu_addr,
-		dma_addr_t handle)
-{
-	dma_free_coherent(&cfspi->pdev->dev, SPI_DMA_BUF_LEN, cpu_addr, handle);
-}
-#endif	/* CONFIG_HAS_DMA */
-
-#ifdef CONFIG_DEBUG_FS
-
-#define DEBUGFS_BUF_SIZE	4096
-
-static struct dentry *dbgfs_root;
-
-static inline void driver_debugfs_create(void)
-{
-	dbgfs_root = debugfs_create_dir(cfspi_spi_driver.driver.name, NULL);
-}
-
-static inline void driver_debugfs_remove(void)
-{
-	debugfs_remove(dbgfs_root);
-}
-
-static inline void dev_debugfs_rem(struct cfspi *cfspi)
-{
-	debugfs_remove(cfspi->dbgfs_frame);
-	debugfs_remove(cfspi->dbgfs_state);
-	debugfs_remove(cfspi->dbgfs_dir);
-}
-
-static ssize_t dbgfs_state(struct file *file, char __user *user_buf,
-			   size_t count, loff_t *ppos)
-{
-	char *buf;
-	int len = 0;
-	ssize_t size;
-	struct cfspi *cfspi = file->private_data;
-
-	buf = kzalloc(DEBUGFS_BUF_SIZE, GFP_KERNEL);
-	if (!buf)
-		return 0;
-
-	/* Print out debug information. */
-	len += scnprintf((buf + len), (DEBUGFS_BUF_SIZE - len),
-			 "CAIF SPI debug information:\n");
-
-	len += scnprintf((buf + len), (DEBUGFS_BUF_SIZE - len), FLAVOR);
-
-	len += scnprintf((buf + len), (DEBUGFS_BUF_SIZE - len),
-			 "STATE: %d\n", cfspi->dbg_state);
-	len += scnprintf((buf + len), (DEBUGFS_BUF_SIZE - len),
-			 "Previous CMD: 0x%x\n", cfspi->pcmd);
-	len += scnprintf((buf + len), (DEBUGFS_BUF_SIZE - len),
-			 "Current CMD: 0x%x\n", cfspi->cmd);
-	len += scnprintf((buf + len), (DEBUGFS_BUF_SIZE - len),
-			 "Previous TX len: %d\n", cfspi->tx_ppck_len);
-	len += scnprintf((buf + len), (DEBUGFS_BUF_SIZE - len),
-			 "Previous RX len: %d\n", cfspi->rx_ppck_len);
-	len += scnprintf((buf + len), (DEBUGFS_BUF_SIZE - len),
-			 "Current TX len: %d\n", cfspi->tx_cpck_len);
-	len += scnprintf((buf + len), (DEBUGFS_BUF_SIZE - len),
-			 "Current RX len: %d\n", cfspi->rx_cpck_len);
-	len += scnprintf((buf + len), (DEBUGFS_BUF_SIZE - len),
-			 "Next TX len: %d\n", cfspi->tx_npck_len);
-	len += scnprintf((buf + len), (DEBUGFS_BUF_SIZE - len),
-			 "Next RX len: %d\n", cfspi->rx_npck_len);
-
-	if (len > DEBUGFS_BUF_SIZE)
-		len = DEBUGFS_BUF_SIZE;
-
-	size = simple_read_from_buffer(user_buf, count, ppos, buf, len);
-	kfree(buf);
-
-	return size;
-}
-
-static ssize_t print_frame(char *buf, size_t size, char *frm,
-			   size_t count, size_t cut)
-{
-	int len = 0;
-	int i;
-	for (i = 0; i < count; i++) {
-		len += scnprintf((buf + len), (size - len),
-					"[0x" BYTE_HEX_FMT "]",
-					frm[i]);
-		if ((i == cut) && (count > (cut * 2))) {
-			/* Fast forward. */
-			i = count - cut;
-			len += scnprintf((buf + len), (size - len),
-					 "--- %zu bytes skipped ---\n",
-					 count - (cut * 2));
-		}
-
-		if ((!(i % 10)) && i) {
-			len += scnprintf((buf + len), (DEBUGFS_BUF_SIZE - len),
-					 "\n");
-		}
-	}
-	len += scnprintf((buf + len), (DEBUGFS_BUF_SIZE - len), "\n");
-	return len;
-}
-
-static ssize_t dbgfs_frame(struct file *file, char __user *user_buf,
-			   size_t count, loff_t *ppos)
-{
-	char *buf;
-	int len = 0;
-	ssize_t size;
-	struct cfspi *cfspi;
-
-	cfspi = file->private_data;
-	buf = kzalloc(DEBUGFS_BUF_SIZE, GFP_KERNEL);
-	if (!buf)
-		return 0;
-
-	/* Print out debug information. */
-	len += scnprintf((buf + len), (DEBUGFS_BUF_SIZE - len),
-			 "Current frame:\n");
-
-	len += scnprintf((buf + len), (DEBUGFS_BUF_SIZE - len),
-			 "Tx data (Len: %d):\n", cfspi->tx_cpck_len);
-
-	len += print_frame((buf + len), (DEBUGFS_BUF_SIZE - len),
-			   cfspi->xfer.va_tx[0],
-			   (cfspi->tx_cpck_len + SPI_CMD_SZ), 100);
-
-	len += scnprintf((buf + len), (DEBUGFS_BUF_SIZE - len),
-			 "Rx data (Len: %d):\n", cfspi->rx_cpck_len);
-
-	len += print_frame((buf + len), (DEBUGFS_BUF_SIZE - len),
-			   cfspi->xfer.va_rx,
-			   (cfspi->rx_cpck_len + SPI_CMD_SZ), 100);
-
-	size = simple_read_from_buffer(user_buf, count, ppos, buf, len);
-	kfree(buf);
-
-	return size;
-}
-
-static const struct file_operations dbgfs_state_fops = {
-	.open = simple_open,
-	.read = dbgfs_state,
-	.owner = THIS_MODULE
-};
-
-static const struct file_operations dbgfs_frame_fops = {
-	.open = simple_open,
-	.read = dbgfs_frame,
-	.owner = THIS_MODULE
-};
-
-static inline void dev_debugfs_add(struct cfspi *cfspi)
-{
-	cfspi->dbgfs_dir = debugfs_create_dir(cfspi->pdev->name, dbgfs_root);
-	cfspi->dbgfs_state = debugfs_create_file("state", 0444,
-						 cfspi->dbgfs_dir, cfspi,
-						 &dbgfs_state_fops);
-	cfspi->dbgfs_frame = debugfs_create_file("frame", 0444,
-						 cfspi->dbgfs_dir, cfspi,
-						 &dbgfs_frame_fops);
-}
-
-inline void cfspi_dbg_state(struct cfspi *cfspi, int state)
-{
-	cfspi->dbg_state = state;
-};
-#else
-
-static inline void driver_debugfs_create(void)
-{
-}
-
-static inline void driver_debugfs_remove(void)
-{
-}
-
-static inline void dev_debugfs_add(struct cfspi *cfspi)
-{
-}
-
-static inline void dev_debugfs_rem(struct cfspi *cfspi)
-{
-}
-
-inline void cfspi_dbg_state(struct cfspi *cfspi, int state)
-{
-}
-#endif				/* CONFIG_DEBUG_FS */
-
-static LIST_HEAD(cfspi_list);
-static spinlock_t cfspi_list_lock;
-
-/* SPI uplink head alignment. */
-static ssize_t up_head_align_show(struct device_driver *driver, char *buf)
-{
-	return sprintf(buf, "%d\n", spi_up_head_align);
-}
-
-static DRIVER_ATTR_RO(up_head_align);
-
-/* SPI uplink tail alignment. */
-static ssize_t up_tail_align_show(struct device_driver *driver, char *buf)
-{
-	return sprintf(buf, "%d\n", spi_up_tail_align);
-}
-
-static DRIVER_ATTR_RO(up_tail_align);
-
-/* SPI downlink head alignment. */
-static ssize_t down_head_align_show(struct device_driver *driver, char *buf)
-{
-	return sprintf(buf, "%d\n", spi_down_head_align);
-}
-
-static DRIVER_ATTR_RO(down_head_align);
-
-/* SPI downlink tail alignment. */
-static ssize_t down_tail_align_show(struct device_driver *driver, char *buf)
-{
-	return sprintf(buf, "%d\n", spi_down_tail_align);
-}
-
-static DRIVER_ATTR_RO(down_tail_align);
-
-/* SPI frame alignment. */
-static ssize_t frame_align_show(struct device_driver *driver, char *buf)
-{
-	return sprintf(buf, "%d\n", spi_frm_align);
-}
-
-static DRIVER_ATTR_RO(frame_align);
-
-int cfspi_xmitfrm(struct cfspi *cfspi, u8 *buf, size_t len)
-{
-	u8 *dst = buf;
-	caif_assert(buf);
-
-	if (cfspi->slave && !cfspi->slave_talked)
-		cfspi->slave_talked = true;
-
-	do {
-		struct sk_buff *skb;
-		struct caif_payload_info *info;
-		int spad = 0;
-		int epad;
-
-		skb = skb_dequeue(&cfspi->chead);
-		if (!skb)
-			break;
-
-		/*
-		 * Calculate length of frame including SPI padding.
-		 * The payload position is found in the control buffer.
-		 */
-		info = (struct caif_payload_info *)&skb->cb;
-
-		/*
-		 * Compute head offset i.e. number of bytes to add to
-		 * get the start of the payload aligned.
-		 */
-		if (spi_up_head_align > 1) {
-			spad = 1 + PAD_POW2((info->hdr_len + 1), spi_up_head_align);
-			*dst = (u8)(spad - 1);
-			dst += spad;
-		}
-
-		/* Copy in CAIF frame. */
-		skb_copy_bits(skb, 0, dst, skb->len);
-		dst += skb->len;
-		cfspi->ndev->stats.tx_packets++;
-		cfspi->ndev->stats.tx_bytes += skb->len;
-
-		/*
-		 * Compute tail offset i.e. number of bytes to add to
-		 * get the complete CAIF frame aligned.
-		 */
-		epad = PAD_POW2((skb->len + spad), spi_up_tail_align);
-		dst += epad;
-
-		dev_kfree_skb(skb);
-
-	} while ((dst - buf) < len);
-
-	return dst - buf;
-}
-
-int cfspi_xmitlen(struct cfspi *cfspi)
-{
-	struct sk_buff *skb = NULL;
-	int frm_len = 0;
-	int pkts = 0;
-
-	/*
-	 * Decommit previously committed frames.
-	 * skb_queue_splice_tail(&cfspi->chead,&cfspi->qhead)
-	 */
-	while (skb_peek(&cfspi->chead)) {
-		skb = skb_dequeue_tail(&cfspi->chead);
-		skb_queue_head(&cfspi->qhead, skb);
-	}
-
-	do {
-		struct caif_payload_info *info = NULL;
-		int spad = 0;
-		int epad = 0;
-
-		skb = skb_dequeue(&cfspi->qhead);
-		if (!skb)
-			break;
-
-		/*
-		 * Calculate length of frame including SPI padding.
-		 * The payload position is found in the control buffer.
-		 */
-		info = (struct caif_payload_info *)&skb->cb;
-
-		/*
-		 * Compute head offset i.e. number of bytes to add to
-		 * get the start of the payload aligned.
-		 */
-		if (spi_up_head_align > 1)
-			spad = 1 + PAD_POW2((info->hdr_len + 1), spi_up_head_align);
-
-		/*
-		 * Compute tail offset i.e. number of bytes to add to
-		 * get the complete CAIF frame aligned.
-		 */
-		epad = PAD_POW2((skb->len + spad), spi_up_tail_align);
-
-		if ((skb->len + spad + epad + frm_len) <= CAIF_MAX_SPI_FRAME) {
-			skb_queue_tail(&cfspi->chead, skb);
-			pkts++;
-			frm_len += skb->len + spad + epad;
-		} else {
-			/* Put back packet. */
-			skb_queue_head(&cfspi->qhead, skb);
-			break;
-		}
-	} while (pkts <= CAIF_MAX_SPI_PKTS);
-
-	/*
-	 * Send flow on if previously sent flow off
-	 * and now go below the low water mark
-	 */
-	if (cfspi->flow_off_sent && cfspi->qhead.qlen < cfspi->qd_low_mark &&
-		cfspi->cfdev.flowctrl) {
-		cfspi->flow_off_sent = 0;
-		cfspi->cfdev.flowctrl(cfspi->ndev, 1);
-	}
-
-	return frm_len;
-}
-
-static void cfspi_ss_cb(bool assert, struct cfspi_ifc *ifc)
-{
-	struct cfspi *cfspi = (struct cfspi *)ifc->priv;
-
-	/*
-	 * The slave device is the master on the link. Interrupts before the
-	 * slave has transmitted are considered spurious.
-	 */
-	if (cfspi->slave && !cfspi->slave_talked) {
-		printk(KERN_WARNING "CFSPI: Spurious SS interrupt.\n");
-		return;
-	}
-
-	if (!in_interrupt())
-		spin_lock(&cfspi->lock);
-	if (assert) {
-		set_bit(SPI_SS_ON, &cfspi->state);
-		set_bit(SPI_XFER, &cfspi->state);
-	} else {
-		set_bit(SPI_SS_OFF, &cfspi->state);
-	}
-	if (!in_interrupt())
-		spin_unlock(&cfspi->lock);
-
-	/* Wake up the xfer thread. */
-	if (assert)
-		wake_up_interruptible(&cfspi->wait);
-}
-
-static void cfspi_xfer_done_cb(struct cfspi_ifc *ifc)
-{
-	struct cfspi *cfspi = (struct cfspi *)ifc->priv;
-
-	/* Transfer done, complete work queue */
-	complete(&cfspi->comp);
-}
-
-static netdev_tx_t cfspi_xmit(struct sk_buff *skb, struct net_device *dev)
-{
-	struct cfspi *cfspi = NULL;
-	unsigned long flags;
-	if (!dev)
-		return -EINVAL;
-
-	cfspi = netdev_priv(dev);
-
-	skb_queue_tail(&cfspi->qhead, skb);
-
-	spin_lock_irqsave(&cfspi->lock, flags);
-	if (!test_and_set_bit(SPI_XFER, &cfspi->state)) {
-		/* Wake up xfer thread. */
-		wake_up_interruptible(&cfspi->wait);
-	}
-	spin_unlock_irqrestore(&cfspi->lock, flags);
-
-	/* Send flow off if number of bytes is above high water mark */
-	if (!cfspi->flow_off_sent &&
-		cfspi->qhead.qlen > cfspi->qd_high_mark &&
-		cfspi->cfdev.flowctrl) {
-		cfspi->flow_off_sent = 1;
-		cfspi->cfdev.flowctrl(cfspi->ndev, 0);
-	}
-
-	return NETDEV_TX_OK;
-}
-
-int cfspi_rxfrm(struct cfspi *cfspi, u8 *buf, size_t len)
-{
-	u8 *src = buf;
-
-	caif_assert(buf != NULL);
-
-	do {
-		int res;
-		struct sk_buff *skb = NULL;
-		int spad = 0;
-		int epad = 0;
-		int pkt_len = 0;
-
-		/*
-		 * Compute head offset i.e. number of bytes added to
-		 * get the start of the payload aligned.
-		 */
-		if (spi_down_head_align > 1) {
-			spad = 1 + *src;
-			src += spad;
-		}
-
-		/* Read length of CAIF frame (little endian). */
-		pkt_len = *src;
-		pkt_len |= ((*(src+1)) << 8) & 0xFF00;
-		pkt_len += 2;	/* Add FCS fields. */
-
-		/* Get a suitable caif packet and copy in data. */
-
-		skb = netdev_alloc_skb(cfspi->ndev, pkt_len + 1);
-		caif_assert(skb != NULL);
-
-		skb_put_data(skb, src, pkt_len);
-		src += pkt_len;
-
-		skb->protocol = htons(ETH_P_CAIF);
-		skb_reset_mac_header(skb);
-
-		/*
-		 * Push received packet up the stack.
-		 */
-		if (!spi_loop)
-			res = netif_rx_ni(skb);
-		else
-			res = cfspi_xmit(skb, cfspi->ndev);
-
-		if (!res) {
-			cfspi->ndev->stats.rx_packets++;
-			cfspi->ndev->stats.rx_bytes += pkt_len;
-		} else
-			cfspi->ndev->stats.rx_dropped++;
-
-		/*
-		 * Compute tail offset i.e. number of bytes added to
-		 * get the complete CAIF frame aligned.
-		 */
-		epad = PAD_POW2((pkt_len + spad), spi_down_tail_align);
-		src += epad;
-	} while ((src - buf) < len);
-
-	return src - buf;
-}
-
-static int cfspi_open(struct net_device *dev)
-{
-	netif_wake_queue(dev);
-	return 0;
-}
-
-static int cfspi_close(struct net_device *dev)
-{
-	netif_stop_queue(dev);
-	return 0;
-}
-
-static int cfspi_init(struct net_device *dev)
-{
-	int res = 0;
-	struct cfspi *cfspi = netdev_priv(dev);
-
-	/* Set flow info. */
-	cfspi->flow_off_sent = 0;
-	cfspi->qd_low_mark = LOW_WATER_MARK;
-	cfspi->qd_high_mark = HIGH_WATER_MARK;
-
-	/* Set slave info. */
-	if (!strncmp(cfspi_spi_driver.driver.name, "cfspi_sspi", 10)) {
-		cfspi->slave = true;
-		cfspi->slave_talked = false;
-	} else {
-		cfspi->slave = false;
-		cfspi->slave_talked = false;
-	}
-
-	/* Allocate DMA buffers. */
-	cfspi->xfer.va_tx[0] = dma_alloc(cfspi, &cfspi->xfer.pa_tx[0]);
-	if (!cfspi->xfer.va_tx[0]) {
-		res = -ENODEV;
-		goto err_dma_alloc_tx_0;
-	}
-
-	cfspi->xfer.va_rx = dma_alloc(cfspi, &cfspi->xfer.pa_rx);
-
-	if (!cfspi->xfer.va_rx) {
-		res = -ENODEV;
-		goto err_dma_alloc_rx;
-	}
-
-	/* Initialize the work queue. */
-	INIT_WORK(&cfspi->work, cfspi_xfer);
-
-	/* Initialize spin locks. */
-	spin_lock_init(&cfspi->lock);
-
-	/* Initialize flow control state. */
-	cfspi->flow_stop = false;
-
-	/* Initialize wait queue. */
-	init_waitqueue_head(&cfspi->wait);
-
-	/* Create work thread. */
-	cfspi->wq = create_singlethread_workqueue(dev->name);
-	if (!cfspi->wq) {
-		printk(KERN_WARNING "CFSPI: failed to create work queue.\n");
-		res = -ENODEV;
-		goto err_create_wq;
-	}
-
-	/* Initialize work queue. */
-	init_completion(&cfspi->comp);
-
-	/* Create debugfs entries. */
-	dev_debugfs_add(cfspi);
-
-	/* Set up the ifc. */
-	cfspi->ifc.ss_cb = cfspi_ss_cb;
-	cfspi->ifc.xfer_done_cb = cfspi_xfer_done_cb;
-	cfspi->ifc.priv = cfspi;
-
-	/* Add CAIF SPI device to list. */
-	spin_lock(&cfspi_list_lock);
-	list_add_tail(&cfspi->list, &cfspi_list);
-	spin_unlock(&cfspi_list_lock);
-
-	/* Schedule the work queue. */
-	queue_work(cfspi->wq, &cfspi->work);
-
-	return 0;
-
- err_create_wq:
-	dma_free(cfspi, cfspi->xfer.va_rx, cfspi->xfer.pa_rx);
- err_dma_alloc_rx:
-	dma_free(cfspi, cfspi->xfer.va_tx[0], cfspi->xfer.pa_tx[0]);
- err_dma_alloc_tx_0:
-	return res;
-}
-
-static void cfspi_uninit(struct net_device *dev)
-{
-	struct cfspi *cfspi = netdev_priv(dev);
-
-	/* Remove from list. */
-	spin_lock(&cfspi_list_lock);
-	list_del(&cfspi->list);
-	spin_unlock(&cfspi_list_lock);
-
-	cfspi->ndev = NULL;
-	/* Free DMA buffers. */
-	dma_free(cfspi, cfspi->xfer.va_rx, cfspi->xfer.pa_rx);
-	dma_free(cfspi, cfspi->xfer.va_tx[0], cfspi->xfer.pa_tx[0]);
-	set_bit(SPI_TERMINATE, &cfspi->state);
-	wake_up_interruptible(&cfspi->wait);
-	destroy_workqueue(cfspi->wq);
-	/* Destroy debugfs directory and files. */
-	dev_debugfs_rem(cfspi);
-	return;
-}
-
-static const struct net_device_ops cfspi_ops = {
-	.ndo_open = cfspi_open,
-	.ndo_stop = cfspi_close,
-	.ndo_init = cfspi_init,
-	.ndo_uninit = cfspi_uninit,
-	.ndo_start_xmit = cfspi_xmit
-};
-
-static void cfspi_setup(struct net_device *dev)
-{
-	struct cfspi *cfspi = netdev_priv(dev);
-	dev->features = 0;
-	dev->netdev_ops = &cfspi_ops;
-	dev->type = ARPHRD_CAIF;
-	dev->flags = IFF_NOARP | IFF_POINTOPOINT;
-	dev->priv_flags |= IFF_NO_QUEUE;
-	dev->mtu = SPI_MAX_PAYLOAD_SIZE;
-	dev->needs_free_netdev = true;
-	skb_queue_head_init(&cfspi->qhead);
-	skb_queue_head_init(&cfspi->chead);
-	cfspi->cfdev.link_select = CAIF_LINK_HIGH_BANDW;
-	cfspi->cfdev.use_frag = false;
-	cfspi->cfdev.use_stx = false;
-	cfspi->cfdev.use_fcs = false;
-	cfspi->ndev = dev;
-}
-
-int cfspi_spi_probe(struct platform_device *pdev)
-{
-	struct cfspi *cfspi = NULL;
-	struct net_device *ndev;
-	struct cfspi_dev *dev;
-	int res;
-	dev = (struct cfspi_dev *)pdev->dev.platform_data;
-
-	if (!dev)
-		return -ENODEV;
-
-	ndev = alloc_netdev(sizeof(struct cfspi), "cfspi%d",
-			    NET_NAME_UNKNOWN, cfspi_setup);
-	if (!ndev)
-		return -ENOMEM;
-
-	cfspi = netdev_priv(ndev);
-	netif_stop_queue(ndev);
-	cfspi->ndev = ndev;
-	cfspi->pdev = pdev;
-
-	/* Assign the SPI device. */
-	cfspi->dev = dev;
-	/* Assign the device ifc to this SPI interface. */
-	dev->ifc = &cfspi->ifc;
-
-	/* Register network device. */
-	res = register_netdev(ndev);
-	if (res) {
-		printk(KERN_ERR "CFSPI: Reg. error: %d.\n", res);
-		goto err_net_reg;
-	}
-	return res;
-
- err_net_reg:
-	free_netdev(ndev);
-
-	return res;
-}
-
-int cfspi_spi_remove(struct platform_device *pdev)
-{
-	/* Everything is done in cfspi_uninit(). */
-	return 0;
-}
-
-static void __exit cfspi_exit_module(void)
-{
-	struct list_head *list_node;
-	struct list_head *n;
-	struct cfspi *cfspi = NULL;
-
-	list_for_each_safe(list_node, n, &cfspi_list) {
-		cfspi = list_entry(list_node, struct cfspi, list);
-		unregister_netdev(cfspi->ndev);
-	}
-
-	/* Destroy sysfs files. */
-	driver_remove_file(&cfspi_spi_driver.driver,
-			   &driver_attr_up_head_align);
-	driver_remove_file(&cfspi_spi_driver.driver,
-			   &driver_attr_up_tail_align);
-	driver_remove_file(&cfspi_spi_driver.driver,
-			   &driver_attr_down_head_align);
-	driver_remove_file(&cfspi_spi_driver.driver,
-			   &driver_attr_down_tail_align);
-	driver_remove_file(&cfspi_spi_driver.driver, &driver_attr_frame_align);
-	/* Unregister platform driver. */
-	platform_driver_unregister(&cfspi_spi_driver);
-	/* Destroy debugfs root directory. */
-	driver_debugfs_remove();
-}
-
-static int __init cfspi_init_module(void)
-{
-	int result;
-
-	/* Initialize spin lock. */
-	spin_lock_init(&cfspi_list_lock);
-
-	/* Register platform driver. */
-	result = platform_driver_register(&cfspi_spi_driver);
-	if (result) {
-		printk(KERN_ERR "Could not register platform SPI driver.\n");
-		goto err_dev_register;
-	}
-
-	/* Create sysfs files. */
-	result =
-	    driver_create_file(&cfspi_spi_driver.driver,
-			       &driver_attr_up_head_align);
-	if (result) {
-		printk(KERN_ERR "Sysfs creation failed 1.\n");
-		goto err_create_up_head_align;
-	}
-
-	result =
-	    driver_create_file(&cfspi_spi_driver.driver,
-			       &driver_attr_up_tail_align);
-	if (result) {
-		printk(KERN_ERR "Sysfs creation failed 2.\n");
-		goto err_create_up_tail_align;
-	}
-
-	result =
-	    driver_create_file(&cfspi_spi_driver.driver,
-			       &driver_attr_down_head_align);
-	if (result) {
-		printk(KERN_ERR "Sysfs creation failed 3.\n");
-		goto err_create_down_head_align;
-	}
-
-	result =
-	    driver_create_file(&cfspi_spi_driver.driver,
-			       &driver_attr_down_tail_align);
-	if (result) {
-		printk(KERN_ERR "Sysfs creation failed 4.\n");
-		goto err_create_down_tail_align;
-	}
-
-	result =
-	    driver_create_file(&cfspi_spi_driver.driver,
-			       &driver_attr_frame_align);
-	if (result) {
-		printk(KERN_ERR "Sysfs creation failed 5.\n");
-		goto err_create_frame_align;
-	}
-	driver_debugfs_create();
-	return result;
-
- err_create_frame_align:
-	driver_remove_file(&cfspi_spi_driver.driver,
-			   &driver_attr_down_tail_align);
- err_create_down_tail_align:
-	driver_remove_file(&cfspi_spi_driver.driver,
-			   &driver_attr_down_head_align);
- err_create_down_head_align:
-	driver_remove_file(&cfspi_spi_driver.driver,
-			   &driver_attr_up_tail_align);
- err_create_up_tail_align:
-	driver_remove_file(&cfspi_spi_driver.driver,
-			   &driver_attr_up_head_align);
- err_create_up_head_align:
-	platform_driver_unregister(&cfspi_spi_driver);
- err_dev_register:
-	return result;
-}
-
-module_init(cfspi_init_module);
-module_exit(cfspi_exit_module);
diff --git a/drivers/net/caif/caif_spi_slave.c b/drivers/net/caif/caif_spi_slave.c
deleted file mode 100644
index bb776d33dd8f..000000000000
--- a/drivers/net/caif/caif_spi_slave.c
+++ /dev/null
@@ -1,254 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Copyright (C) ST-Ericsson AB 2010
- * Author:  Daniel Martensson
- */
-#include <linux/module.h>
-#include <linux/device.h>
-#include <linux/platform_device.h>
-#include <linux/string.h>
-#include <linux/semaphore.h>
-#include <linux/workqueue.h>
-#include <linux/completion.h>
-#include <linux/list.h>
-#include <linux/interrupt.h>
-#include <linux/dma-mapping.h>
-#include <linux/delay.h>
-#include <linux/sched.h>
-#include <linux/debugfs.h>
-#include <net/caif/caif_spi.h>
-
-#ifndef CONFIG_CAIF_SPI_SYNC
-#define SPI_DATA_POS 0
-static inline int forward_to_spi_cmd(struct cfspi *cfspi)
-{
-	return cfspi->rx_cpck_len;
-}
-#else
-#define SPI_DATA_POS SPI_CMD_SZ
-static inline int forward_to_spi_cmd(struct cfspi *cfspi)
-{
-	return 0;
-}
-#endif
-
-int spi_frm_align = 2;
-
-/*
- * SPI padding options.
- * Warning: must be a base of 2 (& operation used) and can not be zero !
- */
-int spi_up_head_align   = 1 << 1;
-int spi_up_tail_align   = 1 << 0;
-int spi_down_head_align = 1 << 2;
-int spi_down_tail_align = 1 << 1;
-
-#ifdef CONFIG_DEBUG_FS
-static inline void debugfs_store_prev(struct cfspi *cfspi)
-{
-	/* Store previous command for debugging reasons.*/
-	cfspi->pcmd = cfspi->cmd;
-	/* Store previous transfer. */
-	cfspi->tx_ppck_len = cfspi->tx_cpck_len;
-	cfspi->rx_ppck_len = cfspi->rx_cpck_len;
-}
-#else
-static inline void debugfs_store_prev(struct cfspi *cfspi)
-{
-}
-#endif
-
-void cfspi_xfer(struct work_struct *work)
-{
-	struct cfspi *cfspi;
-	u8 *ptr = NULL;
-	unsigned long flags;
-	int ret;
-	cfspi = container_of(work, struct cfspi, work);
-
-	/* Initialize state. */
-	cfspi->cmd = SPI_CMD_EOT;
-
-	for (;;) {
-
-		cfspi_dbg_state(cfspi, CFSPI_STATE_WAITING);
-
-		/* Wait for master talk or transmit event. */
-		wait_event_interruptible(cfspi->wait,
-				 test_bit(SPI_XFER, &cfspi->state) ||
-				 test_bit(SPI_TERMINATE, &cfspi->state));
-
-		if (test_bit(SPI_TERMINATE, &cfspi->state))
-			return;
-
-#if CFSPI_DBG_PREFILL
-		/* Prefill buffers for easier debugging. */
-		memset(cfspi->xfer.va_tx, 0xFF, SPI_DMA_BUF_LEN);
-		memset(cfspi->xfer.va_rx, 0xFF, SPI_DMA_BUF_LEN);
-#endif	/* CFSPI_DBG_PREFILL */
-
-		cfspi_dbg_state(cfspi, CFSPI_STATE_AWAKE);
-
-	/* Check whether we have a committed frame. */
-		if (cfspi->tx_cpck_len) {
-			int len;
-
-			cfspi_dbg_state(cfspi, CFSPI_STATE_FETCH_PKT);
-
-			/* Copy committed SPI frames after the SPI indication. */
-			ptr = (u8 *) cfspi->xfer.va_tx;
-			ptr += SPI_IND_SZ;
-			len = cfspi_xmitfrm(cfspi, ptr, cfspi->tx_cpck_len);
-			WARN_ON(len != cfspi->tx_cpck_len);
-	}
-
-		cfspi_dbg_state(cfspi, CFSPI_STATE_GET_NEXT);
-
-		/* Get length of next frame to commit. */
-		cfspi->tx_npck_len = cfspi_xmitlen(cfspi);
-
-		WARN_ON(cfspi->tx_npck_len > SPI_DMA_BUF_LEN);
-
-		/*
-		 * Add indication and length at the beginning of the frame,
-		 * using little endian.
-		 */
-		ptr = (u8 *) cfspi->xfer.va_tx;
-		*ptr++ = SPI_CMD_IND;
-		*ptr++ = (SPI_CMD_IND  & 0xFF00) >> 8;
-		*ptr++ = cfspi->tx_npck_len & 0x00FF;
-		*ptr++ = (cfspi->tx_npck_len & 0xFF00) >> 8;
-
-		/* Calculate length of DMAs. */
-		cfspi->xfer.tx_dma_len = cfspi->tx_cpck_len + SPI_IND_SZ;
-		cfspi->xfer.rx_dma_len = cfspi->rx_cpck_len + SPI_CMD_SZ;
-
-		/* Add SPI TX frame alignment padding, if necessary. */
-		if (cfspi->tx_cpck_len &&
-			(cfspi->xfer.tx_dma_len % spi_frm_align)) {
-
-			cfspi->xfer.tx_dma_len += spi_frm_align -
-			    (cfspi->xfer.tx_dma_len % spi_frm_align);
-		}
-
-		/* Add SPI RX frame alignment padding, if necessary. */
-		if (cfspi->rx_cpck_len &&
-			(cfspi->xfer.rx_dma_len % spi_frm_align)) {
-
-			cfspi->xfer.rx_dma_len += spi_frm_align -
-			    (cfspi->xfer.rx_dma_len % spi_frm_align);
-		}
-
-		cfspi_dbg_state(cfspi, CFSPI_STATE_INIT_XFER);
-
-		/* Start transfer. */
-		ret = cfspi->dev->init_xfer(&cfspi->xfer, cfspi->dev);
-		WARN_ON(ret);
-
-		cfspi_dbg_state(cfspi, CFSPI_STATE_WAIT_ACTIVE);
-
-		/*
-		 * TODO: We might be able to make an assumption if this is the
-		 * first loop. Make sure that minimum toggle time is respected.
-		 */
-		udelay(MIN_TRANSITION_TIME_USEC);
-
-		cfspi_dbg_state(cfspi, CFSPI_STATE_SIG_ACTIVE);
-
-		/* Signal that we are ready to receive data. */
-		cfspi->dev->sig_xfer(true, cfspi->dev);
-
-		cfspi_dbg_state(cfspi, CFSPI_STATE_WAIT_XFER_DONE);
-
-		/* Wait for transfer completion. */
-		wait_for_completion(&cfspi->comp);
-
-		cfspi_dbg_state(cfspi, CFSPI_STATE_XFER_DONE);
-
-		if (cfspi->cmd == SPI_CMD_EOT) {
-			/*
-			 * Clear the master talk bit. A xfer is always at
-			 *  least two bursts.
-			 */
-			clear_bit(SPI_SS_ON, &cfspi->state);
-		}
-
-		cfspi_dbg_state(cfspi, CFSPI_STATE_WAIT_INACTIVE);
-
-		/* Make sure that the minimum toggle time is respected. */
-		if (SPI_XFER_TIME_USEC(cfspi->xfer.tx_dma_len,
-					cfspi->dev->clk_mhz) <
-			MIN_TRANSITION_TIME_USEC) {
-
-			udelay(MIN_TRANSITION_TIME_USEC -
-				SPI_XFER_TIME_USEC
-				(cfspi->xfer.tx_dma_len, cfspi->dev->clk_mhz));
-		}
-
-		cfspi_dbg_state(cfspi, CFSPI_STATE_SIG_INACTIVE);
-
-		/* De-assert transfer signal. */
-		cfspi->dev->sig_xfer(false, cfspi->dev);
-
-		/* Check whether we received a CAIF packet. */
-		if (cfspi->rx_cpck_len) {
-			int len;
-
-			cfspi_dbg_state(cfspi, CFSPI_STATE_DELIVER_PKT);
-
-			/* Parse SPI frame. */
-			ptr = ((u8 *)(cfspi->xfer.va_rx + SPI_DATA_POS));
-
-			len = cfspi_rxfrm(cfspi, ptr, cfspi->rx_cpck_len);
-			WARN_ON(len != cfspi->rx_cpck_len);
-		}
-
-		/* Check the next SPI command and length. */
-		ptr = (u8 *) cfspi->xfer.va_rx;
-
-		ptr += forward_to_spi_cmd(cfspi);
-
-		cfspi->cmd = *ptr++;
-		cfspi->cmd |= ((*ptr++) << 8) & 0xFF00;
-		cfspi->rx_npck_len = *ptr++;
-		cfspi->rx_npck_len |= ((*ptr++) << 8) & 0xFF00;
-
-		WARN_ON(cfspi->rx_npck_len > SPI_DMA_BUF_LEN);
-		WARN_ON(cfspi->cmd > SPI_CMD_EOT);
-
-		debugfs_store_prev(cfspi);
-
-		/* Check whether the master issued an EOT command. */
-		if (cfspi->cmd == SPI_CMD_EOT) {
-			/* Reset state. */
-			cfspi->tx_cpck_len = 0;
-			cfspi->rx_cpck_len = 0;
-		} else {
-			/* Update state. */
-			cfspi->tx_cpck_len = cfspi->tx_npck_len;
-			cfspi->rx_cpck_len = cfspi->rx_npck_len;
-		}
-
-		/*
-		 * Check whether we need to clear the xfer bit.
-		 * Spin lock needed for packet insertion.
-		 * Test and clear of different bits
-		 * are not supported.
-		 */
-		spin_lock_irqsave(&cfspi->lock, flags);
-		if (cfspi->cmd == SPI_CMD_EOT && !cfspi_xmitlen(cfspi)
-			&& !test_bit(SPI_SS_ON, &cfspi->state))
-			clear_bit(SPI_XFER, &cfspi->state);
-
-		spin_unlock_irqrestore(&cfspi->lock, flags);
-	}
-}
-
-struct platform_driver cfspi_spi_driver = {
-	.probe = cfspi_spi_probe,
-	.remove = cfspi_spi_remove,
-	.driver = {
-		   .name = "cfspi_sspi",
-		   .owner = THIS_MODULE,
-		   },
-};
diff --git a/drivers/net/caif/caif_virtio.c b/drivers/net/caif/caif_virtio.c
index 80ea2e913c2b..47a6d62b7511 100644
--- a/drivers/net/caif/caif_virtio.c
+++ b/drivers/net/caif/caif_virtio.c
@@ -652,7 +652,7 @@ static int cfv_probe(struct virtio_device *vdev)
 	const char *cfv_netdev_name = "cfvrt";
 	struct net_device *netdev;
 	struct cfv_info *cfv;
-	int err = -EINVAL;
+	int err;
 
 	netdev = alloc_netdev(sizeof(struct cfv_info), cfv_netdev_name,
 			      NET_NAME_UNKNOWN, cfv_netdev_setup);
diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c
index 19403e88daa3..fbdd9a8c9374 100644
--- a/drivers/net/can/flexcan.c
+++ b/drivers/net/can/flexcan.c
@@ -9,7 +9,7 @@
 //
 // Based on code originally by Andrey Volkov <avolkov@varma-el.com>
 
-#include <linux/netdevice.h>
+#include <linux/bitfield.h>
 #include <linux/can.h>
 #include <linux/can/dev.h>
 #include <linux/can/error.h>
@@ -21,12 +21,14 @@
 #include <linux/io.h>
 #include <linux/mfd/syscon.h>
 #include <linux/module.h>
+#include <linux/netdevice.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
+#include <linux/pinctrl/consumer.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
-#include <linux/regulator/consumer.h>
 #include <linux/regmap.h>
+#include <linux/regulator/consumer.h>
 
 #define DRV_NAME			"flexcan"
 
@@ -52,6 +54,7 @@
 #define FLEXCAN_MCR_IRMQ		BIT(16)
 #define FLEXCAN_MCR_LPRIO_EN		BIT(13)
 #define FLEXCAN_MCR_AEN			BIT(12)
+#define FLEXCAN_MCR_FDEN		BIT(11)
 /* MCR_MAXMB: maximum used MBs is MAXMB + 1 */
 #define FLEXCAN_MCR_MAXMB(x)		((x) & 0x7f)
 #define FLEXCAN_MCR_IDAM_A		(0x0 << 8)
@@ -91,6 +94,7 @@
 #define FLEXCAN_CTRL2_MRP		BIT(18)
 #define FLEXCAN_CTRL2_RRS		BIT(17)
 #define FLEXCAN_CTRL2_EACEN		BIT(16)
+#define FLEXCAN_CTRL2_ISOCANFDEN	BIT(12)
 
 /* FLEXCAN memory error control register (MECR) bits */
 #define FLEXCAN_MECR_ECRWRDIS		BIT(31)
@@ -134,8 +138,35 @@
 	(FLEXCAN_ESR_ERR_BUS | FLEXCAN_ESR_ERR_STATE)
 #define FLEXCAN_ESR_ALL_INT \
 	(FLEXCAN_ESR_TWRN_INT | FLEXCAN_ESR_RWRN_INT | \
-	 FLEXCAN_ESR_BOFF_INT | FLEXCAN_ESR_ERR_INT | \
-	 FLEXCAN_ESR_WAK_INT)
+	 FLEXCAN_ESR_BOFF_INT | FLEXCAN_ESR_ERR_INT)
+
+/* FLEXCAN Bit Timing register (CBT) bits */
+#define FLEXCAN_CBT_BTF			BIT(31)
+#define FLEXCAN_CBT_EPRESDIV_MASK	GENMASK(30, 21)
+#define FLEXCAN_CBT_ERJW_MASK		GENMASK(20, 16)
+#define FLEXCAN_CBT_EPROPSEG_MASK	GENMASK(15, 10)
+#define FLEXCAN_CBT_EPSEG1_MASK		GENMASK(9, 5)
+#define FLEXCAN_CBT_EPSEG2_MASK		GENMASK(4, 0)
+
+/* FLEXCAN FD control register (FDCTRL) bits */
+#define FLEXCAN_FDCTRL_FDRATE		BIT(31)
+#define FLEXCAN_FDCTRL_MBDSR1		GENMASK(20, 19)
+#define FLEXCAN_FDCTRL_MBDSR0		GENMASK(17, 16)
+#define FLEXCAN_FDCTRL_MBDSR_8		0x0
+#define FLEXCAN_FDCTRL_MBDSR_12		0x1
+#define FLEXCAN_FDCTRL_MBDSR_32		0x2
+#define FLEXCAN_FDCTRL_MBDSR_64		0x3
+#define FLEXCAN_FDCTRL_TDCEN		BIT(15)
+#define FLEXCAN_FDCTRL_TDCFAIL		BIT(14)
+#define FLEXCAN_FDCTRL_TDCOFF		GENMASK(12, 8)
+#define FLEXCAN_FDCTRL_TDCVAL		GENMASK(5, 0)
+
+/* FLEXCAN FD Bit Timing register (FDCBT) bits */
+#define FLEXCAN_FDCBT_FPRESDIV_MASK	GENMASK(29, 20)
+#define FLEXCAN_FDCBT_FRJW_MASK		GENMASK(18, 16)
+#define FLEXCAN_FDCBT_FPROPSEG_MASK	GENMASK(14, 10)
+#define FLEXCAN_FDCBT_FPSEG1_MASK	GENMASK(7, 5)
+#define FLEXCAN_FDCBT_FPSEG2_MASK	GENMASK(2, 0)
 
 /* FLEXCAN interrupt flag register (IFLAG) bits */
 /* Errata ERR005829 step7: Reserve first valid MB */
@@ -161,6 +192,9 @@
 #define FLEXCAN_MB_CODE_TX_DATA		(0xc << 24)
 #define FLEXCAN_MB_CODE_TX_TANSWER	(0xe << 24)
 
+#define FLEXCAN_MB_CNT_EDL		BIT(31)
+#define FLEXCAN_MB_CNT_BRS		BIT(30)
+#define FLEXCAN_MB_CNT_ESI		BIT(29)
 #define FLEXCAN_MB_CNT_SRR		BIT(22)
 #define FLEXCAN_MB_CNT_IDE		BIT(21)
 #define FLEXCAN_MB_CNT_RTR		BIT(20)
@@ -172,26 +206,42 @@
 /* FLEXCAN hardware feature flags
  *
  * Below is some version info we got:
- *    SOC   Version   IP-Version  Glitch- [TR]WRN_INT IRQ Err Memory err RTR re-
- *                                Filter? connected?  Passive detection  ception in MB
- *   MX25  FlexCAN2  03.00.00.00     no        no        no       no        no
- *   MX28  FlexCAN2  03.00.04.00    yes       yes        no       no        no
- *   MX35  FlexCAN2  03.00.00.00     no        no        no       no        no
- *   MX53  FlexCAN2  03.00.00.00    yes        no        no       no        no
- *   MX6s  FlexCAN3  10.00.12.00    yes       yes        no       no       yes
- *   VF610 FlexCAN3  ?               no       yes        no      yes       yes?
- * LS1021A FlexCAN2  03.00.04.00     no       yes        no       no       yes
+ *    SOC   Version   IP-Version  Glitch- [TR]WRN_INT IRQ Err Memory err RTR rece-   FD Mode
+ *                                Filter? connected?  Passive detection  ption in MB Supported?
+ *   MX25  FlexCAN2  03.00.00.00     no        no        no       no        no           no
+ *   MX28  FlexCAN2  03.00.04.00    yes       yes        no       no        no           no
+ *   MX35  FlexCAN2  03.00.00.00     no        no        no       no        no           no
+ *   MX53  FlexCAN2  03.00.00.00    yes        no        no       no        no           no
+ *   MX6s  FlexCAN3  10.00.12.00    yes       yes        no       no       yes           no
+ *   MX8QM FlexCAN3  03.00.23.00    yes       yes        no       no       yes          yes
+ *   MX8MP FlexCAN3  03.00.17.01    yes       yes        no      yes       yes          yes
+ *   VF610 FlexCAN3  ?               no       yes        no      yes       yes?          no
+ * LS1021A FlexCAN2  03.00.04.00     no       yes        no       no       yes           no
+ * LX2160A FlexCAN3  03.00.23.00     no       yes        no       no       yes          yes
  *
  * Some SOCs do not have the RX_WARN & TX_WARN interrupt line connected.
  */
-#define FLEXCAN_QUIRK_BROKEN_WERR_STATE	BIT(1) /* [TR]WRN_INT not connected */
-#define FLEXCAN_QUIRK_DISABLE_RXFG	BIT(2) /* Disable RX FIFO Global mask */
-#define FLEXCAN_QUIRK_ENABLE_EACEN_RRS	BIT(3) /* Enable EACEN and RRS bit in ctrl2 */
-#define FLEXCAN_QUIRK_DISABLE_MECR	BIT(4) /* Disable Memory error detection */
-#define FLEXCAN_QUIRK_USE_OFF_TIMESTAMP	BIT(5) /* Use timestamp based offloading */
-#define FLEXCAN_QUIRK_BROKEN_PERR_STATE	BIT(6) /* No interrupt for error passive */
-#define FLEXCAN_QUIRK_DEFAULT_BIG_ENDIAN	BIT(7) /* default to BE register access */
-#define FLEXCAN_QUIRK_SETUP_STOP_MODE		BIT(8) /* Setup stop mode to support wakeup */
+
+/* [TR]WRN_INT not connected */
+#define FLEXCAN_QUIRK_BROKEN_WERR_STATE BIT(1)
+ /* Disable RX FIFO Global mask */
+#define FLEXCAN_QUIRK_DISABLE_RXFG BIT(2)
+/* Enable EACEN and RRS bit in ctrl2 */
+#define FLEXCAN_QUIRK_ENABLE_EACEN_RRS  BIT(3)
+/* Disable non-correctable errors interrupt and freeze mode */
+#define FLEXCAN_QUIRK_DISABLE_MECR BIT(4)
+/* Use timestamp based offloading */
+#define FLEXCAN_QUIRK_USE_OFF_TIMESTAMP BIT(5)
+/* No interrupt for error passive */
+#define FLEXCAN_QUIRK_BROKEN_PERR_STATE BIT(6)
+/* default to BE register access */
+#define FLEXCAN_QUIRK_DEFAULT_BIG_ENDIAN BIT(7)
+/* Setup stop mode to support wakeup */
+#define FLEXCAN_QUIRK_SETUP_STOP_MODE BIT(8)
+/* Support CAN-FD mode */
+#define FLEXCAN_QUIRK_SUPPORT_FD BIT(9)
+/* support memory detection and correction */
+#define FLEXCAN_QUIRK_SUPPORT_ECC BIT(10)
 
 /* Structure of the message buffer */
 struct flexcan_mb {
@@ -203,12 +253,12 @@ struct flexcan_mb {
 /* Structure of the hardware registers */
 struct flexcan_regs {
 	u32 mcr;		/* 0x00 */
-	u32 ctrl;		/* 0x04 */
+	u32 ctrl;		/* 0x04 - Not affected by Soft Reset */
 	u32 timer;		/* 0x08 */
-	u32 _reserved1;		/* 0x0c */
-	u32 rxgmask;		/* 0x10 */
-	u32 rx14mask;		/* 0x14 */
-	u32 rx15mask;		/* 0x18 */
+	u32 tcr;		/* 0x0c */
+	u32 rxgmask;		/* 0x10 - Not affected by Soft Reset */
+	u32 rx14mask;		/* 0x14 - Not affected by Soft Reset */
+	u32 rx15mask;		/* 0x18 - Not affected by Soft Reset */
 	u32 ecr;		/* 0x1c */
 	u32 esr;		/* 0x20 */
 	u32 imask2;		/* 0x24 */
@@ -217,16 +267,20 @@ struct flexcan_regs {
 	u32 iflag1;		/* 0x30 */
 	union {			/* 0x34 */
 		u32 gfwr_mx28;	/* MX28, MX53 */
-		u32 ctrl2;	/* MX6, VF610 */
+		u32 ctrl2;	/* MX6, VF610 - Not affected by Soft Reset */
 	};
 	u32 esr2;		/* 0x38 */
 	u32 imeur;		/* 0x3c */
 	u32 lrfr;		/* 0x40 */
 	u32 crcr;		/* 0x44 */
 	u32 rxfgmask;		/* 0x48 */
-	u32 rxfir;		/* 0x4c */
-	u32 _reserved3[12];	/* 0x50 */
-	u8 mb[2][512];		/* 0x80 */
+	u32 rxfir;		/* 0x4c - Not affected by Soft Reset */
+	u32 cbt;		/* 0x50 - Not affected by Soft Reset */
+	u32 _reserved2;		/* 0x54 */
+	u32 dbg1;		/* 0x58 */
+	u32 dbg2;		/* 0x5c */
+	u32 _reserved3[8];	/* 0x60 */
+	u8 mb[2][512];		/* 0x80 - Not affected by Soft Reset */
 	/* FIFO-mode:
 	 *			MB
 	 * 0x080...0x08f	0	RX message buffer
@@ -238,10 +292,19 @@ struct flexcan_regs {
 	 *				(mx6, vf610)
 	 */
 	u32 _reserved4[256];	/* 0x480 */
-	u32 rximr[64];		/* 0x880 */
+	u32 rximr[64];		/* 0x880 - Not affected by Soft Reset */
 	u32 _reserved5[24];	/* 0x980 */
 	u32 gfwr_mx6;		/* 0x9e0 - MX6 */
-	u32 _reserved6[63];	/* 0x9e4 */
+	u32 _reserved6[39];	/* 0x9e4 */
+	u32 _rxfir[6];		/* 0xa80 */
+	u32 _reserved8[2];	/* 0xa98 */
+	u32 _rxmgmask;		/* 0xaa0 */
+	u32 _rxfgmask;		/* 0xaa4 */
+	u32 _rx14mask;		/* 0xaa8 */
+	u32 _rx15mask;		/* 0xaac */
+	u32 tx_smb[4];		/* 0xab0 */
+	u32 rx_smb0[4];		/* 0xac0 */
+	u32 rx_smb1[4];		/* 0xad0 */
 	u32 mecr;		/* 0xae0 */
 	u32 erriar;		/* 0xae4 */
 	u32 erridpr;		/* 0xae8 */
@@ -250,8 +313,18 @@ struct flexcan_regs {
 	u32 rerrdr;		/* 0xaf4 */
 	u32 rerrsynr;		/* 0xaf8 */
 	u32 errsr;		/* 0xafc */
+	u32 _reserved7[64];	/* 0xb00 */
+	u32 fdctrl;		/* 0xc00 - Not affected by Soft Reset */
+	u32 fdcbt;		/* 0xc04 - Not affected by Soft Reset */
+	u32 fdcrc;		/* 0xc08 */
+	u32 _reserved9[199];	/* 0xc0c */
+	u32 tx_smb_fd[18];	/* 0xf28 */
+	u32 rx_smb0_fd[18];	/* 0xf70 */
+	u32 rx_smb1_fd[18];	/* 0xfb8 */
 };
 
+static_assert(sizeof(struct flexcan_regs) ==  0x4 * 18 + 0xfb8);
+
 struct flexcan_devtype_data {
 	u32 quirks;		/* quirks needed for different IP cores */
 };
@@ -313,6 +386,19 @@ static const struct flexcan_devtype_data fsl_imx6q_devtype_data = {
 		FLEXCAN_QUIRK_SETUP_STOP_MODE,
 };
 
+static const struct flexcan_devtype_data fsl_imx8qm_devtype_data = {
+	.quirks = FLEXCAN_QUIRK_DISABLE_RXFG | FLEXCAN_QUIRK_ENABLE_EACEN_RRS |
+		FLEXCAN_QUIRK_USE_OFF_TIMESTAMP | FLEXCAN_QUIRK_BROKEN_PERR_STATE |
+		FLEXCAN_QUIRK_SUPPORT_FD,
+};
+
+static struct flexcan_devtype_data fsl_imx8mp_devtype_data = {
+	.quirks = FLEXCAN_QUIRK_DISABLE_RXFG | FLEXCAN_QUIRK_ENABLE_EACEN_RRS |
+		FLEXCAN_QUIRK_DISABLE_MECR | FLEXCAN_QUIRK_USE_OFF_TIMESTAMP |
+		FLEXCAN_QUIRK_BROKEN_PERR_STATE | FLEXCAN_QUIRK_SETUP_STOP_MODE |
+		FLEXCAN_QUIRK_SUPPORT_FD | FLEXCAN_QUIRK_SUPPORT_ECC,
+};
+
 static const struct flexcan_devtype_data fsl_vf610_devtype_data = {
 	.quirks = FLEXCAN_QUIRK_DISABLE_RXFG | FLEXCAN_QUIRK_ENABLE_EACEN_RRS |
 		FLEXCAN_QUIRK_DISABLE_MECR | FLEXCAN_QUIRK_USE_OFF_TIMESTAMP |
@@ -325,6 +411,12 @@ static const struct flexcan_devtype_data fsl_ls1021a_r2_devtype_data = {
 		FLEXCAN_QUIRK_USE_OFF_TIMESTAMP,
 };
 
+static const struct flexcan_devtype_data fsl_lx2160a_r1_devtype_data = {
+	.quirks = FLEXCAN_QUIRK_DISABLE_RXFG | FLEXCAN_QUIRK_ENABLE_EACEN_RRS |
+		FLEXCAN_QUIRK_DISABLE_MECR | FLEXCAN_QUIRK_BROKEN_PERR_STATE |
+		FLEXCAN_QUIRK_USE_OFF_TIMESTAMP | FLEXCAN_QUIRK_SUPPORT_FD,
+};
+
 static const struct can_bittiming_const flexcan_bittiming_const = {
 	.name = DRV_NAME,
 	.tseg1_min = 4,
@@ -337,6 +429,30 @@ static const struct can_bittiming_const flexcan_bittiming_const = {
 	.brp_inc = 1,
 };
 
+static const struct can_bittiming_const flexcan_fd_bittiming_const = {
+	.name = DRV_NAME,
+	.tseg1_min = 2,
+	.tseg1_max = 96,
+	.tseg2_min = 2,
+	.tseg2_max = 32,
+	.sjw_max = 16,
+	.brp_min = 1,
+	.brp_max = 1024,
+	.brp_inc = 1,
+};
+
+static const struct can_bittiming_const flexcan_fd_data_bittiming_const = {
+	.name = DRV_NAME,
+	.tseg1_min = 2,
+	.tseg1_max = 39,
+	.tseg2_min = 2,
+	.tseg2_max = 8,
+	.sjw_max = 4,
+	.brp_min = 1,
+	.brp_max = 1024,
+	.brp_inc = 1,
+};
+
 /* FlexCAN module is essentially modelled as a little-endian IP in most
  * SoCs, i.e the registers as well as the message buffer areas are
  * implemented in a little-endian fashion.
@@ -457,7 +573,6 @@ static inline int flexcan_exit_stop_mode(struct flexcan_priv *priv)
 	regmap_update_bits(priv->stm.gpr, priv->stm.req_gpr,
 			   1 << priv->stm.req_bit, 0);
 
-
 	reg_mcr = priv->read(&regs->mcr);
 	reg_mcr &= ~FLEXCAN_MCR_SLF_WAK;
 	priv->write(reg_mcr, &regs->mcr);
@@ -628,10 +743,10 @@ static int flexcan_get_berr_counter(const struct net_device *dev,
 static netdev_tx_t flexcan_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	const struct flexcan_priv *priv = netdev_priv(dev);
-	struct can_frame *cf = (struct can_frame *)skb->data;
+	struct canfd_frame *cfd = (struct canfd_frame *)skb->data;
 	u32 can_id;
 	u32 data;
-	u32 ctrl = FLEXCAN_MB_CODE_TX_DATA | (cf->can_dlc << 16);
+	u32 ctrl = FLEXCAN_MB_CODE_TX_DATA | ((can_len2dlc(cfd->len)) << 16);
 	int i;
 
 	if (can_dropped_invalid_skb(dev, skb))
@@ -639,18 +754,25 @@ static netdev_tx_t flexcan_start_xmit(struct sk_buff *skb, struct net_device *de
 
 	netif_stop_queue(dev);
 
-	if (cf->can_id & CAN_EFF_FLAG) {
-		can_id = cf->can_id & CAN_EFF_MASK;
+	if (cfd->can_id & CAN_EFF_FLAG) {
+		can_id = cfd->can_id & CAN_EFF_MASK;
 		ctrl |= FLEXCAN_MB_CNT_IDE | FLEXCAN_MB_CNT_SRR;
 	} else {
-		can_id = (cf->can_id & CAN_SFF_MASK) << 18;
+		can_id = (cfd->can_id & CAN_SFF_MASK) << 18;
 	}
 
-	if (cf->can_id & CAN_RTR_FLAG)
+	if (cfd->can_id & CAN_RTR_FLAG)
 		ctrl |= FLEXCAN_MB_CNT_RTR;
 
-	for (i = 0; i < cf->can_dlc; i += sizeof(u32)) {
-		data = be32_to_cpup((__be32 *)&cf->data[i]);
+	if (can_is_canfd_skb(skb)) {
+		ctrl |= FLEXCAN_MB_CNT_EDL;
+
+		if (cfd->flags & CANFD_BRS)
+			ctrl |= FLEXCAN_MB_CNT_BRS;
+	}
+
+	for (i = 0; i < cfd->len; i += sizeof(u32)) {
+		data = be32_to_cpup((__be32 *)&cfd->data[i]);
 		priv->write(data, &priv->tx_mb->data[i / sizeof(u32)]);
 	}
 
@@ -822,7 +944,7 @@ static struct sk_buff *flexcan_mailbox_read(struct can_rx_offload *offload,
 	struct flexcan_regs __iomem *regs = priv->regs;
 	struct flexcan_mb __iomem *mb;
 	struct sk_buff *skb;
-	struct can_frame *cf;
+	struct canfd_frame *cfd;
 	u32 reg_ctrl, reg_id, reg_iflag1;
 	int i;
 
@@ -859,8 +981,11 @@ static struct sk_buff *flexcan_mailbox_read(struct can_rx_offload *offload,
 		reg_ctrl = priv->read(&mb->can_ctrl);
 	}
 
-	skb = alloc_can_skb(offload->dev, &cf);
-	if (!skb) {
+	if (reg_ctrl & FLEXCAN_MB_CNT_EDL)
+		skb = alloc_canfd_skb(offload->dev, &cfd);
+	else
+		skb = alloc_can_skb(offload->dev, (struct can_frame **)&cfd);
+	if (unlikely(!skb)) {
 		skb = ERR_PTR(-ENOMEM);
 		goto mark_as_read;
 	}
@@ -870,17 +995,28 @@ static struct sk_buff *flexcan_mailbox_read(struct can_rx_offload *offload,
 
 	reg_id = priv->read(&mb->can_id);
 	if (reg_ctrl & FLEXCAN_MB_CNT_IDE)
-		cf->can_id = ((reg_id >> 0) & CAN_EFF_MASK) | CAN_EFF_FLAG;
+		cfd->can_id = ((reg_id >> 0) & CAN_EFF_MASK) | CAN_EFF_FLAG;
 	else
-		cf->can_id = (reg_id >> 18) & CAN_SFF_MASK;
+		cfd->can_id = (reg_id >> 18) & CAN_SFF_MASK;
+
+	if (reg_ctrl & FLEXCAN_MB_CNT_EDL) {
+		cfd->len = can_dlc2len(get_canfd_dlc((reg_ctrl >> 16) & 0xf));
+
+		if (reg_ctrl & FLEXCAN_MB_CNT_BRS)
+			cfd->flags |= CANFD_BRS;
+	} else {
+		cfd->len = get_can_dlc((reg_ctrl >> 16) & 0xf);
+
+		if (reg_ctrl & FLEXCAN_MB_CNT_RTR)
+			cfd->can_id |= CAN_RTR_FLAG;
+	}
 
-	if (reg_ctrl & FLEXCAN_MB_CNT_RTR)
-		cf->can_id |= CAN_RTR_FLAG;
-	cf->can_dlc = get_can_dlc((reg_ctrl >> 16) & 0xf);
+	if (reg_ctrl & FLEXCAN_MB_CNT_ESI)
+		cfd->flags |= CANFD_ESI;
 
-	for (i = 0; i < cf->can_dlc; i += sizeof(u32)) {
+	for (i = 0; i < cfd->len; i += sizeof(u32)) {
 		__be32 data = cpu_to_be32(priv->read(&mb->data[i / sizeof(u32)]));
-		*(__be32 *)(cf->data + i) = data;
+		*(__be32 *)(cfd->data + i) = data;
 	}
 
  mark_as_read:
@@ -961,10 +1097,10 @@ static irqreturn_t flexcan_irq(int irq, void *dev_id)
 
 	reg_esr = priv->read(&regs->esr);
 
-	/* ACK all bus error and state change IRQ sources */
-	if (reg_esr & FLEXCAN_ESR_ALL_INT) {
+	/* ACK all bus error, state change and wake IRQ sources */
+	if (reg_esr & (FLEXCAN_ESR_ALL_INT | FLEXCAN_ESR_WAK_INT)) {
 		handled = IRQ_HANDLED;
-		priv->write(reg_esr & FLEXCAN_ESR_ALL_INT, &regs->esr);
+		priv->write(reg_esr & (FLEXCAN_ESR_ALL_INT | FLEXCAN_ESR_WAK_INT), &regs->esr);
 	}
 
 	/* state change interrupt or broken error state quirk fix is enabled */
@@ -1019,7 +1155,7 @@ static irqreturn_t flexcan_irq(int irq, void *dev_id)
 	return handled;
 }
 
-static void flexcan_set_bittiming(struct net_device *dev)
+static void flexcan_set_bittiming_ctrl(const struct net_device *dev)
 {
 	const struct flexcan_priv *priv = netdev_priv(dev);
 	const struct can_bittiming *bt = &priv->can.bittiming;
@@ -1031,10 +1167,7 @@ static void flexcan_set_bittiming(struct net_device *dev)
 		 FLEXCAN_CTRL_RJW(0x3) |
 		 FLEXCAN_CTRL_PSEG1(0x7) |
 		 FLEXCAN_CTRL_PSEG2(0x7) |
-		 FLEXCAN_CTRL_PROPSEG(0x7) |
-		 FLEXCAN_CTRL_LPB |
-		 FLEXCAN_CTRL_SMP |
-		 FLEXCAN_CTRL_LOM);
+		 FLEXCAN_CTRL_PROPSEG(0x7));
 
 	reg |= FLEXCAN_CTRL_PRESDIV(bt->brp - 1) |
 		FLEXCAN_CTRL_PSEG1(bt->phase_seg1 - 1) |
@@ -1042,6 +1175,130 @@ static void flexcan_set_bittiming(struct net_device *dev)
 		FLEXCAN_CTRL_RJW(bt->sjw - 1) |
 		FLEXCAN_CTRL_PROPSEG(bt->prop_seg - 1);
 
+	netdev_dbg(dev, "writing ctrl=0x%08x\n", reg);
+	priv->write(reg, &regs->ctrl);
+
+	/* print chip status */
+	netdev_dbg(dev, "%s: mcr=0x%08x ctrl=0x%08x\n", __func__,
+		   priv->read(&regs->mcr), priv->read(&regs->ctrl));
+}
+
+static void flexcan_set_bittiming_cbt(const struct net_device *dev)
+{
+	struct flexcan_priv *priv = netdev_priv(dev);
+	struct can_bittiming *bt = &priv->can.bittiming;
+	struct can_bittiming *dbt = &priv->can.data_bittiming;
+	struct flexcan_regs __iomem *regs = priv->regs;
+	u32 reg_cbt, reg_fdctrl;
+
+	/* CBT */
+	/* CBT[EPSEG1] is 5 bit long and CBT[EPROPSEG] is 6 bit
+	 * long. The can_calc_bittiming() tries to divide the tseg1
+	 * equally between phase_seg1 and prop_seg, which may not fit
+	 * in CBT register. Therefore, if phase_seg1 is more than
+	 * possible value, increase prop_seg and decrease phase_seg1.
+	 */
+	if (bt->phase_seg1 > 0x20) {
+		bt->prop_seg += (bt->phase_seg1 - 0x20);
+		bt->phase_seg1 = 0x20;
+	}
+
+	reg_cbt = FLEXCAN_CBT_BTF |
+		FIELD_PREP(FLEXCAN_CBT_EPRESDIV_MASK, bt->brp - 1) |
+		FIELD_PREP(FLEXCAN_CBT_ERJW_MASK, bt->sjw - 1) |
+		FIELD_PREP(FLEXCAN_CBT_EPROPSEG_MASK, bt->prop_seg - 1) |
+		FIELD_PREP(FLEXCAN_CBT_EPSEG1_MASK, bt->phase_seg1 - 1) |
+		FIELD_PREP(FLEXCAN_CBT_EPSEG2_MASK, bt->phase_seg2 - 1);
+
+	netdev_dbg(dev, "writing cbt=0x%08x\n", reg_cbt);
+	priv->write(reg_cbt, &regs->cbt);
+
+	if (priv->can.ctrlmode & CAN_CTRLMODE_FD) {
+		u32 reg_fdcbt, reg_ctrl2;
+
+		if (bt->brp != dbt->brp)
+			netdev_warn(dev, "Data brp=%d and brp=%d don't match, this may result in a phase error. Consider using different bitrate and/or data bitrate.\n",
+				    dbt->brp, bt->brp);
+
+		/* FDCBT */
+		/* FDCBT[FPSEG1] is 3 bit long and FDCBT[FPROPSEG] is
+		 * 5 bit long. The can_calc_bittiming tries to divide
+		 * the tseg1 equally between phase_seg1 and prop_seg,
+		 * which may not fit in FDCBT register. Therefore, if
+		 * phase_seg1 is more than possible value, increase
+		 * prop_seg and decrease phase_seg1
+		 */
+		if (dbt->phase_seg1 > 0x8) {
+			dbt->prop_seg += (dbt->phase_seg1 - 0x8);
+			dbt->phase_seg1 = 0x8;
+		}
+
+		reg_fdcbt = priv->read(&regs->fdcbt);
+		reg_fdcbt &= ~(FIELD_PREP(FLEXCAN_FDCBT_FPRESDIV_MASK, 0x3ff) |
+			       FIELD_PREP(FLEXCAN_FDCBT_FRJW_MASK, 0x7) |
+			       FIELD_PREP(FLEXCAN_FDCBT_FPROPSEG_MASK, 0x1f) |
+			       FIELD_PREP(FLEXCAN_FDCBT_FPSEG1_MASK, 0x7) |
+			       FIELD_PREP(FLEXCAN_FDCBT_FPSEG2_MASK, 0x7));
+
+		reg_fdcbt |= FIELD_PREP(FLEXCAN_FDCBT_FPRESDIV_MASK, dbt->brp - 1) |
+			FIELD_PREP(FLEXCAN_FDCBT_FRJW_MASK, dbt->sjw - 1) |
+			FIELD_PREP(FLEXCAN_FDCBT_FPROPSEG_MASK, dbt->prop_seg) |
+			FIELD_PREP(FLEXCAN_FDCBT_FPSEG1_MASK, dbt->phase_seg1 - 1) |
+			FIELD_PREP(FLEXCAN_FDCBT_FPSEG2_MASK, dbt->phase_seg2 - 1);
+
+		netdev_dbg(dev, "writing fdcbt=0x%08x\n", reg_fdcbt);
+		priv->write(reg_fdcbt, &regs->fdcbt);
+
+		/* CTRL2 */
+		reg_ctrl2 = priv->read(&regs->ctrl2);
+		reg_ctrl2 &= ~FLEXCAN_CTRL2_ISOCANFDEN;
+		if (!(priv->can.ctrlmode & CAN_CTRLMODE_FD_NON_ISO))
+			reg_ctrl2 |= FLEXCAN_CTRL2_ISOCANFDEN;
+
+		netdev_dbg(dev, "writing ctrl2=0x%08x\n", reg_ctrl2);
+		priv->write(reg_ctrl2, &regs->ctrl2);
+	}
+
+	/* FDCTRL */
+	reg_fdctrl = priv->read(&regs->fdctrl);
+	reg_fdctrl &= ~(FLEXCAN_FDCTRL_FDRATE |
+			FIELD_PREP(FLEXCAN_FDCTRL_TDCOFF, 0x1f));
+
+	if (priv->can.ctrlmode & CAN_CTRLMODE_FD) {
+		reg_fdctrl |= FLEXCAN_FDCTRL_FDRATE;
+
+		if (priv->can.ctrlmode & CAN_CTRLMODE_LOOPBACK) {
+			/* TDC must be disabled for Loop Back mode */
+			reg_fdctrl &= ~FLEXCAN_FDCTRL_TDCEN;
+		} else {
+			reg_fdctrl |= FLEXCAN_FDCTRL_TDCEN |
+				FIELD_PREP(FLEXCAN_FDCTRL_TDCOFF,
+					   ((dbt->phase_seg1 - 1) +
+					    dbt->prop_seg + 2) *
+					   ((dbt->brp - 1 ) + 1));
+		}
+	}
+
+	netdev_dbg(dev, "writing fdctrl=0x%08x\n", reg_fdctrl);
+	priv->write(reg_fdctrl, &regs->fdctrl);
+
+	netdev_dbg(dev, "%s: mcr=0x%08x ctrl=0x%08x ctrl2=0x%08x fdctrl=0x%08x cbt=0x%08x fdcbt=0x%08x\n",
+		   __func__,
+		   priv->read(&regs->mcr), priv->read(&regs->ctrl),
+		   priv->read(&regs->ctrl2), priv->read(&regs->fdctrl),
+		   priv->read(&regs->cbt), priv->read(&regs->fdcbt));
+}
+
+static void flexcan_set_bittiming(struct net_device *dev)
+{
+	const struct flexcan_priv *priv = netdev_priv(dev);
+	struct flexcan_regs __iomem *regs = priv->regs;
+	u32 reg;
+
+	reg = priv->read(&regs->ctrl);
+	reg &= ~(FLEXCAN_CTRL_LPB | FLEXCAN_CTRL_SMP |
+		 FLEXCAN_CTRL_LOM);
+
 	if (priv->can.ctrlmode & CAN_CTRLMODE_LOOPBACK)
 		reg |= FLEXCAN_CTRL_LPB;
 	if (priv->can.ctrlmode & CAN_CTRLMODE_LISTENONLY)
@@ -1052,9 +1309,41 @@ static void flexcan_set_bittiming(struct net_device *dev)
 	netdev_dbg(dev, "writing ctrl=0x%08x\n", reg);
 	priv->write(reg, &regs->ctrl);
 
-	/* print chip status */
-	netdev_dbg(dev, "%s: mcr=0x%08x ctrl=0x%08x\n", __func__,
-		   priv->read(&regs->mcr), priv->read(&regs->ctrl));
+	if (priv->can.ctrlmode_supported & CAN_CTRLMODE_FD)
+		return flexcan_set_bittiming_cbt(dev);
+	else
+		return flexcan_set_bittiming_ctrl(dev);
+}
+
+static void flexcan_ram_init(struct net_device *dev)
+{
+	struct flexcan_priv *priv = netdev_priv(dev);
+	struct flexcan_regs __iomem *regs = priv->regs;
+	u32 reg_ctrl2;
+
+	/* 11.8.3.13 Detection and correction of memory errors:
+	 * CTRL2[WRMFRZ] grants write access to all memory positions
+	 * that require initialization, ranging from 0x080 to 0xADF
+	 * and from 0xF28 to 0xFFF when the CAN FD feature is enabled.
+	 * The RXMGMASK, RX14MASK, RX15MASK, and RXFGMASK registers
+	 * need to be initialized as well. MCR[RFEN] must not be set
+	 * during memory initialization.
+	 */
+	reg_ctrl2 = priv->read(&regs->ctrl2);
+	reg_ctrl2 |= FLEXCAN_CTRL2_WRMFRZ;
+	priv->write(reg_ctrl2, &regs->ctrl2);
+
+	memset_io(&regs->mb[0][0], 0,
+		  offsetof(struct flexcan_regs, rx_smb1[3]) -
+		  offsetof(struct flexcan_regs, mb[0][0]) + 0x4);
+
+	if (priv->can.ctrlmode & CAN_CTRLMODE_FD)
+		memset_io(&regs->tx_smb_fd[0], 0,
+			  offsetof(struct flexcan_regs, rx_smb1_fd[17]) -
+			  offsetof(struct flexcan_regs, tx_smb_fd[0]) + 0x4);
+
+	reg_ctrl2 &= ~FLEXCAN_CTRL2_WRMFRZ;
+	priv->write(reg_ctrl2, &regs->ctrl2);
 }
 
 /* flexcan_chip_start
@@ -1081,6 +1370,9 @@ static int flexcan_chip_start(struct net_device *dev)
 	if (err)
 		goto out_chip_disable;
 
+	if (priv->devtype_data->quirks & FLEXCAN_QUIRK_SUPPORT_ECC)
+		flexcan_ram_init(dev);
+
 	flexcan_set_bittiming(dev);
 
 	/* MCR
@@ -1127,6 +1419,12 @@ static int flexcan_chip_start(struct net_device *dev)
 	else
 		reg_mcr |= FLEXCAN_MCR_SRX_DIS;
 
+	/* MCR - CAN-FD */
+	if (priv->can.ctrlmode & CAN_CTRLMODE_FD)
+		reg_mcr |= FLEXCAN_MCR_FDEN;
+	else
+		reg_mcr &= ~FLEXCAN_MCR_FDEN;
+
 	netdev_dbg(dev, "%s: writing mcr=0x%08x", __func__, reg_mcr);
 	priv->write(reg_mcr, &regs->mcr);
 
@@ -1169,6 +1467,32 @@ static int flexcan_chip_start(struct net_device *dev)
 		priv->write(reg_ctrl2, &regs->ctrl2);
 	}
 
+	if (priv->can.ctrlmode_supported & CAN_CTRLMODE_FD) {
+		u32 reg_fdctrl;
+
+		reg_fdctrl = priv->read(&regs->fdctrl);
+		reg_fdctrl &= ~(FIELD_PREP(FLEXCAN_FDCTRL_MBDSR1, 0x3) |
+				FIELD_PREP(FLEXCAN_FDCTRL_MBDSR0, 0x3));
+
+		if (priv->can.ctrlmode & CAN_CTRLMODE_FD) {
+			reg_fdctrl |=
+				FIELD_PREP(FLEXCAN_FDCTRL_MBDSR1,
+					   FLEXCAN_FDCTRL_MBDSR_64) |
+				FIELD_PREP(FLEXCAN_FDCTRL_MBDSR0,
+					   FLEXCAN_FDCTRL_MBDSR_64);
+		} else {
+			reg_fdctrl |=
+				FIELD_PREP(FLEXCAN_FDCTRL_MBDSR1,
+					   FLEXCAN_FDCTRL_MBDSR_8) |
+				FIELD_PREP(FLEXCAN_FDCTRL_MBDSR0,
+					   FLEXCAN_FDCTRL_MBDSR_8);
+		}
+
+		netdev_dbg(dev, "%s: writing fdctrl=0x%08x",
+			   __func__, reg_fdctrl);
+		priv->write(reg_fdctrl, &regs->fdctrl);
+	}
+
 	if (priv->devtype_data->quirks & FLEXCAN_QUIRK_USE_OFF_TIMESTAMP) {
 		for (i = priv->offload.mb_first; i <= priv->offload.mb_last; i++) {
 			mb = flexcan_get_mb(priv, i);
@@ -1204,28 +1528,43 @@ static int flexcan_chip_start(struct net_device *dev)
 	for (i = 0; i < priv->mb_count; i++)
 		priv->write(0, &regs->rximr[i]);
 
-	/* On Vybrid, disable memory error detection interrupts
-	 * and freeze mode.
-	 * This also works around errata e5295 which generates
-	 * false positive memory errors and put the device in
-	 * freeze mode.
+	/* On Vybrid, disable non-correctable errors interrupt and
+	 * freeze mode. It still can correct the correctable errors
+	 * when HW supports ECC.
+	 *
+	 * This also works around errata e5295 which generates false
+	 * positive memory errors and put the device in freeze mode.
 	 */
 	if (priv->devtype_data->quirks & FLEXCAN_QUIRK_DISABLE_MECR) {
 		/* Follow the protocol as described in "Detection
 		 * and Correction of Memory Errors" to write to
-		 * MECR register
+		 * MECR register (step 1 - 5)
+		 *
+		 * 1. By default, CTRL2[ECRWRE] = 0, MECR[ECRWRDIS] = 1
+		 * 2. set CTRL2[ECRWRE]
 		 */
 		reg_ctrl2 = priv->read(&regs->ctrl2);
 		reg_ctrl2 |= FLEXCAN_CTRL2_ECRWRE;
 		priv->write(reg_ctrl2, &regs->ctrl2);
 
+		/* 3. clear MECR[ECRWRDIS] */
 		reg_mecr = priv->read(&regs->mecr);
 		reg_mecr &= ~FLEXCAN_MECR_ECRWRDIS;
 		priv->write(reg_mecr, &regs->mecr);
-		reg_mecr |= FLEXCAN_MECR_ECCDIS;
+
+		/* 4. all writes to MECR must keep MECR[ECRWRDIS] cleared */
 		reg_mecr &= ~(FLEXCAN_MECR_NCEFAFRZ | FLEXCAN_MECR_HANCEI_MSK |
 			      FLEXCAN_MECR_FANCEI_MSK);
 		priv->write(reg_mecr, &regs->mecr);
+
+		/* 5. after configuration done, lock MECR by either
+		 * setting MECR[ECRWRDIS] or clearing CTRL2[ECRWRE]
+		 */
+		reg_mecr |= FLEXCAN_MECR_ECRWRDIS;
+		priv->write(reg_mecr, &regs->mecr);
+
+		reg_ctrl2 &= ~FLEXCAN_CTRL2_ECRWRE;
+		priv->write(reg_ctrl2, &regs->ctrl2);
 	}
 
 	err = flexcan_transceiver_enable(priv);
@@ -1260,18 +1599,23 @@ static int flexcan_chip_start(struct net_device *dev)
 	return err;
 }
 
-/* flexcan_chip_stop
+/* __flexcan_chip_stop
  *
- * this functions is entered with clocks enabled
+ * this function is entered with clocks enabled
  */
-static void flexcan_chip_stop(struct net_device *dev)
+static int __flexcan_chip_stop(struct net_device *dev, bool disable_on_error)
 {
 	struct flexcan_priv *priv = netdev_priv(dev);
 	struct flexcan_regs __iomem *regs = priv->regs;
+	int err;
 
 	/* freeze + disable module */
-	flexcan_chip_freeze(priv);
-	flexcan_chip_disable(priv);
+	err = flexcan_chip_freeze(priv);
+	if (err && !disable_on_error)
+		return err;
+	err = flexcan_chip_disable(priv);
+	if (err && !disable_on_error)
+		goto out_chip_unfreeze;
 
 	/* Disable all interrupts */
 	priv->write(0, &regs->imask2);
@@ -1281,6 +1625,23 @@ static void flexcan_chip_stop(struct net_device *dev)
 
 	flexcan_transceiver_disable(priv);
 	priv->can.state = CAN_STATE_STOPPED;
+
+	return 0;
+
+ out_chip_unfreeze:
+	flexcan_chip_unfreeze(priv);
+
+	return err;
+}
+
+static inline int flexcan_chip_stop_disable_on_error(struct net_device *dev)
+{
+	return __flexcan_chip_stop(dev, true);
+}
+
+static inline int flexcan_chip_stop(struct net_device *dev)
+{
+	return __flexcan_chip_stop(dev, false);
 }
 
 static int flexcan_open(struct net_device *dev)
@@ -1288,6 +1649,12 @@ static int flexcan_open(struct net_device *dev)
 	struct flexcan_priv *priv = netdev_priv(dev);
 	int err;
 
+	if ((priv->can.ctrlmode & CAN_CTRLMODE_3_SAMPLES) &&
+	    (priv->can.ctrlmode & CAN_CTRLMODE_FD)) {
+		netdev_err(dev, "Three Samples mode and CAN-FD mode can't be used together\n");
+		return -EINVAL;
+	}
+
 	err = pm_runtime_get_sync(priv->dev);
 	if (err < 0)
 		return err;
@@ -1300,7 +1667,10 @@ static int flexcan_open(struct net_device *dev)
 	if (err)
 		goto out_close;
 
-	priv->mb_size = sizeof(struct flexcan_mb) + CAN_MAX_DLEN;
+	if (priv->can.ctrlmode & CAN_CTRLMODE_FD)
+		priv->mb_size = sizeof(struct flexcan_mb) + CANFD_MAX_DLEN;
+	else
+		priv->mb_size = sizeof(struct flexcan_mb) + CAN_MAX_DLEN;
 	priv->mb_count = (sizeof(priv->regs->mb[0]) / priv->mb_size) +
 			 (sizeof(priv->regs->mb[1]) / priv->mb_size);
 
@@ -1362,7 +1732,7 @@ static int flexcan_close(struct net_device *dev)
 
 	netif_stop_queue(dev);
 	can_rx_offload_disable(&priv->offload);
-	flexcan_chip_stop(dev);
+	flexcan_chip_stop_disable_on_error(dev);
 
 	can_rx_offload_del(&priv->offload);
 	free_irq(dev->irq, dev);
@@ -1531,6 +1901,8 @@ out_put_node:
 }
 
 static const struct of_device_id flexcan_of_match[] = {
+	{ .compatible = "fsl,imx8qm-flexcan", .data = &fsl_imx8qm_devtype_data, },
+	{ .compatible = "fsl,imx8mp-flexcan", .data = &fsl_imx8mp_devtype_data, },
 	{ .compatible = "fsl,imx6q-flexcan", .data = &fsl_imx6q_devtype_data, },
 	{ .compatible = "fsl,imx28-flexcan", .data = &fsl_imx28_devtype_data, },
 	{ .compatible = "fsl,imx53-flexcan", .data = &fsl_imx25_devtype_data, },
@@ -1539,6 +1911,7 @@ static const struct of_device_id flexcan_of_match[] = {
 	{ .compatible = "fsl,p1010-flexcan", .data = &fsl_p1010_devtype_data, },
 	{ .compatible = "fsl,vf610-flexcan", .data = &fsl_vf610_devtype_data, },
 	{ .compatible = "fsl,ls1021ar2-flexcan", .data = &fsl_ls1021a_r2_devtype_data, },
+	{ .compatible = "fsl,lx2160ar1-flexcan", .data = &fsl_lx2160a_r1_devtype_data, },
 	{ /* sentinel */ },
 };
 MODULE_DEVICE_TABLE(of, flexcan_of_match);
@@ -1562,11 +1935,13 @@ static int flexcan_probe(struct platform_device *pdev)
 	u8 clk_src = 1;
 	u32 clock_freq = 0;
 
-	reg_xceiver = devm_regulator_get(&pdev->dev, "xceiver");
+	reg_xceiver = devm_regulator_get_optional(&pdev->dev, "xceiver");
 	if (PTR_ERR(reg_xceiver) == -EPROBE_DEFER)
 		return -EPROBE_DEFER;
-	else if (IS_ERR(reg_xceiver))
+	else if (PTR_ERR(reg_xceiver) == -ENODEV)
 		reg_xceiver = NULL;
+	else if (IS_ERR(reg_xceiver))
+		return PTR_ERR(reg_xceiver);
 
 	if (pdev->dev.of_node) {
 		of_property_read_u32(pdev->dev.of_node,
@@ -1608,6 +1983,12 @@ static int flexcan_probe(struct platform_device *pdev)
 		return -ENODEV;
 	}
 
+	if ((devtype_data->quirks & FLEXCAN_QUIRK_SUPPORT_FD) &&
+	    !(devtype_data->quirks & FLEXCAN_QUIRK_USE_OFF_TIMESTAMP)) {
+		dev_err(&pdev->dev, "CAN-FD mode doesn't work with FIFO mode!\n");
+		return -EINVAL;
+	}
+
 	dev = alloc_candev(sizeof(struct flexcan_priv), 1);
 	if (!dev)
 		return -ENOMEM;
@@ -1632,7 +2013,6 @@ static int flexcan_probe(struct platform_device *pdev)
 
 	priv->dev = &pdev->dev;
 	priv->can.clock.freq = clock_freq;
-	priv->can.bittiming_const = &flexcan_bittiming_const;
 	priv->can.do_set_mode = flexcan_set_mode;
 	priv->can.do_get_berr_counter = flexcan_get_berr_counter;
 	priv->can.ctrlmode_supported = CAN_CTRLMODE_LOOPBACK |
@@ -1645,6 +2025,16 @@ static int flexcan_probe(struct platform_device *pdev)
 	priv->devtype_data = devtype_data;
 	priv->reg_xceiver = reg_xceiver;
 
+	if (priv->devtype_data->quirks & FLEXCAN_QUIRK_SUPPORT_FD) {
+		priv->can.ctrlmode_supported |= CAN_CTRLMODE_FD |
+			CAN_CTRLMODE_FD_NON_ISO;
+		priv->can.bittiming_const = &flexcan_fd_bittiming_const;
+		priv->can.data_bittiming_const =
+			&flexcan_fd_data_bittiming_const;
+	} else {
+		priv->can.bittiming_const = &flexcan_bittiming_const;
+	}
+
 	pm_runtime_get_noresume(&pdev->dev);
 	pm_runtime_set_active(&pdev->dev);
 	pm_runtime_enable(&pdev->dev);
@@ -1655,6 +2045,7 @@ static int flexcan_probe(struct platform_device *pdev)
 		goto failed_register;
 	}
 
+	of_can_transceiver(dev);
 	devm_can_led_init(dev);
 
 	if (priv->devtype_data->quirks & FLEXCAN_QUIRK_SETUP_STOP_MODE) {
@@ -1666,6 +2057,8 @@ static int flexcan_probe(struct platform_device *pdev)
 	return 0;
 
  failed_register:
+	pm_runtime_put_noidle(&pdev->dev);
+	pm_runtime_disable(&pdev->dev);
 	free_candev(dev);
 	return err;
 }
@@ -1685,7 +2078,7 @@ static int __maybe_unused flexcan_suspend(struct device *device)
 {
 	struct net_device *dev = dev_get_drvdata(device);
 	struct flexcan_priv *priv = netdev_priv(dev);
-	int err = 0;
+	int err;
 
 	if (netif_running(dev)) {
 		/* if wakeup is enabled, enter stop mode
@@ -1697,25 +2090,27 @@ static int __maybe_unused flexcan_suspend(struct device *device)
 			if (err)
 				return err;
 		} else {
-			err = flexcan_chip_disable(priv);
+			err = flexcan_chip_stop(dev);
 			if (err)
 				return err;
 
-			err = pm_runtime_force_suspend(device);
+			err = pinctrl_pm_select_sleep_state(device);
+			if (err)
+				return err;
 		}
 		netif_stop_queue(dev);
 		netif_device_detach(dev);
 	}
 	priv->can.state = CAN_STATE_SLEEPING;
 
-	return err;
+	return 0;
 }
 
 static int __maybe_unused flexcan_resume(struct device *device)
 {
 	struct net_device *dev = dev_get_drvdata(device);
 	struct flexcan_priv *priv = netdev_priv(dev);
-	int err = 0;
+	int err;
 
 	priv->can.state = CAN_STATE_ERROR_ACTIVE;
 	if (netif_running(dev)) {
@@ -1727,15 +2122,17 @@ static int __maybe_unused flexcan_resume(struct device *device)
 			if (err)
 				return err;
 		} else {
-			err = pm_runtime_force_resume(device);
+			err = pinctrl_pm_select_default_state(device);
 			if (err)
 				return err;
 
-			err = flexcan_chip_enable(priv);
+			err = flexcan_chip_start(dev);
+			if (err)
+				return err;
 		}
 	}
 
-	return err;
+	return 0;
 }
 
 static int __maybe_unused flexcan_runtime_suspend(struct device *device)
@@ -1761,8 +2158,16 @@ static int __maybe_unused flexcan_noirq_suspend(struct device *device)
 	struct net_device *dev = dev_get_drvdata(device);
 	struct flexcan_priv *priv = netdev_priv(dev);
 
-	if (netif_running(dev) && device_may_wakeup(device))
-		flexcan_enable_wakeup_irq(priv, true);
+	if (netif_running(dev)) {
+		int err;
+
+		if (device_may_wakeup(device))
+			flexcan_enable_wakeup_irq(priv, true);
+
+		err = pm_runtime_force_suspend(device);
+		if (err)
+			return err;
+	}
 
 	return 0;
 }
@@ -1772,8 +2177,16 @@ static int __maybe_unused flexcan_noirq_resume(struct device *device)
 	struct net_device *dev = dev_get_drvdata(device);
 	struct flexcan_priv *priv = netdev_priv(dev);
 
-	if (netif_running(dev) && device_may_wakeup(device))
-		flexcan_enable_wakeup_irq(priv, false);
+	if (netif_running(dev)) {
+		int err;
+
+		err = pm_runtime_force_resume(device);
+		if (err)
+			return err;
+
+		if (device_may_wakeup(device))
+			flexcan_enable_wakeup_irq(priv, false);
+	}
 
 	return 0;
 }
diff --git a/drivers/net/can/spi/Kconfig b/drivers/net/can/spi/Kconfig
index a82240628c33..f45449210047 100644
--- a/drivers/net/can/spi/Kconfig
+++ b/drivers/net/can/spi/Kconfig
@@ -13,6 +13,6 @@ config CAN_MCP251X
 	  Driver for the Microchip MCP251x and MCP25625 SPI CAN
 	  controllers.
 
-source "drivers/net/can/spi/mcp25xxfd/Kconfig"
+source "drivers/net/can/spi/mcp251xfd/Kconfig"
 
 endmenu
diff --git a/drivers/net/can/spi/Makefile b/drivers/net/can/spi/Makefile
index 20c18ac96b1c..33e3f60bbc10 100644
--- a/drivers/net/can/spi/Makefile
+++ b/drivers/net/can/spi/Makefile
@@ -6,4 +6,4 @@
 
 obj-$(CONFIG_CAN_HI311X)	+= hi311x.o
 obj-$(CONFIG_CAN_MCP251X)	+= mcp251x.o
-obj-y				+= mcp25xxfd/
+obj-y				+= mcp251xfd/
diff --git a/drivers/net/can/spi/mcp25xxfd/Kconfig b/drivers/net/can/spi/mcp251xfd/Kconfig
index 9eb596019a58..f5a147a92cb2 100644
--- a/drivers/net/can/spi/mcp25xxfd/Kconfig
+++ b/drivers/net/can/spi/mcp251xfd/Kconfig
@@ -1,14 +1,14 @@
 # SPDX-License-Identifier: GPL-2.0-only
 
-config CAN_MCP25XXFD
-	tristate "Microchip MCP25xxFD SPI CAN controllers"
+config CAN_MCP251XFD
+	tristate "Microchip MCP251xFD SPI CAN controllers"
 	select REGMAP
 	help
-	  Driver for the Microchip MCP25XXFD SPI FD-CAN controller
+	  Driver for the Microchip MCP251XFD SPI FD-CAN controller
 	  family.
 
-config CAN_MCP25XXFD_SANITY
-	depends on CAN_MCP25XXFD
+config CAN_MCP251XFD_SANITY
+	depends on CAN_MCP251XFD
 	bool "Additional Sanity Checks"
 	help
 	  This option enables additional sanity checks in the driver,
diff --git a/drivers/net/can/spi/mcp251xfd/Makefile b/drivers/net/can/spi/mcp251xfd/Makefile
new file mode 100644
index 000000000000..cb71244cbe89
--- /dev/null
+++ b/drivers/net/can/spi/mcp251xfd/Makefile
@@ -0,0 +1,8 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+obj-$(CONFIG_CAN_MCP251XFD) += mcp251xfd.o
+
+mcp251xfd-objs :=
+mcp251xfd-objs += mcp251xfd-core.o
+mcp251xfd-objs += mcp251xfd-crc16.o
+mcp251xfd-objs += mcp251xfd-regmap.o
diff --git a/drivers/net/can/spi/mcp25xxfd/mcp25xxfd-core.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
index bd2ba981ae36..c3f49543ff26 100644
--- a/drivers/net/can/spi/mcp25xxfd/mcp25xxfd-core.c
+++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 //
-// mcp25xxfd - Microchip MCP25xxFD Family CAN controller driver
+// mcp251xfd - Microchip MCP251xFD Family CAN controller driver
 //
 // Copyright (c) 2019, 2020 Pengutronix,
 //                          Marc Kleine-Budde <kernel@pengutronix.de>
@@ -23,31 +23,31 @@
 
 #include <asm/unaligned.h>
 
-#include "mcp25xxfd.h"
+#include "mcp251xfd.h"
 
-#define DEVICE_NAME "mcp25xxfd"
+#define DEVICE_NAME "mcp251xfd"
 
-static const struct mcp25xxfd_devtype_data mcp25xxfd_devtype_data_mcp2517fd = {
-	.quirks = MCP25XXFD_QUIRK_MAB_NO_WARN | MCP25XXFD_QUIRK_CRC_REG |
-		MCP25XXFD_QUIRK_CRC_RX | MCP25XXFD_QUIRK_CRC_TX |
-		MCP25XXFD_QUIRK_ECC,
-	.model = MCP25XXFD_MODEL_MCP2517FD,
+static const struct mcp251xfd_devtype_data mcp251xfd_devtype_data_mcp2517fd = {
+	.quirks = MCP251XFD_QUIRK_MAB_NO_WARN | MCP251XFD_QUIRK_CRC_REG |
+		MCP251XFD_QUIRK_CRC_RX | MCP251XFD_QUIRK_CRC_TX |
+		MCP251XFD_QUIRK_ECC,
+	.model = MCP251XFD_MODEL_MCP2517FD,
 };
 
-static const struct mcp25xxfd_devtype_data mcp25xxfd_devtype_data_mcp2518fd = {
-	.quirks = MCP25XXFD_QUIRK_CRC_REG | MCP25XXFD_QUIRK_CRC_RX |
-		MCP25XXFD_QUIRK_CRC_TX | MCP25XXFD_QUIRK_ECC,
-	.model = MCP25XXFD_MODEL_MCP2518FD,
+static const struct mcp251xfd_devtype_data mcp251xfd_devtype_data_mcp2518fd = {
+	.quirks = MCP251XFD_QUIRK_CRC_REG | MCP251XFD_QUIRK_CRC_RX |
+		MCP251XFD_QUIRK_CRC_TX | MCP251XFD_QUIRK_ECC,
+	.model = MCP251XFD_MODEL_MCP2518FD,
 };
 
 /* Autodetect model, start with CRC enabled. */
-static const struct mcp25xxfd_devtype_data mcp25xxfd_devtype_data_mcp25xxfd = {
-	.quirks = MCP25XXFD_QUIRK_CRC_REG | MCP25XXFD_QUIRK_CRC_RX |
-		MCP25XXFD_QUIRK_CRC_TX | MCP25XXFD_QUIRK_ECC,
-	.model = MCP25XXFD_MODEL_MCP25XXFD,
+static const struct mcp251xfd_devtype_data mcp251xfd_devtype_data_mcp251xfd = {
+	.quirks = MCP251XFD_QUIRK_CRC_REG | MCP251XFD_QUIRK_CRC_RX |
+		MCP251XFD_QUIRK_CRC_TX | MCP251XFD_QUIRK_ECC,
+	.model = MCP251XFD_MODEL_MCP251XFD,
 };
 
-static const struct can_bittiming_const mcp25xxfd_bittiming_const = {
+static const struct can_bittiming_const mcp251xfd_bittiming_const = {
 	.name = DEVICE_NAME,
 	.tseg1_min = 2,
 	.tseg1_max = 256,
@@ -59,7 +59,7 @@ static const struct can_bittiming_const mcp25xxfd_bittiming_const = {
 	.brp_inc = 1,
 };
 
-static const struct can_bittiming_const mcp25xxfd_data_bittiming_const = {
+static const struct can_bittiming_const mcp251xfd_data_bittiming_const = {
 	.name = DEVICE_NAME,
 	.tseg1_min = 1,
 	.tseg1_max = 32,
@@ -71,51 +71,51 @@ static const struct can_bittiming_const mcp25xxfd_data_bittiming_const = {
 	.brp_inc = 1,
 };
 
-static const char *__mcp25xxfd_get_model_str(enum mcp25xxfd_model model)
+static const char *__mcp251xfd_get_model_str(enum mcp251xfd_model model)
 {
 	switch (model) {
-	case MCP25XXFD_MODEL_MCP2517FD:
+	case MCP251XFD_MODEL_MCP2517FD:
 		return "MCP2517FD"; break;
-	case MCP25XXFD_MODEL_MCP2518FD:
+	case MCP251XFD_MODEL_MCP2518FD:
 		return "MCP2518FD"; break;
-	case MCP25XXFD_MODEL_MCP25XXFD:
-		return "MCP25xxFD"; break;
+	case MCP251XFD_MODEL_MCP251XFD:
+		return "MCP251xFD"; break;
 	}
 
 	return "<unknown>";
 }
 
 static inline const char *
-mcp25xxfd_get_model_str(const struct mcp25xxfd_priv *priv)
+mcp251xfd_get_model_str(const struct mcp251xfd_priv *priv)
 {
-	return __mcp25xxfd_get_model_str(priv->devtype_data.model);
+	return __mcp251xfd_get_model_str(priv->devtype_data.model);
 }
 
-static const char *mcp25xxfd_get_mode_str(const u8 mode)
+static const char *mcp251xfd_get_mode_str(const u8 mode)
 {
 	switch (mode) {
-	case MCP25XXFD_REG_CON_MODE_MIXED:
+	case MCP251XFD_REG_CON_MODE_MIXED:
 		return "Mixed (CAN FD/CAN 2.0)"; break;
-	case MCP25XXFD_REG_CON_MODE_SLEEP:
+	case MCP251XFD_REG_CON_MODE_SLEEP:
 		return "Sleep"; break;
-	case MCP25XXFD_REG_CON_MODE_INT_LOOPBACK:
+	case MCP251XFD_REG_CON_MODE_INT_LOOPBACK:
 		return "Internal Loopback"; break;
-	case MCP25XXFD_REG_CON_MODE_LISTENONLY:
+	case MCP251XFD_REG_CON_MODE_LISTENONLY:
 		return "Listen Only"; break;
-	case MCP25XXFD_REG_CON_MODE_CONFIG:
+	case MCP251XFD_REG_CON_MODE_CONFIG:
 		return "Configuration"; break;
-	case MCP25XXFD_REG_CON_MODE_EXT_LOOPBACK:
+	case MCP251XFD_REG_CON_MODE_EXT_LOOPBACK:
 		return "External Loopback"; break;
-	case MCP25XXFD_REG_CON_MODE_CAN2_0:
+	case MCP251XFD_REG_CON_MODE_CAN2_0:
 		return "CAN 2.0"; break;
-	case MCP25XXFD_REG_CON_MODE_RESTRICTED:
+	case MCP251XFD_REG_CON_MODE_RESTRICTED:
 		return "Restricted Operation"; break;
 	}
 
 	return "<unknown>";
 }
 
-static inline int mcp25xxfd_vdd_enable(const struct mcp25xxfd_priv *priv)
+static inline int mcp251xfd_vdd_enable(const struct mcp251xfd_priv *priv)
 {
 	if (!priv->reg_vdd)
 		return 0;
@@ -123,7 +123,7 @@ static inline int mcp25xxfd_vdd_enable(const struct mcp25xxfd_priv *priv)
 	return regulator_enable(priv->reg_vdd);
 }
 
-static inline int mcp25xxfd_vdd_disable(const struct mcp25xxfd_priv *priv)
+static inline int mcp251xfd_vdd_disable(const struct mcp251xfd_priv *priv)
 {
 	if (!priv->reg_vdd)
 		return 0;
@@ -132,7 +132,7 @@ static inline int mcp25xxfd_vdd_disable(const struct mcp25xxfd_priv *priv)
 }
 
 static inline int
-mcp25xxfd_transceiver_enable(const struct mcp25xxfd_priv *priv)
+mcp251xfd_transceiver_enable(const struct mcp251xfd_priv *priv)
 {
 	if (!priv->reg_xceiver)
 		return 0;
@@ -141,7 +141,7 @@ mcp25xxfd_transceiver_enable(const struct mcp25xxfd_priv *priv)
 }
 
 static inline int
-mcp25xxfd_transceiver_disable(const struct mcp25xxfd_priv *priv)
+mcp251xfd_transceiver_disable(const struct mcp251xfd_priv *priv)
 {
 	if (!priv->reg_xceiver)
 		return 0;
@@ -149,7 +149,7 @@ mcp25xxfd_transceiver_disable(const struct mcp25xxfd_priv *priv)
 	return regulator_disable(priv->reg_xceiver);
 }
 
-static int mcp25xxfd_clks_and_vdd_enable(const struct mcp25xxfd_priv *priv)
+static int mcp251xfd_clks_and_vdd_enable(const struct mcp251xfd_priv *priv)
 {
 	int err;
 
@@ -157,22 +157,22 @@ static int mcp25xxfd_clks_and_vdd_enable(const struct mcp25xxfd_priv *priv)
 	if (err)
 		return err;
 
-	err = mcp25xxfd_vdd_enable(priv);
+	err = mcp251xfd_vdd_enable(priv);
 	if (err)
 		clk_disable_unprepare(priv->clk);
 
 	/* Wait for oscillator stabilisation time after power up */
-	usleep_range(MCP25XXFD_OSC_STAB_SLEEP_US,
-		     2 * MCP25XXFD_OSC_STAB_SLEEP_US);
+	usleep_range(MCP251XFD_OSC_STAB_SLEEP_US,
+		     2 * MCP251XFD_OSC_STAB_SLEEP_US);
 
 	return err;
 }
 
-static int mcp25xxfd_clks_and_vdd_disable(const struct mcp25xxfd_priv *priv)
+static int mcp251xfd_clks_and_vdd_disable(const struct mcp251xfd_priv *priv)
 {
 	int err;
 
-	err = mcp25xxfd_vdd_disable(priv);
+	err = mcp251xfd_vdd_disable(priv);
 	if (err)
 		return err;
 
@@ -182,30 +182,30 @@ static int mcp25xxfd_clks_and_vdd_disable(const struct mcp25xxfd_priv *priv)
 }
 
 static inline u8
-mcp25xxfd_cmd_prepare_write_reg(const struct mcp25xxfd_priv *priv,
-				union mcp25xxfd_write_reg_buf *write_reg_buf,
+mcp251xfd_cmd_prepare_write_reg(const struct mcp251xfd_priv *priv,
+				union mcp251xfd_write_reg_buf *write_reg_buf,
 				const u16 reg, const u32 mask, const u32 val)
 {
 	u8 first_byte, last_byte, len;
 	u8 *data;
 	__le32 val_le32;
 
-	first_byte = mcp25xxfd_first_byte_set(mask);
-	last_byte = mcp25xxfd_last_byte_set(mask);
+	first_byte = mcp251xfd_first_byte_set(mask);
+	last_byte = mcp251xfd_last_byte_set(mask);
 	len = last_byte - first_byte + 1;
 
-	data = mcp25xxfd_spi_cmd_write(priv, write_reg_buf, reg + first_byte);
+	data = mcp251xfd_spi_cmd_write(priv, write_reg_buf, reg + first_byte);
 	val_le32 = cpu_to_le32(val >> BITS_PER_BYTE * first_byte);
 	memcpy(data, &val_le32, len);
 
-	if (priv->devtype_data.quirks & MCP25XXFD_QUIRK_CRC_REG) {
+	if (priv->devtype_data.quirks & MCP251XFD_QUIRK_CRC_REG) {
 		u16 crc;
 
-		mcp25xxfd_spi_cmd_crc_set_len_in_reg(&write_reg_buf->crc.cmd,
+		mcp251xfd_spi_cmd_crc_set_len_in_reg(&write_reg_buf->crc.cmd,
 						     len);
 		/* CRC */
 		len += sizeof(write_reg_buf->crc.cmd);
-		crc = mcp25xxfd_crc16_compute(&write_reg_buf->crc, len);
+		crc = mcp251xfd_crc16_compute(&write_reg_buf->crc, len);
 		put_unaligned_be16(crc, (void *)write_reg_buf + len);
 
 		/* Total length */
@@ -218,80 +218,80 @@ mcp25xxfd_cmd_prepare_write_reg(const struct mcp25xxfd_priv *priv,
 }
 
 static inline int
-mcp25xxfd_tef_tail_get_from_chip(const struct mcp25xxfd_priv *priv,
+mcp251xfd_tef_tail_get_from_chip(const struct mcp251xfd_priv *priv,
 				 u8 *tef_tail)
 {
 	u32 tef_ua;
 	int err;
 
-	err = regmap_read(priv->map_reg, MCP25XXFD_REG_TEFUA, &tef_ua);
+	err = regmap_read(priv->map_reg, MCP251XFD_REG_TEFUA, &tef_ua);
 	if (err)
 		return err;
 
-	*tef_tail = tef_ua / sizeof(struct mcp25xxfd_hw_tef_obj);
+	*tef_tail = tef_ua / sizeof(struct mcp251xfd_hw_tef_obj);
 
 	return 0;
 }
 
 static inline int
-mcp25xxfd_tx_tail_get_from_chip(const struct mcp25xxfd_priv *priv,
+mcp251xfd_tx_tail_get_from_chip(const struct mcp251xfd_priv *priv,
 				u8 *tx_tail)
 {
 	u32 fifo_sta;
 	int err;
 
 	err = regmap_read(priv->map_reg,
-			  MCP25XXFD_REG_FIFOSTA(MCP25XXFD_TX_FIFO),
+			  MCP251XFD_REG_FIFOSTA(MCP251XFD_TX_FIFO),
 			  &fifo_sta);
 	if (err)
 		return err;
 
-	*tx_tail = FIELD_GET(MCP25XXFD_REG_FIFOSTA_FIFOCI_MASK, fifo_sta);
+	*tx_tail = FIELD_GET(MCP251XFD_REG_FIFOSTA_FIFOCI_MASK, fifo_sta);
 
 	return 0;
 }
 
 static inline int
-mcp25xxfd_rx_head_get_from_chip(const struct mcp25xxfd_priv *priv,
-				const struct mcp25xxfd_rx_ring *ring,
+mcp251xfd_rx_head_get_from_chip(const struct mcp251xfd_priv *priv,
+				const struct mcp251xfd_rx_ring *ring,
 				u8 *rx_head)
 {
 	u32 fifo_sta;
 	int err;
 
-	err = regmap_read(priv->map_reg, MCP25XXFD_REG_FIFOSTA(ring->fifo_nr),
+	err = regmap_read(priv->map_reg, MCP251XFD_REG_FIFOSTA(ring->fifo_nr),
 			  &fifo_sta);
 	if (err)
 		return err;
 
-	*rx_head = FIELD_GET(MCP25XXFD_REG_FIFOSTA_FIFOCI_MASK, fifo_sta);
+	*rx_head = FIELD_GET(MCP251XFD_REG_FIFOSTA_FIFOCI_MASK, fifo_sta);
 
 	return 0;
 }
 
 static inline int
-mcp25xxfd_rx_tail_get_from_chip(const struct mcp25xxfd_priv *priv,
-				const struct mcp25xxfd_rx_ring *ring,
+mcp251xfd_rx_tail_get_from_chip(const struct mcp251xfd_priv *priv,
+				const struct mcp251xfd_rx_ring *ring,
 				u8 *rx_tail)
 {
 	u32 fifo_ua;
 	int err;
 
-	err = regmap_read(priv->map_reg, MCP25XXFD_REG_FIFOUA(ring->fifo_nr),
+	err = regmap_read(priv->map_reg, MCP251XFD_REG_FIFOUA(ring->fifo_nr),
 			  &fifo_ua);
 	if (err)
 		return err;
 
-	fifo_ua -= ring->base - MCP25XXFD_RAM_START;
+	fifo_ua -= ring->base - MCP251XFD_RAM_START;
 	*rx_tail = fifo_ua / ring->obj_size;
 
 	return 0;
 }
 
 static void
-mcp25xxfd_tx_ring_init_tx_obj(const struct mcp25xxfd_priv *priv,
-			      const struct mcp25xxfd_tx_ring *ring,
-			      struct mcp25xxfd_tx_obj *tx_obj,
+mcp251xfd_tx_ring_init_tx_obj(const struct mcp251xfd_priv *priv,
+			      const struct mcp251xfd_tx_ring *ring,
+			      struct mcp251xfd_tx_obj *tx_obj,
 			      const u8 rts_buf_len,
 			      const u8 n)
 {
@@ -299,12 +299,12 @@ mcp25xxfd_tx_ring_init_tx_obj(const struct mcp25xxfd_priv *priv,
 	u16 addr;
 
 	/* FIFO load */
-	addr = mcp25xxfd_get_tx_obj_addr(ring, n);
-	if (priv->devtype_data.quirks & MCP25XXFD_QUIRK_CRC_TX)
-		mcp25xxfd_spi_cmd_write_crc_set_addr(&tx_obj->buf.crc.cmd,
+	addr = mcp251xfd_get_tx_obj_addr(ring, n);
+	if (priv->devtype_data.quirks & MCP251XFD_QUIRK_CRC_TX)
+		mcp251xfd_spi_cmd_write_crc_set_addr(&tx_obj->buf.crc.cmd,
 						     addr);
 	else
-		mcp25xxfd_spi_cmd_write_nocrc(&tx_obj->buf.nocrc.cmd,
+		mcp251xfd_spi_cmd_write_nocrc(&tx_obj->buf.nocrc.cmd,
 					      addr);
 
 	xfer = &tx_obj->xfer[0];
@@ -324,11 +324,11 @@ mcp25xxfd_tx_ring_init_tx_obj(const struct mcp25xxfd_priv *priv,
 					ARRAY_SIZE(tx_obj->xfer));
 }
 
-static void mcp25xxfd_ring_init(struct mcp25xxfd_priv *priv)
+static void mcp251xfd_ring_init(struct mcp251xfd_priv *priv)
 {
-	struct mcp25xxfd_tx_ring *tx_ring;
-	struct mcp25xxfd_rx_ring *rx_ring, *prev_rx_ring = NULL;
-	struct mcp25xxfd_tx_obj *tx_obj;
+	struct mcp251xfd_tx_ring *tx_ring;
+	struct mcp251xfd_rx_ring *rx_ring, *prev_rx_ring = NULL;
+	struct mcp251xfd_tx_obj *tx_obj;
 	u32 val;
 	u16 addr;
 	u8 len;
@@ -342,27 +342,27 @@ static void mcp25xxfd_ring_init(struct mcp25xxfd_priv *priv)
 	tx_ring = priv->tx;
 	tx_ring->head = 0;
 	tx_ring->tail = 0;
-	tx_ring->base = mcp25xxfd_get_tef_obj_addr(tx_ring->obj_num);
+	tx_ring->base = mcp251xfd_get_tef_obj_addr(tx_ring->obj_num);
 
 	/* FIFO request to send */
-	addr = MCP25XXFD_REG_FIFOCON(MCP25XXFD_TX_FIFO);
-	val = MCP25XXFD_REG_FIFOCON_TXREQ | MCP25XXFD_REG_FIFOCON_UINC;
-	len = mcp25xxfd_cmd_prepare_write_reg(priv, &tx_ring->rts_buf,
+	addr = MCP251XFD_REG_FIFOCON(MCP251XFD_TX_FIFO);
+	val = MCP251XFD_REG_FIFOCON_TXREQ | MCP251XFD_REG_FIFOCON_UINC;
+	len = mcp251xfd_cmd_prepare_write_reg(priv, &tx_ring->rts_buf,
 					      addr, val, val);
 
-	mcp25xxfd_for_each_tx_obj(tx_ring, tx_obj, i)
-		mcp25xxfd_tx_ring_init_tx_obj(priv, tx_ring, tx_obj, len, i);
+	mcp251xfd_for_each_tx_obj(tx_ring, tx_obj, i)
+		mcp251xfd_tx_ring_init_tx_obj(priv, tx_ring, tx_obj, len, i);
 
 	/* RX */
-	mcp25xxfd_for_each_rx_ring(priv, rx_ring, i) {
+	mcp251xfd_for_each_rx_ring(priv, rx_ring, i) {
 		rx_ring->head = 0;
 		rx_ring->tail = 0;
 		rx_ring->nr = i;
-		rx_ring->fifo_nr = MCP25XXFD_RX_FIFO(i);
+		rx_ring->fifo_nr = MCP251XFD_RX_FIFO(i);
 
 		if (!prev_rx_ring)
 			rx_ring->base =
-				mcp25xxfd_get_tx_obj_addr(tx_ring,
+				mcp251xfd_get_tx_obj_addr(tx_ring,
 							  tx_ring->obj_num);
 		else
 			rx_ring->base = prev_rx_ring->base +
@@ -373,41 +373,41 @@ static void mcp25xxfd_ring_init(struct mcp25xxfd_priv *priv)
 	}
 }
 
-static void mcp25xxfd_ring_free(struct mcp25xxfd_priv *priv)
+static void mcp251xfd_ring_free(struct mcp251xfd_priv *priv)
 {
 	int i;
 
-	for (i = ARRAY_SIZE(priv->rx) - 1; i > 0; i--) {
+	for (i = ARRAY_SIZE(priv->rx) - 1; i >= 0; i--) {
 		kfree(priv->rx[i]);
 		priv->rx[i] = NULL;
 	}
 }
 
-static int mcp25xxfd_ring_alloc(struct mcp25xxfd_priv *priv)
+static int mcp251xfd_ring_alloc(struct mcp251xfd_priv *priv)
 {
-	struct mcp25xxfd_tx_ring *tx_ring;
-	struct mcp25xxfd_rx_ring *rx_ring;
+	struct mcp251xfd_tx_ring *tx_ring;
+	struct mcp251xfd_rx_ring *rx_ring;
 	int tef_obj_size, tx_obj_size, rx_obj_size;
 	int tx_obj_num;
 	int ram_free, i;
 
-	tef_obj_size = sizeof(struct mcp25xxfd_hw_tef_obj);
+	tef_obj_size = sizeof(struct mcp251xfd_hw_tef_obj);
 	/* listen-only mode works like FD mode */
 	if (priv->can.ctrlmode & (CAN_CTRLMODE_LISTENONLY | CAN_CTRLMODE_FD)) {
-		tx_obj_num = MCP25XXFD_TX_OBJ_NUM_CANFD;
-		tx_obj_size = sizeof(struct mcp25xxfd_hw_tx_obj_canfd);
-		rx_obj_size = sizeof(struct mcp25xxfd_hw_rx_obj_canfd);
+		tx_obj_num = MCP251XFD_TX_OBJ_NUM_CANFD;
+		tx_obj_size = sizeof(struct mcp251xfd_hw_tx_obj_canfd);
+		rx_obj_size = sizeof(struct mcp251xfd_hw_rx_obj_canfd);
 	} else {
-		tx_obj_num = MCP25XXFD_TX_OBJ_NUM_CAN;
-		tx_obj_size = sizeof(struct mcp25xxfd_hw_tx_obj_can);
-		rx_obj_size = sizeof(struct mcp25xxfd_hw_rx_obj_can);
+		tx_obj_num = MCP251XFD_TX_OBJ_NUM_CAN;
+		tx_obj_size = sizeof(struct mcp251xfd_hw_tx_obj_can);
+		rx_obj_size = sizeof(struct mcp251xfd_hw_rx_obj_can);
 	}
 
 	tx_ring = priv->tx;
 	tx_ring->obj_num = tx_obj_num;
 	tx_ring->obj_size = tx_obj_size;
 
-	ram_free = MCP25XXFD_RAM_SIZE - tx_obj_num *
+	ram_free = MCP251XFD_RAM_SIZE - tx_obj_num *
 		(tef_obj_size + tx_obj_size);
 
 	for (i = 0;
@@ -421,7 +421,7 @@ static int mcp25xxfd_ring_alloc(struct mcp25xxfd_priv *priv)
 		rx_ring = kzalloc(sizeof(*rx_ring) + rx_obj_size * rx_obj_num,
 				  GFP_KERNEL);
 		if (!rx_ring) {
-			mcp25xxfd_ring_free(priv);
+			mcp251xfd_ring_free(priv);
 			return -ENOMEM;
 		}
 		rx_ring->obj_num = rx_obj_num;
@@ -437,7 +437,7 @@ static int mcp25xxfd_ring_alloc(struct mcp25xxfd_priv *priv)
 		   tx_obj_num, tef_obj_size, tef_obj_size * tx_obj_num,
 		   tx_obj_num, tx_obj_size, tx_obj_size * tx_obj_num);
 
-	mcp25xxfd_for_each_rx_ring(priv, rx_ring, i) {
+	mcp251xfd_for_each_rx_ring(priv, rx_ring, i) {
 		netdev_dbg(priv->ndev,
 			   "FIFO setup: RX-%d: %d*%d bytes = %d bytes\n",
 			   i, rx_ring->obj_num, rx_ring->obj_size,
@@ -452,48 +452,48 @@ static int mcp25xxfd_ring_alloc(struct mcp25xxfd_priv *priv)
 }
 
 static inline int
-mcp25xxfd_chip_get_mode(const struct mcp25xxfd_priv *priv, u8 *mode)
+mcp251xfd_chip_get_mode(const struct mcp251xfd_priv *priv, u8 *mode)
 {
 	u32 val;
 	int err;
 
-	err = regmap_read(priv->map_reg, MCP25XXFD_REG_CON, &val);
+	err = regmap_read(priv->map_reg, MCP251XFD_REG_CON, &val);
 	if (err)
 		return err;
 
-	*mode = FIELD_GET(MCP25XXFD_REG_CON_OPMOD_MASK, val);
+	*mode = FIELD_GET(MCP251XFD_REG_CON_OPMOD_MASK, val);
 
 	return 0;
 }
 
 static int
-__mcp25xxfd_chip_set_mode(const struct mcp25xxfd_priv *priv,
+__mcp251xfd_chip_set_mode(const struct mcp251xfd_priv *priv,
 			  const u8 mode_req, bool nowait)
 {
 	u32 con, con_reqop;
 	int err;
 
-	con_reqop = FIELD_PREP(MCP25XXFD_REG_CON_REQOP_MASK, mode_req);
-	err = regmap_update_bits(priv->map_reg, MCP25XXFD_REG_CON,
-				 MCP25XXFD_REG_CON_REQOP_MASK, con_reqop);
+	con_reqop = FIELD_PREP(MCP251XFD_REG_CON_REQOP_MASK, mode_req);
+	err = regmap_update_bits(priv->map_reg, MCP251XFD_REG_CON,
+				 MCP251XFD_REG_CON_REQOP_MASK, con_reqop);
 	if (err)
 		return err;
 
-	if (mode_req == MCP25XXFD_REG_CON_MODE_SLEEP || nowait)
+	if (mode_req == MCP251XFD_REG_CON_MODE_SLEEP || nowait)
 		return 0;
 
-	err = regmap_read_poll_timeout(priv->map_reg, MCP25XXFD_REG_CON, con,
-				       FIELD_GET(MCP25XXFD_REG_CON_OPMOD_MASK,
+	err = regmap_read_poll_timeout(priv->map_reg, MCP251XFD_REG_CON, con,
+				       FIELD_GET(MCP251XFD_REG_CON_OPMOD_MASK,
 						 con) == mode_req,
-				       MCP25XXFD_POLL_SLEEP_US,
-				       MCP25XXFD_POLL_TIMEOUT_US);
+				       MCP251XFD_POLL_SLEEP_US,
+				       MCP251XFD_POLL_TIMEOUT_US);
 	if (err) {
-		u8 mode = FIELD_GET(MCP25XXFD_REG_CON_OPMOD_MASK, con);
+		u8 mode = FIELD_GET(MCP251XFD_REG_CON_OPMOD_MASK, con);
 
 		netdev_err(priv->ndev,
 			   "Controller failed to enter mode %s Mode (%u) and stays in %s Mode (%u).\n",
-			   mcp25xxfd_get_mode_str(mode_req), mode_req,
-			   mcp25xxfd_get_mode_str(mode), mode);
+			   mcp251xfd_get_mode_str(mode_req), mode_req,
+			   mcp251xfd_get_mode_str(mode), mode);
 		return err;
 	}
 
@@ -501,25 +501,25 @@ __mcp25xxfd_chip_set_mode(const struct mcp25xxfd_priv *priv,
 }
 
 static inline int
-mcp25xxfd_chip_set_mode(const struct mcp25xxfd_priv *priv,
+mcp251xfd_chip_set_mode(const struct mcp251xfd_priv *priv,
 			const u8 mode_req)
 {
-	return __mcp25xxfd_chip_set_mode(priv, mode_req, false);
+	return __mcp251xfd_chip_set_mode(priv, mode_req, false);
 }
 
 static inline int
-mcp25xxfd_chip_set_mode_nowait(const struct mcp25xxfd_priv *priv,
+mcp251xfd_chip_set_mode_nowait(const struct mcp251xfd_priv *priv,
 			       const u8 mode_req)
 {
-	return __mcp25xxfd_chip_set_mode(priv, mode_req, true);
+	return __mcp251xfd_chip_set_mode(priv, mode_req, true);
 }
 
-static inline bool mcp25xxfd_osc_invalid(u32 reg)
+static inline bool mcp251xfd_osc_invalid(u32 reg)
 {
 	return reg == 0x0 || reg == 0xffffffff;
 }
 
-static int mcp25xxfd_chip_clock_enable(const struct mcp25xxfd_priv *priv)
+static int mcp251xfd_chip_clock_enable(const struct mcp251xfd_priv *priv)
 {
 	u32 osc, osc_reference, osc_mask;
 	int err;
@@ -527,10 +527,10 @@ static int mcp25xxfd_chip_clock_enable(const struct mcp25xxfd_priv *priv)
 	/* Set Power On Defaults for "Clock Output Divisor" and remove
 	 * "Oscillator Disable" bit.
 	 */
-	osc = FIELD_PREP(MCP25XXFD_REG_OSC_CLKODIV_MASK,
-			 MCP25XXFD_REG_OSC_CLKODIV_10);
-	osc_reference = MCP25XXFD_REG_OSC_OSCRDY;
-	osc_mask = MCP25XXFD_REG_OSC_OSCRDY | MCP25XXFD_REG_OSC_PLLRDY;
+	osc = FIELD_PREP(MCP251XFD_REG_OSC_CLKODIV_MASK,
+			 MCP251XFD_REG_OSC_CLKODIV_10);
+	osc_reference = MCP251XFD_REG_OSC_OSCRDY;
+	osc_mask = MCP251XFD_REG_OSC_OSCRDY | MCP251XFD_REG_OSC_PLLRDY;
 
 	/* Note:
 	 *
@@ -538,19 +538,19 @@ static int mcp25xxfd_chip_clock_enable(const struct mcp25xxfd_priv *priv)
 	 * removes the "Oscillator Disable" bit and powers it up. All
 	 * other bits are unaffected.
 	 */
-	err = regmap_write(priv->map_reg, MCP25XXFD_REG_OSC, osc);
+	err = regmap_write(priv->map_reg, MCP251XFD_REG_OSC, osc);
 	if (err)
 		return err;
 
 	/* Wait for "Oscillator Ready" bit */
-	err = regmap_read_poll_timeout(priv->map_reg, MCP25XXFD_REG_OSC, osc,
+	err = regmap_read_poll_timeout(priv->map_reg, MCP251XFD_REG_OSC, osc,
 				       (osc & osc_mask) == osc_reference,
-				       MCP25XXFD_OSC_STAB_SLEEP_US,
-				       MCP25XXFD_OSC_STAB_TIMEOUT_US);
-	if (mcp25xxfd_osc_invalid(osc)) {
+				       MCP251XFD_OSC_STAB_SLEEP_US,
+				       MCP251XFD_OSC_STAB_TIMEOUT_US);
+	if (mcp251xfd_osc_invalid(osc)) {
 		netdev_err(priv->ndev,
 			   "Failed to detect %s (osc=0x%08x).\n",
-			   mcp25xxfd_get_model_str(priv), osc);
+			   mcp251xfd_get_model_str(priv), osc);
 		return -ENODEV;
 	} else if (err == -ETIMEDOUT) {
 		netdev_err(priv->ndev,
@@ -564,19 +564,19 @@ static int mcp25xxfd_chip_clock_enable(const struct mcp25xxfd_priv *priv)
 	return 0;
 }
 
-static int mcp25xxfd_chip_softreset_do(const struct mcp25xxfd_priv *priv)
+static int mcp251xfd_chip_softreset_do(const struct mcp251xfd_priv *priv)
 {
-	const __be16 cmd = mcp25xxfd_cmd_reset();
+	const __be16 cmd = mcp251xfd_cmd_reset();
 	int err;
 
 	/* The Set Mode and SPI Reset command only seems to works if
 	 * the controller is not in Sleep Mode.
 	 */
-	err = mcp25xxfd_chip_clock_enable(priv);
+	err = mcp251xfd_chip_clock_enable(priv);
 	if (err)
 		return err;
 
-	err = mcp25xxfd_chip_set_mode(priv, MCP25XXFD_REG_CON_MODE_CONFIG);
+	err = mcp251xfd_chip_set_mode(priv, MCP251XFD_REG_CON_MODE_CONFIG);
 	if (err)
 		return err;
 
@@ -584,29 +584,29 @@ static int mcp25xxfd_chip_softreset_do(const struct mcp25xxfd_priv *priv)
 	return spi_write_then_read(priv->spi, &cmd, sizeof(cmd), NULL, 0);
 }
 
-static int mcp25xxfd_chip_softreset_check(const struct mcp25xxfd_priv *priv)
+static int mcp251xfd_chip_softreset_check(const struct mcp251xfd_priv *priv)
 {
 	u32 osc, osc_reference;
 	u8 mode;
 	int err;
 
-	err = mcp25xxfd_chip_get_mode(priv, &mode);
+	err = mcp251xfd_chip_get_mode(priv, &mode);
 	if (err)
 		return err;
 
-	if (mode != MCP25XXFD_REG_CON_MODE_CONFIG) {
+	if (mode != MCP251XFD_REG_CON_MODE_CONFIG) {
 		netdev_info(priv->ndev,
 			    "Controller not in Config Mode after reset, but in %s Mode (%u).\n",
-			    mcp25xxfd_get_mode_str(mode), mode);
+			    mcp251xfd_get_mode_str(mode), mode);
 		return -ETIMEDOUT;
 	}
 
-	osc_reference = MCP25XXFD_REG_OSC_OSCRDY |
-		FIELD_PREP(MCP25XXFD_REG_OSC_CLKODIV_MASK,
-			   MCP25XXFD_REG_OSC_CLKODIV_10);
+	osc_reference = MCP251XFD_REG_OSC_OSCRDY |
+		FIELD_PREP(MCP251XFD_REG_OSC_CLKODIV_MASK,
+			   MCP251XFD_REG_OSC_CLKODIV_10);
 
 	/* check reset defaults of OSC reg */
-	err = regmap_read(priv->map_reg, MCP25XXFD_REG_OSC, &osc);
+	err = regmap_read(priv->map_reg, MCP251XFD_REG_OSC, &osc);
 	if (err)
 		return err;
 
@@ -620,22 +620,22 @@ static int mcp25xxfd_chip_softreset_check(const struct mcp25xxfd_priv *priv)
 	return 0;
 }
 
-static int mcp25xxfd_chip_softreset(const struct mcp25xxfd_priv *priv)
+static int mcp251xfd_chip_softreset(const struct mcp251xfd_priv *priv)
 {
 	int err, i;
 
-	for (i = 0; i < MCP25XXFD_SOFTRESET_RETRIES_MAX; i++) {
+	for (i = 0; i < MCP251XFD_SOFTRESET_RETRIES_MAX; i++) {
 		if (i)
 			netdev_info(priv->ndev,
 				    "Retrying to reset Controller.\n");
 
-		err = mcp25xxfd_chip_softreset_do(priv);
+		err = mcp251xfd_chip_softreset_do(priv);
 		if (err == -ETIMEDOUT)
 			continue;
 		if (err)
 			return err;
 
-		err = mcp25xxfd_chip_softreset_check(priv);
+		err = mcp251xfd_chip_softreset_check(priv);
 		if (err == -ETIMEDOUT)
 			continue;
 		if (err)
@@ -650,7 +650,7 @@ static int mcp25xxfd_chip_softreset(const struct mcp25xxfd_priv *priv)
 	return -ETIMEDOUT;
 }
 
-static int mcp25xxfd_chip_clock_init(const struct mcp25xxfd_priv *priv)
+static int mcp251xfd_chip_clock_init(const struct mcp251xfd_priv *priv)
 {
 	u32 osc;
 	int err;
@@ -659,10 +659,10 @@ static int mcp25xxfd_chip_clock_init(const struct mcp25xxfd_priv *priv)
 	 * works on the MCP2518FD. The MCP2517FD will go into normal
 	 * Sleep Mode instead.
 	 */
-	osc = MCP25XXFD_REG_OSC_LPMEN |
-		FIELD_PREP(MCP25XXFD_REG_OSC_CLKODIV_MASK,
-			   MCP25XXFD_REG_OSC_CLKODIV_10);
-	err = regmap_write(priv->map_reg, MCP25XXFD_REG_OSC, osc);
+	osc = MCP251XFD_REG_OSC_LPMEN |
+		FIELD_PREP(MCP251XFD_REG_OSC_CLKODIV_MASK,
+			   MCP251XFD_REG_OSC_CLKODIV_10);
+	err = regmap_write(priv->map_reg, MCP251XFD_REG_OSC, osc);
 	if (err)
 		return err;
 
@@ -671,11 +671,11 @@ static int mcp25xxfd_chip_clock_init(const struct mcp25xxfd_priv *priv)
 	 * This means an overflow of the 32 bit Time Base Counter
 	 * register at 40 MHz every 107 seconds.
 	 */
-	return regmap_write(priv->map_reg, MCP25XXFD_REG_TSCON,
-			    MCP25XXFD_REG_TSCON_TBCEN);
+	return regmap_write(priv->map_reg, MCP251XFD_REG_TSCON,
+			    MCP251XFD_REG_TSCON_TBCEN);
 }
 
-static int mcp25xxfd_set_bittiming(const struct mcp25xxfd_priv *priv)
+static int mcp251xfd_set_bittiming(const struct mcp251xfd_priv *priv)
 {
 	const struct can_bittiming *bt = &priv->can.bittiming;
 	const struct can_bittiming *dbt = &priv->can.data_bittiming;
@@ -699,32 +699,32 @@ static int mcp25xxfd_set_bittiming(const struct mcp25xxfd_priv *priv)
 	 * - protocol exception is treated as a form error
 	 * - Do not compare data bytes
 	 */
-	val = FIELD_PREP(MCP25XXFD_REG_CON_REQOP_MASK,
-			 MCP25XXFD_REG_CON_MODE_CONFIG) |
-		MCP25XXFD_REG_CON_STEF |
-		MCP25XXFD_REG_CON_ESIGM |
-		MCP25XXFD_REG_CON_RTXAT |
-		FIELD_PREP(MCP25XXFD_REG_CON_WFT_MASK,
-			   MCP25XXFD_REG_CON_WFT_T11FILTER) |
-		MCP25XXFD_REG_CON_WAKFIL |
-		MCP25XXFD_REG_CON_PXEDIS;
+	val = FIELD_PREP(MCP251XFD_REG_CON_REQOP_MASK,
+			 MCP251XFD_REG_CON_MODE_CONFIG) |
+		MCP251XFD_REG_CON_STEF |
+		MCP251XFD_REG_CON_ESIGM |
+		MCP251XFD_REG_CON_RTXAT |
+		FIELD_PREP(MCP251XFD_REG_CON_WFT_MASK,
+			   MCP251XFD_REG_CON_WFT_T11FILTER) |
+		MCP251XFD_REG_CON_WAKFIL |
+		MCP251XFD_REG_CON_PXEDIS;
 
 	if (!(priv->can.ctrlmode & CAN_CTRLMODE_FD_NON_ISO))
-		val |= MCP25XXFD_REG_CON_ISOCRCEN;
+		val |= MCP251XFD_REG_CON_ISOCRCEN;
 
-	err = regmap_write(priv->map_reg, MCP25XXFD_REG_CON, val);
+	err = regmap_write(priv->map_reg, MCP251XFD_REG_CON, val);
 	if (err)
 		return err;
 
 	/* Nominal Bit Time */
-	val = FIELD_PREP(MCP25XXFD_REG_NBTCFG_BRP_MASK, bt->brp - 1) |
-		FIELD_PREP(MCP25XXFD_REG_NBTCFG_TSEG1_MASK,
+	val = FIELD_PREP(MCP251XFD_REG_NBTCFG_BRP_MASK, bt->brp - 1) |
+		FIELD_PREP(MCP251XFD_REG_NBTCFG_TSEG1_MASK,
 			   bt->prop_seg + bt->phase_seg1 - 1) |
-		FIELD_PREP(MCP25XXFD_REG_NBTCFG_TSEG2_MASK,
+		FIELD_PREP(MCP251XFD_REG_NBTCFG_TSEG2_MASK,
 			   bt->phase_seg2 - 1) |
-		FIELD_PREP(MCP25XXFD_REG_NBTCFG_SJW_MASK, bt->sjw - 1);
+		FIELD_PREP(MCP251XFD_REG_NBTCFG_SJW_MASK, bt->sjw - 1);
 
-	err = regmap_write(priv->map_reg, MCP25XXFD_REG_NBTCFG, val);
+	err = regmap_write(priv->map_reg, MCP251XFD_REG_NBTCFG, val);
 	if (err)
 		return err;
 
@@ -732,28 +732,28 @@ static int mcp25xxfd_set_bittiming(const struct mcp25xxfd_priv *priv)
 		return 0;
 
 	/* Data Bit Time */
-	val = FIELD_PREP(MCP25XXFD_REG_DBTCFG_BRP_MASK, dbt->brp - 1) |
-		FIELD_PREP(MCP25XXFD_REG_DBTCFG_TSEG1_MASK,
+	val = FIELD_PREP(MCP251XFD_REG_DBTCFG_BRP_MASK, dbt->brp - 1) |
+		FIELD_PREP(MCP251XFD_REG_DBTCFG_TSEG1_MASK,
 			   dbt->prop_seg + dbt->phase_seg1 - 1) |
-		FIELD_PREP(MCP25XXFD_REG_DBTCFG_TSEG2_MASK,
+		FIELD_PREP(MCP251XFD_REG_DBTCFG_TSEG2_MASK,
 			   dbt->phase_seg2 - 1) |
-		FIELD_PREP(MCP25XXFD_REG_DBTCFG_SJW_MASK, dbt->sjw - 1);
+		FIELD_PREP(MCP251XFD_REG_DBTCFG_SJW_MASK, dbt->sjw - 1);
 
-	err = regmap_write(priv->map_reg, MCP25XXFD_REG_DBTCFG, val);
+	err = regmap_write(priv->map_reg, MCP251XFD_REG_DBTCFG, val);
 	if (err)
 		return err;
 
 	/* Transmitter Delay Compensation */
 	tdco = clamp_t(int, dbt->brp * (dbt->prop_seg + dbt->phase_seg1),
 		       -64, 63);
-	val = FIELD_PREP(MCP25XXFD_REG_TDC_TDCMOD_MASK,
-			 MCP25XXFD_REG_TDC_TDCMOD_AUTO) |
-		FIELD_PREP(MCP25XXFD_REG_TDC_TDCO_MASK, tdco);
+	val = FIELD_PREP(MCP251XFD_REG_TDC_TDCMOD_MASK,
+			 MCP251XFD_REG_TDC_TDCMOD_AUTO) |
+		FIELD_PREP(MCP251XFD_REG_TDC_TDCO_MASK, tdco);
 
-	return regmap_write(priv->map_reg, MCP25XXFD_REG_TDC, val);
+	return regmap_write(priv->map_reg, MCP251XFD_REG_TDC, val);
 }
 
-static int mcp25xxfd_chip_rx_int_enable(const struct mcp25xxfd_priv *priv)
+static int mcp251xfd_chip_rx_int_enable(const struct mcp251xfd_priv *priv)
 {
 	u32 val;
 
@@ -769,12 +769,12 @@ static int mcp25xxfd_chip_rx_int_enable(const struct mcp25xxfd_priv *priv)
 	 * (in the first byte of the SPI transfer) and configuring the
 	 * PIN as interrupt (in the last byte of the SPI transfer).
 	 */
-	val = MCP25XXFD_REG_IOCON_PM0 | MCP25XXFD_REG_IOCON_TRIS1 |
-		MCP25XXFD_REG_IOCON_TRIS0;
-	return regmap_write(priv->map_reg, MCP25XXFD_REG_IOCON, val);
+	val = MCP251XFD_REG_IOCON_PM0 | MCP251XFD_REG_IOCON_TRIS1 |
+		MCP251XFD_REG_IOCON_TRIS0;
+	return regmap_write(priv->map_reg, MCP251XFD_REG_IOCON, val);
 }
 
-static int mcp25xxfd_chip_rx_int_disable(const struct mcp25xxfd_priv *priv)
+static int mcp251xfd_chip_rx_int_disable(const struct mcp251xfd_priv *priv)
 {
 	u32 val;
 
@@ -785,14 +785,14 @@ static int mcp25xxfd_chip_rx_int_disable(const struct mcp25xxfd_priv *priv)
 	 * - PIN0: GPIO Input
 	 * - PIN1: GPIO Input
 	 */
-	val = MCP25XXFD_REG_IOCON_PM1 | MCP25XXFD_REG_IOCON_PM0 |
-		MCP25XXFD_REG_IOCON_TRIS1 | MCP25XXFD_REG_IOCON_TRIS0;
-	return regmap_write(priv->map_reg, MCP25XXFD_REG_IOCON, val);
+	val = MCP251XFD_REG_IOCON_PM1 | MCP251XFD_REG_IOCON_PM0 |
+		MCP251XFD_REG_IOCON_TRIS1 | MCP251XFD_REG_IOCON_TRIS0;
+	return regmap_write(priv->map_reg, MCP251XFD_REG_IOCON, val);
 }
 
 static int
-mcp25xxfd_chip_rx_fifo_init_one(const struct mcp25xxfd_priv *priv,
-				const struct mcp25xxfd_rx_ring *ring)
+mcp251xfd_chip_rx_fifo_init_one(const struct mcp251xfd_priv *priv,
+				const struct mcp251xfd_rx_ring *ring)
 {
 	u32 fifo_con;
 
@@ -802,89 +802,89 @@ mcp25xxfd_chip_rx_fifo_init_one(const struct mcp25xxfd_priv *priv,
 	 * generate a RXOVIF, use this to properly detect RX MAB
 	 * overflows.
 	 */
-	fifo_con = FIELD_PREP(MCP25XXFD_REG_FIFOCON_FSIZE_MASK,
+	fifo_con = FIELD_PREP(MCP251XFD_REG_FIFOCON_FSIZE_MASK,
 			      ring->obj_num - 1) |
-		MCP25XXFD_REG_FIFOCON_RXTSEN |
-		MCP25XXFD_REG_FIFOCON_RXOVIE |
-		MCP25XXFD_REG_FIFOCON_TFNRFNIE;
+		MCP251XFD_REG_FIFOCON_RXTSEN |
+		MCP251XFD_REG_FIFOCON_RXOVIE |
+		MCP251XFD_REG_FIFOCON_TFNRFNIE;
 
 	if (priv->can.ctrlmode & (CAN_CTRLMODE_LISTENONLY | CAN_CTRLMODE_FD))
-		fifo_con |= FIELD_PREP(MCP25XXFD_REG_FIFOCON_PLSIZE_MASK,
-				       MCP25XXFD_REG_FIFOCON_PLSIZE_64);
+		fifo_con |= FIELD_PREP(MCP251XFD_REG_FIFOCON_PLSIZE_MASK,
+				       MCP251XFD_REG_FIFOCON_PLSIZE_64);
 	else
-		fifo_con |= FIELD_PREP(MCP25XXFD_REG_FIFOCON_PLSIZE_MASK,
-				       MCP25XXFD_REG_FIFOCON_PLSIZE_8);
+		fifo_con |= FIELD_PREP(MCP251XFD_REG_FIFOCON_PLSIZE_MASK,
+				       MCP251XFD_REG_FIFOCON_PLSIZE_8);
 
 	return regmap_write(priv->map_reg,
-			    MCP25XXFD_REG_FIFOCON(ring->fifo_nr), fifo_con);
+			    MCP251XFD_REG_FIFOCON(ring->fifo_nr), fifo_con);
 }
 
 static int
-mcp25xxfd_chip_rx_filter_init_one(const struct mcp25xxfd_priv *priv,
-				  const struct mcp25xxfd_rx_ring *ring)
+mcp251xfd_chip_rx_filter_init_one(const struct mcp251xfd_priv *priv,
+				  const struct mcp251xfd_rx_ring *ring)
 {
 	u32 fltcon;
 
-	fltcon = MCP25XXFD_REG_FLTCON_FLTEN(ring->nr) |
-		MCP25XXFD_REG_FLTCON_FBP(ring->nr, ring->fifo_nr);
+	fltcon = MCP251XFD_REG_FLTCON_FLTEN(ring->nr) |
+		MCP251XFD_REG_FLTCON_FBP(ring->nr, ring->fifo_nr);
 
 	return regmap_update_bits(priv->map_reg,
-				  MCP25XXFD_REG_FLTCON(ring->nr >> 2),
-				  MCP25XXFD_REG_FLTCON_FLT_MASK(ring->nr),
+				  MCP251XFD_REG_FLTCON(ring->nr >> 2),
+				  MCP251XFD_REG_FLTCON_FLT_MASK(ring->nr),
 				  fltcon);
 }
 
-static int mcp25xxfd_chip_fifo_init(const struct mcp25xxfd_priv *priv)
+static int mcp251xfd_chip_fifo_init(const struct mcp251xfd_priv *priv)
 {
-	const struct mcp25xxfd_tx_ring *tx_ring = priv->tx;
-	const struct mcp25xxfd_rx_ring *rx_ring;
+	const struct mcp251xfd_tx_ring *tx_ring = priv->tx;
+	const struct mcp251xfd_rx_ring *rx_ring;
 	u32 val;
 	int err, n;
 
 	/* TEF */
-	val = FIELD_PREP(MCP25XXFD_REG_TEFCON_FSIZE_MASK,
+	val = FIELD_PREP(MCP251XFD_REG_TEFCON_FSIZE_MASK,
 			 tx_ring->obj_num - 1) |
-		MCP25XXFD_REG_TEFCON_TEFTSEN |
-		MCP25XXFD_REG_TEFCON_TEFOVIE |
-		MCP25XXFD_REG_TEFCON_TEFNEIE;
+		MCP251XFD_REG_TEFCON_TEFTSEN |
+		MCP251XFD_REG_TEFCON_TEFOVIE |
+		MCP251XFD_REG_TEFCON_TEFNEIE;
 
-	err = regmap_write(priv->map_reg, MCP25XXFD_REG_TEFCON, val);
+	err = regmap_write(priv->map_reg, MCP251XFD_REG_TEFCON, val);
 	if (err)
 		return err;
 
 	/* FIFO 1 - TX */
-	val = FIELD_PREP(MCP25XXFD_REG_FIFOCON_FSIZE_MASK,
+	val = FIELD_PREP(MCP251XFD_REG_FIFOCON_FSIZE_MASK,
 			 tx_ring->obj_num - 1) |
-		MCP25XXFD_REG_FIFOCON_TXEN |
-		MCP25XXFD_REG_FIFOCON_TXATIE;
+		MCP251XFD_REG_FIFOCON_TXEN |
+		MCP251XFD_REG_FIFOCON_TXATIE;
 
 	if (priv->can.ctrlmode & (CAN_CTRLMODE_LISTENONLY | CAN_CTRLMODE_FD))
-		val |= FIELD_PREP(MCP25XXFD_REG_FIFOCON_PLSIZE_MASK,
-				  MCP25XXFD_REG_FIFOCON_PLSIZE_64);
+		val |= FIELD_PREP(MCP251XFD_REG_FIFOCON_PLSIZE_MASK,
+				  MCP251XFD_REG_FIFOCON_PLSIZE_64);
 	else
-		val |= FIELD_PREP(MCP25XXFD_REG_FIFOCON_PLSIZE_MASK,
-				  MCP25XXFD_REG_FIFOCON_PLSIZE_8);
+		val |= FIELD_PREP(MCP251XFD_REG_FIFOCON_PLSIZE_MASK,
+				  MCP251XFD_REG_FIFOCON_PLSIZE_8);
 
 	if (priv->can.ctrlmode & CAN_CTRLMODE_ONE_SHOT)
-		val |= FIELD_PREP(MCP25XXFD_REG_FIFOCON_TXAT_MASK,
-				  MCP25XXFD_REG_FIFOCON_TXAT_ONE_SHOT);
+		val |= FIELD_PREP(MCP251XFD_REG_FIFOCON_TXAT_MASK,
+				  MCP251XFD_REG_FIFOCON_TXAT_ONE_SHOT);
 	else
-		val |= FIELD_PREP(MCP25XXFD_REG_FIFOCON_TXAT_MASK,
-				  MCP25XXFD_REG_FIFOCON_TXAT_UNLIMITED);
+		val |= FIELD_PREP(MCP251XFD_REG_FIFOCON_TXAT_MASK,
+				  MCP251XFD_REG_FIFOCON_TXAT_UNLIMITED);
 
 	err = regmap_write(priv->map_reg,
-			   MCP25XXFD_REG_FIFOCON(MCP25XXFD_TX_FIFO),
+			   MCP251XFD_REG_FIFOCON(MCP251XFD_TX_FIFO),
 			   val);
 	if (err)
 		return err;
 
 	/* RX FIFOs */
-	mcp25xxfd_for_each_rx_ring(priv, rx_ring, n) {
-		err = mcp25xxfd_chip_rx_fifo_init_one(priv, rx_ring);
+	mcp251xfd_for_each_rx_ring(priv, rx_ring, n) {
+		err = mcp251xfd_chip_rx_fifo_init_one(priv, rx_ring);
 		if (err)
 			return err;
 
-		err = mcp25xxfd_chip_rx_filter_init_one(priv, rx_ring);
+		err = mcp251xfd_chip_rx_filter_init_one(priv, rx_ring);
 		if (err)
 			return err;
 	}
@@ -892,195 +892,195 @@ static int mcp25xxfd_chip_fifo_init(const struct mcp25xxfd_priv *priv)
 	return 0;
 }
 
-static int mcp25xxfd_chip_ecc_init(struct mcp25xxfd_priv *priv)
+static int mcp251xfd_chip_ecc_init(struct mcp251xfd_priv *priv)
 {
-	struct mcp25xxfd_ecc *ecc = &priv->ecc;
+	struct mcp251xfd_ecc *ecc = &priv->ecc;
 	void *ram;
 	u32 val = 0;
 	int err;
 
 	ecc->ecc_stat = 0;
 
-	if (priv->devtype_data.quirks & MCP25XXFD_QUIRK_ECC)
-		val = MCP25XXFD_REG_ECCCON_ECCEN;
+	if (priv->devtype_data.quirks & MCP251XFD_QUIRK_ECC)
+		val = MCP251XFD_REG_ECCCON_ECCEN;
 
-	err = regmap_update_bits(priv->map_reg, MCP25XXFD_REG_ECCCON,
-				 MCP25XXFD_REG_ECCCON_ECCEN, val);
+	err = regmap_update_bits(priv->map_reg, MCP251XFD_REG_ECCCON,
+				 MCP251XFD_REG_ECCCON_ECCEN, val);
 	if (err)
 		return err;
 
-	ram = kzalloc(MCP25XXFD_RAM_SIZE, GFP_KERNEL);
+	ram = kzalloc(MCP251XFD_RAM_SIZE, GFP_KERNEL);
 	if (!ram)
 		return -ENOMEM;
 
-	err = regmap_raw_write(priv->map_reg, MCP25XXFD_RAM_START, ram,
-			       MCP25XXFD_RAM_SIZE);
+	err = regmap_raw_write(priv->map_reg, MCP251XFD_RAM_START, ram,
+			       MCP251XFD_RAM_SIZE);
 	kfree(ram);
 
 	return err;
 }
 
-static inline void mcp25xxfd_ecc_tefif_successful(struct mcp25xxfd_priv *priv)
+static inline void mcp251xfd_ecc_tefif_successful(struct mcp251xfd_priv *priv)
 {
-	struct mcp25xxfd_ecc *ecc = &priv->ecc;
+	struct mcp251xfd_ecc *ecc = &priv->ecc;
 
 	ecc->ecc_stat = 0;
 }
 
-static u8 mcp25xxfd_get_normal_mode(const struct mcp25xxfd_priv *priv)
+static u8 mcp251xfd_get_normal_mode(const struct mcp251xfd_priv *priv)
 {
 	u8 mode;
 
 	if (priv->can.ctrlmode & CAN_CTRLMODE_LISTENONLY)
-		mode = MCP25XXFD_REG_CON_MODE_LISTENONLY;
+		mode = MCP251XFD_REG_CON_MODE_LISTENONLY;
 	else if (priv->can.ctrlmode & CAN_CTRLMODE_FD)
-		mode = MCP25XXFD_REG_CON_MODE_MIXED;
+		mode = MCP251XFD_REG_CON_MODE_MIXED;
 	else
-		mode = MCP25XXFD_REG_CON_MODE_CAN2_0;
+		mode = MCP251XFD_REG_CON_MODE_CAN2_0;
 
 	return mode;
 }
 
 static int
-__mcp25xxfd_chip_set_normal_mode(const struct mcp25xxfd_priv *priv,
+__mcp251xfd_chip_set_normal_mode(const struct mcp251xfd_priv *priv,
 				 bool nowait)
 {
 	u8 mode;
 
-	mode = mcp25xxfd_get_normal_mode(priv);
+	mode = mcp251xfd_get_normal_mode(priv);
 
-	return __mcp25xxfd_chip_set_mode(priv, mode, nowait);
+	return __mcp251xfd_chip_set_mode(priv, mode, nowait);
 }
 
 static inline int
-mcp25xxfd_chip_set_normal_mode(const struct mcp25xxfd_priv *priv)
+mcp251xfd_chip_set_normal_mode(const struct mcp251xfd_priv *priv)
 {
-	return __mcp25xxfd_chip_set_normal_mode(priv, false);
+	return __mcp251xfd_chip_set_normal_mode(priv, false);
 }
 
 static inline int
-mcp25xxfd_chip_set_normal_mode_nowait(const struct mcp25xxfd_priv *priv)
+mcp251xfd_chip_set_normal_mode_nowait(const struct mcp251xfd_priv *priv)
 {
-	return __mcp25xxfd_chip_set_normal_mode(priv, true);
+	return __mcp251xfd_chip_set_normal_mode(priv, true);
 }
 
-static int mcp25xxfd_chip_interrupts_enable(const struct mcp25xxfd_priv *priv)
+static int mcp251xfd_chip_interrupts_enable(const struct mcp251xfd_priv *priv)
 {
 	u32 val;
 	int err;
 
-	val = MCP25XXFD_REG_CRC_FERRIE | MCP25XXFD_REG_CRC_CRCERRIE;
-	err = regmap_write(priv->map_reg, MCP25XXFD_REG_CRC, val);
+	val = MCP251XFD_REG_CRC_FERRIE | MCP251XFD_REG_CRC_CRCERRIE;
+	err = regmap_write(priv->map_reg, MCP251XFD_REG_CRC, val);
 	if (err)
 		return err;
 
-	val = MCP25XXFD_REG_ECCCON_DEDIE | MCP25XXFD_REG_ECCCON_SECIE;
-	err = regmap_update_bits(priv->map_reg, MCP25XXFD_REG_ECCCON, val, val);
+	val = MCP251XFD_REG_ECCCON_DEDIE | MCP251XFD_REG_ECCCON_SECIE;
+	err = regmap_update_bits(priv->map_reg, MCP251XFD_REG_ECCCON, val, val);
 	if (err)
 		return err;
 
-	val = MCP25XXFD_REG_INT_CERRIE |
-		MCP25XXFD_REG_INT_SERRIE |
-		MCP25XXFD_REG_INT_RXOVIE |
-		MCP25XXFD_REG_INT_TXATIE |
-		MCP25XXFD_REG_INT_SPICRCIE |
-		MCP25XXFD_REG_INT_ECCIE |
-		MCP25XXFD_REG_INT_TEFIE |
-		MCP25XXFD_REG_INT_MODIE |
-		MCP25XXFD_REG_INT_RXIE;
+	val = MCP251XFD_REG_INT_CERRIE |
+		MCP251XFD_REG_INT_SERRIE |
+		MCP251XFD_REG_INT_RXOVIE |
+		MCP251XFD_REG_INT_TXATIE |
+		MCP251XFD_REG_INT_SPICRCIE |
+		MCP251XFD_REG_INT_ECCIE |
+		MCP251XFD_REG_INT_TEFIE |
+		MCP251XFD_REG_INT_MODIE |
+		MCP251XFD_REG_INT_RXIE;
 
 	if (priv->can.ctrlmode & CAN_CTRLMODE_BERR_REPORTING)
-		val |= MCP25XXFD_REG_INT_IVMIE;
+		val |= MCP251XFD_REG_INT_IVMIE;
 
-	return regmap_write(priv->map_reg, MCP25XXFD_REG_INT, val);
+	return regmap_write(priv->map_reg, MCP251XFD_REG_INT, val);
 }
 
-static int mcp25xxfd_chip_interrupts_disable(const struct mcp25xxfd_priv *priv)
+static int mcp251xfd_chip_interrupts_disable(const struct mcp251xfd_priv *priv)
 {
 	int err;
 	u32 mask;
 
-	err = regmap_write(priv->map_reg, MCP25XXFD_REG_INT, 0);
+	err = regmap_write(priv->map_reg, MCP251XFD_REG_INT, 0);
 	if (err)
 		return err;
 
-	mask = MCP25XXFD_REG_ECCCON_DEDIE | MCP25XXFD_REG_ECCCON_SECIE;
-	err = regmap_update_bits(priv->map_reg, MCP25XXFD_REG_ECCCON,
+	mask = MCP251XFD_REG_ECCCON_DEDIE | MCP251XFD_REG_ECCCON_SECIE;
+	err = regmap_update_bits(priv->map_reg, MCP251XFD_REG_ECCCON,
 				 mask, 0x0);
 	if (err)
 		return err;
 
-	return regmap_write(priv->map_reg, MCP25XXFD_REG_CRC, 0);
+	return regmap_write(priv->map_reg, MCP251XFD_REG_CRC, 0);
 }
 
-static int mcp25xxfd_chip_stop(struct mcp25xxfd_priv *priv,
+static int mcp251xfd_chip_stop(struct mcp251xfd_priv *priv,
 			       const enum can_state state)
 {
 	priv->can.state = state;
 
-	mcp25xxfd_chip_interrupts_disable(priv);
-	mcp25xxfd_chip_rx_int_disable(priv);
-	return mcp25xxfd_chip_set_mode(priv, MCP25XXFD_REG_CON_MODE_SLEEP);
+	mcp251xfd_chip_interrupts_disable(priv);
+	mcp251xfd_chip_rx_int_disable(priv);
+	return mcp251xfd_chip_set_mode(priv, MCP251XFD_REG_CON_MODE_SLEEP);
 }
 
-static int mcp25xxfd_chip_start(struct mcp25xxfd_priv *priv)
+static int mcp251xfd_chip_start(struct mcp251xfd_priv *priv)
 {
 	int err;
 
-	err = mcp25xxfd_chip_softreset(priv);
+	err = mcp251xfd_chip_softreset(priv);
 	if (err)
 		goto out_chip_stop;
 
-	err = mcp25xxfd_chip_clock_init(priv);
+	err = mcp251xfd_chip_clock_init(priv);
 	if (err)
 		goto out_chip_stop;
 
-	err = mcp25xxfd_set_bittiming(priv);
+	err = mcp251xfd_set_bittiming(priv);
 	if (err)
 		goto out_chip_stop;
 
-	err = mcp25xxfd_chip_rx_int_enable(priv);
+	err = mcp251xfd_chip_rx_int_enable(priv);
 	if (err)
 		return err;
 
-	err = mcp25xxfd_chip_ecc_init(priv);
+	err = mcp251xfd_chip_ecc_init(priv);
 	if (err)
 		goto out_chip_stop;
 
-	mcp25xxfd_ring_init(priv);
+	mcp251xfd_ring_init(priv);
 
-	err = mcp25xxfd_chip_fifo_init(priv);
+	err = mcp251xfd_chip_fifo_init(priv);
 	if (err)
 		goto out_chip_stop;
 
 	priv->can.state = CAN_STATE_ERROR_ACTIVE;
 
-	err = mcp25xxfd_chip_set_normal_mode(priv);
+	err = mcp251xfd_chip_set_normal_mode(priv);
 	if (err)
 		goto out_chip_stop;
 
 	return 0;
 
  out_chip_stop:
-	mcp25xxfd_chip_stop(priv, CAN_STATE_STOPPED);
+	mcp251xfd_chip_stop(priv, CAN_STATE_STOPPED);
 
 	return err;
 }
 
-static int mcp25xxfd_set_mode(struct net_device *ndev, enum can_mode mode)
+static int mcp251xfd_set_mode(struct net_device *ndev, enum can_mode mode)
 {
-	struct mcp25xxfd_priv *priv = netdev_priv(ndev);
+	struct mcp251xfd_priv *priv = netdev_priv(ndev);
 	int err;
 
 	switch (mode) {
 	case CAN_MODE_START:
-		err = mcp25xxfd_chip_start(priv);
+		err = mcp251xfd_chip_start(priv);
 		if (err)
 			return err;
 
-		err = mcp25xxfd_chip_interrupts_enable(priv);
+		err = mcp251xfd_chip_interrupts_enable(priv);
 		if (err) {
-			mcp25xxfd_chip_stop(priv, CAN_STATE_STOPPED);
+			mcp251xfd_chip_stop(priv, CAN_STATE_STOPPED);
 			return err;
 		}
 
@@ -1094,30 +1094,30 @@ static int mcp25xxfd_set_mode(struct net_device *ndev, enum can_mode mode)
 	return 0;
 }
 
-static int __mcp25xxfd_get_berr_counter(const struct net_device *ndev,
+static int __mcp251xfd_get_berr_counter(const struct net_device *ndev,
 					struct can_berr_counter *bec)
 {
-	const struct mcp25xxfd_priv *priv = netdev_priv(ndev);
+	const struct mcp251xfd_priv *priv = netdev_priv(ndev);
 	u32 trec;
 	int err;
 
-	err = regmap_read(priv->map_reg, MCP25XXFD_REG_TREC, &trec);
+	err = regmap_read(priv->map_reg, MCP251XFD_REG_TREC, &trec);
 	if (err)
 		return err;
 
-	if (trec & MCP25XXFD_REG_TREC_TXBO)
+	if (trec & MCP251XFD_REG_TREC_TXBO)
 		bec->txerr = 256;
 	else
-		bec->txerr = FIELD_GET(MCP25XXFD_REG_TREC_TEC_MASK, trec);
-	bec->rxerr = FIELD_GET(MCP25XXFD_REG_TREC_REC_MASK, trec);
+		bec->txerr = FIELD_GET(MCP251XFD_REG_TREC_TEC_MASK, trec);
+	bec->rxerr = FIELD_GET(MCP251XFD_REG_TREC_REC_MASK, trec);
 
 	return 0;
 }
 
-static int mcp25xxfd_get_berr_counter(const struct net_device *ndev,
+static int mcp251xfd_get_berr_counter(const struct net_device *ndev,
 				      struct can_berr_counter *bec)
 {
-	const struct mcp25xxfd_priv *priv = netdev_priv(ndev);
+	const struct mcp251xfd_priv *priv = netdev_priv(ndev);
 
 	/* Avoid waking up the controller if the interface is down */
 	if (!(ndev->flags & IFF_UP))
@@ -1131,22 +1131,22 @@ static int mcp25xxfd_get_berr_counter(const struct net_device *ndev,
 		return 0;
 	}
 
-	return __mcp25xxfd_get_berr_counter(ndev, bec);
+	return __mcp251xfd_get_berr_counter(ndev, bec);
 }
 
-static int mcp25xxfd_check_tef_tail(const struct mcp25xxfd_priv *priv)
+static int mcp251xfd_check_tef_tail(const struct mcp251xfd_priv *priv)
 {
 	u8 tef_tail_chip, tef_tail;
 	int err;
 
-	if (!IS_ENABLED(CONFIG_CAN_MCP25XXFD_SANITY))
+	if (!IS_ENABLED(CONFIG_CAN_MCP251XFD_SANITY))
 		return 0;
 
-	err = mcp25xxfd_tef_tail_get_from_chip(priv, &tef_tail_chip);
+	err = mcp251xfd_tef_tail_get_from_chip(priv, &tef_tail_chip);
 	if (err)
 		return err;
 
-	tef_tail = mcp25xxfd_get_tef_tail(priv);
+	tef_tail = mcp251xfd_get_tef_tail(priv);
 	if (tef_tail_chip != tef_tail) {
 		netdev_err(priv->ndev,
 			   "TEF tail of chip (0x%02x) and ours (0x%08x) inconsistent.\n",
@@ -1158,20 +1158,20 @@ static int mcp25xxfd_check_tef_tail(const struct mcp25xxfd_priv *priv)
 }
 
 static int
-mcp25xxfd_check_rx_tail(const struct mcp25xxfd_priv *priv,
-			const struct mcp25xxfd_rx_ring *ring)
+mcp251xfd_check_rx_tail(const struct mcp251xfd_priv *priv,
+			const struct mcp251xfd_rx_ring *ring)
 {
 	u8 rx_tail_chip, rx_tail;
 	int err;
 
-	if (!IS_ENABLED(CONFIG_CAN_MCP25XXFD_SANITY))
+	if (!IS_ENABLED(CONFIG_CAN_MCP251XFD_SANITY))
 		return 0;
 
-	err = mcp25xxfd_rx_tail_get_from_chip(priv, ring, &rx_tail_chip);
+	err = mcp251xfd_rx_tail_get_from_chip(priv, ring, &rx_tail_chip);
 	if (err)
 		return err;
 
-	rx_tail = mcp25xxfd_get_rx_tail(ring);
+	rx_tail = mcp251xfd_get_rx_tail(ring);
 	if (rx_tail_chip != rx_tail) {
 		netdev_err(priv->ndev,
 			   "RX tail of chip (%d) and ours (%d) inconsistent.\n",
@@ -1183,17 +1183,17 @@ mcp25xxfd_check_rx_tail(const struct mcp25xxfd_priv *priv,
 }
 
 static int
-mcp25xxfd_handle_tefif_recover(const struct mcp25xxfd_priv *priv, const u32 seq)
+mcp251xfd_handle_tefif_recover(const struct mcp251xfd_priv *priv, const u32 seq)
 {
-	const struct mcp25xxfd_tx_ring *tx_ring = priv->tx;
+	const struct mcp251xfd_tx_ring *tx_ring = priv->tx;
 	u32 tef_sta;
 	int err;
 
-	err = regmap_read(priv->map_reg, MCP25XXFD_REG_TEFSTA, &tef_sta);
+	err = regmap_read(priv->map_reg, MCP251XFD_REG_TEFSTA, &tef_sta);
 	if (err)
 		return err;
 
-	if (tef_sta & MCP25XXFD_REG_TEFSTA_TEFOVIF) {
+	if (tef_sta & MCP251XFD_REG_TEFSTA_TEFOVIF) {
 		netdev_err(priv->ndev,
 			   "Transmit Event FIFO buffer overflow.\n");
 		return -ENOBUFS;
@@ -1201,8 +1201,8 @@ mcp25xxfd_handle_tefif_recover(const struct mcp25xxfd_priv *priv, const u32 seq)
 
 	netdev_info(priv->ndev,
 		    "Transmit Event FIFO buffer %s. (seq=0x%08x, tef_tail=0x%08x, tef_head=0x%08x, tx_head=0x%08x)\n",
-		    tef_sta & MCP25XXFD_REG_TEFSTA_TEFFIF ?
-		    "full" : tef_sta & MCP25XXFD_REG_TEFSTA_TEFNEIF ?
+		    tef_sta & MCP251XFD_REG_TEFSTA_TEFFIF ?
+		    "full" : tef_sta & MCP251XFD_REG_TEFSTA_TEFNEIF ?
 		    "not empty" : "empty",
 		    seq, priv->tef.tail, priv->tef.head, tx_ring->head);
 
@@ -1211,15 +1211,15 @@ mcp25xxfd_handle_tefif_recover(const struct mcp25xxfd_priv *priv, const u32 seq)
 }
 
 static int
-mcp25xxfd_handle_tefif_one(struct mcp25xxfd_priv *priv,
-			   const struct mcp25xxfd_hw_tef_obj *hw_tef_obj)
+mcp251xfd_handle_tefif_one(struct mcp251xfd_priv *priv,
+			   const struct mcp251xfd_hw_tef_obj *hw_tef_obj)
 {
-	struct mcp25xxfd_tx_ring *tx_ring = priv->tx;
+	struct mcp251xfd_tx_ring *tx_ring = priv->tx;
 	struct net_device_stats *stats = &priv->ndev->stats;
 	u32 seq, seq_masked, tef_tail_masked;
 	int err;
 
-	seq = FIELD_GET(MCP25XXFD_OBJ_FLAGS_SEQ_MCP2518FD_MASK,
+	seq = FIELD_GET(MCP251XFD_OBJ_FLAGS_SEQ_MCP2518FD_MASK,
 			hw_tef_obj->flags);
 
 	/* Use the MCP2517FD mask on the MCP2518FD, too. We only
@@ -1227,39 +1227,39 @@ mcp25xxfd_handle_tefif_one(struct mcp25xxfd_priv *priv,
 	 * net-yet-completed, i.e. old TEF objects.
 	 */
 	seq_masked = seq &
-		field_mask(MCP25XXFD_OBJ_FLAGS_SEQ_MCP2517FD_MASK);
+		field_mask(MCP251XFD_OBJ_FLAGS_SEQ_MCP2517FD_MASK);
 	tef_tail_masked = priv->tef.tail &
-		field_mask(MCP25XXFD_OBJ_FLAGS_SEQ_MCP2517FD_MASK);
+		field_mask(MCP251XFD_OBJ_FLAGS_SEQ_MCP2517FD_MASK);
 	if (seq_masked != tef_tail_masked)
-		return mcp25xxfd_handle_tefif_recover(priv, seq);
+		return mcp251xfd_handle_tefif_recover(priv, seq);
 
 	stats->tx_bytes +=
 		can_rx_offload_get_echo_skb(&priv->offload,
-					    mcp25xxfd_get_tef_tail(priv),
+					    mcp251xfd_get_tef_tail(priv),
 					    hw_tef_obj->ts);
 	stats->tx_packets++;
 
 	/* finally increment the TEF pointer */
-	err = regmap_update_bits(priv->map_reg, MCP25XXFD_REG_TEFCON,
+	err = regmap_update_bits(priv->map_reg, MCP251XFD_REG_TEFCON,
 				 GENMASK(15, 8),
-				 MCP25XXFD_REG_TEFCON_UINC);
+				 MCP251XFD_REG_TEFCON_UINC);
 	if (err)
 		return err;
 
 	priv->tef.tail++;
 	tx_ring->tail++;
 
-	return mcp25xxfd_check_tef_tail(priv);
+	return mcp251xfd_check_tef_tail(priv);
 }
 
-static int mcp25xxfd_tef_ring_update(struct mcp25xxfd_priv *priv)
+static int mcp251xfd_tef_ring_update(struct mcp251xfd_priv *priv)
 {
-	const struct mcp25xxfd_tx_ring *tx_ring = priv->tx;
+	const struct mcp251xfd_tx_ring *tx_ring = priv->tx;
 	unsigned int new_head;
 	u8 chip_tx_tail;
 	int err;
 
-	err = mcp25xxfd_tx_tail_get_from_chip(priv, &chip_tx_tail);
+	err = mcp251xfd_tx_tail_get_from_chip(priv, &chip_tx_tail);
 	if (err)
 		return err;
 
@@ -1273,17 +1273,17 @@ static int mcp25xxfd_tef_ring_update(struct mcp25xxfd_priv *priv)
 	/* ... but it cannot exceed the TX head. */
 	priv->tef.head = min(new_head, tx_ring->head);
 
-	return mcp25xxfd_check_tef_tail(priv);
+	return mcp251xfd_check_tef_tail(priv);
 }
 
 static inline int
-mcp25xxfd_tef_obj_read(const struct mcp25xxfd_priv *priv,
-		       struct mcp25xxfd_hw_tef_obj *hw_tef_obj,
+mcp251xfd_tef_obj_read(const struct mcp251xfd_priv *priv,
+		       struct mcp251xfd_hw_tef_obj *hw_tef_obj,
 		       const u8 offset, const u8 len)
 {
-	const struct mcp25xxfd_tx_ring *tx_ring = priv->tx;
+	const struct mcp251xfd_tx_ring *tx_ring = priv->tx;
 
-	if (IS_ENABLED(CONFIG_CAN_MCP25XXFD_SANITY) &&
+	if (IS_ENABLED(CONFIG_CAN_MCP251XFD_SANITY) &&
 	    (offset > tx_ring->obj_num ||
 	     len > tx_ring->obj_num ||
 	     offset + len > tx_ring->obj_num)) {
@@ -1294,36 +1294,36 @@ mcp25xxfd_tef_obj_read(const struct mcp25xxfd_priv *priv,
 	}
 
 	return regmap_bulk_read(priv->map_rx,
-				mcp25xxfd_get_tef_obj_addr(offset),
+				mcp251xfd_get_tef_obj_addr(offset),
 				hw_tef_obj,
 				sizeof(*hw_tef_obj) / sizeof(u32) * len);
 }
 
-static int mcp25xxfd_handle_tefif(struct mcp25xxfd_priv *priv)
+static int mcp251xfd_handle_tefif(struct mcp251xfd_priv *priv)
 {
-	struct mcp25xxfd_hw_tef_obj hw_tef_obj[MCP25XXFD_TX_OBJ_NUM_MAX];
+	struct mcp251xfd_hw_tef_obj hw_tef_obj[MCP251XFD_TX_OBJ_NUM_MAX];
 	u8 tef_tail, len, l;
 	int err, i;
 
-	err = mcp25xxfd_tef_ring_update(priv);
+	err = mcp251xfd_tef_ring_update(priv);
 	if (err)
 		return err;
 
-	tef_tail = mcp25xxfd_get_tef_tail(priv);
-	len = mcp25xxfd_get_tef_len(priv);
-	l = mcp25xxfd_get_tef_linear_len(priv);
-	err = mcp25xxfd_tef_obj_read(priv, hw_tef_obj, tef_tail, l);
+	tef_tail = mcp251xfd_get_tef_tail(priv);
+	len = mcp251xfd_get_tef_len(priv);
+	l = mcp251xfd_get_tef_linear_len(priv);
+	err = mcp251xfd_tef_obj_read(priv, hw_tef_obj, tef_tail, l);
 	if (err)
 		return err;
 
 	if (l < len) {
-		err = mcp25xxfd_tef_obj_read(priv, &hw_tef_obj[l], 0, len - l);
+		err = mcp251xfd_tef_obj_read(priv, &hw_tef_obj[l], 0, len - l);
 		if (err)
 			return err;
 	}
 
 	for (i = 0; i < len; i++) {
-		err = mcp25xxfd_handle_tefif_one(priv, &hw_tef_obj[i]);
+		err = mcp251xfd_handle_tefif_one(priv, &hw_tef_obj[i]);
 		/* -EAGAIN means the Sequence Number in the TEF
 		 * doesn't match our tef_tail. This can happen if we
 		 * read the TEF objects too early. Leave loop let the
@@ -1336,9 +1336,9 @@ static int mcp25xxfd_handle_tefif(struct mcp25xxfd_priv *priv)
 	}
 
  out_netif_wake_queue:
-	mcp25xxfd_ecc_tefif_successful(priv);
+	mcp251xfd_ecc_tefif_successful(priv);
 
-	if (mcp25xxfd_get_tx_free(priv->tx)) {
+	if (mcp251xfd_get_tx_free(priv->tx)) {
 		/* Make sure that anybody stopping the queue after
 		 * this sees the new tx_ring->tail.
 		 */
@@ -1350,14 +1350,14 @@ static int mcp25xxfd_handle_tefif(struct mcp25xxfd_priv *priv)
 }
 
 static int
-mcp25xxfd_rx_ring_update(const struct mcp25xxfd_priv *priv,
-			 struct mcp25xxfd_rx_ring *ring)
+mcp251xfd_rx_ring_update(const struct mcp251xfd_priv *priv,
+			 struct mcp251xfd_rx_ring *ring)
 {
 	u32 new_head;
 	u8 chip_rx_head;
 	int err;
 
-	err = mcp25xxfd_rx_head_get_from_chip(priv, ring, &chip_rx_head);
+	err = mcp251xfd_rx_head_get_from_chip(priv, ring, &chip_rx_head);
 	if (err)
 		return err;
 
@@ -1370,47 +1370,47 @@ mcp25xxfd_rx_ring_update(const struct mcp25xxfd_priv *priv,
 
 	ring->head = new_head;
 
-	return mcp25xxfd_check_rx_tail(priv, ring);
+	return mcp251xfd_check_rx_tail(priv, ring);
 }
 
 static void
-mcp25xxfd_hw_rx_obj_to_skb(const struct mcp25xxfd_priv *priv,
-			   const struct mcp25xxfd_hw_rx_obj_canfd *hw_rx_obj,
+mcp251xfd_hw_rx_obj_to_skb(const struct mcp251xfd_priv *priv,
+			   const struct mcp251xfd_hw_rx_obj_canfd *hw_rx_obj,
 			   struct sk_buff *skb)
 {
 	struct canfd_frame *cfd = (struct canfd_frame *)skb->data;
 
-	if (hw_rx_obj->flags & MCP25XXFD_OBJ_FLAGS_IDE) {
+	if (hw_rx_obj->flags & MCP251XFD_OBJ_FLAGS_IDE) {
 		u32 sid, eid;
 
-		eid = FIELD_GET(MCP25XXFD_OBJ_ID_EID_MASK, hw_rx_obj->id);
-		sid = FIELD_GET(MCP25XXFD_OBJ_ID_SID_MASK, hw_rx_obj->id);
+		eid = FIELD_GET(MCP251XFD_OBJ_ID_EID_MASK, hw_rx_obj->id);
+		sid = FIELD_GET(MCP251XFD_OBJ_ID_SID_MASK, hw_rx_obj->id);
 
 		cfd->can_id = CAN_EFF_FLAG |
-			FIELD_PREP(MCP25XXFD_REG_FRAME_EFF_EID_MASK, eid) |
-			FIELD_PREP(MCP25XXFD_REG_FRAME_EFF_SID_MASK, sid);
+			FIELD_PREP(MCP251XFD_REG_FRAME_EFF_EID_MASK, eid) |
+			FIELD_PREP(MCP251XFD_REG_FRAME_EFF_SID_MASK, sid);
 	} else {
-		cfd->can_id = FIELD_GET(MCP25XXFD_OBJ_ID_SID_MASK,
+		cfd->can_id = FIELD_GET(MCP251XFD_OBJ_ID_SID_MASK,
 					hw_rx_obj->id);
 	}
 
 	/* CANFD */
-	if (hw_rx_obj->flags & MCP25XXFD_OBJ_FLAGS_FDF) {
+	if (hw_rx_obj->flags & MCP251XFD_OBJ_FLAGS_FDF) {
 		u8 dlc;
 
-		if (hw_rx_obj->flags & MCP25XXFD_OBJ_FLAGS_ESI)
+		if (hw_rx_obj->flags & MCP251XFD_OBJ_FLAGS_ESI)
 			cfd->flags |= CANFD_ESI;
 
-		if (hw_rx_obj->flags & MCP25XXFD_OBJ_FLAGS_BRS)
+		if (hw_rx_obj->flags & MCP251XFD_OBJ_FLAGS_BRS)
 			cfd->flags |= CANFD_BRS;
 
-		dlc = FIELD_GET(MCP25XXFD_OBJ_FLAGS_DLC, hw_rx_obj->flags);
+		dlc = FIELD_GET(MCP251XFD_OBJ_FLAGS_DLC, hw_rx_obj->flags);
 		cfd->len = can_dlc2len(get_canfd_dlc(dlc));
 	} else {
-		if (hw_rx_obj->flags & MCP25XXFD_OBJ_FLAGS_RTR)
+		if (hw_rx_obj->flags & MCP251XFD_OBJ_FLAGS_RTR)
 			cfd->can_id |= CAN_RTR_FLAG;
 
-		cfd->len = get_can_dlc(FIELD_GET(MCP25XXFD_OBJ_FLAGS_DLC,
+		cfd->len = get_can_dlc(FIELD_GET(MCP251XFD_OBJ_FLAGS_DLC,
 						 hw_rx_obj->flags));
 	}
 
@@ -1418,16 +1418,16 @@ mcp25xxfd_hw_rx_obj_to_skb(const struct mcp25xxfd_priv *priv,
 }
 
 static int
-mcp25xxfd_handle_rxif_one(struct mcp25xxfd_priv *priv,
-			  struct mcp25xxfd_rx_ring *ring,
-			  const struct mcp25xxfd_hw_rx_obj_canfd *hw_rx_obj)
+mcp251xfd_handle_rxif_one(struct mcp251xfd_priv *priv,
+			  struct mcp251xfd_rx_ring *ring,
+			  const struct mcp251xfd_hw_rx_obj_canfd *hw_rx_obj)
 {
 	struct net_device_stats *stats = &priv->ndev->stats;
 	struct sk_buff *skb;
 	struct canfd_frame *cfd;
 	int err;
 
-	if (hw_rx_obj->flags & MCP25XXFD_OBJ_FLAGS_FDF)
+	if (hw_rx_obj->flags & MCP251XFD_OBJ_FLAGS_FDF)
 		skb = alloc_canfd_skb(priv->ndev, &cfd);
 	else
 		skb = alloc_can_skb(priv->ndev, (struct can_frame **)&cfd);
@@ -1437,7 +1437,7 @@ mcp25xxfd_handle_rxif_one(struct mcp25xxfd_priv *priv,
 		return 0;
 	}
 
-	mcp25xxfd_hw_rx_obj_to_skb(priv, hw_rx_obj, skb);
+	mcp251xfd_hw_rx_obj_to_skb(priv, hw_rx_obj, skb);
 	err = can_rx_offload_queue_sorted(&priv->offload, skb, hw_rx_obj->ts);
 	if (err)
 		stats->rx_fifo_errors++;
@@ -1446,21 +1446,21 @@ mcp25xxfd_handle_rxif_one(struct mcp25xxfd_priv *priv,
 
 	/* finally increment the RX pointer */
 	return regmap_update_bits(priv->map_reg,
-				  MCP25XXFD_REG_FIFOCON(ring->fifo_nr),
+				  MCP251XFD_REG_FIFOCON(ring->fifo_nr),
 				  GENMASK(15, 8),
-				  MCP25XXFD_REG_FIFOCON_UINC);
+				  MCP251XFD_REG_FIFOCON_UINC);
 }
 
 static inline int
-mcp25xxfd_rx_obj_read(const struct mcp25xxfd_priv *priv,
-		      const struct mcp25xxfd_rx_ring *ring,
-		      struct mcp25xxfd_hw_rx_obj_canfd *hw_rx_obj,
+mcp251xfd_rx_obj_read(const struct mcp251xfd_priv *priv,
+		      const struct mcp251xfd_rx_ring *ring,
+		      struct mcp251xfd_hw_rx_obj_canfd *hw_rx_obj,
 		      const u8 offset, const u8 len)
 {
 	int err;
 
 	err = regmap_bulk_read(priv->map_rx,
-			       mcp25xxfd_get_rx_obj_addr(ring, offset),
+			       mcp251xfd_get_rx_obj_addr(ring, offset),
 			       hw_rx_obj,
 			       len * ring->obj_size / sizeof(u32));
 
@@ -1468,27 +1468,27 @@ mcp25xxfd_rx_obj_read(const struct mcp25xxfd_priv *priv,
 }
 
 static int
-mcp25xxfd_handle_rxif_ring(struct mcp25xxfd_priv *priv,
-			   struct mcp25xxfd_rx_ring *ring)
+mcp251xfd_handle_rxif_ring(struct mcp251xfd_priv *priv,
+			   struct mcp251xfd_rx_ring *ring)
 {
-	struct mcp25xxfd_hw_rx_obj_canfd *hw_rx_obj = ring->obj;
+	struct mcp251xfd_hw_rx_obj_canfd *hw_rx_obj = ring->obj;
 	u8 rx_tail, len;
 	int err, i;
 
-	err = mcp25xxfd_rx_ring_update(priv, ring);
+	err = mcp251xfd_rx_ring_update(priv, ring);
 	if (err)
 		return err;
 
-	while ((len = mcp25xxfd_get_rx_linear_len(ring))) {
-		rx_tail = mcp25xxfd_get_rx_tail(ring);
+	while ((len = mcp251xfd_get_rx_linear_len(ring))) {
+		rx_tail = mcp251xfd_get_rx_tail(ring);
 
-		err = mcp25xxfd_rx_obj_read(priv, ring, hw_rx_obj,
+		err = mcp251xfd_rx_obj_read(priv, ring, hw_rx_obj,
 					    rx_tail, len);
 		if (err)
 			return err;
 
 		for (i = 0; i < len; i++) {
-			err = mcp25xxfd_handle_rxif_one(priv, ring,
+			err = mcp251xfd_handle_rxif_one(priv, ring,
 							(void *)hw_rx_obj +
 							i * ring->obj_size);
 			if (err)
@@ -1499,13 +1499,13 @@ mcp25xxfd_handle_rxif_ring(struct mcp25xxfd_priv *priv,
 	return 0;
 }
 
-static int mcp25xxfd_handle_rxif(struct mcp25xxfd_priv *priv)
+static int mcp251xfd_handle_rxif(struct mcp251xfd_priv *priv)
 {
-	struct mcp25xxfd_rx_ring *ring;
+	struct mcp251xfd_rx_ring *ring;
 	int err, n;
 
-	mcp25xxfd_for_each_rx_ring(priv, ring, n) {
-		err = mcp25xxfd_handle_rxif_ring(priv, ring);
+	mcp251xfd_for_each_rx_ring(priv, ring, n) {
+		err = mcp251xfd_handle_rxif_ring(priv, ring);
 		if (err)
 			return err;
 	}
@@ -1513,29 +1513,29 @@ static int mcp25xxfd_handle_rxif(struct mcp25xxfd_priv *priv)
 	return 0;
 }
 
-static inline int mcp25xxfd_get_timestamp(const struct mcp25xxfd_priv *priv,
+static inline int mcp251xfd_get_timestamp(const struct mcp251xfd_priv *priv,
 					  u32 *timestamp)
 {
-	return regmap_read(priv->map_reg, MCP25XXFD_REG_TBC, timestamp);
+	return regmap_read(priv->map_reg, MCP251XFD_REG_TBC, timestamp);
 }
 
 static struct sk_buff *
-mcp25xxfd_alloc_can_err_skb(const struct mcp25xxfd_priv *priv,
+mcp251xfd_alloc_can_err_skb(const struct mcp251xfd_priv *priv,
 			    struct can_frame **cf, u32 *timestamp)
 {
 	int err;
 
-	err = mcp25xxfd_get_timestamp(priv, timestamp);
+	err = mcp251xfd_get_timestamp(priv, timestamp);
 	if (err)
 		return NULL;
 
 	return alloc_can_err_skb(priv->ndev, cf);
 }
 
-static int mcp25xxfd_handle_rxovif(struct mcp25xxfd_priv *priv)
+static int mcp251xfd_handle_rxovif(struct mcp251xfd_priv *priv)
 {
 	struct net_device_stats *stats = &priv->ndev->stats;
-	struct mcp25xxfd_rx_ring *ring;
+	struct mcp251xfd_rx_ring *ring;
 	struct sk_buff *skb;
 	struct can_frame *cf;
 	u32 timestamp, rxovif;
@@ -1544,16 +1544,16 @@ static int mcp25xxfd_handle_rxovif(struct mcp25xxfd_priv *priv)
 	stats->rx_over_errors++;
 	stats->rx_errors++;
 
-	err = regmap_read(priv->map_reg, MCP25XXFD_REG_RXOVIF, &rxovif);
+	err = regmap_read(priv->map_reg, MCP251XFD_REG_RXOVIF, &rxovif);
 	if (err)
 		return err;
 
-	mcp25xxfd_for_each_rx_ring(priv, ring, i) {
+	mcp251xfd_for_each_rx_ring(priv, ring, i) {
 		if (!(rxovif & BIT(ring->fifo_nr)))
 			continue;
 
 		/* If SERRIF is active, there was a RX MAB overflow. */
-		if (priv->regs_status.intf & MCP25XXFD_REG_INT_SERRIF) {
+		if (priv->regs_status.intf & MCP251XFD_REG_INT_SERRIF) {
 			netdev_info(priv->ndev,
 				    "RX-%d: MAB overflow detected.\n",
 				    ring->nr);
@@ -1563,14 +1563,14 @@ static int mcp25xxfd_handle_rxovif(struct mcp25xxfd_priv *priv)
 		}
 
 		err = regmap_update_bits(priv->map_reg,
-					 MCP25XXFD_REG_FIFOSTA(ring->fifo_nr),
-					 MCP25XXFD_REG_FIFOSTA_RXOVIF,
+					 MCP251XFD_REG_FIFOSTA(ring->fifo_nr),
+					 MCP251XFD_REG_FIFOSTA_RXOVIF,
 					 0x0);
 		if (err)
 			return err;
 	}
 
-	skb = mcp25xxfd_alloc_can_err_skb(priv, &cf, &timestamp);
+	skb = mcp251xfd_alloc_can_err_skb(priv, &cf, &timestamp);
 	if (!skb)
 		return 0;
 
@@ -1584,14 +1584,14 @@ static int mcp25xxfd_handle_rxovif(struct mcp25xxfd_priv *priv)
 	return 0;
 }
 
-static int mcp25xxfd_handle_txatif(struct mcp25xxfd_priv *priv)
+static int mcp251xfd_handle_txatif(struct mcp251xfd_priv *priv)
 {
 	netdev_info(priv->ndev, "%s\n", __func__);
 
 	return 0;
 }
 
-static int mcp25xxfd_handle_ivmif(struct mcp25xxfd_priv *priv)
+static int mcp251xfd_handle_ivmif(struct mcp251xfd_priv *priv)
 {
 	struct net_device_stats *stats = &priv->ndev->stats;
 	u32 bdiag1, timestamp;
@@ -1599,18 +1599,18 @@ static int mcp25xxfd_handle_ivmif(struct mcp25xxfd_priv *priv)
 	struct can_frame *cf = NULL;
 	int err;
 
-	err = mcp25xxfd_get_timestamp(priv, &timestamp);
+	err = mcp251xfd_get_timestamp(priv, &timestamp);
 	if (err)
 		return err;
 
-	err = regmap_read(priv->map_reg, MCP25XXFD_REG_BDIAG1, &bdiag1);
+	err = regmap_read(priv->map_reg, MCP251XFD_REG_BDIAG1, &bdiag1);
 	if (err)
 		return err;
 
 	/* Write 0s to clear error bits, don't write 1s to non active
 	 * bits, as they will be set.
 	 */
-	err = regmap_write(priv->map_reg, MCP25XXFD_REG_BDIAG1, 0x0);
+	err = regmap_write(priv->map_reg, MCP251XFD_REG_BDIAG1, 0x0);
 	if (err)
 		return err;
 
@@ -1621,29 +1621,29 @@ static int mcp25xxfd_handle_ivmif(struct mcp25xxfd_priv *priv)
 		cf->can_id |= CAN_ERR_PROT | CAN_ERR_BUSERROR;
 
 	/* Controller misconfiguration */
-	if (WARN_ON(bdiag1 & MCP25XXFD_REG_BDIAG1_DLCMM))
+	if (WARN_ON(bdiag1 & MCP251XFD_REG_BDIAG1_DLCMM))
 		netdev_err(priv->ndev,
 			   "recv'd DLC is larger than PLSIZE of FIFO element.");
 
 	/* RX errors */
-	if (bdiag1 & (MCP25XXFD_REG_BDIAG1_DCRCERR |
-		      MCP25XXFD_REG_BDIAG1_NCRCERR)) {
+	if (bdiag1 & (MCP251XFD_REG_BDIAG1_DCRCERR |
+		      MCP251XFD_REG_BDIAG1_NCRCERR)) {
 		netdev_dbg(priv->ndev, "CRC error\n");
 
 		stats->rx_errors++;
 		if (cf)
 			cf->data[3] |= CAN_ERR_PROT_LOC_CRC_SEQ;
 	}
-	if (bdiag1 & (MCP25XXFD_REG_BDIAG1_DSTUFERR |
-		      MCP25XXFD_REG_BDIAG1_NSTUFERR)) {
+	if (bdiag1 & (MCP251XFD_REG_BDIAG1_DSTUFERR |
+		      MCP251XFD_REG_BDIAG1_NSTUFERR)) {
 		netdev_dbg(priv->ndev, "Stuff error\n");
 
 		stats->rx_errors++;
 		if (cf)
 			cf->data[2] |= CAN_ERR_PROT_STUFF;
 	}
-	if (bdiag1 & (MCP25XXFD_REG_BDIAG1_DFORMERR |
-		      MCP25XXFD_REG_BDIAG1_NFORMERR)) {
+	if (bdiag1 & (MCP251XFD_REG_BDIAG1_DFORMERR |
+		      MCP251XFD_REG_BDIAG1_NFORMERR)) {
 		netdev_dbg(priv->ndev, "Format error\n");
 
 		stats->rx_errors++;
@@ -1652,7 +1652,7 @@ static int mcp25xxfd_handle_ivmif(struct mcp25xxfd_priv *priv)
 	}
 
 	/* TX errors */
-	if (bdiag1 & MCP25XXFD_REG_BDIAG1_NACKERR) {
+	if (bdiag1 & MCP251XFD_REG_BDIAG1_NACKERR) {
 		netdev_dbg(priv->ndev, "NACK error\n");
 
 		stats->tx_errors++;
@@ -1661,16 +1661,16 @@ static int mcp25xxfd_handle_ivmif(struct mcp25xxfd_priv *priv)
 			cf->data[2] |= CAN_ERR_PROT_TX;
 		}
 	}
-	if (bdiag1 & (MCP25XXFD_REG_BDIAG1_DBIT1ERR |
-		      MCP25XXFD_REG_BDIAG1_NBIT1ERR)) {
+	if (bdiag1 & (MCP251XFD_REG_BDIAG1_DBIT1ERR |
+		      MCP251XFD_REG_BDIAG1_NBIT1ERR)) {
 		netdev_dbg(priv->ndev, "Bit1 error\n");
 
 		stats->tx_errors++;
 		if (cf)
 			cf->data[2] |= CAN_ERR_PROT_TX | CAN_ERR_PROT_BIT1;
 	}
-	if (bdiag1 & (MCP25XXFD_REG_BDIAG1_DBIT0ERR |
-		      MCP25XXFD_REG_BDIAG1_NBIT0ERR)) {
+	if (bdiag1 & (MCP251XFD_REG_BDIAG1_DBIT0ERR |
+		      MCP251XFD_REG_BDIAG1_NBIT0ERR)) {
 		netdev_dbg(priv->ndev, "Bit0 error\n");
 
 		stats->tx_errors++;
@@ -1688,7 +1688,7 @@ static int mcp25xxfd_handle_ivmif(struct mcp25xxfd_priv *priv)
 	return 0;
 }
 
-static int mcp25xxfd_handle_cerrif(struct mcp25xxfd_priv *priv)
+static int mcp251xfd_handle_cerrif(struct mcp251xfd_priv *priv)
 {
 	struct net_device_stats *stats = &priv->ndev->stats;
 	struct sk_buff *skb;
@@ -1697,22 +1697,22 @@ static int mcp25xxfd_handle_cerrif(struct mcp25xxfd_priv *priv)
 	u32 trec, timestamp;
 	int err;
 
-	err = regmap_read(priv->map_reg, MCP25XXFD_REG_TREC, &trec);
+	err = regmap_read(priv->map_reg, MCP251XFD_REG_TREC, &trec);
 	if (err)
 		return err;
 
-	if (trec & MCP25XXFD_REG_TREC_TXBO)
+	if (trec & MCP251XFD_REG_TREC_TXBO)
 		tx_state = CAN_STATE_BUS_OFF;
-	else if (trec & MCP25XXFD_REG_TREC_TXBP)
+	else if (trec & MCP251XFD_REG_TREC_TXBP)
 		tx_state = CAN_STATE_ERROR_PASSIVE;
-	else if (trec & MCP25XXFD_REG_TREC_TXWARN)
+	else if (trec & MCP251XFD_REG_TREC_TXWARN)
 		tx_state = CAN_STATE_ERROR_WARNING;
 	else
 		tx_state = CAN_STATE_ERROR_ACTIVE;
 
-	if (trec & MCP25XXFD_REG_TREC_RXBP)
+	if (trec & MCP251XFD_REG_TREC_RXBP)
 		rx_state = CAN_STATE_ERROR_PASSIVE;
-	else if (trec & MCP25XXFD_REG_TREC_RXWARN)
+	else if (trec & MCP251XFD_REG_TREC_RXWARN)
 		rx_state = CAN_STATE_ERROR_WARNING;
 	else
 		rx_state = CAN_STATE_ERROR_ACTIVE;
@@ -1724,7 +1724,7 @@ static int mcp25xxfd_handle_cerrif(struct mcp25xxfd_priv *priv)
 	/* The skb allocation might fail, but can_change_state()
 	 * handles cf == NULL.
 	 */
-	skb = mcp25xxfd_alloc_can_err_skb(priv, &cf, &timestamp);
+	skb = mcp251xfd_alloc_can_err_skb(priv, &cf, &timestamp);
 	can_change_state(priv->ndev, cf, tx_state, rx_state);
 
 	if (new_state == CAN_STATE_BUS_OFF) {
@@ -1733,11 +1733,11 @@ static int mcp25xxfd_handle_cerrif(struct mcp25xxfd_priv *priv)
 		 * userspace, if do_get_berr_counter() is called while
 		 * the chip is in Bus Off.
 		 */
-		err = __mcp25xxfd_get_berr_counter(priv->ndev, &priv->bec);
+		err = __mcp251xfd_get_berr_counter(priv->ndev, &priv->bec);
 		if (err)
 			return err;
 
-		mcp25xxfd_chip_stop(priv, CAN_STATE_BUS_OFF);
+		mcp251xfd_chip_stop(priv, CAN_STATE_BUS_OFF);
 		can_bus_off(priv->ndev);
 	}
 
@@ -1747,7 +1747,7 @@ static int mcp25xxfd_handle_cerrif(struct mcp25xxfd_priv *priv)
 	if (new_state != CAN_STATE_BUS_OFF) {
 		struct can_berr_counter bec;
 
-		err = mcp25xxfd_get_berr_counter(priv->ndev, &bec);
+		err = mcp251xfd_get_berr_counter(priv->ndev, &bec);
 		if (err)
 			return err;
 		cf->data[6] = bec.txerr;
@@ -1762,20 +1762,20 @@ static int mcp25xxfd_handle_cerrif(struct mcp25xxfd_priv *priv)
 }
 
 static int
-mcp25xxfd_handle_modif(const struct mcp25xxfd_priv *priv, bool *set_normal_mode)
+mcp251xfd_handle_modif(const struct mcp251xfd_priv *priv, bool *set_normal_mode)
 {
-	const u8 mode_reference = mcp25xxfd_get_normal_mode(priv);
+	const u8 mode_reference = mcp251xfd_get_normal_mode(priv);
 	u8 mode;
 	int err;
 
-	err = mcp25xxfd_chip_get_mode(priv, &mode);
+	err = mcp251xfd_chip_get_mode(priv, &mode);
 	if (err)
 		return err;
 
 	if (mode == mode_reference) {
 		netdev_dbg(priv->ndev,
 			   "Controller changed into %s Mode (%u).\n",
-			   mcp25xxfd_get_mode_str(mode), mode);
+			   mcp251xfd_get_mode_str(mode), mode);
 		return 0;
 	}
 
@@ -1789,16 +1789,16 @@ mcp25xxfd_handle_modif(const struct mcp25xxfd_priv *priv, bool *set_normal_mode)
 	 * first. When polling this bit we see that it will transition
 	 * to Restricted Operation Mode shortly after.
 	 */
-	if ((priv->devtype_data.quirks & MCP25XXFD_QUIRK_MAB_NO_WARN) &&
-	    (mode == MCP25XXFD_REG_CON_MODE_RESTRICTED ||
-	     mode == MCP25XXFD_REG_CON_MODE_LISTENONLY))
+	if ((priv->devtype_data.quirks & MCP251XFD_QUIRK_MAB_NO_WARN) &&
+	    (mode == MCP251XFD_REG_CON_MODE_RESTRICTED ||
+	     mode == MCP251XFD_REG_CON_MODE_LISTENONLY))
 		netdev_dbg(priv->ndev,
 			   "Controller changed into %s Mode (%u).\n",
-			   mcp25xxfd_get_mode_str(mode), mode);
+			   mcp251xfd_get_mode_str(mode), mode);
 	else
 		netdev_err(priv->ndev,
 			   "Controller changed into %s Mode (%u).\n",
-			   mcp25xxfd_get_mode_str(mode), mode);
+			   mcp251xfd_get_mode_str(mode), mode);
 
 	/* After the application requests Normal mode, the Controller
 	 * will automatically attempt to retransmit the message that
@@ -1806,19 +1806,19 @@ mcp25xxfd_handle_modif(const struct mcp25xxfd_priv *priv, bool *set_normal_mode)
 	 *
 	 * However, if there is an ECC error in the TX-RAM, we first
 	 * have to reload the tx-object before requesting Normal
-	 * mode. This is done later in mcp25xxfd_handle_eccif().
+	 * mode. This is done later in mcp251xfd_handle_eccif().
 	 */
-	if (priv->regs_status.intf & MCP25XXFD_REG_INT_ECCIF) {
+	if (priv->regs_status.intf & MCP251XFD_REG_INT_ECCIF) {
 		*set_normal_mode = true;
 		return 0;
 	}
 
-	return mcp25xxfd_chip_set_normal_mode_nowait(priv);
+	return mcp251xfd_chip_set_normal_mode_nowait(priv);
 }
 
-static int mcp25xxfd_handle_serrif(struct mcp25xxfd_priv *priv)
+static int mcp251xfd_handle_serrif(struct mcp251xfd_priv *priv)
 {
-	struct mcp25xxfd_ecc *ecc = &priv->ecc;
+	struct mcp251xfd_ecc *ecc = &priv->ecc;
 	struct net_device_stats *stats = &priv->ndev->stats;
 	bool handled = false;
 
@@ -1844,19 +1844,19 @@ static int mcp25xxfd_handle_serrif(struct mcp25xxfd_priv *priv)
 	 *
 	 * Treat all as a known system errors..
 	 */
-	if ((priv->regs_status.intf & MCP25XXFD_REG_INT_MODIF &&
-	     priv->regs_status.intf & MCP25XXFD_REG_INT_IVMIF) ||
-	    priv->regs_status.intf & MCP25XXFD_REG_INT_ECCIF ||
+	if ((priv->regs_status.intf & MCP251XFD_REG_INT_MODIF &&
+	     priv->regs_status.intf & MCP251XFD_REG_INT_IVMIF) ||
+	    priv->regs_status.intf & MCP251XFD_REG_INT_ECCIF ||
 	    ecc->cnt) {
 		const char *msg;
 
-		if (priv->regs_status.intf & MCP25XXFD_REG_INT_ECCIF ||
+		if (priv->regs_status.intf & MCP251XFD_REG_INT_ECCIF ||
 		    ecc->cnt)
 			msg = "TX MAB underflow due to ECC error detected.";
 		else
 			msg = "TX MAB underflow detected.";
 
-		if (priv->devtype_data.quirks & MCP25XXFD_QUIRK_MAB_NO_WARN)
+		if (priv->devtype_data.quirks & MCP251XFD_QUIRK_MAB_NO_WARN)
 			netdev_dbg(priv->ndev, "%s\n", msg);
 		else
 			netdev_info(priv->ndev, "%s\n", msg);
@@ -1880,8 +1880,8 @@ static int mcp25xxfd_handle_serrif(struct mcp25xxfd_priv *priv)
 	 *
 	 * Treat all as a known system errors..
 	 */
-	if (priv->regs_status.intf & MCP25XXFD_REG_INT_RXOVIF ||
-	    priv->regs_status.intf & MCP25XXFD_REG_INT_RXIF) {
+	if (priv->regs_status.intf & MCP251XFD_REG_INT_RXOVIF ||
+	    priv->regs_status.intf & MCP251XFD_REG_INT_RXIF) {
 		stats->rx_dropped++;
 		handled = true;
 	}
@@ -1895,22 +1895,22 @@ static int mcp25xxfd_handle_serrif(struct mcp25xxfd_priv *priv)
 }
 
 static int
-mcp25xxfd_handle_eccif_recover(struct mcp25xxfd_priv *priv, u8 nr)
+mcp251xfd_handle_eccif_recover(struct mcp251xfd_priv *priv, u8 nr)
 {
-	struct mcp25xxfd_tx_ring *tx_ring = priv->tx;
-	struct mcp25xxfd_ecc *ecc = &priv->ecc;
-	struct mcp25xxfd_tx_obj *tx_obj;
+	struct mcp251xfd_tx_ring *tx_ring = priv->tx;
+	struct mcp251xfd_ecc *ecc = &priv->ecc;
+	struct mcp251xfd_tx_obj *tx_obj;
 	u8 chip_tx_tail, tx_tail, offset;
 	u16 addr;
 	int err;
 
-	addr = FIELD_GET(MCP25XXFD_REG_ECCSTAT_ERRADDR_MASK, ecc->ecc_stat);
+	addr = FIELD_GET(MCP251XFD_REG_ECCSTAT_ERRADDR_MASK, ecc->ecc_stat);
 
-	err = mcp25xxfd_tx_tail_get_from_chip(priv, &chip_tx_tail);
+	err = mcp251xfd_tx_tail_get_from_chip(priv, &chip_tx_tail);
 	if (err)
 		return err;
 
-	tx_tail = mcp25xxfd_get_tx_tail(tx_ring);
+	tx_tail = mcp251xfd_get_tx_tail(tx_ring);
 	offset = (nr - chip_tx_tail) & (tx_ring->obj_num - 1);
 
 	/* Bail out if one of the following is met:
@@ -1919,7 +1919,7 @@ mcp25xxfd_handle_eccif_recover(struct mcp25xxfd_priv *priv, u8 nr)
 	 * - for mcp2518fd: offset not 0 or 1
 	 */
 	if (chip_tx_tail != tx_tail ||
-	    !(offset == 0 || (offset == 1 && mcp25xxfd_is_2518(priv)))) {
+	    !(offset == 0 || (offset == 1 && mcp251xfd_is_2518(priv)))) {
 		netdev_err(priv->ndev,
 			   "ECC Error information inconsistent (addr=0x%04x, nr=%d, tx_tail=0x%08x(%d), chip_tx_tail=%d, offset=%d).\n",
 			   addr, nr, tx_ring->tail, tx_tail, chip_tx_tail,
@@ -1929,7 +1929,7 @@ mcp25xxfd_handle_eccif_recover(struct mcp25xxfd_priv *priv, u8 nr)
 
 	netdev_info(priv->ndev,
 		    "Recovering %s ECC Error at address 0x%04x (in TX-RAM, tx_obj=%d, tx_tail=0x%08x(%d), offset=%d).\n",
-		    ecc->ecc_stat & MCP25XXFD_REG_ECCSTAT_SECIF ?
+		    ecc->ecc_stat & MCP251XFD_REG_ECCSTAT_SECIF ?
 		    "Single" : "Double",
 		    addr, nr, tx_ring->tail, tx_tail, offset);
 
@@ -1940,13 +1940,13 @@ mcp25xxfd_handle_eccif_recover(struct mcp25xxfd_priv *priv, u8 nr)
 		return err;
 
 	/* ... and trigger retransmit */
-	return mcp25xxfd_chip_set_normal_mode(priv);
+	return mcp251xfd_chip_set_normal_mode(priv);
 }
 
 static int
-mcp25xxfd_handle_eccif(struct mcp25xxfd_priv *priv, bool set_normal_mode)
+mcp251xfd_handle_eccif(struct mcp251xfd_priv *priv, bool set_normal_mode)
 {
-	struct mcp25xxfd_ecc *ecc = &priv->ecc;
+	struct mcp251xfd_ecc *ecc = &priv->ecc;
 	const char *msg;
 	bool in_tx_ram;
 	u32 ecc_stat;
@@ -1954,18 +1954,18 @@ mcp25xxfd_handle_eccif(struct mcp25xxfd_priv *priv, bool set_normal_mode)
 	u8 nr;
 	int err;
 
-	err = regmap_read(priv->map_reg, MCP25XXFD_REG_ECCSTAT, &ecc_stat);
+	err = regmap_read(priv->map_reg, MCP251XFD_REG_ECCSTAT, &ecc_stat);
 	if (err)
 		return err;
 
-	err = regmap_update_bits(priv->map_reg, MCP25XXFD_REG_ECCSTAT,
-				 MCP25XXFD_REG_ECCSTAT_IF_MASK, ~ecc_stat);
+	err = regmap_update_bits(priv->map_reg, MCP251XFD_REG_ECCSTAT,
+				 MCP251XFD_REG_ECCSTAT_IF_MASK, ~ecc_stat);
 	if (err)
 		return err;
 
 	/* Check if ECC error occurred in TX-RAM */
-	addr = FIELD_GET(MCP25XXFD_REG_ECCSTAT_ERRADDR_MASK, ecc_stat);
-	err = mcp25xxfd_get_tx_nr_by_addr(priv->tx, &nr, addr);
+	addr = FIELD_GET(MCP251XFD_REG_ECCSTAT_ERRADDR_MASK, ecc_stat);
+	err = mcp251xfd_get_tx_nr_by_addr(priv->tx, &nr, addr);
 	if (!err)
 		in_tx_ram = true;
 	else if (err == -ENOENT)
@@ -1973,9 +1973,21 @@ mcp25xxfd_handle_eccif(struct mcp25xxfd_priv *priv, bool set_normal_mode)
 	else
 		return err;
 
-	if (ecc_stat & MCP25XXFD_REG_ECCSTAT_SECIF)
-		msg = "Single ECC Error corrected at address";
-	else if (ecc_stat & MCP25XXFD_REG_ECCSTAT_DEDIF)
+	/* Errata Reference:
+	 * mcp2517fd: DS80000789B, mcp2518fd: DS80000792C 2.
+	 *
+	 * ECC single error correction does not work in all cases:
+	 *
+	 * Fix/Work Around:
+	 * Enable single error correction and double error detection
+	 * interrupts by setting SECIE and DEDIE. Handle SECIF as a
+	 * detection interrupt and do not rely on the error
+	 * correction. Instead, handle both interrupts as a
+	 * notification that the RAM word at ERRADDR was corrupted.
+	 */
+	if (ecc_stat & MCP251XFD_REG_ECCSTAT_SECIF)
+		msg = "Single ECC Error detected at address";
+	else if (ecc_stat & MCP251XFD_REG_ECCSTAT_DEDIF)
 		msg = "Double ECC Error detected at address";
 	else
 		return -EINVAL;
@@ -1983,12 +1995,7 @@ mcp25xxfd_handle_eccif(struct mcp25xxfd_priv *priv, bool set_normal_mode)
 	if (!in_tx_ram) {
 		ecc->ecc_stat = 0;
 
-		if (ecc_stat & MCP25XXFD_REG_ECCSTAT_SECIF)
-			netdev_info(priv->ndev, "%s 0x%04x.\n",
-				    msg, addr);
-		else
-			netdev_notice(priv->ndev, "%s 0x%04x.\n",
-				      msg, addr);
+		netdev_notice(priv->ndev, "%s 0x%04x.\n", msg, addr);
 	} else {
 		/* Re-occurring error? */
 		if (ecc->ecc_stat == ecc_stat) {
@@ -2002,57 +2009,57 @@ mcp25xxfd_handle_eccif(struct mcp25xxfd_priv *priv, bool set_normal_mode)
 			    "%s 0x%04x (in TX-RAM, tx_obj=%d), occurred %d time%s.\n",
 			    msg, addr, nr, ecc->cnt, ecc->cnt > 1 ? "s" : "");
 
-		if (ecc->cnt >= MCP25XXFD_ECC_CNT_MAX)
-			return mcp25xxfd_handle_eccif_recover(priv, nr);
+		if (ecc->cnt >= MCP251XFD_ECC_CNT_MAX)
+			return mcp251xfd_handle_eccif_recover(priv, nr);
 	}
 
 	if (set_normal_mode)
-		return mcp25xxfd_chip_set_normal_mode_nowait(priv);
+		return mcp251xfd_chip_set_normal_mode_nowait(priv);
 
 	return 0;
 }
 
-static int mcp25xxfd_handle_spicrcif(struct mcp25xxfd_priv *priv)
+static int mcp251xfd_handle_spicrcif(struct mcp251xfd_priv *priv)
 {
 	int err;
 	u32 crc;
 
-	err = regmap_read(priv->map_reg, MCP25XXFD_REG_CRC, &crc);
+	err = regmap_read(priv->map_reg, MCP251XFD_REG_CRC, &crc);
 	if (err)
 		return err;
 
-	err = regmap_update_bits(priv->map_reg, MCP25XXFD_REG_CRC,
-				 MCP25XXFD_REG_CRC_IF_MASK,
+	err = regmap_update_bits(priv->map_reg, MCP251XFD_REG_CRC,
+				 MCP251XFD_REG_CRC_IF_MASK,
 				 ~crc);
 	if (err)
 		return err;
 
-	if (crc & MCP25XXFD_REG_CRC_FERRIF)
+	if (crc & MCP251XFD_REG_CRC_FERRIF)
 		netdev_notice(priv->ndev, "CRC write command format error.\n");
-	else if (crc & MCP25XXFD_REG_CRC_CRCERRIF)
+	else if (crc & MCP251XFD_REG_CRC_CRCERRIF)
 		netdev_notice(priv->ndev,
 			      "CRC write error detected. CRC=0x%04lx.\n",
-			      FIELD_GET(MCP25XXFD_REG_CRC_MASK, crc));
+			      FIELD_GET(MCP251XFD_REG_CRC_MASK, crc));
 
 	return 0;
 }
 
-#define mcp25xxfd_handle(priv, irq, ...) \
+#define mcp251xfd_handle(priv, irq, ...) \
 ({ \
-	struct mcp25xxfd_priv *_priv = (priv); \
+	struct mcp251xfd_priv *_priv = (priv); \
 	int err; \
 \
-	err = mcp25xxfd_handle_##irq(_priv, ## __VA_ARGS__); \
+	err = mcp251xfd_handle_##irq(_priv, ## __VA_ARGS__); \
 	if (err) \
 		netdev_err(_priv->ndev, \
-			"IRQ handler mcp25xxfd_handle_%s() returned %d.\n", \
+			"IRQ handler mcp251xfd_handle_%s() returned %d.\n", \
 			__stringify(irq), err); \
 	err; \
 })
 
-static irqreturn_t mcp25xxfd_irq(int irq, void *dev_id)
+static irqreturn_t mcp251xfd_irq(int irq, void *dev_id)
 {
-	struct mcp25xxfd_priv *priv = dev_id;
+	struct mcp251xfd_priv *priv = dev_id;
 	irqreturn_t handled = IRQ_NONE;
 	int err;
 
@@ -2064,7 +2071,7 @@ static irqreturn_t mcp25xxfd_irq(int irq, void *dev_id)
 			if (!rx_pending)
 				break;
 
-			err = mcp25xxfd_handle(priv, rxif);
+			err = mcp251xfd_handle(priv, rxif);
 			if (err)
 				goto out_fail;
 
@@ -2073,92 +2080,92 @@ static irqreturn_t mcp25xxfd_irq(int irq, void *dev_id)
 
 	do {
 		u32 intf_pending, intf_pending_clearable;
-		bool set_normal_mode;
+		bool set_normal_mode = false;
 
-		err = regmap_bulk_read(priv->map_reg, MCP25XXFD_REG_INT,
+		err = regmap_bulk_read(priv->map_reg, MCP251XFD_REG_INT,
 				       &priv->regs_status,
 				       sizeof(priv->regs_status) /
 				       sizeof(u32));
 		if (err)
 			goto out_fail;
 
-		intf_pending = FIELD_GET(MCP25XXFD_REG_INT_IF_MASK,
+		intf_pending = FIELD_GET(MCP251XFD_REG_INT_IF_MASK,
 					 priv->regs_status.intf) &
-			FIELD_GET(MCP25XXFD_REG_INT_IE_MASK,
+			FIELD_GET(MCP251XFD_REG_INT_IE_MASK,
 				  priv->regs_status.intf);
 
 		if (!(intf_pending))
 			return handled;
 
 		/* Some interrupts must be ACKed in the
-		 * MCP25XXFD_REG_INT register.
+		 * MCP251XFD_REG_INT register.
 		 * - First ACK then handle, to avoid lost-IRQ race
 		 *   condition on fast re-occurring interrupts.
 		 * - Write "0" to clear active IRQs, "1" to all other,
 		 *   to avoid r/m/w race condition on the
-		 *   MCP25XXFD_REG_INT register.
+		 *   MCP251XFD_REG_INT register.
 		 */
 		intf_pending_clearable = intf_pending &
-			MCP25XXFD_REG_INT_IF_CLEARABLE_MASK;
+			MCP251XFD_REG_INT_IF_CLEARABLE_MASK;
 		if (intf_pending_clearable) {
 			err = regmap_update_bits(priv->map_reg,
-						 MCP25XXFD_REG_INT,
-						 MCP25XXFD_REG_INT_IF_MASK,
+						 MCP251XFD_REG_INT,
+						 MCP251XFD_REG_INT_IF_MASK,
 						 ~intf_pending_clearable);
 			if (err)
 				goto out_fail;
 		}
 
-		if (intf_pending & MCP25XXFD_REG_INT_MODIF) {
-			err = mcp25xxfd_handle(priv, modif, &set_normal_mode);
+		if (intf_pending & MCP251XFD_REG_INT_MODIF) {
+			err = mcp251xfd_handle(priv, modif, &set_normal_mode);
 			if (err)
 				goto out_fail;
 		}
 
-		if (intf_pending & MCP25XXFD_REG_INT_RXIF) {
-			err = mcp25xxfd_handle(priv, rxif);
+		if (intf_pending & MCP251XFD_REG_INT_RXIF) {
+			err = mcp251xfd_handle(priv, rxif);
 			if (err)
 				goto out_fail;
 		}
 
-		if (intf_pending & MCP25XXFD_REG_INT_TEFIF) {
-			err = mcp25xxfd_handle(priv, tefif);
+		if (intf_pending & MCP251XFD_REG_INT_TEFIF) {
+			err = mcp251xfd_handle(priv, tefif);
 			if (err)
 				goto out_fail;
 		}
 
-		if (intf_pending & MCP25XXFD_REG_INT_RXOVIF) {
-			err = mcp25xxfd_handle(priv, rxovif);
+		if (intf_pending & MCP251XFD_REG_INT_RXOVIF) {
+			err = mcp251xfd_handle(priv, rxovif);
 			if (err)
 				goto out_fail;
 		}
 
-		if (intf_pending & MCP25XXFD_REG_INT_TXATIF) {
-			err = mcp25xxfd_handle(priv, txatif);
+		if (intf_pending & MCP251XFD_REG_INT_TXATIF) {
+			err = mcp251xfd_handle(priv, txatif);
 			if (err)
 				goto out_fail;
 		}
 
-		if (intf_pending & MCP25XXFD_REG_INT_IVMIF) {
-			err = mcp25xxfd_handle(priv, ivmif);
+		if (intf_pending & MCP251XFD_REG_INT_IVMIF) {
+			err = mcp251xfd_handle(priv, ivmif);
 			if (err)
 				goto out_fail;
 		}
 
-		if (intf_pending & MCP25XXFD_REG_INT_SERRIF) {
-			err = mcp25xxfd_handle(priv, serrif);
+		if (intf_pending & MCP251XFD_REG_INT_SERRIF) {
+			err = mcp251xfd_handle(priv, serrif);
 			if (err)
 				goto out_fail;
 		}
 
-		if (intf_pending & MCP25XXFD_REG_INT_ECCIF) {
-			err = mcp25xxfd_handle(priv, eccif, set_normal_mode);
+		if (intf_pending & MCP251XFD_REG_INT_ECCIF) {
+			err = mcp251xfd_handle(priv, eccif, set_normal_mode);
 			if (err)
 				goto out_fail;
 		}
 
-		if (intf_pending & MCP25XXFD_REG_INT_SPICRCIF) {
-			err = mcp25xxfd_handle(priv, spicrcif);
+		if (intf_pending & MCP251XFD_REG_INT_SPICRCIF) {
+			err = mcp251xfd_handle(priv, spicrcif);
 			if (err)
 				goto out_fail;
 		}
@@ -2167,16 +2174,16 @@ static irqreturn_t mcp25xxfd_irq(int irq, void *dev_id)
 		 * CERRIF IRQ on the transition TX ERROR_WARNING -> TX
 		 * ERROR_ACTIVE.
 		 */
-		if (intf_pending & MCP25XXFD_REG_INT_CERRIF ||
+		if (intf_pending & MCP251XFD_REG_INT_CERRIF ||
 		    priv->can.state > CAN_STATE_ERROR_ACTIVE) {
-			err = mcp25xxfd_handle(priv, cerrif);
+			err = mcp251xfd_handle(priv, cerrif);
 			if (err)
 				goto out_fail;
 
 			/* In Bus Off we completely shut down the
 			 * controller. Every subsequent register read
 			 * will read bogus data, and if
-			 * MCP25XXFD_QUIRK_CRC_REG is enabled the CRC
+			 * MCP251XFD_QUIRK_CRC_REG is enabled the CRC
 			 * check will fail, too. So leave IRQ handler
 			 * directly.
 			 */
@@ -2190,30 +2197,30 @@ static irqreturn_t mcp25xxfd_irq(int irq, void *dev_id)
  out_fail:
 	netdev_err(priv->ndev, "IRQ handler returned %d (intf=0x%08x).\n",
 		   err, priv->regs_status.intf);
-	mcp25xxfd_chip_interrupts_disable(priv);
+	mcp251xfd_chip_interrupts_disable(priv);
 
 	return handled;
 }
 
 static inline struct
-mcp25xxfd_tx_obj *mcp25xxfd_get_tx_obj_next(struct mcp25xxfd_tx_ring *tx_ring)
+mcp251xfd_tx_obj *mcp251xfd_get_tx_obj_next(struct mcp251xfd_tx_ring *tx_ring)
 {
 	u8 tx_head;
 
-	tx_head = mcp25xxfd_get_tx_head(tx_ring);
+	tx_head = mcp251xfd_get_tx_head(tx_ring);
 
 	return &tx_ring->obj[tx_head];
 }
 
 static void
-mcp25xxfd_tx_obj_from_skb(const struct mcp25xxfd_priv *priv,
-			  struct mcp25xxfd_tx_obj *tx_obj,
+mcp251xfd_tx_obj_from_skb(const struct mcp251xfd_priv *priv,
+			  struct mcp251xfd_tx_obj *tx_obj,
 			  const struct sk_buff *skb,
 			  unsigned int seq)
 {
 	const struct canfd_frame *cfd = (struct canfd_frame *)skb->data;
-	struct mcp25xxfd_hw_tx_obj_raw *hw_tx_obj;
-	union mcp25xxfd_tx_obj_load_buf *load_buf;
+	struct mcp251xfd_hw_tx_obj_raw *hw_tx_obj;
+	union mcp251xfd_tx_obj_load_buf *load_buf;
 	u8 dlc;
 	u32 id, flags;
 	int offset, len;
@@ -2221,15 +2228,15 @@ mcp25xxfd_tx_obj_from_skb(const struct mcp25xxfd_priv *priv,
 	if (cfd->can_id & CAN_EFF_FLAG) {
 		u32 sid, eid;
 
-		sid = FIELD_GET(MCP25XXFD_REG_FRAME_EFF_SID_MASK, cfd->can_id);
-		eid = FIELD_GET(MCP25XXFD_REG_FRAME_EFF_EID_MASK, cfd->can_id);
+		sid = FIELD_GET(MCP251XFD_REG_FRAME_EFF_SID_MASK, cfd->can_id);
+		eid = FIELD_GET(MCP251XFD_REG_FRAME_EFF_EID_MASK, cfd->can_id);
 
-		id = FIELD_PREP(MCP25XXFD_OBJ_ID_EID_MASK, eid) |
-			FIELD_PREP(MCP25XXFD_OBJ_ID_SID_MASK, sid);
+		id = FIELD_PREP(MCP251XFD_OBJ_ID_EID_MASK, eid) |
+			FIELD_PREP(MCP251XFD_OBJ_ID_SID_MASK, sid);
 
-		flags = MCP25XXFD_OBJ_FLAGS_IDE;
+		flags = MCP251XFD_OBJ_FLAGS_IDE;
 	} else {
-		id = FIELD_PREP(MCP25XXFD_OBJ_ID_SID_MASK, cfd->can_id);
+		id = FIELD_PREP(MCP251XFD_OBJ_ID_SID_MASK, cfd->can_id);
 		flags = 0;
 	}
 
@@ -2238,25 +2245,25 @@ mcp25xxfd_tx_obj_from_skb(const struct mcp25xxfd_priv *priv,
 	 * TEF object.
 	 */
 	dlc = can_len2dlc(cfd->len);
-	flags |= FIELD_PREP(MCP25XXFD_OBJ_FLAGS_SEQ_MCP2518FD_MASK, seq) |
-		FIELD_PREP(MCP25XXFD_OBJ_FLAGS_DLC, dlc);
+	flags |= FIELD_PREP(MCP251XFD_OBJ_FLAGS_SEQ_MCP2518FD_MASK, seq) |
+		FIELD_PREP(MCP251XFD_OBJ_FLAGS_DLC, dlc);
 
 	if (cfd->can_id & CAN_RTR_FLAG)
-		flags |= MCP25XXFD_OBJ_FLAGS_RTR;
+		flags |= MCP251XFD_OBJ_FLAGS_RTR;
 
 	/* CANFD */
 	if (can_is_canfd_skb(skb)) {
 		if (cfd->flags & CANFD_ESI)
-			flags |= MCP25XXFD_OBJ_FLAGS_ESI;
+			flags |= MCP251XFD_OBJ_FLAGS_ESI;
 
-		flags |= MCP25XXFD_OBJ_FLAGS_FDF;
+		flags |= MCP251XFD_OBJ_FLAGS_FDF;
 
 		if (cfd->flags & CANFD_BRS)
-			flags |= MCP25XXFD_OBJ_FLAGS_BRS;
+			flags |= MCP251XFD_OBJ_FLAGS_BRS;
 	}
 
 	load_buf = &tx_obj->buf;
-	if (priv->devtype_data.quirks & MCP25XXFD_QUIRK_CRC_TX)
+	if (priv->devtype_data.quirks & MCP251XFD_QUIRK_CRC_TX)
 		hw_tx_obj = &load_buf->crc.hw_tx_obj;
 	else
 		hw_tx_obj = &load_buf->nocrc.hw_tx_obj;
@@ -2267,25 +2274,25 @@ mcp25xxfd_tx_obj_from_skb(const struct mcp25xxfd_priv *priv,
 	/* Clear data at end of CAN frame */
 	offset = round_down(cfd->len, sizeof(u32));
 	len = round_up(can_dlc2len(dlc), sizeof(u32)) - offset;
-	if (MCP25XXFD_SANITIZE_CAN && len)
+	if (MCP251XFD_SANITIZE_CAN && len)
 		memset(hw_tx_obj->data + offset, 0x0, len);
 	memcpy(hw_tx_obj->data, cfd->data, cfd->len);
 
 	/* Number of bytes to be written into the RAM of the controller */
 	len = sizeof(hw_tx_obj->id) + sizeof(hw_tx_obj->flags);
-	if (MCP25XXFD_SANITIZE_CAN)
+	if (MCP251XFD_SANITIZE_CAN)
 		len += round_up(can_dlc2len(dlc), sizeof(u32));
 	else
 		len += round_up(cfd->len, sizeof(u32));
 
-	if (priv->devtype_data.quirks & MCP25XXFD_QUIRK_CRC_TX) {
+	if (priv->devtype_data.quirks & MCP251XFD_QUIRK_CRC_TX) {
 		u16 crc;
 
-		mcp25xxfd_spi_cmd_crc_set_len_in_ram(&load_buf->crc.cmd,
+		mcp251xfd_spi_cmd_crc_set_len_in_ram(&load_buf->crc.cmd,
 						     len);
 		/* CRC */
 		len += sizeof(load_buf->crc.cmd);
-		crc = mcp25xxfd_crc16_compute(&load_buf->crc, len);
+		crc = mcp251xfd_crc16_compute(&load_buf->crc, len);
 		put_unaligned_be16(crc, (void *)load_buf + len);
 
 		/* Total length */
@@ -2297,16 +2304,16 @@ mcp25xxfd_tx_obj_from_skb(const struct mcp25xxfd_priv *priv,
 	tx_obj->xfer[0].len = len;
 }
 
-static int mcp25xxfd_tx_obj_write(const struct mcp25xxfd_priv *priv,
-				  struct mcp25xxfd_tx_obj *tx_obj)
+static int mcp251xfd_tx_obj_write(const struct mcp251xfd_priv *priv,
+				  struct mcp251xfd_tx_obj *tx_obj)
 {
 	return spi_async(priv->spi, &tx_obj->msg);
 }
 
-static bool mcp25xxfd_tx_busy(const struct mcp25xxfd_priv *priv,
-			      struct mcp25xxfd_tx_ring *tx_ring)
+static bool mcp251xfd_tx_busy(const struct mcp251xfd_priv *priv,
+			      struct mcp251xfd_tx_ring *tx_ring)
 {
-	if (mcp25xxfd_get_tx_free(tx_ring) > 0)
+	if (mcp251xfd_get_tx_free(tx_ring) > 0)
 		return false;
 
 	netif_stop_queue(priv->ndev);
@@ -2314,7 +2321,7 @@ static bool mcp25xxfd_tx_busy(const struct mcp25xxfd_priv *priv,
 	/* Memory barrier before checking tx_free (head and tail) */
 	smp_mb();
 
-	if (mcp25xxfd_get_tx_free(tx_ring) == 0) {
+	if (mcp251xfd_get_tx_free(tx_ring) == 0) {
 		netdev_dbg(priv->ndev,
 			   "Stopping tx-queue (tx_head=0x%08x, tx_tail=0x%08x, len=%d).\n",
 			   tx_ring->head, tx_ring->tail,
@@ -2328,33 +2335,33 @@ static bool mcp25xxfd_tx_busy(const struct mcp25xxfd_priv *priv,
 	return false;
 }
 
-static netdev_tx_t mcp25xxfd_start_xmit(struct sk_buff *skb,
+static netdev_tx_t mcp251xfd_start_xmit(struct sk_buff *skb,
 					struct net_device *ndev)
 {
-	struct mcp25xxfd_priv *priv = netdev_priv(ndev);
-	struct mcp25xxfd_tx_ring *tx_ring = priv->tx;
-	struct mcp25xxfd_tx_obj *tx_obj;
+	struct mcp251xfd_priv *priv = netdev_priv(ndev);
+	struct mcp251xfd_tx_ring *tx_ring = priv->tx;
+	struct mcp251xfd_tx_obj *tx_obj;
 	u8 tx_head;
 	int err;
 
 	if (can_dropped_invalid_skb(ndev, skb))
 		return NETDEV_TX_OK;
 
-	if (mcp25xxfd_tx_busy(priv, tx_ring))
+	if (mcp251xfd_tx_busy(priv, tx_ring))
 		return NETDEV_TX_BUSY;
 
-	tx_obj = mcp25xxfd_get_tx_obj_next(tx_ring);
-	mcp25xxfd_tx_obj_from_skb(priv, tx_obj, skb, tx_ring->head);
+	tx_obj = mcp251xfd_get_tx_obj_next(tx_ring);
+	mcp251xfd_tx_obj_from_skb(priv, tx_obj, skb, tx_ring->head);
 
 	/* Stop queue if we occupy the complete TX FIFO */
-	tx_head = mcp25xxfd_get_tx_head(tx_ring);
+	tx_head = mcp251xfd_get_tx_head(tx_ring);
 	tx_ring->head++;
 	if (tx_ring->head - tx_ring->tail >= tx_ring->obj_num)
 		netif_stop_queue(ndev);
 
 	can_put_echo_skb(skb, ndev, tx_head);
 
-	err = mcp25xxfd_tx_obj_write(priv, tx_obj);
+	err = mcp251xfd_tx_obj_write(priv, tx_obj);
 	if (err)
 		goto out_err;
 
@@ -2366,9 +2373,9 @@ static netdev_tx_t mcp25xxfd_start_xmit(struct sk_buff *skb,
 	return NETDEV_TX_OK;
 }
 
-static int mcp25xxfd_open(struct net_device *ndev)
+static int mcp251xfd_open(struct net_device *ndev)
 {
-	struct mcp25xxfd_priv *priv = netdev_priv(ndev);
+	struct mcp251xfd_priv *priv = netdev_priv(ndev);
 	const struct spi_device *spi = priv->spi;
 	int err;
 
@@ -2382,27 +2389,27 @@ static int mcp25xxfd_open(struct net_device *ndev)
 	if (err)
 		goto out_pm_runtime_put;
 
-	err = mcp25xxfd_ring_alloc(priv);
+	err = mcp251xfd_ring_alloc(priv);
 	if (err)
 		goto out_close_candev;
 
-	err = mcp25xxfd_transceiver_enable(priv);
+	err = mcp251xfd_transceiver_enable(priv);
 	if (err)
-		goto out_mcp25xxfd_ring_free;
+		goto out_mcp251xfd_ring_free;
 
-	err = mcp25xxfd_chip_start(priv);
+	err = mcp251xfd_chip_start(priv);
 	if (err)
 		goto out_transceiver_disable;
 
 	can_rx_offload_enable(&priv->offload);
 
-	err = request_threaded_irq(spi->irq, NULL, mcp25xxfd_irq,
+	err = request_threaded_irq(spi->irq, NULL, mcp251xfd_irq,
 				   IRQF_ONESHOT, dev_name(&spi->dev),
 				   priv);
 	if (err)
 		goto out_can_rx_offload_disable;
 
-	err = mcp25xxfd_chip_interrupts_enable(priv);
+	err = mcp251xfd_chip_interrupts_enable(priv);
 	if (err)
 		goto out_free_irq;
 
@@ -2415,29 +2422,29 @@ static int mcp25xxfd_open(struct net_device *ndev)
  out_can_rx_offload_disable:
 	can_rx_offload_disable(&priv->offload);
  out_transceiver_disable:
-	mcp25xxfd_transceiver_disable(priv);
- out_mcp25xxfd_ring_free:
-	mcp25xxfd_ring_free(priv);
+	mcp251xfd_transceiver_disable(priv);
+ out_mcp251xfd_ring_free:
+	mcp251xfd_ring_free(priv);
  out_close_candev:
 	close_candev(ndev);
  out_pm_runtime_put:
-	mcp25xxfd_chip_stop(priv, CAN_STATE_STOPPED);
+	mcp251xfd_chip_stop(priv, CAN_STATE_STOPPED);
 	pm_runtime_put(ndev->dev.parent);
 
 	return err;
 }
 
-static int mcp25xxfd_stop(struct net_device *ndev)
+static int mcp251xfd_stop(struct net_device *ndev)
 {
-	struct mcp25xxfd_priv *priv = netdev_priv(ndev);
+	struct mcp251xfd_priv *priv = netdev_priv(ndev);
 
 	netif_stop_queue(ndev);
-	mcp25xxfd_chip_interrupts_disable(priv);
+	mcp251xfd_chip_interrupts_disable(priv);
 	free_irq(ndev->irq, priv);
 	can_rx_offload_disable(&priv->offload);
-	mcp25xxfd_chip_stop(priv, CAN_STATE_STOPPED);
-	mcp25xxfd_transceiver_disable(priv);
-	mcp25xxfd_ring_free(priv);
+	mcp251xfd_chip_stop(priv, CAN_STATE_STOPPED);
+	mcp251xfd_transceiver_disable(priv);
+	mcp251xfd_ring_free(priv);
 	close_candev(ndev);
 
 	pm_runtime_put(ndev->dev.parent);
@@ -2445,72 +2452,72 @@ static int mcp25xxfd_stop(struct net_device *ndev)
 	return 0;
 }
 
-static const struct net_device_ops mcp25xxfd_netdev_ops = {
-	.ndo_open = mcp25xxfd_open,
-	.ndo_stop = mcp25xxfd_stop,
-	.ndo_start_xmit	= mcp25xxfd_start_xmit,
+static const struct net_device_ops mcp251xfd_netdev_ops = {
+	.ndo_open = mcp251xfd_open,
+	.ndo_stop = mcp251xfd_stop,
+	.ndo_start_xmit	= mcp251xfd_start_xmit,
 	.ndo_change_mtu = can_change_mtu,
 };
 
 static void
-mcp25xxfd_register_quirks(struct mcp25xxfd_priv *priv)
+mcp251xfd_register_quirks(struct mcp251xfd_priv *priv)
 {
 	const struct spi_device *spi = priv->spi;
 	const struct spi_controller *ctlr = spi->controller;
 
 	if (ctlr->flags & SPI_CONTROLLER_HALF_DUPLEX)
-		priv->devtype_data.quirks |= MCP25XXFD_QUIRK_HALF_DUPLEX;
+		priv->devtype_data.quirks |= MCP251XFD_QUIRK_HALF_DUPLEX;
 }
 
-static int mcp25xxfd_register_chip_detect(struct mcp25xxfd_priv *priv)
+static int mcp251xfd_register_chip_detect(struct mcp251xfd_priv *priv)
 {
 	const struct net_device *ndev = priv->ndev;
-	const struct mcp25xxfd_devtype_data *devtype_data;
+	const struct mcp251xfd_devtype_data *devtype_data;
 	u32 osc;
 	int err;
 
 	/* The OSC_LPMEN is only supported on MCP2518FD, so use it to
 	 * autodetect the model.
 	 */
-	err = regmap_update_bits(priv->map_reg, MCP25XXFD_REG_OSC,
-				 MCP25XXFD_REG_OSC_LPMEN,
-				 MCP25XXFD_REG_OSC_LPMEN);
+	err = regmap_update_bits(priv->map_reg, MCP251XFD_REG_OSC,
+				 MCP251XFD_REG_OSC_LPMEN,
+				 MCP251XFD_REG_OSC_LPMEN);
 	if (err)
 		return err;
 
-	err = regmap_read(priv->map_reg, MCP25XXFD_REG_OSC, &osc);
+	err = regmap_read(priv->map_reg, MCP251XFD_REG_OSC, &osc);
 	if (err)
 		return err;
 
-	if (osc & MCP25XXFD_REG_OSC_LPMEN)
-		devtype_data = &mcp25xxfd_devtype_data_mcp2518fd;
+	if (osc & MCP251XFD_REG_OSC_LPMEN)
+		devtype_data = &mcp251xfd_devtype_data_mcp2518fd;
 	else
-		devtype_data = &mcp25xxfd_devtype_data_mcp2517fd;
+		devtype_data = &mcp251xfd_devtype_data_mcp2517fd;
 
-	if (!mcp25xxfd_is_25XX(priv) &&
+	if (!mcp251xfd_is_251X(priv) &&
 	    priv->devtype_data.model != devtype_data->model) {
 		netdev_info(ndev,
 			    "Detected %s, but firmware specifies a %s. Fixing up.",
-			    __mcp25xxfd_get_model_str(devtype_data->model),
-			    mcp25xxfd_get_model_str(priv));
+			    __mcp251xfd_get_model_str(devtype_data->model),
+			    mcp251xfd_get_model_str(priv));
 	}
 	priv->devtype_data = *devtype_data;
 
 	/* We need to preserve the Half Duplex Quirk. */
-	mcp25xxfd_register_quirks(priv);
+	mcp251xfd_register_quirks(priv);
 
 	/* Re-init regmap with quirks of detected model. */
-	return mcp25xxfd_regmap_init(priv);
+	return mcp251xfd_regmap_init(priv);
 }
 
-static int mcp25xxfd_register_check_rx_int(struct mcp25xxfd_priv *priv)
+static int mcp251xfd_register_check_rx_int(struct mcp251xfd_priv *priv)
 {
 	int err, rx_pending;
 
 	if (!priv->rx_int)
 		return 0;
 
-	err = mcp25xxfd_chip_rx_int_enable(priv);
+	err = mcp251xfd_chip_rx_int_enable(priv);
 	if (err)
 		return err;
 
@@ -2519,7 +2526,7 @@ static int mcp25xxfd_register_check_rx_int(struct mcp25xxfd_priv *priv)
 	 */
 	rx_pending = gpiod_get_value_cansleep(priv->rx_int);
 
-	err = mcp25xxfd_chip_rx_int_disable(priv);
+	err = mcp251xfd_chip_rx_int_disable(priv);
 	if (err)
 		return err;
 
@@ -2535,11 +2542,11 @@ static int mcp25xxfd_register_check_rx_int(struct mcp25xxfd_priv *priv)
 }
 
 static int
-mcp25xxfd_register_get_dev_id(const struct mcp25xxfd_priv *priv,
+mcp251xfd_register_get_dev_id(const struct mcp251xfd_priv *priv,
 			      u32 *dev_id, u32 *effective_speed_hz)
 {
-	struct mcp25xxfd_map_buf_nocrc *buf_rx;
-	struct mcp25xxfd_map_buf_nocrc *buf_tx;
+	struct mcp251xfd_map_buf_nocrc *buf_rx;
+	struct mcp251xfd_map_buf_nocrc *buf_tx;
 	struct spi_transfer xfer[2] = { };
 	int err;
 
@@ -2558,7 +2565,7 @@ mcp25xxfd_register_get_dev_id(const struct mcp25xxfd_priv *priv,
 	xfer[1].rx_buf = buf_rx->data;
 	xfer[1].len = sizeof(dev_id);
 
-	mcp25xxfd_spi_cmd_read_nocrc(&buf_tx->cmd, MCP25XXFD_REG_DEVID);
+	mcp251xfd_spi_cmd_read_nocrc(&buf_tx->cmd, MCP251XFD_REG_DEVID);
 	err = spi_sync_transfer(priv->spi, xfer, ARRAY_SIZE(xfer));
 	if (err)
 		goto out_kfree_buf_tx;
@@ -2574,32 +2581,32 @@ mcp25xxfd_register_get_dev_id(const struct mcp25xxfd_priv *priv,
 	return 0;
 }
 
-#define MCP25XXFD_QUIRK_ACTIVE(quirk) \
-	(priv->devtype_data.quirks & MCP25XXFD_QUIRK_##quirk ? '+' : '-')
+#define MCP251XFD_QUIRK_ACTIVE(quirk) \
+	(priv->devtype_data.quirks & MCP251XFD_QUIRK_##quirk ? '+' : '-')
 
 static int
-mcp25xxfd_register_done(const struct mcp25xxfd_priv *priv)
+mcp251xfd_register_done(const struct mcp251xfd_priv *priv)
 {
 	u32 dev_id, effective_speed_hz;
 	int err;
 
-	err = mcp25xxfd_register_get_dev_id(priv, &dev_id,
+	err = mcp251xfd_register_get_dev_id(priv, &dev_id,
 					    &effective_speed_hz);
 	if (err)
 		return err;
 
 	netdev_info(priv->ndev,
 		    "%s rev%lu.%lu (%cRX_INT %cMAB_NO_WARN %cCRC_REG %cCRC_RX %cCRC_TX %cECC %cHD c:%u.%02uMHz m:%u.%02uMHz r:%u.%02uMHz e:%u.%02uMHz) successfully initialized.\n",
-		    mcp25xxfd_get_model_str(priv),
-		    FIELD_GET(MCP25XXFD_REG_DEVID_ID_MASK, dev_id),
-		    FIELD_GET(MCP25XXFD_REG_DEVID_REV_MASK, dev_id),
+		    mcp251xfd_get_model_str(priv),
+		    FIELD_GET(MCP251XFD_REG_DEVID_ID_MASK, dev_id),
+		    FIELD_GET(MCP251XFD_REG_DEVID_REV_MASK, dev_id),
 		    priv->rx_int ? '+' : '-',
-		    MCP25XXFD_QUIRK_ACTIVE(MAB_NO_WARN),
-		    MCP25XXFD_QUIRK_ACTIVE(CRC_REG),
-		    MCP25XXFD_QUIRK_ACTIVE(CRC_RX),
-		    MCP25XXFD_QUIRK_ACTIVE(CRC_TX),
-		    MCP25XXFD_QUIRK_ACTIVE(ECC),
-		    MCP25XXFD_QUIRK_ACTIVE(HALF_DUPLEX),
+		    MCP251XFD_QUIRK_ACTIVE(MAB_NO_WARN),
+		    MCP251XFD_QUIRK_ACTIVE(CRC_REG),
+		    MCP251XFD_QUIRK_ACTIVE(CRC_RX),
+		    MCP251XFD_QUIRK_ACTIVE(CRC_TX),
+		    MCP251XFD_QUIRK_ACTIVE(ECC),
+		    MCP251XFD_QUIRK_ACTIVE(HALF_DUPLEX),
 		    priv->can.clock.freq / 1000000,
 		    priv->can.clock.freq % 1000000 / 1000 / 10,
 		    priv->spi_max_speed_hz_orig / 1000000,
@@ -2612,12 +2619,12 @@ mcp25xxfd_register_done(const struct mcp25xxfd_priv *priv)
 	return 0;
 }
 
-static int mcp25xxfd_register(struct mcp25xxfd_priv *priv)
+static int mcp251xfd_register(struct mcp251xfd_priv *priv)
 {
 	struct net_device *ndev = priv->ndev;
 	int err;
 
-	err = mcp25xxfd_clks_and_vdd_enable(priv);
+	err = mcp251xfd_clks_and_vdd_enable(priv);
 	if (err)
 		return err;
 
@@ -2627,19 +2634,19 @@ static int mcp25xxfd_register(struct mcp25xxfd_priv *priv)
 		goto out_runtime_put_noidle;
 	pm_runtime_enable(ndev->dev.parent);
 
-	mcp25xxfd_register_quirks(priv);
+	mcp251xfd_register_quirks(priv);
 
-	err = mcp25xxfd_chip_softreset(priv);
+	err = mcp251xfd_chip_softreset(priv);
 	if (err == -ENODEV)
 		goto out_runtime_disable;
 	if (err)
 		goto out_chip_set_mode_sleep;
 
-	err = mcp25xxfd_register_chip_detect(priv);
+	err = mcp251xfd_register_chip_detect(priv);
 	if (err)
 		goto out_chip_set_mode_sleep;
 
-	err = mcp25xxfd_register_check_rx_int(priv);
+	err = mcp251xfd_register_check_rx_int(priv);
 	if (err)
 		goto out_chip_set_mode_sleep;
 
@@ -2647,7 +2654,7 @@ static int mcp25xxfd_register(struct mcp25xxfd_priv *priv)
 	if (err)
 		goto out_chip_set_mode_sleep;
 
-	err = mcp25xxfd_register_done(priv);
+	err = mcp251xfd_register_done(priv);
 	if (err)
 		goto out_unregister_candev;
 
@@ -2655,7 +2662,7 @@ static int mcp25xxfd_register(struct mcp25xxfd_priv *priv)
 	 * disable the clocks and vdd. If CONFIG_PM is not enabled,
 	 * the clocks and vdd will stay powered.
 	 */
-	err = mcp25xxfd_chip_set_mode(priv, MCP25XXFD_REG_CON_MODE_SLEEP);
+	err = mcp251xfd_chip_set_mode(priv, MCP251XFD_REG_CON_MODE_SLEEP);
 	if (err)
 		goto out_unregister_candev;
 
@@ -2666,17 +2673,17 @@ static int mcp25xxfd_register(struct mcp25xxfd_priv *priv)
  out_unregister_candev:
 	unregister_candev(ndev);
  out_chip_set_mode_sleep:
-	mcp25xxfd_chip_set_mode(priv, MCP25XXFD_REG_CON_MODE_SLEEP);
+	mcp251xfd_chip_set_mode(priv, MCP251XFD_REG_CON_MODE_SLEEP);
  out_runtime_disable:
 	pm_runtime_disable(ndev->dev.parent);
  out_runtime_put_noidle:
 	pm_runtime_put_noidle(ndev->dev.parent);
-	mcp25xxfd_clks_and_vdd_disable(priv);
+	mcp251xfd_clks_and_vdd_disable(priv);
 
 	return err;
 }
 
-static inline void mcp25xxfd_unregister(struct mcp25xxfd_priv *priv)
+static inline void mcp251xfd_unregister(struct mcp251xfd_priv *priv)
 {
 	struct net_device *ndev	= priv->ndev;
 
@@ -2684,47 +2691,47 @@ static inline void mcp25xxfd_unregister(struct mcp25xxfd_priv *priv)
 
 	pm_runtime_get_sync(ndev->dev.parent);
 	pm_runtime_put_noidle(ndev->dev.parent);
-	mcp25xxfd_clks_and_vdd_disable(priv);
+	mcp251xfd_clks_and_vdd_disable(priv);
 	pm_runtime_disable(ndev->dev.parent);
 }
 
-static const struct of_device_id mcp25xxfd_of_match[] = {
+static const struct of_device_id mcp251xfd_of_match[] = {
 	{
 		.compatible = "microchip,mcp2517fd",
-		.data = &mcp25xxfd_devtype_data_mcp2517fd,
+		.data = &mcp251xfd_devtype_data_mcp2517fd,
 	}, {
 		.compatible = "microchip,mcp2518fd",
-		.data = &mcp25xxfd_devtype_data_mcp2518fd,
+		.data = &mcp251xfd_devtype_data_mcp2518fd,
 	}, {
-		.compatible = "microchip,mcp25xxfd",
-		.data = &mcp25xxfd_devtype_data_mcp25xxfd,
+		.compatible = "microchip,mcp251xfd",
+		.data = &mcp251xfd_devtype_data_mcp251xfd,
 	}, {
 		/* sentinel */
 	},
 };
-MODULE_DEVICE_TABLE(of, mcp25xxfd_of_match);
+MODULE_DEVICE_TABLE(of, mcp251xfd_of_match);
 
-static const struct spi_device_id mcp25xxfd_id_table[] = {
+static const struct spi_device_id mcp251xfd_id_table[] = {
 	{
 		.name = "mcp2517fd",
-		.driver_data = (kernel_ulong_t)&mcp25xxfd_devtype_data_mcp2517fd,
+		.driver_data = (kernel_ulong_t)&mcp251xfd_devtype_data_mcp2517fd,
 	}, {
 		.name = "mcp2518fd",
-		.driver_data = (kernel_ulong_t)&mcp25xxfd_devtype_data_mcp2518fd,
+		.driver_data = (kernel_ulong_t)&mcp251xfd_devtype_data_mcp2518fd,
 	}, {
-		.name = "mcp25xxfd",
-		.driver_data = (kernel_ulong_t)&mcp25xxfd_devtype_data_mcp25xxfd,
+		.name = "mcp251xfd",
+		.driver_data = (kernel_ulong_t)&mcp251xfd_devtype_data_mcp251xfd,
 	}, {
 		/* sentinel */
 	},
 };
-MODULE_DEVICE_TABLE(spi, mcp25xxfd_id_table);
+MODULE_DEVICE_TABLE(spi, mcp251xfd_id_table);
 
-static int mcp25xxfd_probe(struct spi_device *spi)
+static int mcp251xfd_probe(struct spi_device *spi)
 {
 	const void *match;
 	struct net_device *ndev;
-	struct mcp25xxfd_priv *priv;
+	struct mcp251xfd_priv *priv;
 	struct gpio_desc *rx_int;
 	struct regulator *reg_vdd, *reg_xceiver;
 	struct clk *clk;
@@ -2762,39 +2769,39 @@ static int mcp25xxfd_probe(struct spi_device *spi)
 	freq = clk_get_rate(clk);
 
 	/* Sanity check */
-	if (freq < MCP25XXFD_SYSCLOCK_HZ_MIN ||
-	    freq > MCP25XXFD_SYSCLOCK_HZ_MAX) {
+	if (freq < MCP251XFD_SYSCLOCK_HZ_MIN ||
+	    freq > MCP251XFD_SYSCLOCK_HZ_MAX) {
 		dev_err(&spi->dev,
 			"Oscillator frequency (%u Hz) is too low or high.\n",
 			freq);
 		return -ERANGE;
 	}
 
-	if (freq <= MCP25XXFD_SYSCLOCK_HZ_MAX / MCP25XXFD_OSC_PLL_MULTIPLIER) {
+	if (freq <= MCP251XFD_SYSCLOCK_HZ_MAX / MCP251XFD_OSC_PLL_MULTIPLIER) {
 		dev_err(&spi->dev,
 			"Oscillator frequency (%u Hz) is too low and PLL is not supported.\n",
 			freq);
 		return -ERANGE;
 	}
 
-	ndev = alloc_candev(sizeof(struct mcp25xxfd_priv),
-			    MCP25XXFD_TX_OBJ_NUM_MAX);
+	ndev = alloc_candev(sizeof(struct mcp251xfd_priv),
+			    MCP251XFD_TX_OBJ_NUM_MAX);
 	if (!ndev)
 		return -ENOMEM;
 
 	SET_NETDEV_DEV(ndev, &spi->dev);
 
-	ndev->netdev_ops = &mcp25xxfd_netdev_ops;
+	ndev->netdev_ops = &mcp251xfd_netdev_ops;
 	ndev->irq = spi->irq;
 	ndev->flags |= IFF_ECHO;
 
 	priv = netdev_priv(ndev);
 	spi_set_drvdata(spi, priv);
 	priv->can.clock.freq = freq;
-	priv->can.do_set_mode = mcp25xxfd_set_mode;
-	priv->can.do_get_berr_counter = mcp25xxfd_get_berr_counter;
-	priv->can.bittiming_const = &mcp25xxfd_bittiming_const;
-	priv->can.data_bittiming_const = &mcp25xxfd_data_bittiming_const;
+	priv->can.do_set_mode = mcp251xfd_set_mode;
+	priv->can.do_get_berr_counter = mcp251xfd_get_berr_counter;
+	priv->can.bittiming_const = &mcp251xfd_bittiming_const;
+	priv->can.data_bittiming_const = &mcp251xfd_data_bittiming_const;
 	priv->can.ctrlmode_supported = CAN_CTRLMODE_LISTENONLY |
 		CAN_CTRLMODE_BERR_REPORTING | CAN_CTRLMODE_FD |
 		CAN_CTRLMODE_FD_NON_ISO;
@@ -2807,16 +2814,26 @@ static int mcp25xxfd_probe(struct spi_device *spi)
 
 	match = device_get_match_data(&spi->dev);
 	if (match)
-		priv->devtype_data = *(struct mcp25xxfd_devtype_data *)match;
+		priv->devtype_data = *(struct mcp251xfd_devtype_data *)match;
 	else
-		priv->devtype_data = *(struct mcp25xxfd_devtype_data *)
+		priv->devtype_data = *(struct mcp251xfd_devtype_data *)
 			spi_get_device_id(spi)->driver_data;
 
-	/* According to the datasheet the SPI clock must be less or
-	 * equal SYSCLOCK / 2.
+	/* Errata Reference:
+	 * mcp2517fd: DS80000789B, mcp2518fd: DS80000792C 4.
+	 *
+	 * The SPI can write corrupted data to the RAM at fast SPI
+	 * speeds:
+	 *
+	 * Simultaneous activity on the CAN bus while writing data to
+	 * RAM via the SPI interface, with high SCK frequency, can
+	 * lead to corrupted data being written to RAM.
+	 *
+	 * Fix/Work Around:
+	 * Ensure that FSCK is less than or equal to 0.85 *
+	 * (FSYSCLK/2).
 	 *
-	 * It turns out, that the Controller is not stable at this
-	 * rate. Known good and bad combinations are:
+	 * Known good and bad combinations are:
 	 *
 	 * MCP	ext-clk	SoC			SPI			SPI-clk		max-clk	parent-clk	Status	config
 	 *
@@ -2829,7 +2846,6 @@ static int mcp25xxfd_probe(struct spi_device *spi)
 	 * 2517 40 MHz	atmel,sama5d27		atmel,at91rm9200-spi	16400000 Hz	 82.00%	 82000000 Hz	good	default
 	 * 2518 40 MHz	atmel,sama5d27		atmel,at91rm9200-spi	16400000 Hz	 82.00%	 82000000 Hz	good	default
 	 *
-	 * Limit SPI clock to 85% of SYSCLOCK / 2 for now.
 	 */
 	priv->spi_max_speed_hz_orig = spi->max_speed_hz;
 	spi->max_speed_hz = min(spi->max_speed_hz, freq / 2 / 1000 * 850);
@@ -2839,16 +2855,16 @@ static int mcp25xxfd_probe(struct spi_device *spi)
 	if (err)
 		goto out_free_candev;
 
-	err = mcp25xxfd_regmap_init(priv);
+	err = mcp251xfd_regmap_init(priv);
 	if (err)
 		goto out_free_candev;
 
 	err = can_rx_offload_add_manual(ndev, &priv->offload,
-					MCP25XXFD_NAPI_WEIGHT);
+					MCP251XFD_NAPI_WEIGHT);
 	if (err)
 		goto out_free_candev;
 
-	err = mcp25xxfd_register(priv);
+	err = mcp251xfd_register(priv);
 	if (err)
 		goto out_free_candev;
 
@@ -2862,50 +2878,50 @@ static int mcp25xxfd_probe(struct spi_device *spi)
 	return err;
 }
 
-static int mcp25xxfd_remove(struct spi_device *spi)
+static int mcp251xfd_remove(struct spi_device *spi)
 {
-	struct mcp25xxfd_priv *priv = spi_get_drvdata(spi);
+	struct mcp251xfd_priv *priv = spi_get_drvdata(spi);
 	struct net_device *ndev = priv->ndev;
 
 	can_rx_offload_del(&priv->offload);
-	mcp25xxfd_unregister(priv);
+	mcp251xfd_unregister(priv);
 	spi->max_speed_hz = priv->spi_max_speed_hz_orig;
 	free_candev(ndev);
 
 	return 0;
 }
 
-static int __maybe_unused mcp25xxfd_runtime_suspend(struct device *device)
+static int __maybe_unused mcp251xfd_runtime_suspend(struct device *device)
 {
-	const struct mcp25xxfd_priv *priv = dev_get_drvdata(device);
+	const struct mcp251xfd_priv *priv = dev_get_drvdata(device);
 
-	return mcp25xxfd_clks_and_vdd_disable(priv);
+	return mcp251xfd_clks_and_vdd_disable(priv);
 }
 
-static int __maybe_unused mcp25xxfd_runtime_resume(struct device *device)
+static int __maybe_unused mcp251xfd_runtime_resume(struct device *device)
 {
-	const struct mcp25xxfd_priv *priv = dev_get_drvdata(device);
+	const struct mcp251xfd_priv *priv = dev_get_drvdata(device);
 
-	return mcp25xxfd_clks_and_vdd_enable(priv);
+	return mcp251xfd_clks_and_vdd_enable(priv);
 }
 
-static const struct dev_pm_ops mcp25xxfd_pm_ops = {
-	SET_RUNTIME_PM_OPS(mcp25xxfd_runtime_suspend,
-			   mcp25xxfd_runtime_resume, NULL)
+static const struct dev_pm_ops mcp251xfd_pm_ops = {
+	SET_RUNTIME_PM_OPS(mcp251xfd_runtime_suspend,
+			   mcp251xfd_runtime_resume, NULL)
 };
 
-static struct spi_driver mcp25xxfd_driver = {
+static struct spi_driver mcp251xfd_driver = {
 	.driver = {
 		.name = DEVICE_NAME,
-		.pm = &mcp25xxfd_pm_ops,
-		.of_match_table = mcp25xxfd_of_match,
+		.pm = &mcp251xfd_pm_ops,
+		.of_match_table = mcp251xfd_of_match,
 	},
-	.probe = mcp25xxfd_probe,
-	.remove = mcp25xxfd_remove,
-	.id_table = mcp25xxfd_id_table,
+	.probe = mcp251xfd_probe,
+	.remove = mcp251xfd_remove,
+	.id_table = mcp251xfd_id_table,
 };
-module_spi_driver(mcp25xxfd_driver);
+module_spi_driver(mcp251xfd_driver);
 
 MODULE_AUTHOR("Marc Kleine-Budde <mkl@pengutronix.de>");
-MODULE_DESCRIPTION("Microchip MCP25xxFD Family CAN controller driver");
+MODULE_DESCRIPTION("Microchip MCP251xFD Family CAN controller driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/net/can/spi/mcp25xxfd/mcp25xxfd-crc16.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-crc16.c
index 79d09aaebf33..a02ca76ac239 100644
--- a/drivers/net/can/spi/mcp25xxfd/mcp25xxfd-crc16.c
+++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-crc16.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 //
-// mcp25xxfd - Microchip MCP25xxFD Family CAN controller driver
+// mcp251xfd - Microchip MCP251xFD Family CAN controller driver
 //
 // Copyright (c) 2020 Pengutronix,
 //                    Marc Kleine-Budde <kernel@pengutronix.de>
@@ -12,7 +12,7 @@
 // Copyright (c) 2019 Martin Sperl <kernel@martin.sperl.org>
 //
 
-#include "mcp25xxfd.h"
+#include "mcp251xfd.h"
 
 /* The standard crc16 in linux/crc16.h is unfortunately not computing
  * the correct results (left shift vs. right shift). So here an
@@ -20,7 +20,7 @@
  *
  * http://lkml.iu.edu/hypermail/linux/kernel/0508.1/1085.html
  */
-static const u16 mcp25xxfd_crc16_table[] = {
+static const u16 mcp251xfd_crc16_table[] = {
 	0x0000, 0x8005, 0x800f, 0x000a, 0x801b, 0x001e, 0x0014, 0x8011,
 	0x8033, 0x0036, 0x003c, 0x8039, 0x0028, 0x802d, 0x8027, 0x0022,
 	0x8063, 0x0066, 0x006c, 0x8069, 0x0078, 0x807d, 0x8077, 0x0072,
@@ -55,35 +55,35 @@ static const u16 mcp25xxfd_crc16_table[] = {
 	0x8213, 0x0216, 0x021c, 0x8219, 0x0208, 0x820d, 0x8207, 0x0202
 };
 
-static inline u16 mcp25xxfd_crc16_byte(u16 crc, const u8 data)
+static inline u16 mcp251xfd_crc16_byte(u16 crc, const u8 data)
 {
 	u8 index = (crc >> 8) ^ data;
 
-	return (crc << 8) ^ mcp25xxfd_crc16_table[index];
+	return (crc << 8) ^ mcp251xfd_crc16_table[index];
 }
 
-static u16 mcp25xxfd_crc16(u16 crc, u8 const *buffer, size_t len)
+static u16 mcp251xfd_crc16(u16 crc, u8 const *buffer, size_t len)
 {
 	while (len--)
-		crc = mcp25xxfd_crc16_byte(crc, *buffer++);
+		crc = mcp251xfd_crc16_byte(crc, *buffer++);
 
 	return crc;
 }
 
-u16 mcp25xxfd_crc16_compute(const void *data, size_t data_size)
+u16 mcp251xfd_crc16_compute(const void *data, size_t data_size)
 {
 	u16 crc = 0xffff;
 
-	return mcp25xxfd_crc16(crc, data, data_size);
+	return mcp251xfd_crc16(crc, data, data_size);
 }
 
-u16 mcp25xxfd_crc16_compute2(const void *cmd, size_t cmd_size,
+u16 mcp251xfd_crc16_compute2(const void *cmd, size_t cmd_size,
 			     const void *data, size_t data_size)
 {
 	u16 crc;
 
-	crc = mcp25xxfd_crc16_compute(cmd, cmd_size);
-	crc = mcp25xxfd_crc16(crc, data, data_size);
+	crc = mcp251xfd_crc16_compute(cmd, cmd_size);
+	crc = mcp251xfd_crc16(crc, data, data_size);
 
 	return crc;
 }
diff --git a/drivers/net/can/spi/mcp25xxfd/mcp25xxfd-regmap.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-regmap.c
index 376649c7e443..ba25902dd78c 100644
--- a/drivers/net/can/spi/mcp25xxfd/mcp25xxfd-regmap.c
+++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-regmap.c
@@ -1,19 +1,19 @@
 // SPDX-License-Identifier: GPL-2.0
 //
-// mcp25xxfd - Microchip MCP25xxFD Family CAN controller driver
+// mcp251xfd - Microchip MCP251xFD Family CAN controller driver
 //
 // Copyright (c) 2019, 2020 Pengutronix,
 //                          Marc Kleine-Budde <kernel@pengutronix.de>
 //
 
-#include "mcp25xxfd.h"
+#include "mcp251xfd.h"
 
 #include <asm/unaligned.h>
 
-static const struct regmap_config mcp25xxfd_regmap_crc;
+static const struct regmap_config mcp251xfd_regmap_crc;
 
 static int
-mcp25xxfd_regmap_nocrc_write(void *context, const void *data, size_t count)
+mcp251xfd_regmap_nocrc_write(void *context, const void *data, size_t count)
 {
 	struct spi_device *spi = context;
 
@@ -21,13 +21,13 @@ mcp25xxfd_regmap_nocrc_write(void *context, const void *data, size_t count)
 }
 
 static int
-mcp25xxfd_regmap_nocrc_gather_write(void *context,
+mcp251xfd_regmap_nocrc_gather_write(void *context,
 				    const void *reg, size_t reg_len,
 				    const void *val, size_t val_len)
 {
 	struct spi_device *spi = context;
-	struct mcp25xxfd_priv *priv = spi_get_drvdata(spi);
-	struct mcp25xxfd_map_buf_nocrc *buf_tx = priv->map_buf_nocrc_tx;
+	struct mcp251xfd_priv *priv = spi_get_drvdata(spi);
+	struct mcp251xfd_map_buf_nocrc *buf_tx = priv->map_buf_nocrc_tx;
 	struct spi_transfer xfer[] = {
 		{
 			.tx_buf = buf_tx,
@@ -37,7 +37,7 @@ mcp25xxfd_regmap_nocrc_gather_write(void *context,
 
 	BUILD_BUG_ON(sizeof(buf_tx->cmd) != sizeof(__be16));
 
-	if (IS_ENABLED(CONFIG_CAN_MCP25XXFD_SANITY) &&
+	if (IS_ENABLED(CONFIG_CAN_MCP251XFD_SANITY) &&
 	    reg_len != sizeof(buf_tx->cmd.cmd))
 		return -EINVAL;
 
@@ -47,20 +47,20 @@ mcp25xxfd_regmap_nocrc_gather_write(void *context,
 	return spi_sync_transfer(spi, xfer, ARRAY_SIZE(xfer));
 }
 
-static inline bool mcp25xxfd_update_bits_read_reg(unsigned int reg)
+static inline bool mcp251xfd_update_bits_read_reg(unsigned int reg)
 {
 	switch (reg) {
-	case MCP25XXFD_REG_INT:
-	case MCP25XXFD_REG_TEFCON:
-	case MCP25XXFD_REG_FIFOCON(MCP25XXFD_RX_FIFO(0)):
-	case MCP25XXFD_REG_FLTCON(0):
-	case MCP25XXFD_REG_ECCSTAT:
-	case MCP25XXFD_REG_CRC:
+	case MCP251XFD_REG_INT:
+	case MCP251XFD_REG_TEFCON:
+	case MCP251XFD_REG_FIFOCON(MCP251XFD_RX_FIFO(0)):
+	case MCP251XFD_REG_FLTCON(0):
+	case MCP251XFD_REG_ECCSTAT:
+	case MCP251XFD_REG_CRC:
 		return false;
-	case MCP25XXFD_REG_CON:
-	case MCP25XXFD_REG_FIFOSTA(MCP25XXFD_RX_FIFO(0)):
-	case MCP25XXFD_REG_OSC:
-	case MCP25XXFD_REG_ECCCON:
+	case MCP251XFD_REG_CON:
+	case MCP251XFD_REG_FIFOSTA(MCP251XFD_RX_FIFO(0)):
+	case MCP251XFD_REG_OSC:
+	case MCP251XFD_REG_ECCCON:
 		return true;
 	default:
 		WARN(1, "Status of reg 0x%04x unknown.\n", reg);
@@ -70,13 +70,13 @@ static inline bool mcp25xxfd_update_bits_read_reg(unsigned int reg)
 }
 
 static int
-mcp25xxfd_regmap_nocrc_update_bits(void *context, unsigned int reg,
+mcp251xfd_regmap_nocrc_update_bits(void *context, unsigned int reg,
 				   unsigned int mask, unsigned int val)
 {
 	struct spi_device *spi = context;
-	struct mcp25xxfd_priv *priv = spi_get_drvdata(spi);
-	struct mcp25xxfd_map_buf_nocrc *buf_rx = priv->map_buf_nocrc_rx;
-	struct mcp25xxfd_map_buf_nocrc *buf_tx = priv->map_buf_nocrc_tx;
+	struct mcp251xfd_priv *priv = spi_get_drvdata(spi);
+	struct mcp251xfd_map_buf_nocrc *buf_rx = priv->map_buf_nocrc_rx;
+	struct mcp251xfd_map_buf_nocrc *buf_tx = priv->map_buf_nocrc_tx;
 	__le32 orig_le32 = 0, mask_le32, val_le32, tmp_le32;
 	u8 first_byte, last_byte, len;
 	int err;
@@ -84,22 +84,22 @@ mcp25xxfd_regmap_nocrc_update_bits(void *context, unsigned int reg,
 	BUILD_BUG_ON(sizeof(buf_rx->cmd) != sizeof(__be16));
 	BUILD_BUG_ON(sizeof(buf_tx->cmd) != sizeof(__be16));
 
-	if (IS_ENABLED(CONFIG_CAN_MCP25XXFD_SANITY) &&
+	if (IS_ENABLED(CONFIG_CAN_MCP251XFD_SANITY) &&
 	    mask == 0)
 		return -EINVAL;
 
-	first_byte = mcp25xxfd_first_byte_set(mask);
-	last_byte = mcp25xxfd_last_byte_set(mask);
+	first_byte = mcp251xfd_first_byte_set(mask);
+	last_byte = mcp251xfd_last_byte_set(mask);
 	len = last_byte - first_byte + 1;
 
-	if (mcp25xxfd_update_bits_read_reg(reg)) {
+	if (mcp251xfd_update_bits_read_reg(reg)) {
 		struct spi_transfer xfer[2] = { };
 		struct spi_message msg;
 
 		spi_message_init(&msg);
 		spi_message_add_tail(&xfer[0], &msg);
 
-		if (priv->devtype_data.quirks & MCP25XXFD_QUIRK_HALF_DUPLEX) {
+		if (priv->devtype_data.quirks & MCP251XFD_QUIRK_HALF_DUPLEX) {
 			xfer[0].tx_buf = buf_tx;
 			xfer[0].len = sizeof(buf_tx->cmd);
 
@@ -111,11 +111,11 @@ mcp25xxfd_regmap_nocrc_update_bits(void *context, unsigned int reg,
 			xfer[0].rx_buf = buf_rx;
 			xfer[0].len = sizeof(buf_tx->cmd) + len;
 
-			if (MCP25XXFD_SANITIZE_SPI)
+			if (MCP251XFD_SANITIZE_SPI)
 				memset(buf_tx->data, 0x0, len);
 		}
 
-		mcp25xxfd_spi_cmd_read_nocrc(&buf_tx->cmd, reg + first_byte);
+		mcp251xfd_spi_cmd_read_nocrc(&buf_tx->cmd, reg + first_byte);
 		err = spi_sync(spi, &msg);
 		if (err)
 			return err;
@@ -129,21 +129,21 @@ mcp25xxfd_regmap_nocrc_update_bits(void *context, unsigned int reg,
 	tmp_le32 = orig_le32 & ~mask_le32;
 	tmp_le32 |= val_le32 & mask_le32;
 
-	mcp25xxfd_spi_cmd_write_nocrc(&buf_tx->cmd, reg + first_byte);
+	mcp251xfd_spi_cmd_write_nocrc(&buf_tx->cmd, reg + first_byte);
 	memcpy(buf_tx->data, &tmp_le32, len);
 
 	return spi_write(spi, buf_tx, sizeof(buf_tx->cmd) + len);
 }
 
 static int
-mcp25xxfd_regmap_nocrc_read(void *context,
+mcp251xfd_regmap_nocrc_read(void *context,
 			    const void *reg, size_t reg_len,
 			    void *val_buf, size_t val_len)
 {
 	struct spi_device *spi = context;
-	struct mcp25xxfd_priv *priv = spi_get_drvdata(spi);
-	struct mcp25xxfd_map_buf_nocrc *buf_rx = priv->map_buf_nocrc_rx;
-	struct mcp25xxfd_map_buf_nocrc *buf_tx = priv->map_buf_nocrc_tx;
+	struct mcp251xfd_priv *priv = spi_get_drvdata(spi);
+	struct mcp251xfd_map_buf_nocrc *buf_rx = priv->map_buf_nocrc_rx;
+	struct mcp251xfd_map_buf_nocrc *buf_tx = priv->map_buf_nocrc_tx;
 	struct spi_transfer xfer[2] = { };
 	struct spi_message msg;
 	int err;
@@ -151,14 +151,14 @@ mcp25xxfd_regmap_nocrc_read(void *context,
 	BUILD_BUG_ON(sizeof(buf_rx->cmd) != sizeof(__be16));
 	BUILD_BUG_ON(sizeof(buf_tx->cmd) != sizeof(__be16));
 
-	if (IS_ENABLED(CONFIG_CAN_MCP25XXFD_SANITY) &&
+	if (IS_ENABLED(CONFIG_CAN_MCP251XFD_SANITY) &&
 	    reg_len != sizeof(buf_tx->cmd.cmd))
 		return -EINVAL;
 
 	spi_message_init(&msg);
 	spi_message_add_tail(&xfer[0], &msg);
 
-	if (priv->devtype_data.quirks & MCP25XXFD_QUIRK_HALF_DUPLEX) {
+	if (priv->devtype_data.quirks & MCP251XFD_QUIRK_HALF_DUPLEX) {
 		xfer[0].tx_buf = reg;
 		xfer[0].len = sizeof(buf_tx->cmd);
 
@@ -171,7 +171,7 @@ mcp25xxfd_regmap_nocrc_read(void *context,
 		xfer[0].len = sizeof(buf_tx->cmd) + val_len;
 
 		memcpy(&buf_tx->cmd, reg, sizeof(buf_tx->cmd));
-		if (MCP25XXFD_SANITIZE_SPI)
+		if (MCP251XFD_SANITIZE_SPI)
 			memset(buf_tx->data, 0x0, val_len);
 	};
 
@@ -179,20 +179,20 @@ mcp25xxfd_regmap_nocrc_read(void *context,
 	if (err)
 		return err;
 
-	if (!(priv->devtype_data.quirks & MCP25XXFD_QUIRK_HALF_DUPLEX))
+	if (!(priv->devtype_data.quirks & MCP251XFD_QUIRK_HALF_DUPLEX))
 		memcpy(val_buf, buf_rx->data, val_len);
 
 	return 0;
 }
 
 static int
-mcp25xxfd_regmap_crc_gather_write(void *context,
+mcp251xfd_regmap_crc_gather_write(void *context,
 				  const void *reg_p, size_t reg_len,
 				  const void *val, size_t val_len)
 {
 	struct spi_device *spi = context;
-	struct mcp25xxfd_priv *priv = spi_get_drvdata(spi);
-	struct mcp25xxfd_map_buf_crc *buf_tx = priv->map_buf_crc_tx;
+	struct mcp251xfd_priv *priv = spi_get_drvdata(spi);
+	struct mcp251xfd_map_buf_crc *buf_tx = priv->map_buf_crc_tx;
 	struct spi_transfer xfer[] = {
 		{
 			.tx_buf = buf_tx,
@@ -205,39 +205,39 @@ mcp25xxfd_regmap_crc_gather_write(void *context,
 
 	BUILD_BUG_ON(sizeof(buf_tx->cmd) != sizeof(__be16) + sizeof(u8));
 
-	if (IS_ENABLED(CONFIG_CAN_MCP25XXFD_SANITY) &&
+	if (IS_ENABLED(CONFIG_CAN_MCP251XFD_SANITY) &&
 	    reg_len != sizeof(buf_tx->cmd.cmd) +
-	    mcp25xxfd_regmap_crc.pad_bits / BITS_PER_BYTE)
+	    mcp251xfd_regmap_crc.pad_bits / BITS_PER_BYTE)
 		return -EINVAL;
 
-	mcp25xxfd_spi_cmd_write_crc(&buf_tx->cmd, reg, val_len);
+	mcp251xfd_spi_cmd_write_crc(&buf_tx->cmd, reg, val_len);
 	memcpy(buf_tx->data, val, val_len);
 
-	crc = mcp25xxfd_crc16_compute(buf_tx, sizeof(buf_tx->cmd) + val_len);
+	crc = mcp251xfd_crc16_compute(buf_tx, sizeof(buf_tx->cmd) + val_len);
 	put_unaligned_be16(crc, buf_tx->data + val_len);
 
 	return spi_sync_transfer(spi, xfer, ARRAY_SIZE(xfer));
 }
 
 static int
-mcp25xxfd_regmap_crc_write(void *context,
+mcp251xfd_regmap_crc_write(void *context,
 			   const void *data, size_t count)
 {
 	const size_t data_offset = sizeof(__be16) +
-		mcp25xxfd_regmap_crc.pad_bits / BITS_PER_BYTE;
+		mcp251xfd_regmap_crc.pad_bits / BITS_PER_BYTE;
 
-	return mcp25xxfd_regmap_crc_gather_write(context,
+	return mcp251xfd_regmap_crc_gather_write(context,
 						 data, data_offset,
 						 data + data_offset,
 						 count - data_offset);
 }
 
 static int
-mcp25xxfd_regmap_crc_read_one(struct mcp25xxfd_priv *priv,
+mcp251xfd_regmap_crc_read_one(struct mcp251xfd_priv *priv,
 			      struct spi_message *msg, unsigned int data_len)
 {
-	const struct mcp25xxfd_map_buf_crc *buf_rx = priv->map_buf_crc_rx;
-	const struct mcp25xxfd_map_buf_crc *buf_tx = priv->map_buf_crc_tx;
+	const struct mcp251xfd_map_buf_crc *buf_rx = priv->map_buf_crc_rx;
+	const struct mcp251xfd_map_buf_crc *buf_tx = priv->map_buf_crc_tx;
 	u16 crc_received, crc_calculated;
 	int err;
 
@@ -249,7 +249,7 @@ mcp25xxfd_regmap_crc_read_one(struct mcp25xxfd_priv *priv,
 		return err;
 
 	crc_received = get_unaligned_be16(buf_rx->data + data_len);
-	crc_calculated = mcp25xxfd_crc16_compute2(&buf_tx->cmd,
+	crc_calculated = mcp251xfd_crc16_compute2(&buf_tx->cmd,
 						  sizeof(buf_tx->cmd),
 						  buf_rx->data,
 						  data_len);
@@ -260,14 +260,14 @@ mcp25xxfd_regmap_crc_read_one(struct mcp25xxfd_priv *priv,
 }
 
 static int
-mcp25xxfd_regmap_crc_read(void *context,
+mcp251xfd_regmap_crc_read(void *context,
 			  const void *reg_p, size_t reg_len,
 			  void *val_buf, size_t val_len)
 {
 	struct spi_device *spi = context;
-	struct mcp25xxfd_priv *priv = spi_get_drvdata(spi);
-	struct mcp25xxfd_map_buf_crc *buf_rx = priv->map_buf_crc_rx;
-	struct mcp25xxfd_map_buf_crc *buf_tx = priv->map_buf_crc_tx;
+	struct mcp251xfd_priv *priv = spi_get_drvdata(spi);
+	struct mcp251xfd_map_buf_crc *buf_rx = priv->map_buf_crc_rx;
+	struct mcp251xfd_map_buf_crc *buf_tx = priv->map_buf_crc_tx;
 	struct spi_transfer xfer[2] = { };
 	struct spi_message msg;
 	u16 reg = *(u16 *)reg_p;
@@ -276,15 +276,15 @@ mcp25xxfd_regmap_crc_read(void *context,
 	BUILD_BUG_ON(sizeof(buf_rx->cmd) != sizeof(__be16) + sizeof(u8));
 	BUILD_BUG_ON(sizeof(buf_tx->cmd) != sizeof(__be16) + sizeof(u8));
 
-	if (IS_ENABLED(CONFIG_CAN_MCP25XXFD_SANITY) &&
+	if (IS_ENABLED(CONFIG_CAN_MCP251XFD_SANITY) &&
 	    reg_len != sizeof(buf_tx->cmd.cmd) +
-	    mcp25xxfd_regmap_crc.pad_bits / BITS_PER_BYTE)
+	    mcp251xfd_regmap_crc.pad_bits / BITS_PER_BYTE)
 		return -EINVAL;
 
 	spi_message_init(&msg);
 	spi_message_add_tail(&xfer[0], &msg);
 
-	if (priv->devtype_data.quirks & MCP25XXFD_QUIRK_HALF_DUPLEX) {
+	if (priv->devtype_data.quirks & MCP251XFD_QUIRK_HALF_DUPLEX) {
 		xfer[0].tx_buf = buf_tx;
 		xfer[0].len = sizeof(buf_tx->cmd);
 
@@ -297,21 +297,21 @@ mcp25xxfd_regmap_crc_read(void *context,
 		xfer[0].len = sizeof(buf_tx->cmd) + val_len +
 			sizeof(buf_tx->crc);
 
-		if (MCP25XXFD_SANITIZE_SPI)
+		if (MCP251XFD_SANITIZE_SPI)
 			memset(buf_tx->data, 0x0, val_len +
 			       sizeof(buf_tx->crc));
 	}
 
-	mcp25xxfd_spi_cmd_read_crc(&buf_tx->cmd, reg, val_len);
+	mcp251xfd_spi_cmd_read_crc(&buf_tx->cmd, reg, val_len);
 
-	for (i = 0; i < MCP25XXFD_READ_CRC_RETRIES_MAX; i++) {
-		err = mcp25xxfd_regmap_crc_read_one(priv, &msg, val_len);
+	for (i = 0; i < MCP251XFD_READ_CRC_RETRIES_MAX; i++) {
+		err = mcp251xfd_regmap_crc_read_one(priv, &msg, val_len);
 		if (!err)
 			goto out;
 		if (err != -EBADMSG)
 			return err;
 
-		/* MCP25XXFD_REG_OSC is the first ever reg we read from.
+		/* MCP251XFD_REG_OSC is the first ever reg we read from.
 		 *
 		 * The chip may be in deep sleep and this SPI transfer
 		 * (i.e. the assertion of the CS) will wake the chip
@@ -325,7 +325,7 @@ mcp25xxfd_regmap_crc_read(void *context,
 		 * to the caller. It will take care of both cases.
 		 *
 		 */
-		if (reg == MCP25XXFD_REG_OSC) {
+		if (reg == MCP251XFD_REG_OSC) {
 			err = 0;
 			goto out;
 		}
@@ -350,88 +350,88 @@ mcp25xxfd_regmap_crc_read(void *context,
 	return 0;
 }
 
-static const struct regmap_range mcp25xxfd_reg_table_yes_range[] = {
+static const struct regmap_range mcp251xfd_reg_table_yes_range[] = {
 	regmap_reg_range(0x000, 0x2ec),	/* CAN FD Controller Module SFR */
 	regmap_reg_range(0x400, 0xbfc),	/* RAM */
 	regmap_reg_range(0xe00, 0xe14),	/* MCP2517/18FD SFR */
 };
 
-static const struct regmap_access_table mcp25xxfd_reg_table = {
-	.yes_ranges = mcp25xxfd_reg_table_yes_range,
-	.n_yes_ranges = ARRAY_SIZE(mcp25xxfd_reg_table_yes_range),
+static const struct regmap_access_table mcp251xfd_reg_table = {
+	.yes_ranges = mcp251xfd_reg_table_yes_range,
+	.n_yes_ranges = ARRAY_SIZE(mcp251xfd_reg_table_yes_range),
 };
 
-static const struct regmap_config mcp25xxfd_regmap_nocrc = {
+static const struct regmap_config mcp251xfd_regmap_nocrc = {
 	.name = "nocrc",
 	.reg_bits = 16,
 	.reg_stride = 4,
 	.pad_bits = 0,
 	.val_bits = 32,
 	.max_register = 0xffc,
-	.wr_table = &mcp25xxfd_reg_table,
-	.rd_table = &mcp25xxfd_reg_table,
+	.wr_table = &mcp251xfd_reg_table,
+	.rd_table = &mcp251xfd_reg_table,
 	.cache_type = REGCACHE_NONE,
 	.read_flag_mask = (__force unsigned long)
-		cpu_to_be16(MCP25XXFD_SPI_INSTRUCTION_READ),
+		cpu_to_be16(MCP251XFD_SPI_INSTRUCTION_READ),
 	.write_flag_mask = (__force unsigned long)
-		cpu_to_be16(MCP25XXFD_SPI_INSTRUCTION_WRITE),
+		cpu_to_be16(MCP251XFD_SPI_INSTRUCTION_WRITE),
 };
 
-static const struct regmap_bus mcp25xxfd_bus_nocrc = {
-	.write = mcp25xxfd_regmap_nocrc_write,
-	.gather_write = mcp25xxfd_regmap_nocrc_gather_write,
-	.reg_update_bits = mcp25xxfd_regmap_nocrc_update_bits,
-	.read = mcp25xxfd_regmap_nocrc_read,
+static const struct regmap_bus mcp251xfd_bus_nocrc = {
+	.write = mcp251xfd_regmap_nocrc_write,
+	.gather_write = mcp251xfd_regmap_nocrc_gather_write,
+	.reg_update_bits = mcp251xfd_regmap_nocrc_update_bits,
+	.read = mcp251xfd_regmap_nocrc_read,
 	.reg_format_endian_default = REGMAP_ENDIAN_BIG,
 	.val_format_endian_default = REGMAP_ENDIAN_LITTLE,
-	.max_raw_read = sizeof_field(struct mcp25xxfd_map_buf_nocrc, data),
-	.max_raw_write = sizeof_field(struct mcp25xxfd_map_buf_nocrc, data),
+	.max_raw_read = sizeof_field(struct mcp251xfd_map_buf_nocrc, data),
+	.max_raw_write = sizeof_field(struct mcp251xfd_map_buf_nocrc, data),
 };
 
-static const struct regmap_config mcp25xxfd_regmap_crc = {
+static const struct regmap_config mcp251xfd_regmap_crc = {
 	.name = "crc",
 	.reg_bits = 16,
 	.reg_stride = 4,
 	.pad_bits = 16,		/* keep data bits aligned */
 	.val_bits = 32,
 	.max_register = 0xffc,
-	.wr_table = &mcp25xxfd_reg_table,
-	.rd_table = &mcp25xxfd_reg_table,
+	.wr_table = &mcp251xfd_reg_table,
+	.rd_table = &mcp251xfd_reg_table,
 	.cache_type = REGCACHE_NONE,
 };
 
-static const struct regmap_bus mcp25xxfd_bus_crc = {
-	.write = mcp25xxfd_regmap_crc_write,
-	.gather_write = mcp25xxfd_regmap_crc_gather_write,
-	.read = mcp25xxfd_regmap_crc_read,
+static const struct regmap_bus mcp251xfd_bus_crc = {
+	.write = mcp251xfd_regmap_crc_write,
+	.gather_write = mcp251xfd_regmap_crc_gather_write,
+	.read = mcp251xfd_regmap_crc_read,
 	.reg_format_endian_default = REGMAP_ENDIAN_NATIVE,
 	.val_format_endian_default = REGMAP_ENDIAN_LITTLE,
-	.max_raw_read = sizeof_field(struct mcp25xxfd_map_buf_crc, data),
-	.max_raw_write = sizeof_field(struct mcp25xxfd_map_buf_crc, data),
+	.max_raw_read = sizeof_field(struct mcp251xfd_map_buf_crc, data),
+	.max_raw_write = sizeof_field(struct mcp251xfd_map_buf_crc, data),
 };
 
 static inline bool
-mcp25xxfd_regmap_use_nocrc(struct mcp25xxfd_priv *priv)
+mcp251xfd_regmap_use_nocrc(struct mcp251xfd_priv *priv)
 {
-	return (!(priv->devtype_data.quirks & MCP25XXFD_QUIRK_CRC_REG)) ||
-		(!(priv->devtype_data.quirks & MCP25XXFD_QUIRK_CRC_RX));
+	return (!(priv->devtype_data.quirks & MCP251XFD_QUIRK_CRC_REG)) ||
+		(!(priv->devtype_data.quirks & MCP251XFD_QUIRK_CRC_RX));
 }
 
 static inline bool
-mcp25xxfd_regmap_use_crc(struct mcp25xxfd_priv *priv)
+mcp251xfd_regmap_use_crc(struct mcp251xfd_priv *priv)
 {
-	return (priv->devtype_data.quirks & MCP25XXFD_QUIRK_CRC_REG) ||
-		(priv->devtype_data.quirks & MCP25XXFD_QUIRK_CRC_RX);
+	return (priv->devtype_data.quirks & MCP251XFD_QUIRK_CRC_REG) ||
+		(priv->devtype_data.quirks & MCP251XFD_QUIRK_CRC_RX);
 }
 
 static int
-mcp25xxfd_regmap_init_nocrc(struct mcp25xxfd_priv *priv)
+mcp251xfd_regmap_init_nocrc(struct mcp251xfd_priv *priv)
 {
 	if (!priv->map_nocrc) {
 		struct regmap *map;
 
-		map = devm_regmap_init(&priv->spi->dev, &mcp25xxfd_bus_nocrc,
-				       priv->spi, &mcp25xxfd_regmap_nocrc);
+		map = devm_regmap_init(&priv->spi->dev, &mcp251xfd_bus_nocrc,
+				       priv->spi, &mcp251xfd_regmap_nocrc);
 		if (IS_ERR(map))
 			return PTR_ERR(map);
 
@@ -456,16 +456,16 @@ mcp25xxfd_regmap_init_nocrc(struct mcp25xxfd_priv *priv)
 			return -ENOMEM;
 	}
 
-	if (!(priv->devtype_data.quirks & MCP25XXFD_QUIRK_CRC_REG))
+	if (!(priv->devtype_data.quirks & MCP251XFD_QUIRK_CRC_REG))
 		priv->map_reg = priv->map_nocrc;
 
-	if (!(priv->devtype_data.quirks & MCP25XXFD_QUIRK_CRC_RX))
+	if (!(priv->devtype_data.quirks & MCP251XFD_QUIRK_CRC_RX))
 		priv->map_rx = priv->map_nocrc;
 
 	return 0;
 }
 
-static void mcp25xxfd_regmap_destroy_nocrc(struct mcp25xxfd_priv *priv)
+static void mcp251xfd_regmap_destroy_nocrc(struct mcp251xfd_priv *priv)
 {
 	if (priv->map_buf_nocrc_rx) {
 		devm_kfree(&priv->spi->dev, priv->map_buf_nocrc_rx);
@@ -478,13 +478,13 @@ static void mcp25xxfd_regmap_destroy_nocrc(struct mcp25xxfd_priv *priv)
 }
 
 static int
-mcp25xxfd_regmap_init_crc(struct mcp25xxfd_priv *priv)
+mcp251xfd_regmap_init_crc(struct mcp251xfd_priv *priv)
 {
 	if (!priv->map_crc) {
 		struct regmap *map;
 
-		map = devm_regmap_init(&priv->spi->dev, &mcp25xxfd_bus_crc,
-				       priv->spi, &mcp25xxfd_regmap_crc);
+		map = devm_regmap_init(&priv->spi->dev, &mcp251xfd_bus_crc,
+				       priv->spi, &mcp251xfd_regmap_crc);
 		if (IS_ERR(map))
 			return PTR_ERR(map);
 
@@ -509,16 +509,16 @@ mcp25xxfd_regmap_init_crc(struct mcp25xxfd_priv *priv)
 			return -ENOMEM;
 	}
 
-	if (priv->devtype_data.quirks & MCP25XXFD_QUIRK_CRC_REG)
+	if (priv->devtype_data.quirks & MCP251XFD_QUIRK_CRC_REG)
 		priv->map_reg = priv->map_crc;
 
-	if (priv->devtype_data.quirks & MCP25XXFD_QUIRK_CRC_RX)
+	if (priv->devtype_data.quirks & MCP251XFD_QUIRK_CRC_RX)
 		priv->map_rx = priv->map_crc;
 
 	return 0;
 }
 
-static void mcp25xxfd_regmap_destroy_crc(struct mcp25xxfd_priv *priv)
+static void mcp251xfd_regmap_destroy_crc(struct mcp251xfd_priv *priv)
 {
 	if (priv->map_buf_crc_rx) {
 		devm_kfree(&priv->spi->dev, priv->map_buf_crc_rx);
@@ -530,26 +530,26 @@ static void mcp25xxfd_regmap_destroy_crc(struct mcp25xxfd_priv *priv)
 	}
 }
 
-int mcp25xxfd_regmap_init(struct mcp25xxfd_priv *priv)
+int mcp251xfd_regmap_init(struct mcp251xfd_priv *priv)
 {
 	int err;
 
-	if (mcp25xxfd_regmap_use_nocrc(priv)) {
-		err = mcp25xxfd_regmap_init_nocrc(priv);
+	if (mcp251xfd_regmap_use_nocrc(priv)) {
+		err = mcp251xfd_regmap_init_nocrc(priv);
 
 		if (err)
 			return err;
 	} else {
-		mcp25xxfd_regmap_destroy_nocrc(priv);
+		mcp251xfd_regmap_destroy_nocrc(priv);
 	}
 
-	if (mcp25xxfd_regmap_use_crc(priv)) {
-		err = mcp25xxfd_regmap_init_crc(priv);
+	if (mcp251xfd_regmap_use_crc(priv)) {
+		err = mcp251xfd_regmap_init_crc(priv);
 
 		if (err)
 			return err;
 	} else {
-		mcp25xxfd_regmap_destroy_crc(priv);
+		mcp251xfd_regmap_destroy_crc(priv);
 	}
 
 	return 0;
diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd.h b/drivers/net/can/spi/mcp251xfd/mcp251xfd.h
new file mode 100644
index 000000000000..fa1246e39980
--- /dev/null
+++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd.h
@@ -0,0 +1,835 @@
+/* SPDX-License-Identifier: GPL-2.0
+ *
+ * mcp251xfd - Microchip MCP251xFD Family CAN controller driver
+ *
+ * Copyright (c) 2019 Pengutronix,
+ *                    Marc Kleine-Budde <kernel@pengutronix.de>
+ * Copyright (c) 2019 Martin Sperl <kernel@martin.sperl.org>
+ */
+
+#ifndef _MCP251XFD_H
+#define _MCP251XFD_H
+
+#include <linux/can/core.h>
+#include <linux/can/dev.h>
+#include <linux/can/rx-offload.h>
+#include <linux/gpio/consumer.h>
+#include <linux/kernel.h>
+#include <linux/regmap.h>
+#include <linux/regulator/consumer.h>
+#include <linux/spi/spi.h>
+
+/* MPC251x registers */
+
+/* CAN FD Controller Module SFR */
+#define MCP251XFD_REG_CON 0x00
+#define MCP251XFD_REG_CON_TXBWS_MASK GENMASK(31, 28)
+#define MCP251XFD_REG_CON_ABAT BIT(27)
+#define MCP251XFD_REG_CON_REQOP_MASK GENMASK(26, 24)
+#define MCP251XFD_REG_CON_MODE_MIXED 0
+#define MCP251XFD_REG_CON_MODE_SLEEP 1
+#define MCP251XFD_REG_CON_MODE_INT_LOOPBACK 2
+#define MCP251XFD_REG_CON_MODE_LISTENONLY 3
+#define MCP251XFD_REG_CON_MODE_CONFIG 4
+#define MCP251XFD_REG_CON_MODE_EXT_LOOPBACK 5
+#define MCP251XFD_REG_CON_MODE_CAN2_0 6
+#define MCP251XFD_REG_CON_MODE_RESTRICTED 7
+#define MCP251XFD_REG_CON_OPMOD_MASK GENMASK(23, 21)
+#define MCP251XFD_REG_CON_TXQEN BIT(20)
+#define MCP251XFD_REG_CON_STEF BIT(19)
+#define MCP251XFD_REG_CON_SERR2LOM BIT(18)
+#define MCP251XFD_REG_CON_ESIGM BIT(17)
+#define MCP251XFD_REG_CON_RTXAT BIT(16)
+#define MCP251XFD_REG_CON_BRSDIS BIT(12)
+#define MCP251XFD_REG_CON_BUSY BIT(11)
+#define MCP251XFD_REG_CON_WFT_MASK GENMASK(10, 9)
+#define MCP251XFD_REG_CON_WFT_T00FILTER 0x0
+#define MCP251XFD_REG_CON_WFT_T01FILTER 0x1
+#define MCP251XFD_REG_CON_WFT_T10FILTER 0x2
+#define MCP251XFD_REG_CON_WFT_T11FILTER 0x3
+#define MCP251XFD_REG_CON_WAKFIL BIT(8)
+#define MCP251XFD_REG_CON_PXEDIS BIT(6)
+#define MCP251XFD_REG_CON_ISOCRCEN BIT(5)
+#define MCP251XFD_REG_CON_DNCNT_MASK GENMASK(4, 0)
+
+#define MCP251XFD_REG_NBTCFG 0x04
+#define MCP251XFD_REG_NBTCFG_BRP_MASK GENMASK(31, 24)
+#define MCP251XFD_REG_NBTCFG_TSEG1_MASK GENMASK(23, 16)
+#define MCP251XFD_REG_NBTCFG_TSEG2_MASK GENMASK(14, 8)
+#define MCP251XFD_REG_NBTCFG_SJW_MASK GENMASK(6, 0)
+
+#define MCP251XFD_REG_DBTCFG 0x08
+#define MCP251XFD_REG_DBTCFG_BRP_MASK GENMASK(31, 24)
+#define MCP251XFD_REG_DBTCFG_TSEG1_MASK GENMASK(20, 16)
+#define MCP251XFD_REG_DBTCFG_TSEG2_MASK GENMASK(11, 8)
+#define MCP251XFD_REG_DBTCFG_SJW_MASK GENMASK(3, 0)
+
+#define MCP251XFD_REG_TDC 0x0c
+#define MCP251XFD_REG_TDC_EDGFLTEN BIT(25)
+#define MCP251XFD_REG_TDC_SID11EN BIT(24)
+#define MCP251XFD_REG_TDC_TDCMOD_MASK GENMASK(17, 16)
+#define MCP251XFD_REG_TDC_TDCMOD_AUTO 2
+#define MCP251XFD_REG_TDC_TDCMOD_MANUAL 1
+#define MCP251XFD_REG_TDC_TDCMOD_DISABLED 0
+#define MCP251XFD_REG_TDC_TDCO_MASK GENMASK(14, 8)
+#define MCP251XFD_REG_TDC_TDCV_MASK GENMASK(5, 0)
+
+#define MCP251XFD_REG_TBC 0x10
+
+#define MCP251XFD_REG_TSCON 0x14
+#define MCP251XFD_REG_TSCON_TSRES BIT(18)
+#define MCP251XFD_REG_TSCON_TSEOF BIT(17)
+#define MCP251XFD_REG_TSCON_TBCEN BIT(16)
+#define MCP251XFD_REG_TSCON_TBCPRE_MASK GENMASK(9, 0)
+
+#define MCP251XFD_REG_VEC 0x18
+#define MCP251XFD_REG_VEC_RXCODE_MASK GENMASK(30, 24)
+#define MCP251XFD_REG_VEC_TXCODE_MASK GENMASK(22, 16)
+#define MCP251XFD_REG_VEC_FILHIT_MASK GENMASK(12, 8)
+#define MCP251XFD_REG_VEC_ICODE_MASK GENMASK(6, 0)
+
+#define MCP251XFD_REG_INT 0x1c
+#define MCP251XFD_REG_INT_IF_MASK GENMASK(15, 0)
+#define MCP251XFD_REG_INT_IE_MASK GENMASK(31, 16)
+#define MCP251XFD_REG_INT_IVMIE BIT(31)
+#define MCP251XFD_REG_INT_WAKIE BIT(30)
+#define MCP251XFD_REG_INT_CERRIE BIT(29)
+#define MCP251XFD_REG_INT_SERRIE BIT(28)
+#define MCP251XFD_REG_INT_RXOVIE BIT(27)
+#define MCP251XFD_REG_INT_TXATIE BIT(26)
+#define MCP251XFD_REG_INT_SPICRCIE BIT(25)
+#define MCP251XFD_REG_INT_ECCIE BIT(24)
+#define MCP251XFD_REG_INT_TEFIE BIT(20)
+#define MCP251XFD_REG_INT_MODIE BIT(19)
+#define MCP251XFD_REG_INT_TBCIE BIT(18)
+#define MCP251XFD_REG_INT_RXIE BIT(17)
+#define MCP251XFD_REG_INT_TXIE BIT(16)
+#define MCP251XFD_REG_INT_IVMIF BIT(15)
+#define MCP251XFD_REG_INT_WAKIF BIT(14)
+#define MCP251XFD_REG_INT_CERRIF BIT(13)
+#define MCP251XFD_REG_INT_SERRIF BIT(12)
+#define MCP251XFD_REG_INT_RXOVIF BIT(11)
+#define MCP251XFD_REG_INT_TXATIF BIT(10)
+#define MCP251XFD_REG_INT_SPICRCIF BIT(9)
+#define MCP251XFD_REG_INT_ECCIF BIT(8)
+#define MCP251XFD_REG_INT_TEFIF BIT(4)
+#define MCP251XFD_REG_INT_MODIF BIT(3)
+#define MCP251XFD_REG_INT_TBCIF BIT(2)
+#define MCP251XFD_REG_INT_RXIF BIT(1)
+#define MCP251XFD_REG_INT_TXIF BIT(0)
+/* These IRQ flags must be cleared by SW in the CAN_INT register */
+#define MCP251XFD_REG_INT_IF_CLEARABLE_MASK \
+	(MCP251XFD_REG_INT_IVMIF | MCP251XFD_REG_INT_WAKIF | \
+	 MCP251XFD_REG_INT_CERRIF |  MCP251XFD_REG_INT_SERRIF | \
+	 MCP251XFD_REG_INT_MODIF)
+
+#define MCP251XFD_REG_RXIF 0x20
+#define MCP251XFD_REG_TXIF 0x24
+#define MCP251XFD_REG_RXOVIF 0x28
+#define MCP251XFD_REG_TXATIF 0x2c
+#define MCP251XFD_REG_TXREQ 0x30
+
+#define MCP251XFD_REG_TREC 0x34
+#define MCP251XFD_REG_TREC_TXBO BIT(21)
+#define MCP251XFD_REG_TREC_TXBP BIT(20)
+#define MCP251XFD_REG_TREC_RXBP BIT(19)
+#define MCP251XFD_REG_TREC_TXWARN BIT(18)
+#define MCP251XFD_REG_TREC_RXWARN BIT(17)
+#define MCP251XFD_REG_TREC_EWARN BIT(16)
+#define MCP251XFD_REG_TREC_TEC_MASK GENMASK(15, 8)
+#define MCP251XFD_REG_TREC_REC_MASK GENMASK(7, 0)
+
+#define MCP251XFD_REG_BDIAG0 0x38
+#define MCP251XFD_REG_BDIAG0_DTERRCNT_MASK GENMASK(31, 24)
+#define MCP251XFD_REG_BDIAG0_DRERRCNT_MASK GENMASK(23, 16)
+#define MCP251XFD_REG_BDIAG0_NTERRCNT_MASK GENMASK(15, 8)
+#define MCP251XFD_REG_BDIAG0_NRERRCNT_MASK GENMASK(7, 0)
+
+#define MCP251XFD_REG_BDIAG1 0x3c
+#define MCP251XFD_REG_BDIAG1_DLCMM BIT(31)
+#define MCP251XFD_REG_BDIAG1_ESI BIT(30)
+#define MCP251XFD_REG_BDIAG1_DCRCERR BIT(29)
+#define MCP251XFD_REG_BDIAG1_DSTUFERR BIT(28)
+#define MCP251XFD_REG_BDIAG1_DFORMERR BIT(27)
+#define MCP251XFD_REG_BDIAG1_DBIT1ERR BIT(25)
+#define MCP251XFD_REG_BDIAG1_DBIT0ERR BIT(24)
+#define MCP251XFD_REG_BDIAG1_TXBOERR BIT(23)
+#define MCP251XFD_REG_BDIAG1_NCRCERR BIT(21)
+#define MCP251XFD_REG_BDIAG1_NSTUFERR BIT(20)
+#define MCP251XFD_REG_BDIAG1_NFORMERR BIT(19)
+#define MCP251XFD_REG_BDIAG1_NACKERR BIT(18)
+#define MCP251XFD_REG_BDIAG1_NBIT1ERR BIT(17)
+#define MCP251XFD_REG_BDIAG1_NBIT0ERR BIT(16)
+#define MCP251XFD_REG_BDIAG1_BERR_MASK \
+	(MCP251XFD_REG_BDIAG1_DLCMM | MCP251XFD_REG_BDIAG1_ESI | \
+	 MCP251XFD_REG_BDIAG1_DCRCERR | MCP251XFD_REG_BDIAG1_DSTUFERR | \
+	 MCP251XFD_REG_BDIAG1_DFORMERR | MCP251XFD_REG_BDIAG1_DBIT1ERR | \
+	 MCP251XFD_REG_BDIAG1_DBIT0ERR | MCP251XFD_REG_BDIAG1_TXBOERR | \
+	 MCP251XFD_REG_BDIAG1_NCRCERR | MCP251XFD_REG_BDIAG1_NSTUFERR | \
+	 MCP251XFD_REG_BDIAG1_NFORMERR | MCP251XFD_REG_BDIAG1_NACKERR | \
+	 MCP251XFD_REG_BDIAG1_NBIT1ERR | MCP251XFD_REG_BDIAG1_NBIT0ERR)
+#define MCP251XFD_REG_BDIAG1_EFMSGCNT_MASK GENMASK(15, 0)
+
+#define MCP251XFD_REG_TEFCON 0x40
+#define MCP251XFD_REG_TEFCON_FSIZE_MASK GENMASK(28, 24)
+#define MCP251XFD_REG_TEFCON_FRESET BIT(10)
+#define MCP251XFD_REG_TEFCON_UINC BIT(8)
+#define MCP251XFD_REG_TEFCON_TEFTSEN BIT(5)
+#define MCP251XFD_REG_TEFCON_TEFOVIE BIT(3)
+#define MCP251XFD_REG_TEFCON_TEFFIE BIT(2)
+#define MCP251XFD_REG_TEFCON_TEFHIE BIT(1)
+#define MCP251XFD_REG_TEFCON_TEFNEIE BIT(0)
+
+#define MCP251XFD_REG_TEFSTA 0x44
+#define MCP251XFD_REG_TEFSTA_TEFOVIF BIT(3)
+#define MCP251XFD_REG_TEFSTA_TEFFIF BIT(2)
+#define MCP251XFD_REG_TEFSTA_TEFHIF BIT(1)
+#define MCP251XFD_REG_TEFSTA_TEFNEIF BIT(0)
+
+#define MCP251XFD_REG_TEFUA 0x48
+
+#define MCP251XFD_REG_TXQCON 0x50
+#define MCP251XFD_REG_TXQCON_PLSIZE_MASK GENMASK(31, 29)
+#define MCP251XFD_REG_TXQCON_PLSIZE_8 0
+#define MCP251XFD_REG_TXQCON_PLSIZE_12 1
+#define MCP251XFD_REG_TXQCON_PLSIZE_16 2
+#define MCP251XFD_REG_TXQCON_PLSIZE_20 3
+#define MCP251XFD_REG_TXQCON_PLSIZE_24 4
+#define MCP251XFD_REG_TXQCON_PLSIZE_32 5
+#define MCP251XFD_REG_TXQCON_PLSIZE_48 6
+#define MCP251XFD_REG_TXQCON_PLSIZE_64 7
+#define MCP251XFD_REG_TXQCON_FSIZE_MASK GENMASK(28, 24)
+#define MCP251XFD_REG_TXQCON_TXAT_UNLIMITED 3
+#define MCP251XFD_REG_TXQCON_TXAT_THREE_SHOT 1
+#define MCP251XFD_REG_TXQCON_TXAT_ONE_SHOT 0
+#define MCP251XFD_REG_TXQCON_TXAT_MASK GENMASK(22, 21)
+#define MCP251XFD_REG_TXQCON_TXPRI_MASK GENMASK(20, 16)
+#define MCP251XFD_REG_TXQCON_FRESET BIT(10)
+#define MCP251XFD_REG_TXQCON_TXREQ BIT(9)
+#define MCP251XFD_REG_TXQCON_UINC BIT(8)
+#define MCP251XFD_REG_TXQCON_TXEN BIT(7)
+#define MCP251XFD_REG_TXQCON_TXATIE BIT(4)
+#define MCP251XFD_REG_TXQCON_TXQEIE BIT(2)
+#define MCP251XFD_REG_TXQCON_TXQNIE BIT(0)
+
+#define MCP251XFD_REG_TXQSTA 0x54
+#define MCP251XFD_REG_TXQSTA_TXQCI_MASK GENMASK(12, 8)
+#define MCP251XFD_REG_TXQSTA_TXABT BIT(7)
+#define MCP251XFD_REG_TXQSTA_TXLARB BIT(6)
+#define MCP251XFD_REG_TXQSTA_TXERR BIT(5)
+#define MCP251XFD_REG_TXQSTA_TXATIF BIT(4)
+#define MCP251XFD_REG_TXQSTA_TXQEIF BIT(2)
+#define MCP251XFD_REG_TXQSTA_TXQNIF BIT(0)
+
+#define MCP251XFD_REG_TXQUA 0x58
+
+#define MCP251XFD_REG_FIFOCON(x) (0x50 + 0xc * (x))
+#define MCP251XFD_REG_FIFOCON_PLSIZE_MASK GENMASK(31, 29)
+#define MCP251XFD_REG_FIFOCON_PLSIZE_8 0
+#define MCP251XFD_REG_FIFOCON_PLSIZE_12 1
+#define MCP251XFD_REG_FIFOCON_PLSIZE_16 2
+#define MCP251XFD_REG_FIFOCON_PLSIZE_20 3
+#define MCP251XFD_REG_FIFOCON_PLSIZE_24 4
+#define MCP251XFD_REG_FIFOCON_PLSIZE_32 5
+#define MCP251XFD_REG_FIFOCON_PLSIZE_48 6
+#define MCP251XFD_REG_FIFOCON_PLSIZE_64 7
+#define MCP251XFD_REG_FIFOCON_FSIZE_MASK GENMASK(28, 24)
+#define MCP251XFD_REG_FIFOCON_TXAT_MASK GENMASK(22, 21)
+#define MCP251XFD_REG_FIFOCON_TXAT_ONE_SHOT 0
+#define MCP251XFD_REG_FIFOCON_TXAT_THREE_SHOT 1
+#define MCP251XFD_REG_FIFOCON_TXAT_UNLIMITED 3
+#define MCP251XFD_REG_FIFOCON_TXPRI_MASK GENMASK(20, 16)
+#define MCP251XFD_REG_FIFOCON_FRESET BIT(10)
+#define MCP251XFD_REG_FIFOCON_TXREQ BIT(9)
+#define MCP251XFD_REG_FIFOCON_UINC BIT(8)
+#define MCP251XFD_REG_FIFOCON_TXEN BIT(7)
+#define MCP251XFD_REG_FIFOCON_RTREN BIT(6)
+#define MCP251XFD_REG_FIFOCON_RXTSEN BIT(5)
+#define MCP251XFD_REG_FIFOCON_TXATIE BIT(4)
+#define MCP251XFD_REG_FIFOCON_RXOVIE BIT(3)
+#define MCP251XFD_REG_FIFOCON_TFERFFIE BIT(2)
+#define MCP251XFD_REG_FIFOCON_TFHRFHIE BIT(1)
+#define MCP251XFD_REG_FIFOCON_TFNRFNIE BIT(0)
+
+#define MCP251XFD_REG_FIFOSTA(x) (0x54 + 0xc * (x))
+#define MCP251XFD_REG_FIFOSTA_FIFOCI_MASK GENMASK(12, 8)
+#define MCP251XFD_REG_FIFOSTA_TXABT BIT(7)
+#define MCP251XFD_REG_FIFOSTA_TXLARB BIT(6)
+#define MCP251XFD_REG_FIFOSTA_TXERR BIT(5)
+#define MCP251XFD_REG_FIFOSTA_TXATIF BIT(4)
+#define MCP251XFD_REG_FIFOSTA_RXOVIF BIT(3)
+#define MCP251XFD_REG_FIFOSTA_TFERFFIF BIT(2)
+#define MCP251XFD_REG_FIFOSTA_TFHRFHIF BIT(1)
+#define MCP251XFD_REG_FIFOSTA_TFNRFNIF BIT(0)
+
+#define MCP251XFD_REG_FIFOUA(x) (0x58 + 0xc * (x))
+
+#define MCP251XFD_REG_FLTCON(x) (0x1d0 + 0x4 * (x))
+#define MCP251XFD_REG_FLTCON_FLTEN3 BIT(31)
+#define MCP251XFD_REG_FLTCON_F3BP_MASK GENMASK(28, 24)
+#define MCP251XFD_REG_FLTCON_FLTEN2 BIT(23)
+#define MCP251XFD_REG_FLTCON_F2BP_MASK GENMASK(20, 16)
+#define MCP251XFD_REG_FLTCON_FLTEN1 BIT(15)
+#define MCP251XFD_REG_FLTCON_F1BP_MASK GENMASK(12, 8)
+#define MCP251XFD_REG_FLTCON_FLTEN0 BIT(7)
+#define MCP251XFD_REG_FLTCON_F0BP_MASK GENMASK(4, 0)
+#define MCP251XFD_REG_FLTCON_FLTEN(x) (BIT(7) << 8 * ((x) & 0x3))
+#define MCP251XFD_REG_FLTCON_FLT_MASK(x) (GENMASK(7, 0) << (8 * ((x) & 0x3)))
+#define MCP251XFD_REG_FLTCON_FBP(x, fifo) ((fifo) << 8 * ((x) & 0x3))
+
+#define MCP251XFD_REG_FLTOBJ(x) (0x1f0 + 0x8 * (x))
+#define MCP251XFD_REG_FLTOBJ_EXIDE BIT(30)
+#define MCP251XFD_REG_FLTOBJ_SID11 BIT(29)
+#define MCP251XFD_REG_FLTOBJ_EID_MASK GENMASK(28, 11)
+#define MCP251XFD_REG_FLTOBJ_SID_MASK GENMASK(10, 0)
+
+#define MCP251XFD_REG_FLTMASK(x) (0x1f4 + 0x8 * (x))
+#define MCP251XFD_REG_MASK_MIDE BIT(30)
+#define MCP251XFD_REG_MASK_MSID11 BIT(29)
+#define MCP251XFD_REG_MASK_MEID_MASK GENMASK(28, 11)
+#define MCP251XFD_REG_MASK_MSID_MASK GENMASK(10, 0)
+
+/* RAM */
+#define MCP251XFD_RAM_START 0x400
+#define MCP251XFD_RAM_SIZE SZ_2K
+
+/* Message Object */
+#define MCP251XFD_OBJ_ID_SID11 BIT(29)
+#define MCP251XFD_OBJ_ID_EID_MASK GENMASK(28, 11)
+#define MCP251XFD_OBJ_ID_SID_MASK GENMASK(10, 0)
+#define MCP251XFD_OBJ_FLAGS_SEQ_MCP2518FD_MASK GENMASK(31, 9)
+#define MCP251XFD_OBJ_FLAGS_SEQ_MCP2517FD_MASK GENMASK(15, 9)
+#define MCP251XFD_OBJ_FLAGS_SEQ_MASK MCP251XFD_OBJ_FLAGS_SEQ_MCP2518FD_MASK
+#define MCP251XFD_OBJ_FLAGS_ESI BIT(8)
+#define MCP251XFD_OBJ_FLAGS_FDF BIT(7)
+#define MCP251XFD_OBJ_FLAGS_BRS BIT(6)
+#define MCP251XFD_OBJ_FLAGS_RTR BIT(5)
+#define MCP251XFD_OBJ_FLAGS_IDE BIT(4)
+#define MCP251XFD_OBJ_FLAGS_DLC GENMASK(3, 0)
+
+#define MCP251XFD_REG_FRAME_EFF_SID_MASK GENMASK(28, 18)
+#define MCP251XFD_REG_FRAME_EFF_EID_MASK GENMASK(17, 0)
+
+/* MCP2517/18FD SFR */
+#define MCP251XFD_REG_OSC 0xe00
+#define MCP251XFD_REG_OSC_SCLKRDY BIT(12)
+#define MCP251XFD_REG_OSC_OSCRDY BIT(10)
+#define MCP251XFD_REG_OSC_PLLRDY BIT(8)
+#define MCP251XFD_REG_OSC_CLKODIV_10 3
+#define MCP251XFD_REG_OSC_CLKODIV_4 2
+#define MCP251XFD_REG_OSC_CLKODIV_2 1
+#define MCP251XFD_REG_OSC_CLKODIV_1 0
+#define MCP251XFD_REG_OSC_CLKODIV_MASK GENMASK(6, 5)
+#define MCP251XFD_REG_OSC_SCLKDIV BIT(4)
+#define MCP251XFD_REG_OSC_LPMEN BIT(3)	/* MCP2518FD only */
+#define MCP251XFD_REG_OSC_OSCDIS BIT(2)
+#define MCP251XFD_REG_OSC_PLLEN BIT(0)
+
+#define MCP251XFD_REG_IOCON 0xe04
+#define MCP251XFD_REG_IOCON_INTOD BIT(30)
+#define MCP251XFD_REG_IOCON_SOF BIT(29)
+#define MCP251XFD_REG_IOCON_TXCANOD BIT(28)
+#define MCP251XFD_REG_IOCON_PM1 BIT(25)
+#define MCP251XFD_REG_IOCON_PM0 BIT(24)
+#define MCP251XFD_REG_IOCON_GPIO1 BIT(17)
+#define MCP251XFD_REG_IOCON_GPIO0 BIT(16)
+#define MCP251XFD_REG_IOCON_LAT1 BIT(9)
+#define MCP251XFD_REG_IOCON_LAT0 BIT(8)
+#define MCP251XFD_REG_IOCON_XSTBYEN BIT(6)
+#define MCP251XFD_REG_IOCON_TRIS1 BIT(1)
+#define MCP251XFD_REG_IOCON_TRIS0 BIT(0)
+
+#define MCP251XFD_REG_CRC 0xe08
+#define MCP251XFD_REG_CRC_FERRIE BIT(25)
+#define MCP251XFD_REG_CRC_CRCERRIE BIT(24)
+#define MCP251XFD_REG_CRC_FERRIF BIT(17)
+#define MCP251XFD_REG_CRC_CRCERRIF BIT(16)
+#define MCP251XFD_REG_CRC_IF_MASK GENMASK(17, 16)
+#define MCP251XFD_REG_CRC_MASK GENMASK(15, 0)
+
+#define MCP251XFD_REG_ECCCON 0xe0c
+#define MCP251XFD_REG_ECCCON_PARITY_MASK GENMASK(14, 8)
+#define MCP251XFD_REG_ECCCON_DEDIE BIT(2)
+#define MCP251XFD_REG_ECCCON_SECIE BIT(1)
+#define MCP251XFD_REG_ECCCON_ECCEN BIT(0)
+
+#define MCP251XFD_REG_ECCSTAT 0xe10
+#define MCP251XFD_REG_ECCSTAT_ERRADDR_MASK GENMASK(27, 16)
+#define MCP251XFD_REG_ECCSTAT_IF_MASK GENMASK(2, 1)
+#define MCP251XFD_REG_ECCSTAT_DEDIF BIT(2)
+#define MCP251XFD_REG_ECCSTAT_SECIF BIT(1)
+
+#define MCP251XFD_REG_DEVID 0xe14	/* MCP2518FD only */
+#define MCP251XFD_REG_DEVID_ID_MASK GENMASK(7, 4)
+#define MCP251XFD_REG_DEVID_REV_MASK GENMASK(3, 0)
+
+/* number of TX FIFO objects, depending on CAN mode
+ *
+ * FIFO setup: tef: 8*12 bytes = 96 bytes, tx: 8*16 bytes = 128 bytes
+ * FIFO setup: tef: 4*12 bytes = 48 bytes, tx: 4*72 bytes = 288 bytes
+ */
+#define MCP251XFD_TX_OBJ_NUM_CAN 8
+#define MCP251XFD_TX_OBJ_NUM_CANFD 4
+
+#if MCP251XFD_TX_OBJ_NUM_CAN > MCP251XFD_TX_OBJ_NUM_CANFD
+#define MCP251XFD_TX_OBJ_NUM_MAX MCP251XFD_TX_OBJ_NUM_CAN
+#else
+#define MCP251XFD_TX_OBJ_NUM_MAX MCP251XFD_TX_OBJ_NUM_CANFD
+#endif
+
+#define MCP251XFD_NAPI_WEIGHT 32
+#define MCP251XFD_TX_FIFO 1
+#define MCP251XFD_RX_FIFO(x) (MCP251XFD_TX_FIFO + 1 + (x))
+
+/* SPI commands */
+#define MCP251XFD_SPI_INSTRUCTION_RESET 0x0000
+#define MCP251XFD_SPI_INSTRUCTION_WRITE 0x2000
+#define MCP251XFD_SPI_INSTRUCTION_READ 0x3000
+#define MCP251XFD_SPI_INSTRUCTION_WRITE_CRC 0xa000
+#define MCP251XFD_SPI_INSTRUCTION_READ_CRC 0xb000
+#define MCP251XFD_SPI_INSTRUCTION_WRITE_CRC_SAFE 0xc000
+#define MCP251XFD_SPI_ADDRESS_MASK GENMASK(11, 0)
+
+#define MCP251XFD_SYSCLOCK_HZ_MAX 40000000
+#define MCP251XFD_SYSCLOCK_HZ_MIN 1000000
+#define MCP251XFD_SPICLOCK_HZ_MAX 20000000
+#define MCP251XFD_OSC_PLL_MULTIPLIER 10
+#define MCP251XFD_OSC_STAB_SLEEP_US (3 * USEC_PER_MSEC)
+#define MCP251XFD_OSC_STAB_TIMEOUT_US (10 * MCP251XFD_OSC_STAB_SLEEP_US)
+#define MCP251XFD_POLL_SLEEP_US (10)
+#define MCP251XFD_POLL_TIMEOUT_US (USEC_PER_MSEC)
+#define MCP251XFD_SOFTRESET_RETRIES_MAX 3
+#define MCP251XFD_READ_CRC_RETRIES_MAX 3
+#define MCP251XFD_ECC_CNT_MAX 2
+#define MCP251XFD_SANITIZE_SPI 1
+#define MCP251XFD_SANITIZE_CAN 1
+
+/* Silence TX MAB overflow warnings */
+#define MCP251XFD_QUIRK_MAB_NO_WARN BIT(0)
+/* Use CRC to access registers */
+#define MCP251XFD_QUIRK_CRC_REG BIT(1)
+/* Use CRC to access RX/TEF-RAM */
+#define MCP251XFD_QUIRK_CRC_RX BIT(2)
+/* Use CRC to access TX-RAM */
+#define MCP251XFD_QUIRK_CRC_TX BIT(3)
+/* Enable ECC for RAM */
+#define MCP251XFD_QUIRK_ECC BIT(4)
+/* Use Half Duplex SPI transfers */
+#define MCP251XFD_QUIRK_HALF_DUPLEX BIT(5)
+
+struct mcp251xfd_hw_tef_obj {
+	u32 id;
+	u32 flags;
+	u32 ts;
+};
+
+/* The tx_obj_raw version is used in spi async, i.e. without
+ * regmap. We have to take care of endianness ourselves.
+ */
+struct mcp251xfd_hw_tx_obj_raw {
+	__le32 id;
+	__le32 flags;
+	u8 data[sizeof_field(struct canfd_frame, data)];
+};
+
+struct mcp251xfd_hw_tx_obj_can {
+	u32 id;
+	u32 flags;
+	u8 data[sizeof_field(struct can_frame, data)];
+};
+
+struct mcp251xfd_hw_tx_obj_canfd {
+	u32 id;
+	u32 flags;
+	u8 data[sizeof_field(struct canfd_frame, data)];
+};
+
+struct mcp251xfd_hw_rx_obj_can {
+	u32 id;
+	u32 flags;
+	u32 ts;
+	u8 data[sizeof_field(struct can_frame, data)];
+};
+
+struct mcp251xfd_hw_rx_obj_canfd {
+	u32 id;
+	u32 flags;
+	u32 ts;
+	u8 data[sizeof_field(struct canfd_frame, data)];
+};
+
+struct mcp251xfd_tef_ring {
+	unsigned int head;
+	unsigned int tail;
+
+	/* u8 obj_num equals tx_ring->obj_num */
+	/* u8 obj_size equals sizeof(struct mcp251xfd_hw_tef_obj) */
+};
+
+struct __packed mcp251xfd_buf_cmd {
+	__be16 cmd;
+};
+
+struct __packed mcp251xfd_buf_cmd_crc {
+	__be16 cmd;
+	u8 len;
+};
+
+union mcp251xfd_tx_obj_load_buf {
+	struct __packed {
+		struct mcp251xfd_buf_cmd cmd;
+		struct mcp251xfd_hw_tx_obj_raw hw_tx_obj;
+	} nocrc;
+	struct __packed {
+		struct mcp251xfd_buf_cmd_crc cmd;
+		struct mcp251xfd_hw_tx_obj_raw hw_tx_obj;
+		__be16 crc;
+	} crc;
+} ____cacheline_aligned;
+
+union mcp251xfd_write_reg_buf {
+	struct __packed {
+		struct mcp251xfd_buf_cmd cmd;
+		u8 data[4];
+	} nocrc;
+	struct __packed {
+		struct mcp251xfd_buf_cmd_crc cmd;
+		u8 data[4];
+		__be16 crc;
+	} crc;
+} ____cacheline_aligned;
+
+struct mcp251xfd_tx_obj {
+	struct spi_message msg;
+	struct spi_transfer xfer[2];
+	union mcp251xfd_tx_obj_load_buf buf;
+};
+
+struct mcp251xfd_tx_ring {
+	unsigned int head;
+	unsigned int tail;
+
+	u16 base;
+	u8 obj_num;
+	u8 obj_size;
+
+	struct mcp251xfd_tx_obj obj[MCP251XFD_TX_OBJ_NUM_MAX];
+	union mcp251xfd_write_reg_buf rts_buf;
+};
+
+struct mcp251xfd_rx_ring {
+	unsigned int head;
+	unsigned int tail;
+
+	u16 base;
+	u8 nr;
+	u8 fifo_nr;
+	u8 obj_num;
+	u8 obj_size;
+
+	struct mcp251xfd_hw_rx_obj_canfd obj[];
+};
+
+struct __packed mcp251xfd_map_buf_nocrc {
+	struct mcp251xfd_buf_cmd cmd;
+	u8 data[256];
+} ____cacheline_aligned;
+
+struct __packed mcp251xfd_map_buf_crc {
+	struct mcp251xfd_buf_cmd_crc cmd;
+	u8 data[256 - 4];
+	__be16 crc;
+} ____cacheline_aligned;
+
+struct mcp251xfd_ecc {
+	u32 ecc_stat;
+	int cnt;
+};
+
+struct mcp251xfd_regs_status {
+	u32 intf;
+};
+
+enum mcp251xfd_model {
+	MCP251XFD_MODEL_MCP2517FD = 0x2517,
+	MCP251XFD_MODEL_MCP2518FD = 0x2518,
+	MCP251XFD_MODEL_MCP251XFD = 0xffff,	/* autodetect model */
+};
+
+struct mcp251xfd_devtype_data {
+	enum mcp251xfd_model model;
+	u32 quirks;
+};
+
+struct mcp251xfd_priv {
+	struct can_priv can;
+	struct can_rx_offload offload;
+	struct net_device *ndev;
+
+	struct regmap *map_reg;			/* register access */
+	struct regmap *map_rx;			/* RX/TEF RAM access */
+
+	struct regmap *map_nocrc;
+	struct mcp251xfd_map_buf_nocrc *map_buf_nocrc_rx;
+	struct mcp251xfd_map_buf_nocrc *map_buf_nocrc_tx;
+
+	struct regmap *map_crc;
+	struct mcp251xfd_map_buf_crc *map_buf_crc_rx;
+	struct mcp251xfd_map_buf_crc *map_buf_crc_tx;
+
+	struct spi_device *spi;
+	u32 spi_max_speed_hz_orig;
+
+	struct mcp251xfd_tef_ring tef;
+	struct mcp251xfd_tx_ring tx[1];
+	struct mcp251xfd_rx_ring *rx[1];
+
+	u8 rx_ring_num;
+
+	struct mcp251xfd_ecc ecc;
+	struct mcp251xfd_regs_status regs_status;
+
+	struct gpio_desc *rx_int;
+	struct clk *clk;
+	struct regulator *reg_vdd;
+	struct regulator *reg_xceiver;
+
+	struct mcp251xfd_devtype_data devtype_data;
+	struct can_berr_counter bec;
+};
+
+#define MCP251XFD_IS(_model) \
+static inline bool \
+mcp251xfd_is_##_model(const struct mcp251xfd_priv *priv) \
+{ \
+	return priv->devtype_data.model == MCP251XFD_MODEL_MCP##_model##FD; \
+}
+
+MCP251XFD_IS(2517);
+MCP251XFD_IS(2518);
+MCP251XFD_IS(251X);
+
+static inline u8 mcp251xfd_first_byte_set(u32 mask)
+{
+	return (mask & 0x0000ffff) ?
+		((mask & 0x000000ff) ? 0 : 1) :
+		((mask & 0x00ff0000) ? 2 : 3);
+}
+
+static inline u8 mcp251xfd_last_byte_set(u32 mask)
+{
+	return (mask & 0xffff0000) ?
+		((mask & 0xff000000) ? 3 : 2) :
+		((mask & 0x0000ff00) ? 1 : 0);
+}
+
+static inline __be16 mcp251xfd_cmd_reset(void)
+{
+	return cpu_to_be16(MCP251XFD_SPI_INSTRUCTION_RESET);
+}
+
+static inline void
+mcp251xfd_spi_cmd_read_nocrc(struct mcp251xfd_buf_cmd *cmd, u16 addr)
+{
+	cmd->cmd = cpu_to_be16(MCP251XFD_SPI_INSTRUCTION_READ | addr);
+}
+
+static inline void
+mcp251xfd_spi_cmd_write_nocrc(struct mcp251xfd_buf_cmd *cmd, u16 addr)
+{
+	cmd->cmd = cpu_to_be16(MCP251XFD_SPI_INSTRUCTION_WRITE | addr);
+}
+
+static inline bool mcp251xfd_reg_in_ram(unsigned int reg)
+{
+	static const struct regmap_range range =
+		regmap_reg_range(MCP251XFD_RAM_START,
+				 MCP251XFD_RAM_START + MCP251XFD_RAM_SIZE - 4);
+
+	return regmap_reg_in_range(reg, &range);
+}
+
+static inline void
+__mcp251xfd_spi_cmd_crc_set_len(struct mcp251xfd_buf_cmd_crc *cmd,
+				u16 len, bool in_ram)
+{
+	/* Number of u32 for RAM access, number of u8 otherwise. */
+	if (in_ram)
+		cmd->len = len >> 2;
+	else
+		cmd->len = len;
+}
+
+static inline void
+mcp251xfd_spi_cmd_crc_set_len_in_ram(struct mcp251xfd_buf_cmd_crc *cmd, u16 len)
+{
+	__mcp251xfd_spi_cmd_crc_set_len(cmd, len, true);
+}
+
+static inline void
+mcp251xfd_spi_cmd_crc_set_len_in_reg(struct mcp251xfd_buf_cmd_crc *cmd, u16 len)
+{
+	__mcp251xfd_spi_cmd_crc_set_len(cmd, len, false);
+}
+
+static inline void
+mcp251xfd_spi_cmd_read_crc_set_addr(struct mcp251xfd_buf_cmd_crc *cmd, u16 addr)
+{
+	cmd->cmd = cpu_to_be16(MCP251XFD_SPI_INSTRUCTION_READ_CRC | addr);
+}
+
+static inline void
+mcp251xfd_spi_cmd_read_crc(struct mcp251xfd_buf_cmd_crc *cmd,
+			   u16 addr, u16 len)
+{
+	mcp251xfd_spi_cmd_read_crc_set_addr(cmd, addr);
+	__mcp251xfd_spi_cmd_crc_set_len(cmd, len, mcp251xfd_reg_in_ram(addr));
+}
+
+static inline void
+mcp251xfd_spi_cmd_write_crc_set_addr(struct mcp251xfd_buf_cmd_crc *cmd,
+				     u16 addr)
+{
+	cmd->cmd = cpu_to_be16(MCP251XFD_SPI_INSTRUCTION_WRITE_CRC | addr);
+}
+
+static inline void
+mcp251xfd_spi_cmd_write_crc(struct mcp251xfd_buf_cmd_crc *cmd,
+			    u16 addr, u16 len)
+{
+	mcp251xfd_spi_cmd_write_crc_set_addr(cmd, addr);
+	__mcp251xfd_spi_cmd_crc_set_len(cmd, len, mcp251xfd_reg_in_ram(addr));
+}
+
+static inline u8 *
+mcp251xfd_spi_cmd_write(const struct mcp251xfd_priv *priv,
+			union mcp251xfd_write_reg_buf *write_reg_buf,
+			u16 addr)
+{
+	u8 *data;
+
+	if (priv->devtype_data.quirks & MCP251XFD_QUIRK_CRC_REG) {
+		mcp251xfd_spi_cmd_write_crc_set_addr(&write_reg_buf->crc.cmd,
+						     addr);
+		data = write_reg_buf->crc.data;
+	} else {
+		mcp251xfd_spi_cmd_write_nocrc(&write_reg_buf->nocrc.cmd,
+					      addr);
+		data = write_reg_buf->nocrc.data;
+	}
+
+	return data;
+}
+
+static inline u16 mcp251xfd_get_tef_obj_addr(u8 n)
+{
+	return MCP251XFD_RAM_START +
+		sizeof(struct mcp251xfd_hw_tef_obj) * n;
+}
+
+static inline u16
+mcp251xfd_get_tx_obj_addr(const struct mcp251xfd_tx_ring *ring, u8 n)
+{
+	return ring->base + ring->obj_size * n;
+}
+
+static inline u16
+mcp251xfd_get_rx_obj_addr(const struct mcp251xfd_rx_ring *ring, u8 n)
+{
+	return ring->base + ring->obj_size * n;
+}
+
+static inline u8 mcp251xfd_get_tef_head(const struct mcp251xfd_priv *priv)
+{
+	return priv->tef.head & (priv->tx->obj_num - 1);
+}
+
+static inline u8 mcp251xfd_get_tef_tail(const struct mcp251xfd_priv *priv)
+{
+	return priv->tef.tail & (priv->tx->obj_num - 1);
+}
+
+static inline u8 mcp251xfd_get_tef_len(const struct mcp251xfd_priv *priv)
+{
+	return priv->tef.head - priv->tef.tail;
+}
+
+static inline u8 mcp251xfd_get_tef_linear_len(const struct mcp251xfd_priv *priv)
+{
+	u8 len;
+
+	len = mcp251xfd_get_tef_len(priv);
+
+	return min_t(u8, len, priv->tx->obj_num - mcp251xfd_get_tef_tail(priv));
+}
+
+static inline u8 mcp251xfd_get_tx_head(const struct mcp251xfd_tx_ring *ring)
+{
+	return ring->head & (ring->obj_num - 1);
+}
+
+static inline u8 mcp251xfd_get_tx_tail(const struct mcp251xfd_tx_ring *ring)
+{
+	return ring->tail & (ring->obj_num - 1);
+}
+
+static inline u8 mcp251xfd_get_tx_free(const struct mcp251xfd_tx_ring *ring)
+{
+	return ring->obj_num - (ring->head - ring->tail);
+}
+
+static inline int
+mcp251xfd_get_tx_nr_by_addr(const struct mcp251xfd_tx_ring *tx_ring, u8 *nr,
+			    u16 addr)
+{
+	if (addr < mcp251xfd_get_tx_obj_addr(tx_ring, 0) ||
+	    addr >= mcp251xfd_get_tx_obj_addr(tx_ring, tx_ring->obj_num))
+		return -ENOENT;
+
+	*nr = (addr - mcp251xfd_get_tx_obj_addr(tx_ring, 0)) /
+		tx_ring->obj_size;
+
+	return 0;
+}
+
+static inline u8 mcp251xfd_get_rx_head(const struct mcp251xfd_rx_ring *ring)
+{
+	return ring->head & (ring->obj_num - 1);
+}
+
+static inline u8 mcp251xfd_get_rx_tail(const struct mcp251xfd_rx_ring *ring)
+{
+	return ring->tail & (ring->obj_num - 1);
+}
+
+static inline u8 mcp251xfd_get_rx_len(const struct mcp251xfd_rx_ring *ring)
+{
+	return ring->head - ring->tail;
+}
+
+static inline u8
+mcp251xfd_get_rx_linear_len(const struct mcp251xfd_rx_ring *ring)
+{
+	u8 len;
+
+	len = mcp251xfd_get_rx_len(ring);
+
+	return min_t(u8, len, ring->obj_num - mcp251xfd_get_rx_tail(ring));
+}
+
+#define mcp251xfd_for_each_tx_obj(ring, _obj, n) \
+	for ((n) = 0, (_obj) = &(ring)->obj[(n)]; \
+	     (n) < (ring)->obj_num; \
+	     (n)++, (_obj) = &(ring)->obj[(n)])
+
+#define mcp251xfd_for_each_rx_ring(priv, ring, n) \
+	for ((n) = 0, (ring) = *((priv)->rx + (n)); \
+	     (n) < (priv)->rx_ring_num; \
+	     (n)++, (ring) = *((priv)->rx + (n)))
+
+int mcp251xfd_regmap_init(struct mcp251xfd_priv *priv);
+u16 mcp251xfd_crc16_compute2(const void *cmd, size_t cmd_size,
+			     const void *data, size_t data_size);
+u16 mcp251xfd_crc16_compute(const void *data, size_t data_size);
+
+#endif
diff --git a/drivers/net/can/spi/mcp25xxfd/Makefile b/drivers/net/can/spi/mcp25xxfd/Makefile
deleted file mode 100644
index 4e17f592e22e..000000000000
--- a/drivers/net/can/spi/mcp25xxfd/Makefile
+++ /dev/null
@@ -1,8 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-
-obj-$(CONFIG_CAN_MCP25XXFD) += mcp25xxfd.o
-
-mcp25xxfd-objs :=
-mcp25xxfd-objs += mcp25xxfd-core.o
-mcp25xxfd-objs += mcp25xxfd-crc16.o
-mcp25xxfd-objs += mcp25xxfd-regmap.o
diff --git a/drivers/net/can/spi/mcp25xxfd/mcp25xxfd.h b/drivers/net/can/spi/mcp25xxfd/mcp25xxfd.h
deleted file mode 100644
index 3bc799204cb0..000000000000
--- a/drivers/net/can/spi/mcp25xxfd/mcp25xxfd.h
+++ /dev/null
@@ -1,835 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0
- *
- * mcp25xxfd - Microchip MCP25xxFD Family CAN controller driver
- *
- * Copyright (c) 2019 Pengutronix,
- *                    Marc Kleine-Budde <kernel@pengutronix.de>
- * Copyright (c) 2019 Martin Sperl <kernel@martin.sperl.org>
- */
-
-#ifndef _MCP25XXFD_H
-#define _MCP25XXFD_H
-
-#include <linux/can/core.h>
-#include <linux/can/dev.h>
-#include <linux/can/rx-offload.h>
-#include <linux/gpio/consumer.h>
-#include <linux/kernel.h>
-#include <linux/regmap.h>
-#include <linux/regulator/consumer.h>
-#include <linux/spi/spi.h>
-
-/* MPC25xx registers */
-
-/* CAN FD Controller Module SFR */
-#define MCP25XXFD_REG_CON 0x00
-#define MCP25XXFD_REG_CON_TXBWS_MASK GENMASK(31, 28)
-#define MCP25XXFD_REG_CON_ABAT BIT(27)
-#define MCP25XXFD_REG_CON_REQOP_MASK GENMASK(26, 24)
-#define MCP25XXFD_REG_CON_MODE_MIXED 0
-#define MCP25XXFD_REG_CON_MODE_SLEEP 1
-#define MCP25XXFD_REG_CON_MODE_INT_LOOPBACK 2
-#define MCP25XXFD_REG_CON_MODE_LISTENONLY 3
-#define MCP25XXFD_REG_CON_MODE_CONFIG 4
-#define MCP25XXFD_REG_CON_MODE_EXT_LOOPBACK 5
-#define MCP25XXFD_REG_CON_MODE_CAN2_0 6
-#define MCP25XXFD_REG_CON_MODE_RESTRICTED 7
-#define MCP25XXFD_REG_CON_OPMOD_MASK GENMASK(23, 21)
-#define MCP25XXFD_REG_CON_TXQEN BIT(20)
-#define MCP25XXFD_REG_CON_STEF BIT(19)
-#define MCP25XXFD_REG_CON_SERR2LOM BIT(18)
-#define MCP25XXFD_REG_CON_ESIGM BIT(17)
-#define MCP25XXFD_REG_CON_RTXAT BIT(16)
-#define MCP25XXFD_REG_CON_BRSDIS BIT(12)
-#define MCP25XXFD_REG_CON_BUSY BIT(11)
-#define MCP25XXFD_REG_CON_WFT_MASK GENMASK(10, 9)
-#define MCP25XXFD_REG_CON_WFT_T00FILTER 0x0
-#define MCP25XXFD_REG_CON_WFT_T01FILTER 0x1
-#define MCP25XXFD_REG_CON_WFT_T10FILTER 0x2
-#define MCP25XXFD_REG_CON_WFT_T11FILTER 0x3
-#define MCP25XXFD_REG_CON_WAKFIL BIT(8)
-#define MCP25XXFD_REG_CON_PXEDIS BIT(6)
-#define MCP25XXFD_REG_CON_ISOCRCEN BIT(5)
-#define MCP25XXFD_REG_CON_DNCNT_MASK GENMASK(4, 0)
-
-#define MCP25XXFD_REG_NBTCFG 0x04
-#define MCP25XXFD_REG_NBTCFG_BRP_MASK GENMASK(31, 24)
-#define MCP25XXFD_REG_NBTCFG_TSEG1_MASK GENMASK(23, 16)
-#define MCP25XXFD_REG_NBTCFG_TSEG2_MASK GENMASK(14, 8)
-#define MCP25XXFD_REG_NBTCFG_SJW_MASK GENMASK(6, 0)
-
-#define MCP25XXFD_REG_DBTCFG 0x08
-#define MCP25XXFD_REG_DBTCFG_BRP_MASK GENMASK(31, 24)
-#define MCP25XXFD_REG_DBTCFG_TSEG1_MASK GENMASK(20, 16)
-#define MCP25XXFD_REG_DBTCFG_TSEG2_MASK GENMASK(11, 8)
-#define MCP25XXFD_REG_DBTCFG_SJW_MASK GENMASK(3, 0)
-
-#define MCP25XXFD_REG_TDC 0x0c
-#define MCP25XXFD_REG_TDC_EDGFLTEN BIT(25)
-#define MCP25XXFD_REG_TDC_SID11EN BIT(24)
-#define MCP25XXFD_REG_TDC_TDCMOD_MASK GENMASK(17, 16)
-#define MCP25XXFD_REG_TDC_TDCMOD_AUTO 2
-#define MCP25XXFD_REG_TDC_TDCMOD_MANUAL 1
-#define MCP25XXFD_REG_TDC_TDCMOD_DISABLED 0
-#define MCP25XXFD_REG_TDC_TDCO_MASK GENMASK(14, 8)
-#define MCP25XXFD_REG_TDC_TDCV_MASK GENMASK(5, 0)
-
-#define MCP25XXFD_REG_TBC 0x10
-
-#define MCP25XXFD_REG_TSCON 0x14
-#define MCP25XXFD_REG_TSCON_TSRES BIT(18)
-#define MCP25XXFD_REG_TSCON_TSEOF BIT(17)
-#define MCP25XXFD_REG_TSCON_TBCEN BIT(16)
-#define MCP25XXFD_REG_TSCON_TBCPRE_MASK GENMASK(9, 0)
-
-#define MCP25XXFD_REG_VEC 0x18
-#define MCP25XXFD_REG_VEC_RXCODE_MASK GENMASK(30, 24)
-#define MCP25XXFD_REG_VEC_TXCODE_MASK GENMASK(22, 16)
-#define MCP25XXFD_REG_VEC_FILHIT_MASK GENMASK(12, 8)
-#define MCP25XXFD_REG_VEC_ICODE_MASK GENMASK(6, 0)
-
-#define MCP25XXFD_REG_INT 0x1c
-#define MCP25XXFD_REG_INT_IF_MASK GENMASK(15, 0)
-#define MCP25XXFD_REG_INT_IE_MASK GENMASK(31, 16)
-#define MCP25XXFD_REG_INT_IVMIE BIT(31)
-#define MCP25XXFD_REG_INT_WAKIE BIT(30)
-#define MCP25XXFD_REG_INT_CERRIE BIT(29)
-#define MCP25XXFD_REG_INT_SERRIE BIT(28)
-#define MCP25XXFD_REG_INT_RXOVIE BIT(27)
-#define MCP25XXFD_REG_INT_TXATIE BIT(26)
-#define MCP25XXFD_REG_INT_SPICRCIE BIT(25)
-#define MCP25XXFD_REG_INT_ECCIE BIT(24)
-#define MCP25XXFD_REG_INT_TEFIE BIT(20)
-#define MCP25XXFD_REG_INT_MODIE BIT(19)
-#define MCP25XXFD_REG_INT_TBCIE BIT(18)
-#define MCP25XXFD_REG_INT_RXIE BIT(17)
-#define MCP25XXFD_REG_INT_TXIE BIT(16)
-#define MCP25XXFD_REG_INT_IVMIF BIT(15)
-#define MCP25XXFD_REG_INT_WAKIF BIT(14)
-#define MCP25XXFD_REG_INT_CERRIF BIT(13)
-#define MCP25XXFD_REG_INT_SERRIF BIT(12)
-#define MCP25XXFD_REG_INT_RXOVIF BIT(11)
-#define MCP25XXFD_REG_INT_TXATIF BIT(10)
-#define MCP25XXFD_REG_INT_SPICRCIF BIT(9)
-#define MCP25XXFD_REG_INT_ECCIF BIT(8)
-#define MCP25XXFD_REG_INT_TEFIF BIT(4)
-#define MCP25XXFD_REG_INT_MODIF BIT(3)
-#define MCP25XXFD_REG_INT_TBCIF BIT(2)
-#define MCP25XXFD_REG_INT_RXIF BIT(1)
-#define MCP25XXFD_REG_INT_TXIF BIT(0)
-/* These IRQ flags must be cleared by SW in the CAN_INT register */
-#define MCP25XXFD_REG_INT_IF_CLEARABLE_MASK \
-	(MCP25XXFD_REG_INT_IVMIF | MCP25XXFD_REG_INT_WAKIF | \
-	 MCP25XXFD_REG_INT_CERRIF |  MCP25XXFD_REG_INT_SERRIF | \
-	 MCP25XXFD_REG_INT_MODIF)
-
-#define MCP25XXFD_REG_RXIF 0x20
-#define MCP25XXFD_REG_TXIF 0x24
-#define MCP25XXFD_REG_RXOVIF 0x28
-#define MCP25XXFD_REG_TXATIF 0x2c
-#define MCP25XXFD_REG_TXREQ 0x30
-
-#define MCP25XXFD_REG_TREC 0x34
-#define MCP25XXFD_REG_TREC_TXBO BIT(21)
-#define MCP25XXFD_REG_TREC_TXBP BIT(20)
-#define MCP25XXFD_REG_TREC_RXBP BIT(19)
-#define MCP25XXFD_REG_TREC_TXWARN BIT(18)
-#define MCP25XXFD_REG_TREC_RXWARN BIT(17)
-#define MCP25XXFD_REG_TREC_EWARN BIT(16)
-#define MCP25XXFD_REG_TREC_TEC_MASK GENMASK(15, 8)
-#define MCP25XXFD_REG_TREC_REC_MASK GENMASK(7, 0)
-
-#define MCP25XXFD_REG_BDIAG0 0x38
-#define MCP25XXFD_REG_BDIAG0_DTERRCNT_MASK GENMASK(31, 24)
-#define MCP25XXFD_REG_BDIAG0_DRERRCNT_MASK GENMASK(23, 16)
-#define MCP25XXFD_REG_BDIAG0_NTERRCNT_MASK GENMASK(15, 8)
-#define MCP25XXFD_REG_BDIAG0_NRERRCNT_MASK GENMASK(7, 0)
-
-#define MCP25XXFD_REG_BDIAG1 0x3c
-#define MCP25XXFD_REG_BDIAG1_DLCMM BIT(31)
-#define MCP25XXFD_REG_BDIAG1_ESI BIT(30)
-#define MCP25XXFD_REG_BDIAG1_DCRCERR BIT(29)
-#define MCP25XXFD_REG_BDIAG1_DSTUFERR BIT(28)
-#define MCP25XXFD_REG_BDIAG1_DFORMERR BIT(27)
-#define MCP25XXFD_REG_BDIAG1_DBIT1ERR BIT(25)
-#define MCP25XXFD_REG_BDIAG1_DBIT0ERR BIT(24)
-#define MCP25XXFD_REG_BDIAG1_TXBOERR BIT(23)
-#define MCP25XXFD_REG_BDIAG1_NCRCERR BIT(21)
-#define MCP25XXFD_REG_BDIAG1_NSTUFERR BIT(20)
-#define MCP25XXFD_REG_BDIAG1_NFORMERR BIT(19)
-#define MCP25XXFD_REG_BDIAG1_NACKERR BIT(18)
-#define MCP25XXFD_REG_BDIAG1_NBIT1ERR BIT(17)
-#define MCP25XXFD_REG_BDIAG1_NBIT0ERR BIT(16)
-#define MCP25XXFD_REG_BDIAG1_BERR_MASK \
-	(MCP25XXFD_REG_BDIAG1_DLCMM | MCP25XXFD_REG_BDIAG1_ESI | \
-	 MCP25XXFD_REG_BDIAG1_DCRCERR | MCP25XXFD_REG_BDIAG1_DSTUFERR | \
-	 MCP25XXFD_REG_BDIAG1_DFORMERR | MCP25XXFD_REG_BDIAG1_DBIT1ERR | \
-	 MCP25XXFD_REG_BDIAG1_DBIT0ERR | MCP25XXFD_REG_BDIAG1_TXBOERR | \
-	 MCP25XXFD_REG_BDIAG1_NCRCERR | MCP25XXFD_REG_BDIAG1_NSTUFERR | \
-	 MCP25XXFD_REG_BDIAG1_NFORMERR | MCP25XXFD_REG_BDIAG1_NACKERR | \
-	 MCP25XXFD_REG_BDIAG1_NBIT1ERR | MCP25XXFD_REG_BDIAG1_NBIT0ERR)
-#define MCP25XXFD_REG_BDIAG1_EFMSGCNT_MASK GENMASK(15, 0)
-
-#define MCP25XXFD_REG_TEFCON 0x40
-#define MCP25XXFD_REG_TEFCON_FSIZE_MASK GENMASK(28, 24)
-#define MCP25XXFD_REG_TEFCON_FRESET BIT(10)
-#define MCP25XXFD_REG_TEFCON_UINC BIT(8)
-#define MCP25XXFD_REG_TEFCON_TEFTSEN BIT(5)
-#define MCP25XXFD_REG_TEFCON_TEFOVIE BIT(3)
-#define MCP25XXFD_REG_TEFCON_TEFFIE BIT(2)
-#define MCP25XXFD_REG_TEFCON_TEFHIE BIT(1)
-#define MCP25XXFD_REG_TEFCON_TEFNEIE BIT(0)
-
-#define MCP25XXFD_REG_TEFSTA 0x44
-#define MCP25XXFD_REG_TEFSTA_TEFOVIF BIT(3)
-#define MCP25XXFD_REG_TEFSTA_TEFFIF BIT(2)
-#define MCP25XXFD_REG_TEFSTA_TEFHIF BIT(1)
-#define MCP25XXFD_REG_TEFSTA_TEFNEIF BIT(0)
-
-#define MCP25XXFD_REG_TEFUA 0x48
-
-#define MCP25XXFD_REG_TXQCON 0x50
-#define MCP25XXFD_REG_TXQCON_PLSIZE_MASK GENMASK(31, 29)
-#define MCP25XXFD_REG_TXQCON_PLSIZE_8 0
-#define MCP25XXFD_REG_TXQCON_PLSIZE_12 1
-#define MCP25XXFD_REG_TXQCON_PLSIZE_16 2
-#define MCP25XXFD_REG_TXQCON_PLSIZE_20 3
-#define MCP25XXFD_REG_TXQCON_PLSIZE_24 4
-#define MCP25XXFD_REG_TXQCON_PLSIZE_32 5
-#define MCP25XXFD_REG_TXQCON_PLSIZE_48 6
-#define MCP25XXFD_REG_TXQCON_PLSIZE_64 7
-#define MCP25XXFD_REG_TXQCON_FSIZE_MASK GENMASK(28, 24)
-#define MCP25XXFD_REG_TXQCON_TXAT_UNLIMITED 3
-#define MCP25XXFD_REG_TXQCON_TXAT_THREE_SHOT 1
-#define MCP25XXFD_REG_TXQCON_TXAT_ONE_SHOT 0
-#define MCP25XXFD_REG_TXQCON_TXAT_MASK GENMASK(22, 21)
-#define MCP25XXFD_REG_TXQCON_TXPRI_MASK GENMASK(20, 16)
-#define MCP25XXFD_REG_TXQCON_FRESET BIT(10)
-#define MCP25XXFD_REG_TXQCON_TXREQ BIT(9)
-#define MCP25XXFD_REG_TXQCON_UINC BIT(8)
-#define MCP25XXFD_REG_TXQCON_TXEN BIT(7)
-#define MCP25XXFD_REG_TXQCON_TXATIE BIT(4)
-#define MCP25XXFD_REG_TXQCON_TXQEIE BIT(2)
-#define MCP25XXFD_REG_TXQCON_TXQNIE BIT(0)
-
-#define MCP25XXFD_REG_TXQSTA 0x54
-#define MCP25XXFD_REG_TXQSTA_TXQCI_MASK GENMASK(12, 8)
-#define MCP25XXFD_REG_TXQSTA_TXABT BIT(7)
-#define MCP25XXFD_REG_TXQSTA_TXLARB BIT(6)
-#define MCP25XXFD_REG_TXQSTA_TXERR BIT(5)
-#define MCP25XXFD_REG_TXQSTA_TXATIF BIT(4)
-#define MCP25XXFD_REG_TXQSTA_TXQEIF BIT(2)
-#define MCP25XXFD_REG_TXQSTA_TXQNIF BIT(0)
-
-#define MCP25XXFD_REG_TXQUA 0x58
-
-#define MCP25XXFD_REG_FIFOCON(x) (0x50 + 0xc * (x))
-#define MCP25XXFD_REG_FIFOCON_PLSIZE_MASK GENMASK(31, 29)
-#define MCP25XXFD_REG_FIFOCON_PLSIZE_8 0
-#define MCP25XXFD_REG_FIFOCON_PLSIZE_12 1
-#define MCP25XXFD_REG_FIFOCON_PLSIZE_16 2
-#define MCP25XXFD_REG_FIFOCON_PLSIZE_20 3
-#define MCP25XXFD_REG_FIFOCON_PLSIZE_24 4
-#define MCP25XXFD_REG_FIFOCON_PLSIZE_32 5
-#define MCP25XXFD_REG_FIFOCON_PLSIZE_48 6
-#define MCP25XXFD_REG_FIFOCON_PLSIZE_64 7
-#define MCP25XXFD_REG_FIFOCON_FSIZE_MASK GENMASK(28, 24)
-#define MCP25XXFD_REG_FIFOCON_TXAT_MASK GENMASK(22, 21)
-#define MCP25XXFD_REG_FIFOCON_TXAT_ONE_SHOT 0
-#define MCP25XXFD_REG_FIFOCON_TXAT_THREE_SHOT 1
-#define MCP25XXFD_REG_FIFOCON_TXAT_UNLIMITED 3
-#define MCP25XXFD_REG_FIFOCON_TXPRI_MASK GENMASK(20, 16)
-#define MCP25XXFD_REG_FIFOCON_FRESET BIT(10)
-#define MCP25XXFD_REG_FIFOCON_TXREQ BIT(9)
-#define MCP25XXFD_REG_FIFOCON_UINC BIT(8)
-#define MCP25XXFD_REG_FIFOCON_TXEN BIT(7)
-#define MCP25XXFD_REG_FIFOCON_RTREN BIT(6)
-#define MCP25XXFD_REG_FIFOCON_RXTSEN BIT(5)
-#define MCP25XXFD_REG_FIFOCON_TXATIE BIT(4)
-#define MCP25XXFD_REG_FIFOCON_RXOVIE BIT(3)
-#define MCP25XXFD_REG_FIFOCON_TFERFFIE BIT(2)
-#define MCP25XXFD_REG_FIFOCON_TFHRFHIE BIT(1)
-#define MCP25XXFD_REG_FIFOCON_TFNRFNIE BIT(0)
-
-#define MCP25XXFD_REG_FIFOSTA(x) (0x54 + 0xc * (x))
-#define MCP25XXFD_REG_FIFOSTA_FIFOCI_MASK GENMASK(12, 8)
-#define MCP25XXFD_REG_FIFOSTA_TXABT BIT(7)
-#define MCP25XXFD_REG_FIFOSTA_TXLARB BIT(6)
-#define MCP25XXFD_REG_FIFOSTA_TXERR BIT(5)
-#define MCP25XXFD_REG_FIFOSTA_TXATIF BIT(4)
-#define MCP25XXFD_REG_FIFOSTA_RXOVIF BIT(3)
-#define MCP25XXFD_REG_FIFOSTA_TFERFFIF BIT(2)
-#define MCP25XXFD_REG_FIFOSTA_TFHRFHIF BIT(1)
-#define MCP25XXFD_REG_FIFOSTA_TFNRFNIF BIT(0)
-
-#define MCP25XXFD_REG_FIFOUA(x) (0x58 + 0xc * (x))
-
-#define MCP25XXFD_REG_FLTCON(x) (0x1d0 + 0x4 * (x))
-#define MCP25XXFD_REG_FLTCON_FLTEN3 BIT(31)
-#define MCP25XXFD_REG_FLTCON_F3BP_MASK GENMASK(28, 24)
-#define MCP25XXFD_REG_FLTCON_FLTEN2 BIT(23)
-#define MCP25XXFD_REG_FLTCON_F2BP_MASK GENMASK(20, 16)
-#define MCP25XXFD_REG_FLTCON_FLTEN1 BIT(15)
-#define MCP25XXFD_REG_FLTCON_F1BP_MASK GENMASK(12, 8)
-#define MCP25XXFD_REG_FLTCON_FLTEN0 BIT(7)
-#define MCP25XXFD_REG_FLTCON_F0BP_MASK GENMASK(4, 0)
-#define MCP25XXFD_REG_FLTCON_FLTEN(x) (BIT(7) << 8 * ((x) & 0x3))
-#define MCP25XXFD_REG_FLTCON_FLT_MASK(x) (GENMASK(7, 0) << (8 * ((x) & 0x3)))
-#define MCP25XXFD_REG_FLTCON_FBP(x, fifo) ((fifo) << 8 * ((x) & 0x3))
-
-#define MCP25XXFD_REG_FLTOBJ(x) (0x1f0 + 0x8 * (x))
-#define MCP25XXFD_REG_FLTOBJ_EXIDE BIT(30)
-#define MCP25XXFD_REG_FLTOBJ_SID11 BIT(29)
-#define MCP25XXFD_REG_FLTOBJ_EID_MASK GENMASK(28, 11)
-#define MCP25XXFD_REG_FLTOBJ_SID_MASK GENMASK(10, 0)
-
-#define MCP25XXFD_REG_FLTMASK(x) (0x1f4 + 0x8 * (x))
-#define MCP25XXFD_REG_MASK_MIDE BIT(30)
-#define MCP25XXFD_REG_MASK_MSID11 BIT(29)
-#define MCP25XXFD_REG_MASK_MEID_MASK GENMASK(28, 11)
-#define MCP25XXFD_REG_MASK_MSID_MASK GENMASK(10, 0)
-
-/* RAM */
-#define MCP25XXFD_RAM_START 0x400
-#define MCP25XXFD_RAM_SIZE SZ_2K
-
-/* Message Object */
-#define MCP25XXFD_OBJ_ID_SID11 BIT(29)
-#define MCP25XXFD_OBJ_ID_EID_MASK GENMASK(28, 11)
-#define MCP25XXFD_OBJ_ID_SID_MASK GENMASK(10, 0)
-#define MCP25XXFD_OBJ_FLAGS_SEQ_MCP2518FD_MASK GENMASK(31, 9)
-#define MCP25XXFD_OBJ_FLAGS_SEQ_MCP2517FD_MASK GENMASK(15, 9)
-#define MCP25XXFD_OBJ_FLAGS_SEQ_MASK MCP25XXFD_OBJ_FLAGS_SEQ_MCP2518FD_MASK
-#define MCP25XXFD_OBJ_FLAGS_ESI BIT(8)
-#define MCP25XXFD_OBJ_FLAGS_FDF BIT(7)
-#define MCP25XXFD_OBJ_FLAGS_BRS BIT(6)
-#define MCP25XXFD_OBJ_FLAGS_RTR BIT(5)
-#define MCP25XXFD_OBJ_FLAGS_IDE BIT(4)
-#define MCP25XXFD_OBJ_FLAGS_DLC GENMASK(3, 0)
-
-#define MCP25XXFD_REG_FRAME_EFF_SID_MASK GENMASK(28, 18)
-#define MCP25XXFD_REG_FRAME_EFF_EID_MASK GENMASK(17, 0)
-
-/* MCP2517/18FD SFR */
-#define MCP25XXFD_REG_OSC 0xe00
-#define MCP25XXFD_REG_OSC_SCLKRDY BIT(12)
-#define MCP25XXFD_REG_OSC_OSCRDY BIT(10)
-#define MCP25XXFD_REG_OSC_PLLRDY BIT(8)
-#define MCP25XXFD_REG_OSC_CLKODIV_10 3
-#define MCP25XXFD_REG_OSC_CLKODIV_4 2
-#define MCP25XXFD_REG_OSC_CLKODIV_2 1
-#define MCP25XXFD_REG_OSC_CLKODIV_1 0
-#define MCP25XXFD_REG_OSC_CLKODIV_MASK GENMASK(6, 5)
-#define MCP25XXFD_REG_OSC_SCLKDIV BIT(4)
-#define MCP25XXFD_REG_OSC_LPMEN BIT(3)	/* MCP2518FD only */
-#define MCP25XXFD_REG_OSC_OSCDIS BIT(2)
-#define MCP25XXFD_REG_OSC_PLLEN BIT(0)
-
-#define MCP25XXFD_REG_IOCON 0xe04
-#define MCP25XXFD_REG_IOCON_INTOD BIT(30)
-#define MCP25XXFD_REG_IOCON_SOF BIT(29)
-#define MCP25XXFD_REG_IOCON_TXCANOD BIT(28)
-#define MCP25XXFD_REG_IOCON_PM1 BIT(25)
-#define MCP25XXFD_REG_IOCON_PM0 BIT(24)
-#define MCP25XXFD_REG_IOCON_GPIO1 BIT(17)
-#define MCP25XXFD_REG_IOCON_GPIO0 BIT(16)
-#define MCP25XXFD_REG_IOCON_LAT1 BIT(9)
-#define MCP25XXFD_REG_IOCON_LAT0 BIT(8)
-#define MCP25XXFD_REG_IOCON_XSTBYEN BIT(6)
-#define MCP25XXFD_REG_IOCON_TRIS1 BIT(1)
-#define MCP25XXFD_REG_IOCON_TRIS0 BIT(0)
-
-#define MCP25XXFD_REG_CRC 0xe08
-#define MCP25XXFD_REG_CRC_FERRIE BIT(25)
-#define MCP25XXFD_REG_CRC_CRCERRIE BIT(24)
-#define MCP25XXFD_REG_CRC_FERRIF BIT(17)
-#define MCP25XXFD_REG_CRC_CRCERRIF BIT(16)
-#define MCP25XXFD_REG_CRC_IF_MASK GENMASK(17, 16)
-#define MCP25XXFD_REG_CRC_MASK GENMASK(15, 0)
-
-#define MCP25XXFD_REG_ECCCON 0xe0c
-#define MCP25XXFD_REG_ECCCON_PARITY_MASK GENMASK(14, 8)
-#define MCP25XXFD_REG_ECCCON_DEDIE BIT(2)
-#define MCP25XXFD_REG_ECCCON_SECIE BIT(1)
-#define MCP25XXFD_REG_ECCCON_ECCEN BIT(0)
-
-#define MCP25XXFD_REG_ECCSTAT 0xe10
-#define MCP25XXFD_REG_ECCSTAT_ERRADDR_MASK GENMASK(27, 16)
-#define MCP25XXFD_REG_ECCSTAT_IF_MASK GENMASK(2, 1)
-#define MCP25XXFD_REG_ECCSTAT_DEDIF BIT(2)
-#define MCP25XXFD_REG_ECCSTAT_SECIF BIT(1)
-
-#define MCP25XXFD_REG_DEVID 0xe14	/* MCP2518FD only */
-#define MCP25XXFD_REG_DEVID_ID_MASK GENMASK(7, 4)
-#define MCP25XXFD_REG_DEVID_REV_MASK GENMASK(3, 0)
-
-/* number of TX FIFO objects, depending on CAN mode
- *
- * FIFO setup: tef: 8*12 bytes = 96 bytes, tx: 8*16 bytes = 128 bytes
- * FIFO setup: tef: 4*12 bytes = 48 bytes, tx: 4*72 bytes = 288 bytes
- */
-#define MCP25XXFD_TX_OBJ_NUM_CAN 8
-#define MCP25XXFD_TX_OBJ_NUM_CANFD 4
-
-#if MCP25XXFD_TX_OBJ_NUM_CAN > MCP25XXFD_TX_OBJ_NUM_CANFD
-#define MCP25XXFD_TX_OBJ_NUM_MAX MCP25XXFD_TX_OBJ_NUM_CAN
-#else
-#define MCP25XXFD_TX_OBJ_NUM_MAX MCP25XXFD_TX_OBJ_NUM_CANFD
-#endif
-
-#define MCP25XXFD_NAPI_WEIGHT 32
-#define MCP25XXFD_TX_FIFO 1
-#define MCP25XXFD_RX_FIFO(x) (MCP25XXFD_TX_FIFO + 1 + (x))
-
-/* SPI commands */
-#define MCP25XXFD_SPI_INSTRUCTION_RESET 0x0000
-#define MCP25XXFD_SPI_INSTRUCTION_WRITE 0x2000
-#define MCP25XXFD_SPI_INSTRUCTION_READ 0x3000
-#define MCP25XXFD_SPI_INSTRUCTION_WRITE_CRC 0xa000
-#define MCP25XXFD_SPI_INSTRUCTION_READ_CRC 0xb000
-#define MCP25XXFD_SPI_INSTRUCTION_WRITE_CRC_SAFE 0xc000
-#define MCP25XXFD_SPI_ADDRESS_MASK GENMASK(11, 0)
-
-#define MCP25XXFD_SYSCLOCK_HZ_MAX 40000000
-#define MCP25XXFD_SYSCLOCK_HZ_MIN 1000000
-#define MCP25XXFD_SPICLOCK_HZ_MAX 20000000
-#define MCP25XXFD_OSC_PLL_MULTIPLIER 10
-#define MCP25XXFD_OSC_STAB_SLEEP_US (3 * USEC_PER_MSEC)
-#define MCP25XXFD_OSC_STAB_TIMEOUT_US (10 * MCP25XXFD_OSC_STAB_SLEEP_US)
-#define MCP25XXFD_POLL_SLEEP_US (10)
-#define MCP25XXFD_POLL_TIMEOUT_US (USEC_PER_MSEC)
-#define MCP25XXFD_SOFTRESET_RETRIES_MAX 3
-#define MCP25XXFD_READ_CRC_RETRIES_MAX 3
-#define MCP25XXFD_ECC_CNT_MAX 2
-#define MCP25XXFD_SANITIZE_SPI 1
-#define MCP25XXFD_SANITIZE_CAN 1
-
-/* Silence TX MAB overflow warnings */
-#define MCP25XXFD_QUIRK_MAB_NO_WARN BIT(0)
-/* Use CRC to access registers */
-#define MCP25XXFD_QUIRK_CRC_REG BIT(1)
-/* Use CRC to access RX/TEF-RAM */
-#define MCP25XXFD_QUIRK_CRC_RX BIT(2)
-/* Use CRC to access TX-RAM */
-#define MCP25XXFD_QUIRK_CRC_TX BIT(3)
-/* Enable ECC for RAM */
-#define MCP25XXFD_QUIRK_ECC BIT(4)
-/* Use Half Duplex SPI transfers */
-#define MCP25XXFD_QUIRK_HALF_DUPLEX BIT(5)
-
-struct mcp25xxfd_hw_tef_obj {
-	u32 id;
-	u32 flags;
-	u32 ts;
-};
-
-/* The tx_obj_raw version is used in spi async, i.e. without
- * regmap. We have to take care of endianness ourselves.
- */
-struct mcp25xxfd_hw_tx_obj_raw {
-	__le32 id;
-	__le32 flags;
-	u8 data[sizeof_field(struct canfd_frame, data)];
-};
-
-struct mcp25xxfd_hw_tx_obj_can {
-	u32 id;
-	u32 flags;
-	u8 data[sizeof_field(struct can_frame, data)];
-};
-
-struct mcp25xxfd_hw_tx_obj_canfd {
-	u32 id;
-	u32 flags;
-	u8 data[sizeof_field(struct canfd_frame, data)];
-};
-
-struct mcp25xxfd_hw_rx_obj_can {
-	u32 id;
-	u32 flags;
-	u32 ts;
-	u8 data[sizeof_field(struct can_frame, data)];
-};
-
-struct mcp25xxfd_hw_rx_obj_canfd {
-	u32 id;
-	u32 flags;
-	u32 ts;
-	u8 data[sizeof_field(struct canfd_frame, data)];
-};
-
-struct mcp25xxfd_tef_ring {
-	unsigned int head;
-	unsigned int tail;
-
-	/* u8 obj_num equals tx_ring->obj_num */
-	/* u8 obj_size equals sizeof(struct mcp25xxfd_hw_tef_obj) */
-};
-
-struct __packed mcp25xxfd_buf_cmd {
-	__be16 cmd;
-};
-
-struct __packed mcp25xxfd_buf_cmd_crc {
-	__be16 cmd;
-	u8 len;
-};
-
-union mcp25xxfd_tx_obj_load_buf {
-	struct __packed {
-		struct mcp25xxfd_buf_cmd cmd;
-		struct mcp25xxfd_hw_tx_obj_raw hw_tx_obj;
-	} nocrc;
-	struct __packed {
-		struct mcp25xxfd_buf_cmd_crc cmd;
-		struct mcp25xxfd_hw_tx_obj_raw hw_tx_obj;
-		__be16 crc;
-	} crc;
-} ____cacheline_aligned;
-
-union mcp25xxfd_write_reg_buf {
-	struct __packed {
-		struct mcp25xxfd_buf_cmd cmd;
-		u8 data[4];
-	} nocrc;
-	struct __packed {
-		struct mcp25xxfd_buf_cmd_crc cmd;
-		u8 data[4];
-		__be16 crc;
-	} crc;
-} ____cacheline_aligned;
-
-struct mcp25xxfd_tx_obj {
-	struct spi_message msg;
-	struct spi_transfer xfer[2];
-	union mcp25xxfd_tx_obj_load_buf buf;
-};
-
-struct mcp25xxfd_tx_ring {
-	unsigned int head;
-	unsigned int tail;
-
-	u16 base;
-	u8 obj_num;
-	u8 obj_size;
-
-	struct mcp25xxfd_tx_obj obj[MCP25XXFD_TX_OBJ_NUM_MAX];
-	union mcp25xxfd_write_reg_buf rts_buf;
-};
-
-struct mcp25xxfd_rx_ring {
-	unsigned int head;
-	unsigned int tail;
-
-	u16 base;
-	u8 nr;
-	u8 fifo_nr;
-	u8 obj_num;
-	u8 obj_size;
-
-	struct mcp25xxfd_hw_rx_obj_canfd obj[];
-};
-
-struct __packed mcp25xxfd_map_buf_nocrc {
-	struct mcp25xxfd_buf_cmd cmd;
-	u8 data[256];
-} ____cacheline_aligned;
-
-struct __packed mcp25xxfd_map_buf_crc {
-	struct mcp25xxfd_buf_cmd_crc cmd;
-	u8 data[256 - 4];
-	__be16 crc;
-} ____cacheline_aligned;
-
-struct mcp25xxfd_ecc {
-	u32 ecc_stat;
-	int cnt;
-};
-
-struct mcp25xxfd_regs_status {
-	u32 intf;
-};
-
-enum mcp25xxfd_model {
-	MCP25XXFD_MODEL_MCP2517FD = 0x2517,
-	MCP25XXFD_MODEL_MCP2518FD = 0x2518,
-	MCP25XXFD_MODEL_MCP25XXFD = 0xffff,	/* autodetect model */
-};
-
-struct mcp25xxfd_devtype_data {
-	enum mcp25xxfd_model model;
-	u32 quirks;
-};
-
-struct mcp25xxfd_priv {
-	struct can_priv can;
-	struct can_rx_offload offload;
-	struct net_device *ndev;
-
-	struct regmap *map_reg;			/* register access */
-	struct regmap *map_rx;			/* RX/TEF RAM access */
-
-	struct regmap *map_nocrc;
-	struct mcp25xxfd_map_buf_nocrc *map_buf_nocrc_rx;
-	struct mcp25xxfd_map_buf_nocrc *map_buf_nocrc_tx;
-
-	struct regmap *map_crc;
-	struct mcp25xxfd_map_buf_crc *map_buf_crc_rx;
-	struct mcp25xxfd_map_buf_crc *map_buf_crc_tx;
-
-	struct spi_device *spi;
-	u32 spi_max_speed_hz_orig;
-
-	struct mcp25xxfd_tef_ring tef;
-	struct mcp25xxfd_tx_ring tx[1];
-	struct mcp25xxfd_rx_ring *rx[1];
-
-	u8 rx_ring_num;
-
-	struct mcp25xxfd_ecc ecc;
-	struct mcp25xxfd_regs_status regs_status;
-
-	struct gpio_desc *rx_int;
-	struct clk *clk;
-	struct regulator *reg_vdd;
-	struct regulator *reg_xceiver;
-
-	struct mcp25xxfd_devtype_data devtype_data;
-	struct can_berr_counter bec;
-};
-
-#define MCP25XXFD_IS(_model) \
-static inline bool \
-mcp25xxfd_is_##_model(const struct mcp25xxfd_priv *priv) \
-{ \
-	return priv->devtype_data.model == MCP25XXFD_MODEL_MCP##_model##FD; \
-}
-
-MCP25XXFD_IS(2517);
-MCP25XXFD_IS(2518);
-MCP25XXFD_IS(25XX);
-
-static inline u8 mcp25xxfd_first_byte_set(u32 mask)
-{
-	return (mask & 0x0000ffff) ?
-		((mask & 0x000000ff) ? 0 : 1) :
-		((mask & 0x00ff0000) ? 2 : 3);
-}
-
-static inline u8 mcp25xxfd_last_byte_set(u32 mask)
-{
-	return (mask & 0xffff0000) ?
-		((mask & 0xff000000) ? 3 : 2) :
-		((mask & 0x0000ff00) ? 1 : 0);
-}
-
-static inline __be16 mcp25xxfd_cmd_reset(void)
-{
-	return cpu_to_be16(MCP25XXFD_SPI_INSTRUCTION_RESET);
-}
-
-static inline void
-mcp25xxfd_spi_cmd_read_nocrc(struct mcp25xxfd_buf_cmd *cmd, u16 addr)
-{
-	cmd->cmd = cpu_to_be16(MCP25XXFD_SPI_INSTRUCTION_READ | addr);
-}
-
-static inline void
-mcp25xxfd_spi_cmd_write_nocrc(struct mcp25xxfd_buf_cmd *cmd, u16 addr)
-{
-	cmd->cmd = cpu_to_be16(MCP25XXFD_SPI_INSTRUCTION_WRITE | addr);
-}
-
-static inline bool mcp25xxfd_reg_in_ram(unsigned int reg)
-{
-	static const struct regmap_range range =
-		regmap_reg_range(MCP25XXFD_RAM_START,
-				 MCP25XXFD_RAM_START + MCP25XXFD_RAM_SIZE - 4);
-
-	return regmap_reg_in_range(reg, &range);
-}
-
-static inline void
-__mcp25xxfd_spi_cmd_crc_set_len(struct mcp25xxfd_buf_cmd_crc *cmd,
-				u16 len, bool in_ram)
-{
-	/* Number of u32 for RAM access, number of u8 otherwise. */
-	if (in_ram)
-		cmd->len = len >> 2;
-	else
-		cmd->len = len;
-}
-
-static inline void
-mcp25xxfd_spi_cmd_crc_set_len_in_ram(struct mcp25xxfd_buf_cmd_crc *cmd, u16 len)
-{
-	__mcp25xxfd_spi_cmd_crc_set_len(cmd, len, true);
-}
-
-static inline void
-mcp25xxfd_spi_cmd_crc_set_len_in_reg(struct mcp25xxfd_buf_cmd_crc *cmd, u16 len)
-{
-	__mcp25xxfd_spi_cmd_crc_set_len(cmd, len, false);
-}
-
-static inline void
-mcp25xxfd_spi_cmd_read_crc_set_addr(struct mcp25xxfd_buf_cmd_crc *cmd, u16 addr)
-{
-	cmd->cmd = cpu_to_be16(MCP25XXFD_SPI_INSTRUCTION_READ_CRC | addr);
-}
-
-static inline void
-mcp25xxfd_spi_cmd_read_crc(struct mcp25xxfd_buf_cmd_crc *cmd,
-			   u16 addr, u16 len)
-{
-	mcp25xxfd_spi_cmd_read_crc_set_addr(cmd, addr);
-	__mcp25xxfd_spi_cmd_crc_set_len(cmd, len, mcp25xxfd_reg_in_ram(addr));
-}
-
-static inline void
-mcp25xxfd_spi_cmd_write_crc_set_addr(struct mcp25xxfd_buf_cmd_crc *cmd,
-				     u16 addr)
-{
-	cmd->cmd = cpu_to_be16(MCP25XXFD_SPI_INSTRUCTION_WRITE_CRC | addr);
-}
-
-static inline void
-mcp25xxfd_spi_cmd_write_crc(struct mcp25xxfd_buf_cmd_crc *cmd,
-			    u16 addr, u16 len)
-{
-	mcp25xxfd_spi_cmd_write_crc_set_addr(cmd, addr);
-	__mcp25xxfd_spi_cmd_crc_set_len(cmd, len, mcp25xxfd_reg_in_ram(addr));
-}
-
-static inline u8 *
-mcp25xxfd_spi_cmd_write(const struct mcp25xxfd_priv *priv,
-			union mcp25xxfd_write_reg_buf *write_reg_buf,
-			u16 addr)
-{
-	u8 *data;
-
-	if (priv->devtype_data.quirks & MCP25XXFD_QUIRK_CRC_REG) {
-		mcp25xxfd_spi_cmd_write_crc_set_addr(&write_reg_buf->crc.cmd,
-						     addr);
-		data = write_reg_buf->crc.data;
-	} else {
-		mcp25xxfd_spi_cmd_write_nocrc(&write_reg_buf->nocrc.cmd,
-					      addr);
-		data = write_reg_buf->nocrc.data;
-	}
-
-	return data;
-}
-
-static inline u16 mcp25xxfd_get_tef_obj_addr(u8 n)
-{
-	return MCP25XXFD_RAM_START +
-		sizeof(struct mcp25xxfd_hw_tef_obj) * n;
-}
-
-static inline u16
-mcp25xxfd_get_tx_obj_addr(const struct mcp25xxfd_tx_ring *ring, u8 n)
-{
-	return ring->base + ring->obj_size * n;
-}
-
-static inline u16
-mcp25xxfd_get_rx_obj_addr(const struct mcp25xxfd_rx_ring *ring, u8 n)
-{
-	return ring->base + ring->obj_size * n;
-}
-
-static inline u8 mcp25xxfd_get_tef_head(const struct mcp25xxfd_priv *priv)
-{
-	return priv->tef.head & (priv->tx->obj_num - 1);
-}
-
-static inline u8 mcp25xxfd_get_tef_tail(const struct mcp25xxfd_priv *priv)
-{
-	return priv->tef.tail & (priv->tx->obj_num - 1);
-}
-
-static inline u8 mcp25xxfd_get_tef_len(const struct mcp25xxfd_priv *priv)
-{
-	return priv->tef.head - priv->tef.tail;
-}
-
-static inline u8 mcp25xxfd_get_tef_linear_len(const struct mcp25xxfd_priv *priv)
-{
-	u8 len;
-
-	len = mcp25xxfd_get_tef_len(priv);
-
-	return min_t(u8, len, priv->tx->obj_num - mcp25xxfd_get_tef_tail(priv));
-}
-
-static inline u8 mcp25xxfd_get_tx_head(const struct mcp25xxfd_tx_ring *ring)
-{
-	return ring->head & (ring->obj_num - 1);
-}
-
-static inline u8 mcp25xxfd_get_tx_tail(const struct mcp25xxfd_tx_ring *ring)
-{
-	return ring->tail & (ring->obj_num - 1);
-}
-
-static inline u8 mcp25xxfd_get_tx_free(const struct mcp25xxfd_tx_ring *ring)
-{
-	return ring->obj_num - (ring->head - ring->tail);
-}
-
-static inline int
-mcp25xxfd_get_tx_nr_by_addr(const struct mcp25xxfd_tx_ring *tx_ring, u8 *nr,
-			    u16 addr)
-{
-	if (addr < mcp25xxfd_get_tx_obj_addr(tx_ring, 0) ||
-	    addr >= mcp25xxfd_get_tx_obj_addr(tx_ring, tx_ring->obj_num))
-		return -ENOENT;
-
-	*nr = (addr - mcp25xxfd_get_tx_obj_addr(tx_ring, 0)) /
-		tx_ring->obj_size;
-
-	return 0;
-}
-
-static inline u8 mcp25xxfd_get_rx_head(const struct mcp25xxfd_rx_ring *ring)
-{
-	return ring->head & (ring->obj_num - 1);
-}
-
-static inline u8 mcp25xxfd_get_rx_tail(const struct mcp25xxfd_rx_ring *ring)
-{
-	return ring->tail & (ring->obj_num - 1);
-}
-
-static inline u8 mcp25xxfd_get_rx_len(const struct mcp25xxfd_rx_ring *ring)
-{
-	return ring->head - ring->tail;
-}
-
-static inline u8
-mcp25xxfd_get_rx_linear_len(const struct mcp25xxfd_rx_ring *ring)
-{
-	u8 len;
-
-	len = mcp25xxfd_get_rx_len(ring);
-
-	return min_t(u8, len, ring->obj_num - mcp25xxfd_get_rx_tail(ring));
-}
-
-#define mcp25xxfd_for_each_tx_obj(ring, _obj, n) \
-	for ((n) = 0, (_obj) = &(ring)->obj[(n)]; \
-	     (n) < (ring)->obj_num; \
-	     (n)++, (_obj) = &(ring)->obj[(n)])
-
-#define mcp25xxfd_for_each_rx_ring(priv, ring, n) \
-	for ((n) = 0, (ring) = *((priv)->rx + (n)); \
-	     (n) < (priv)->rx_ring_num; \
-	     (n)++, (ring) = *((priv)->rx + (n)))
-
-int mcp25xxfd_regmap_init(struct mcp25xxfd_priv *priv);
-u16 mcp25xxfd_crc16_compute2(const void *cmd, size_t cmd_size,
-			     const void *data, size_t data_size);
-u16 mcp25xxfd_crc16_compute(const void *data, size_t data_size);
-
-#endif
diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index 6a5796c32721..ce18ba0b74eb 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -1377,23 +1377,6 @@ EXPORT_SYMBOL(b53_phylink_mac_link_up);
 int b53_vlan_filtering(struct dsa_switch *ds, int port, bool vlan_filtering)
 {
 	struct b53_device *dev = ds->priv;
-	u16 pvid, new_pvid;
-
-	b53_read16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(port), &pvid);
-	if (!vlan_filtering) {
-		/* Filtering is currently enabled, use the default PVID since
-		 * the bridge does not expect tagging anymore
-		 */
-		dev->ports[port].pvid = pvid;
-		new_pvid = b53_default_pvid(dev);
-	} else {
-		/* Filtering is currently disabled, restore the previous PVID */
-		new_pvid = dev->ports[port].pvid;
-	}
-
-	if (pvid != new_pvid)
-		b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(port),
-			    new_pvid);
 
 	b53_enable_vlan(dev, dev->vlan_enabled, vlan_filtering);
 
@@ -2619,6 +2602,9 @@ struct b53_device *b53_switch_alloc(struct device *base,
 	dev->priv = priv;
 	dev->ops = ops;
 	ds->ops = &b53_switch_ops;
+	ds->configure_vlan_while_not_filtering = true;
+	ds->untag_bridge_pvid = true;
+	dev->vlan_enabled = ds->configure_vlan_while_not_filtering;
 	mutex_init(&dev->reg_mutex);
 	mutex_init(&dev->stats_mutex);
 
diff --git a/drivers/net/dsa/b53/b53_priv.h b/drivers/net/dsa/b53/b53_priv.h
index c55c0a9f1b47..24893b592216 100644
--- a/drivers/net/dsa/b53/b53_priv.h
+++ b/drivers/net/dsa/b53/b53_priv.h
@@ -91,7 +91,6 @@ enum {
 struct b53_port {
 	u16		vlan_ctl_mask;
 	struct ethtool_eee eee;
-	u16		pvid;
 };
 
 struct b53_vlan {
diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index 723820603107..0b5b2b33b3b6 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -457,6 +457,7 @@ static void bcm_sf2_identify_ports(struct bcm_sf2_priv *priv,
 {
 	struct device_node *port;
 	unsigned int port_num;
+	struct property *prop;
 	phy_interface_t mode;
 	int err;
 
@@ -483,6 +484,16 @@ static void bcm_sf2_identify_ports(struct bcm_sf2_priv *priv,
 
 		if (of_property_read_bool(port, "brcm,use-bcm-hdr"))
 			priv->brcm_tag_mask |= 1 << port_num;
+
+		/* Ensure that port 5 is not picked up as a DSA CPU port
+		 * flavour but a regular port instead. We should be using
+		 * devlink to be able to set the port flavour.
+		 */
+		if (port_num == 5 && priv->type == BCM7278_DEVICE_ID) {
+			prop = of_find_property(port, "ethernet", NULL);
+			if (prop)
+				of_remove_property(port, prop);
+		}
 	}
 }
 
@@ -527,7 +538,7 @@ static int bcm_sf2_mdio_register(struct dsa_switch *ds)
 	 * driver.
 	 */
 	if (of_machine_is_compatible("brcm,bcm7445d0"))
-		priv->indir_phy_mask |= (1 << BRCM_PSEUDO_PHY_ADDR);
+		priv->indir_phy_mask |= (1 << BRCM_PSEUDO_PHY_ADDR) | (1 << 0);
 	else
 		priv->indir_phy_mask = 0;
 
diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c
index 8f1d15ea15d9..f5779e152377 100644
--- a/drivers/net/dsa/microchip/ksz8795.c
+++ b/drivers/net/dsa/microchip/ksz8795.c
@@ -932,11 +932,19 @@ static void ksz8795_port_setup(struct ksz_device *dev, int port, bool cpu_port)
 	ksz_port_cfg(dev, port, P_PRIO_CTRL, PORT_802_1P_ENABLE, true);
 
 	if (cpu_port) {
+		if (!p->interface && dev->compat_interface) {
+			dev_warn(dev->dev,
+				 "Using legacy switch \"phy-mode\" property, because it is missing on port %d node. "
+				 "Please update your device tree.\n",
+				 port);
+			p->interface = dev->compat_interface;
+		}
+
 		/* Configure MII interface for proper network communication. */
 		ksz_read8(dev, REG_PORT_5_CTRL_6, &data8);
 		data8 &= ~PORT_INTERFACE_TYPE;
 		data8 &= ~PORT_GMII_1GPS_MODE;
-		switch (dev->interface) {
+		switch (p->interface) {
 		case PHY_INTERFACE_MODE_MII:
 			p->phydev.speed = SPEED_100;
 			break;
@@ -952,11 +960,11 @@ static void ksz8795_port_setup(struct ksz_device *dev, int port, bool cpu_port)
 		default:
 			data8 &= ~PORT_RGMII_ID_IN_ENABLE;
 			data8 &= ~PORT_RGMII_ID_OUT_ENABLE;
-			if (dev->interface == PHY_INTERFACE_MODE_RGMII_ID ||
-			    dev->interface == PHY_INTERFACE_MODE_RGMII_RXID)
+			if (p->interface == PHY_INTERFACE_MODE_RGMII_ID ||
+			    p->interface == PHY_INTERFACE_MODE_RGMII_RXID)
 				data8 |= PORT_RGMII_ID_IN_ENABLE;
-			if (dev->interface == PHY_INTERFACE_MODE_RGMII_ID ||
-			    dev->interface == PHY_INTERFACE_MODE_RGMII_TXID)
+			if (p->interface == PHY_INTERFACE_MODE_RGMII_ID ||
+			    p->interface == PHY_INTERFACE_MODE_RGMII_TXID)
 				data8 |= PORT_RGMII_ID_OUT_ENABLE;
 			data8 |= PORT_GMII_1GPS_MODE;
 			data8 |= PORT_INTERFACE_RGMII;
@@ -1252,7 +1260,7 @@ static int ksz8795_switch_init(struct ksz_device *dev)
 	}
 
 	/* set the real number of ports */
-	dev->ds->num_ports = dev->port_cnt;
+	dev->ds->num_ports = dev->port_cnt + 1;
 
 	return 0;
 }
diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c
index b62dd64470a8..153664bf0e20 100644
--- a/drivers/net/dsa/microchip/ksz9477.c
+++ b/drivers/net/dsa/microchip/ksz9477.c
@@ -1208,7 +1208,7 @@ static void ksz9477_port_setup(struct ksz_device *dev, int port, bool cpu_port)
 
 		/* configure MAC to 1G & RGMII mode */
 		ksz_pread8(dev, port, REG_PORT_XMII_CTRL_1, &data8);
-		switch (dev->interface) {
+		switch (p->interface) {
 		case PHY_INTERFACE_MODE_MII:
 			ksz9477_set_xmii(dev, 0, &data8);
 			ksz9477_set_gbit(dev, false, &data8);
@@ -1229,11 +1229,11 @@ static void ksz9477_port_setup(struct ksz_device *dev, int port, bool cpu_port)
 			ksz9477_set_gbit(dev, true, &data8);
 			data8 &= ~PORT_RGMII_ID_IG_ENABLE;
 			data8 &= ~PORT_RGMII_ID_EG_ENABLE;
-			if (dev->interface == PHY_INTERFACE_MODE_RGMII_ID ||
-			    dev->interface == PHY_INTERFACE_MODE_RGMII_RXID)
+			if (p->interface == PHY_INTERFACE_MODE_RGMII_ID ||
+			    p->interface == PHY_INTERFACE_MODE_RGMII_RXID)
 				data8 |= PORT_RGMII_ID_IG_ENABLE;
-			if (dev->interface == PHY_INTERFACE_MODE_RGMII_ID ||
-			    dev->interface == PHY_INTERFACE_MODE_RGMII_TXID)
+			if (p->interface == PHY_INTERFACE_MODE_RGMII_ID ||
+			    p->interface == PHY_INTERFACE_MODE_RGMII_TXID)
 				data8 |= PORT_RGMII_ID_EG_ENABLE;
 			/* On KSZ9893, disable RGMII in-band status support */
 			if (dev->features & IS_9893)
@@ -1274,15 +1274,25 @@ static void ksz9477_config_cpu_port(struct dsa_switch *ds)
 			dev->cpu_port = i;
 			dev->host_mask = (1 << dev->cpu_port);
 			dev->port_mask |= dev->host_mask;
+			p = &dev->ports[i];
 
 			/* Read from XMII register to determine host port
 			 * interface.  If set specifically in device tree
 			 * note the difference to help debugging.
 			 */
 			interface = ksz9477_get_interface(dev, i);
-			if (!dev->interface)
-				dev->interface = interface;
-			if (interface && interface != dev->interface) {
+			if (!p->interface) {
+				if (dev->compat_interface) {
+					dev_warn(dev->dev,
+						 "Using legacy switch \"phy-mode\" property, because it is missing on port %d node. "
+						 "Please update your device tree.\n",
+						 i);
+					p->interface = dev->compat_interface;
+				} else {
+					p->interface = interface;
+				}
+			}
+			if (interface && interface != p->interface) {
 				prev_msg = " instead of ";
 				prev_mode = phy_modes(interface);
 			} else {
@@ -1292,13 +1302,12 @@ static void ksz9477_config_cpu_port(struct dsa_switch *ds)
 			dev_info(dev->dev,
 				 "Port%d: using phy mode %s%s%s\n",
 				 i,
-				 phy_modes(dev->interface),
+				 phy_modes(p->interface),
 				 prev_msg,
 				 prev_mode);
 
 			/* enable cpu port */
 			ksz9477_port_setup(dev, i, true);
-			p = &dev->ports[dev->cpu_port];
 			p->vid_member = dev->port_mask;
 			p->on = 1;
 		}
diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c
index a31738662d95..cb534547c715 100644
--- a/drivers/net/dsa/microchip/ksz_common.c
+++ b/drivers/net/dsa/microchip/ksz_common.c
@@ -388,6 +388,8 @@ int ksz_switch_register(struct ksz_device *dev,
 			const struct ksz_dev_ops *ops)
 {
 	phy_interface_t interface;
+	struct device_node *port;
+	unsigned int port_num;
 	int ret;
 
 	if (dev->pdata)
@@ -422,10 +424,19 @@ int ksz_switch_register(struct ksz_device *dev,
 	/* Host port interface will be self detected, or specifically set in
 	 * device tree.
 	 */
+	for (port_num = 0; port_num < dev->port_cnt; ++port_num)
+		dev->ports[port_num].interface = PHY_INTERFACE_MODE_NA;
 	if (dev->dev->of_node) {
 		ret = of_get_phy_mode(dev->dev->of_node, &interface);
 		if (ret == 0)
-			dev->interface = interface;
+			dev->compat_interface = interface;
+		for_each_available_child_of_node(dev->dev->of_node, port) {
+			if (of_property_read_u32(port, "reg", &port_num))
+				continue;
+			if (port_num >= dev->port_cnt)
+				return -EINVAL;
+			of_get_phy_mode(port, &dev->ports[port_num].interface);
+		}
 		dev->synclko_125 = of_property_read_bool(dev->dev->of_node,
 							 "microchip,synclko-125");
 	}
diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h
index 206838160f49..cf866e48ff66 100644
--- a/drivers/net/dsa/microchip/ksz_common.h
+++ b/drivers/net/dsa/microchip/ksz_common.h
@@ -39,6 +39,7 @@ struct ksz_port {
 	u32 freeze:1;			/* MIB counter freeze is enabled */
 
 	struct ksz_port_mib mib;
+	phy_interface_t interface;
 };
 
 struct ksz_device {
@@ -72,7 +73,7 @@ struct ksz_device {
 	int mib_cnt;
 	int mib_port_cnt;
 	int last_port;			/* ports after that not used */
-	phy_interface_t interface;
+	phy_interface_t compat_interface;
 	u32 regs_size;
 	bool phy_errata_9477;
 	bool synclko_125;
diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c
index f9a7034be0c7..552b1f7bde17 100644
--- a/drivers/net/dsa/ocelot/felix.c
+++ b/drivers/net/dsa/ocelot/felix.c
@@ -435,10 +435,10 @@ static int felix_init_structs(struct felix *felix, int num_phys_ports)
 	ocelot->num_stats	= felix->info->num_stats;
 	ocelot->shared_queue_sz	= felix->info->shared_queue_sz;
 	ocelot->num_mact_rows	= felix->info->num_mact_rows;
-	ocelot->vcap_is2_keys	= felix->info->vcap_is2_keys;
-	ocelot->vcap_is2_actions= felix->info->vcap_is2_actions;
 	ocelot->vcap		= felix->info->vcap;
 	ocelot->ops		= felix->info->ops;
+	ocelot->inj_prefix	= OCELOT_TAG_PREFIX_SHORT;
+	ocelot->xtr_prefix	= OCELOT_TAG_PREFIX_SHORT;
 
 	port_phy_modes = kcalloc(num_phys_ports, sizeof(phy_interface_t),
 				 GFP_KERNEL);
@@ -509,7 +509,7 @@ static int felix_init_structs(struct felix *felix, int num_phys_ports)
 			return PTR_ERR(target);
 		}
 
-		template = devm_kzalloc(ocelot->dev, OCELOT_TAG_LEN,
+		template = devm_kzalloc(ocelot->dev, OCELOT_TOTAL_TAG_LEN,
 					GFP_KERNEL);
 		if (!template) {
 			dev_err(ocelot->dev,
@@ -538,6 +538,28 @@ static int felix_init_structs(struct felix *felix, int num_phys_ports)
 	return 0;
 }
 
+/* The CPU port module is connected to the Node Processor Interface (NPI). This
+ * is the mode through which frames can be injected from and extracted to an
+ * external CPU, over Ethernet.
+ */
+static void felix_npi_port_init(struct ocelot *ocelot, int port)
+{
+	ocelot->npi = port;
+
+	ocelot_write(ocelot, QSYS_EXT_CPU_CFG_EXT_CPUQ_MSK_M |
+		     QSYS_EXT_CPU_CFG_EXT_CPU_PORT(port),
+		     QSYS_EXT_CPU_CFG);
+
+	/* NPI port Injection/Extraction configuration */
+	ocelot_fields_write(ocelot, port, SYS_PORT_MODE_INCL_XTR_HDR,
+			    ocelot->xtr_prefix);
+	ocelot_fields_write(ocelot, port, SYS_PORT_MODE_INCL_INJ_HDR,
+			    ocelot->inj_prefix);
+
+	/* Disable transmission of pause frames */
+	ocelot_fields_write(ocelot, port, SYS_PAUSE_CFG_PAUSE_ENA, 0);
+}
+
 /* Hardware initialization done here so that we can allocate structures with
  * devm without fear of dsa_register_switch returning -EPROBE_DEFER and causing
  * us to allocate structures twice (leak memory) and map PCI memory twice
@@ -554,7 +576,10 @@ static int felix_setup(struct dsa_switch *ds)
 	if (err)
 		return err;
 
-	ocelot_init(ocelot);
+	err = ocelot_init(ocelot);
+	if (err)
+		return err;
+
 	if (ocelot->ptp) {
 		err = ocelot_init_timestamp(ocelot, felix->info->ptp_caps);
 		if (err) {
@@ -567,11 +592,8 @@ static int felix_setup(struct dsa_switch *ds)
 	for (port = 0; port < ds->num_ports; port++) {
 		ocelot_init_port(ocelot, port);
 
-		/* Bring up the CPU port module and configure the NPI port */
 		if (dsa_is_cpu_port(ds, port))
-			ocelot_configure_cpu(ocelot, port,
-					     OCELOT_TAG_PREFIX_NONE,
-					     OCELOT_TAG_PREFIX_LONG);
+			felix_npi_port_init(ocelot, port);
 
 		/* Set the default QoS Classification based on PCP and DEI
 		 * bits of vlan tag.
@@ -604,10 +626,13 @@ static void felix_teardown(struct dsa_switch *ds)
 {
 	struct ocelot *ocelot = ds->priv;
 	struct felix *felix = ocelot_to_felix(ocelot);
+	int port;
 
 	if (felix->info->mdio_bus_free)
 		felix->info->mdio_bus_free(ocelot);
 
+	for (port = 0; port < ocelot->num_phys_ports; port++)
+		ocelot_deinit_port(ocelot, port);
 	ocelot_deinit_timestamp(ocelot);
 	/* stop workqueue thread */
 	ocelot_deinit(ocelot);
@@ -663,8 +688,11 @@ static bool felix_txtstamp(struct dsa_switch *ds, int port,
 	struct ocelot *ocelot = ds->priv;
 	struct ocelot_port *ocelot_port = ocelot->ports[port];
 
-	if (!ocelot_port_add_txtstamp_skb(ocelot_port, clone))
+	if (ocelot->ptp && (skb_shinfo(clone)->tx_flags & SKBTX_HW_TSTAMP) &&
+	    ocelot_port->ptp_cmd == IFH_REW_OP_TWO_STEP_PTP) {
+		ocelot_port_add_txtstamp_skb(ocelot, port, clone);
 		return true;
+	}
 
 	return false;
 }
@@ -782,3 +810,25 @@ const struct dsa_switch_ops felix_switch_ops = {
 	.cls_flower_stats	= felix_cls_flower_stats,
 	.port_setup_tc		= felix_port_setup_tc,
 };
+
+struct net_device *felix_port_to_netdev(struct ocelot *ocelot, int port)
+{
+	struct felix *felix = ocelot_to_felix(ocelot);
+	struct dsa_switch *ds = felix->ds;
+
+	if (!dsa_is_user_port(ds, port))
+		return NULL;
+
+	return dsa_to_port(ds, port)->slave;
+}
+
+int felix_netdev_to_port(struct net_device *dev)
+{
+	struct dsa_port *dp;
+
+	dp = dsa_port_from_netdev(dev);
+	if (IS_ERR(dp))
+		return -EINVAL;
+
+	return dp->index;
+}
diff --git a/drivers/net/dsa/ocelot/felix.h b/drivers/net/dsa/ocelot/felix.h
index cc3ec83a600a..4c717324ac2f 100644
--- a/drivers/net/dsa/ocelot/felix.h
+++ b/drivers/net/dsa/ocelot/felix.h
@@ -21,9 +21,7 @@ struct felix_info {
 	unsigned int			num_stats;
 	int				num_ports;
 	int				num_tx_queues;
-	struct vcap_field		*vcap_is2_keys;
-	struct vcap_field		*vcap_is2_actions;
-	const struct vcap_props		*vcap;
+	struct vcap_props		*vcap;
 	int				switch_pci_bar;
 	int				imdio_pci_bar;
 	const struct ptp_clock_info	*ptp_caps;
@@ -54,4 +52,7 @@ struct felix {
 	resource_size_t			imdio_base;
 };
 
+struct net_device *felix_port_to_netdev(struct ocelot *ocelot, int port);
+int felix_netdev_to_port(struct net_device *dev);
+
 #endif
diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c
index 79ddc4ba27a3..875ea60c0df0 100644
--- a/drivers/net/dsa/ocelot/felix_vsc9959.c
+++ b/drivers/net/dsa/ocelot/felix_vsc9959.c
@@ -16,9 +16,6 @@
 #include <linux/pci.h>
 #include "felix.h"
 
-#define VSC9959_VCAP_IS2_CNT		1024
-#define VSC9959_VCAP_IS2_ENTRY_WIDTH	376
-#define VSC9959_VCAP_PORT_CNT		6
 #define VSC9959_TAS_GCL_ENTRY_MAX	63
 
 static const u32 vsc9959_ana_regmap[] = {
@@ -138,14 +135,27 @@ static const u32 vsc9959_qs_regmap[] = {
 	REG_RESERVED(QS_INH_DBG),
 };
 
-static const u32 vsc9959_s2_regmap[] = {
-	REG(S2_CORE_UPDATE_CTRL,		0x000000),
-	REG(S2_CORE_MV_CFG,			0x000004),
-	REG(S2_CACHE_ENTRY_DAT,			0x000008),
-	REG(S2_CACHE_MASK_DAT,			0x000108),
-	REG(S2_CACHE_ACTION_DAT,		0x000208),
-	REG(S2_CACHE_CNT_DAT,			0x000308),
-	REG(S2_CACHE_TG_DAT,			0x000388),
+static const u32 vsc9959_vcap_regmap[] = {
+	/* VCAP_CORE_CFG */
+	REG(VCAP_CORE_UPDATE_CTRL,		0x000000),
+	REG(VCAP_CORE_MV_CFG,			0x000004),
+	/* VCAP_CORE_CACHE */
+	REG(VCAP_CACHE_ENTRY_DAT,		0x000008),
+	REG(VCAP_CACHE_MASK_DAT,		0x000108),
+	REG(VCAP_CACHE_ACTION_DAT,		0x000208),
+	REG(VCAP_CACHE_CNT_DAT,			0x000308),
+	REG(VCAP_CACHE_TG_DAT,			0x000388),
+	/* VCAP_CONST */
+	REG(VCAP_CONST_VCAP_VER,		0x000398),
+	REG(VCAP_CONST_ENTRY_WIDTH,		0x00039c),
+	REG(VCAP_CONST_ENTRY_CNT,		0x0003a0),
+	REG(VCAP_CONST_ENTRY_SWCNT,		0x0003a4),
+	REG(VCAP_CONST_ENTRY_TG_WIDTH,		0x0003a8),
+	REG(VCAP_CONST_ACTION_DEF_CNT,		0x0003ac),
+	REG(VCAP_CONST_ACTION_WIDTH,		0x0003b0),
+	REG(VCAP_CONST_CNT_WIDTH,		0x0003b4),
+	REG(VCAP_CONST_CORE_CNT,		0x0003b8),
+	REG(VCAP_CONST_IF_CNT,			0x0003bc),
 };
 
 static const u32 vsc9959_qsys_regmap[] = {
@@ -359,7 +369,9 @@ static const u32 *vsc9959_regmap[TARGET_MAX] = {
 	[QSYS]	= vsc9959_qsys_regmap,
 	[REW]	= vsc9959_rew_regmap,
 	[SYS]	= vsc9959_sys_regmap,
-	[S2]	= vsc9959_s2_regmap,
+	[S0]	= vsc9959_vcap_regmap,
+	[S1]	= vsc9959_vcap_regmap,
+	[S2]	= vsc9959_vcap_regmap,
 	[PTP]	= vsc9959_ptp_regmap,
 	[GCB]	= vsc9959_gcb_regmap,
 	[DEV_GMII] = vsc9959_dev_gmii_regmap,
@@ -392,6 +404,16 @@ static const struct resource vsc9959_target_io_res[TARGET_MAX] = {
 		.end	= 0x001ffff,
 		.name	= "sys",
 	},
+	[S0] = {
+		.start	= 0x0040000,
+		.end	= 0x00403ff,
+		.name	= "s0",
+	},
+	[S1] = {
+		.start	= 0x0050000,
+		.end	= 0x00503ff,
+		.name	= "s1",
+	},
 	[S2] = {
 		.start	= 0x0060000,
 		.end	= 0x00603ff,
@@ -596,6 +618,113 @@ static const struct ocelot_stat_layout vsc9959_stats_layout[] = {
 	{ .offset = 0x111,	.name = "drop_green_prio_7", },
 };
 
+static const struct vcap_field vsc9959_vcap_es0_keys[] = {
+	[VCAP_ES0_EGR_PORT]			= {  0,  3},
+	[VCAP_ES0_IGR_PORT]			= {  3,  3},
+	[VCAP_ES0_RSV]				= {  6,  2},
+	[VCAP_ES0_L2_MC]			= {  8,  1},
+	[VCAP_ES0_L2_BC]			= {  9,  1},
+	[VCAP_ES0_VID]				= { 10, 12},
+	[VCAP_ES0_DP]				= { 22,  1},
+	[VCAP_ES0_PCP]				= { 23,  3},
+};
+
+static const struct vcap_field vsc9959_vcap_es0_actions[] = {
+	[VCAP_ES0_ACT_PUSH_OUTER_TAG]		= {  0,  2},
+	[VCAP_ES0_ACT_PUSH_INNER_TAG]		= {  2,  1},
+	[VCAP_ES0_ACT_TAG_A_TPID_SEL]		= {  3,  2},
+	[VCAP_ES0_ACT_TAG_A_VID_SEL]		= {  5,  1},
+	[VCAP_ES0_ACT_TAG_A_PCP_SEL]		= {  6,  2},
+	[VCAP_ES0_ACT_TAG_A_DEI_SEL]		= {  8,  2},
+	[VCAP_ES0_ACT_TAG_B_TPID_SEL]		= { 10,  2},
+	[VCAP_ES0_ACT_TAG_B_VID_SEL]		= { 12,  1},
+	[VCAP_ES0_ACT_TAG_B_PCP_SEL]		= { 13,  2},
+	[VCAP_ES0_ACT_TAG_B_DEI_SEL]		= { 15,  2},
+	[VCAP_ES0_ACT_VID_A_VAL]		= { 17, 12},
+	[VCAP_ES0_ACT_PCP_A_VAL]		= { 29,  3},
+	[VCAP_ES0_ACT_DEI_A_VAL]		= { 32,  1},
+	[VCAP_ES0_ACT_VID_B_VAL]		= { 33, 12},
+	[VCAP_ES0_ACT_PCP_B_VAL]		= { 45,  3},
+	[VCAP_ES0_ACT_DEI_B_VAL]		= { 48,  1},
+	[VCAP_ES0_ACT_RSV]			= { 49, 23},
+	[VCAP_ES0_ACT_HIT_STICKY]		= { 72,  1},
+};
+
+static const struct vcap_field vsc9959_vcap_is1_keys[] = {
+	[VCAP_IS1_HK_TYPE]			= {  0,   1},
+	[VCAP_IS1_HK_LOOKUP]			= {  1,   2},
+	[VCAP_IS1_HK_IGR_PORT_MASK]		= {  3,   7},
+	[VCAP_IS1_HK_RSV]			= { 10,   9},
+	[VCAP_IS1_HK_OAM_Y1731]			= { 19,   1},
+	[VCAP_IS1_HK_L2_MC]			= { 20,   1},
+	[VCAP_IS1_HK_L2_BC]			= { 21,   1},
+	[VCAP_IS1_HK_IP_MC]			= { 22,   1},
+	[VCAP_IS1_HK_VLAN_TAGGED]		= { 23,   1},
+	[VCAP_IS1_HK_VLAN_DBL_TAGGED]		= { 24,   1},
+	[VCAP_IS1_HK_TPID]			= { 25,   1},
+	[VCAP_IS1_HK_VID]			= { 26,  12},
+	[VCAP_IS1_HK_DEI]			= { 38,   1},
+	[VCAP_IS1_HK_PCP]			= { 39,   3},
+	/* Specific Fields for IS1 Half Key S1_NORMAL */
+	[VCAP_IS1_HK_L2_SMAC]			= { 42,  48},
+	[VCAP_IS1_HK_ETYPE_LEN]			= { 90,   1},
+	[VCAP_IS1_HK_ETYPE]			= { 91,  16},
+	[VCAP_IS1_HK_IP_SNAP]			= {107,   1},
+	[VCAP_IS1_HK_IP4]			= {108,   1},
+	/* Layer-3 Information */
+	[VCAP_IS1_HK_L3_FRAGMENT]		= {109,   1},
+	[VCAP_IS1_HK_L3_FRAG_OFS_GT0]		= {110,   1},
+	[VCAP_IS1_HK_L3_OPTIONS]		= {111,   1},
+	[VCAP_IS1_HK_L3_DSCP]			= {112,   6},
+	[VCAP_IS1_HK_L3_IP4_SIP]		= {118,  32},
+	/* Layer-4 Information */
+	[VCAP_IS1_HK_TCP_UDP]			= {150,   1},
+	[VCAP_IS1_HK_TCP]			= {151,   1},
+	[VCAP_IS1_HK_L4_SPORT]			= {152,  16},
+	[VCAP_IS1_HK_L4_RNG]			= {168,   8},
+	/* Specific Fields for IS1 Half Key S1_5TUPLE_IP4 */
+	[VCAP_IS1_HK_IP4_INNER_TPID]            = { 42,   1},
+	[VCAP_IS1_HK_IP4_INNER_VID]		= { 43,  12},
+	[VCAP_IS1_HK_IP4_INNER_DEI]		= { 55,   1},
+	[VCAP_IS1_HK_IP4_INNER_PCP]		= { 56,   3},
+	[VCAP_IS1_HK_IP4_IP4]			= { 59,   1},
+	[VCAP_IS1_HK_IP4_L3_FRAGMENT]		= { 60,   1},
+	[VCAP_IS1_HK_IP4_L3_FRAG_OFS_GT0]	= { 61,   1},
+	[VCAP_IS1_HK_IP4_L3_OPTIONS]		= { 62,   1},
+	[VCAP_IS1_HK_IP4_L3_DSCP]		= { 63,   6},
+	[VCAP_IS1_HK_IP4_L3_IP4_DIP]		= { 69,  32},
+	[VCAP_IS1_HK_IP4_L3_IP4_SIP]		= {101,  32},
+	[VCAP_IS1_HK_IP4_L3_PROTO]		= {133,   8},
+	[VCAP_IS1_HK_IP4_TCP_UDP]		= {141,   1},
+	[VCAP_IS1_HK_IP4_TCP]			= {142,   1},
+	[VCAP_IS1_HK_IP4_L4_RNG]		= {143,   8},
+	[VCAP_IS1_HK_IP4_IP_PAYLOAD_S1_5TUPLE]	= {151,  32},
+};
+
+static const struct vcap_field vsc9959_vcap_is1_actions[] = {
+	[VCAP_IS1_ACT_DSCP_ENA]			= {  0,  1},
+	[VCAP_IS1_ACT_DSCP_VAL]			= {  1,  6},
+	[VCAP_IS1_ACT_QOS_ENA]			= {  7,  1},
+	[VCAP_IS1_ACT_QOS_VAL]			= {  8,  3},
+	[VCAP_IS1_ACT_DP_ENA]			= { 11,  1},
+	[VCAP_IS1_ACT_DP_VAL]			= { 12,  1},
+	[VCAP_IS1_ACT_PAG_OVERRIDE_MASK]	= { 13,  8},
+	[VCAP_IS1_ACT_PAG_VAL]			= { 21,  8},
+	[VCAP_IS1_ACT_RSV]			= { 29,  9},
+	/* The fields below are incorrectly shifted by 2 in the manual */
+	[VCAP_IS1_ACT_VID_REPLACE_ENA]		= { 38,  1},
+	[VCAP_IS1_ACT_VID_ADD_VAL]		= { 39, 12},
+	[VCAP_IS1_ACT_FID_SEL]			= { 51,  2},
+	[VCAP_IS1_ACT_FID_VAL]			= { 53, 13},
+	[VCAP_IS1_ACT_PCP_DEI_ENA]		= { 66,  1},
+	[VCAP_IS1_ACT_PCP_VAL]			= { 67,  3},
+	[VCAP_IS1_ACT_DEI_VAL]			= { 70,  1},
+	[VCAP_IS1_ACT_VLAN_POP_CNT_ENA]		= { 71,  1},
+	[VCAP_IS1_ACT_VLAN_POP_CNT]		= { 72,  2},
+	[VCAP_IS1_ACT_CUSTOM_ACE_TYPE_ENA]	= { 74,  4},
+	[VCAP_IS1_ACT_HIT_STICKY]		= { 78,  1},
+};
+
 static struct vcap_field vsc9959_vcap_is2_keys[] = {
 	/* Common: 41 bits */
 	[VCAP_IS2_TYPE]				= {  0,   4},
@@ -646,17 +775,17 @@ static struct vcap_field vsc9959_vcap_is2_keys[] = {
 	[VCAP_IS2_HK_DIP_EQ_SIP]		= {118,   1},
 	/* IP4_TCP_UDP (TYPE=100) */
 	[VCAP_IS2_HK_TCP]			= {119,   1},
-	[VCAP_IS2_HK_L4_SPORT]			= {120,  16},
-	[VCAP_IS2_HK_L4_DPORT]			= {136,  16},
+	[VCAP_IS2_HK_L4_DPORT]			= {120,  16},
+	[VCAP_IS2_HK_L4_SPORT]			= {136,  16},
 	[VCAP_IS2_HK_L4_RNG]			= {152,   8},
 	[VCAP_IS2_HK_L4_SPORT_EQ_DPORT]		= {160,   1},
 	[VCAP_IS2_HK_L4_SEQUENCE_EQ0]		= {161,   1},
-	[VCAP_IS2_HK_L4_URG]			= {162,   1},
-	[VCAP_IS2_HK_L4_ACK]			= {163,   1},
-	[VCAP_IS2_HK_L4_PSH]			= {164,   1},
-	[VCAP_IS2_HK_L4_RST]			= {165,   1},
-	[VCAP_IS2_HK_L4_SYN]			= {166,   1},
-	[VCAP_IS2_HK_L4_FIN]			= {167,   1},
+	[VCAP_IS2_HK_L4_FIN]			= {162,   1},
+	[VCAP_IS2_HK_L4_SYN]			= {163,   1},
+	[VCAP_IS2_HK_L4_RST]			= {164,   1},
+	[VCAP_IS2_HK_L4_PSH]			= {165,   1},
+	[VCAP_IS2_HK_L4_ACK]			= {166,   1},
+	[VCAP_IS2_HK_L4_URG]			= {167,   1},
 	[VCAP_IS2_HK_L4_1588_DOM]		= {168,   8},
 	[VCAP_IS2_HK_L4_1588_VER]		= {176,   4},
 	/* IP4_OTHER (TYPE=101) */
@@ -694,15 +823,32 @@ static struct vcap_field vsc9959_vcap_is2_actions[] = {
 	[VCAP_IS2_ACT_HIT_CNT]			= { 49, 32},
 };
 
-static const struct vcap_props vsc9959_vcap_props[] = {
+static struct vcap_props vsc9959_vcap_props[] = {
+	[VCAP_ES0] = {
+		.action_type_width = 0,
+		.action_table = {
+			[ES0_ACTION_TYPE_NORMAL] = {
+				.width = 72, /* HIT_STICKY not included */
+				.count = 1,
+			},
+		},
+		.target = S0,
+		.keys = vsc9959_vcap_es0_keys,
+		.actions = vsc9959_vcap_es0_actions,
+	},
+	[VCAP_IS1] = {
+		.action_type_width = 0,
+		.action_table = {
+			[IS1_ACTION_TYPE_NORMAL] = {
+				.width = 78, /* HIT_STICKY not included */
+				.count = 4,
+			},
+		},
+		.target = S1,
+		.keys = vsc9959_vcap_is1_keys,
+		.actions = vsc9959_vcap_is1_actions,
+	},
 	[VCAP_IS2] = {
-		.tg_width = 2,
-		.sw_count = 4,
-		.entry_count = VSC9959_VCAP_IS2_CNT,
-		.entry_width = VSC9959_VCAP_IS2_ENTRY_WIDTH,
-		.action_count = VSC9959_VCAP_IS2_CNT +
-				VSC9959_VCAP_PORT_CNT + 2,
-		.action_width = 89,
 		.action_type_width = 1,
 		.action_table = {
 			[IS2_ACTION_TYPE_NORMAL] = {
@@ -714,8 +860,9 @@ static const struct vcap_props vsc9959_vcap_props[] = {
 				.count = 4
 			},
 		},
-		.counter_words = 4,
-		.counter_width = 32,
+		.target = S2,
+		.keys = vsc9959_vcap_is2_keys,
+		.actions = vsc9959_vcap_is2_actions,
 	},
 };
 
@@ -860,6 +1007,8 @@ static u16 vsc9959_wm_enc(u16 value)
 static const struct ocelot_ops vsc9959_ops = {
 	.reset			= vsc9959_reset,
 	.wm_enc			= vsc9959_wm_enc,
+	.port_to_netdev		= felix_port_to_netdev,
+	.netdev_to_port		= felix_netdev_to_port,
 };
 
 static int vsc9959_mdio_bus_alloc(struct ocelot *ocelot)
@@ -1155,6 +1304,8 @@ static void vsc9959_xmit_template_populate(struct ocelot *ocelot, int port)
 	struct ocelot_port *ocelot_port = ocelot->ports[port];
 	u8 *template = ocelot_port->xmit_template;
 	u64 bypass, dest, src;
+	__be32 *prefix;
+	u8 *injection;
 
 	/* Set the source port as the CPU port module and not the
 	 * NPI port
@@ -1163,9 +1314,14 @@ static void vsc9959_xmit_template_populate(struct ocelot *ocelot, int port)
 	dest = BIT(port);
 	bypass = true;
 
-	packing(template, &bypass, 127, 127, OCELOT_TAG_LEN, PACK, 0);
-	packing(template, &dest,    68,  56, OCELOT_TAG_LEN, PACK, 0);
-	packing(template, &src,     46,  43, OCELOT_TAG_LEN, PACK, 0);
+	injection = template + OCELOT_SHORT_PREFIX_LEN;
+	prefix = (__be32 *)template;
+
+	packing(injection, &bypass, 127, 127, OCELOT_TAG_LEN, PACK, 0);
+	packing(injection, &dest,    68,  56, OCELOT_TAG_LEN, PACK, 0);
+	packing(injection, &src,     46,  43, OCELOT_TAG_LEN, PACK, 0);
+
+	*prefix = cpu_to_be32(0x8880000a);
 }
 
 static const struct felix_info felix_info_vsc9959 = {
@@ -1177,8 +1333,6 @@ static const struct felix_info felix_info_vsc9959 = {
 	.ops			= &vsc9959_ops,
 	.stats_layout		= vsc9959_stats_layout,
 	.num_stats		= ARRAY_SIZE(vsc9959_stats_layout),
-	.vcap_is2_keys		= vsc9959_vcap_is2_keys,
-	.vcap_is2_actions	= vsc9959_vcap_is2_actions,
 	.vcap			= vsc9959_vcap_props,
 	.shared_queue_sz	= 128 * 1024,
 	.num_mact_rows		= 2048,
diff --git a/drivers/net/dsa/ocelot/seville_vsc9953.c b/drivers/net/dsa/ocelot/seville_vsc9953.c
index 12c7fb9c2c3f..f9b7507a4eb3 100644
--- a/drivers/net/dsa/ocelot/seville_vsc9953.c
+++ b/drivers/net/dsa/ocelot/seville_vsc9953.c
@@ -12,10 +12,6 @@
 #include <linux/iopoll.h>
 #include "felix.h"
 
-#define VSC9953_VCAP_IS2_CNT			1024
-#define VSC9953_VCAP_IS2_ENTRY_WIDTH		376
-#define VSC9953_VCAP_PORT_CNT			10
-
 #define MSCC_MIIM_CMD_OPR_WRITE			BIT(1)
 #define MSCC_MIIM_CMD_OPR_READ			BIT(2)
 #define MSCC_MIIM_CMD_WRDATA_SHIFT		4
@@ -140,14 +136,27 @@ static const u32 vsc9953_qs_regmap[] = {
 	REG_RESERVED(QS_INH_DBG),
 };
 
-static const u32 vsc9953_s2_regmap[] = {
-	REG(S2_CORE_UPDATE_CTRL,		0x000000),
-	REG(S2_CORE_MV_CFG,			0x000004),
-	REG(S2_CACHE_ENTRY_DAT,			0x000008),
-	REG(S2_CACHE_MASK_DAT,			0x000108),
-	REG(S2_CACHE_ACTION_DAT,		0x000208),
-	REG(S2_CACHE_CNT_DAT,			0x000308),
-	REG(S2_CACHE_TG_DAT,			0x000388),
+static const u32 vsc9953_vcap_regmap[] = {
+	/* VCAP_CORE_CFG */
+	REG(VCAP_CORE_UPDATE_CTRL,		0x000000),
+	REG(VCAP_CORE_MV_CFG,			0x000004),
+	/* VCAP_CORE_CACHE */
+	REG(VCAP_CACHE_ENTRY_DAT,		0x000008),
+	REG(VCAP_CACHE_MASK_DAT,		0x000108),
+	REG(VCAP_CACHE_ACTION_DAT,		0x000208),
+	REG(VCAP_CACHE_CNT_DAT,			0x000308),
+	REG(VCAP_CACHE_TG_DAT,			0x000388),
+	/* VCAP_CONST */
+	REG(VCAP_CONST_VCAP_VER,		0x000398),
+	REG(VCAP_CONST_ENTRY_WIDTH,		0x00039c),
+	REG(VCAP_CONST_ENTRY_CNT,		0x0003a0),
+	REG(VCAP_CONST_ENTRY_SWCNT,		0x0003a4),
+	REG(VCAP_CONST_ENTRY_TG_WIDTH,		0x0003a8),
+	REG(VCAP_CONST_ACTION_DEF_CNT,		0x0003ac),
+	REG(VCAP_CONST_ACTION_WIDTH,		0x0003b0),
+	REG(VCAP_CONST_CNT_WIDTH,		0x0003b4),
+	REG_RESERVED(VCAP_CONST_CORE_CNT),
+	REG_RESERVED(VCAP_CONST_IF_CNT),
 };
 
 static const u32 vsc9953_qsys_regmap[] = {
@@ -352,7 +361,9 @@ static const u32 *vsc9953_regmap[TARGET_MAX] = {
 	[QSYS]		= vsc9953_qsys_regmap,
 	[REW]		= vsc9953_rew_regmap,
 	[SYS]		= vsc9953_sys_regmap,
-	[S2]		= vsc9953_s2_regmap,
+	[S0]		= vsc9953_vcap_regmap,
+	[S1]		= vsc9953_vcap_regmap,
+	[S2]		= vsc9953_vcap_regmap,
 	[GCB]		= vsc9953_gcb_regmap,
 	[DEV_GMII]	= vsc9953_dev_gmii_regmap,
 };
@@ -384,6 +395,16 @@ static const struct resource vsc9953_target_io_res[TARGET_MAX] = {
 		.end	= 0x001ffff,
 		.name	= "sys",
 	},
+	[S0] = {
+		.start	= 0x0040000,
+		.end	= 0x00403ff,
+		.name	= "s0",
+	},
+	[S1] = {
+		.start	= 0x0050000,
+		.end	= 0x00503ff,
+		.name	= "s1",
+	},
 	[S2] = {
 		.start	= 0x0060000,
 		.end	= 0x00603ff,
@@ -599,6 +620,112 @@ static const struct ocelot_stat_layout vsc9953_stats_layout[] = {
 	{ .offset = 0x91,	.name = "drop_green_prio_7", },
 };
 
+static const struct vcap_field vsc9953_vcap_es0_keys[] = {
+	[VCAP_ES0_EGR_PORT]			= {  0,  4},
+	[VCAP_ES0_IGR_PORT]			= {  4,  4},
+	[VCAP_ES0_RSV]				= {  8,  2},
+	[VCAP_ES0_L2_MC]			= { 10,  1},
+	[VCAP_ES0_L2_BC]			= { 11,  1},
+	[VCAP_ES0_VID]				= { 12, 12},
+	[VCAP_ES0_DP]				= { 24,  1},
+	[VCAP_ES0_PCP]				= { 25,  3},
+};
+
+static const struct vcap_field vsc9953_vcap_es0_actions[] = {
+	[VCAP_ES0_ACT_PUSH_OUTER_TAG]		= {  0,  2},
+	[VCAP_ES0_ACT_PUSH_INNER_TAG]		= {  2,  1},
+	[VCAP_ES0_ACT_TAG_A_TPID_SEL]		= {  3,  2},
+	[VCAP_ES0_ACT_TAG_A_VID_SEL]		= {  5,  1},
+	[VCAP_ES0_ACT_TAG_A_PCP_SEL]		= {  6,  2},
+	[VCAP_ES0_ACT_TAG_A_DEI_SEL]		= {  8,  2},
+	[VCAP_ES0_ACT_TAG_B_TPID_SEL]		= { 10,  2},
+	[VCAP_ES0_ACT_TAG_B_VID_SEL]		= { 12,  1},
+	[VCAP_ES0_ACT_TAG_B_PCP_SEL]		= { 13,  2},
+	[VCAP_ES0_ACT_TAG_B_DEI_SEL]		= { 15,  2},
+	[VCAP_ES0_ACT_VID_A_VAL]		= { 17, 12},
+	[VCAP_ES0_ACT_PCP_A_VAL]		= { 29,  3},
+	[VCAP_ES0_ACT_DEI_A_VAL]		= { 32,  1},
+	[VCAP_ES0_ACT_VID_B_VAL]		= { 33, 12},
+	[VCAP_ES0_ACT_PCP_B_VAL]		= { 45,  3},
+	[VCAP_ES0_ACT_DEI_B_VAL]		= { 48,  1},
+	[VCAP_ES0_ACT_RSV]			= { 49, 24},
+	[VCAP_ES0_ACT_HIT_STICKY]		= { 73,  1},
+};
+
+static const struct vcap_field vsc9953_vcap_is1_keys[] = {
+	[VCAP_IS1_HK_TYPE]			= {  0,   1},
+	[VCAP_IS1_HK_LOOKUP]			= {  1,   2},
+	[VCAP_IS1_HK_IGR_PORT_MASK]		= {  3,  11},
+	[VCAP_IS1_HK_RSV]			= { 14,  10},
+	/* VCAP_IS1_HK_OAM_Y1731 not supported */
+	[VCAP_IS1_HK_L2_MC]			= { 24,   1},
+	[VCAP_IS1_HK_L2_BC]			= { 25,   1},
+	[VCAP_IS1_HK_IP_MC]			= { 26,   1},
+	[VCAP_IS1_HK_VLAN_TAGGED]		= { 27,   1},
+	[VCAP_IS1_HK_VLAN_DBL_TAGGED]		= { 28,   1},
+	[VCAP_IS1_HK_TPID]			= { 29,   1},
+	[VCAP_IS1_HK_VID]			= { 30,  12},
+	[VCAP_IS1_HK_DEI]			= { 42,   1},
+	[VCAP_IS1_HK_PCP]			= { 43,   3},
+	/* Specific Fields for IS1 Half Key S1_NORMAL */
+	[VCAP_IS1_HK_L2_SMAC]			= { 46,  48},
+	[VCAP_IS1_HK_ETYPE_LEN]			= { 94,   1},
+	[VCAP_IS1_HK_ETYPE]			= { 95,  16},
+	[VCAP_IS1_HK_IP_SNAP]			= {111,   1},
+	[VCAP_IS1_HK_IP4]			= {112,   1},
+	/* Layer-3 Information */
+	[VCAP_IS1_HK_L3_FRAGMENT]		= {113,   1},
+	[VCAP_IS1_HK_L3_FRAG_OFS_GT0]		= {114,   1},
+	[VCAP_IS1_HK_L3_OPTIONS]		= {115,   1},
+	[VCAP_IS1_HK_L3_DSCP]			= {116,   6},
+	[VCAP_IS1_HK_L3_IP4_SIP]		= {122,  32},
+	/* Layer-4 Information */
+	[VCAP_IS1_HK_TCP_UDP]			= {154,   1},
+	[VCAP_IS1_HK_TCP]			= {155,   1},
+	[VCAP_IS1_HK_L4_SPORT]			= {156,  16},
+	[VCAP_IS1_HK_L4_RNG]			= {172,   8},
+	/* Specific Fields for IS1 Half Key S1_5TUPLE_IP4 */
+	[VCAP_IS1_HK_IP4_INNER_TPID]            = { 46,   1},
+	[VCAP_IS1_HK_IP4_INNER_VID]		= { 47,  12},
+	[VCAP_IS1_HK_IP4_INNER_DEI]		= { 59,   1},
+	[VCAP_IS1_HK_IP4_INNER_PCP]		= { 60,   3},
+	[VCAP_IS1_HK_IP4_IP4]			= { 63,   1},
+	[VCAP_IS1_HK_IP4_L3_FRAGMENT]		= { 64,   1},
+	[VCAP_IS1_HK_IP4_L3_FRAG_OFS_GT0]	= { 65,   1},
+	[VCAP_IS1_HK_IP4_L3_OPTIONS]		= { 66,   1},
+	[VCAP_IS1_HK_IP4_L3_DSCP]		= { 67,   6},
+	[VCAP_IS1_HK_IP4_L3_IP4_DIP]		= { 73,  32},
+	[VCAP_IS1_HK_IP4_L3_IP4_SIP]		= {105,  32},
+	[VCAP_IS1_HK_IP4_L3_PROTO]		= {137,   8},
+	[VCAP_IS1_HK_IP4_TCP_UDP]		= {145,   1},
+	[VCAP_IS1_HK_IP4_TCP]			= {146,   1},
+	[VCAP_IS1_HK_IP4_L4_RNG]		= {147,   8},
+	[VCAP_IS1_HK_IP4_IP_PAYLOAD_S1_5TUPLE]	= {155,  32},
+};
+
+static const struct vcap_field vsc9953_vcap_is1_actions[] = {
+	[VCAP_IS1_ACT_DSCP_ENA]			= {  0,  1},
+	[VCAP_IS1_ACT_DSCP_VAL]			= {  1,  6},
+	[VCAP_IS1_ACT_QOS_ENA]			= {  7,  1},
+	[VCAP_IS1_ACT_QOS_VAL]			= {  8,  3},
+	[VCAP_IS1_ACT_DP_ENA]			= { 11,  1},
+	[VCAP_IS1_ACT_DP_VAL]			= { 12,  1},
+	[VCAP_IS1_ACT_PAG_OVERRIDE_MASK]	= { 13,  8},
+	[VCAP_IS1_ACT_PAG_VAL]			= { 21,  8},
+	[VCAP_IS1_ACT_RSV]			= { 29, 11},
+	[VCAP_IS1_ACT_VID_REPLACE_ENA]		= { 40,  1},
+	[VCAP_IS1_ACT_VID_ADD_VAL]		= { 41, 12},
+	[VCAP_IS1_ACT_FID_SEL]			= { 53,  2},
+	[VCAP_IS1_ACT_FID_VAL]			= { 55, 13},
+	[VCAP_IS1_ACT_PCP_DEI_ENA]		= { 68,  1},
+	[VCAP_IS1_ACT_PCP_VAL]			= { 69,  3},
+	[VCAP_IS1_ACT_DEI_VAL]			= { 72,  1},
+	[VCAP_IS1_ACT_VLAN_POP_CNT_ENA]		= { 73,  1},
+	[VCAP_IS1_ACT_VLAN_POP_CNT]		= { 74,  2},
+	[VCAP_IS1_ACT_CUSTOM_ACE_TYPE_ENA]	= { 76,  4},
+	[VCAP_IS1_ACT_HIT_STICKY]		= { 80,  1},
+};
+
 static struct vcap_field vsc9953_vcap_is2_keys[] = {
 	/* Common: 41 bits */
 	[VCAP_IS2_TYPE]				= {  0,   4},
@@ -649,17 +776,17 @@ static struct vcap_field vsc9953_vcap_is2_keys[] = {
 	[VCAP_IS2_HK_DIP_EQ_SIP]		= {122,   1},
 	/* IP4_TCP_UDP (TYPE=100) */
 	[VCAP_IS2_HK_TCP]			= {123,   1},
-	[VCAP_IS2_HK_L4_SPORT]			= {124,  16},
-	[VCAP_IS2_HK_L4_DPORT]			= {140,  16},
+	[VCAP_IS2_HK_L4_DPORT]			= {124,  16},
+	[VCAP_IS2_HK_L4_SPORT]			= {140,  16},
 	[VCAP_IS2_HK_L4_RNG]			= {156,   8},
 	[VCAP_IS2_HK_L4_SPORT_EQ_DPORT]		= {164,   1},
 	[VCAP_IS2_HK_L4_SEQUENCE_EQ0]		= {165,   1},
-	[VCAP_IS2_HK_L4_URG]			= {166,   1},
-	[VCAP_IS2_HK_L4_ACK]			= {167,   1},
-	[VCAP_IS2_HK_L4_PSH]			= {168,   1},
-	[VCAP_IS2_HK_L4_RST]			= {169,   1},
-	[VCAP_IS2_HK_L4_SYN]			= {170,   1},
-	[VCAP_IS2_HK_L4_FIN]			= {171,   1},
+	[VCAP_IS2_HK_L4_FIN]			= {166,   1},
+	[VCAP_IS2_HK_L4_SYN]			= {167,   1},
+	[VCAP_IS2_HK_L4_RST]			= {168,   1},
+	[VCAP_IS2_HK_L4_PSH]			= {169,   1},
+	[VCAP_IS2_HK_L4_ACK]			= {170,   1},
+	[VCAP_IS2_HK_L4_URG]			= {171,   1},
 	/* IP4_OTHER (TYPE=101) */
 	[VCAP_IS2_HK_IP4_L3_PROTO]		= {123,   8},
 	[VCAP_IS2_HK_L3_PAYLOAD]		= {131,  56},
@@ -684,15 +811,32 @@ static struct vcap_field vsc9953_vcap_is2_actions[] = {
 	[VCAP_IS2_ACT_HIT_CNT]			= { 50, 32},
 };
 
-static const struct vcap_props vsc9953_vcap_props[] = {
+static struct vcap_props vsc9953_vcap_props[] = {
+	[VCAP_ES0] = {
+		.action_type_width = 0,
+		.action_table = {
+			[ES0_ACTION_TYPE_NORMAL] = {
+				.width = 73, /* HIT_STICKY not included */
+				.count = 1,
+			},
+		},
+		.target = S0,
+		.keys = vsc9953_vcap_es0_keys,
+		.actions = vsc9953_vcap_es0_actions,
+	},
+	[VCAP_IS1] = {
+		.action_type_width = 0,
+		.action_table = {
+			[IS1_ACTION_TYPE_NORMAL] = {
+				.width = 80, /* HIT_STICKY not included */
+				.count = 4,
+			},
+		},
+		.target = S1,
+		.keys = vsc9953_vcap_is1_keys,
+		.actions = vsc9953_vcap_is1_actions,
+	},
 	[VCAP_IS2] = {
-		.tg_width = 2,
-		.sw_count = 4,
-		.entry_count = VSC9953_VCAP_IS2_CNT,
-		.entry_width = VSC9953_VCAP_IS2_ENTRY_WIDTH,
-		.action_count = VSC9953_VCAP_IS2_CNT +
-				VSC9953_VCAP_PORT_CNT + 2,
-		.action_width = 101,
 		.action_type_width = 1,
 		.action_table = {
 			[IS2_ACTION_TYPE_NORMAL] = {
@@ -704,8 +848,9 @@ static const struct vcap_props vsc9953_vcap_props[] = {
 				.count = 4
 			},
 		},
-		.counter_words = 4,
-		.counter_width = 32,
+		.target = S2,
+		.keys = vsc9953_vcap_is2_keys,
+		.actions = vsc9953_vcap_is2_actions,
 	},
 };
 
@@ -913,6 +1058,8 @@ static u16 vsc9953_wm_enc(u16 value)
 static const struct ocelot_ops vsc9953_ops = {
 	.reset			= vsc9953_reset,
 	.wm_enc			= vsc9953_wm_enc,
+	.port_to_netdev		= felix_port_to_netdev,
+	.netdev_to_port		= felix_netdev_to_port,
 };
 
 static int vsc9953_mdio_bus_alloc(struct ocelot *ocelot)
@@ -1003,6 +1150,8 @@ static void vsc9953_xmit_template_populate(struct ocelot *ocelot, int port)
 	struct ocelot_port *ocelot_port = ocelot->ports[port];
 	u8 *template = ocelot_port->xmit_template;
 	u64 bypass, dest, src;
+	__be32 *prefix;
+	u8 *injection;
 
 	/* Set the source port as the CPU port module and not the
 	 * NPI port
@@ -1011,9 +1160,14 @@ static void vsc9953_xmit_template_populate(struct ocelot *ocelot, int port)
 	dest = BIT(port);
 	bypass = true;
 
-	packing(template, &bypass, 127, 127, OCELOT_TAG_LEN, PACK, 0);
-	packing(template, &dest,    67,  57, OCELOT_TAG_LEN, PACK, 0);
-	packing(template, &src,     46,  43, OCELOT_TAG_LEN, PACK, 0);
+	injection = template + OCELOT_SHORT_PREFIX_LEN;
+	prefix = (__be32 *)template;
+
+	packing(injection, &bypass, 127, 127, OCELOT_TAG_LEN, PACK, 0);
+	packing(injection, &dest,    67,  57, OCELOT_TAG_LEN, PACK, 0);
+	packing(injection, &src,     46,  43, OCELOT_TAG_LEN, PACK, 0);
+
+	*prefix = cpu_to_be32(0x88800005);
 }
 
 static const struct felix_info seville_info_vsc9953 = {
@@ -1024,10 +1178,8 @@ static const struct felix_info seville_info_vsc9953 = {
 	.ops			= &vsc9953_ops,
 	.stats_layout		= vsc9953_stats_layout,
 	.num_stats		= ARRAY_SIZE(vsc9953_stats_layout),
-	.vcap_is2_keys		= vsc9953_vcap_is2_keys,
-	.vcap_is2_actions	= vsc9953_vcap_is2_actions,
 	.vcap			= vsc9953_vcap_props,
-	.shared_queue_sz	= 128 * 1024,
+	.shared_queue_sz	= 2048 * 1024,
 	.num_mact_rows		= 2048,
 	.num_ports		= 10,
 	.mdio_bus_alloc		= vsc9953_mdio_bus_alloc,
diff --git a/drivers/net/dsa/rtl8366.c b/drivers/net/dsa/rtl8366.c
index 7c09ed747bc0..c58ca324a4b2 100644
--- a/drivers/net/dsa/rtl8366.c
+++ b/drivers/net/dsa/rtl8366.c
@@ -474,13 +474,19 @@ int rtl8366_vlan_del(struct dsa_switch *ds, int port,
 				return ret;
 
 			if (vid == vlanmc.vid) {
-				/* clear VLAN member configurations */
-				vlanmc.vid = 0;
-				vlanmc.priority = 0;
-				vlanmc.member = 0;
-				vlanmc.untag = 0;
-				vlanmc.fid = 0;
-
+				/* Remove this port from the VLAN */
+				vlanmc.member &= ~BIT(port);
+				vlanmc.untag &= ~BIT(port);
+				/*
+				 * If no ports are members of this VLAN
+				 * anymore then clear the whole member
+				 * config so it can be reused.
+				 */
+				if (!vlanmc.member && vlanmc.untag) {
+					vlanmc.vid = 0;
+					vlanmc.priority = 0;
+					vlanmc.fid = 0;
+				}
 				ret = smi->ops->set_vlan_mc(smi, i, &vlanmc);
 				if (ret) {
 					dev_err(smi->dev,
diff --git a/drivers/net/dsa/sja1105/Makefile b/drivers/net/dsa/sja1105/Makefile
index c88e56a29db8..a860e3a910be 100644
--- a/drivers/net/dsa/sja1105/Makefile
+++ b/drivers/net/dsa/sja1105/Makefile
@@ -6,6 +6,7 @@ sja1105-objs := \
     sja1105_main.o \
     sja1105_flower.o \
     sja1105_ethtool.o \
+    sja1105_devlink.o \
     sja1105_clocking.o \
     sja1105_static_config.o \
     sja1105_dynamic_config.o \
diff --git a/drivers/net/dsa/sja1105/sja1105.h b/drivers/net/dsa/sja1105/sja1105.h
index a93f580b558a..d582308c2401 100644
--- a/drivers/net/dsa/sja1105/sja1105.h
+++ b/drivers/net/dsa/sja1105/sja1105.h
@@ -218,6 +218,7 @@ struct sja1105_private {
 	struct mutex mgmt_lock;
 	struct dsa_8021q_context *dsa_8021q_ctx;
 	enum sja1105_vlan_state vlan_state;
+	struct devlink_region **regions;
 	struct sja1105_cbs_entry *cbs;
 	struct sja1105_tagger_data tagger_data;
 	struct sja1105_ptp_data ptp_data;
@@ -244,9 +245,20 @@ enum sja1105_reset_reason {
 
 int sja1105_static_config_reload(struct sja1105_private *priv,
 				 enum sja1105_reset_reason reason);
-
+int sja1105_vlan_filtering(struct dsa_switch *ds, int port, bool enabled);
 void sja1105_frame_memory_partitioning(struct sja1105_private *priv);
 
+/* From sja1105_devlink.c */
+int sja1105_devlink_setup(struct dsa_switch *ds);
+void sja1105_devlink_teardown(struct dsa_switch *ds);
+int sja1105_devlink_param_get(struct dsa_switch *ds, u32 id,
+			      struct devlink_param_gset_ctx *ctx);
+int sja1105_devlink_param_set(struct dsa_switch *ds, u32 id,
+			      struct devlink_param_gset_ctx *ctx);
+int sja1105_devlink_info_get(struct dsa_switch *ds,
+			     struct devlink_info_req *req,
+			     struct netlink_ext_ack *extack);
+
 /* From sja1105_spi.c */
 int sja1105_xfer_buf(const struct sja1105_private *priv,
 		     sja1105_spi_rw_mode_t rw, u64 reg_addr,
@@ -257,6 +269,8 @@ int sja1105_xfer_u32(const struct sja1105_private *priv,
 int sja1105_xfer_u64(const struct sja1105_private *priv,
 		     sja1105_spi_rw_mode_t rw, u64 reg_addr, u64 *value,
 		     struct ptp_system_timestamp *ptp_sts);
+int static_config_buf_prepare_for_upload(struct sja1105_private *priv,
+					 void *config_buf, int buf_len);
 int sja1105_static_config_upload(struct sja1105_private *priv);
 int sja1105_inhibit_tx(const struct sja1105_private *priv,
 		       unsigned long port_bitmap, bool tx_inhibited);
diff --git a/drivers/net/dsa/sja1105/sja1105_devlink.c b/drivers/net/dsa/sja1105/sja1105_devlink.c
new file mode 100644
index 000000000000..b4bf1b10e66c
--- /dev/null
+++ b/drivers/net/dsa/sja1105/sja1105_devlink.c
@@ -0,0 +1,255 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2018-2019, Vladimir Oltean <olteanv@gmail.com>
+ * Copyright 2020 NXP Semiconductors
+ */
+#include "sja1105.h"
+
+/* Since devlink regions have a fixed size and the static config has a variable
+ * size, we need to calculate the maximum possible static config size by
+ * creating a dummy config with all table entries populated to the max, and get
+ * its packed length. This is done dynamically as opposed to simply hardcoding
+ * a number, since currently not all static config tables are implemented, so
+ * we are avoiding a possible code desynchronization.
+ */
+static size_t sja1105_static_config_get_max_size(struct sja1105_private *priv)
+{
+	struct sja1105_static_config config;
+	enum sja1105_blk_idx blk_idx;
+	int rc;
+
+	rc = sja1105_static_config_init(&config,
+					priv->info->static_ops,
+					priv->info->device_id);
+	if (rc)
+		return 0;
+
+	for (blk_idx = 0; blk_idx < BLK_IDX_MAX; blk_idx++) {
+		struct sja1105_table *table = &config.tables[blk_idx];
+
+		table->entry_count = table->ops->max_entry_count;
+	}
+
+	return sja1105_static_config_get_length(&config);
+}
+
+static int
+sja1105_region_static_config_snapshot(struct devlink *dl,
+				      const struct devlink_region_ops *ops,
+				      struct netlink_ext_ack *extack,
+				      u8 **data)
+{
+	struct dsa_switch *ds = dsa_devlink_to_ds(dl);
+	struct sja1105_private *priv = ds->priv;
+	size_t max_len, len;
+
+	len = sja1105_static_config_get_length(&priv->static_config);
+	max_len = sja1105_static_config_get_max_size(priv);
+
+	*data = kcalloc(max_len, sizeof(u8), GFP_KERNEL);
+	if (!*data)
+		return -ENOMEM;
+
+	return static_config_buf_prepare_for_upload(priv, *data, len);
+}
+
+static struct devlink_region_ops sja1105_region_static_config_ops = {
+	.name = "static-config",
+	.snapshot = sja1105_region_static_config_snapshot,
+	.destructor = kfree,
+};
+
+enum sja1105_region_id {
+	SJA1105_REGION_STATIC_CONFIG = 0,
+};
+
+struct sja1105_region {
+	const struct devlink_region_ops *ops;
+	size_t (*get_size)(struct sja1105_private *priv);
+};
+
+static struct sja1105_region sja1105_regions[] = {
+	[SJA1105_REGION_STATIC_CONFIG] = {
+		.ops = &sja1105_region_static_config_ops,
+		.get_size = sja1105_static_config_get_max_size,
+	},
+};
+
+static int sja1105_setup_devlink_regions(struct dsa_switch *ds)
+{
+	int i, num_regions = ARRAY_SIZE(sja1105_regions);
+	struct sja1105_private *priv = ds->priv;
+	const struct devlink_region_ops *ops;
+	struct devlink_region *region;
+	u64 size;
+
+	priv->regions = kcalloc(num_regions, sizeof(struct devlink_region *),
+				GFP_KERNEL);
+	if (!priv->regions)
+		return -ENOMEM;
+
+	for (i = 0; i < num_regions; i++) {
+		size = sja1105_regions[i].get_size(priv);
+		ops = sja1105_regions[i].ops;
+
+		region = dsa_devlink_region_create(ds, ops, 1, size);
+		if (IS_ERR(region)) {
+			while (i-- >= 0)
+				dsa_devlink_region_destroy(priv->regions[i]);
+			return PTR_ERR(region);
+		}
+
+		priv->regions[i] = region;
+	}
+
+	return 0;
+}
+
+static void sja1105_teardown_devlink_regions(struct dsa_switch *ds)
+{
+	int i, num_regions = ARRAY_SIZE(sja1105_regions);
+	struct sja1105_private *priv = ds->priv;
+
+	for (i = 0; i < num_regions; i++)
+		dsa_devlink_region_destroy(priv->regions[i]);
+
+	kfree(priv->regions);
+}
+
+static int sja1105_best_effort_vlan_filtering_get(struct sja1105_private *priv,
+						  bool *be_vlan)
+{
+	*be_vlan = priv->best_effort_vlan_filtering;
+
+	return 0;
+}
+
+static int sja1105_best_effort_vlan_filtering_set(struct sja1105_private *priv,
+						  bool be_vlan)
+{
+	struct dsa_switch *ds = priv->ds;
+	bool vlan_filtering;
+	int port;
+	int rc;
+
+	priv->best_effort_vlan_filtering = be_vlan;
+
+	rtnl_lock();
+	for (port = 0; port < ds->num_ports; port++) {
+		struct dsa_port *dp;
+
+		if (!dsa_is_user_port(ds, port))
+			continue;
+
+		dp = dsa_to_port(ds, port);
+		vlan_filtering = dsa_port_is_vlan_filtering(dp);
+
+		rc = sja1105_vlan_filtering(ds, port, vlan_filtering);
+		if (rc)
+			break;
+	}
+	rtnl_unlock();
+
+	return rc;
+}
+
+enum sja1105_devlink_param_id {
+	SJA1105_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX,
+	SJA1105_DEVLINK_PARAM_ID_BEST_EFFORT_VLAN_FILTERING,
+};
+
+int sja1105_devlink_param_get(struct dsa_switch *ds, u32 id,
+			      struct devlink_param_gset_ctx *ctx)
+{
+	struct sja1105_private *priv = ds->priv;
+	int err;
+
+	switch (id) {
+	case SJA1105_DEVLINK_PARAM_ID_BEST_EFFORT_VLAN_FILTERING:
+		err = sja1105_best_effort_vlan_filtering_get(priv,
+							     &ctx->val.vbool);
+		break;
+	default:
+		err = -EOPNOTSUPP;
+		break;
+	}
+
+	return err;
+}
+
+int sja1105_devlink_param_set(struct dsa_switch *ds, u32 id,
+			      struct devlink_param_gset_ctx *ctx)
+{
+	struct sja1105_private *priv = ds->priv;
+	int err;
+
+	switch (id) {
+	case SJA1105_DEVLINK_PARAM_ID_BEST_EFFORT_VLAN_FILTERING:
+		err = sja1105_best_effort_vlan_filtering_set(priv,
+							     ctx->val.vbool);
+		break;
+	default:
+		err = -EOPNOTSUPP;
+		break;
+	}
+
+	return err;
+}
+
+static const struct devlink_param sja1105_devlink_params[] = {
+	DSA_DEVLINK_PARAM_DRIVER(SJA1105_DEVLINK_PARAM_ID_BEST_EFFORT_VLAN_FILTERING,
+				 "best_effort_vlan_filtering",
+				 DEVLINK_PARAM_TYPE_BOOL,
+				 BIT(DEVLINK_PARAM_CMODE_RUNTIME)),
+};
+
+static int sja1105_setup_devlink_params(struct dsa_switch *ds)
+{
+	return dsa_devlink_params_register(ds, sja1105_devlink_params,
+					   ARRAY_SIZE(sja1105_devlink_params));
+}
+
+static void sja1105_teardown_devlink_params(struct dsa_switch *ds)
+{
+	dsa_devlink_params_unregister(ds, sja1105_devlink_params,
+				      ARRAY_SIZE(sja1105_devlink_params));
+}
+
+int sja1105_devlink_info_get(struct dsa_switch *ds,
+			     struct devlink_info_req *req,
+			     struct netlink_ext_ack *extack)
+{
+	struct sja1105_private *priv = ds->priv;
+	int rc;
+
+	rc = devlink_info_driver_name_put(req, "sja1105");
+	if (rc)
+		return rc;
+
+	rc = devlink_info_version_fixed_put(req,
+					    DEVLINK_INFO_VERSION_GENERIC_ASIC_ID,
+					    priv->info->name);
+	return rc;
+}
+
+int sja1105_devlink_setup(struct dsa_switch *ds)
+{
+	int rc;
+
+	rc = sja1105_setup_devlink_params(ds);
+	if (rc)
+		return rc;
+
+	rc = sja1105_setup_devlink_regions(ds);
+	if (rc < 0) {
+		sja1105_teardown_devlink_params(ds);
+		return rc;
+	}
+
+	return 0;
+}
+
+void sja1105_devlink_teardown(struct dsa_switch *ds)
+{
+	sja1105_teardown_devlink_params(ds);
+	sja1105_teardown_devlink_regions(ds);
+}
diff --git a/drivers/net/dsa/sja1105/sja1105_dynamic_config.c b/drivers/net/dsa/sja1105/sja1105_dynamic_config.c
index 75247f342124..b777d3f37573 100644
--- a/drivers/net/dsa/sja1105/sja1105_dynamic_config.c
+++ b/drivers/net/dsa/sja1105/sja1105_dynamic_config.c
@@ -97,10 +97,10 @@
 
 #define SJA1105_SIZE_DYN_CMD					4
 
-#define SJA1105ET_SJA1105_SIZE_VL_LOOKUP_DYN_CMD		\
+#define SJA1105ET_SIZE_VL_LOOKUP_DYN_CMD			\
 	SJA1105_SIZE_DYN_CMD
 
-#define SJA1105PQRS_SJA1105_SIZE_VL_LOOKUP_DYN_CMD		\
+#define SJA1105PQRS_SIZE_VL_LOOKUP_DYN_CMD			\
 	(SJA1105_SIZE_DYN_CMD + SJA1105_SIZE_VL_LOOKUP_ENTRY)
 
 #define SJA1105ET_SIZE_MAC_CONFIG_DYN_ENTRY			\
@@ -183,7 +183,7 @@ static size_t sja1105et_vl_lookup_entry_packing(void *buf, void *entry_ptr,
 						enum packing_op op)
 {
 	struct sja1105_vl_lookup_entry *entry = entry_ptr;
-	const int size = SJA1105ET_SJA1105_SIZE_VL_LOOKUP_DYN_CMD;
+	const int size = SJA1105ET_SIZE_VL_LOOKUP_DYN_CMD;
 
 	sja1105_packing(buf, &entry->egrmirr,  21, 17, size, op);
 	sja1105_packing(buf, &entry->ingrmirr, 16, 16, size, op);
@@ -644,7 +644,7 @@ const struct sja1105_dynamic_table_ops sja1105et_dyn_ops[BLK_IDX_MAX_DYN] = {
 		.cmd_packing = sja1105_vl_lookup_cmd_packing,
 		.access = OP_WRITE,
 		.max_entry_count = SJA1105_MAX_VL_LOOKUP_COUNT,
-		.packed_size = SJA1105ET_SJA1105_SIZE_VL_LOOKUP_DYN_CMD,
+		.packed_size = SJA1105ET_SIZE_VL_LOOKUP_DYN_CMD,
 		.addr = 0x35,
 	},
 	[BLK_IDX_L2_LOOKUP] = {
@@ -728,7 +728,7 @@ const struct sja1105_dynamic_table_ops sja1105pqrs_dyn_ops[BLK_IDX_MAX_DYN] = {
 		.cmd_packing = sja1105_vl_lookup_cmd_packing,
 		.access = (OP_READ | OP_WRITE),
 		.max_entry_count = SJA1105_MAX_VL_LOOKUP_COUNT,
-		.packed_size = SJA1105PQRS_SJA1105_SIZE_VL_LOOKUP_DYN_CMD,
+		.packed_size = SJA1105PQRS_SIZE_VL_LOOKUP_DYN_CMD,
 		.addr = 0x47,
 	},
 	[BLK_IDX_L2_LOOKUP] = {
diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c
index 4a298729937b..547487c535df 100644
--- a/drivers/net/dsa/sja1105/sja1105_main.c
+++ b/drivers/net/dsa/sja1105/sja1105_main.c
@@ -2634,7 +2634,7 @@ static int sja1105_vlan_prepare(struct dsa_switch *ds, int port,
  * which can only be partially reconfigured at runtime (and not the TPID).
  * So a switch reset is required.
  */
-static int sja1105_vlan_filtering(struct dsa_switch *ds, int port, bool enabled)
+int sja1105_vlan_filtering(struct dsa_switch *ds, int port, bool enabled)
 {
 	struct sja1105_l2_lookup_params_entry *l2_lookup_params;
 	struct sja1105_general_params_entry *general_params;
@@ -2864,105 +2864,6 @@ static const struct dsa_8021q_ops sja1105_dsa_8021q_ops = {
 	.vlan_del	= sja1105_dsa_8021q_vlan_del,
 };
 
-static int sja1105_best_effort_vlan_filtering_get(struct sja1105_private *priv,
-						  bool *be_vlan)
-{
-	*be_vlan = priv->best_effort_vlan_filtering;
-
-	return 0;
-}
-
-static int sja1105_best_effort_vlan_filtering_set(struct sja1105_private *priv,
-						  bool be_vlan)
-{
-	struct dsa_switch *ds = priv->ds;
-	bool vlan_filtering;
-	int port;
-	int rc;
-
-	priv->best_effort_vlan_filtering = be_vlan;
-
-	rtnl_lock();
-	for (port = 0; port < ds->num_ports; port++) {
-		struct dsa_port *dp;
-
-		if (!dsa_is_user_port(ds, port))
-			continue;
-
-		dp = dsa_to_port(ds, port);
-		vlan_filtering = dsa_port_is_vlan_filtering(dp);
-
-		rc = sja1105_vlan_filtering(ds, port, vlan_filtering);
-		if (rc)
-			break;
-	}
-	rtnl_unlock();
-
-	return rc;
-}
-
-enum sja1105_devlink_param_id {
-	SJA1105_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX,
-	SJA1105_DEVLINK_PARAM_ID_BEST_EFFORT_VLAN_FILTERING,
-};
-
-static int sja1105_devlink_param_get(struct dsa_switch *ds, u32 id,
-				     struct devlink_param_gset_ctx *ctx)
-{
-	struct sja1105_private *priv = ds->priv;
-	int err;
-
-	switch (id) {
-	case SJA1105_DEVLINK_PARAM_ID_BEST_EFFORT_VLAN_FILTERING:
-		err = sja1105_best_effort_vlan_filtering_get(priv,
-							     &ctx->val.vbool);
-		break;
-	default:
-		err = -EOPNOTSUPP;
-		break;
-	}
-
-	return err;
-}
-
-static int sja1105_devlink_param_set(struct dsa_switch *ds, u32 id,
-				     struct devlink_param_gset_ctx *ctx)
-{
-	struct sja1105_private *priv = ds->priv;
-	int err;
-
-	switch (id) {
-	case SJA1105_DEVLINK_PARAM_ID_BEST_EFFORT_VLAN_FILTERING:
-		err = sja1105_best_effort_vlan_filtering_set(priv,
-							     ctx->val.vbool);
-		break;
-	default:
-		err = -EOPNOTSUPP;
-		break;
-	}
-
-	return err;
-}
-
-static const struct devlink_param sja1105_devlink_params[] = {
-	DSA_DEVLINK_PARAM_DRIVER(SJA1105_DEVLINK_PARAM_ID_BEST_EFFORT_VLAN_FILTERING,
-				 "best_effort_vlan_filtering",
-				 DEVLINK_PARAM_TYPE_BOOL,
-				 BIT(DEVLINK_PARAM_CMODE_RUNTIME)),
-};
-
-static int sja1105_setup_devlink_params(struct dsa_switch *ds)
-{
-	return dsa_devlink_params_register(ds, sja1105_devlink_params,
-					   ARRAY_SIZE(sja1105_devlink_params));
-}
-
-static void sja1105_teardown_devlink_params(struct dsa_switch *ds)
-{
-	dsa_devlink_params_unregister(ds, sja1105_devlink_params,
-				      ARRAY_SIZE(sja1105_devlink_params));
-}
-
 /* The programming model for the SJA1105 switch is "all-at-once" via static
  * configuration tables. Some of these can be dynamically modified at runtime,
  * but not the xMII mode parameters table.
@@ -3030,7 +2931,7 @@ static int sja1105_setup(struct dsa_switch *ds)
 
 	ds->configure_vlan_while_not_filtering = true;
 
-	rc = sja1105_setup_devlink_params(ds);
+	rc = sja1105_devlink_setup(ds);
 	if (rc < 0)
 		return rc;
 
@@ -3061,7 +2962,7 @@ static void sja1105_teardown(struct dsa_switch *ds)
 			kthread_destroy_worker(sp->xmit_worker);
 	}
 
-	sja1105_teardown_devlink_params(ds);
+	sja1105_devlink_teardown(ds);
 	sja1105_flower_teardown(ds);
 	sja1105_tas_teardown(ds);
 	sja1105_ptp_clock_unregister(ds);
@@ -3415,6 +3316,7 @@ static const struct dsa_switch_ops sja1105_switch_ops = {
 	.crosschip_bridge_leave	= sja1105_crosschip_bridge_leave,
 	.devlink_param_get	= sja1105_devlink_param_get,
 	.devlink_param_set	= sja1105_devlink_param_set,
+	.devlink_info_get	= sja1105_devlink_info_get,
 };
 
 static const struct of_device_id sja1105_dt_ids[];
diff --git a/drivers/net/dsa/sja1105/sja1105_spi.c b/drivers/net/dsa/sja1105/sja1105_spi.c
index 704dcf1d1c01..591c5734747d 100644
--- a/drivers/net/dsa/sja1105/sja1105_spi.c
+++ b/drivers/net/dsa/sja1105/sja1105_spi.c
@@ -302,9 +302,8 @@ static int sja1105_status_get(struct sja1105_private *priv,
  * for upload requires the recalculation of table CRCs and updating the
  * structures with these.
  */
-static int
-static_config_buf_prepare_for_upload(struct sja1105_private *priv,
-				     void *config_buf, int buf_len)
+int static_config_buf_prepare_for_upload(struct sja1105_private *priv,
+					 void *config_buf, int buf_len)
 {
 	struct sja1105_static_config *config = &priv->static_config;
 	struct sja1105_table_header final_header;
diff --git a/drivers/net/ethernet/8390/lib8390.c b/drivers/net/ethernet/8390/lib8390.c
index 1f48d7f6365c..e84021282edf 100644
--- a/drivers/net/ethernet/8390/lib8390.c
+++ b/drivers/net/ethernet/8390/lib8390.c
@@ -50,6 +50,7 @@
 
   */
 
+#include <linux/build_bug.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/jiffies.h>
@@ -112,8 +113,10 @@ static void do_set_multicast_list(struct net_device *dev);
 static void __NS8390_init(struct net_device *dev, int startp);
 
 static unsigned version_printed;
-static u32 msg_enable;
-module_param(msg_enable, uint, 0444);
+static int msg_enable;
+static const int default_msg_level = (NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_RX_ERR |
+				     NETIF_MSG_TX_ERR);
+module_param(msg_enable, int, 0444);
 MODULE_PARM_DESC(msg_enable, "Debug message level (see linux/netdevice.h for bitmap)");
 
 /*
@@ -973,14 +976,14 @@ static void ethdev_setup(struct net_device *dev)
 {
 	struct ei_device *ei_local = netdev_priv(dev);
 
-	if ((msg_enable & NETIF_MSG_DRV) && (version_printed++ == 0))
-		pr_info("%s", version);
-
 	ether_setup(dev);
 
 	spin_lock_init(&ei_local->page_lock);
 
-	ei_local->msg_enable = msg_enable;
+	ei_local->msg_enable = netif_msg_init(msg_enable, default_msg_level);
+
+	if (netif_msg_drv(ei_local) && (version_printed++ == 0))
+		pr_info("%s", version);
 }
 
 /**
@@ -1018,8 +1021,7 @@ static void __NS8390_init(struct net_device *dev, int startp)
 	    ? (0x48 | ENDCFG_WTS | (ei_local->bigendian ? ENDCFG_BOS : 0))
 	    : 0x48;
 
-	if (sizeof(struct e8390_pkt_hdr) != 4)
-		panic("8390.c: header struct mispacked\n");
+	BUILD_BUG_ON(sizeof(struct e8390_pkt_hdr) != 4);
 	/* Follow National Semi's recommendations for initing the DP83902. */
 	ei_outb_p(E8390_NODMA+E8390_PAGE0+E8390_STOP, e8390_base+E8390_CMD); /* 0x21 */
 	ei_outb_p(endcfg, e8390_base + EN0_DCFG);	/* 0x48 or 0x49 */
diff --git a/drivers/net/ethernet/allwinner/sun4i-emac.c b/drivers/net/ethernet/allwinner/sun4i-emac.c
index b3b8a8010142..862ea44beea7 100644
--- a/drivers/net/ethernet/allwinner/sun4i-emac.c
+++ b/drivers/net/ethernet/allwinner/sun4i-emac.c
@@ -640,13 +640,11 @@ static irqreturn_t emac_interrupt(int irq, void *dev_id)
 	struct net_device *dev = dev_id;
 	struct emac_board_info *db = netdev_priv(dev);
 	int int_status;
-	unsigned long flags;
 	unsigned int reg_val;
 
 	/* A real interrupt coming */
 
-	/* holders of db->lock must always block IRQs */
-	spin_lock_irqsave(&db->lock, flags);
+	spin_lock(&db->lock);
 
 	/* Disable all interrupts */
 	writel(0, db->membase + EMAC_INT_CTL_REG);
@@ -680,7 +678,7 @@ static irqreturn_t emac_interrupt(int irq, void *dev_id)
 		reg_val |= (0xf << 0) | (0x01 << 8);
 		writel(reg_val, db->membase + EMAC_INT_CTL_REG);
 	}
-	spin_unlock_irqrestore(&db->lock, flags);
+	spin_unlock(&db->lock);
 
 	return IRQ_HANDLED;
 }
diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c
index 34434c6b6000..5f8769aa469d 100644
--- a/drivers/net/ethernet/amazon/ena/ena_com.c
+++ b/drivers/net/ethernet/amazon/ena/ena_com.c
@@ -579,7 +579,7 @@ err:
 	return ret;
 }
 
-/**
+/*
  * Set the LLQ configurations of the firmware
  *
  * The driver provides only the enabled feature values to the device,
diff --git a/drivers/net/ethernet/amd/sun3lance.c b/drivers/net/ethernet/amd/sun3lance.c
index e1fde585fd0d..00ae1081254d 100644
--- a/drivers/net/ethernet/amd/sun3lance.c
+++ b/drivers/net/ethernet/amd/sun3lance.c
@@ -657,16 +657,6 @@ static irqreturn_t lance_interrupt( int irq, void *dev_id)
 	struct net_device *dev = dev_id;
 	struct lance_private *lp = netdev_priv(dev);
 	int csr0;
-	static int in_interrupt;
-
-	if (dev == NULL) {
-		DPRINTK( 1, ( "lance_interrupt(): invalid dev_id\n" ));
-		return IRQ_NONE;
-	}
-
-	if (in_interrupt)
-		DPRINTK( 2, ( "%s: Re-entering the interrupt handler.\n", dev->name ));
-	in_interrupt = 1;
 
  still_more:
 	flush_cache_all();
@@ -774,7 +764,6 @@ static irqreturn_t lance_interrupt( int irq, void *dev_id)
 
 	DPRINTK( 2, ( "%s: exiting interrupt, csr0=%#04x.\n",
 				  dev->name, DREG ));
-	in_interrupt = 0;
 	return IRQ_HANDLED;
 }
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
index 8941ac4df9e3..9f1b15077e7d 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
@@ -1536,7 +1536,7 @@ static int hw_atl_b0_hw_fl2_clear(struct aq_hw_s *self,
 	return aq_hw_err_from_flags(self);
 }
 
-/**
+/*
  * @brief Set VLAN filter table
  * @details Configure VLAN filter table to accept (and assign the queue) traffic
  *  for the particular vlan ids.
diff --git a/drivers/net/ethernet/arc/emac_arc.c b/drivers/net/ethernet/arc/emac_arc.c
index 1c7736b7eaf7..800620b8f10d 100644
--- a/drivers/net/ethernet/arc/emac_arc.c
+++ b/drivers/net/ethernet/arc/emac_arc.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /**
- * emac_arc.c - ARC EMAC specific glue layer
+ * DOC: emac_arc.c - ARC EMAC specific glue layer
  *
  * Copyright (C) 2014 Romain Perier
  *
diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
index c7288e1fa3a2..0c12cf7bda50 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
@@ -204,7 +204,7 @@ static u32 atl1c_wait_until_idle(struct atl1c_hw *hw, u32 modu_ctrl)
 
 /**
  * atl1c_phy_config - Timer Call-back
- * @data: pointer to netdev cast into an unsigned long
+ * @t: timer list containing pointer to netdev cast into an unsigned long
  */
 static void atl1c_phy_config(struct timer_list *t)
 {
@@ -220,7 +220,6 @@ static void atl1c_phy_config(struct timer_list *t)
 
 void atl1c_reinit_locked(struct atl1c_adapter *adapter)
 {
-	WARN_ON(in_interrupt());
 	atl1c_down(adapter);
 	atl1c_up(adapter);
 	clear_bit(__AT_RESETTING, &adapter->flags);
@@ -346,6 +345,7 @@ static void atl1c_del_timer(struct atl1c_adapter *adapter)
 /**
  * atl1c_tx_timeout - Respond to a Tx Hang
  * @netdev: network interface device structure
+ * @txqueue: index of hanging tx queue
  */
 static void atl1c_tx_timeout(struct net_device *netdev, unsigned int txqueue)
 {
@@ -846,6 +846,7 @@ static inline void atl1c_clean_buffer(struct pci_dev *pdev,
 /**
  * atl1c_clean_tx_ring - Free Tx-skb
  * @adapter: board private structure
+ * @type: type of transmit queue
  */
 static void atl1c_clean_tx_ring(struct atl1c_adapter *adapter,
 				enum atl1c_trans_queue type)
@@ -1861,6 +1862,8 @@ rrs_checked:
 
 /**
  * atl1c_clean - NAPI Rx polling callback
+ * @napi: napi info
+ * @budget: limit of packets to clean
  */
 static int atl1c_clean(struct napi_struct *napi, int budget)
 {
diff --git a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
index fb78f6c31708..098b0328e3cb 100644
--- a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
+++ b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
@@ -111,7 +111,7 @@ static inline void atl1e_irq_reset(struct atl1e_adapter *adapter)
 
 /**
  * atl1e_phy_config - Timer Call-back
- * @data: pointer to netdev cast into an unsigned long
+ * @t: timer list containing pointer to netdev cast into an unsigned long
  */
 static void atl1e_phy_config(struct timer_list *t)
 {
@@ -127,8 +127,6 @@ static void atl1e_phy_config(struct timer_list *t)
 
 void atl1e_reinit_locked(struct atl1e_adapter *adapter)
 {
-
-	WARN_ON(in_interrupt());
 	while (test_and_set_bit(__AT_RESETTING, &adapter->flags))
 		msleep(1);
 	atl1e_down(adapter);
@@ -196,7 +194,7 @@ static int atl1e_check_link(struct atl1e_adapter *adapter)
 
 /**
  * atl1e_link_chg_task - deal with link change event Out of interrupt context
- * @netdev: network interface device structure
+ * @work: work struct with driver info
  */
 static void atl1e_link_chg_task(struct work_struct *work)
 {
@@ -246,6 +244,7 @@ static void atl1e_cancel_work(struct atl1e_adapter *adapter)
 /**
  * atl1e_tx_timeout - Respond to a Tx Hang
  * @netdev: network interface device structure
+ * @txqueue: the index of the hanging queue
  */
 static void atl1e_tx_timeout(struct net_device *netdev, unsigned int txqueue)
 {
@@ -1502,6 +1501,8 @@ fatal_err:
 
 /**
  * atl1e_clean - NAPI Rx polling callback
+ * @napi: napi info
+ * @budget: number of packets to clean
  */
 static int atl1e_clean(struct napi_struct *napi, int budget)
 {
diff --git a/drivers/net/ethernet/atheros/atlx/atl1.c b/drivers/net/ethernet/atheros/atlx/atl1.c
index 60f8aa79deb2..eaf96d002fa5 100644
--- a/drivers/net/ethernet/atheros/atlx/atl1.c
+++ b/drivers/net/ethernet/atheros/atlx/atl1.c
@@ -2552,7 +2552,7 @@ static irqreturn_t atl1_intr(int irq, void *data)
 
 /**
  * atl1_phy_config - Timer Call-back
- * @data: pointer to netdev cast into an unsigned long
+ * @t: timer_list containing pointer to netdev cast into an unsigned long
  */
 static void atl1_phy_config(struct timer_list *t)
 {
diff --git a/drivers/net/ethernet/atheros/atlx/atl2.c b/drivers/net/ethernet/atheros/atlx/atl2.c
index e2526c0fb7cf..7b80d924632a 100644
--- a/drivers/net/ethernet/atheros/atlx/atl2.c
+++ b/drivers/net/ethernet/atheros/atlx/atl2.c
@@ -994,6 +994,7 @@ static int atl2_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
 /**
  * atl2_tx_timeout - Respond to a Tx Hang
  * @netdev: network interface device structure
+ * @txqueue: index of the hanging transmit queue
  */
 static void atl2_tx_timeout(struct net_device *netdev, unsigned int txqueue)
 {
@@ -1005,7 +1006,7 @@ static void atl2_tx_timeout(struct net_device *netdev, unsigned int txqueue)
 
 /**
  * atl2_watchdog - Timer Call-back
- * @data: pointer to netdev cast into an unsigned long
+ * @t: timer list containing a pointer to netdev cast into an unsigned long
  */
 static void atl2_watchdog(struct timer_list *t)
 {
@@ -1030,7 +1031,7 @@ static void atl2_watchdog(struct timer_list *t)
 
 /**
  * atl2_phy_config - Timer Call-back
- * @data: pointer to netdev cast into an unsigned long
+ * @t: timer list containing a pointer to netdev cast into an unsigned long
  */
 static void atl2_phy_config(struct timer_list *t)
 {
@@ -1085,7 +1086,6 @@ err_up:
 
 static void atl2_reinit_locked(struct atl2_adapter *adapter)
 {
-	WARN_ON(in_interrupt());
 	while (test_and_set_bit(__ATL2_RESETTING, &adapter->flags))
 		msleep(1);
 	atl2_down(adapter);
@@ -1235,6 +1235,7 @@ static int atl2_check_link(struct atl2_adapter *adapter)
 
 /**
  * atl2_link_chg_task - deal with link change event Out of interrupt context
+ * @work: pointer to work struct with private info
  */
 static void atl2_link_chg_task(struct work_struct *work)
 {
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index 2c0ccd4fba9b..1a6ec1a12d53 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -504,6 +504,7 @@ static void bnx2x_tpa_start(struct bnx2x_fastpath *fp, u16 queue,
  * @len_on_bd:		total length of the first packet for the
  *			aggregation.
  * @pkt_len:		length of all segments
+ * @num_of_coalesced_segs: count of segments
  *
  * Approximate value of the MSS for this aggregation calculated using
  * the first packet of it.
@@ -1958,6 +1959,7 @@ void bnx2x_set_num_queues(struct bnx2x *bp)
  * bnx2x_set_real_num_queues - configure netdev->real_num_[tx,rx]_queues
  *
  * @bp:		Driver handle
+ * @include_cnic: handle cnic case
  *
  * We currently support for at most 16 Tx queues for each CoS thus we will
  * allocate a multiple of 16 for ETH L2 rings according to the value of the
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
index 7cea33803f7f..32245bbe88a8 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
@@ -839,8 +839,9 @@ static bool bnx2x_is_wreg_in_chip(struct bnx2x *bp,
 /**
  * bnx2x_read_pages_regs - read "paged" registers
  *
- * @bp		device handle
- * @p		output buffer
+ * @bp:		device handle
+ * @p:		output buffer
+ * @preset:	the preset value
  *
  * Reads "paged" memories: memories that may only be read by first writing to a
  * specific address ("write address") and then reading from a specific address
@@ -3561,6 +3562,7 @@ static void bnx2x_get_channels(struct net_device *dev,
  * bnx2x_change_num_queues - change the number of RSS queues.
  *
  * @bp:			bnx2x private structure
+ * @num_rss:		rss count
  *
  * Re-configure interrupt mode to get the new number of MSI-X
  * vectors and re-add NAPI objects.
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index 35f659310084..28069b290862 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -3086,9 +3086,9 @@ void bnx2x_func_init(struct bnx2x *bp, struct bnx2x_func_init_params *p)
 /**
  * bnx2x_get_common_flags - Return common flags
  *
- * @bp		device handle
- * @fp		queue handle
- * @zero_stats	TRUE if statistics zeroing is needed
+ * @bp:		device handle
+ * @fp:		queue handle
+ * @zero_stats:	TRUE if statistics zeroing is needed
  *
  * Return the flags that are common for the Tx-only and not normal connections.
  */
@@ -6313,11 +6313,11 @@ static void bnx2x_init_internal(struct bnx2x *bp, u32 load_code)
 	case FW_MSG_CODE_DRV_LOAD_COMMON:
 	case FW_MSG_CODE_DRV_LOAD_COMMON_CHIP:
 		bnx2x_init_internal_common(bp);
-		/* no break */
+		fallthrough;
 
 	case FW_MSG_CODE_DRV_LOAD_PORT:
 		/* nothing to do */
-		/* no break */
+		fallthrough;
 
 	case FW_MSG_CODE_DRV_LOAD_FUNCTION:
 		/* internal memory per function is
@@ -13591,8 +13591,8 @@ static int bnx2x_set_qm_cid_count(struct bnx2x *bp)
 
 /**
  * bnx2x_get_num_none_def_sbs - return the number of none default SBs
- *
- * @dev:	pci device
+ * @pdev: pci device
+ * @cnic_cnt: count
  *
  */
 static int bnx2x_get_num_non_def_sbs(struct pci_dev *pdev, int cnic_cnt)
@@ -14451,9 +14451,7 @@ module_exit(bnx2x_cleanup);
 
 /**
  * bnx2x_set_iscsi_eth_mac_addr - set iSCSI MAC(s).
- *
  * @bp:		driver handle
- * @set:	set or clear the CAM entry
  *
  * This function will wait until the ramrod completion returns.
  * Return 0 if success, -ENODEV if ramrod doesn't return.
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
index e26f4da5a6d7..6cd1523ad9e5 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
@@ -37,10 +37,12 @@
 /**
  * bnx2x_exe_queue_init - init the Exe Queue object
  *
+ * @bp:		driver handle
  * @o:		pointer to the object
  * @exe_len:	length
  * @owner:	pointer to the owner
  * @validate:	validate function pointer
+ * @remove:	remove function pointer
  * @optimize:	optimize function pointer
  * @exec:	execute function pointer
  * @get:	get function pointer
@@ -103,7 +105,7 @@ static inline int bnx2x_exe_queue_length(struct bnx2x_exe_queue_obj *o)
  *
  * @bp:		driver handle
  * @o:		queue
- * @cmd:	new command to add
+ * @elem:	new command to add
  * @restore:	true - do not optimize the command
  *
  * If the element is optimized or is illegal, frees it.
@@ -277,7 +279,7 @@ static void bnx2x_raw_set_pending(struct bnx2x_raw_obj *o)
  *
  * @bp:		device handle
  * @state:	state which is to be cleared
- * @state_p:	state buffer
+ * @pstate:	state buffer
  *
  */
 static inline int bnx2x_state_wait(struct bnx2x *bp, int state,
@@ -424,8 +426,8 @@ static bool bnx2x_put_credit_vlan_mac(struct bnx2x_vlan_mac_obj *o)
  * @bp:		device handle
  * @o:		vlan_mac object
  *
- * @details: Non-blocking implementation; should be called under execution
- *           queue lock.
+ * Context: Non-blocking implementation; should be called under execution
+ *          queue lock.
  */
 static int __bnx2x_vlan_mac_h_write_trylock(struct bnx2x *bp,
 					    struct bnx2x_vlan_mac_obj *o)
@@ -445,7 +447,7 @@ static int __bnx2x_vlan_mac_h_write_trylock(struct bnx2x *bp,
  * @bp:		device handle
  * @o:		vlan_mac object
  *
- * @details Should be called under execution queue lock; notice it might release
+ * details Should be called under execution queue lock; notice it might release
  *          and reclaim it during its run.
  */
 static void __bnx2x_vlan_mac_h_exec_pending(struct bnx2x *bp,
@@ -475,7 +477,7 @@ static void __bnx2x_vlan_mac_h_exec_pending(struct bnx2x *bp,
  * @o:			vlan_mac object
  * @ramrod_flags:	ramrod flags of missed execution
  *
- * @details Should be called under execution queue lock.
+ * Context: Should be called under execution queue lock.
  */
 static void __bnx2x_vlan_mac_h_pend(struct bnx2x *bp,
 				    struct bnx2x_vlan_mac_obj *o,
@@ -493,7 +495,7 @@ static void __bnx2x_vlan_mac_h_pend(struct bnx2x *bp,
  * @bp:			device handle
  * @o:			vlan_mac object
  *
- * @details Should be called under execution queue lock. Notice if a pending
+ * Context: Should be called under execution queue lock. Notice if a pending
  *          execution exists, it would perform it - possibly releasing and
  *          reclaiming the execution queue lock.
  */
@@ -516,7 +518,7 @@ static void __bnx2x_vlan_mac_h_write_unlock(struct bnx2x *bp,
  * @bp:			device handle
  * @o:			vlan_mac object
  *
- * @details Should be called under the execution queue lock. May sleep. May
+ * Context: Should be called under the execution queue lock. May sleep. May
  *          release and reclaim execution queue lock during its run.
  */
 static int __bnx2x_vlan_mac_h_read_lock(struct bnx2x *bp,
@@ -536,7 +538,7 @@ static int __bnx2x_vlan_mac_h_read_lock(struct bnx2x *bp,
  * @bp:			device handle
  * @o:			vlan_mac object
  *
- * @details May sleep. Claims and releases execution queue lock during its run.
+ * Context: May sleep. Claims and releases execution queue lock during its run.
  */
 int bnx2x_vlan_mac_h_read_lock(struct bnx2x *bp,
 			       struct bnx2x_vlan_mac_obj *o)
@@ -556,7 +558,7 @@ int bnx2x_vlan_mac_h_read_lock(struct bnx2x *bp,
  * @bp:			device handle
  * @o:			vlan_mac object
  *
- * @details Should be called under execution queue lock. Notice if a pending
+ * Context: Should be called under execution queue lock. Notice if a pending
  *          execution exists, it would be performed if this was the last
  *          reader. possibly releasing and reclaiming the execution queue lock.
  */
@@ -591,7 +593,7 @@ static void __bnx2x_vlan_mac_h_read_unlock(struct bnx2x *bp,
  * @bp:			device handle
  * @o:			vlan_mac object
  *
- * @details Notice if a pending execution exists, it would be performed if this
+ * Context: Notice if a pending execution exists, it would be performed if this
  *          was the last reader. Claims and releases the execution queue lock
  *          during its run.
  */
@@ -968,7 +970,7 @@ static void bnx2x_set_one_mac_e2(struct bnx2x *bp,
  *
  * @bp:		device handle
  * @o:		queue
- * @type:
+ * @type:	the type of echo
  * @cam_offset:	offset in cam memory
  * @hdr:	pointer to a header to setup
  *
@@ -1608,8 +1610,8 @@ static int __bnx2x_vlan_mac_execute_step(struct bnx2x *bp,
  *
  * @bp:		device handle
  * @o:		bnx2x_vlan_mac_obj
- * @cqe:
- * @cont:	if true schedule next execution chunk
+ * @cqe:	completion element
+ * @ramrod_flags: if set schedule next execution chunk
  *
  */
 static int bnx2x_complete_vlan_mac(struct bnx2x *bp,
@@ -1656,7 +1658,7 @@ static int bnx2x_complete_vlan_mac(struct bnx2x *bp,
  * bnx2x_optimize_vlan_mac - optimize ADD and DEL commands.
  *
  * @bp:		device handle
- * @o:		bnx2x_qable_obj
+ * @qo:		bnx2x_qable_obj
  * @elem:	bnx2x_exeq_elem
  */
 static int bnx2x_optimize_vlan_mac(struct bnx2x *bp,
@@ -1714,10 +1716,10 @@ static int bnx2x_optimize_vlan_mac(struct bnx2x *bp,
  * bnx2x_vlan_mac_get_registry_elem - prepare a registry element
  *
  * @bp:	  device handle
- * @o:
- * @elem:
- * @restore:
- * @re:
+ * @o:	vlan object
+ * @elem: element
+ * @restore: to restore or not
+ * @re: registry
  *
  * prepare a registry element according to the current command request.
  */
@@ -1768,9 +1770,9 @@ static inline int bnx2x_vlan_mac_get_registry_elem(
  * bnx2x_execute_vlan_mac - execute vlan mac command
  *
  * @bp:			device handle
- * @qo:
- * @exe_chunk:
- * @ramrod_flags:
+ * @qo:			bnx2x_qable_obj pointer
+ * @exe_chunk:		chunk
+ * @ramrod_flags:	flags
  *
  * go and send a ramrod!
  */
@@ -2006,8 +2008,8 @@ int bnx2x_config_vlan_mac(struct bnx2x *bp,
  * bnx2x_vlan_mac_del_all - delete elements with given vlan_mac_flags spec
  *
  * @bp:			device handle
- * @o:
- * @vlan_mac_flags:
+ * @o:			vlan object info
+ * @vlan_mac_flags:	vlan flags
  * @ramrod_flags:	execution flags to be used for this deletion
  *
  * if the last operation has completed successfully and there are no
@@ -2767,7 +2769,7 @@ static int bnx2x_mcast_enqueue_cmd(struct bnx2x *bp,
 /**
  * bnx2x_mcast_get_next_bin - get the next set bin (index)
  *
- * @o:
+ * @o:		multicast object info
  * @last:	index to start looking from (including)
  *
  * returns the next found (set) bin or a negative value if none is found.
@@ -2892,7 +2894,7 @@ static void bnx2x_mcast_set_one_rule_e2(struct bnx2x *bp,
  * bnx2x_mcast_handle_restore_cmd_e2 - restore configuration from the registry
  *
  * @bp:		device handle
- * @o:
+ * @o:		multicast object info
  * @start_bin:	index in the registry to start from (including)
  * @rdata_idx:	index in the ramrod data to start from
  *
@@ -3202,11 +3204,11 @@ static inline void bnx2x_mcast_hdl_del(struct bnx2x *bp,
 }
 
 /**
- * bnx2x_mcast_handle_current_cmd -
+ * bnx2x_mcast_handle_current_cmd - send command if room
  *
  * @bp:		device handle
- * @p:
- * @cmd:
+ * @p:		ramrod mcast info
+ * @cmd:	command
  * @start_cnt:	first line in the ramrod data that may be used
  *
  * This function is called iff there is enough place for the current command in
@@ -3323,7 +3325,7 @@ static void bnx2x_mcast_revert_e2(struct bnx2x *bp,
  * bnx2x_mcast_set_rdata_hdr_e2 - sets a header values
  *
  * @bp:		device handle
- * @p:
+ * @p:		ramrod parameters
  * @len:	number of rules to handle
  */
 static inline void bnx2x_mcast_set_rdata_hdr_e2(struct bnx2x *bp,
@@ -3684,7 +3686,7 @@ static void bnx2x_mcast_set_one_rule_e1(struct bnx2x *bp,
  * bnx2x_mcast_set_rdata_hdr_e1  - set header values in mac_configuration_cmd
  *
  * @bp:		device handle
- * @p:
+ * @p:		ramrod parameters
  * @len:	number of rules to handle
  */
 static inline void bnx2x_mcast_set_rdata_hdr_e1(struct bnx2x *bp,
@@ -3711,7 +3713,7 @@ static inline void bnx2x_mcast_set_rdata_hdr_e1(struct bnx2x *bp,
  * bnx2x_mcast_handle_restore_cmd_e1 - restore command for 57710
  *
  * @bp:		device handle
- * @o:
+ * @o:		multicast info
  * @start_idx:	index in the registry to start from
  * @rdata_idx:	index in the ramrod data to start from
  *
@@ -3798,10 +3800,10 @@ static inline int bnx2x_mcast_handle_pending_cmds_e1(
 /**
  * bnx2x_get_fw_mac_addr - revert the bnx2x_set_fw_mac_addr().
  *
- * @fw_hi:
- * @fw_mid:
- * @fw_lo:
- * @mac:
+ * @fw_hi: address
+ * @fw_mid: address
+ * @fw_lo: address
+ * @mac: mac address
  */
 static inline void bnx2x_get_fw_mac_addr(__le16 *fw_hi, __le16 *fw_mid,
 					 __le16 *fw_lo, u8 *mac)
@@ -3818,7 +3820,7 @@ static inline void bnx2x_get_fw_mac_addr(__le16 *fw_hi, __le16 *fw_mid,
  * bnx2x_mcast_refresh_registry_e1 -
  *
  * @bp:		device handle
- * @cnt:
+ * @o:		multicast info
  *
  * Check the ramrod data first entry flag to see if it's a DELETE or ADD command
  * and update the registry correspondingly: if ADD - allocate a memory and add
@@ -4311,7 +4313,7 @@ static bool bnx2x_credit_pool_get_entry_always_true(
 /**
  * bnx2x_init_credit_pool - initialize credit pool internals.
  *
- * @p:
+ * @p:		credit pool
  * @base:	Base entry in the CAM to use.
  * @credit:	pool size.
  *
@@ -4725,8 +4727,8 @@ static int bnx2x_queue_wait_comp(struct bnx2x *bp,
  * bnx2x_queue_comp_cmd - complete the state change command.
  *
  * @bp:		device handle
- * @o:
- * @cmd:
+ * @o:		queue info
+ * @cmd:	command to exec
  *
  * Checks that the arrived completion is expected.
  */
@@ -5477,8 +5479,8 @@ static int bnx2x_queue_send_cmd_e2(struct bnx2x *bp,
  * bnx2x_queue_chk_transition - check state machine of a regular Queue
  *
  * @bp:		device handle
- * @o:
- * @params:
+ * @o:		queue info
+ * @params:	queue state
  *
  * (not Forwarding)
  * It both checks if the requested command is legal in a current
@@ -5735,8 +5737,8 @@ static int bnx2x_func_wait_comp(struct bnx2x *bp,
  * bnx2x_func_state_change_comp - complete the state machine transition
  *
  * @bp:		device handle
- * @o:
- * @cmd:
+ * @o:		function info
+ * @cmd:	more info
  *
  * Called on state change transition. Completes the state
  * machine transition only - no HW interaction.
@@ -5776,8 +5778,8 @@ static inline int bnx2x_func_state_change_comp(struct bnx2x *bp,
  * bnx2x_func_comp_cmd - complete the state change command
  *
  * @bp:		device handle
- * @o:
- * @cmd:
+ * @o:		function info
+ * @cmd:	more info
  *
  * Checks that the arrived completion is expected.
  */
@@ -5796,8 +5798,8 @@ static int bnx2x_func_comp_cmd(struct bnx2x *bp,
  * bnx2x_func_chk_transition - perform function state machine transition
  *
  * @bp:		device handle
- * @o:
- * @params:
+ * @o:		function info
+ * @params:	state parameters
  *
  * It both checks if the requested command is legal in a current
  * state and, if it's legal, sets a `next_state' in the object
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 53f64ca673c3..38bbd7631fca 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -3782,6 +3782,7 @@ static int bnxt_hwrm_func_qstat_ext(struct bnxt *bp,
 		return -EOPNOTSUPP;
 
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_QSTATS_EXT, -1, -1);
+	req.fid = cpu_to_le16(0xffff);
 	req.flags = FUNC_QSTATS_EXT_REQ_FLAGS_COUNTER_MASK;
 	mutex_lock(&bp->hwrm_cmd_lock);
 	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
@@ -3852,7 +3853,7 @@ static void bnxt_init_stats(struct bnxt *bp)
 		tx_masks = stats->hw_masks;
 		tx_count = sizeof(struct tx_port_stats_ext) / 8;
 
-		flags = FUNC_QSTATS_EXT_REQ_FLAGS_COUNTER_MASK;
+		flags = PORT_QSTATS_EXT_REQ_FLAGS_COUNTER_MASK;
 		rc = bnxt_hwrm_port_qstats_ext(bp, flags);
 		if (rc) {
 			mask = (1ULL << 40) - 1;
@@ -4305,7 +4306,7 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len,
 	u32 bar_offset = BNXT_GRCPF_REG_CHIMP_COMM;
 	u16 dst = BNXT_HWRM_CHNL_CHIMP;
 
-	if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state))
+	if (BNXT_NO_FW_ACCESS(bp))
 		return -EBUSY;
 
 	if (msg_len > BNXT_HWRM_MAX_REQ_LEN) {
@@ -5342,13 +5343,16 @@ static int bnxt_hwrm_vnic_qcaps(struct bnxt *bp)
 		 * VLAN_STRIP_CAP properly.
 		 */
 		if ((flags & VNIC_QCAPS_RESP_FLAGS_VLAN_STRIP_CAP) ||
-		    ((bp->flags & BNXT_FLAG_CHIP_P5) &&
+		    (BNXT_CHIP_P5_THOR(bp) &&
 		     !(bp->fw_cap & BNXT_FW_CAP_EXT_HW_STATS_SUPPORTED)))
 			bp->fw_cap |= BNXT_FW_CAP_VLAN_RX_STRIP;
 		bp->max_tpa_v2 = le16_to_cpu(resp->max_aggs_supported);
-		if (bp->max_tpa_v2)
-			bp->hw_ring_stats_size =
-				sizeof(struct ctx_hw_stats_ext);
+		if (bp->max_tpa_v2) {
+			if (BNXT_CHIP_P5_THOR(bp))
+				bp->hw_ring_stats_size = BNXT_RING_STATS_SIZE_P5;
+			else
+				bp->hw_ring_stats_size = BNXT_RING_STATS_SIZE_P5_SR2;
+		}
 	}
 	mutex_unlock(&bp->hwrm_cmd_lock);
 	return rc;
@@ -5723,7 +5727,7 @@ static int hwrm_ring_free_send_msg(struct bnxt *bp,
 	struct hwrm_ring_free_output *resp = bp->hwrm_cmd_resp_addr;
 	u16 error_code;
 
-	if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state))
+	if (BNXT_NO_FW_ACCESS(bp))
 		return 0;
 
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_RING_FREE, cmpl_ring_id, -1);
@@ -7817,7 +7821,7 @@ static int bnxt_set_tpa(struct bnxt *bp, bool set_tpa)
 
 	if (set_tpa)
 		tpa_flags = bp->flags & BNXT_FLAG_TPA;
-	else if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state))
+	else if (BNXT_NO_FW_ACCESS(bp))
 		return 0;
 	for (i = 0; i < bp->nr_vnics; i++) {
 		rc = bnxt_hwrm_vnic_set_tpa(bp, i, tpa_flags);
@@ -8733,6 +8737,30 @@ void bnxt_tx_enable(struct bnxt *bp)
 		netif_carrier_on(bp->dev);
 }
 
+static char *bnxt_report_fec(struct bnxt_link_info *link_info)
+{
+	u8 active_fec = link_info->active_fec_sig_mode &
+			PORT_PHY_QCFG_RESP_ACTIVE_FEC_MASK;
+
+	switch (active_fec) {
+	default:
+	case PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_NONE_ACTIVE:
+		return "None";
+	case PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_CLAUSE74_ACTIVE:
+		return "Clause 74 BaseR";
+	case PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_CLAUSE91_ACTIVE:
+		return "Clause 91 RS(528,514)";
+	case PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_RS544_1XN_ACTIVE:
+		return "Clause 91 RS544_1XN";
+	case PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_RS544_IEEE_ACTIVE:
+		return "Clause 91 RS(544,514)";
+	case PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_RS272_1XN_ACTIVE:
+		return "Clause 91 RS272_1XN";
+	case PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_RS272_IEEE_ACTIVE:
+		return "Clause 91 RS(272,257)";
+	}
+}
+
 static void bnxt_report_link(struct bnxt *bp)
 {
 	if (bp->link_info.link_up) {
@@ -8763,16 +8791,25 @@ static void bnxt_report_link(struct bnxt *bp)
 							 "not active");
 		fec = bp->link_info.fec_cfg;
 		if (!(fec & PORT_PHY_QCFG_RESP_FEC_CFG_FEC_NONE_SUPPORTED))
-			netdev_info(bp->dev, "FEC autoneg %s encodings: %s\n",
+			netdev_info(bp->dev, "FEC autoneg %s encoding: %s\n",
 				    (fec & BNXT_FEC_AUTONEG) ? "on" : "off",
-				    (fec & BNXT_FEC_ENC_BASE_R) ? "BaseR" :
-				     (fec & BNXT_FEC_ENC_RS) ? "RS" : "None");
+				    bnxt_report_fec(&bp->link_info));
 	} else {
 		netif_carrier_off(bp->dev);
 		netdev_err(bp->dev, "NIC Link is Down\n");
 	}
 }
 
+static bool bnxt_phy_qcaps_no_speed(struct hwrm_port_phy_qcaps_output *resp)
+{
+	if (!resp->supported_speeds_auto_mode &&
+	    !resp->supported_speeds_force_mode &&
+	    !resp->supported_pam4_speeds_auto_mode &&
+	    !resp->supported_pam4_speeds_force_mode)
+		return true;
+	return false;
+}
+
 static int bnxt_hwrm_phy_qcaps(struct bnxt *bp)
 {
 	int rc = 0;
@@ -8820,9 +8857,24 @@ static int bnxt_hwrm_phy_qcaps(struct bnxt *bp)
 	if (resp->flags & PORT_PHY_QCAPS_RESP_FLAGS_CUMULATIVE_COUNTERS_ON_RESET)
 		bp->fw_cap |= BNXT_FW_CAP_PORT_STATS_NO_RESET;
 
+	if (bp->hwrm_spec_code >= 0x10a01) {
+		if (bnxt_phy_qcaps_no_speed(resp)) {
+			link_info->phy_state = BNXT_PHY_STATE_DISABLED;
+			netdev_warn(bp->dev, "Ethernet link disabled\n");
+		} else if (link_info->phy_state == BNXT_PHY_STATE_DISABLED) {
+			link_info->phy_state = BNXT_PHY_STATE_ENABLED;
+			netdev_info(bp->dev, "Ethernet link enabled\n");
+			/* Phy re-enabled, reprobe the speeds */
+			link_info->support_auto_speeds = 0;
+			link_info->support_pam4_auto_speeds = 0;
+		}
+	}
 	if (resp->supported_speeds_auto_mode)
 		link_info->support_auto_speeds =
 			le16_to_cpu(resp->supported_speeds_auto_mode);
+	if (resp->supported_pam4_speeds_auto_mode)
+		link_info->support_pam4_auto_speeds =
+			le16_to_cpu(resp->supported_pam4_speeds_auto_mode);
 
 	bp->port_count = resp->port_cnt;
 
@@ -8831,14 +8883,21 @@ hwrm_phy_qcaps_exit:
 	return rc;
 }
 
-static int bnxt_update_link(struct bnxt *bp, bool chng_link_state)
+static bool bnxt_support_dropped(u16 advertising, u16 supported)
+{
+	u16 diff = advertising ^ supported;
+
+	return ((supported | diff) != supported);
+}
+
+int bnxt_update_link(struct bnxt *bp, bool chng_link_state)
 {
 	int rc = 0;
 	struct bnxt_link_info *link_info = &bp->link_info;
 	struct hwrm_port_phy_qcfg_input req = {0};
 	struct hwrm_port_phy_qcfg_output *resp = bp->hwrm_cmd_resp_addr;
 	u8 link_up = link_info->link_up;
-	u16 diff;
+	bool support_changed = false;
 
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_PORT_PHY_QCFG, -1, -1);
 
@@ -8865,10 +8924,17 @@ static int bnxt_update_link(struct bnxt *bp, bool chng_link_state)
 	else
 		link_info->link_speed = 0;
 	link_info->force_link_speed = le16_to_cpu(resp->force_link_speed);
+	link_info->force_pam4_link_speed =
+		le16_to_cpu(resp->force_pam4_link_speed);
 	link_info->support_speeds = le16_to_cpu(resp->support_speeds);
+	link_info->support_pam4_speeds = le16_to_cpu(resp->support_pam4_speeds);
 	link_info->auto_link_speeds = le16_to_cpu(resp->auto_link_speed_mask);
+	link_info->auto_pam4_link_speeds =
+		le16_to_cpu(resp->auto_pam4_link_speed_mask);
 	link_info->lp_auto_link_speeds =
 		le16_to_cpu(resp->link_partner_adv_speeds);
+	link_info->lp_auto_pam4_link_speeds =
+		resp->link_partner_pam4_adv_speeds;
 	link_info->preemphasis = le32_to_cpu(resp->preemphasis);
 	link_info->phy_ver[0] = resp->phy_maj;
 	link_info->phy_ver[1] = resp->phy_min;
@@ -8917,9 +8983,10 @@ static int bnxt_update_link(struct bnxt *bp, bool chng_link_state)
 	}
 
 	link_info->fec_cfg = PORT_PHY_QCFG_RESP_FEC_CFG_FEC_NONE_SUPPORTED;
-	if (bp->hwrm_spec_code >= 0x10504)
+	if (bp->hwrm_spec_code >= 0x10504) {
 		link_info->fec_cfg = le16_to_cpu(resp->fec_cfg);
-
+		link_info->active_fec_sig_mode = resp->active_fec_signal_mode;
+	}
 	/* TODO: need to add more logic to report VF link */
 	if (chng_link_state) {
 		if (link_info->phy_link_status == BNXT_LINK_LINK)
@@ -8937,17 +9004,21 @@ static int bnxt_update_link(struct bnxt *bp, bool chng_link_state)
 	if (!BNXT_PHY_CFG_ABLE(bp))
 		return 0;
 
-	diff = link_info->support_auto_speeds ^ link_info->advertising;
-	if ((link_info->support_auto_speeds | diff) !=
-	    link_info->support_auto_speeds) {
-		/* An advertised speed is no longer supported, so we need to
-		 * update the advertisement settings.  Caller holds RTNL
-		 * so we can modify link settings.
-		 */
+	/* Check if any advertised speeds are no longer supported. The caller
+	 * holds the link_lock mutex, so we can modify link_info settings.
+	 */
+	if (bnxt_support_dropped(link_info->advertising,
+				 link_info->support_auto_speeds)) {
 		link_info->advertising = link_info->support_auto_speeds;
-		if (link_info->autoneg & BNXT_AUTONEG_SPEED)
-			bnxt_hwrm_set_link_setting(bp, true, false);
+		support_changed = true;
+	}
+	if (bnxt_support_dropped(link_info->advertising_pam4,
+				 link_info->support_pam4_auto_speeds)) {
+		link_info->advertising_pam4 = link_info->support_pam4_auto_speeds;
+		support_changed = true;
 	}
+	if (support_changed && (link_info->autoneg & BNXT_AUTONEG_SPEED))
+		bnxt_hwrm_set_link_setting(bp, true, false);
 	return 0;
 }
 
@@ -9006,27 +9077,30 @@ bnxt_hwrm_set_pause_common(struct bnxt *bp, struct hwrm_port_phy_cfg_input *req)
 	}
 }
 
-static void bnxt_hwrm_set_link_common(struct bnxt *bp,
-				      struct hwrm_port_phy_cfg_input *req)
+static void bnxt_hwrm_set_link_common(struct bnxt *bp, struct hwrm_port_phy_cfg_input *req)
 {
-	u8 autoneg = bp->link_info.autoneg;
-	u16 fw_link_speed = bp->link_info.req_link_speed;
-	u16 advertising = bp->link_info.advertising;
-
-	if (autoneg & BNXT_AUTONEG_SPEED) {
-		req->auto_mode |=
-			PORT_PHY_CFG_REQ_AUTO_MODE_SPEED_MASK;
-
-		req->enables |= cpu_to_le32(
-			PORT_PHY_CFG_REQ_ENABLES_AUTO_LINK_SPEED_MASK);
-		req->auto_link_speed_mask = cpu_to_le16(advertising);
-
+	if (bp->link_info.autoneg & BNXT_AUTONEG_SPEED) {
+		req->auto_mode |= PORT_PHY_CFG_REQ_AUTO_MODE_SPEED_MASK;
+		if (bp->link_info.advertising) {
+			req->enables |= cpu_to_le32(PORT_PHY_CFG_REQ_ENABLES_AUTO_LINK_SPEED_MASK);
+			req->auto_link_speed_mask = cpu_to_le16(bp->link_info.advertising);
+		}
+		if (bp->link_info.advertising_pam4) {
+			req->enables |=
+				cpu_to_le32(PORT_PHY_CFG_REQ_ENABLES_AUTO_PAM4_LINK_SPEED_MASK);
+			req->auto_link_pam4_speed_mask =
+				cpu_to_le16(bp->link_info.advertising_pam4);
+		}
 		req->enables |= cpu_to_le32(PORT_PHY_CFG_REQ_ENABLES_AUTO_MODE);
-		req->flags |=
-			cpu_to_le32(PORT_PHY_CFG_REQ_FLAGS_RESTART_AUTONEG);
+		req->flags |= cpu_to_le32(PORT_PHY_CFG_REQ_FLAGS_RESTART_AUTONEG);
 	} else {
-		req->force_link_speed = cpu_to_le16(fw_link_speed);
 		req->flags |= cpu_to_le32(PORT_PHY_CFG_REQ_FLAGS_FORCE);
+		if (bp->link_info.req_signal_mode == BNXT_SIG_MODE_PAM4) {
+			req->force_pam4_link_speed = cpu_to_le16(bp->link_info.req_link_speed);
+			req->enables |= cpu_to_le32(PORT_PHY_CFG_REQ_ENABLES_FORCE_PAM4_LINK_SPEED);
+		} else {
+			req->force_link_speed = cpu_to_le16(bp->link_info.req_link_speed);
+		}
 	}
 
 	/* tell chimp that the setting takes effect immediately */
@@ -9310,18 +9384,16 @@ static ssize_t bnxt_show_temp(struct device *dev,
 	struct hwrm_temp_monitor_query_output *resp;
 	struct bnxt *bp = dev_get_drvdata(dev);
 	u32 len = 0;
+	int rc;
 
 	resp = bp->hwrm_cmd_resp_addr;
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_TEMP_MONITOR_QUERY, -1, -1);
 	mutex_lock(&bp->hwrm_cmd_lock);
-	if (!_hwrm_send_message_silent(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT))
+	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (!rc)
 		len = sprintf(buf, "%u\n", resp->temp * 1000); /* display millidegree */
 	mutex_unlock(&bp->hwrm_cmd_lock);
-
-	if (len)
-		return len;
-
-	return sprintf(buf, "unknown\n");
+	return rc ?: len;
 }
 static SENSOR_DEVICE_ATTR(temp1_input, 0444, bnxt_show_temp, NULL, 0);
 
@@ -9341,7 +9413,16 @@ static void bnxt_hwmon_close(struct bnxt *bp)
 
 static void bnxt_hwmon_open(struct bnxt *bp)
 {
+	struct hwrm_temp_monitor_query_input req = {0};
 	struct pci_dev *pdev = bp->pdev;
+	int rc;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_TEMP_MONITOR_QUERY, -1, -1);
+	rc = hwrm_send_message_silent(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (rc == -EACCES || rc == -EOPNOTSUPP) {
+		bnxt_hwmon_close(bp);
+		return;
+	}
 
 	if (bp->hwmon_dev)
 		return;
@@ -9415,14 +9496,19 @@ static int bnxt_update_phy_setting(struct bnxt *bp)
 	if (!(link_info->autoneg & BNXT_AUTONEG_SPEED)) {
 		if (BNXT_AUTO_MODE(link_info->auto_mode))
 			update_link = true;
-		if (link_info->req_link_speed != link_info->force_link_speed)
+		if (link_info->req_signal_mode == BNXT_SIG_MODE_NRZ &&
+		    link_info->req_link_speed != link_info->force_link_speed)
+			update_link = true;
+		else if (link_info->req_signal_mode == BNXT_SIG_MODE_PAM4 &&
+			 link_info->req_link_speed != link_info->force_pam4_link_speed)
 			update_link = true;
 		if (link_info->req_duplex != link_info->duplex_setting)
 			update_link = true;
 	} else {
 		if (link_info->auto_mode == BNXT_LINK_AUTO_NONE)
 			update_link = true;
-		if (link_info->advertising != link_info->auto_link_speeds)
+		if (link_info->advertising != link_info->auto_link_speeds ||
+		    link_info->advertising_pam4 != link_info->auto_pam4_link_speeds)
 			update_link = true;
 	}
 
@@ -10682,8 +10768,15 @@ static void bnxt_init_ethtool_link_settings(struct bnxt *bp)
 			link_info->autoneg |= BNXT_AUTONEG_FLOW_CTRL;
 		}
 		link_info->advertising = link_info->auto_link_speeds;
+		link_info->advertising_pam4 = link_info->auto_pam4_link_speeds;
 	} else {
 		link_info->req_link_speed = link_info->force_link_speed;
+		link_info->req_signal_mode = BNXT_SIG_MODE_NRZ;
+		if (link_info->force_pam4_link_speed) {
+			link_info->req_link_speed =
+				link_info->force_pam4_link_speed;
+			link_info->req_signal_mode = BNXT_SIG_MODE_PAM4;
+		}
 		link_info->req_duplex = link_info->duplex_setting;
 	}
 	if (link_info->autoneg & BNXT_AUTONEG_FLOW_CTRL)
@@ -11778,6 +11871,10 @@ static void bnxt_remove_one(struct pci_dev *pdev)
 	if (BNXT_PF(bp))
 		bnxt_sriov_disable(bp);
 
+	clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
+	bnxt_cancel_sp_work(bp);
+	bp->sp_event = 0;
+
 	bnxt_dl_fw_reporters_destroy(bp, true);
 	if (BNXT_PF(bp))
 		devlink_port_type_clear(&bp->dl_port);
@@ -11785,9 +11882,6 @@ static void bnxt_remove_one(struct pci_dev *pdev)
 	unregister_netdev(dev);
 	bnxt_dl_unregister(bp);
 	bnxt_shutdown_tc(bp);
-	clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
-	bnxt_cancel_sp_work(bp);
-	bp->sp_event = 0;
 
 	bnxt_clear_int_mode(bp);
 	bnxt_hwrm_func_drv_unrgtr(bp);
@@ -12088,7 +12182,7 @@ static int bnxt_init_mac_addr(struct bnxt *bp)
 static void bnxt_vpd_read_info(struct bnxt *bp)
 {
 	struct pci_dev *pdev = bp->pdev;
-	int i, len, pos, ro_size;
+	int i, len, pos, ro_size, size;
 	ssize_t vpd_size;
 	u8 *vpd_data;
 
@@ -12123,7 +12217,8 @@ static void bnxt_vpd_read_info(struct bnxt *bp)
 	if (len + pos > vpd_size)
 		goto read_sn;
 
-	strlcpy(bp->board_partno, &vpd_data[pos], min(len, BNXT_VPD_FLD_LEN));
+	size = min(len, BNXT_VPD_FLD_LEN - 1);
+	memcpy(bp->board_partno, &vpd_data[pos], size);
 
 read_sn:
 	pos = pci_vpd_find_info_keyword(vpd_data, i, ro_size,
@@ -12136,7 +12231,8 @@ read_sn:
 	if (len + pos > vpd_size)
 		goto exit;
 
-	strlcpy(bp->board_serialno, &vpd_data[pos], min(len, BNXT_VPD_FLD_LEN));
+	size = min(len, BNXT_VPD_FLD_LEN - 1);
+	memcpy(bp->board_serialno, &vpd_data[pos], size);
 exit:
 	kfree(vpd_data);
 }
@@ -12222,8 +12318,11 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (rc)
 		goto init_err_pci_clean;
 
-	if (BNXT_CHIP_P5(bp))
+	if (BNXT_CHIP_P5(bp)) {
 		bp->flags |= BNXT_FLAG_CHIP_P5;
+		if (BNXT_CHIP_SR2(bp))
+			bp->flags |= BNXT_FLAG_CHIP_SR2;
+	}
 
 	rc = bnxt_alloc_rss_indir_tbl(bp);
 	if (rc)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 5a13eb66beda..74387259e1c6 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1142,50 +1142,6 @@ struct bnxt_ntuple_filter {
 #define BNXT_FLTR_UPDATE	1
 };
 
-struct hwrm_port_phy_qcfg_output_compat {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	link;
-	u8	link_signal_mode;
-	__le16	link_speed;
-	u8	duplex_cfg;
-	u8	pause;
-	__le16	support_speeds;
-	__le16	force_link_speed;
-	u8	auto_mode;
-	u8	auto_pause;
-	__le16	auto_link_speed;
-	__le16	auto_link_speed_mask;
-	u8	wirespeed;
-	u8	lpbk;
-	u8	force_pause;
-	u8	module_status;
-	__le32	preemphasis;
-	u8	phy_maj;
-	u8	phy_min;
-	u8	phy_bld;
-	u8	phy_type;
-	u8	media_type;
-	u8	xcvr_pkg_type;
-	u8	eee_config_phy_addr;
-	u8	parallel_detect;
-	__le16	link_partner_adv_speeds;
-	u8	link_partner_adv_auto_mode;
-	u8	link_partner_adv_pause;
-	__le16	adv_eee_link_speed_mask;
-	__le16	link_partner_adv_eee_link_speed_mask;
-	__le32	xcvr_identifier_type_tx_lpi_timer;
-	__le16	fec_cfg;
-	u8	duplex_state;
-	u8	option_flags;
-	char	phy_vendor_name[16];
-	char	phy_vendor_partnumber[16];
-	u8	unused_0[7];
-	u8	valid;
-};
-
 struct bnxt_link_info {
 	u8			phy_type;
 	u8			media_type;
@@ -1196,7 +1152,10 @@ struct bnxt_link_info {
 #define BNXT_LINK_SIGNAL	PORT_PHY_QCFG_RESP_LINK_SIGNAL
 #define BNXT_LINK_LINK		PORT_PHY_QCFG_RESP_LINK_LINK
 	u8			wire_speed;
-	u8			loop_back;
+	u8			phy_state;
+#define BNXT_PHY_STATE_ENABLED		0
+#define BNXT_PHY_STATE_DISABLED		1
+
 	u8			link_up;
 	u8			duplex;
 #define BNXT_LINK_DUPLEX_HALF	PORT_PHY_QCFG_RESP_DUPLEX_STATE_HALF
@@ -1232,6 +1191,7 @@ struct bnxt_link_info {
 #define BNXT_LINK_SPEED_50GB	PORT_PHY_QCFG_RESP_LINK_SPEED_50GB
 #define BNXT_LINK_SPEED_100GB	PORT_PHY_QCFG_RESP_LINK_SPEED_100GB
 	u16			support_speeds;
+	u16			support_pam4_speeds;
 	u16			auto_link_speeds;	/* fw adv setting */
 #define BNXT_LINK_SPEED_MSK_100MB PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_100MB
 #define BNXT_LINK_SPEED_MSK_1GB PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_1GB
@@ -1243,24 +1203,51 @@ struct bnxt_link_info {
 #define BNXT_LINK_SPEED_MSK_40GB PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_40GB
 #define BNXT_LINK_SPEED_MSK_50GB PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_50GB
 #define BNXT_LINK_SPEED_MSK_100GB PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_100GB
+	u16			auto_pam4_link_speeds;
+#define BNXT_LINK_PAM4_SPEED_MSK_50GB PORT_PHY_QCFG_RESP_SUPPORT_PAM4_SPEEDS_50G
+#define BNXT_LINK_PAM4_SPEED_MSK_100GB PORT_PHY_QCFG_RESP_SUPPORT_PAM4_SPEEDS_100G
+#define BNXT_LINK_PAM4_SPEED_MSK_200GB PORT_PHY_QCFG_RESP_SUPPORT_PAM4_SPEEDS_200G
 	u16			support_auto_speeds;
+	u16			support_pam4_auto_speeds;
 	u16			lp_auto_link_speeds;
+	u16			lp_auto_pam4_link_speeds;
 	u16			force_link_speed;
+	u16			force_pam4_link_speed;
 	u32			preemphasis;
 	u8			module_status;
+	u8			active_fec_sig_mode;
 	u16			fec_cfg;
+#define BNXT_FEC_NONE		PORT_PHY_QCFG_RESP_FEC_CFG_FEC_NONE_SUPPORTED
+#define BNXT_FEC_AUTONEG_CAP	PORT_PHY_QCFG_RESP_FEC_CFG_FEC_AUTONEG_SUPPORTED
 #define BNXT_FEC_AUTONEG	PORT_PHY_QCFG_RESP_FEC_CFG_FEC_AUTONEG_ENABLED
+#define BNXT_FEC_ENC_BASE_R_CAP	\
+	PORT_PHY_QCFG_RESP_FEC_CFG_FEC_CLAUSE74_SUPPORTED
 #define BNXT_FEC_ENC_BASE_R	PORT_PHY_QCFG_RESP_FEC_CFG_FEC_CLAUSE74_ENABLED
-#define BNXT_FEC_ENC_RS		PORT_PHY_QCFG_RESP_FEC_CFG_FEC_CLAUSE91_ENABLED
+#define BNXT_FEC_ENC_RS_CAP	\
+	PORT_PHY_QCFG_RESP_FEC_CFG_FEC_CLAUSE91_SUPPORTED
+#define BNXT_FEC_ENC_LLRS_CAP	\
+	(PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS272_1XN_SUPPORTED |	\
+	 PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS272_IEEE_SUPPORTED)
+#define BNXT_FEC_ENC_RS		\
+	(PORT_PHY_QCFG_RESP_FEC_CFG_FEC_CLAUSE91_ENABLED |	\
+	 PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS544_1XN_ENABLED |	\
+	 PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS544_IEEE_ENABLED)
+#define BNXT_FEC_ENC_LLRS	\
+	(PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS272_1XN_ENABLED |	\
+	 PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS272_IEEE_ENABLED)
 
 	/* copy of requested setting from ethtool cmd */
 	u8			autoneg;
 #define BNXT_AUTONEG_SPEED		1
 #define BNXT_AUTONEG_FLOW_CTRL		2
+	u8			req_signal_mode;
+#define BNXT_SIG_MODE_NRZ	PORT_PHY_QCFG_RESP_SIGNAL_MODE_NRZ
+#define BNXT_SIG_MODE_PAM4	PORT_PHY_QCFG_RESP_SIGNAL_MODE_PAM4
 	u8			req_duplex;
 	u8			req_flow_ctrl;
 	u16			req_link_speed;
 	u16			advertising;	/* user adv setting */
+	u16			advertising_pam4;
 	bool			force_link_chng;
 
 	bool			phy_retry;
@@ -1272,6 +1259,49 @@ struct bnxt_link_info {
 	struct hwrm_port_phy_qcfg_output phy_qcfg_resp;
 };
 
+#define BNXT_FEC_RS544_ON					\
+	 (PORT_PHY_CFG_REQ_FLAGS_FEC_RS544_1XN_ENABLE |		\
+	  PORT_PHY_CFG_REQ_FLAGS_FEC_RS544_IEEE_ENABLE)
+
+#define BNXT_FEC_RS544_OFF					\
+	 (PORT_PHY_CFG_REQ_FLAGS_FEC_RS544_1XN_DISABLE |	\
+	  PORT_PHY_CFG_REQ_FLAGS_FEC_RS544_IEEE_DISABLE)
+
+#define BNXT_FEC_RS272_ON					\
+	 (PORT_PHY_CFG_REQ_FLAGS_FEC_RS272_1XN_ENABLE |		\
+	  PORT_PHY_CFG_REQ_FLAGS_FEC_RS272_IEEE_ENABLE)
+
+#define BNXT_FEC_RS272_OFF					\
+	 (PORT_PHY_CFG_REQ_FLAGS_FEC_RS272_1XN_DISABLE |	\
+	  PORT_PHY_CFG_REQ_FLAGS_FEC_RS272_IEEE_DISABLE)
+
+#define BNXT_PAM4_SUPPORTED(link_info)				\
+	((link_info)->support_pam4_speeds)
+
+#define BNXT_FEC_RS_ON(link_info)				\
+	(PORT_PHY_CFG_REQ_FLAGS_FEC_CLAUSE91_ENABLE |		\
+	 PORT_PHY_CFG_REQ_FLAGS_FEC_CLAUSE74_DISABLE |		\
+	 (BNXT_PAM4_SUPPORTED(link_info) ?			\
+	  (BNXT_FEC_RS544_ON | BNXT_FEC_RS272_OFF) : 0))
+
+#define BNXT_FEC_LLRS_ON					\
+	(PORT_PHY_CFG_REQ_FLAGS_FEC_CLAUSE91_ENABLE |		\
+	 PORT_PHY_CFG_REQ_FLAGS_FEC_CLAUSE74_DISABLE |		\
+	 BNXT_FEC_RS272_ON | BNXT_FEC_RS544_OFF)
+
+#define BNXT_FEC_RS_OFF(link_info)				\
+	(PORT_PHY_CFG_REQ_FLAGS_FEC_CLAUSE91_DISABLE |		\
+	 (BNXT_PAM4_SUPPORTED(link_info) ?			\
+	  (BNXT_FEC_RS544_OFF | BNXT_FEC_RS272_OFF) : 0))
+
+#define BNXT_FEC_BASE_R_ON(link_info)				\
+	(PORT_PHY_CFG_REQ_FLAGS_FEC_CLAUSE74_ENABLE |		\
+	 BNXT_FEC_RS_OFF(link_info))
+
+#define BNXT_FEC_ALL_OFF(link_info)				\
+	(PORT_PHY_CFG_REQ_FLAGS_FEC_CLAUSE74_DISABLE |		\
+	 BNXT_FEC_RS_OFF(link_info))
+
 #define BNXT_MAX_QUEUE	8
 
 struct bnxt_queue_info {
@@ -1535,6 +1565,8 @@ struct bnxt {
 
 	u8			chip_rev;
 
+#define CHIP_NUM_58818		0xd818
+
 #define BNXT_CHIP_NUM_5730X(chip_num)		\
 	((chip_num) >= CHIP_NUM_57301 &&	\
 	 (chip_num) <= CHIP_NUM_57304)
@@ -1613,6 +1645,7 @@ struct bnxt {
 					 BNXT_FLAG_ROCEV2_CAP)
 	#define BNXT_FLAG_NO_AGG_RINGS	0x20000
 	#define BNXT_FLAG_RX_PAGE_MODE	0x40000
+	#define BNXT_FLAG_CHIP_SR2	0x80000
 	#define BNXT_FLAG_MULTI_HOST	0x100000
 	#define BNXT_FLAG_DSN_VALID	0x200000
 	#define BNXT_FLAG_DOUBLE_DB	0x400000
@@ -1630,20 +1663,27 @@ struct bnxt {
 #define BNXT_NPAR(bp)		((bp)->port_partition_type)
 #define BNXT_MH(bp)		((bp)->flags & BNXT_FLAG_MULTI_HOST)
 #define BNXT_SINGLE_PF(bp)	(BNXT_PF(bp) && !BNXT_NPAR(bp) && !BNXT_MH(bp))
-#define BNXT_PHY_CFG_ABLE(bp)	(BNXT_SINGLE_PF(bp) ||			\
-				 ((bp)->fw_cap & BNXT_FW_CAP_SHARED_PORT_CFG))
+#define BNXT_PHY_CFG_ABLE(bp)	((BNXT_SINGLE_PF(bp) ||			\
+				  ((bp)->fw_cap & BNXT_FW_CAP_SHARED_PORT_CFG)) && \
+				 (bp)->link_info.phy_state == BNXT_PHY_STATE_ENABLED)
 #define BNXT_CHIP_TYPE_NITRO_A0(bp) ((bp)->flags & BNXT_FLAG_CHIP_NITRO_A0)
 #define BNXT_RX_PAGE_MODE(bp)	((bp)->flags & BNXT_FLAG_RX_PAGE_MODE)
 #define BNXT_SUPPORTS_TPA(bp)	(!BNXT_CHIP_TYPE_NITRO_A0(bp) &&	\
 				 (!((bp)->flags & BNXT_FLAG_CHIP_P5) ||	\
 				  (bp)->max_tpa_v2) && !is_kdump_kernel())
 
-/* Chip class phase 5 */
-#define BNXT_CHIP_P5(bp)			\
+#define BNXT_CHIP_SR2(bp)			\
+	((bp)->chip_num == CHIP_NUM_58818)
+
+#define BNXT_CHIP_P5_THOR(bp)			\
 	((bp)->chip_num == CHIP_NUM_57508 ||	\
 	 (bp)->chip_num == CHIP_NUM_57504 ||	\
 	 (bp)->chip_num == CHIP_NUM_57502)
 
+/* Chip class phase 5 */
+#define BNXT_CHIP_P5(bp)			\
+	(BNXT_CHIP_P5_THOR(bp) || BNXT_CHIP_SR2(bp))
+
 /* Chip class phase 4.x */
 #define BNXT_CHIP_P4(bp)			\
 	(BNXT_CHIP_NUM_57X1X((bp)->chip_num) ||	\
@@ -1737,6 +1777,10 @@ struct bnxt {
 #define BNXT_STATE_FW_FATAL_COND	6
 #define BNXT_STATE_DRV_REGISTERED	7
 
+#define BNXT_NO_FW_ACCESS(bp)					\
+	(test_bit(BNXT_STATE_FW_FATAL_COND, &(bp)->state) ||	\
+	 pci_channel_offline((bp)->pdev))
+
 	struct bnxt_irq	*irq_tbl;
 	int			total_irqs;
 	u8			mac_addr[ETH_ALEN];
@@ -1931,6 +1975,20 @@ struct bnxt {
 	struct device		*hwmon_dev;
 };
 
+#define BNXT_NUM_RX_RING_STATS			8
+#define BNXT_NUM_TX_RING_STATS			8
+#define BNXT_NUM_TPA_RING_STATS			4
+#define BNXT_NUM_TPA_RING_STATS_P5		5
+#define BNXT_NUM_TPA_RING_STATS_P5_SR2		6
+
+#define BNXT_RING_STATS_SIZE_P5					\
+	((BNXT_NUM_RX_RING_STATS + BNXT_NUM_TX_RING_STATS +	\
+	  BNXT_NUM_TPA_RING_STATS_P5) * 8)
+
+#define BNXT_RING_STATS_SIZE_P5_SR2				\
+	((BNXT_NUM_RX_RING_STATS + BNXT_NUM_TX_RING_STATS +	\
+	  BNXT_NUM_TPA_RING_STATS_P5_SR2) * 8)
+
 #define BNXT_GET_RING_STATS64(sw, counter)		\
 	(*((sw) + offsetof(struct ctx_hw_stats, counter) / 8))
 
@@ -2110,6 +2168,7 @@ int bnxt_get_avail_msix(struct bnxt *bp, int num);
 int bnxt_reserve_rings(struct bnxt *bp, bool irq_re_init);
 void bnxt_tx_disable(struct bnxt *bp);
 void bnxt_tx_enable(struct bnxt *bp);
+int bnxt_update_link(struct bnxt *bp, bool chng_link_state);
 int bnxt_hwrm_set_pause(struct bnxt *);
 int bnxt_hwrm_set_link_setting(struct bnxt *, bool, bool);
 int bnxt_hwrm_alloc_wol_fltr(struct bnxt *bp);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
index 3a854195d5b0..d436134bdc40 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
@@ -17,15 +17,13 @@
 #include "bnxt_ethtool.h"
 
 static int
-bnxt_dl_flash_update(struct devlink *dl, const char *filename,
-		     const char *region, struct netlink_ext_ack *extack)
+bnxt_dl_flash_update(struct devlink *dl,
+		     struct devlink_flash_update_params *params,
+		     struct netlink_ext_ack *extack)
 {
 	struct bnxt *bp = bnxt_get_bp_from_dl(dl);
 	int rc;
 
-	if (region)
-		return -EOPNOTSUPP;
-
 	if (!BNXT_PF(bp)) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "flash update not supported from a VF");
@@ -33,15 +31,12 @@ bnxt_dl_flash_update(struct devlink *dl, const char *filename,
 	}
 
 	devlink_flash_update_begin_notify(dl);
-	devlink_flash_update_status_notify(dl, "Preparing to flash", region, 0,
-					   0);
-	rc = bnxt_flash_package_from_file(bp->dev, filename, 0);
+	devlink_flash_update_status_notify(dl, "Preparing to flash", NULL, 0, 0);
+	rc = bnxt_flash_package_from_file(bp->dev, params->file_name, 0);
 	if (!rc)
-		devlink_flash_update_status_notify(dl, "Flashing done", region,
-						   0, 0);
+		devlink_flash_update_status_notify(dl, "Flashing done", NULL, 0, 0);
 	else
-		devlink_flash_update_status_notify(dl, "Flashing failed",
-						   region, 0, 0);
+		devlink_flash_update_status_notify(dl, "Flashing failed", NULL, 0, 0);
 	devlink_flash_update_end_notify(dl);
 	return rc;
 }
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 5a65f28ef771..19b8e3e822f1 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -11,6 +11,7 @@
 #include <linux/ctype.h>
 #include <linux/stringify.h>
 #include <linux/ethtool.h>
+#include <linux/linkmode.h>
 #include <linux/interrupt.h>
 #include <linux/pci.h>
 #include <linux/etherdevice.h>
@@ -172,6 +173,7 @@ static const char * const bnxt_ring_tpa2_stats_str[] = {
 	"rx_tpa_pkt",
 	"rx_tpa_bytes",
 	"rx_tpa_errors",
+	"rx_tpa_events",
 };
 
 static const char * const bnxt_rx_sw_stats_str[] = {
@@ -462,9 +464,12 @@ static const struct {
 static int bnxt_get_num_tpa_ring_stats(struct bnxt *bp)
 {
 	if (BNXT_SUPPORTS_TPA(bp)) {
-		if (bp->max_tpa_v2)
-			return ARRAY_SIZE(bnxt_ring_tpa2_stats_str);
-		return ARRAY_SIZE(bnxt_ring_tpa_stats_str);
+		if (bp->max_tpa_v2) {
+			if (BNXT_CHIP_P5_THOR(bp))
+				return BNXT_NUM_TPA_RING_STATS_P5;
+			return BNXT_NUM_TPA_RING_STATS_P5_SR2;
+		}
+		return BNXT_NUM_TPA_RING_STATS;
 	}
 	return 0;
 }
@@ -796,7 +801,7 @@ static void bnxt_get_channels(struct net_device *dev,
 	struct bnxt *bp = netdev_priv(dev);
 	struct bnxt_hw_resc *hw_resc = &bp->hw_resc;
 	int max_rx_rings, max_tx_rings, tcs;
-	int max_tx_sch_inputs;
+	int max_tx_sch_inputs, tx_grps;
 
 	/* Get the most up-to-date max_tx_sch_inputs. */
 	if (netif_running(dev) && BNXT_NEW_RM(bp))
@@ -806,6 +811,12 @@ static void bnxt_get_channels(struct net_device *dev,
 	bnxt_get_max_rings(bp, &max_rx_rings, &max_tx_rings, true);
 	if (max_tx_sch_inputs)
 		max_tx_rings = min_t(int, max_tx_rings, max_tx_sch_inputs);
+
+	tcs = netdev_get_num_tc(dev);
+	tx_grps = max(tcs, 1);
+	if (bp->tx_nr_rings_xdp)
+		tx_grps++;
+	max_tx_rings /= tx_grps;
 	channel->max_combined = min_t(int, max_rx_rings, max_tx_rings);
 
 	if (bnxt_get_max_rings(bp, &max_rx_rings, &max_tx_rings, false)) {
@@ -815,7 +826,6 @@ static void bnxt_get_channels(struct net_device *dev,
 	if (max_tx_sch_inputs)
 		max_tx_rings = min_t(int, max_tx_rings, max_tx_sch_inputs);
 
-	tcs = netdev_get_num_tc(dev);
 	if (tcs > 1)
 		max_tx_rings /= tcs;
 
@@ -1322,6 +1332,9 @@ static int bnxt_get_regs_len(struct net_device *dev)
 	struct bnxt *bp = netdev_priv(dev);
 	int reg_len;
 
+	if (!BNXT_PF(bp))
+		return -EOPNOTSUPP;
+
 	reg_len = BNXT_PXP_REG_LEN;
 
 	if (bp->fw_cap & BNXT_FW_CAP_PCIE_STATS_SUPPORTED)
@@ -1500,6 +1513,53 @@ u32 _bnxt_fw_to_ethtool_adv_spds(u16 fw_speeds, u8 fw_pause)
 		(fw_speeds) |= BNXT_LINK_SPEED_MSK_100GB;		\
 }
 
+#define BNXT_FW_TO_ETHTOOL_PAM4_SPDS(fw_speeds, lk_ksettings, name)	\
+{									\
+	if ((fw_speeds) & BNXT_LINK_PAM4_SPEED_MSK_50GB)		\
+		ethtool_link_ksettings_add_link_mode(lk_ksettings, name,\
+						     50000baseCR_Full);	\
+	if ((fw_speeds) & BNXT_LINK_PAM4_SPEED_MSK_100GB)		\
+		ethtool_link_ksettings_add_link_mode(lk_ksettings, name,\
+						     100000baseCR2_Full);\
+	if ((fw_speeds) & BNXT_LINK_PAM4_SPEED_MSK_200GB)		\
+		ethtool_link_ksettings_add_link_mode(lk_ksettings, name,\
+						     200000baseCR4_Full);\
+}
+
+#define BNXT_ETHTOOL_TO_FW_PAM4_SPDS(fw_speeds, lk_ksettings, name)	\
+{									\
+	if (ethtool_link_ksettings_test_link_mode(lk_ksettings, name,	\
+						  50000baseCR_Full))	\
+		(fw_speeds) |= BNXT_LINK_PAM4_SPEED_MSK_50GB;		\
+	if (ethtool_link_ksettings_test_link_mode(lk_ksettings, name,	\
+						  100000baseCR2_Full))	\
+		(fw_speeds) |= BNXT_LINK_PAM4_SPEED_MSK_100GB;		\
+	if (ethtool_link_ksettings_test_link_mode(lk_ksettings, name,	\
+						  200000baseCR4_Full))	\
+		(fw_speeds) |= BNXT_LINK_PAM4_SPEED_MSK_200GB;		\
+}
+
+static void bnxt_fw_to_ethtool_advertised_fec(struct bnxt_link_info *link_info,
+				struct ethtool_link_ksettings *lk_ksettings)
+{
+	u16 fec_cfg = link_info->fec_cfg;
+
+	if ((fec_cfg & BNXT_FEC_NONE) || !(fec_cfg & BNXT_FEC_AUTONEG)) {
+		linkmode_set_bit(ETHTOOL_LINK_MODE_FEC_NONE_BIT,
+				 lk_ksettings->link_modes.advertising);
+		return;
+	}
+	if (fec_cfg & BNXT_FEC_ENC_BASE_R)
+		linkmode_set_bit(ETHTOOL_LINK_MODE_FEC_BASER_BIT,
+				 lk_ksettings->link_modes.advertising);
+	if (fec_cfg & BNXT_FEC_ENC_RS)
+		linkmode_set_bit(ETHTOOL_LINK_MODE_FEC_RS_BIT,
+				 lk_ksettings->link_modes.advertising);
+	if (fec_cfg & BNXT_FEC_ENC_LLRS)
+		linkmode_set_bit(ETHTOOL_LINK_MODE_FEC_LLRS_BIT,
+				 lk_ksettings->link_modes.advertising);
+}
+
 static void bnxt_fw_to_ethtool_advertised_spds(struct bnxt_link_info *link_info,
 				struct ethtool_link_ksettings *lk_ksettings)
 {
@@ -1510,6 +1570,9 @@ static void bnxt_fw_to_ethtool_advertised_spds(struct bnxt_link_info *link_info,
 		fw_pause = link_info->auto_pause_setting;
 
 	BNXT_FW_TO_ETHTOOL_SPDS(fw_speeds, fw_pause, lk_ksettings, advertising);
+	fw_speeds = link_info->advertising_pam4;
+	BNXT_FW_TO_ETHTOOL_PAM4_SPDS(fw_speeds, lk_ksettings, advertising);
+	bnxt_fw_to_ethtool_advertised_fec(link_info, lk_ksettings);
 }
 
 static void bnxt_fw_to_ethtool_lp_adv(struct bnxt_link_info *link_info,
@@ -1523,6 +1586,29 @@ static void bnxt_fw_to_ethtool_lp_adv(struct bnxt_link_info *link_info,
 
 	BNXT_FW_TO_ETHTOOL_SPDS(fw_speeds, fw_pause, lk_ksettings,
 				lp_advertising);
+	fw_speeds = link_info->lp_auto_pam4_link_speeds;
+	BNXT_FW_TO_ETHTOOL_PAM4_SPDS(fw_speeds, lk_ksettings, lp_advertising);
+}
+
+static void bnxt_fw_to_ethtool_support_fec(struct bnxt_link_info *link_info,
+				struct ethtool_link_ksettings *lk_ksettings)
+{
+	u16 fec_cfg = link_info->fec_cfg;
+
+	if (fec_cfg & BNXT_FEC_NONE) {
+		linkmode_set_bit(ETHTOOL_LINK_MODE_FEC_NONE_BIT,
+				 lk_ksettings->link_modes.supported);
+		return;
+	}
+	if (fec_cfg & BNXT_FEC_ENC_BASE_R_CAP)
+		linkmode_set_bit(ETHTOOL_LINK_MODE_FEC_BASER_BIT,
+				 lk_ksettings->link_modes.supported);
+	if (fec_cfg & BNXT_FEC_ENC_RS_CAP)
+		linkmode_set_bit(ETHTOOL_LINK_MODE_FEC_RS_BIT,
+				 lk_ksettings->link_modes.supported);
+	if (fec_cfg & BNXT_FEC_ENC_LLRS_CAP)
+		linkmode_set_bit(ETHTOOL_LINK_MODE_FEC_LLRS_BIT,
+				 lk_ksettings->link_modes.supported);
 }
 
 static void bnxt_fw_to_ethtool_support_spds(struct bnxt_link_info *link_info,
@@ -1531,14 +1617,18 @@ static void bnxt_fw_to_ethtool_support_spds(struct bnxt_link_info *link_info,
 	u16 fw_speeds = link_info->support_speeds;
 
 	BNXT_FW_TO_ETHTOOL_SPDS(fw_speeds, 0, lk_ksettings, supported);
+	fw_speeds = link_info->support_pam4_speeds;
+	BNXT_FW_TO_ETHTOOL_PAM4_SPDS(fw_speeds, lk_ksettings, supported);
 
 	ethtool_link_ksettings_add_link_mode(lk_ksettings, supported, Pause);
 	ethtool_link_ksettings_add_link_mode(lk_ksettings, supported,
 					     Asym_Pause);
 
-	if (link_info->support_auto_speeds)
+	if (link_info->support_auto_speeds ||
+	    link_info->support_pam4_auto_speeds)
 		ethtool_link_ksettings_add_link_mode(lk_ksettings, supported,
 						     Autoneg);
+	bnxt_fw_to_ethtool_support_fec(link_info, lk_ksettings);
 }
 
 u32 bnxt_fw_to_ethtool_speed(u16 fw_link_speed)
@@ -1629,55 +1719,86 @@ static int bnxt_get_link_ksettings(struct net_device *dev,
 	return 0;
 }
 
-static u32 bnxt_get_fw_speed(struct net_device *dev, u32 ethtool_speed)
+static int bnxt_force_link_speed(struct net_device *dev, u32 ethtool_speed)
 {
 	struct bnxt *bp = netdev_priv(dev);
 	struct bnxt_link_info *link_info = &bp->link_info;
+	u16 support_pam4_spds = link_info->support_pam4_speeds;
 	u16 support_spds = link_info->support_speeds;
-	u32 fw_speed = 0;
+	u8 sig_mode = BNXT_SIG_MODE_NRZ;
+	u16 fw_speed = 0;
 
 	switch (ethtool_speed) {
 	case SPEED_100:
 		if (support_spds & BNXT_LINK_SPEED_MSK_100MB)
-			fw_speed = PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_100MB;
+			fw_speed = PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_100MB;
 		break;
 	case SPEED_1000:
 		if (support_spds & BNXT_LINK_SPEED_MSK_1GB)
-			fw_speed = PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_1GB;
+			fw_speed = PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_1GB;
 		break;
 	case SPEED_2500:
 		if (support_spds & BNXT_LINK_SPEED_MSK_2_5GB)
-			fw_speed = PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_2_5GB;
+			fw_speed = PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_2_5GB;
 		break;
 	case SPEED_10000:
 		if (support_spds & BNXT_LINK_SPEED_MSK_10GB)
-			fw_speed = PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_10GB;
+			fw_speed = PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_10GB;
 		break;
 	case SPEED_20000:
 		if (support_spds & BNXT_LINK_SPEED_MSK_20GB)
-			fw_speed = PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_20GB;
+			fw_speed = PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_20GB;
 		break;
 	case SPEED_25000:
 		if (support_spds & BNXT_LINK_SPEED_MSK_25GB)
-			fw_speed = PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_25GB;
+			fw_speed = PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_25GB;
 		break;
 	case SPEED_40000:
 		if (support_spds & BNXT_LINK_SPEED_MSK_40GB)
-			fw_speed = PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_40GB;
+			fw_speed = PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_40GB;
 		break;
 	case SPEED_50000:
-		if (support_spds & BNXT_LINK_SPEED_MSK_50GB)
-			fw_speed = PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_50GB;
+		if (support_spds & BNXT_LINK_SPEED_MSK_50GB) {
+			fw_speed = PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_50GB;
+		} else if (support_pam4_spds & BNXT_LINK_PAM4_SPEED_MSK_50GB) {
+			fw_speed = PORT_PHY_CFG_REQ_FORCE_PAM4_LINK_SPEED_50GB;
+			sig_mode = BNXT_SIG_MODE_PAM4;
+		}
 		break;
 	case SPEED_100000:
-		if (support_spds & BNXT_LINK_SPEED_MSK_100GB)
-			fw_speed = PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_100GB;
+		if (support_spds & BNXT_LINK_SPEED_MSK_100GB) {
+			fw_speed = PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_100GB;
+		} else if (support_pam4_spds & BNXT_LINK_PAM4_SPEED_MSK_100GB) {
+			fw_speed = PORT_PHY_CFG_REQ_FORCE_PAM4_LINK_SPEED_100GB;
+			sig_mode = BNXT_SIG_MODE_PAM4;
+		}
 		break;
-	default:
-		netdev_err(dev, "unsupported speed!\n");
+	case SPEED_200000:
+		if (support_pam4_spds & BNXT_LINK_PAM4_SPEED_MSK_200GB) {
+			fw_speed = PORT_PHY_CFG_REQ_FORCE_PAM4_LINK_SPEED_200GB;
+			sig_mode = BNXT_SIG_MODE_PAM4;
+		}
 		break;
 	}
-	return fw_speed;
+
+	if (!fw_speed) {
+		netdev_err(dev, "unsupported speed!\n");
+		return -EINVAL;
+	}
+
+	if (link_info->req_link_speed == fw_speed &&
+	    link_info->req_signal_mode == sig_mode &&
+	    link_info->autoneg == 0)
+		return -EALREADY;
+
+	link_info->req_link_speed = fw_speed;
+	link_info->req_signal_mode = sig_mode;
+	link_info->req_duplex = BNXT_LINK_DUPLEX_FULL;
+	link_info->autoneg = 0;
+	link_info->advertising = 0;
+	link_info->advertising_pam4 = 0;
+
+	return 0;
 }
 
 u16 bnxt_get_fw_auto_link_speeds(u32 advertising)
@@ -1709,7 +1830,6 @@ static int bnxt_set_link_ksettings(struct net_device *dev,
 	struct bnxt_link_info *link_info = &bp->link_info;
 	const struct ethtool_link_settings *base = &lk_ksettings->base;
 	bool set_pause = false;
-	u16 fw_advertising = 0;
 	u32 speed;
 	int rc = 0;
 
@@ -1718,19 +1838,23 @@ static int bnxt_set_link_ksettings(struct net_device *dev,
 
 	mutex_lock(&bp->link_lock);
 	if (base->autoneg == AUTONEG_ENABLE) {
-		BNXT_ETHTOOL_TO_FW_SPDS(fw_advertising, lk_ksettings,
+		link_info->advertising = 0;
+		link_info->advertising_pam4 = 0;
+		BNXT_ETHTOOL_TO_FW_SPDS(link_info->advertising, lk_ksettings,
 					advertising);
+		BNXT_ETHTOOL_TO_FW_PAM4_SPDS(link_info->advertising_pam4,
+					     lk_ksettings, advertising);
 		link_info->autoneg |= BNXT_AUTONEG_SPEED;
-		if (!fw_advertising)
+		if (!link_info->advertising && !link_info->advertising_pam4) {
 			link_info->advertising = link_info->support_auto_speeds;
-		else
-			link_info->advertising = fw_advertising;
+			link_info->advertising_pam4 =
+				link_info->support_pam4_auto_speeds;
+		}
 		/* any change to autoneg will cause link change, therefore the
 		 * driver should put back the original pause setting in autoneg
 		 */
 		set_pause = true;
 	} else {
-		u16 fw_speed;
 		u8 phy_type = link_info->phy_type;
 
 		if (phy_type == PORT_PHY_QCFG_RESP_PHY_TYPE_BASET  ||
@@ -1746,15 +1870,12 @@ static int bnxt_set_link_ksettings(struct net_device *dev,
 			goto set_setting_exit;
 		}
 		speed = base->speed;
-		fw_speed = bnxt_get_fw_speed(dev, speed);
-		if (!fw_speed) {
-			rc = -EINVAL;
+		rc = bnxt_force_link_speed(dev, speed);
+		if (rc) {
+			if (rc == -EALREADY)
+				rc = 0;
 			goto set_setting_exit;
 		}
-		link_info->req_link_speed = fw_speed;
-		link_info->req_duplex = BNXT_LINK_DUPLEX_FULL;
-		link_info->autoneg = 0;
-		link_info->advertising = 0;
 	}
 
 	if (netif_running(dev))
@@ -1765,6 +1886,110 @@ set_setting_exit:
 	return rc;
 }
 
+static int bnxt_get_fecparam(struct net_device *dev,
+			     struct ethtool_fecparam *fec)
+{
+	struct bnxt *bp = netdev_priv(dev);
+	struct bnxt_link_info *link_info;
+	u8 active_fec;
+	u16 fec_cfg;
+
+	link_info = &bp->link_info;
+	fec_cfg = link_info->fec_cfg;
+	active_fec = link_info->active_fec_sig_mode &
+		     PORT_PHY_QCFG_RESP_ACTIVE_FEC_MASK;
+	if (fec_cfg & BNXT_FEC_NONE) {
+		fec->fec = ETHTOOL_FEC_NONE;
+		fec->active_fec = ETHTOOL_FEC_NONE;
+		return 0;
+	}
+	if (fec_cfg & BNXT_FEC_AUTONEG)
+		fec->fec |= ETHTOOL_FEC_AUTO;
+	if (fec_cfg & BNXT_FEC_ENC_BASE_R)
+		fec->fec |= ETHTOOL_FEC_BASER;
+	if (fec_cfg & BNXT_FEC_ENC_RS)
+		fec->fec |= ETHTOOL_FEC_RS;
+	if (fec_cfg & BNXT_FEC_ENC_LLRS)
+		fec->fec |= ETHTOOL_FEC_LLRS;
+
+	switch (active_fec) {
+	case PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_CLAUSE74_ACTIVE:
+		fec->active_fec |= ETHTOOL_FEC_BASER;
+		break;
+	case PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_CLAUSE91_ACTIVE:
+	case PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_RS544_1XN_ACTIVE:
+	case PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_RS544_IEEE_ACTIVE:
+		fec->active_fec |= ETHTOOL_FEC_RS;
+		break;
+	case PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_RS272_1XN_ACTIVE:
+	case PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_RS272_IEEE_ACTIVE:
+		fec->active_fec |= ETHTOOL_FEC_LLRS;
+		break;
+	}
+	return 0;
+}
+
+static u32 bnxt_ethtool_forced_fec_to_fw(struct bnxt_link_info *link_info,
+					 u32 fec)
+{
+	u32 fw_fec = PORT_PHY_CFG_REQ_FLAGS_FEC_AUTONEG_DISABLE;
+
+	if (fec & ETHTOOL_FEC_BASER)
+		fw_fec |= BNXT_FEC_BASE_R_ON(link_info);
+	else if (fec & ETHTOOL_FEC_RS)
+		fw_fec |= BNXT_FEC_RS_ON(link_info);
+	else if (fec & ETHTOOL_FEC_LLRS)
+		fw_fec |= BNXT_FEC_LLRS_ON;
+	return fw_fec;
+}
+
+static int bnxt_set_fecparam(struct net_device *dev,
+			     struct ethtool_fecparam *fecparam)
+{
+	struct hwrm_port_phy_cfg_input req = {0};
+	struct bnxt *bp = netdev_priv(dev);
+	struct bnxt_link_info *link_info;
+	u32 new_cfg, fec = fecparam->fec;
+	u16 fec_cfg;
+	int rc;
+
+	link_info = &bp->link_info;
+	fec_cfg = link_info->fec_cfg;
+	if (fec_cfg & BNXT_FEC_NONE)
+		return -EOPNOTSUPP;
+
+	if (fec & ETHTOOL_FEC_OFF) {
+		new_cfg = PORT_PHY_CFG_REQ_FLAGS_FEC_AUTONEG_DISABLE |
+			  BNXT_FEC_ALL_OFF(link_info);
+		goto apply_fec;
+	}
+	if (((fec & ETHTOOL_FEC_AUTO) && !(fec_cfg & BNXT_FEC_AUTONEG_CAP)) ||
+	    ((fec & ETHTOOL_FEC_RS) && !(fec_cfg & BNXT_FEC_ENC_RS_CAP)) ||
+	    ((fec & ETHTOOL_FEC_LLRS) && !(fec_cfg & BNXT_FEC_ENC_LLRS_CAP)) ||
+	    ((fec & ETHTOOL_FEC_BASER) && !(fec_cfg & BNXT_FEC_ENC_BASE_R_CAP)))
+		return -EINVAL;
+
+	if (fec & ETHTOOL_FEC_AUTO) {
+		if (!link_info->autoneg)
+			return -EINVAL;
+		new_cfg = PORT_PHY_CFG_REQ_FLAGS_FEC_AUTONEG_ENABLE;
+	} else {
+		new_cfg = bnxt_ethtool_forced_fec_to_fw(link_info, fec);
+	}
+
+apply_fec:
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_PORT_PHY_CFG, -1, -1);
+	req.flags = cpu_to_le32(new_cfg | PORT_PHY_CFG_REQ_FLAGS_RESET_PHY);
+	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	/* update current settings */
+	if (!rc) {
+		mutex_lock(&bp->link_lock);
+		bnxt_update_link(bp, false);
+		mutex_unlock(&bp->link_lock);
+	}
+	return rc;
+}
+
 static void bnxt_get_pauseparam(struct net_device *dev,
 				struct ethtool_pauseparam *epause)
 {
@@ -1804,9 +2029,12 @@ static int bnxt_set_pauseparam(struct net_device *dev,
 	if (!BNXT_PHY_CFG_ABLE(bp))
 		return -EOPNOTSUPP;
 
+	mutex_lock(&bp->link_lock);
 	if (epause->autoneg) {
-		if (!(link_info->autoneg & BNXT_AUTONEG_SPEED))
-			return -EINVAL;
+		if (!(link_info->autoneg & BNXT_AUTONEG_SPEED)) {
+			rc = -EINVAL;
+			goto pause_exit;
+		}
 
 		link_info->autoneg |= BNXT_AUTONEG_FLOW_CTRL;
 		if (bp->hwrm_spec_code >= 0x10201)
@@ -1827,11 +2055,11 @@ static int bnxt_set_pauseparam(struct net_device *dev,
 	if (epause->tx_pause)
 		link_info->req_flow_ctrl |= BNXT_LINK_PAUSE_TX;
 
-	if (netif_running(dev)) {
-		mutex_lock(&bp->link_lock);
+	if (netif_running(dev))
 		rc = bnxt_hwrm_set_pause(bp);
-		mutex_unlock(&bp->link_lock);
-	}
+
+pause_exit:
+	mutex_unlock(&bp->link_lock);
 	return rc;
 }
 
@@ -2568,8 +2796,7 @@ static int bnxt_set_eee(struct net_device *dev, struct ethtool_eee *edata)
 	struct bnxt *bp = netdev_priv(dev);
 	struct ethtool_eee *eee = &bp->eee;
 	struct bnxt_link_info *link_info = &bp->link_info;
-	u32 advertising =
-		 _bnxt_fw_to_ethtool_adv_spds(link_info->advertising, 0);
+	u32 advertising;
 	int rc = 0;
 
 	if (!BNXT_PHY_CFG_ABLE(bp))
@@ -2578,19 +2805,23 @@ static int bnxt_set_eee(struct net_device *dev, struct ethtool_eee *edata)
 	if (!(bp->flags & BNXT_FLAG_EEE_CAP))
 		return -EOPNOTSUPP;
 
+	mutex_lock(&bp->link_lock);
+	advertising = _bnxt_fw_to_ethtool_adv_spds(link_info->advertising, 0);
 	if (!edata->eee_enabled)
 		goto eee_ok;
 
 	if (!(link_info->autoneg & BNXT_AUTONEG_SPEED)) {
 		netdev_warn(dev, "EEE requires autoneg\n");
-		return -EINVAL;
+		rc = -EINVAL;
+		goto eee_exit;
 	}
 	if (edata->tx_lpi_enabled) {
 		if (bp->lpi_tmr_hi && (edata->tx_lpi_timer > bp->lpi_tmr_hi ||
 				       edata->tx_lpi_timer < bp->lpi_tmr_lo)) {
 			netdev_warn(dev, "Valid LPI timer range is %d and %d microsecs\n",
 				    bp->lpi_tmr_lo, bp->lpi_tmr_hi);
-			return -EINVAL;
+			rc = -EINVAL;
+			goto eee_exit;
 		} else if (!bp->lpi_tmr_hi) {
 			edata->tx_lpi_timer = eee->tx_lpi_timer;
 		}
@@ -2600,7 +2831,8 @@ static int bnxt_set_eee(struct net_device *dev, struct ethtool_eee *edata)
 	} else if (edata->advertised & ~advertising) {
 		netdev_warn(dev, "EEE advertised %x must be a subset of autoneg advertised speeds %x\n",
 			    edata->advertised, advertising);
-		return -EINVAL;
+		rc = -EINVAL;
+		goto eee_exit;
 	}
 
 	eee->advertised = edata->advertised;
@@ -2612,6 +2844,8 @@ eee_ok:
 	if (netif_running(dev))
 		rc = bnxt_hwrm_set_link_setting(bp, false, true);
 
+eee_exit:
+	mutex_unlock(&bp->link_lock);
 	return rc;
 }
 
@@ -3661,6 +3895,8 @@ const struct ethtool_ops bnxt_ethtool_ops = {
 				     ETHTOOL_COALESCE_USE_ADAPTIVE_RX,
 	.get_link_ksettings	= bnxt_get_link_ksettings,
 	.set_link_ksettings	= bnxt_set_link_ksettings,
+	.get_fecparam		= bnxt_get_fecparam,
+	.set_fecparam		= bnxt_set_fecparam,
 	.get_pause_stats	= bnxt_get_pause_stats,
 	.get_pauseparam		= bnxt_get_pauseparam,
 	.set_pauseparam		= bnxt_set_pauseparam,
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
index c4af6bf15e36..303713aa03b0 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
@@ -213,7 +213,10 @@ struct cmd_nums {
 	#define HWRM_PORT_PHY_MDIO_BUS_ACQUIRE            0xb7UL
 	#define HWRM_PORT_PHY_MDIO_BUS_RELEASE            0xb8UL
 	#define HWRM_PORT_QSTATS_EXT_PFC_WD               0xb9UL
-	#define HWRM_PORT_ECN_QSTATS                      0xbaUL
+	#define HWRM_RESERVED7                            0xbaUL
+	#define HWRM_PORT_TX_FIR_CFG                      0xbbUL
+	#define HWRM_PORT_TX_FIR_QCFG                     0xbcUL
+	#define HWRM_PORT_ECN_QSTATS                      0xbdUL
 	#define HWRM_FW_RESET                             0xc0UL
 	#define HWRM_FW_QSTATUS                           0xc1UL
 	#define HWRM_FW_HEALTH_CHECK                      0xc2UL
@@ -370,6 +373,8 @@ struct cmd_nums {
 	#define HWRM_TF_SESSION_RESC_FLUSH                0x2cfUL
 	#define HWRM_TF_TBL_TYPE_GET                      0x2daUL
 	#define HWRM_TF_TBL_TYPE_SET                      0x2dbUL
+	#define HWRM_TF_CTXT_MEM_ALLOC                    0x2e2UL
+	#define HWRM_TF_CTXT_MEM_FREE                     0x2e3UL
 	#define HWRM_TF_CTXT_MEM_RGTR                     0x2e4UL
 	#define HWRM_TF_CTXT_MEM_UNRGTR                   0x2e5UL
 	#define HWRM_TF_EXT_EM_QCAPS                      0x2e6UL
@@ -384,6 +389,8 @@ struct cmd_nums {
 	#define HWRM_TF_TCAM_FREE                         0x2fbUL
 	#define HWRM_TF_GLOBAL_CFG_SET                    0x2fcUL
 	#define HWRM_TF_GLOBAL_CFG_GET                    0x2fdUL
+	#define HWRM_TF_IF_TBL_SET                        0x2feUL
+	#define HWRM_TF_IF_TBL_GET                        0x2ffUL
 	#define HWRM_SV                                   0x400UL
 	#define HWRM_DBG_READ_DIRECT                      0xff10UL
 	#define HWRM_DBG_READ_INDIRECT                    0xff11UL
@@ -447,6 +454,7 @@ struct ret_codes {
 	#define HWRM_ERR_CODE_KEY_ALREADY_EXISTS           0xeUL
 	#define HWRM_ERR_CODE_HWRM_ERROR                   0xfUL
 	#define HWRM_ERR_CODE_BUSY                         0x10UL
+	#define HWRM_ERR_CODE_RESOURCE_LOCKED              0x11UL
 	#define HWRM_ERR_CODE_TLV_ENCAPSULATED_RESPONSE    0x8000UL
 	#define HWRM_ERR_CODE_UNKNOWN_ERR                  0xfffeUL
 	#define HWRM_ERR_CODE_CMD_NOT_SUPPORTED            0xffffUL
@@ -478,8 +486,8 @@ struct hwrm_err_output {
 #define HWRM_VERSION_MAJOR 1
 #define HWRM_VERSION_MINOR 10
 #define HWRM_VERSION_UPDATE 1
-#define HWRM_VERSION_RSVD 54
-#define HWRM_VERSION_STR "1.10.1.54"
+#define HWRM_VERSION_RSVD 65
+#define HWRM_VERSION_STR "1.10.1.65"
 
 /* hwrm_ver_get_input (size:192b/24B) */
 struct hwrm_ver_get_input {
@@ -675,6 +683,7 @@ struct hwrm_async_event_cmpl {
 	#define ASYNC_EVENT_CMPL_EVENT_ID_PORT_PHY_CFG_CHANGE        0x7UL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_RESET_NOTIFY               0x8UL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_ERROR_RECOVERY             0x9UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_RING_MONITOR_MSG           0xaUL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_FUNC_DRVR_UNLOAD           0x10UL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_FUNC_DRVR_LOAD             0x11UL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_FUNC_FLR_PROC_CMPLT        0x12UL
@@ -851,6 +860,32 @@ struct hwrm_async_event_cmpl_error_recovery {
 	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_DATA1_FLAGS_RECOVERY_ENABLED      0x2UL
 };
 
+/* hwrm_async_event_cmpl_ring_monitor_msg (size:128b/16B) */
+struct hwrm_async_event_cmpl_ring_monitor_msg {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_TYPE_LAST             ASYNC_EVENT_CMPL_RING_MONITOR_MSG_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_EVENT_ID_RING_MONITOR_MSG 0xaUL
+	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_EVENT_ID_LAST            ASYNC_EVENT_CMPL_RING_MONITOR_MSG_EVENT_ID_RING_MONITOR_MSG
+	__le32	event_data2;
+	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_EVENT_DATA2_DISABLE_RING_TYPE_MASK 0xffUL
+	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_EVENT_DATA2_DISABLE_RING_TYPE_SFT 0
+	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_EVENT_DATA2_DISABLE_RING_TYPE_TX    0x0UL
+	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_EVENT_DATA2_DISABLE_RING_TYPE_RX    0x1UL
+	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_EVENT_DATA2_DISABLE_RING_TYPE_CMPL  0x2UL
+	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_EVENT_DATA2_DISABLE_RING_TYPE_LAST ASYNC_EVENT_CMPL_RING_MONITOR_MSG_EVENT_DATA2_DISABLE_RING_TYPE_CMPL
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_V          0x1UL
+	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+};
+
 /* hwrm_async_event_cmpl_vf_cfg_change (size:128b/16B) */
 struct hwrm_async_event_cmpl_vf_cfg_change {
 	__le16	type;
@@ -975,6 +1010,28 @@ struct hwrm_async_event_cmpl_eem_cache_flush_done {
 	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_EVENT_DATA1_FID_SFT 0
 };
 
+/* hwrm_async_event_cmpl_deferred_response (size:128b/16B) */
+struct hwrm_async_event_cmpl_deferred_response {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_TYPE_LAST             ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_EVENT_ID_DEFERRED_RESPONSE 0x40UL
+	#define ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_EVENT_ID_LAST             ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_EVENT_ID_DEFERRED_RESPONSE
+	__le32	event_data2;
+	#define ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_EVENT_DATA2_SEQ_ID_MASK 0xffffUL
+	#define ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_EVENT_DATA2_SEQ_ID_SFT 0
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_V          0x1UL
+	#define ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+};
+
 /* hwrm_func_reset_input (size:192b/24B) */
 struct hwrm_func_reset_input {
 	__le16	req_type;
@@ -1214,7 +1271,13 @@ struct hwrm_func_qcaps_output {
 	#define FUNC_QCAPS_RESP_FLAGS_EXT_SCHQ_SUPPORTED                         0x40UL
 	#define FUNC_QCAPS_RESP_FLAGS_EXT_PPP_PUSH_MODE_SUPPORTED                0x80UL
 	u8	max_schqs;
-	u8	unused_1[2];
+	u8	mpc_chnls_cap;
+	#define FUNC_QCAPS_RESP_MPC_CHNLS_CAP_TCE         0x1UL
+	#define FUNC_QCAPS_RESP_MPC_CHNLS_CAP_RCE         0x2UL
+	#define FUNC_QCAPS_RESP_MPC_CHNLS_CAP_TE_CFA      0x4UL
+	#define FUNC_QCAPS_RESP_MPC_CHNLS_CAP_RE_CFA      0x8UL
+	#define FUNC_QCAPS_RESP_MPC_CHNLS_CAP_PRIMATE     0x10UL
+	u8	unused_1;
 	u8	valid;
 };
 
@@ -1250,6 +1313,7 @@ struct hwrm_func_qcfg_output {
 	#define FUNC_QCFG_RESP_FLAGS_PREBOOT_LEGACY_L2_RINGS      0x100UL
 	#define FUNC_QCFG_RESP_FLAGS_HOT_RESET_ALLOWED            0x200UL
 	#define FUNC_QCFG_RESP_FLAGS_PPP_PUSH_MODE_ENABLED        0x400UL
+	#define FUNC_QCFG_RESP_FLAGS_RING_MONITOR_ENABLED         0x800UL
 	u8	mac_address[6];
 	__le16	pci_id;
 	__le16	alloc_rsscos_ctx;
@@ -1341,7 +1405,13 @@ struct hwrm_func_qcfg_output {
 	#define FUNC_QCFG_RESP_SVIF_INFO_SVIF_MASK      0x7fffUL
 	#define FUNC_QCFG_RESP_SVIF_INFO_SVIF_SFT       0
 	#define FUNC_QCFG_RESP_SVIF_INFO_SVIF_VALID     0x8000UL
-	u8	unused_2[7];
+	u8	mpc_chnls;
+	#define FUNC_QCFG_RESP_MPC_CHNLS_TCE_ENABLED         0x1UL
+	#define FUNC_QCFG_RESP_MPC_CHNLS_RCE_ENABLED         0x2UL
+	#define FUNC_QCFG_RESP_MPC_CHNLS_TE_CFA_ENABLED      0x4UL
+	#define FUNC_QCFG_RESP_MPC_CHNLS_RE_CFA_ENABLED      0x8UL
+	#define FUNC_QCFG_RESP_MPC_CHNLS_PRIMATE_ENABLED     0x10UL
+	u8	unused_2[6];
 	u8	valid;
 };
 
@@ -1405,6 +1475,7 @@ struct hwrm_func_cfg_input {
 	#define FUNC_CFG_REQ_ENABLES_ADMIN_LINK_STATE         0x400000UL
 	#define FUNC_CFG_REQ_ENABLES_HOT_RESET_IF_SUPPORT     0x800000UL
 	#define FUNC_CFG_REQ_ENABLES_SCHQ_ID                  0x1000000UL
+	#define FUNC_CFG_REQ_ENABLES_MPC_CHNLS                0x2000000UL
 	__le16	mtu;
 	__le16	mru;
 	__le16	num_rsscos_ctxs;
@@ -1479,7 +1550,18 @@ struct hwrm_func_cfg_input {
 	#define FUNC_CFG_REQ_OPTIONS_RSVD_SFT                    4
 	__le16	num_mcast_filters;
 	__le16	schq_id;
-	u8	unused_0[6];
+	__le16	mpc_chnls;
+	#define FUNC_CFG_REQ_MPC_CHNLS_TCE_ENABLE          0x1UL
+	#define FUNC_CFG_REQ_MPC_CHNLS_TCE_DISABLE         0x2UL
+	#define FUNC_CFG_REQ_MPC_CHNLS_RCE_ENABLE          0x4UL
+	#define FUNC_CFG_REQ_MPC_CHNLS_RCE_DISABLE         0x8UL
+	#define FUNC_CFG_REQ_MPC_CHNLS_TE_CFA_ENABLE       0x10UL
+	#define FUNC_CFG_REQ_MPC_CHNLS_TE_CFA_DISABLE      0x20UL
+	#define FUNC_CFG_REQ_MPC_CHNLS_RE_CFA_ENABLE       0x40UL
+	#define FUNC_CFG_REQ_MPC_CHNLS_RE_CFA_DISABLE      0x80UL
+	#define FUNC_CFG_REQ_MPC_CHNLS_PRIMATE_ENABLE      0x100UL
+	#define FUNC_CFG_REQ_MPC_CHNLS_PRIMATE_DISABLE     0x200UL
+	u8	unused_0[4];
 };
 
 /* hwrm_func_cfg_output (size:128b/16B) */
@@ -1559,7 +1641,7 @@ struct hwrm_func_qstats_ext_input {
 	u8	unused_1[4];
 };
 
-/* hwrm_func_qstats_ext_output (size:1472b/184B) */
+/* hwrm_func_qstats_ext_output (size:1536b/192B) */
 struct hwrm_func_qstats_ext_output {
 	__le16	error_code;
 	__le16	req_type;
@@ -1586,6 +1668,7 @@ struct hwrm_func_qstats_ext_output {
 	__le64	rx_tpa_pkt;
 	__le64	rx_tpa_bytes;
 	__le64	rx_tpa_errors;
+	__le64	rx_tpa_events;
 	u8	unused_0[7];
 	u8	valid;
 };
@@ -2412,25 +2495,29 @@ struct hwrm_port_phy_cfg_input {
 	__le16	target_id;
 	__le64	resp_addr;
 	__le32	flags;
-	#define PORT_PHY_CFG_REQ_FLAGS_RESET_PHY                 0x1UL
-	#define PORT_PHY_CFG_REQ_FLAGS_DEPRECATED                0x2UL
-	#define PORT_PHY_CFG_REQ_FLAGS_FORCE                     0x4UL
-	#define PORT_PHY_CFG_REQ_FLAGS_RESTART_AUTONEG           0x8UL
-	#define PORT_PHY_CFG_REQ_FLAGS_EEE_ENABLE                0x10UL
-	#define PORT_PHY_CFG_REQ_FLAGS_EEE_DISABLE               0x20UL
-	#define PORT_PHY_CFG_REQ_FLAGS_EEE_TX_LPI_ENABLE         0x40UL
-	#define PORT_PHY_CFG_REQ_FLAGS_EEE_TX_LPI_DISABLE        0x80UL
-	#define PORT_PHY_CFG_REQ_FLAGS_FEC_AUTONEG_ENABLE        0x100UL
-	#define PORT_PHY_CFG_REQ_FLAGS_FEC_AUTONEG_DISABLE       0x200UL
-	#define PORT_PHY_CFG_REQ_FLAGS_FEC_CLAUSE74_ENABLE       0x400UL
-	#define PORT_PHY_CFG_REQ_FLAGS_FEC_CLAUSE74_DISABLE      0x800UL
-	#define PORT_PHY_CFG_REQ_FLAGS_FEC_CLAUSE91_ENABLE       0x1000UL
-	#define PORT_PHY_CFG_REQ_FLAGS_FEC_CLAUSE91_DISABLE      0x2000UL
-	#define PORT_PHY_CFG_REQ_FLAGS_FORCE_LINK_DWN            0x4000UL
-	#define PORT_PHY_CFG_REQ_FLAGS_FEC_RS544_1XN_ENABLE      0x8000UL
-	#define PORT_PHY_CFG_REQ_FLAGS_FEC_RS544_1XN_DISABLE     0x10000UL
-	#define PORT_PHY_CFG_REQ_FLAGS_FEC_RS544_2XN_ENABLE      0x20000UL
-	#define PORT_PHY_CFG_REQ_FLAGS_FEC_RS544_2XN_DISABLE     0x40000UL
+	#define PORT_PHY_CFG_REQ_FLAGS_RESET_PHY                  0x1UL
+	#define PORT_PHY_CFG_REQ_FLAGS_DEPRECATED                 0x2UL
+	#define PORT_PHY_CFG_REQ_FLAGS_FORCE                      0x4UL
+	#define PORT_PHY_CFG_REQ_FLAGS_RESTART_AUTONEG            0x8UL
+	#define PORT_PHY_CFG_REQ_FLAGS_EEE_ENABLE                 0x10UL
+	#define PORT_PHY_CFG_REQ_FLAGS_EEE_DISABLE                0x20UL
+	#define PORT_PHY_CFG_REQ_FLAGS_EEE_TX_LPI_ENABLE          0x40UL
+	#define PORT_PHY_CFG_REQ_FLAGS_EEE_TX_LPI_DISABLE         0x80UL
+	#define PORT_PHY_CFG_REQ_FLAGS_FEC_AUTONEG_ENABLE         0x100UL
+	#define PORT_PHY_CFG_REQ_FLAGS_FEC_AUTONEG_DISABLE        0x200UL
+	#define PORT_PHY_CFG_REQ_FLAGS_FEC_CLAUSE74_ENABLE        0x400UL
+	#define PORT_PHY_CFG_REQ_FLAGS_FEC_CLAUSE74_DISABLE       0x800UL
+	#define PORT_PHY_CFG_REQ_FLAGS_FEC_CLAUSE91_ENABLE        0x1000UL
+	#define PORT_PHY_CFG_REQ_FLAGS_FEC_CLAUSE91_DISABLE       0x2000UL
+	#define PORT_PHY_CFG_REQ_FLAGS_FORCE_LINK_DWN             0x4000UL
+	#define PORT_PHY_CFG_REQ_FLAGS_FEC_RS544_1XN_ENABLE       0x8000UL
+	#define PORT_PHY_CFG_REQ_FLAGS_FEC_RS544_1XN_DISABLE      0x10000UL
+	#define PORT_PHY_CFG_REQ_FLAGS_FEC_RS544_IEEE_ENABLE      0x20000UL
+	#define PORT_PHY_CFG_REQ_FLAGS_FEC_RS544_IEEE_DISABLE     0x40000UL
+	#define PORT_PHY_CFG_REQ_FLAGS_FEC_RS272_1XN_ENABLE       0x80000UL
+	#define PORT_PHY_CFG_REQ_FLAGS_FEC_RS272_1XN_DISABLE      0x100000UL
+	#define PORT_PHY_CFG_REQ_FLAGS_FEC_RS272_IEEE_ENABLE      0x200000UL
+	#define PORT_PHY_CFG_REQ_FLAGS_FEC_RS272_IEEE_DISABLE     0x400000UL
 	__le32	enables;
 	#define PORT_PHY_CFG_REQ_ENABLES_AUTO_MODE                     0x1UL
 	#define PORT_PHY_CFG_REQ_ENABLES_AUTO_DUPLEX                   0x2UL
@@ -2573,7 +2660,7 @@ struct hwrm_port_phy_qcfg_input {
 	u8	unused_0[6];
 };
 
-/* hwrm_port_phy_qcfg_output (size:832b/104B) */
+/* hwrm_port_phy_qcfg_output (size:768b/96B) */
 struct hwrm_port_phy_qcfg_output {
 	__le16	error_code;
 	__le16	req_type;
@@ -2584,10 +2671,22 @@ struct hwrm_port_phy_qcfg_output {
 	#define PORT_PHY_QCFG_RESP_LINK_SIGNAL  0x1UL
 	#define PORT_PHY_QCFG_RESP_LINK_LINK    0x2UL
 	#define PORT_PHY_QCFG_RESP_LINK_LAST   PORT_PHY_QCFG_RESP_LINK_LINK
-	u8	link_signal_mode;
-	#define PORT_PHY_QCFG_RESP_LINK_SIGNAL_MODE_NRZ  0x0UL
-	#define PORT_PHY_QCFG_RESP_LINK_SIGNAL_MODE_PAM4 0x1UL
-	#define PORT_PHY_QCFG_RESP_LINK_SIGNAL_MODE_LAST PORT_PHY_QCFG_RESP_LINK_SIGNAL_MODE_PAM4
+	u8	active_fec_signal_mode;
+	#define PORT_PHY_QCFG_RESP_SIGNAL_MODE_MASK                0xfUL
+	#define PORT_PHY_QCFG_RESP_SIGNAL_MODE_SFT                 0
+	#define PORT_PHY_QCFG_RESP_SIGNAL_MODE_NRZ                   0x0UL
+	#define PORT_PHY_QCFG_RESP_SIGNAL_MODE_PAM4                  0x1UL
+	#define PORT_PHY_QCFG_RESP_SIGNAL_MODE_LAST                 PORT_PHY_QCFG_RESP_SIGNAL_MODE_PAM4
+	#define PORT_PHY_QCFG_RESP_ACTIVE_FEC_MASK                 0xf0UL
+	#define PORT_PHY_QCFG_RESP_ACTIVE_FEC_SFT                  4
+	#define PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_NONE_ACTIVE        (0x0UL << 4)
+	#define PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_CLAUSE74_ACTIVE    (0x1UL << 4)
+	#define PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_CLAUSE91_ACTIVE    (0x2UL << 4)
+	#define PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_RS544_1XN_ACTIVE   (0x3UL << 4)
+	#define PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_RS544_IEEE_ACTIVE  (0x4UL << 4)
+	#define PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_RS272_1XN_ACTIVE   (0x5UL << 4)
+	#define PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_RS272_IEEE_ACTIVE  (0x6UL << 4)
+	#define PORT_PHY_QCFG_RESP_ACTIVE_FEC_LAST                  PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_RS272_IEEE_ACTIVE
 	__le16	link_speed;
 	#define PORT_PHY_QCFG_RESP_LINK_SPEED_100MB 0x1UL
 	#define PORT_PHY_QCFG_RESP_LINK_SPEED_1GB   0xaUL
@@ -2809,21 +2908,21 @@ struct hwrm_port_phy_qcfg_output {
 	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_QSFP28    (0x11UL << 24)
 	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_LAST     PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_QSFP28
 	__le16	fec_cfg;
-	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_NONE_SUPPORTED          0x1UL
-	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_AUTONEG_SUPPORTED       0x2UL
-	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_AUTONEG_ENABLED         0x4UL
-	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_CLAUSE74_SUPPORTED      0x8UL
-	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_CLAUSE74_ENABLED        0x10UL
-	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_CLAUSE91_SUPPORTED      0x20UL
-	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_CLAUSE91_ENABLED        0x40UL
-	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS544_1XN_SUPPORTED     0x80UL
-	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS544_1XN_ENABLED       0x100UL
-	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS544_2XN_SUPPORTED     0x200UL
-	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS544_2XN_ENABLED       0x400UL
-	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_CLAUSE74_ACTIVE         0x800UL
-	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_CLAUSE91_ACTIVE         0x1000UL
-	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS544_1XN_ACTIVE        0x2000UL
-	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS544_2XN_ACTIVE        0x4000UL
+	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_NONE_SUPPORTED           0x1UL
+	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_AUTONEG_SUPPORTED        0x2UL
+	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_AUTONEG_ENABLED          0x4UL
+	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_CLAUSE74_SUPPORTED       0x8UL
+	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_CLAUSE74_ENABLED         0x10UL
+	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_CLAUSE91_SUPPORTED       0x20UL
+	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_CLAUSE91_ENABLED         0x40UL
+	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS544_1XN_SUPPORTED      0x80UL
+	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS544_1XN_ENABLED        0x100UL
+	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS544_IEEE_SUPPORTED     0x200UL
+	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS544_IEEE_ENABLED       0x400UL
+	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS272_1XN_SUPPORTED      0x800UL
+	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS272_1XN_ENABLED        0x1000UL
+	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS272_IEEE_SUPPORTED     0x2000UL
+	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS272_IEEE_ENABLED       0x4000UL
 	u8	duplex_state;
 	#define PORT_PHY_QCFG_RESP_DUPLEX_STATE_HALF 0x0UL
 	#define PORT_PHY_QCFG_RESP_DUPLEX_STATE_FULL 0x1UL
@@ -2845,11 +2944,10 @@ struct hwrm_port_phy_qcfg_output {
 	#define PORT_PHY_QCFG_RESP_AUTO_PAM4_LINK_SPEED_MASK_50G      0x1UL
 	#define PORT_PHY_QCFG_RESP_AUTO_PAM4_LINK_SPEED_MASK_100G     0x2UL
 	#define PORT_PHY_QCFG_RESP_AUTO_PAM4_LINK_SPEED_MASK_200G     0x4UL
-	__le16	link_partner_pam4_adv_speeds;
+	u8	link_partner_pam4_adv_speeds;
 	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_PAM4_ADV_SPEEDS_50GB      0x1UL
 	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_PAM4_ADV_SPEEDS_100GB     0x2UL
 	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_PAM4_ADV_SPEEDS_200GB     0x4UL
-	u8	unused_0[7];
 	u8	valid;
 };
 
@@ -3293,6 +3391,47 @@ struct hwrm_port_lpbk_qstats_output {
 	u8	valid;
 };
 
+/* hwrm_port_ecn_qstats_input (size:256b/32B) */
+struct hwrm_port_ecn_qstats_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	port_id;
+	__le16	ecn_stat_buf_size;
+	u8	flags;
+	#define PORT_ECN_QSTATS_REQ_FLAGS_UNUSED       0x0UL
+	#define PORT_ECN_QSTATS_REQ_FLAGS_COUNTER_MASK 0x1UL
+	#define PORT_ECN_QSTATS_REQ_FLAGS_LAST        PORT_ECN_QSTATS_REQ_FLAGS_COUNTER_MASK
+	u8	unused_0[3];
+	__le64	ecn_stat_host_addr;
+};
+
+/* hwrm_port_ecn_qstats_output (size:128b/16B) */
+struct hwrm_port_ecn_qstats_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	ecn_stat_buf_size;
+	u8	mark_en;
+	u8	unused_0[4];
+	u8	valid;
+};
+
+/* port_stats_ecn (size:512b/64B) */
+struct port_stats_ecn {
+	__le64	mark_cnt_cos0;
+	__le64	mark_cnt_cos1;
+	__le64	mark_cnt_cos2;
+	__le64	mark_cnt_cos3;
+	__le64	mark_cnt_cos4;
+	__le64	mark_cnt_cos5;
+	__le64	mark_cnt_cos6;
+	__le64	mark_cnt_cos7;
+};
+
 /* hwrm_port_clr_stats_input (size:192b/24B) */
 struct hwrm_port_clr_stats_input {
 	__le16	req_type;
@@ -3387,8 +3526,9 @@ struct hwrm_port_phy_qcaps_output {
 	#define PORT_PHY_QCAPS_RESP_FLAGS_AUTONEG_LPBK_SUPPORTED           0x4UL
 	#define PORT_PHY_QCAPS_RESP_FLAGS_SHARED_PHY_CFG_SUPPORTED         0x8UL
 	#define PORT_PHY_QCAPS_RESP_FLAGS_CUMULATIVE_COUNTERS_ON_RESET     0x10UL
-	#define PORT_PHY_QCAPS_RESP_FLAGS_RSVD1_MASK                       0xe0UL
-	#define PORT_PHY_QCAPS_RESP_FLAGS_RSVD1_SFT                        5
+	#define PORT_PHY_QCAPS_RESP_FLAGS_LOCAL_LPBK_NOT_SUPPORTED         0x20UL
+	#define PORT_PHY_QCAPS_RESP_FLAGS_RSVD1_MASK                       0xc0UL
+	#define PORT_PHY_QCAPS_RESP_FLAGS_RSVD1_SFT                        6
 	u8	port_cnt;
 	#define PORT_PHY_QCAPS_RESP_PORT_CNT_UNKNOWN 0x0UL
 	#define PORT_PHY_QCAPS_RESP_PORT_CNT_1       0x1UL
@@ -5365,6 +5505,7 @@ struct hwrm_ring_alloc_input {
 	#define RING_ALLOC_REQ_ENABLES_NQ_RING_ID_VALID      0x80UL
 	#define RING_ALLOC_REQ_ENABLES_RX_BUF_SIZE_VALID     0x100UL
 	#define RING_ALLOC_REQ_ENABLES_SCHQ_ID               0x200UL
+	#define RING_ALLOC_REQ_ENABLES_MPC_CHNLS_TYPE        0x400UL
 	u8	ring_type;
 	#define RING_ALLOC_REQ_RING_TYPE_L2_CMPL   0x0UL
 	#define RING_ALLOC_REQ_RING_TYPE_TX        0x1UL
@@ -5424,7 +5565,14 @@ struct hwrm_ring_alloc_input {
 	#define RING_ALLOC_REQ_INT_MODE_MSIX   0x2UL
 	#define RING_ALLOC_REQ_INT_MODE_POLL   0x3UL
 	#define RING_ALLOC_REQ_INT_MODE_LAST  RING_ALLOC_REQ_INT_MODE_POLL
-	u8	unused_4[3];
+	u8	mpc_chnls_type;
+	#define RING_ALLOC_REQ_MPC_CHNLS_TYPE_TCE     0x0UL
+	#define RING_ALLOC_REQ_MPC_CHNLS_TYPE_RCE     0x1UL
+	#define RING_ALLOC_REQ_MPC_CHNLS_TYPE_TE_CFA  0x2UL
+	#define RING_ALLOC_REQ_MPC_CHNLS_TYPE_RE_CFA  0x3UL
+	#define RING_ALLOC_REQ_MPC_CHNLS_TYPE_PRIMATE 0x4UL
+	#define RING_ALLOC_REQ_MPC_CHNLS_TYPE_LAST   RING_ALLOC_REQ_MPC_CHNLS_TYPE_PRIMATE
+	u8	unused_4[2];
 	__le64	cq_handle;
 };
 
@@ -6661,7 +6809,7 @@ struct hwrm_cfa_vfr_alloc_output {
 	u8	valid;
 };
 
-/* hwrm_cfa_vfr_free_input (size:384b/48B) */
+/* hwrm_cfa_vfr_free_input (size:448b/56B) */
 struct hwrm_cfa_vfr_free_input {
 	__le16	req_type;
 	__le16	cmpl_ring;
@@ -6669,6 +6817,9 @@ struct hwrm_cfa_vfr_free_input {
 	__le16	target_id;
 	__le64	resp_addr;
 	char	vfr_name[32];
+	__le16	vf_id;
+	__le16	reserved;
+	u8	unused_0[4];
 };
 
 /* hwrm_cfa_vfr_free_output (size:128b/16B) */
@@ -6970,7 +7121,7 @@ struct ctx_hw_stats {
 	__le64	tpa_aborts;
 };
 
-/* ctx_hw_stats_ext (size:1344b/168B) */
+/* ctx_hw_stats_ext (size:1408b/176B) */
 struct ctx_hw_stats_ext {
 	__le64	rx_ucast_pkts;
 	__le64	rx_mcast_pkts;
@@ -6993,6 +7144,7 @@ struct ctx_hw_stats_ext {
 	__le64	rx_tpa_pkt;
 	__le64	rx_tpa_bytes;
 	__le64	rx_tpa_errors;
+	__le64	rx_tpa_events;
 };
 
 /* hwrm_stat_ctx_alloc_input (size:256b/32B) */
@@ -7065,16 +7217,16 @@ struct hwrm_stat_ctx_query_output {
 	__le64	tx_ucast_pkts;
 	__le64	tx_mcast_pkts;
 	__le64	tx_bcast_pkts;
-	__le64	tx_err_pkts;
-	__le64	tx_drop_pkts;
+	__le64	tx_discard_pkts;
+	__le64	tx_error_pkts;
 	__le64	tx_ucast_bytes;
 	__le64	tx_mcast_bytes;
 	__le64	tx_bcast_bytes;
 	__le64	rx_ucast_pkts;
 	__le64	rx_mcast_pkts;
 	__le64	rx_bcast_pkts;
-	__le64	rx_err_pkts;
-	__le64	rx_drop_pkts;
+	__le64	rx_discard_pkts;
+	__le64	rx_error_pkts;
 	__le64	rx_ucast_bytes;
 	__le64	rx_mcast_bytes;
 	__le64	rx_bcast_bytes;
@@ -7099,7 +7251,7 @@ struct hwrm_stat_ext_ctx_query_input {
 	u8	unused_0[3];
 };
 
-/* hwrm_stat_ext_ctx_query_output (size:1472b/184B) */
+/* hwrm_stat_ext_ctx_query_output (size:1536b/192B) */
 struct hwrm_stat_ext_ctx_query_output {
 	__le16	error_code;
 	__le16	req_type;
@@ -7126,6 +7278,7 @@ struct hwrm_stat_ext_ctx_query_output {
 	__le64	rx_tpa_pkt;
 	__le64	rx_tpa_bytes;
 	__le64	rx_tpa_errors;
+	__le64	rx_tpa_events;
 	u8	unused_0[7];
 	u8	valid;
 };
@@ -7702,6 +7855,77 @@ struct hwrm_dbg_read_direct_output {
 	u8	valid;
 };
 
+/* hwrm_dbg_qcaps_input (size:192b/24B) */
+struct hwrm_dbg_qcaps_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	fid;
+	u8	unused_0[6];
+};
+
+/* hwrm_dbg_qcaps_output (size:192b/24B) */
+struct hwrm_dbg_qcaps_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	fid;
+	u8	unused_0[2];
+	__le32	coredump_component_disable_caps;
+	#define DBG_QCAPS_RESP_COREDUMP_COMPONENT_DISABLE_CAPS_NVRAM     0x1UL
+	__le32	flags;
+	#define DBG_QCAPS_RESP_FLAGS_CRASHDUMP_NVM          0x1UL
+	#define DBG_QCAPS_RESP_FLAGS_CRASHDUMP_HOST_DDR     0x2UL
+	#define DBG_QCAPS_RESP_FLAGS_CRASHDUMP_SOC_DDR      0x4UL
+	u8	unused_1[3];
+	u8	valid;
+};
+
+/* hwrm_dbg_qcfg_input (size:192b/24B) */
+struct hwrm_dbg_qcfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	fid;
+	__le16	flags;
+	#define DBG_QCFG_REQ_FLAGS_CRASHDUMP_SIZE_FOR_DEST_MASK         0x3UL
+	#define DBG_QCFG_REQ_FLAGS_CRASHDUMP_SIZE_FOR_DEST_SFT          0
+	#define DBG_QCFG_REQ_FLAGS_CRASHDUMP_SIZE_FOR_DEST_DEST_NVM       0x0UL
+	#define DBG_QCFG_REQ_FLAGS_CRASHDUMP_SIZE_FOR_DEST_DEST_HOST_DDR  0x1UL
+	#define DBG_QCFG_REQ_FLAGS_CRASHDUMP_SIZE_FOR_DEST_DEST_SOC_DDR   0x2UL
+	#define DBG_QCFG_REQ_FLAGS_CRASHDUMP_SIZE_FOR_DEST_LAST          DBG_QCFG_REQ_FLAGS_CRASHDUMP_SIZE_FOR_DEST_DEST_SOC_DDR
+	__le32	coredump_component_disable_flags;
+	#define DBG_QCFG_REQ_COREDUMP_COMPONENT_DISABLE_FLAGS_NVRAM     0x1UL
+};
+
+/* hwrm_dbg_qcfg_output (size:256b/32B) */
+struct hwrm_dbg_qcfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	fid;
+	u8	unused_0[2];
+	__le32	coredump_size;
+	__le32	flags;
+	#define DBG_QCFG_RESP_FLAGS_UART_LOG               0x1UL
+	#define DBG_QCFG_RESP_FLAGS_UART_LOG_SECONDARY     0x2UL
+	#define DBG_QCFG_RESP_FLAGS_FW_TRACE               0x4UL
+	#define DBG_QCFG_RESP_FLAGS_FW_TRACE_SECONDARY     0x8UL
+	#define DBG_QCFG_RESP_FLAGS_DEBUG_NOTIFY           0x10UL
+	#define DBG_QCFG_RESP_FLAGS_JTAG_DEBUG             0x20UL
+	__le16	async_cmpl_ring;
+	u8	unused_2[2];
+	__le32	crashdump_size;
+	u8	unused_3[3];
+	u8	valid;
+};
+
 /* coredump_segment_record (size:128b/16B) */
 struct coredump_segment_record {
 	__le16	component_id;
@@ -8381,6 +8605,16 @@ struct hwrm_selftest_irq_output {
 	u8	valid;
 };
 
+/* db_push_info (size:64b/8B) */
+struct db_push_info {
+	u32	push_size_push_index;
+	#define DB_PUSH_INFO_PUSH_INDEX_MASK 0xffffffUL
+	#define DB_PUSH_INFO_PUSH_INDEX_SFT 0
+	#define DB_PUSH_INFO_PUSH_SIZE_MASK 0x1f000000UL
+	#define DB_PUSH_INFO_PUSH_SIZE_SFT  24
+	u32	reserved32;
+};
+
 /* fw_status_reg (size:32b/4B) */
 struct fw_status_reg {
 	u32	fw_status;
@@ -8395,4 +8629,29 @@ struct fw_status_reg {
 	#define FW_STATUS_REG_SHUTDOWN               0x100000UL
 };
 
+/* hcomm_status (size:64b/8B) */
+struct hcomm_status {
+	u32	sig_ver;
+	#define HCOMM_STATUS_VER_MASK      0xffUL
+	#define HCOMM_STATUS_VER_SFT       0
+	#define HCOMM_STATUS_VER_LATEST      0x1UL
+	#define HCOMM_STATUS_VER_LAST       HCOMM_STATUS_VER_LATEST
+	#define HCOMM_STATUS_SIGNATURE_MASK 0xffffff00UL
+	#define HCOMM_STATUS_SIGNATURE_SFT 8
+	#define HCOMM_STATUS_SIGNATURE_VAL   (0x484353UL << 8)
+	#define HCOMM_STATUS_SIGNATURE_LAST HCOMM_STATUS_SIGNATURE_VAL
+	u32	fw_status_loc;
+	#define HCOMM_STATUS_TRUE_ADDR_SPACE_MASK    0x3UL
+	#define HCOMM_STATUS_TRUE_ADDR_SPACE_SFT     0
+	#define HCOMM_STATUS_FW_STATUS_LOC_ADDR_SPACE_PCIE_CFG  0x0UL
+	#define HCOMM_STATUS_FW_STATUS_LOC_ADDR_SPACE_GRC       0x1UL
+	#define HCOMM_STATUS_FW_STATUS_LOC_ADDR_SPACE_BAR0      0x2UL
+	#define HCOMM_STATUS_FW_STATUS_LOC_ADDR_SPACE_BAR1      0x3UL
+	#define HCOMM_STATUS_FW_STATUS_LOC_ADDR_SPACE_LAST     HCOMM_STATUS_FW_STATUS_LOC_ADDR_SPACE_BAR1
+	#define HCOMM_STATUS_TRUE_OFFSET_MASK        0xfffffffcUL
+	#define HCOMM_STATUS_TRUE_OFFSET_SFT         2
+};
+
+#define HCOMM_STATUS_STRUCT_LOC 0x31001F0UL
+
 #endif /* _BNXT_HSI_H_ */
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
index cc2ee4d0bd18..23b80aa171dd 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
@@ -1029,7 +1029,7 @@ static int bnxt_vf_set_link(struct bnxt *bp, struct bnxt_vf_info *vf)
 		rc = bnxt_hwrm_exec_fwd_resp(
 			bp, vf, sizeof(struct hwrm_port_phy_qcfg_input));
 	} else {
-		struct hwrm_port_phy_qcfg_output_compat phy_qcfg_resp = {0};
+		struct hwrm_port_phy_qcfg_output phy_qcfg_resp = {0};
 		struct hwrm_port_phy_qcfg_input *phy_qcfg_req;
 
 		phy_qcfg_req =
diff --git a/drivers/net/ethernet/brocade/bna/bfa_cee.c b/drivers/net/ethernet/brocade/bna/bfa_cee.c
index 09fb9315d1ae..06f221c44802 100644
--- a/drivers/net/ethernet/brocade/bna/bfa_cee.c
+++ b/drivers/net/ethernet/brocade/bna/bfa_cee.c
@@ -102,14 +102,10 @@ bfa_cee_get_stats_isr(struct bfa_cee *cee, enum bfa_status status)
 }
 
 /**
- * bfa_cee_get_attr_isr()
+ * bfa_cee_reset_stats_isr - CEE ISR for reset-stats responses from f/w
  *
- * @brief CEE ISR for reset-stats responses from f/w
- *
- * @param[in] cee - Pointer to the CEE module
- *            status - Return status from the f/w
- *
- * @return void
+ * @cee: Input Pointer to the CEE module
+ * @status: Return status from the f/w
  */
 static void
 bfa_cee_reset_stats_isr(struct bfa_cee *cee, enum bfa_status status)
@@ -148,9 +144,12 @@ bfa_nw_cee_mem_claim(struct bfa_cee *cee, u8 *dma_kva, u64 dma_pa)
 }
 
 /**
- * bfa_cee_get_attr - Send the request to the f/w to fetch CEE attributes.
+ * bfa_nw_cee_get_attr - Send the request to the f/w to fetch CEE attributes.
  *
  * @cee: Pointer to the CEE module data structure.
+ * @attr: attribute requested
+ * @cbfn: function pointer
+ * @cbarg: function pointer arguments
  *
  * Return: status
  */
@@ -181,7 +180,9 @@ bfa_nw_cee_get_attr(struct bfa_cee *cee, struct bfa_cee_attr *attr,
 }
 
 /**
- * bfa_cee_isrs - Handles Mail-box interrupts for CEE module.
+ * bfa_cee_isr - Handles Mail-box interrupts for CEE module.
+ * @cbarg: argument passed containing pointer to the CEE module data structure.
+ * @m: message pointer
  */
 
 static void
@@ -210,6 +211,7 @@ bfa_cee_isr(void *cbarg, struct bfi_mbmsg *m)
 /**
  * bfa_cee_notify - CEE module heart-beat failure handler.
  *
+ * @arg: argument passed containing pointer to the CEE module data structure.
  * @event: IOC event type
  */
 
diff --git a/drivers/net/ethernet/brocade/bna/bfa_ioc.c b/drivers/net/ethernet/brocade/bna/bfa_ioc.c
index b9dd06b12945..cd933817a0b8 100644
--- a/drivers/net/ethernet/brocade/bna/bfa_ioc.c
+++ b/drivers/net/ethernet/brocade/bna/bfa_ioc.c
@@ -269,7 +269,7 @@ bfa_ioc_sm_enabling(struct bfa_ioc *ioc, enum ioc_event event)
 		break;
 
 	case IOC_E_PFFAILED:
-		/* !!! fall through !!! */
+		fallthrough;
 	case IOC_E_HWERROR:
 		ioc->cbfn->enable_cbfn(ioc->bfa, BFA_STATUS_IOC_FAILURE);
 		bfa_fsm_set_state(ioc, bfa_ioc_sm_fail);
@@ -365,7 +365,8 @@ bfa_ioc_sm_op(struct bfa_ioc *ioc, enum ioc_event event)
 	case IOC_E_PFFAILED:
 	case IOC_E_HWERROR:
 		bfa_ioc_hb_stop(ioc);
-		/* !!! fall through !!! */
+		fallthrough;
+
 	case IOC_E_HBFAIL:
 		if (ioc->iocpf.auto_recover)
 			bfa_fsm_set_state(ioc, bfa_ioc_sm_fail_retry);
@@ -1763,7 +1764,7 @@ bfa_ioc_flash_fwver_cmp(struct bfa_ioc *ioc,
 		return BFI_IOC_IMG_VER_INCOMP;
 }
 
-/**
+/*
  * Returns TRUE if driver is willing to work with current smem f/w version.
  */
 bool
@@ -2469,6 +2470,7 @@ bfa_ioc_isr(struct bfa_ioc *ioc, struct bfi_mbmsg *m)
  *
  * @ioc:	memory for IOC
  * @bfa:	driver instance structure
+ * @cbfn:	callback function
  */
 void
 bfa_nw_ioc_attach(struct bfa_ioc *ioc, void *bfa, struct bfa_ioc_cbfn *cbfn)
@@ -2500,7 +2502,9 @@ bfa_nw_ioc_detach(struct bfa_ioc *ioc)
 /**
  * bfa_nw_ioc_pci_init - Setup IOC PCI properties.
  *
+ * @ioc:	memory for IOC
  * @pcidev:	PCI device information for this IOC
+ * @clscode:	class code
  */
 void
 bfa_nw_ioc_pci_init(struct bfa_ioc *ioc, struct bfa_pcidev *pcidev,
@@ -2569,6 +2573,7 @@ bfa_nw_ioc_pci_init(struct bfa_ioc *ioc, struct bfa_pcidev *pcidev,
 /**
  * bfa_nw_ioc_mem_claim - Initialize IOC dma memory
  *
+ * @ioc:	memory for IOC
  * @dm_kva:	kernel virtual address of IOC dma memory
  * @dm_pa:	physical address of IOC dma memory
  */
@@ -2636,6 +2641,8 @@ bfa_nw_ioc_mbox_regisr(struct bfa_ioc *ioc, enum bfi_mclass mc,
  *
  * @ioc:	IOC instance
  * @cmd:	Mailbox command
+ * @cbfn:	callback function
+ * @cbarg:	arguments to callback
  *
  * Waits if mailbox is busy. Responsibility of caller to serialize
  */
diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c
index cc80bbbefe87..7e4e831d720f 100644
--- a/drivers/net/ethernet/brocade/bna/bnad.c
+++ b/drivers/net/ethernet/brocade/bna/bnad.c
@@ -3277,7 +3277,7 @@ bnad_change_mtu(struct net_device *netdev, int new_mtu)
 {
 	int err, mtu;
 	struct bnad *bnad = netdev_priv(netdev);
-	u32 rx_count = 0, frame, new_frame;
+	u32 frame, new_frame;
 
 	mutex_lock(&bnad->conf_mutex);
 
@@ -3293,12 +3293,9 @@ bnad_change_mtu(struct net_device *netdev, int new_mtu)
 		/* only when transition is over 4K */
 		if ((frame <= 4096 && new_frame > 4096) ||
 		    (frame > 4096 && new_frame <= 4096))
-			rx_count = bnad_reinit_rx(bnad);
+			bnad_reinit_rx(bnad);
 	}
 
-	/* rx_count > 0 - new rx created
-	 *	- Linux set err = 0 and return
-	 */
 	err = bnad_mtu_set(bnad, new_frame);
 	if (err)
 		err = -EBUSY;
diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h
index 4f1b41569260..3fd5c6cc23af 100644
--- a/drivers/net/ethernet/cadence/macb.h
+++ b/drivers/net/ethernet/cadence/macb.h
@@ -7,6 +7,7 @@
 #ifndef _MACB_H
 #define _MACB_H
 
+#include <linux/clk.h>
 #include <linux/phylink.h>
 #include <linux/ptp_clock_kernel.h>
 #include <linux/net_tstamp.h>
@@ -1298,4 +1299,14 @@ static inline bool gem_has_ptp(struct macb *bp)
 	return !!(bp->caps & MACB_CAPS_GEM_HAS_PTP);
 }
 
+/**
+ * struct macb_platform_data - platform data for MACB Ethernet used for PCI registration
+ * @pclk:		platform clock
+ * @hclk:		AHB clock
+ */
+struct macb_platform_data {
+	struct clk	*pclk;
+	struct clk	*hclk;
+};
+
 #endif /* _MACB_H */
diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 830c537bc08c..4b42b2d6398c 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -23,7 +23,6 @@
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
 #include <linux/dma-mapping.h>
-#include <linux/platform_data/macb.h>
 #include <linux/platform_device.h>
 #include <linux/phylink.h>
 #include <linux/of.h>
@@ -458,9 +457,9 @@ static void macb_init_buffers(struct macb *bp)
 
 /**
  * macb_set_tx_clk() - Set a clock to a new frequency
- * @clk		Pointer to the clock to change
- * @rate	New frequency in Hz
- * @dev		Pointer to the struct net_device
+ * @clk:	Pointer to the clock to change
+ * @speed:	New frequency in Hz
+ * @dev:	Pointer to the struct net_device
  */
 static void macb_set_tx_clk(struct clk *clk, int speed, struct net_device *dev)
 {
@@ -647,8 +646,7 @@ static void macb_mac_link_up(struct phylink_config *config,
 				ctrl |= GEM_BIT(GBE);
 		}
 
-		/* We do not support MLO_PAUSE_RX yet */
-		if (tx_pause)
+		if (rx_pause)
 			ctrl |= MACB_BIT(PAE);
 
 		macb_set_tx_clk(bp->tx_clk, speed, ndev);
diff --git a/drivers/net/ethernet/cadence/macb_pci.c b/drivers/net/ethernet/cadence/macb_pci.c
index cd7d0332cba3..353393dea639 100644
--- a/drivers/net/ethernet/cadence/macb_pci.c
+++ b/drivers/net/ethernet/cadence/macb_pci.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /**
- * Cadence GEM PCI wrapper.
+ * DOC: Cadence GEM PCI wrapper.
  *
  * Copyright (C) 2016 Cadence Design Systems - https://www.cadence.com
  *
@@ -13,7 +13,6 @@
 #include <linux/etherdevice.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/platform_data/macb.h>
 #include <linux/platform_device.h>
 #include "macb.h"
 
diff --git a/drivers/net/ethernet/calxeda/xgmac.c b/drivers/net/ethernet/calxeda/xgmac.c
index 05a3d067c3fc..bbb453c6a5f7 100644
--- a/drivers/net/ethernet/calxeda/xgmac.c
+++ b/drivers/net/ethernet/calxeda/xgmac.c
@@ -1246,6 +1246,8 @@ static int xgmac_poll(struct napi_struct *napi, int budget)
 /**
  *  xgmac_tx_timeout
  *  @dev : Pointer to net device structure
+ *  @txqueue: index of the hung transmit queue
+ *
  *  Description: this function is called when a packet transmission fails to
  *   complete within a reasonable tmrate. The driver will mark the error in the
  *   netdev structure and arrange for the device to be reset to a sane state
diff --git a/drivers/net/ethernet/cavium/liquidio/cn68xx_device.c b/drivers/net/ethernet/cavium/liquidio/cn68xx_device.c
index cd5d5d6e7e5e..2a6d1cadac9e 100644
--- a/drivers/net/ethernet/cavium/liquidio/cn68xx_device.c
+++ b/drivers/net/ethernet/cavium/liquidio/cn68xx_device.c
@@ -25,6 +25,7 @@
 #include "octeon_main.h"
 #include "cn66xx_regs.h"
 #include "cn66xx_device.h"
+#include "cn68xx_device.h"
 #include "cn68xx_regs.h"
 #include "cn68xx_device.h"
 
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_core.c b/drivers/net/ethernet/cavium/liquidio/lio_core.c
index e40c64b79f66..9ef172976b35 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_core.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_core.c
@@ -32,8 +32,8 @@
 #define OCTNIC_MAX_SG  MAX_SKB_FRAGS
 
 /**
- * \brief Delete gather lists
- * @param lio per-network private data
+ * lio_delete_glists - Delete gather lists
+ * @lio: per-network private data
  */
 void lio_delete_glists(struct lio *lio)
 {
@@ -73,8 +73,10 @@ void lio_delete_glists(struct lio *lio)
 }
 
 /**
- * \brief Setup gather lists
- * @param lio per-network private data
+ * lio_setup_glists - Setup gather lists
+ * @oct: octeon_device
+ * @lio: per-network private data
+ * @num_iqs: count of iqs to allocate
  */
 int lio_setup_glists(struct octeon_device *oct, struct lio *lio, int num_iqs)
 {
@@ -521,12 +523,12 @@ static void lio_update_txq_status(struct octeon_device *oct, int iq_num)
 }
 
 /**
- * \brief Setup output queue
- * @param oct octeon device
- * @param q_no which queue
- * @param num_descs how many descriptors
- * @param desc_size size of each descriptor
- * @param app_ctx application context
+ * octeon_setup_droq - Setup output queue
+ * @oct: octeon device
+ * @q_no: which queue
+ * @num_descs: how many descriptors
+ * @desc_size: size of each descriptor
+ * @app_ctx: application context
  */
 static int octeon_setup_droq(struct octeon_device *oct, int q_no, int num_descs,
 			     int desc_size, void *app_ctx)
@@ -555,16 +557,17 @@ static int octeon_setup_droq(struct octeon_device *oct, int q_no, int num_descs,
 	return ret_val;
 }
 
-/** Routine to push packets arriving on Octeon interface upto network layer.
- * @param oct_id   - octeon device id.
- * @param skbuff   - skbuff struct to be passed to network layer.
- * @param len      - size of total data received.
- * @param rh       - Control header associated with the packet
- * @param param    - additional control data with the packet
- * @param arg      - farg registered in droq_ops
+/**
+ * liquidio_push_packet - Routine to push packets arriving on Octeon interface upto network layer.
+ * @octeon_id:octeon device id.
+ * @skbuff:   skbuff struct to be passed to network layer.
+ * @len:      size of total data received.
+ * @rh:       Control header associated with the packet
+ * @param:    additional control data with the packet
+ * @arg:      farg registered in droq_ops
  */
 static void
-liquidio_push_packet(u32 octeon_id __attribute__((unused)),
+liquidio_push_packet(u32 __maybe_unused octeon_id,
 		     void *skbuff,
 		     u32 len,
 		     union octeon_rh *rh,
@@ -698,8 +701,8 @@ liquidio_push_packet(u32 octeon_id __attribute__((unused)),
 }
 
 /**
- * \brief wrapper for calling napi_schedule
- * @param param parameters to pass to napi_schedule
+ * napi_schedule_wrapper - wrapper for calling napi_schedule
+ * @param: parameters to pass to napi_schedule
  *
  * Used when scheduling on different CPUs
  */
@@ -711,8 +714,8 @@ static void napi_schedule_wrapper(void *param)
 }
 
 /**
- * \brief callback when receive interrupt occurs and we are in NAPI mode
- * @param arg pointer to octeon output queue
+ * liquidio_napi_drv_callback - callback when receive interrupt occurs and we are in NAPI mode
+ * @arg: pointer to octeon output queue
  */
 static void liquidio_napi_drv_callback(void *arg)
 {
@@ -737,9 +740,9 @@ static void liquidio_napi_drv_callback(void *arg)
 }
 
 /**
- * \brief Entry point for NAPI polling
- * @param napi NAPI structure
- * @param budget maximum number of items to process
+ * liquidio_napi_poll - Entry point for NAPI polling
+ * @napi: NAPI structure
+ * @budget: maximum number of items to process
  */
 static int liquidio_napi_poll(struct napi_struct *napi, int budget)
 {
@@ -792,9 +795,11 @@ static int liquidio_napi_poll(struct napi_struct *napi, int budget)
 }
 
 /**
- * \brief Setup input and output queues
- * @param octeon_dev octeon device
- * @param ifidx Interface index
+ * liquidio_setup_io_queues - Setup input and output queues
+ * @octeon_dev: octeon device
+ * @ifidx: Interface index
+ * @num_iqs: input io queue count
+ * @num_oqs: output io queue count
  *
  * Note: Queues are with respect to the octeon device. Thus
  * an input queue is for egress packets, and output queues
@@ -927,7 +932,7 @@ int liquidio_schedule_msix_droq_pkt_handler(struct octeon_droq *droq, u64 ret)
 }
 
 irqreturn_t
-liquidio_msix_intr_handler(int irq __attribute__((unused)), void *dev)
+liquidio_msix_intr_handler(int __maybe_unused irq, void *dev)
 {
 	struct octeon_ioq_vector *ioq_vector = (struct octeon_ioq_vector *)dev;
 	struct octeon_device *oct = ioq_vector->oct_dev;
@@ -943,8 +948,8 @@ liquidio_msix_intr_handler(int irq __attribute__((unused)), void *dev)
 }
 
 /**
- * \brief Droq packet processor sceduler
- * @param oct octeon device
+ * liquidio_schedule_droq_pkt_handlers - Droq packet processor sceduler
+ * @oct: octeon device
  */
 static void liquidio_schedule_droq_pkt_handlers(struct octeon_device *oct)
 {
@@ -972,13 +977,12 @@ static void liquidio_schedule_droq_pkt_handlers(struct octeon_device *oct)
 }
 
 /**
- * \brief Interrupt handler for octeon
- * @param irq unused
- * @param dev octeon device
+ * liquidio_legacy_intr_handler - Interrupt handler for octeon
+ * @irq: unused
+ * @dev: octeon device
  */
 static
-irqreturn_t liquidio_legacy_intr_handler(int irq __attribute__((unused)),
-					 void *dev)
+irqreturn_t liquidio_legacy_intr_handler(int __maybe_unused irq, void *dev)
 {
 	struct octeon_device *oct = (struct octeon_device *)dev;
 	irqreturn_t ret;
@@ -999,8 +1003,9 @@ irqreturn_t liquidio_legacy_intr_handler(int irq __attribute__((unused)),
 }
 
 /**
- * \brief Setup interrupt for octeon device
- * @param oct octeon device
+ * octeon_setup_interrupt - Setup interrupt for octeon device
+ * @oct: octeon device
+ * @num_ioqs: number of queues
  *
  *  Enable interrupt in Octeon device as given in the PCI interrupt mask.
  */
@@ -1083,7 +1088,7 @@ int octeon_setup_interrupt(struct octeon_device *oct, u32 num_ioqs)
 		dev_dbg(&oct->pci_dev->dev, "OCTEON: Enough MSI-X interrupts are allocated...\n");
 
 		num_ioq_vectors = oct->num_msix_irqs;
-		/** For PF, there is one non-ioq interrupt handler */
+		/* For PF, there is one non-ioq interrupt handler */
 		if (OCTEON_CN23XX_PF(oct)) {
 			num_ioq_vectors -= 1;
 
@@ -1126,13 +1131,13 @@ int octeon_setup_interrupt(struct octeon_device *oct, u32 num_ioqs)
 				dev_err(&oct->pci_dev->dev,
 					"Request_irq failed for MSIX interrupt Error: %d\n",
 					irqret);
-				/** Freeing the non-ioq irq vector here . */
+				/* Freeing the non-ioq irq vector here . */
 				free_irq(msix_entries[num_ioq_vectors].vector,
 					 oct);
 
 				while (i) {
 					i--;
-					/** clearing affinity mask. */
+					/* clearing affinity mask. */
 					irq_set_affinity_hint(
 						      msix_entries[i].vector,
 						      NULL);
@@ -1197,8 +1202,9 @@ int octeon_setup_interrupt(struct octeon_device *oct, u32 num_ioqs)
 }
 
 /**
- * \brief Net device change_mtu
- * @param netdev network device
+ * liquidio_change_mtu - Net device change_mtu
+ * @netdev: network device
+ * @new_mtu: the new max transmit unit size
  */
 int liquidio_change_mtu(struct net_device *netdev, int new_mtu)
 {
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c
index 9eac0d43b58d..7d00d3a8ded4 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c
@@ -69,9 +69,9 @@ MODULE_PARM_DESC(console_bitmask,
 		 "Bitmask indicating which consoles have debug output redirected to syslog.");
 
 /**
- * \brief determines if a given console has debug enabled.
- * @param console console to check
- * @returns  1 = enabled. 0 otherwise
+ * octeon_console_debug_enabled - determines if a given console has debug enabled.
+ * @console: console to check
+ * Return:  1 = enabled. 0 otherwise
  */
 static int octeon_console_debug_enabled(u32 console)
 {
@@ -126,7 +126,7 @@ union tx_info {
 	} s;
 };
 
-/** Octeon device properties to be used by the NIC module.
+/* Octeon device properties to be used by the NIC module.
  * Each octeon device in the system will be represented
  * by this structure in the NIC module.
  */
@@ -222,8 +222,8 @@ static int lio_wait_for_oq_pkts(struct octeon_device *oct)
 }
 
 /**
- * \brief Forces all IO queues off on a given device
- * @param oct Pointer to Octeon device
+ * force_io_queues_off - Forces all IO queues off on a given device
+ * @oct: Pointer to Octeon device
  */
 static void force_io_queues_off(struct octeon_device *oct)
 {
@@ -238,8 +238,8 @@ static void force_io_queues_off(struct octeon_device *oct)
 }
 
 /**
- * \brief Cause device to go quiet so it can be safely removed/reset/etc
- * @param oct Pointer to Octeon device
+ * pcierror_quiesce_device - Cause device to go quiet so it can be safely removed/reset/etc
+ * @oct: Pointer to Octeon device
  */
 static inline void pcierror_quiesce_device(struct octeon_device *oct)
 {
@@ -283,8 +283,8 @@ static inline void pcierror_quiesce_device(struct octeon_device *oct)
 }
 
 /**
- * \brief Cleanup PCI AER uncorrectable error status
- * @param dev Pointer to PCI device
+ * cleanup_aer_uncorrect_error_status - Cleanup PCI AER uncorrectable error status
+ * @dev: Pointer to PCI device
  */
 static void cleanup_aer_uncorrect_error_status(struct pci_dev *dev)
 {
@@ -303,8 +303,8 @@ static void cleanup_aer_uncorrect_error_status(struct pci_dev *dev)
 }
 
 /**
- * \brief Stop all PCI IO to a given device
- * @param dev Pointer to Octeon device
+ * stop_pci_io - Stop all PCI IO to a given device
+ * @oct: Pointer to Octeon device
  */
 static void stop_pci_io(struct octeon_device *oct)
 {
@@ -332,9 +332,9 @@ static void stop_pci_io(struct octeon_device *oct)
 }
 
 /**
- * \brief called when PCI error is detected
- * @param pdev Pointer to PCI device
- * @param state The current pci connection state
+ * liquidio_pcie_error_detected - called when PCI error is detected
+ * @pdev: Pointer to PCI device
+ * @state: The current pci connection state
  *
  * This function is called after a PCI bus error affecting
  * this device has been detected.
@@ -362,11 +362,10 @@ static pci_ers_result_t liquidio_pcie_error_detected(struct pci_dev *pdev,
 }
 
 /**
- * \brief mmio handler
- * @param pdev Pointer to PCI device
+ * liquidio_pcie_mmio_enabled - mmio handler
+ * @pdev: Pointer to PCI device
  */
-static pci_ers_result_t liquidio_pcie_mmio_enabled(
-				struct pci_dev *pdev __attribute__((unused)))
+static pci_ers_result_t liquidio_pcie_mmio_enabled(struct pci_dev __maybe_unused *pdev)
 {
 	/* We should never hit this since we never ask for a reset for a Fatal
 	 * Error. We always return DISCONNECT in io_error above.
@@ -376,14 +375,13 @@ static pci_ers_result_t liquidio_pcie_mmio_enabled(
 }
 
 /**
- * \brief called after the pci bus has been reset.
- * @param pdev Pointer to PCI device
+ * liquidio_pcie_slot_reset - called after the pci bus has been reset.
+ * @pdev: Pointer to PCI device
  *
  * Restart the card from scratch, as if from a cold-boot. Implementation
  * resembles the first-half of the octeon_resume routine.
  */
-static pci_ers_result_t liquidio_pcie_slot_reset(
-				struct pci_dev *pdev __attribute__((unused)))
+static pci_ers_result_t liquidio_pcie_slot_reset(struct pci_dev __maybe_unused *pdev)
 {
 	/* We should never hit this since we never ask for a reset for a Fatal
 	 * Error. We always return DISCONNECT in io_error above.
@@ -393,14 +391,14 @@ static pci_ers_result_t liquidio_pcie_slot_reset(
 }
 
 /**
- * \brief called when traffic can start flowing again.
- * @param pdev Pointer to PCI device
+ * liquidio_pcie_resume - called when traffic can start flowing again.
+ * @pdev: Pointer to PCI device
  *
  * This callback is called when the error recovery driver tells us that
  * its OK to resume normal operation. Implementation resembles the
  * second-half of the octeon_resume routine.
  */
-static void liquidio_pcie_resume(struct pci_dev *pdev __attribute__((unused)))
+static void liquidio_pcie_resume(struct pci_dev __maybe_unused *pdev)
 {
 	/* Nothing to be done here. */
 }
@@ -447,7 +445,7 @@ static struct pci_driver liquidio_pci_driver = {
 };
 
 /**
- * \brief register PCI driver
+ * liquidio_init_pci - register PCI driver
  */
 static int liquidio_init_pci(void)
 {
@@ -455,7 +453,7 @@ static int liquidio_init_pci(void)
 }
 
 /**
- * \brief unregister PCI driver
+ * liquidio_deinit_pci - unregister PCI driver
  */
 static void liquidio_deinit_pci(void)
 {
@@ -463,9 +461,9 @@ static void liquidio_deinit_pci(void)
 }
 
 /**
- * \brief Check Tx queue status, and take appropriate action
- * @param lio per-network private data
- * @returns 0 if full, number of queues woken up otherwise
+ * check_txq_status - Check Tx queue status, and take appropriate action
+ * @lio: per-network private data
+ * Return: 0 if full, number of queues woken up otherwise
  */
 static inline int check_txq_status(struct lio *lio)
 {
@@ -491,8 +489,8 @@ static inline int check_txq_status(struct lio *lio)
 }
 
 /**
- * \brief Print link information
- * @param netdev network device
+ * print_link_info -  Print link information
+ * @netdev: network device
  */
 static void print_link_info(struct net_device *netdev)
 {
@@ -513,8 +511,8 @@ static void print_link_info(struct net_device *netdev)
 }
 
 /**
- * \brief Routine to notify MTU change
- * @param work work_struct data structure
+ * octnet_link_status_change - Routine to notify MTU change
+ * @work: work_struct data structure
  */
 static void octnet_link_status_change(struct work_struct *work)
 {
@@ -531,8 +529,8 @@ static void octnet_link_status_change(struct work_struct *work)
 }
 
 /**
- * \brief Sets up the mtu status change work
- * @param netdev network device
+ * setup_link_status_change_wq - Sets up the mtu status change work
+ * @netdev: network device
  */
 static inline int setup_link_status_change_wq(struct net_device *netdev)
 {
@@ -563,9 +561,9 @@ static inline void cleanup_link_status_change_wq(struct net_device *netdev)
 }
 
 /**
- * \brief Update link status
- * @param netdev network device
- * @param ls link status structure
+ * update_link_status - Update link status
+ * @netdev: network device
+ * @ls: link status structure
  *
  * Called on receipt of a link status response from the core application to
  * update each interface's link status.
@@ -663,10 +661,9 @@ static void lio_sync_octeon_time(struct work_struct *work)
 }
 
 /**
- * setup_sync_octeon_time_wq - Sets up the work to periodically update
- * local time to octeon firmware
+ * setup_sync_octeon_time_wq - prepare work to periodically update local time to octeon firmware
  *
- * @netdev - network device which should send time update to firmware
+ * @netdev: network device which should send time update to firmware
  **/
 static inline int setup_sync_octeon_time_wq(struct net_device *netdev)
 {
@@ -690,10 +687,12 @@ static inline int setup_sync_octeon_time_wq(struct net_device *netdev)
 }
 
 /**
- * cleanup_sync_octeon_time_wq - stop scheduling and destroy the work created
- * to periodically update local time to octeon firmware
+ * cleanup_sync_octeon_time_wq - destroy wq
  *
- * @netdev - network device which should send time update to firmware
+ * @netdev: network device which should send time update to firmware
+ *
+ * Stop scheduling and destroy the work created to periodically update local
+ * time to octeon firmware.
  **/
 static inline void cleanup_sync_octeon_time_wq(struct net_device *netdev)
 {
@@ -828,13 +827,12 @@ static int liquidio_watchdog(void *param)
 }
 
 /**
- * \brief PCI probe handler
- * @param pdev PCI device structure
- * @param ent unused
+ * liquidio_probe - PCI probe handler
+ * @pdev: PCI device structure
+ * @ent: unused
  */
 static int
-liquidio_probe(struct pci_dev *pdev,
-	       const struct pci_device_id *ent __attribute__((unused)))
+liquidio_probe(struct pci_dev *pdev, const struct pci_device_id __maybe_unused *ent)
 {
 	struct octeon_device *oct_dev = NULL;
 	struct handshake *hs;
@@ -924,8 +922,8 @@ static bool fw_type_is_auto(void)
 }
 
 /**
- * \brief PCI FLR for each Octeon device.
- * @param oct octeon device
+ * octeon_pci_flr - PCI FLR for each Octeon device.
+ * @oct: octeon device
  */
 static void octeon_pci_flr(struct octeon_device *oct)
 {
@@ -951,9 +949,8 @@ static void octeon_pci_flr(struct octeon_device *oct)
 }
 
 /**
- *\brief Destroy resources associated with octeon device
- * @param pdev PCI device structure
- * @param ent unused
+ * octeon_destroy_resources - Destroy resources associated with octeon device
+ * @oct: octeon device
  */
 static void octeon_destroy_resources(struct octeon_device *oct)
 {
@@ -1152,9 +1149,9 @@ static void octeon_destroy_resources(struct octeon_device *oct)
 }
 
 /**
- * \brief Send Rx control command
- * @param lio per-network private data
- * @param start_stop whether to start or stop
+ * send_rx_ctrl_cmd - Send Rx control command
+ * @lio: per-network private data
+ * @start_stop: whether to start or stop
  */
 static void send_rx_ctrl_cmd(struct lio *lio, int start_stop)
 {
@@ -1210,9 +1207,9 @@ static void send_rx_ctrl_cmd(struct lio *lio, int start_stop)
 }
 
 /**
- * \brief Destroy NIC device interface
- * @param oct octeon device
- * @param ifidx which interface to destroy
+ * liquidio_destroy_nic_device - Destroy NIC device interface
+ * @oct: octeon device
+ * @ifidx: which interface to destroy
  *
  * Cleanup associated with each interface for an Octeon device  when NIC
  * module is being unloaded or if initialization fails during load.
@@ -1272,8 +1269,8 @@ static void liquidio_destroy_nic_device(struct octeon_device *oct, int ifidx)
 }
 
 /**
- * \brief Stop complete NIC functionality
- * @param oct octeon device
+ * liquidio_stop_nic_module - Stop complete NIC functionality
+ * @oct: octeon device
  */
 static int liquidio_stop_nic_module(struct octeon_device *oct)
 {
@@ -1313,8 +1310,8 @@ static int liquidio_stop_nic_module(struct octeon_device *oct)
 }
 
 /**
- * \brief Cleans up resources at unload time
- * @param pdev PCI device structure
+ * liquidio_remove - Cleans up resources at unload time
+ * @pdev: PCI device structure
  */
 static void liquidio_remove(struct pci_dev *pdev)
 {
@@ -1346,8 +1343,8 @@ static void liquidio_remove(struct pci_dev *pdev)
 }
 
 /**
- * \brief Identify the Octeon device and to map the BAR address space
- * @param oct octeon device
+ * octeon_chip_specific_setup - Identify the Octeon device and to map the BAR address space
+ * @oct: octeon device
  */
 static int octeon_chip_specific_setup(struct octeon_device *oct)
 {
@@ -1390,8 +1387,8 @@ static int octeon_chip_specific_setup(struct octeon_device *oct)
 }
 
 /**
- * \brief PCI initialization for each Octeon device.
- * @param oct octeon device
+ * octeon_pci_os_setup - PCI initialization for each Octeon device.
+ * @oct: octeon device
  */
 static int octeon_pci_os_setup(struct octeon_device *oct)
 {
@@ -1414,8 +1411,8 @@ static int octeon_pci_os_setup(struct octeon_device *oct)
 }
 
 /**
- * \brief Unmap and free network buffer
- * @param buf buffer
+ * free_netbuf - Unmap and free network buffer
+ * @buf: buffer
  */
 static void free_netbuf(void *buf)
 {
@@ -1434,8 +1431,8 @@ static void free_netbuf(void *buf)
 }
 
 /**
- * \brief Unmap and free gather buffer
- * @param buf buffer
+ * free_netsgbuf - Unmap and free gather buffer
+ * @buf: buffer
  */
 static void free_netsgbuf(void *buf)
 {
@@ -1474,8 +1471,8 @@ static void free_netsgbuf(void *buf)
 }
 
 /**
- * \brief Unmap and free gather buffer with response
- * @param buf buffer
+ * free_netsgbuf_with_resp - Unmap and free gather buffer with response
+ * @buf: buffer
  */
 static void free_netsgbuf_with_resp(void *buf)
 {
@@ -1518,9 +1515,9 @@ static void free_netsgbuf_with_resp(void *buf)
 }
 
 /**
- * \brief Adjust ptp frequency
- * @param ptp PTP clock info
- * @param ppb how much to adjust by, in parts-per-billion
+ * liquidio_ptp_adjfreq - Adjust ptp frequency
+ * @ptp: PTP clock info
+ * @ppb: how much to adjust by, in parts-per-billion
  */
 static int liquidio_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb)
 {
@@ -1555,9 +1552,9 @@ static int liquidio_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb)
 }
 
 /**
- * \brief Adjust ptp time
- * @param ptp PTP clock info
- * @param delta how much to adjust by, in nanosecs
+ * liquidio_ptp_adjtime - Adjust ptp time
+ * @ptp: PTP clock info
+ * @delta: how much to adjust by, in nanosecs
  */
 static int liquidio_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
 {
@@ -1572,9 +1569,9 @@ static int liquidio_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
 }
 
 /**
- * \brief Get hardware clock time, including any adjustment
- * @param ptp PTP clock info
- * @param ts timespec
+ * liquidio_ptp_gettime - Get hardware clock time, including any adjustment
+ * @ptp: PTP clock info
+ * @ts: timespec
  */
 static int liquidio_ptp_gettime(struct ptp_clock_info *ptp,
 				struct timespec64 *ts)
@@ -1595,9 +1592,9 @@ static int liquidio_ptp_gettime(struct ptp_clock_info *ptp,
 }
 
 /**
- * \brief Set hardware clock time. Reset adjustment
- * @param ptp PTP clock info
- * @param ts timespec
+ * liquidio_ptp_settime - Set hardware clock time. Reset adjustment
+ * @ptp: PTP clock info
+ * @ts: timespec
  */
 static int liquidio_ptp_settime(struct ptp_clock_info *ptp,
 				const struct timespec64 *ts)
@@ -1618,22 +1615,22 @@ static int liquidio_ptp_settime(struct ptp_clock_info *ptp,
 }
 
 /**
- * \brief Check if PTP is enabled
- * @param ptp PTP clock info
- * @param rq request
- * @param on is it on
+ * liquidio_ptp_enable - Check if PTP is enabled
+ * @ptp: PTP clock info
+ * @rq: request
+ * @on: is it on
  */
 static int
-liquidio_ptp_enable(struct ptp_clock_info *ptp __attribute__((unused)),
-		    struct ptp_clock_request *rq __attribute__((unused)),
-		    int on __attribute__((unused)))
+liquidio_ptp_enable(struct ptp_clock_info __maybe_unused *ptp,
+		    struct ptp_clock_request __maybe_unused *rq,
+		    int __maybe_unused on)
 {
 	return -EOPNOTSUPP;
 }
 
 /**
- * \brief Open PTP clock source
- * @param netdev network device
+ * oct_ptp_open - Open PTP clock source
+ * @netdev: network device
  */
 static void oct_ptp_open(struct net_device *netdev)
 {
@@ -1665,8 +1662,8 @@ static void oct_ptp_open(struct net_device *netdev)
 }
 
 /**
- * \brief Init PTP clock
- * @param oct octeon device
+ * liquidio_ptp_init - Init PTP clock
+ * @oct: octeon device
  */
 static void liquidio_ptp_init(struct octeon_device *oct)
 {
@@ -1682,8 +1679,8 @@ static void liquidio_ptp_init(struct octeon_device *oct)
 }
 
 /**
- * \brief Load firmware to device
- * @param oct octeon device
+ * load_firmware - Load firmware to device
+ * @oct: octeon device
  *
  * Maps device to firmware filename, requests firmware, and downloads it
  */
@@ -1721,8 +1718,8 @@ static int load_firmware(struct octeon_device *oct)
 }
 
 /**
- * \brief Poll routine for checking transmit queue status
- * @param work work_struct data structure
+ * octnet_poll_check_txq_status - Poll routine for checking transmit queue status
+ * @work: work_struct data structure
  */
 static void octnet_poll_check_txq_status(struct work_struct *work)
 {
@@ -1738,8 +1735,8 @@ static void octnet_poll_check_txq_status(struct work_struct *work)
 }
 
 /**
- * \brief Sets up the txq poll check
- * @param netdev network device
+ * setup_tx_poll_fn - Sets up the txq poll check
+ * @netdev: network device
  */
 static inline int setup_tx_poll_fn(struct net_device *netdev)
 {
@@ -1771,8 +1768,8 @@ static inline void cleanup_tx_poll_fn(struct net_device *netdev)
 }
 
 /**
- * \brief Net device open for LiquidIO
- * @param netdev network device
+ * liquidio_open - Net device open for LiquidIO
+ * @netdev: network device
  */
 static int liquidio_open(struct net_device *netdev)
 {
@@ -1831,8 +1828,8 @@ static int liquidio_open(struct net_device *netdev)
 }
 
 /**
- * \brief Net device stop for LiquidIO
- * @param netdev network device
+ * liquidio_stop - Net device stop for LiquidIO
+ * @netdev: network device
  */
 static int liquidio_stop(struct net_device *netdev)
 {
@@ -1896,8 +1893,8 @@ static int liquidio_stop(struct net_device *netdev)
 }
 
 /**
- * \brief Converts a mask based on net device flags
- * @param netdev network device
+ * get_new_flags - Converts a mask based on net device flags
+ * @netdev: network device
  *
  * This routine generates a octnet_ifflags mask from the net device flags
  * received from the OS.
@@ -1929,8 +1926,8 @@ static inline enum octnet_ifflags get_new_flags(struct net_device *netdev)
 }
 
 /**
- * \brief Net device set_multicast_list
- * @param netdev network device
+ * liquidio_set_mcast_list - Net device set_multicast_list
+ * @netdev: network device
  */
 static void liquidio_set_mcast_list(struct net_device *netdev)
 {
@@ -1977,8 +1974,9 @@ static void liquidio_set_mcast_list(struct net_device *netdev)
 }
 
 /**
- * \brief Net device set_mac_address
- * @param netdev network device
+ * liquidio_set_mac - Net device set_mac_address
+ * @netdev: network device
+ * @p: pointer to sockaddr
  */
 static int liquidio_set_mac(struct net_device *netdev, void *p)
 {
@@ -2096,10 +2094,9 @@ liquidio_get_stats64(struct net_device *netdev,
 }
 
 /**
- * \brief Handler for SIOCSHWTSTAMP ioctl
- * @param netdev network device
- * @param ifr interface request
- * @param cmd command
+ * hwtstamp_ioctl - Handler for SIOCSHWTSTAMP ioctl
+ * @netdev: network device
+ * @ifr: interface request
  */
 static int hwtstamp_ioctl(struct net_device *netdev, struct ifreq *ifr)
 {
@@ -2154,10 +2151,10 @@ static int hwtstamp_ioctl(struct net_device *netdev, struct ifreq *ifr)
 }
 
 /**
- * \brief ioctl handler
- * @param netdev network device
- * @param ifr interface request
- * @param cmd command
+ * liquidio_ioctl - ioctl handler
+ * @netdev: network device
+ * @ifr: interface request
+ * @cmd: command
  */
 static int liquidio_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
 {
@@ -2174,9 +2171,10 @@ static int liquidio_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
 }
 
 /**
- * \brief handle a Tx timestamp response
- * @param status response status
- * @param buf pointer to skb
+ * handle_timestamp - handle a Tx timestamp response
+ * @oct: octeon device
+ * @status: response status
+ * @buf: pointer to skb
  */
 static void handle_timestamp(struct octeon_device *oct,
 			     u32 status,
@@ -2217,10 +2215,12 @@ static void handle_timestamp(struct octeon_device *oct,
 	tx_buffer_free(skb);
 }
 
-/* \brief Send a data packet that will be timestamped
- * @param oct octeon device
- * @param ndata pointer to network data
- * @param finfo pointer to private network data
+/**
+ * send_nic_timestamp_pkt - Send a data packet that will be timestamped
+ * @oct: octeon device
+ * @ndata: pointer to network data
+ * @finfo: pointer to private network data
+ * @xmit_more: more is coming
  */
 static inline int send_nic_timestamp_pkt(struct octeon_device *oct,
 					 struct octnic_data_pkt *ndata,
@@ -2276,10 +2276,12 @@ static inline int send_nic_timestamp_pkt(struct octeon_device *oct,
 	return retval;
 }
 
-/** \brief Transmit networks packets to the Octeon interface
- * @param skbuff   skbuff struct to be passed to network layer.
- * @param netdev    pointer to network device
- * @returns whether the packet was transmitted to the device okay or not
+/**
+ * liquidio_xmit - Transmit networks packets to the Octeon interface
+ * @skb: skbuff struct to be passed to network layer.
+ * @netdev: pointer to network device
+ *
+ * Return: whether the packet was transmitted to the device okay or not
  *             (NETDEV_TX_OK or NETDEV_TX_BUSY)
  */
 static netdev_tx_t liquidio_xmit(struct sk_buff *skb, struct net_device *netdev)
@@ -2524,8 +2526,10 @@ lio_xmit_failed:
 	return NETDEV_TX_OK;
 }
 
-/** \brief Network device Tx timeout
- * @param netdev    pointer to network device
+/**
+ * liquidio_tx_timeout - Network device Tx timeout
+ * @netdev:    pointer to network device
+ * @txqueue: index of the hung transmit queue
  */
 static void liquidio_tx_timeout(struct net_device *netdev, unsigned int txqueue)
 {
@@ -2597,12 +2601,12 @@ static int liquidio_vlan_rx_kill_vid(struct net_device *netdev,
 	return ret;
 }
 
-/** Sending command to enable/disable RX checksum offload
- * @param netdev                pointer to network device
- * @param command               OCTNET_CMD_TNL_RX_CSUM_CTL
- * @param rx_cmd_bit            OCTNET_CMD_RXCSUM_ENABLE/
- *                              OCTNET_CMD_RXCSUM_DISABLE
- * @returns                     SUCCESS or FAILURE
+/**
+ * liquidio_set_rxcsum_command - Sending command to enable/disable RX checksum offload
+ * @netdev:                pointer to network device
+ * @command:               OCTNET_CMD_TNL_RX_CSUM_CTL
+ * @rx_cmd:                OCTNET_CMD_RXCSUM_ENABLE/OCTNET_CMD_RXCSUM_DISABLE
+ * Returns:                SUCCESS or FAILURE
  */
 static int liquidio_set_rxcsum_command(struct net_device *netdev, int command,
 				       u8 rx_cmd)
@@ -2632,13 +2636,14 @@ static int liquidio_set_rxcsum_command(struct net_device *netdev, int command,
 	return ret;
 }
 
-/** Sending command to add/delete VxLAN UDP port to firmware
- * @param netdev                pointer to network device
- * @param command               OCTNET_CMD_VXLAN_PORT_CONFIG
- * @param vxlan_port            VxLAN port to be added or deleted
- * @param vxlan_cmd_bit         OCTNET_CMD_VXLAN_PORT_ADD,
+/**
+ * liquidio_vxlan_port_command - Sending command to add/delete VxLAN UDP port to firmware
+ * @netdev:                pointer to network device
+ * @command:               OCTNET_CMD_VXLAN_PORT_CONFIG
+ * @vxlan_port:            VxLAN port to be added or deleted
+ * @vxlan_cmd_bit:         OCTNET_CMD_VXLAN_PORT_ADD,
  *                              OCTNET_CMD_VXLAN_PORT_DEL
- * @returns                     SUCCESS or FAILURE
+ * Return:                     SUCCESS or FAILURE
  */
 static int liquidio_vxlan_port_command(struct net_device *netdev, int command,
 				       u16 vxlan_port, u8 vxlan_cmd_bit)
@@ -2698,10 +2703,11 @@ static const struct udp_tunnel_nic_info liquidio_udp_tunnels = {
 	},
 };
 
-/** \brief Net device fix features
- * @param netdev  pointer to network device
- * @param request features requested
- * @returns updated features list
+/**
+ * liquidio_fix_features - Net device fix features
+ * @netdev:  pointer to network device
+ * @request: features requested
+ * Return: updated features list
  */
 static netdev_features_t liquidio_fix_features(struct net_device *netdev,
 					       netdev_features_t request)
@@ -2737,9 +2743,10 @@ static netdev_features_t liquidio_fix_features(struct net_device *netdev,
 	return request;
 }
 
-/** \brief Net device set features
- * @param netdev  pointer to network device
- * @param features features to enable/disable
+/**
+ * liquidio_set_features - Net device set features
+ * @netdev:  pointer to network device
+ * @features: features to enable/disable
  */
 static int liquidio_set_features(struct net_device *netdev,
 				 netdev_features_t features)
@@ -3224,7 +3231,8 @@ static const struct net_device_ops lionetdevops = {
 	.ndo_get_port_parent_id	= liquidio_get_port_parent_id,
 };
 
-/** \brief Entry point for the liquidio module
+/**
+ * liquidio_init - Entry point for the liquidio module
  */
 static int __init liquidio_init(void)
 {
@@ -3307,8 +3315,8 @@ nic_info_err:
 }
 
 /**
- * \brief Setup network interfaces
- * @param octeon_dev  octeon device
+ * setup_nic_devices - Setup network interfaces
+ * @octeon_dev:  octeon device
  *
  * Called during init time for each device. It assumes the NIC
  * is already up and running.  The link information for each
@@ -3872,8 +3880,8 @@ static int liquidio_enable_sriov(struct pci_dev *dev, int num_vfs)
 #endif
 
 /**
- * \brief initialize the NIC
- * @param oct octeon device
+ * liquidio_init_nic_module - initialize the NIC
+ * @oct: octeon device
  *
  * This initialization routine is called once the Octeon device application is
  * up and running
@@ -3928,9 +3936,10 @@ octnet_init_failure:
 }
 
 /**
- * \brief starter callback that invokes the remaining initialization work after
- * the NIC is up and running.
- * @param octptr  work struct work_struct
+ * nic_starter - finish init
+ * @work:  work struct work_struct
+ *
+ * starter callback that invokes the remaining initialization work after the NIC is up and running.
  */
 static void nic_starter(struct work_struct *work)
 {
@@ -4023,8 +4032,8 @@ octeon_recv_vf_drv_notice(struct octeon_recv_info *recv_info, void *buf)
 }
 
 /**
- * \brief Device initialization for each Octeon device that is probed
- * @param octeon_dev  octeon device
+ * octeon_device_init - Device initialization for each Octeon device that is probed
+ * @octeon_dev:  octeon device
  */
 static int octeon_device_init(struct octeon_device *octeon_dev)
 {
@@ -4303,11 +4312,11 @@ static int octeon_device_init(struct octeon_device *octeon_dev)
 }
 
 /**
- * \brief Debug console print function
- * @param octeon_dev  octeon device
- * @param console_num console number
- * @param prefix      first portion of line to display
- * @param suffix      second portion of line to display
+ * octeon_dbg_console_print - Debug console print function
+ * @oct:  octeon device
+ * @console_num: console number
+ * @prefix:      first portion of line to display
+ * @suffix:      second portion of line to display
  *
  * The OCTEON debug console outputs entire lines (excluding '\n').
  * Normally, the line will be passed in the 'prefix' parameter.
@@ -4330,7 +4339,7 @@ static int octeon_dbg_console_print(struct octeon_device *oct, u32 console_num,
 }
 
 /**
- * \brief Exits the module
+ * liquidio_exit - Exits the module
  */
 static void __exit liquidio_exit(void)
 {
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c
index 8c5879e31240..103440f97bc8 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c
@@ -99,8 +99,8 @@ static int lio_wait_for_oq_pkts(struct octeon_device *oct)
 }
 
 /**
- * \brief Cause device to go quiet so it can be safely removed/reset/etc
- * @param oct Pointer to Octeon device
+ * pcierror_quiesce_device - Cause device to go quiet so it can be safely removed/reset/etc
+ * @oct: Pointer to Octeon device
  */
 static void pcierror_quiesce_device(struct octeon_device *oct)
 {
@@ -143,8 +143,8 @@ static void pcierror_quiesce_device(struct octeon_device *oct)
 }
 
 /**
- * \brief Cleanup PCI AER uncorrectable error status
- * @param dev Pointer to PCI device
+ * cleanup_aer_uncorrect_error_status - Cleanup PCI AER uncorrectable error status
+ * @dev: Pointer to PCI device
  */
 static void cleanup_aer_uncorrect_error_status(struct pci_dev *dev)
 {
@@ -163,8 +163,8 @@ static void cleanup_aer_uncorrect_error_status(struct pci_dev *dev)
 }
 
 /**
- * \brief Stop all PCI IO to a given device
- * @param dev Pointer to Octeon device
+ * stop_pci_io - Stop all PCI IO to a given device
+ * @oct: Pointer to Octeon device
  */
 static void stop_pci_io(struct octeon_device *oct)
 {
@@ -205,9 +205,9 @@ static void stop_pci_io(struct octeon_device *oct)
 }
 
 /**
- * \brief called when PCI error is detected
- * @param pdev Pointer to PCI device
- * @param state The current pci connection state
+ * liquidio_pcie_error_detected - called when PCI error is detected
+ * @pdev: Pointer to PCI device
+ * @state: The current pci connection state
  *
  * This function is called after a PCI bus error affecting
  * this device has been detected.
@@ -256,8 +256,8 @@ static struct pci_driver liquidio_vf_pci_driver = {
 };
 
 /**
- * \brief Print link information
- * @param netdev network device
+ * print_link_info - Print link information
+ * @netdev: network device
  */
 static void print_link_info(struct net_device *netdev)
 {
@@ -278,8 +278,8 @@ static void print_link_info(struct net_device *netdev)
 }
 
 /**
- * \brief Routine to notify MTU change
- * @param work work_struct data structure
+ * octnet_link_status_change - Routine to notify MTU change
+ * @work: work_struct data structure
  */
 static void octnet_link_status_change(struct work_struct *work)
 {
@@ -296,8 +296,8 @@ static void octnet_link_status_change(struct work_struct *work)
 }
 
 /**
- * \brief Sets up the mtu status change work
- * @param netdev network device
+ * setup_link_status_change_wq - Sets up the mtu status change work
+ * @netdev: network device
  */
 static int setup_link_status_change_wq(struct net_device *netdev)
 {
@@ -328,9 +328,9 @@ static void cleanup_link_status_change_wq(struct net_device *netdev)
 }
 
 /**
- * \brief Update link status
- * @param netdev network device
- * @param ls link status structure
+ * update_link_status - Update link status
+ * @netdev: network device
+ * @ls: link status structure
  *
  * Called on receipt of a link status response from the core application to
  * update each interface's link status.
@@ -374,13 +374,13 @@ static void update_link_status(struct net_device *netdev,
 }
 
 /**
- * \brief PCI probe handler
- * @param pdev PCI device structure
- * @param ent unused
+ * liquidio_vf_probe - PCI probe handler
+ * @pdev: PCI device structure
+ * @ent: unused
  */
 static int
 liquidio_vf_probe(struct pci_dev *pdev,
-		  const struct pci_device_id *ent __attribute__((unused)))
+		  const struct pci_device_id __maybe_unused *ent)
 {
 	struct octeon_device *oct_dev = NULL;
 
@@ -416,8 +416,8 @@ liquidio_vf_probe(struct pci_dev *pdev,
 }
 
 /**
- * \brief PCI FLR for each Octeon device.
- * @param oct octeon device
+ * octeon_pci_flr - PCI FLR for each Octeon device.
+ * @oct: octeon device
  */
 static void octeon_pci_flr(struct octeon_device *oct)
 {
@@ -437,9 +437,8 @@ static void octeon_pci_flr(struct octeon_device *oct)
 }
 
 /**
- *\brief Destroy resources associated with octeon device
- * @param pdev PCI device structure
- * @param ent unused
+ * octeon_destroy_resources - Destroy resources associated with octeon device
+ * @oct: octeon device
  */
 static void octeon_destroy_resources(struct octeon_device *oct)
 {
@@ -592,9 +591,9 @@ static void octeon_destroy_resources(struct octeon_device *oct)
 }
 
 /**
- * \brief Send Rx control command
- * @param lio per-network private data
- * @param start_stop whether to start or stop
+ * send_rx_ctrl_cmd - Send Rx control command
+ * @lio: per-network private data
+ * @start_stop: whether to start or stop
  */
 static void send_rx_ctrl_cmd(struct lio *lio, int start_stop)
 {
@@ -644,9 +643,9 @@ static void send_rx_ctrl_cmd(struct lio *lio, int start_stop)
 }
 
 /**
- * \brief Destroy NIC device interface
- * @param oct octeon device
- * @param ifidx which interface to destroy
+ * liquidio_destroy_nic_device - Destroy NIC device interface
+ * @oct: octeon device
+ * @ifidx: which interface to destroy
  *
  * Cleanup associated with each interface for an Octeon device  when NIC
  * module is being unloaded or if initialization fails during load.
@@ -704,8 +703,8 @@ static void liquidio_destroy_nic_device(struct octeon_device *oct, int ifidx)
 }
 
 /**
- * \brief Stop complete NIC functionality
- * @param oct octeon device
+ * liquidio_stop_nic_module - Stop complete NIC functionality
+ * @oct: octeon device
  */
 static int liquidio_stop_nic_module(struct octeon_device *oct)
 {
@@ -737,8 +736,8 @@ static int liquidio_stop_nic_module(struct octeon_device *oct)
 }
 
 /**
- * \brief Cleans up resources at unload time
- * @param pdev PCI device structure
+ * liquidio_vf_remove - Cleans up resources at unload time
+ * @pdev: PCI device structure
  */
 static void liquidio_vf_remove(struct pci_dev *pdev)
 {
@@ -763,8 +762,8 @@ static void liquidio_vf_remove(struct pci_dev *pdev)
 }
 
 /**
- * \brief PCI initialization for each Octeon device.
- * @param oct octeon device
+ * octeon_pci_os_setup - PCI initialization for each Octeon device.
+ * @oct: octeon device
  */
 static int octeon_pci_os_setup(struct octeon_device *oct)
 {
@@ -792,8 +791,8 @@ static int octeon_pci_os_setup(struct octeon_device *oct)
 }
 
 /**
- * \brief Unmap and free network buffer
- * @param buf buffer
+ * free_netbuf - Unmap and free network buffer
+ * @buf: buffer
  */
 static void free_netbuf(void *buf)
 {
@@ -812,8 +811,8 @@ static void free_netbuf(void *buf)
 }
 
 /**
- * \brief Unmap and free gather buffer
- * @param buf buffer
+ * free_netsgbuf - Unmap and free gather buffer
+ * @buf: buffer
  */
 static void free_netsgbuf(void *buf)
 {
@@ -853,8 +852,8 @@ static void free_netsgbuf(void *buf)
 }
 
 /**
- * \brief Unmap and free gather buffer with response
- * @param buf buffer
+ * free_netsgbuf_with_resp - Unmap and free gather buffer with response
+ * @buf: buffer
  */
 static void free_netsgbuf_with_resp(void *buf)
 {
@@ -897,8 +896,8 @@ static void free_netsgbuf_with_resp(void *buf)
 }
 
 /**
- * \brief Net device open for LiquidIO
- * @param netdev network device
+ * liquidio_open - Net device open for LiquidIO
+ * @netdev: network device
  */
 static int liquidio_open(struct net_device *netdev)
 {
@@ -941,8 +940,8 @@ static int liquidio_open(struct net_device *netdev)
 }
 
 /**
- * \brief Net device stop for LiquidIO
- * @param netdev network device
+ * liquidio_stop - jNet device stop for LiquidIO
+ * @netdev: network device
  */
 static int liquidio_stop(struct net_device *netdev)
 {
@@ -991,8 +990,8 @@ static int liquidio_stop(struct net_device *netdev)
 }
 
 /**
- * \brief Converts a mask based on net device flags
- * @param netdev network device
+ * get_new_flags - Converts a mask based on net device flags
+ * @netdev: network device
  *
  * This routine generates a octnet_ifflags mask from the net device flags
  * received from the OS.
@@ -1060,8 +1059,8 @@ static void liquidio_set_uc_list(struct net_device *netdev)
 }
 
 /**
- * \brief Net device set_multicast_list
- * @param netdev network device
+ * liquidio_set_mcast_list - Net device set_multicast_list
+ * @netdev: network device
  */
 static void liquidio_set_mcast_list(struct net_device *netdev)
 {
@@ -1110,8 +1109,9 @@ static void liquidio_set_mcast_list(struct net_device *netdev)
 }
 
 /**
- * \brief Net device set_mac_address
- * @param netdev network device
+ * liquidio_set_mac - Net device set_mac_address
+ * @netdev: network device
+ * @p: opaque pointer to sockaddr
  */
 static int liquidio_set_mac(struct net_device *netdev, void *p)
 {
@@ -1229,10 +1229,9 @@ liquidio_get_stats64(struct net_device *netdev,
 }
 
 /**
- * \brief Handler for SIOCSHWTSTAMP ioctl
- * @param netdev network device
- * @param ifr interface request
- * @param cmd command
+ * hwtstamp_ioctl - Handler for SIOCSHWTSTAMP ioctl
+ * @netdev: network device
+ * @ifr: interface request
  */
 static int hwtstamp_ioctl(struct net_device *netdev, struct ifreq *ifr)
 {
@@ -1287,10 +1286,10 @@ static int hwtstamp_ioctl(struct net_device *netdev, struct ifreq *ifr)
 }
 
 /**
- * \brief ioctl handler
- * @param netdev network device
- * @param ifr interface request
- * @param cmd command
+ * liquidio_ioctl - ioctl handler
+ * @netdev: network device
+ * @ifr: interface request
+ * @cmd: command
  */
 static int liquidio_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
 {
@@ -1339,10 +1338,10 @@ static void handle_timestamp(struct octeon_device *oct, u32 status, void *buf)
 	tx_buffer_free(skb);
 }
 
-/* \brief Send a data packet that will be timestamped
- * @param oct octeon device
- * @param ndata pointer to network data
- * @param finfo pointer to private network data
+/* send_nic_timestamp_pkt - Send a data packet that will be timestamped
+ * @oct: octeon device
+ * @ndata: pointer to network data
+ * @finfo: pointer to private network data
  */
 static int send_nic_timestamp_pkt(struct octeon_device *oct,
 				  struct octnic_data_pkt *ndata,
@@ -1393,9 +1392,10 @@ static int send_nic_timestamp_pkt(struct octeon_device *oct,
 	return retval;
 }
 
-/** \brief Transmit networks packets to the Octeon interface
- * @param skbuff   skbuff struct to be passed to network layer.
- * @param netdev   pointer to network device
+/**
+ * liquidio_xmit - Transmit networks packets to the Octeon interface
+ * @skb: skbuff struct to be passed to network layer.
+ * @netdev: pointer to network device
  * @returns whether the packet was transmitted to the device okay or not
  *             (NETDEV_TX_OK or NETDEV_TX_BUSY)
  */
@@ -1623,8 +1623,10 @@ lio_xmit_failed:
 	return NETDEV_TX_OK;
 }
 
-/** \brief Network device Tx timeout
- * @param netdev    pointer to network device
+/**
+ * liquidio_tx_timeout - Network device Tx timeout
+ * @netdev: pointer to network device
+ * @txqueue: index of the hung transmit queue
  */
 static void liquidio_tx_timeout(struct net_device *netdev, unsigned int txqueue)
 {
@@ -1917,8 +1919,8 @@ nic_info_err:
 }
 
 /**
- * \brief Setup network interfaces
- * @param octeon_dev  octeon device
+ * setup_nic_devices - Setup network interfaces
+ * @octeon_dev:  octeon device
  *
  * Called during init time for each device. It assumes the NIC
  * is already up and running.  The link information for each
@@ -2229,8 +2231,8 @@ setup_nic_dev_done:
 }
 
 /**
- * \brief initialize the NIC
- * @param oct octeon device
+ * liquidio_init_nic_module - initialize the NIC
+ * @oct: octeon device
  *
  * This initialization routine is called once the Octeon device application is
  * up and running
@@ -2270,8 +2272,8 @@ octnet_init_failure:
 }
 
 /**
- * \brief Device initialization for each Octeon device that is probed
- * @param octeon_dev  octeon device
+ * octeon_device_init - Device initialization for each Octeon device that is probed
+ * @oct:  octeon device
  */
 static int octeon_device_init(struct octeon_device *oct)
 {
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_console.c b/drivers/net/ethernet/cavium/liquidio/octeon_console.c
index 0d2831d10f65..28feabec8fbb 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_console.c
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_console.c
@@ -15,7 +15,7 @@
  * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
  * NONINFRINGEMENT.  See the GNU General Public License for more details.
  ***********************************************************************/
-/**
+/*
  * @file octeon_console.c
  */
 #include <linux/moduleparam.h>
@@ -131,7 +131,7 @@ struct octeon_pci_console_desc {
 	/* Implicit storage for console_addr_array */
 };
 
-/**
+/*
  * This function is the implementation of the get macros defined
  * for individual structure members. The argument are generated
  * by the macros inorder to read only the needed memory.
@@ -160,7 +160,7 @@ static inline u64 __cvmx_bootmem_desc_get(struct octeon_device *oct,
 	}
 }
 
-/**
+/*
  * This function retrieves the string name of a named block. It is
  * more complicated than a simple memcpy() since the named block
  * descriptor may not be directly accessible.
@@ -182,7 +182,7 @@ static void CVMX_BOOTMEM_NAMED_GET_NAME(struct octeon_device *oct,
 
 /* See header file for descriptions of functions */
 
-/**
+/*
  * Check the version information on the bootmem descriptor
  *
  * @param exact_match
@@ -323,7 +323,7 @@ static u64 cvmx_bootmem_phy_named_block_find(struct octeon_device *oct,
 	return result;
 }
 
-/**
+/*
  * Find a named block on the remote Octeon
  *
  * @param name      Name of block to find
@@ -707,7 +707,7 @@ int octeon_add_console(struct octeon_device *oct, u32 console_num,
 	return ret;
 }
 
-/**
+/*
  * Removes all consoles
  *
  * @param oct         octeon device
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_device.c b/drivers/net/ethernet/cavium/liquidio/octeon_device.c
index fbde7c58c4db..387a57cbfb73 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_device.c
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_device.c
@@ -1307,7 +1307,7 @@ struct octeon_config *octeon_get_conf(struct octeon_device *oct)
 /* scratch register address is same in all the OCT-II and CN70XX models */
 #define CNXX_SLI_SCRATCH1   0x3C0
 
-/** Get the octeon device pointer.
+/* Get the octeon device pointer.
  *  @param octeon_id  - The id for which the octeon device pointer is required.
  *  @return Success: Octeon device pointer.
  *  @return Failure: NULL.
@@ -1410,7 +1410,7 @@ int octeon_wait_for_ddr_init(struct octeon_device *oct, u32 *timeout)
 	return ret;
 }
 
-/** Get the octeon id assigned to the octeon device passed as argument.
+/* Get the octeon id assigned to the octeon device passed as argument.
  *  This function is exported to other modules.
  *  @param dev - octeon device pointer passed as a void *.
  *  @return octeon device id
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_droq.c b/drivers/net/ethernet/cavium/liquidio/octeon_droq.c
index cf4fe5b17f8a..d4080bddcb6b 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_droq.c
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_droq.c
@@ -774,7 +774,7 @@ octeon_droq_process_packets(struct octeon_device *oct,
 	return 0;
 }
 
-/**
+/*
  * Utility function to poll for packets. check_hw_for_packets must be
  * called before calling this routine.
  */
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.c b/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.c
index 614d07be7181..ad685f5d0a13 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.c
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.c
@@ -28,7 +28,7 @@
 
 /**
  * octeon_mbox_read:
- * @oct: Pointer mailbox
+ * @mbox: Pointer mailbox
  *
  * Reads the 8-bytes of data from the mbox register
  * Writes back the acknowldgement inidcating completion of read
@@ -285,7 +285,8 @@ static int octeon_mbox_process_cmd(struct octeon_mbox *mbox,
 }
 
 /**
- *octeon_mbox_process_message:
+ * octeon_mbox_process_message
+ * @mbox: mailbox
  *
  * Process the received mbox message.
  */
diff --git a/drivers/net/ethernet/chelsio/cxgb3/adapter.h b/drivers/net/ethernet/chelsio/cxgb3/adapter.h
index 087ff0ffb597..f80fbd81b609 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/adapter.h
+++ b/drivers/net/ethernet/chelsio/cxgb3/adapter.h
@@ -313,6 +313,7 @@ void t3_os_link_fault(struct adapter *adapter, int port_id, int state);
 void t3_os_link_fault_handler(struct adapter *adapter, int port_id);
 
 void t3_sge_start(struct adapter *adap);
+void t3_sge_stop_dma(struct adapter *adap);
 void t3_sge_stop(struct adapter *adap);
 void t3_start_sge_timers(struct adapter *adap);
 void t3_stop_sge_timers(struct adapter *adap);
diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
index 387c357e1b8e..84ad7261e243 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
@@ -148,7 +148,7 @@ struct workqueue_struct *cxgb3_wq;
 
 /**
  *	link_report - show link status and link speed/duplex
- *	@p: the port whose settings are to be reported
+ *	@dev: the port whose settings are to be reported
  *
  *	Shows the link status, speed, and duplex of a port.
  */
@@ -304,8 +304,8 @@ void t3_os_link_changed(struct adapter *adapter, int port_id, int link_stat,
 
 /**
  *	t3_os_phymod_changed - handle PHY module changes
- *	@phy: the PHY reporting the module change
- *	@mod_type: new module type
+ *	@adap: the adapter associated with the link change
+ *	@port_id: the port index whose limk status has changed
  *
  *	This is the OS-dependent handler for PHY module changes.  It is
  *	invoked when a PHY module is removed or inserted for any OS-specific
@@ -1200,7 +1200,7 @@ static void cxgb_vlan_mode(struct net_device *dev, netdev_features_t features)
 
 /**
  *	cxgb_up - enable the adapter
- *	@adapter: adapter being enabled
+ *	@adap: adapter being enabled
  *
  *	Called when the first port is enabled, this function performs the
  *	actions necessary to make an adapter operational, such as completing
@@ -2996,7 +2996,7 @@ void t3_fatal_err(struct adapter *adapter)
 	unsigned int fw_status[4];
 
 	if (adapter->flags & FULL_INIT_DONE) {
-		t3_sge_stop(adapter);
+		t3_sge_stop_dma(adapter);
 		t3_write_reg(adapter, A_XGM_TX_CTRL, 0);
 		t3_write_reg(adapter, A_XGM_RX_CTRL, 0);
 		t3_write_reg(adapter, XGM_REG(A_XGM_TX_CTRL, 1), 0);
diff --git a/drivers/net/ethernet/chelsio/cxgb3/sge.c b/drivers/net/ethernet/chelsio/cxgb3/sge.c
index a978a00acc1e..e18e9ce27f94 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb3/sge.c
@@ -372,7 +372,7 @@ static void clear_rx_desc(struct pci_dev *pdev, const struct sge_fl *q,
 /**
  *	free_rx_bufs - free the Rx buffers on an SGE free list
  *	@pdev: the PCI device associated with the adapter
- *	@rxq: the SGE free list to clean up
+ *	@q: the SGE free list to clean up
  *
  *	Release the buffers on an SGE free-buffer Rx queue.  HW fetching from
  *	this queue should be stopped before calling this function.
@@ -493,7 +493,7 @@ static inline void ring_fl_db(struct adapter *adap, struct sge_fl *q)
 
 /**
  *	refill_fl - refill an SGE free-buffer list
- *	@adapter: the adapter
+ *	@adap: the adapter
  *	@q: the free-list to refill
  *	@n: the number of new buffers to allocate
  *	@gfp: the gfp flags for allocating new buffers
@@ -568,7 +568,7 @@ static inline void __refill_fl(struct adapter *adap, struct sge_fl *fl)
 
 /**
  *	recycle_rx_buf - recycle a receive buffer
- *	@adapter: the adapter
+ *	@adap: the adapter
  *	@q: the SGE free list
  *	@idx: index of buffer to recycle
  *
@@ -825,6 +825,7 @@ use_orig_buf:
  *	get_packet_pg - return the next ingress packet buffer from a free list
  *	@adap: the adapter that received the packet
  *	@fl: the SGE free list holding the packet
+ *	@q: the queue
  *	@len: the packet length including any SGE padding
  *	@drop_thres: # of remaining buffers before we start dropping packets
  *
@@ -1173,6 +1174,7 @@ static void write_wr_hdr_sgl(unsigned int ndesc, struct sk_buff *skb,
  *	@q: the Tx queue
  *	@ndesc: number of descriptors the packet will occupy
  *	@compl: the value of the COMPL bit to use
+ *	@addr: address
  *
  *	Generate a TX_PKT work request to send the supplied packet.
  */
@@ -1622,6 +1624,7 @@ static void setup_deferred_unmapping(struct sk_buff *skb, struct pci_dev *pdev,
  *	@pidx: index of the first Tx descriptor to write
  *	@gen: the generation value to use
  *	@ndesc: number of descriptors the packet will occupy
+ *	@addr: the address
  *
  *	Write an offload work request to send the supplied packet.  The packet
  *	data already carry the work request with most fields populated.
@@ -1883,7 +1886,7 @@ static inline void deliver_partial_bundle(struct t3cdev *tdev,
 
 /**
  *	ofld_poll - NAPI handler for offload packets in interrupt mode
- *	@dev: the network device doing the polling
+ *	@napi: the network device doing the polling
  *	@budget: polling budget
  *
  *	The NAPI handler for offload packets when a response queue is serviced
@@ -2007,7 +2010,7 @@ static void restart_tx(struct sge_qset *qs)
 
 /**
  *	cxgb3_arp_process - process an ARP request probing a private IP address
- *	@adapter: the adapter
+ *	@pi: the port info
  *	@skb: the skbuff containing the ARP request
  *
  *	Check if the ARP request is probing the private IP address
@@ -2069,7 +2072,8 @@ static void cxgb3_process_iscsi_prov_pack(struct port_info *pi,
  *	@adap: the adapter
  *	@rq: the response queue that received the packet
  *	@skb: the packet
- *	@pad: amount of padding at the start of the buffer
+ *	@pad: padding
+ *	@lro: large receive offload
  *
  *	Process an ingress ethernet pakcet and deliver it to the stack.
  *	The padding is 2 if the packet was delivered in an Rx buffer and 0
@@ -2239,7 +2243,7 @@ static inline void handle_rsp_cntrl_info(struct sge_qset *qs, u32 flags)
 
 /**
  *	check_ring_db - check if we need to ring any doorbells
- *	@adapter: the adapter
+ *	@adap: the adapter
  *	@qs: the queue set whose Tx queues are to be examined
  *	@sleeping: indicates which Tx queue sent GTS
  *
@@ -2899,7 +2903,7 @@ void t3_sge_err_intr_handler(struct adapter *adapter)
 
 /**
  *	sge_timer_tx - perform periodic maintenance of an SGE qset
- *	@data: the SGE queue set to maintain
+ *	@t: a timer list containing the SGE queue set to maintain
  *
  *	Runs periodically from a timer to perform maintenance of an SGE queue
  *	set.  It performs two tasks:
@@ -2943,7 +2947,7 @@ static void sge_timer_tx(struct timer_list *t)
 
 /**
  *	sge_timer_rx - perform periodic maintenance of an SGE qset
- *	@data: the SGE queue set to maintain
+ *	@t: the timer list containing the SGE queue set to maintain
  *
  *	a) Replenishes Rx queues that have run out due to memory shortage.
  *	Normally new Rx buffers are added when existing ones are consumed but
@@ -3021,7 +3025,7 @@ void t3_update_qset_coalesce(struct sge_qset *qs, const struct qset_params *p)
  *	@irq_vec_idx: the IRQ vector index for response queue interrupts
  *	@p: configuration parameters for this queue set
  *	@ntxq: number of Tx queues for the queue set
- *	@netdev: net device associated with this queue set
+ *	@dev: net device associated with this queue set
  *	@netdevq: net device TX queue associated with this queue set
  *
  *	Allocate resources and initialize an SGE queue set.  A queue set
@@ -3266,30 +3270,40 @@ void t3_sge_start(struct adapter *adap)
 }
 
 /**
- *	t3_sge_stop - disable SGE operation
+ *	t3_sge_stop_dma - Disable SGE DMA engine operation
  *	@adap: the adapter
  *
- *	Disables the DMA engine.  This can be called in emeregencies (e.g.,
- *	from error interrupts) or from normal process context.  In the latter
- *	case it also disables any pending queue restart tasklets.  Note that
- *	if it is called in interrupt context it cannot disable the restart
- *	tasklets as it cannot wait, however the tasklets will have no effect
- *	since the doorbells are disabled and the driver will call this again
- *	later from process context, at which time the tasklets will be stopped
- *	if they are still running.
+ *	Can be invoked from interrupt context e.g.  error handler.
+ *
+ *	Note that this function cannot disable the restart of tasklets as
+ *	it cannot wait if called from interrupt context, however the
+ *	tasklets will have no effect since the doorbells are disabled. The
+ *	driver will call tg3_sge_stop() later from process context, at
+ *	which time the tasklets will be stopped if they are still running.
  */
-void t3_sge_stop(struct adapter *adap)
+void t3_sge_stop_dma(struct adapter *adap)
 {
 	t3_set_reg_field(adap, A_SG_CONTROL, F_GLOBALENABLE, 0);
-	if (!in_interrupt()) {
-		int i;
+}
 
-		for (i = 0; i < SGE_QSETS; ++i) {
-			struct sge_qset *qs = &adap->sge.qs[i];
+/**
+ *	t3_sge_stop - disable SGE operation completly
+ *	@adap: the adapter
+ *
+ *	Called from process context. Disables the DMA engine and any
+ *	pending queue restart tasklets.
+ */
+void t3_sge_stop(struct adapter *adap)
+{
+	int i;
 
-			tasklet_kill(&qs->txq[TXQ_OFLD].qresume_tsk);
-			tasklet_kill(&qs->txq[TXQ_CTRL].qresume_tsk);
-		}
+	t3_sge_stop_dma(adap);
+
+	for (i = 0; i < SGE_QSETS; ++i) {
+		struct sge_qset *qs = &adap->sge.qs[i];
+
+		tasklet_kill(&qs->txq[TXQ_OFLD].qresume_tsk);
+		tasklet_kill(&qs->txq[TXQ_CTRL].qresume_tsk);
 	}
 }
 
diff --git a/drivers/net/ethernet/chelsio/cxgb3/t3_hw.c b/drivers/net/ethernet/chelsio/cxgb3/t3_hw.c
index 311fed38c101..7ff31d1026fb 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/t3_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb3/t3_hw.c
@@ -2484,6 +2484,7 @@ int t3_sge_disable_cqcntxt(struct adapter *adapter, unsigned int id)
  *	@adapter: the adapter
  *	@id: the context id
  *	@op: the operation to perform
+ *	@credits: credit value to write
  *
  *	Perform the selected operation on an SGE completion queue context.
  *	The caller is responsible for ensuring only one context operation
@@ -2885,7 +2886,7 @@ static void init_cong_ctrl(unsigned short *a, unsigned short *b)
  *	t3_load_mtus - write the MTU and congestion control HW tables
  *	@adap: the adapter
  *	@mtus: the unrestricted values for the MTU table
- *	@alphs: the values for the congestion control alpha parameter
+ *	@alpha: the values for the congestion control alpha parameter
  *	@beta: the values for the congestion control beta parameter
  *	@mtu_cap: the maximum permitted effective MTU
  *
@@ -3483,7 +3484,7 @@ static void get_pci_mode(struct adapter *adapter, struct pci_params *p)
 /**
  *	init_link_config - initialize a link's SW state
  *	@lc: structure holding the link state
- *	@ai: information about the current card
+ *	@caps: information about the current card
  *
  *	Initializes the SW state maintained for each link, including the link's
  *	capabilities and default speed/duplex/flow-control/autonegotiation
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
index 5491a41fd1be..0273f40b85f7 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
@@ -3527,6 +3527,10 @@ DEFINE_SHOW_ATTRIBUTE(meminfo);
 
 static int chcr_stats_show(struct seq_file *seq, void *v)
 {
+#if IS_ENABLED(CONFIG_CHELSIO_TLS_DEVICE)
+	struct ch_ktls_port_stats_debug *ktls_port;
+	int i = 0;
+#endif
 	struct adapter *adap = seq->private;
 
 	seq_puts(seq, "Chelsio Crypto Accelerator Stats \n");
@@ -3557,18 +3561,6 @@ static int chcr_stats_show(struct seq_file *seq, void *v)
 	seq_puts(seq, "\nChelsio KTLS Crypto Accelerator Stats\n");
 	seq_printf(seq, "Tx TLS offload refcount:          %20u\n",
 		   refcount_read(&adap->chcr_ktls.ktls_refcount));
-	seq_printf(seq, "Tx HW offload contexts added:     %20llu\n",
-		   atomic64_read(&adap->ch_ktls_stats.ktls_tx_ctx));
-	seq_printf(seq, "Tx connection created:            %20llu\n",
-		   atomic64_read(&adap->ch_ktls_stats.ktls_tx_connection_open));
-	seq_printf(seq, "Tx connection failed:             %20llu\n",
-		   atomic64_read(&adap->ch_ktls_stats.ktls_tx_connection_fail));
-	seq_printf(seq, "Tx connection closed:             %20llu\n",
-		   atomic64_read(&adap->ch_ktls_stats.ktls_tx_connection_close));
-	seq_printf(seq, "Packets passed for encryption :   %20llu\n",
-		   atomic64_read(&adap->ch_ktls_stats.ktls_tx_encrypted_packets));
-	seq_printf(seq, "Bytes passed for encryption :     %20llu\n",
-		   atomic64_read(&adap->ch_ktls_stats.ktls_tx_encrypted_bytes));
 	seq_printf(seq, "Tx records send:                  %20llu\n",
 		   atomic64_read(&adap->ch_ktls_stats.ktls_tx_send_records));
 	seq_printf(seq, "Tx partial start of records:      %20llu\n",
@@ -3581,14 +3573,17 @@ static int chcr_stats_show(struct seq_file *seq, void *v)
 		   atomic64_read(&adap->ch_ktls_stats.ktls_tx_complete_pkts));
 	seq_printf(seq, "TX trim pkts :                    %20llu\n",
 		   atomic64_read(&adap->ch_ktls_stats.ktls_tx_trimmed_pkts));
-	seq_printf(seq, "Tx out of order packets:          %20llu\n",
-		   atomic64_read(&adap->ch_ktls_stats.ktls_tx_ooo));
-	seq_printf(seq, "Tx drop pkts before HW offload:   %20llu\n",
-		   atomic64_read(&adap->ch_ktls_stats.ktls_tx_skip_no_sync_data));
-	seq_printf(seq, "Tx drop not synced packets:       %20llu\n",
-		   atomic64_read(&adap->ch_ktls_stats.ktls_tx_drop_no_sync_data));
-	seq_printf(seq, "Tx drop bypass req:               %20llu\n",
-		   atomic64_read(&adap->ch_ktls_stats.ktls_tx_drop_bypass_req));
+	while (i < MAX_NPORTS) {
+		ktls_port = &adap->ch_ktls_stats.ktls_port[i];
+		seq_printf(seq, "Port %d\n", i);
+		seq_printf(seq, "Tx connection created:            %20llu\n",
+			   atomic64_read(&ktls_port->ktls_tx_connection_open));
+		seq_printf(seq, "Tx connection failed:             %20llu\n",
+			   atomic64_read(&ktls_port->ktls_tx_connection_fail));
+		seq_printf(seq, "Tx connection closed:             %20llu\n",
+			   atomic64_read(&ktls_port->ktls_tx_connection_close));
+		i++;
+	}
 #endif
 	return 0;
 }
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
index 8c6c9bedcba1..61ea3ec5c3fc 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
@@ -117,14 +117,6 @@ static const char stats_strings[][ETH_GSTRING_LEN] = {
 	"vlan_insertions        ",
 	"gro_packets            ",
 	"gro_merged             ",
-};
-
-static char adapter_stats_strings[][ETH_GSTRING_LEN] = {
-	"db_drop                ",
-	"db_full                ",
-	"db_empty               ",
-	"write_coal_success     ",
-	"write_coal_fail        ",
 #if  IS_ENABLED(CONFIG_CHELSIO_TLS_DEVICE)
 	"tx_tls_encrypted_packets",
 	"tx_tls_encrypted_bytes  ",
@@ -136,6 +128,14 @@ static char adapter_stats_strings[][ETH_GSTRING_LEN] = {
 #endif
 };
 
+static char adapter_stats_strings[][ETH_GSTRING_LEN] = {
+	"db_drop                ",
+	"db_full                ",
+	"db_empty               ",
+	"write_coal_success     ",
+	"write_coal_fail        ",
+};
+
 static char loopback_stats_strings[][ETH_GSTRING_LEN] = {
 	"-------Loopback----------- ",
 	"octets_ok              ",
@@ -257,14 +257,6 @@ struct queue_port_stats {
 	u64 vlan_ins;
 	u64 gro_pkts;
 	u64 gro_merged;
-};
-
-struct adapter_stats {
-	u64 db_drop;
-	u64 db_full;
-	u64 db_empty;
-	u64 wc_success;
-	u64 wc_fail;
 #if IS_ENABLED(CONFIG_CHELSIO_TLS_DEVICE)
 	u64 tx_tls_encrypted_packets;
 	u64 tx_tls_encrypted_bytes;
@@ -276,12 +268,23 @@ struct adapter_stats {
 #endif
 };
 
+struct adapter_stats {
+	u64 db_drop;
+	u64 db_full;
+	u64 db_empty;
+	u64 wc_success;
+	u64 wc_fail;
+};
+
 static void collect_sge_port_stats(const struct adapter *adap,
 				   const struct port_info *p,
 				   struct queue_port_stats *s)
 {
 	const struct sge_eth_txq *tx = &adap->sge.ethtxq[p->first_qset];
 	const struct sge_eth_rxq *rx = &adap->sge.ethrxq[p->first_qset];
+#if IS_ENABLED(CONFIG_CHELSIO_TLS_DEVICE)
+	const struct ch_ktls_port_stats_debug *ktls_stats;
+#endif
 	struct sge_eohw_txq *eohw_tx;
 	unsigned int i;
 
@@ -306,6 +309,21 @@ static void collect_sge_port_stats(const struct adapter *adap,
 			s->vlan_ins += eohw_tx->vlan_ins;
 		}
 	}
+#if IS_ENABLED(CONFIG_CHELSIO_TLS_DEVICE)
+	ktls_stats = &adap->ch_ktls_stats.ktls_port[p->port_id];
+	s->tx_tls_encrypted_packets =
+		atomic64_read(&ktls_stats->ktls_tx_encrypted_packets);
+	s->tx_tls_encrypted_bytes =
+		atomic64_read(&ktls_stats->ktls_tx_encrypted_bytes);
+	s->tx_tls_ctx = atomic64_read(&ktls_stats->ktls_tx_ctx);
+	s->tx_tls_ooo = atomic64_read(&ktls_stats->ktls_tx_ooo);
+	s->tx_tls_skip_no_sync_data =
+		atomic64_read(&ktls_stats->ktls_tx_skip_no_sync_data);
+	s->tx_tls_drop_no_sync_data =
+		atomic64_read(&ktls_stats->ktls_tx_drop_no_sync_data);
+	s->tx_tls_drop_bypass_req =
+		atomic64_read(&ktls_stats->ktls_tx_drop_bypass_req);
+#endif
 }
 
 static void collect_adapter_stats(struct adapter *adap, struct adapter_stats *s)
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
index f6c1ec140e09..6ec5f2f26f05 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
@@ -1908,13 +1908,16 @@ out:
 static int configure_filter_tcb(struct adapter *adap, unsigned int tid,
 				struct filter_entry *f)
 {
-	if (f->fs.hitcnts)
+	if (f->fs.hitcnts) {
 		set_tcb_field(adap, f, tid, TCB_TIMESTAMP_W,
-			      TCB_TIMESTAMP_V(TCB_TIMESTAMP_M) |
+			      TCB_TIMESTAMP_V(TCB_TIMESTAMP_M),
+			      TCB_TIMESTAMP_V(0ULL),
+			      1);
+		set_tcb_field(adap, f, tid, TCB_RTT_TS_RECENT_AGE_W,
 			      TCB_RTT_TS_RECENT_AGE_V(TCB_RTT_TS_RECENT_AGE_M),
-			      TCB_TIMESTAMP_V(0ULL) |
 			      TCB_RTT_TS_RECENT_AGE_V(0ULL),
 			      1);
+	}
 
 	if (f->fs.newdmac)
 		set_tcb_tflag(adap, f, tid, TF_CCTRL_ECE_S, 1,
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_mps.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_mps.c
index b1a073eea60b..a020e8490681 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_mps.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_mps.c
@@ -229,7 +229,7 @@ void cxgb4_free_mps_ref_entries(struct adapter *adap)
 {
 	struct mps_entries_ref *mps_entry, *tmp;
 
-	if (!list_empty(&adap->mps_ref))
+	if (list_empty(&adap->mps_ref))
 		return;
 
 	spin_lock(&adap->mps_ref_lock);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c
index b154190e1ee2..743af9e654aa 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c
@@ -690,8 +690,8 @@ int cxgb4_set_ktls_feature(struct adapter *adap, bool enable)
 			 * ULD is/are already active, return failure.
 			 */
 			if (cxgb4_uld_in_use(adap)) {
-				dev_warn(adap->pdev_dev,
-					 "ULD connections (tid/stid) active. Can't enable kTLS\n");
+				dev_dbg(adap->pdev_dev,
+					"ULD connections (tid/stid) active. Can't enable kTLS\n");
 				return -EINVAL;
 			}
 			ret = t4_set_params(adap, adap->mbox, adap->pf,
@@ -699,7 +699,7 @@ int cxgb4_set_ktls_feature(struct adapter *adap, bool enable)
 			if (ret)
 				return ret;
 			refcount_set(&adap->chcr_ktls.ktls_refcount, 1);
-			pr_info("kTLS has been enabled. Restrictions placed on ULD support\n");
+			pr_debug("kTLS has been enabled. Restrictions placed on ULD support\n");
 		} else {
 			/* ktls settings already up, just increment refcount. */
 			refcount_inc(&adap->chcr_ktls.ktls_refcount);
@@ -716,7 +716,7 @@ int cxgb4_set_ktls_feature(struct adapter *adap, bool enable)
 					    0, 1, &params, &params);
 			if (ret)
 				return ret;
-			pr_info("kTLS is disabled. Restrictions on ULD support removed\n");
+			pr_debug("kTLS is disabled. Restrictions on ULD support removed\n");
 		}
 	}
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
index ea2fabbdd934..b169776ab484 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
@@ -44,6 +44,7 @@
 #include "cxgb4.h"
 
 #define MAX_ULD_QSETS 16
+#define MAX_ULD_NPORTS 4
 
 /* CPL message priority levels */
 enum {
@@ -365,17 +366,10 @@ struct cxgb4_virt_res {                      /* virtualized HW resources */
 };
 
 #if IS_ENABLED(CONFIG_CHELSIO_TLS_DEVICE)
-struct ch_ktls_stats_debug {
+struct ch_ktls_port_stats_debug {
 	atomic64_t ktls_tx_connection_open;
 	atomic64_t ktls_tx_connection_fail;
 	atomic64_t ktls_tx_connection_close;
-	atomic64_t ktls_tx_send_records;
-	atomic64_t ktls_tx_end_pkts;
-	atomic64_t ktls_tx_start_pkts;
-	atomic64_t ktls_tx_middle_pkts;
-	atomic64_t ktls_tx_retransmit_pkts;
-	atomic64_t ktls_tx_complete_pkts;
-	atomic64_t ktls_tx_trimmed_pkts;
 	atomic64_t ktls_tx_encrypted_packets;
 	atomic64_t ktls_tx_encrypted_bytes;
 	atomic64_t ktls_tx_ctx;
@@ -384,6 +378,17 @@ struct ch_ktls_stats_debug {
 	atomic64_t ktls_tx_drop_no_sync_data;
 	atomic64_t ktls_tx_drop_bypass_req;
 };
+
+struct ch_ktls_stats_debug {
+	struct ch_ktls_port_stats_debug ktls_port[MAX_ULD_NPORTS];
+	atomic64_t ktls_tx_send_records;
+	atomic64_t ktls_tx_end_pkts;
+	atomic64_t ktls_tx_start_pkts;
+	atomic64_t ktls_tx_middle_pkts;
+	atomic64_t ktls_tx_retransmit_pkts;
+	atomic64_t ktls_tx_complete_pkts;
+	atomic64_t ktls_tx_trimmed_pkts;
+};
 #endif
 
 struct chcr_stats_debug {
diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c
index 2b942b4825d4..54e22f17af3d 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c
@@ -4872,9 +4872,6 @@ void t4_sge_stop(struct adapter *adap)
 	int i;
 	struct sge *s = &adap->sge;
 
-	if (in_interrupt())  /* actions below require waiting */
-		return;
-
 	if (s->rx_timer.function)
 		del_timer_sync(&s->rx_timer);
 	if (s->tx_timer.function)
diff --git a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c
index 4609f1f78426..5195f692f14d 100644
--- a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c
+++ b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c
@@ -125,60 +125,6 @@ out:
 	return ret;
 }
 
-static int chcr_ktls_update_connection_state(struct chcr_ktls_info *tx_info,
-					     int new_state)
-{
-	/* This function can be called from both rx (interrupt context) and tx
-	 * queue contexts.
-	 */
-	spin_lock_bh(&tx_info->lock);
-	switch (tx_info->connection_state) {
-	case KTLS_CONN_CLOSED:
-		tx_info->connection_state = new_state;
-		break;
-
-	case KTLS_CONN_ACT_OPEN_REQ:
-		/* only go forward if state is greater than current state. */
-		if (new_state <= tx_info->connection_state)
-			break;
-		/* update to the next state and also initialize TCB */
-		tx_info->connection_state = new_state;
-		fallthrough;
-	case KTLS_CONN_ACT_OPEN_RPL:
-		/* if we are stuck in this state, means tcb init might not
-		 * received by HW, try sending it again.
-		 */
-		if (!chcr_init_tcb_fields(tx_info))
-			tx_info->connection_state = KTLS_CONN_SET_TCB_REQ;
-		break;
-
-	case KTLS_CONN_SET_TCB_REQ:
-		/* only go forward if state is greater than current state. */
-		if (new_state <= tx_info->connection_state)
-			break;
-		/* update to the next state and check if l2t_state is valid  */
-		tx_info->connection_state = new_state;
-		fallthrough;
-	case KTLS_CONN_SET_TCB_RPL:
-		/* Check if l2t state is valid, then move to ready state. */
-		if (cxgb4_check_l2t_valid(tx_info->l2te)) {
-			tx_info->connection_state = KTLS_CONN_TX_READY;
-			atomic64_inc(&tx_info->adap->ch_ktls_stats.ktls_tx_ctx);
-		}
-		break;
-
-	case KTLS_CONN_TX_READY:
-		/* nothing to be done here */
-		break;
-
-	default:
-		pr_err("unknown KTLS connection state\n");
-		break;
-	}
-	spin_unlock_bh(&tx_info->lock);
-
-	return tx_info->connection_state;
-}
 /*
  * chcr_ktls_act_open_req: creates TCB entry for ipv4 connection.
  * @sk - tcp socket.
@@ -298,27 +244,17 @@ static int chcr_setup_connection(struct sock *sk,
 		return -EINVAL;
 
 	tx_info->atid = atid;
-	tx_info->ip_family = sk->sk_family;
 
-	if (sk->sk_family == AF_INET) {
-		tx_info->ip_family = AF_INET;
+	if (tx_info->ip_family == AF_INET) {
 		ret = chcr_ktls_act_open_req(sk, tx_info, atid);
 #if IS_ENABLED(CONFIG_IPV6)
 	} else {
-		if (!sk->sk_ipv6only &&
-		    ipv6_addr_type(&sk->sk_v6_daddr) == IPV6_ADDR_MAPPED) {
-			tx_info->ip_family = AF_INET;
-			ret = chcr_ktls_act_open_req(sk, tx_info, atid);
-		} else {
-			tx_info->ip_family = AF_INET6;
-			ret = cxgb4_clip_get(tx_info->netdev,
-					     (const u32 *)
-					     &sk->sk_v6_rcv_saddr.s6_addr,
-					     1);
-			if (ret)
-				goto out;
-			ret = chcr_ktls_act_open_req6(sk, tx_info, atid);
-		}
+		ret = cxgb4_clip_get(tx_info->netdev, (const u32 *)
+				     &sk->sk_v6_rcv_saddr,
+				     1);
+		if (ret)
+			return ret;
+		ret = chcr_ktls_act_open_req6(sk, tx_info, atid);
 #endif
 	}
 
@@ -326,16 +262,21 @@ static int chcr_setup_connection(struct sock *sk,
 	 * success, if any other return type clear atid and return that failure.
 	 */
 	if (ret) {
-		if (ret == NET_XMIT_CN)
+		if (ret == NET_XMIT_CN) {
 			ret = 0;
-		else
+		} else {
+#if IS_ENABLED(CONFIG_IPV6)
+			/* clear clip entry */
+			if (tx_info->ip_family == AF_INET6)
+				cxgb4_clip_release(tx_info->netdev,
+						   (const u32 *)
+						   &sk->sk_v6_rcv_saddr,
+						   1);
+#endif
 			cxgb4_free_atid(t, atid);
-		goto out;
+		}
 	}
 
-	/* update the connection state */
-	chcr_ktls_update_connection_state(tx_info, KTLS_CONN_ACT_OPEN_REQ);
-out:
 	return ret;
 }
 
@@ -396,15 +337,10 @@ static void chcr_ktls_dev_del(struct net_device *netdev,
 	struct chcr_ktls_ofld_ctx_tx *tx_ctx =
 				chcr_get_ktls_tx_context(tls_ctx);
 	struct chcr_ktls_info *tx_info = tx_ctx->chcr_info;
-	struct sock *sk;
+	struct ch_ktls_port_stats_debug *port_stats;
 
 	if (!tx_info)
 		return;
-	sk = tx_info->sk;
-
-	spin_lock(&tx_info->lock);
-	tx_info->connection_state = KTLS_CONN_CLOSED;
-	spin_unlock(&tx_info->lock);
 
 	/* clear l2t entry */
 	if (tx_info->l2te)
@@ -413,8 +349,8 @@ static void chcr_ktls_dev_del(struct net_device *netdev,
 #if IS_ENABLED(CONFIG_IPV6)
 	/* clear clip entry */
 	if (tx_info->ip_family == AF_INET6)
-		cxgb4_clip_release(netdev,
-				   (const u32 *)&sk->sk_v6_daddr.in6_u.u6_addr8,
+		cxgb4_clip_release(netdev, (const u32 *)
+				   &tx_info->sk->sk_v6_rcv_saddr,
 				   1);
 #endif
 
@@ -426,7 +362,8 @@ static void chcr_ktls_dev_del(struct net_device *netdev,
 				 tx_info->tid, tx_info->ip_family);
 	}
 
-	atomic64_inc(&tx_info->adap->ch_ktls_stats.ktls_tx_connection_close);
+	port_stats = &tx_info->adap->ch_ktls_stats.ktls_port[tx_info->port_id];
+	atomic64_inc(&port_stats->ktls_tx_connection_close);
 	kvfree(tx_info);
 	tx_ctx->chcr_info = NULL;
 	/* release module refcount */
@@ -448,6 +385,7 @@ static int chcr_ktls_dev_add(struct net_device *netdev, struct sock *sk,
 			     u32 start_offload_tcp_sn)
 {
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
+	struct ch_ktls_port_stats_debug *port_stats;
 	struct chcr_ktls_ofld_ctx_tx *tx_ctx;
 	struct chcr_ktls_info *tx_info;
 	struct dst_entry *dst;
@@ -461,30 +399,23 @@ static int chcr_ktls_dev_add(struct net_device *netdev, struct sock *sk,
 
 	pi = netdev_priv(netdev);
 	adap = pi->adapter;
+	port_stats = &adap->ch_ktls_stats.ktls_port[pi->port_id];
+	atomic64_inc(&port_stats->ktls_tx_connection_open);
+
 	if (direction == TLS_OFFLOAD_CTX_DIR_RX) {
 		pr_err("not expecting for RX direction\n");
-		ret = -EINVAL;
 		goto out;
 	}
-	if (tx_ctx->chcr_info) {
-		ret = -EINVAL;
+
+	if (tx_ctx->chcr_info)
 		goto out;
-	}
 
 	tx_info = kvzalloc(sizeof(*tx_info), GFP_KERNEL);
-	if (!tx_info) {
-		ret = -ENOMEM;
+	if (!tx_info)
 		goto out;
-	}
-
-	spin_lock_init(&tx_info->lock);
-
-	/* clear connection state */
-	spin_lock(&tx_info->lock);
-	tx_info->connection_state = KTLS_CONN_CLOSED;
-	spin_unlock(&tx_info->lock);
 
 	tx_info->sk = sk;
+	spin_lock_init(&tx_info->lock);
 	/* initialize tid and atid to -1, 0 is a also a valid id. */
 	tx_info->tid = -1;
 	tx_info->atid = -1;
@@ -495,10 +426,12 @@ static int chcr_ktls_dev_add(struct net_device *netdev, struct sock *sk,
 	tx_info->tx_chan = pi->tx_chan;
 	tx_info->smt_idx = pi->smt_idx;
 	tx_info->port_id = pi->port_id;
+	tx_info->prev_ack = 0;
+	tx_info->prev_win = 0;
 
 	tx_info->rx_qid = chcr_get_first_rx_qid(adap);
 	if (unlikely(tx_info->rx_qid < 0))
-		goto out2;
+		goto free_tx_info;
 
 	tx_info->prev_seq = start_offload_tcp_sn;
 	tx_info->tcp_start_seq_number = start_offload_tcp_sn;
@@ -506,18 +439,22 @@ static int chcr_ktls_dev_add(struct net_device *netdev, struct sock *sk,
 	/* save crypto keys */
 	ret = chcr_ktls_save_keys(tx_info, crypto_info, direction);
 	if (ret < 0)
-		goto out2;
+		goto free_tx_info;
 
 	/* get peer ip */
 	if (sk->sk_family == AF_INET) {
 		memcpy(daaddr, &sk->sk_daddr, 4);
+		tx_info->ip_family = AF_INET;
 #if IS_ENABLED(CONFIG_IPV6)
 	} else {
 		if (!sk->sk_ipv6only &&
-		    ipv6_addr_type(&sk->sk_v6_daddr) == IPV6_ADDR_MAPPED)
+		    ipv6_addr_type(&sk->sk_v6_daddr) == IPV6_ADDR_MAPPED) {
 			memcpy(daaddr, &sk->sk_daddr, 4);
-		else
+			tx_info->ip_family = AF_INET;
+		} else {
 			memcpy(daaddr, sk->sk_v6_daddr.in6_u.u6_addr8, 16);
+			tx_info->ip_family = AF_INET6;
+		}
 #endif
 	}
 
@@ -525,13 +462,13 @@ static int chcr_ktls_dev_add(struct net_device *netdev, struct sock *sk,
 	dst = sk_dst_get(sk);
 	if (!dst) {
 		pr_err("DST entry not found\n");
-		goto out2;
+		goto free_tx_info;
 	}
 	n = dst_neigh_lookup(dst, daaddr);
 	if (!n || !n->dev) {
 		pr_err("neighbour not found\n");
 		dst_release(dst);
-		goto out2;
+		goto free_tx_info;
 	}
 	tx_info->l2te  = cxgb4_l2t_get(adap->l2t, n, n->dev, 0);
 
@@ -540,31 +477,86 @@ static int chcr_ktls_dev_add(struct net_device *netdev, struct sock *sk,
 
 	if (!tx_info->l2te) {
 		pr_err("l2t entry not found\n");
-		goto out2;
+		goto free_tx_info;
 	}
 
-	tx_ctx->chcr_info = tx_info;
+	/* Driver shouldn't be removed until any single connection exists */
+	if (!try_module_get(THIS_MODULE))
+		goto free_l2t;
 
+	init_completion(&tx_info->completion);
 	/* create a filter and call cxgb4_l2t_send to send the packet out, which
 	 * will take care of updating l2t entry in hw if not already done.
 	 */
-	ret = chcr_setup_connection(sk, tx_info);
-	if (ret)
-		goto out2;
+	tx_info->open_state = CH_KTLS_OPEN_PENDING;
 
-	/* Driver shouldn't be removed until any single connection exists */
-	if (!try_module_get(THIS_MODULE)) {
-		ret = -EINVAL;
-		goto out2;
+	if (chcr_setup_connection(sk, tx_info))
+		goto put_module;
+
+	/* Wait for reply */
+	wait_for_completion_timeout(&tx_info->completion, 30 * HZ);
+	spin_lock_bh(&tx_info->lock);
+	if (tx_info->open_state) {
+		/* need to wait for hw response, can't free tx_info yet. */
+		if (tx_info->open_state == CH_KTLS_OPEN_PENDING)
+			tx_info->pending_close = true;
+		/* free the lock after the cleanup */
+		goto put_module;
+	}
+	spin_unlock_bh(&tx_info->lock);
+
+	/* initialize tcb */
+	reinit_completion(&tx_info->completion);
+	/* mark it pending for hw response */
+	tx_info->open_state = CH_KTLS_OPEN_PENDING;
+
+	if (chcr_init_tcb_fields(tx_info))
+		goto free_tid;
+
+	/* Wait for reply */
+	wait_for_completion_timeout(&tx_info->completion, 30 * HZ);
+	spin_lock_bh(&tx_info->lock);
+	if (tx_info->open_state) {
+		/* need to wait for hw response, can't free tx_info yet. */
+		tx_info->pending_close = true;
+		/* free the lock after cleanup */
+		goto free_tid;
 	}
+	spin_unlock_bh(&tx_info->lock);
+
+	if (!cxgb4_check_l2t_valid(tx_info->l2te))
+		goto free_tid;
+
+	atomic64_inc(&port_stats->ktls_tx_ctx);
+	tx_ctx->chcr_info = tx_info;
 
-	atomic64_inc(&adap->ch_ktls_stats.ktls_tx_connection_open);
 	return 0;
-out2:
-	kvfree(tx_info);
+
+free_tid:
+	chcr_ktls_mark_tcb_close(tx_info);
+#if IS_ENABLED(CONFIG_IPV6)
+	/* clear clip entry */
+	if (tx_info->ip_family == AF_INET6)
+		cxgb4_clip_release(netdev, (const u32 *)
+				   &sk->sk_v6_rcv_saddr,
+				   1);
+#endif
+	cxgb4_remove_tid(&tx_info->adap->tids, tx_info->tx_chan,
+			 tx_info->tid, tx_info->ip_family);
+
+put_module:
+	/* release module refcount */
+	module_put(THIS_MODULE);
+free_l2t:
+	cxgb4_l2t_release(tx_info->l2te);
+free_tx_info:
+	if (tx_info->pending_close)
+		spin_unlock_bh(&tx_info->lock);
+	else
+		kvfree(tx_info);
 out:
-	atomic64_inc(&adap->ch_ktls_stats.ktls_tx_connection_fail);
-	return ret;
+	atomic64_inc(&port_stats->ktls_tx_connection_fail);
+	return -1;
 }
 
 /*
@@ -627,20 +619,39 @@ static int chcr_ktls_cpl_act_open_rpl(struct adapter *adap,
 	tx_info = lookup_atid(t, atid);
 
 	if (!tx_info || tx_info->atid != atid) {
-		pr_err("tx_info or atid is not correct\n");
+		pr_err("%s: incorrect tx_info or atid\n", __func__);
 		return -1;
 	}
 
+	cxgb4_free_atid(t, atid);
+	tx_info->atid = -1;
+
+	spin_lock(&tx_info->lock);
+	/* HW response is very close, finish pending cleanup */
+	if (tx_info->pending_close) {
+		spin_unlock(&tx_info->lock);
+		if (!status) {
+			/* it's a late success, tcb status is establised,
+			 * mark it close.
+			 */
+			chcr_ktls_mark_tcb_close(tx_info);
+			cxgb4_remove_tid(&tx_info->adap->tids, tx_info->tx_chan,
+					 tid, tx_info->ip_family);
+		}
+		kvfree(tx_info);
+		return 0;
+	}
+
 	if (!status) {
 		tx_info->tid = tid;
 		cxgb4_insert_tid(t, tx_info, tx_info->tid, tx_info->ip_family);
-
-		cxgb4_free_atid(t, atid);
-		tx_info->atid = -1;
-		/* update the connection state */
-		chcr_ktls_update_connection_state(tx_info,
-						  KTLS_CONN_ACT_OPEN_RPL);
+		tx_info->open_state = CH_KTLS_OPEN_SUCCESS;
+	} else {
+		tx_info->open_state = CH_KTLS_OPEN_FAILURE;
 	}
+	spin_unlock(&tx_info->lock);
+
+	complete(&tx_info->completion);
 	return 0;
 }
 
@@ -658,12 +669,22 @@ static int chcr_ktls_cpl_set_tcb_rpl(struct adapter *adap, unsigned char *input)
 
 	t = &adap->tids;
 	tx_info = lookup_tid(t, tid);
+
 	if (!tx_info || tx_info->tid != tid) {
-		pr_err("tx_info or atid is not correct\n");
+		pr_err("%s: incorrect tx_info or tid\n", __func__);
 		return -1;
 	}
-	/* update the connection state */
-	chcr_ktls_update_connection_state(tx_info, KTLS_CONN_SET_TCB_RPL);
+
+	spin_lock(&tx_info->lock);
+	if (tx_info->pending_close) {
+		spin_unlock(&tx_info->lock);
+		kvfree(tx_info);
+		return 0;
+	}
+	tx_info->open_state = false;
+	spin_unlock(&tx_info->lock);
+
+	complete(&tx_info->completion);
 	return 0;
 }
 
@@ -765,6 +786,7 @@ static int chcr_ktls_xmit_tcb_cpls(struct chcr_ktls_info *tx_info,
 				   u64 tcp_ack, u64 tcp_win)
 {
 	bool first_wr = ((tx_info->prev_ack == 0) && (tx_info->prev_win == 0));
+	struct ch_ktls_port_stats_debug *port_stats;
 	u32 len, cpl = 0, ndesc, wr_len;
 	struct fw_ulptx_wr *wr;
 	int credits;
@@ -798,12 +820,14 @@ static int chcr_ktls_xmit_tcb_cpls(struct chcr_ktls_info *tx_info,
 	/* reset snd una if it's a re-transmit pkt */
 	if (tcp_seq != tx_info->prev_seq) {
 		/* reset snd_una */
+		port_stats =
+			&tx_info->adap->ch_ktls_stats.ktls_port[tx_info->port_id];
 		pos = chcr_write_cpl_set_tcb_ulp(tx_info, q, tx_info->tid, pos,
 						 TCB_SND_UNA_RAW_W,
 						 TCB_SND_UNA_RAW_V
 						 (TCB_SND_UNA_RAW_M),
 						 TCB_SND_UNA_RAW_V(0), 0);
-		atomic64_inc(&tx_info->adap->ch_ktls_stats.ktls_tx_ooo);
+		atomic64_inc(&port_stats->ktls_tx_ooo);
 		cpl++;
 	}
 	/* update ack */
@@ -1836,6 +1860,7 @@ out:
 /* nic tls TX handler */
 static int chcr_ktls_xmit(struct sk_buff *skb, struct net_device *dev)
 {
+	struct ch_ktls_port_stats_debug *port_stats;
 	struct chcr_ktls_ofld_ctx_tx *tx_ctx;
 	struct ch_ktls_stats_debug *stats;
 	struct tcphdr *th = tcp_hdr(skb);
@@ -1845,7 +1870,6 @@ static int chcr_ktls_xmit(struct sk_buff *skb, struct net_device *dev)
 	u32 tls_end_offset, tcp_seq;
 	struct tls_context *tls_ctx;
 	struct sk_buff *local_skb;
-	int new_connection_state;
 	struct sge_eth_txq *q;
 	struct adapter *adap;
 	unsigned long flags;
@@ -1868,15 +1892,6 @@ static int chcr_ktls_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (unlikely(!tx_info))
 		goto out;
 
-	/* check the connection state, we don't need to pass new connection
-	 * state, state machine will check and update the new state if it is
-	 * stuck due to responses not received from HW.
-	 * Start the tx handling only if state is KTLS_CONN_TX_READY.
-	 */
-	new_connection_state = chcr_ktls_update_connection_state(tx_info, 0);
-	if (new_connection_state != KTLS_CONN_TX_READY)
-		goto out;
-
 	/* don't touch the original skb, make a new skb to extract each records
 	 * and send them separately.
 	 */
@@ -1887,6 +1902,7 @@ static int chcr_ktls_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	adap = tx_info->adap;
 	stats = &adap->ch_ktls_stats;
+	port_stats = &stats->ktls_port[tx_info->port_id];
 
 	qidx = skb->queue_mapping;
 	q = &adap->sge.ethtxq[qidx + tx_info->first_qset];
@@ -1932,13 +1948,13 @@ static int chcr_ktls_xmit(struct sk_buff *skb, struct net_device *dev)
 		 */
 		if (unlikely(!record)) {
 			spin_unlock_irqrestore(&tx_ctx->base.lock, flags);
-			atomic64_inc(&stats->ktls_tx_drop_no_sync_data);
+			atomic64_inc(&port_stats->ktls_tx_drop_no_sync_data);
 			goto out;
 		}
 
 		if (unlikely(tls_record_is_start_marker(record))) {
 			spin_unlock_irqrestore(&tx_ctx->base.lock, flags);
-			atomic64_inc(&stats->ktls_tx_skip_no_sync_data);
+			atomic64_inc(&port_stats->ktls_tx_skip_no_sync_data);
 			goto out;
 		}
 
@@ -2009,9 +2025,8 @@ clear_ref:
 	} while (data_len > 0);
 
 	tx_info->prev_seq = ntohl(th->seq) + skb->data_len;
-
-	atomic64_inc(&stats->ktls_tx_encrypted_packets);
-	atomic64_add(skb->data_len, &stats->ktls_tx_encrypted_bytes);
+	atomic64_inc(&port_stats->ktls_tx_encrypted_packets);
+	atomic64_add(skb->data_len, &port_stats->ktls_tx_encrypted_bytes);
 
 	/* tcp finish is set, send a separate tcp msg including all the options
 	 * as well.
diff --git a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.h b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.h
index 4ae6ae38c406..c1651b1431a0 100644
--- a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.h
+++ b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.h
@@ -27,22 +27,20 @@
 #define CHCR_KTLS_WR_SIZE	(CHCR_PLAIN_TX_DATA_LEN +\
 				 sizeof(struct cpl_tx_sec_pdu))
 
-enum chcr_ktls_conn_state {
-	KTLS_CONN_CLOSED,
-	KTLS_CONN_ACT_OPEN_REQ,
-	KTLS_CONN_ACT_OPEN_RPL,
-	KTLS_CONN_SET_TCB_REQ,
-	KTLS_CONN_SET_TCB_RPL,
-	KTLS_CONN_TX_READY,
+enum ch_ktls_open_state {
+	CH_KTLS_OPEN_SUCCESS = 0,
+	CH_KTLS_OPEN_PENDING = 1,
+	CH_KTLS_OPEN_FAILURE = 2,
 };
 
 struct chcr_ktls_info {
 	struct sock *sk;
-	spinlock_t lock; /* state machine lock */
+	spinlock_t lock; /* lock for pending_close */
 	struct ktls_key_ctx key_ctx;
 	struct adapter *adap;
 	struct l2t_entry *l2te;
 	struct net_device *netdev;
+	struct completion completion;
 	u64 iv;
 	u64 record_no;
 	int tid;
@@ -58,13 +56,14 @@ struct chcr_ktls_info {
 	u32 tcp_start_seq_number;
 	u32 scmd0_short_seqno_numivs;
 	u32 scmd0_short_ivgen_hdrlen;
-	enum chcr_ktls_conn_state connection_state;
 	u16 prev_win;
 	u8 tx_chan;
 	u8 smt_idx;
 	u8 port_id;
 	u8 ip_family;
 	u8 first_qset;
+	enum ch_ktls_open_state open_state;
+	bool pending_close;
 };
 
 struct chcr_ktls_ofld_ctx_tx {
diff --git a/drivers/net/ethernet/cisco/enic/enic.h b/drivers/net/ethernet/cisco/enic/enic.h
index 18f3aeb88f22..c67a16a48d62 100644
--- a/drivers/net/ethernet/cisco/enic/enic.h
+++ b/drivers/net/ethernet/cisco/enic/enic.h
@@ -169,6 +169,7 @@ struct enic {
 	u16 num_vfs;
 #endif
 	spinlock_t enic_api_lock;
+	bool enic_api_busy;
 	struct enic_port_profile *pp;
 
 	/* work queue cache line section */
diff --git a/drivers/net/ethernet/cisco/enic/enic_api.c b/drivers/net/ethernet/cisco/enic/enic_api.c
index b161f24522b8..3bdc74fba1e3 100644
--- a/drivers/net/ethernet/cisco/enic/enic_api.c
+++ b/drivers/net/ethernet/cisco/enic/enic_api.c
@@ -1,4 +1,4 @@
-/**
+/*
  * Copyright 2013 Cisco Systems, Inc.  All rights reserved.
  *
  * This program is free software; you may redistribute it and/or modify
@@ -34,6 +34,12 @@ int enic_api_devcmd_proxy_by_index(struct net_device *netdev, int vf,
 	struct vnic_dev *vdev = enic->vdev;
 
 	spin_lock(&enic->enic_api_lock);
+	while (enic->enic_api_busy) {
+		spin_unlock(&enic->enic_api_lock);
+		cpu_relax();
+		spin_lock(&enic->enic_api_lock);
+	}
+
 	spin_lock_bh(&enic->devcmd_lock);
 
 	vnic_dev_cmd_proxy_by_index_start(vdev, vf);
diff --git a/drivers/net/ethernet/cisco/enic/enic_ethtool.c b/drivers/net/ethernet/cisco/enic/enic_ethtool.c
index 4d8e0aa447fb..a4dd52bba2c3 100644
--- a/drivers/net/ethernet/cisco/enic/enic_ethtool.c
+++ b/drivers/net/ethernet/cisco/enic/enic_ethtool.c
@@ -1,4 +1,4 @@
-/**
+/*
  * Copyright 2013 Cisco Systems, Inc.  All rights reserved.
  *
  * This program is free software; you may redistribute it and/or modify
diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c
index 4f0329d8778f..fb269d587b74 100644
--- a/drivers/net/ethernet/cisco/enic/enic_main.c
+++ b/drivers/net/ethernet/cisco/enic/enic_main.c
@@ -2107,8 +2107,6 @@ static int enic_dev_wait(struct vnic_dev *vdev,
 	int done;
 	int err;
 
-	BUG_ON(in_interrupt());
-
 	err = start(vdev, arg);
 	if (err)
 		return err;
@@ -2297,6 +2295,13 @@ static int enic_set_rss_nic_cfg(struct enic *enic)
 		rss_hash_bits, rss_base_cpu, rss_enable);
 }
 
+static void enic_set_api_busy(struct enic *enic, bool busy)
+{
+	spin_lock(&enic->enic_api_lock);
+	enic->enic_api_busy = busy;
+	spin_unlock(&enic->enic_api_lock);
+}
+
 static void enic_reset(struct work_struct *work)
 {
 	struct enic *enic = container_of(work, struct enic, reset);
@@ -2306,7 +2311,9 @@ static void enic_reset(struct work_struct *work)
 
 	rtnl_lock();
 
-	spin_lock(&enic->enic_api_lock);
+	/* Stop any activity from infiniband */
+	enic_set_api_busy(enic, true);
+
 	enic_stop(enic->netdev);
 	enic_dev_soft_reset(enic);
 	enic_reset_addr_lists(enic);
@@ -2314,7 +2321,10 @@ static void enic_reset(struct work_struct *work)
 	enic_set_rss_nic_cfg(enic);
 	enic_dev_set_ig_vlan_rewrite_mode(enic);
 	enic_open(enic->netdev);
-	spin_unlock(&enic->enic_api_lock);
+
+	/* Allow infiniband to fiddle with the device again */
+	enic_set_api_busy(enic, false);
+
 	call_netdevice_notifiers(NETDEV_REBOOT, enic->netdev);
 
 	rtnl_unlock();
@@ -2326,7 +2336,9 @@ static void enic_tx_hang_reset(struct work_struct *work)
 
 	rtnl_lock();
 
-	spin_lock(&enic->enic_api_lock);
+	/* Stop any activity from infiniband */
+	enic_set_api_busy(enic, true);
+
 	enic_dev_hang_notify(enic);
 	enic_stop(enic->netdev);
 	enic_dev_hang_reset(enic);
@@ -2335,7 +2347,10 @@ static void enic_tx_hang_reset(struct work_struct *work)
 	enic_set_rss_nic_cfg(enic);
 	enic_dev_set_ig_vlan_rewrite_mode(enic);
 	enic_open(enic->netdev);
-	spin_unlock(&enic->enic_api_lock);
+
+	/* Allow infiniband to fiddle with the device again */
+	enic_set_api_busy(enic, false);
+
 	call_netdevice_notifiers(NETDEV_REBOOT, enic->netdev);
 
 	rtnl_unlock();
diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c
index 07e9dee03c98..8df6f081f244 100644
--- a/drivers/net/ethernet/cortina/gemini.c
+++ b/drivers/net/ethernet/cortina/gemini.c
@@ -85,6 +85,8 @@ MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)");
 
 /**
  * struct gmac_queue_page - page buffer per-page info
+ * @page: the page struct
+ * @mapping: the dma address handle
  */
 struct gmac_queue_page {
 	struct page *page;
diff --git a/drivers/net/ethernet/dec/tulip/de2104x.c b/drivers/net/ethernet/dec/tulip/de2104x.c
index e648724c2c36..d9f6c19940ef 100644
--- a/drivers/net/ethernet/dec/tulip/de2104x.c
+++ b/drivers/net/ethernet/dec/tulip/de2104x.c
@@ -85,7 +85,7 @@ MODULE_PARM_DESC (rx_copybreak, "de2104x Breakpoint at which Rx packets are copi
 #define DSL			CONFIG_DE2104X_DSL
 #endif
 
-#define DE_RX_RING_SIZE		64
+#define DE_RX_RING_SIZE		128
 #define DE_TX_RING_SIZE		64
 #define DE_RING_BYTES		\
 		((sizeof(struct de_desc) * DE_RX_RING_SIZE) +	\
diff --git a/drivers/net/ethernet/dec/tulip/de4x5.c b/drivers/net/ethernet/dec/tulip/de4x5.c
index f9dd1aa9f2da..683e328b5461 100644
--- a/drivers/net/ethernet/dec/tulip/de4x5.c
+++ b/drivers/net/ethernet/dec/tulip/de4x5.c
@@ -4925,11 +4925,11 @@ mii_get_oui(u_char phyaddr, u_long ioaddr)
 	u_char breg[2];
     } a;
     int i, r2, r3, ret=0;*/
-    int r2, r3;
+    int r2;
 
     /* Read r2 and r3 */
     r2 = mii_rd(MII_ID0, phyaddr, ioaddr);
-    r3 = mii_rd(MII_ID1, phyaddr, ioaddr);
+    mii_rd(MII_ID1, phyaddr, ioaddr);
                                                 /* SEEQ and Cypress way * /
     / * Shuffle r2 and r3 * /
     a.reg=0;
diff --git a/drivers/net/ethernet/dec/tulip/media.c b/drivers/net/ethernet/dec/tulip/media.c
index dcf21a36a9cf..011604787b8e 100644
--- a/drivers/net/ethernet/dec/tulip/media.c
+++ b/drivers/net/ethernet/dec/tulip/media.c
@@ -319,13 +319,8 @@ void tulip_select_media(struct net_device *dev, int startup)
 			break;
 		}
 		case 5: case 6: {
-			u16 setup[5];
-
 			new_csr6 = 0; /* FIXME */
 
-			for (i = 0; i < 5; i++)
-				setup[i] = get_u16(&p[i*2 + 1]);
-
 			if (startup && mtable->has_reset) {
 				struct medialeaf *rleaf = &mtable->mleaf[mtable->has_reset];
 				unsigned char *rst = rleaf->leafdata;
diff --git a/drivers/net/ethernet/dnet.c b/drivers/net/ethernet/dnet.c
index 7f87b0f51404..48c6eb142dcc 100644
--- a/drivers/net/ethernet/dnet.c
+++ b/drivers/net/ethernet/dnet.c
@@ -507,10 +507,10 @@ static netdev_tx_t dnet_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 
 	struct dnet *bp = netdev_priv(dev);
-	u32 irq_enable;
 	unsigned int i, tx_cmd, wrsz;
 	unsigned long flags;
 	unsigned int *bufp;
+	u32 irq_enable;
 
 	dnet_readl(bp, TX_STATUS);
 
diff --git a/drivers/net/ethernet/ethoc.c b/drivers/net/ethernet/ethoc.c
index a817ca661c1f..0981fe9652e5 100644
--- a/drivers/net/ethernet/ethoc.c
+++ b/drivers/net/ethernet/ethoc.c
@@ -177,6 +177,7 @@ MODULE_PARM_DESC(buffer_size, "DMA buffer allocation size");
  * struct ethoc - driver-private device structure
  * @iobase:	pointer to I/O memory region
  * @membase:	pointer to buffer memory region
+ * @big_endian: just big or little (endian)
  * @num_bd:	number of buffer descriptors
  * @num_tx:	number of send buffers
  * @cur_tx:	last send buffer written
@@ -189,7 +190,10 @@ MODULE_PARM_DESC(buffer_size, "DMA buffer allocation size");
  * @msg_enable:	device state flags
  * @lock:	device lock
  * @mdio:	MDIO bus for PHY access
+ * @clk:	clock
  * @phy_id:	address of attached PHY
+ * @old_link:	previous link info
+ * @old_duplex: previous duplex info
  */
 struct ethoc {
 	void __iomem *iobase;
@@ -1015,7 +1019,7 @@ static const struct net_device_ops ethoc_netdev_ops = {
 
 /**
  * ethoc_probe - initialize OpenCores ethernet MAC
- * pdev:	platform device
+ * @pdev:	platform device
  */
 static int ethoc_probe(struct platform_device *pdev)
 {
diff --git a/drivers/net/ethernet/freescale/dpaa2/Kconfig b/drivers/net/ethernet/freescale/dpaa2/Kconfig
index feea797cde02..cfd369cf4c8c 100644
--- a/drivers/net/ethernet/freescale/dpaa2/Kconfig
+++ b/drivers/net/ethernet/freescale/dpaa2/Kconfig
@@ -3,6 +3,7 @@ config FSL_DPAA2_ETH
 	tristate "Freescale DPAA2 Ethernet"
 	depends on FSL_MC_BUS && FSL_MC_DPIO
 	select PHYLINK
+	select PCS_LYNX
 	help
 	  This is the DPAA2 Ethernet driver supporting Freescale SoCs
 	  with DPAA2 (DataPath Acceleration Architecture v2).
diff --git a/drivers/net/ethernet/freescale/dpaa2/Makefile b/drivers/net/ethernet/freescale/dpaa2/Makefile
index 6e7f33c956bf..146cb3540e61 100644
--- a/drivers/net/ethernet/freescale/dpaa2/Makefile
+++ b/drivers/net/ethernet/freescale/dpaa2/Makefile
@@ -6,7 +6,7 @@
 obj-$(CONFIG_FSL_DPAA2_ETH)		+= fsl-dpaa2-eth.o
 obj-$(CONFIG_FSL_DPAA2_PTP_CLOCK)	+= fsl-dpaa2-ptp.o
 
-fsl-dpaa2-eth-objs	:= dpaa2-eth.o dpaa2-ethtool.o dpni.o dpaa2-mac.o dpmac.o
+fsl-dpaa2-eth-objs	:= dpaa2-eth.o dpaa2-ethtool.o dpni.o dpaa2-mac.o dpmac.o dpaa2-eth-devlink.o
 fsl-dpaa2-eth-${CONFIG_FSL_DPAA2_ETH_DCB} += dpaa2-eth-dcb.o
 fsl-dpaa2-eth-${CONFIG_DEBUG_FS} += dpaa2-eth-debugfs.o
 fsl-dpaa2-ptp-objs	:= dpaa2-ptp.o dprtc.o
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-devlink.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-devlink.c
new file mode 100644
index 000000000000..833696245565
--- /dev/null
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-devlink.c
@@ -0,0 +1,309 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause)
+#include "dpaa2-eth.h"
+/* Copyright 2020 NXP
+ */
+
+#define DPAA2_ETH_TRAP_DROP(_id, _group_id)					\
+	DEVLINK_TRAP_GENERIC(DROP, DROP, _id,					\
+			     DEVLINK_TRAP_GROUP_GENERIC_ID_##_group_id, 0)
+
+static const struct devlink_trap_group dpaa2_eth_trap_groups_arr[] = {
+	DEVLINK_TRAP_GROUP_GENERIC(PARSER_ERROR_DROPS, 0),
+};
+
+static const struct devlink_trap dpaa2_eth_traps_arr[] = {
+	DPAA2_ETH_TRAP_DROP(VXLAN_PARSING, PARSER_ERROR_DROPS),
+	DPAA2_ETH_TRAP_DROP(LLC_SNAP_PARSING, PARSER_ERROR_DROPS),
+	DPAA2_ETH_TRAP_DROP(VLAN_PARSING, PARSER_ERROR_DROPS),
+	DPAA2_ETH_TRAP_DROP(PPPOE_PPP_PARSING, PARSER_ERROR_DROPS),
+	DPAA2_ETH_TRAP_DROP(MPLS_PARSING, PARSER_ERROR_DROPS),
+	DPAA2_ETH_TRAP_DROP(ARP_PARSING, PARSER_ERROR_DROPS),
+	DPAA2_ETH_TRAP_DROP(IP_1_PARSING, PARSER_ERROR_DROPS),
+	DPAA2_ETH_TRAP_DROP(IP_N_PARSING, PARSER_ERROR_DROPS),
+	DPAA2_ETH_TRAP_DROP(GRE_PARSING, PARSER_ERROR_DROPS),
+	DPAA2_ETH_TRAP_DROP(UDP_PARSING, PARSER_ERROR_DROPS),
+	DPAA2_ETH_TRAP_DROP(TCP_PARSING, PARSER_ERROR_DROPS),
+	DPAA2_ETH_TRAP_DROP(IPSEC_PARSING, PARSER_ERROR_DROPS),
+	DPAA2_ETH_TRAP_DROP(SCTP_PARSING, PARSER_ERROR_DROPS),
+	DPAA2_ETH_TRAP_DROP(DCCP_PARSING, PARSER_ERROR_DROPS),
+	DPAA2_ETH_TRAP_DROP(GTP_PARSING, PARSER_ERROR_DROPS),
+	DPAA2_ETH_TRAP_DROP(ESP_PARSING, PARSER_ERROR_DROPS),
+};
+
+static int dpaa2_eth_dl_info_get(struct devlink *devlink,
+				 struct devlink_info_req *req,
+				 struct netlink_ext_ack *extack)
+{
+	struct dpaa2_eth_devlink_priv *dl_priv = devlink_priv(devlink);
+	struct dpaa2_eth_priv *priv = dl_priv->dpaa2_priv;
+	char buf[10];
+	int err;
+
+	err = devlink_info_driver_name_put(req, KBUILD_MODNAME);
+	if (err)
+		return err;
+
+	scnprintf(buf, 10, "%d.%d", priv->dpni_ver_major, priv->dpni_ver_minor);
+	err = devlink_info_version_running_put(req, "dpni", buf);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+static struct dpaa2_eth_trap_item *
+dpaa2_eth_dl_trap_item_lookup(struct dpaa2_eth_priv *priv, u16 trap_id)
+{
+	struct dpaa2_eth_trap_data *dpaa2_eth_trap_data = priv->trap_data;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(dpaa2_eth_traps_arr); i++) {
+		if (dpaa2_eth_traps_arr[i].id == trap_id)
+			return &dpaa2_eth_trap_data->trap_items_arr[i];
+	}
+
+	return NULL;
+}
+
+struct dpaa2_eth_trap_item *dpaa2_eth_dl_get_trap(struct dpaa2_eth_priv *priv,
+						  struct dpaa2_fapr *fapr)
+{
+	struct dpaa2_faf_error_bit {
+		int position;
+		enum devlink_trap_generic_id trap_id;
+	} faf_bits[] = {
+		{ .position = 5,  .trap_id = DEVLINK_TRAP_GENERIC_ID_VXLAN_PARSING },
+		{ .position = 20, .trap_id = DEVLINK_TRAP_GENERIC_ID_LLC_SNAP_PARSING },
+		{ .position = 24, .trap_id = DEVLINK_TRAP_GENERIC_ID_VLAN_PARSING },
+		{ .position = 26, .trap_id = DEVLINK_TRAP_GENERIC_ID_PPPOE_PPP_PARSING },
+		{ .position = 29, .trap_id = DEVLINK_TRAP_GENERIC_ID_MPLS_PARSING },
+		{ .position = 31, .trap_id = DEVLINK_TRAP_GENERIC_ID_ARP_PARSING },
+		{ .position = 52, .trap_id = DEVLINK_TRAP_GENERIC_ID_IP_1_PARSING },
+		{ .position = 61, .trap_id = DEVLINK_TRAP_GENERIC_ID_IP_N_PARSING },
+		{ .position = 67, .trap_id = DEVLINK_TRAP_GENERIC_ID_GRE_PARSING },
+		{ .position = 71, .trap_id = DEVLINK_TRAP_GENERIC_ID_UDP_PARSING },
+		{ .position = 76, .trap_id = DEVLINK_TRAP_GENERIC_ID_TCP_PARSING },
+		{ .position = 80, .trap_id = DEVLINK_TRAP_GENERIC_ID_IPSEC_PARSING },
+		{ .position = 82, .trap_id = DEVLINK_TRAP_GENERIC_ID_SCTP_PARSING },
+		{ .position = 84, .trap_id = DEVLINK_TRAP_GENERIC_ID_DCCP_PARSING },
+		{ .position = 88, .trap_id = DEVLINK_TRAP_GENERIC_ID_GTP_PARSING },
+		{ .position = 90, .trap_id = DEVLINK_TRAP_GENERIC_ID_ESP_PARSING },
+	};
+	u64 faf_word;
+	u64 mask;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(faf_bits); i++) {
+		if (faf_bits[i].position < 32) {
+			/* Low part of FAF.
+			 * position ranges from 31 to 0, mask from 0 to 31.
+			 */
+			mask = 1ull << (31 - faf_bits[i].position);
+			faf_word = __le32_to_cpu(fapr->faf_lo);
+		} else {
+			/* High part of FAF.
+			 * position ranges from 95 to 32, mask from 0 to 63.
+			 */
+			mask = 1ull << (63 - (faf_bits[i].position - 32));
+			faf_word = __le64_to_cpu(fapr->faf_hi);
+		}
+		if (faf_word & mask)
+			return dpaa2_eth_dl_trap_item_lookup(priv, faf_bits[i].trap_id);
+	}
+	return NULL;
+}
+
+static int dpaa2_eth_dl_trap_init(struct devlink *devlink,
+				  const struct devlink_trap *trap,
+				  void *trap_ctx)
+{
+	struct dpaa2_eth_devlink_priv *dl_priv = devlink_priv(devlink);
+	struct dpaa2_eth_priv *priv = dl_priv->dpaa2_priv;
+	struct dpaa2_eth_trap_item *dpaa2_eth_trap_item;
+
+	dpaa2_eth_trap_item = dpaa2_eth_dl_trap_item_lookup(priv, trap->id);
+	if (WARN_ON(!dpaa2_eth_trap_item))
+		return -ENOENT;
+
+	dpaa2_eth_trap_item->trap_ctx = trap_ctx;
+
+	return 0;
+}
+
+static int dpaa2_eth_dl_trap_action_set(struct devlink *devlink,
+					const struct devlink_trap *trap,
+					enum devlink_trap_action action,
+					struct netlink_ext_ack *extack)
+{
+	/* No support for changing the action of an independent packet trap,
+	 * only per trap group - parser error drops
+	 */
+	NL_SET_ERR_MSG_MOD(extack,
+			   "Cannot change trap action independently of group");
+	return -EOPNOTSUPP;
+}
+
+static int dpaa2_eth_dl_trap_group_action_set(struct devlink *devlink,
+					      const struct devlink_trap_group *group,
+					      enum devlink_trap_action action,
+					      struct netlink_ext_ack *extack)
+{
+	struct dpaa2_eth_devlink_priv *dl_priv = devlink_priv(devlink);
+	struct dpaa2_eth_priv *priv = dl_priv->dpaa2_priv;
+	struct net_device *net_dev = priv->net_dev;
+	struct device *dev = net_dev->dev.parent;
+	struct dpni_error_cfg err_cfg = {0};
+	int err;
+
+	if (group->id != DEVLINK_TRAP_GROUP_GENERIC_ID_PARSER_ERROR_DROPS)
+		return -EOPNOTSUPP;
+
+	/* Configure handling of frames marked as errors from the parser */
+	err_cfg.errors = DPAA2_FAS_RX_ERR_MASK;
+	err_cfg.set_frame_annotation = 1;
+
+	switch (action) {
+	case DEVLINK_TRAP_ACTION_DROP:
+		err_cfg.error_action = DPNI_ERROR_ACTION_DISCARD;
+		break;
+	case DEVLINK_TRAP_ACTION_TRAP:
+		err_cfg.error_action = DPNI_ERROR_ACTION_SEND_TO_ERROR_QUEUE;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	err = dpni_set_errors_behavior(priv->mc_io, 0, priv->mc_token, &err_cfg);
+	if (err) {
+		dev_err(dev, "dpni_set_errors_behavior failed\n");
+		return err;
+	}
+
+	return 0;
+}
+
+static const struct devlink_ops dpaa2_eth_devlink_ops = {
+	.info_get = dpaa2_eth_dl_info_get,
+	.trap_init = dpaa2_eth_dl_trap_init,
+	.trap_action_set = dpaa2_eth_dl_trap_action_set,
+	.trap_group_action_set = dpaa2_eth_dl_trap_group_action_set,
+};
+
+int dpaa2_eth_dl_register(struct dpaa2_eth_priv *priv)
+{
+	struct net_device *net_dev = priv->net_dev;
+	struct device *dev = net_dev->dev.parent;
+	struct dpaa2_eth_devlink_priv *dl_priv;
+	int err;
+
+	priv->devlink = devlink_alloc(&dpaa2_eth_devlink_ops, sizeof(*dl_priv));
+	if (!priv->devlink) {
+		dev_err(dev, "devlink_alloc failed\n");
+		return -ENOMEM;
+	}
+	dl_priv = devlink_priv(priv->devlink);
+	dl_priv->dpaa2_priv = priv;
+
+	err = devlink_register(priv->devlink, dev);
+	if (err) {
+		dev_err(dev, "devlink_register() = %d\n", err);
+		goto devlink_free;
+	}
+
+	return 0;
+
+devlink_free:
+	devlink_free(priv->devlink);
+
+	return err;
+}
+
+void dpaa2_eth_dl_unregister(struct dpaa2_eth_priv *priv)
+{
+	devlink_unregister(priv->devlink);
+	devlink_free(priv->devlink);
+}
+
+int dpaa2_eth_dl_port_add(struct dpaa2_eth_priv *priv)
+{
+	struct devlink_port *devlink_port = &priv->devlink_port;
+	struct devlink_port_attrs attrs = {};
+	int err;
+
+	attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL;
+	devlink_port_attrs_set(devlink_port, &attrs);
+
+	err = devlink_port_register(priv->devlink, devlink_port, 0);
+	if (err)
+		return err;
+
+	devlink_port_type_eth_set(devlink_port, priv->net_dev);
+
+	return 0;
+}
+
+void dpaa2_eth_dl_port_del(struct dpaa2_eth_priv *priv)
+{
+	struct devlink_port *devlink_port = &priv->devlink_port;
+
+	devlink_port_type_clear(devlink_port);
+	devlink_port_unregister(devlink_port);
+}
+
+int dpaa2_eth_dl_traps_register(struct dpaa2_eth_priv *priv)
+{
+	struct dpaa2_eth_trap_data *dpaa2_eth_trap_data;
+	struct net_device *net_dev = priv->net_dev;
+	struct device *dev = net_dev->dev.parent;
+	int err;
+
+	dpaa2_eth_trap_data = kzalloc(sizeof(*dpaa2_eth_trap_data), GFP_KERNEL);
+	if (!dpaa2_eth_trap_data)
+		return -ENOMEM;
+	priv->trap_data = dpaa2_eth_trap_data;
+
+	dpaa2_eth_trap_data->trap_items_arr = kcalloc(ARRAY_SIZE(dpaa2_eth_traps_arr),
+						      sizeof(struct dpaa2_eth_trap_item),
+						      GFP_KERNEL);
+	if (!dpaa2_eth_trap_data->trap_items_arr) {
+		err = -ENOMEM;
+		goto trap_data_free;
+	}
+
+	err = devlink_trap_groups_register(priv->devlink, dpaa2_eth_trap_groups_arr,
+					   ARRAY_SIZE(dpaa2_eth_trap_groups_arr));
+	if (err) {
+		dev_err(dev, "devlink_trap_groups_register() = %d\n", err);
+		goto trap_items_arr_free;
+	}
+
+	err = devlink_traps_register(priv->devlink, dpaa2_eth_traps_arr,
+				     ARRAY_SIZE(dpaa2_eth_traps_arr), priv);
+	if (err) {
+		dev_err(dev, "devlink_traps_register() = %d\n", err);
+		goto trap_groups_unregiser;
+	}
+
+	return 0;
+
+trap_groups_unregiser:
+	devlink_trap_groups_unregister(priv->devlink, dpaa2_eth_trap_groups_arr,
+				       ARRAY_SIZE(dpaa2_eth_trap_groups_arr));
+trap_items_arr_free:
+	kfree(dpaa2_eth_trap_data->trap_items_arr);
+trap_data_free:
+	kfree(dpaa2_eth_trap_data);
+	priv->trap_data = NULL;
+
+	return err;
+}
+
+void dpaa2_eth_dl_traps_unregister(struct dpaa2_eth_priv *priv)
+{
+	devlink_traps_unregister(priv->devlink, dpaa2_eth_traps_arr,
+				 ARRAY_SIZE(dpaa2_eth_traps_arr));
+	devlink_trap_groups_unregister(priv->devlink, dpaa2_eth_trap_groups_arr,
+				       ARRAY_SIZE(dpaa2_eth_trap_groups_arr));
+	kfree(priv->trap_data->trap_items_arr);
+	kfree(priv->trap_data);
+}
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index 5bc965186f8c..cf9400a9886d 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -509,6 +509,58 @@ err_frame_format:
 	percpu_stats->rx_dropped++;
 }
 
+/* Processing of Rx frames received on the error FQ
+ * We check and print the error bits and then free the frame
+ */
+static void dpaa2_eth_rx_err(struct dpaa2_eth_priv *priv,
+			     struct dpaa2_eth_channel *ch,
+			     const struct dpaa2_fd *fd,
+			     struct dpaa2_eth_fq *fq __always_unused)
+{
+	struct device *dev = priv->net_dev->dev.parent;
+	dma_addr_t addr = dpaa2_fd_get_addr(fd);
+	u8 fd_format = dpaa2_fd_get_format(fd);
+	struct rtnl_link_stats64 *percpu_stats;
+	struct dpaa2_eth_trap_item *trap_item;
+	struct dpaa2_fapr *fapr;
+	struct sk_buff *skb;
+	void *buf_data;
+	void *vaddr;
+
+	vaddr = dpaa2_iova_to_virt(priv->iommu_domain, addr);
+	dma_sync_single_for_cpu(dev, addr, priv->rx_buf_size,
+				DMA_BIDIRECTIONAL);
+
+	buf_data = vaddr + dpaa2_fd_get_offset(fd);
+
+	if (fd_format == dpaa2_fd_single) {
+		dma_unmap_page(dev, addr, priv->rx_buf_size,
+			       DMA_BIDIRECTIONAL);
+		skb = dpaa2_eth_build_linear_skb(ch, fd, vaddr);
+	} else if (fd_format == dpaa2_fd_sg) {
+		dma_unmap_page(dev, addr, priv->rx_buf_size,
+			       DMA_BIDIRECTIONAL);
+		skb = dpaa2_eth_build_frag_skb(priv, ch, buf_data);
+		free_pages((unsigned long)vaddr, 0);
+	} else {
+		/* We don't support any other format */
+		dpaa2_eth_free_rx_fd(priv, fd, vaddr);
+		goto err_frame_format;
+	}
+
+	fapr = dpaa2_get_fapr(vaddr, false);
+	trap_item = dpaa2_eth_dl_get_trap(priv, fapr);
+	if (trap_item)
+		devlink_trap_report(priv->devlink, skb, trap_item->trap_ctx,
+				    &priv->devlink_port, NULL);
+	consume_skb(skb);
+
+err_frame_format:
+	percpu_stats = this_cpu_ptr(priv->percpu_stats);
+	percpu_stats->rx_errors++;
+	ch->buf_count--;
+}
+
 /* Consume all frames pull-dequeued into the store. This is the simplest way to
  * make sure we don't accidentally issue another volatile dequeue which would
  * overwrite (leak) frames already in the store.
@@ -1344,7 +1396,7 @@ static int dpaa2_eth_seed_pool(struct dpaa2_eth_priv *priv, u16 bpid)
 	return 0;
 }
 
-/**
+/*
  * Drain the specified number of buffers from the DPNI's private buffer pool.
  * @count must not exceeed DPAA2_ETH_BUFS_PER_CMD
  */
@@ -1700,22 +1752,11 @@ static int dpaa2_eth_open(struct net_device *net_dev)
 		goto enable_err;
 	}
 
-	if (!priv->mac) {
-		/* If the DPMAC object has already processed the link up
-		 * interrupt, we have to learn the link state ourselves.
-		 */
-		err = dpaa2_eth_link_state_update(priv);
-		if (err < 0) {
-			netdev_err(net_dev, "Can't update link state\n");
-			goto link_state_err;
-		}
-	} else {
+	if (priv->mac)
 		phylink_start(priv->mac->phylink);
-	}
 
 	return 0;
 
-link_state_err:
 enable_err:
 	dpaa2_eth_disable_ch_napi(priv);
 	dpaa2_eth_drain_pool(priv);
@@ -2734,6 +2775,7 @@ static void dpaa2_eth_set_fq_affinity(struct dpaa2_eth_priv *priv)
 		fq = &priv->fq[i];
 		switch (fq->type) {
 		case DPAA2_RX_FQ:
+		case DPAA2_RX_ERR_FQ:
 			fq->target_cpu = rx_cpu;
 			rx_cpu = cpumask_next(rx_cpu, &priv->dpio_cpumask);
 			if (rx_cpu >= nr_cpu_ids)
@@ -2777,6 +2819,10 @@ static void dpaa2_eth_setup_fqs(struct dpaa2_eth_priv *priv)
 		}
 	}
 
+	/* We have exactly one Rx error queue per DPNI */
+	priv->fq[priv->num_fqs].type = DPAA2_RX_ERR_FQ;
+	priv->fq[priv->num_fqs++].consume = dpaa2_eth_rx_err;
+
 	/* For each FQ, decide on which core to process incoming frames */
 	dpaa2_eth_set_fq_affinity(priv);
 }
@@ -3352,6 +3398,38 @@ static int dpaa2_eth_setup_tx_flow(struct dpaa2_eth_priv *priv,
 	return 0;
 }
 
+static int setup_rx_err_flow(struct dpaa2_eth_priv *priv,
+			     struct dpaa2_eth_fq *fq)
+{
+	struct device *dev = priv->net_dev->dev.parent;
+	struct dpni_queue q = { { 0 } };
+	struct dpni_queue_id qid;
+	u8 q_opt = DPNI_QUEUE_OPT_USER_CTX | DPNI_QUEUE_OPT_DEST;
+	int err;
+
+	err = dpni_get_queue(priv->mc_io, 0, priv->mc_token,
+			     DPNI_QUEUE_RX_ERR, 0, 0, &q, &qid);
+	if (err) {
+		dev_err(dev, "dpni_get_queue() failed (%d)\n", err);
+		return err;
+	}
+
+	fq->fqid = qid.fqid;
+
+	q.destination.id = fq->channel->dpcon_id;
+	q.destination.type = DPNI_DEST_DPCON;
+	q.destination.priority = 1;
+	q.user_context = (u64)(uintptr_t)fq;
+	err = dpni_set_queue(priv->mc_io, 0, priv->mc_token,
+			     DPNI_QUEUE_RX_ERR, 0, 0, q_opt, &q);
+	if (err) {
+		dev_err(dev, "dpni_set_queue() failed (%d)\n", err);
+		return err;
+	}
+
+	return 0;
+}
+
 /* Supported header fields for Rx hash distribution key */
 static const struct dpaa2_eth_dist_fields dist_fields[] = {
 	{
@@ -3465,6 +3543,12 @@ static int dpaa2_eth_config_hash_key(struct dpaa2_eth_priv *priv, dma_addr_t key
 			dev_err(dev, "dpni_set_rx_hash_dist failed\n");
 			break;
 		}
+
+		/* If the flow steering / hashing key is shared between all
+		 * traffic classes, install it just once
+		 */
+		if (priv->dpni_attrs.options & DPNI_OPT_SHARED_FS)
+			break;
 	}
 
 	return err;
@@ -3491,6 +3575,12 @@ static int dpaa2_eth_config_cls_key(struct dpaa2_eth_priv *priv, dma_addr_t key)
 			dev_err(dev, "dpni_set_rx_fs_dist failed\n");
 			break;
 		}
+
+		/* If the flow steering / hashing key is shared between all
+		 * traffic classes, install it just once
+		 */
+		if (priv->dpni_attrs.options & DPNI_OPT_SHARED_FS)
+			break;
 	}
 
 	return err;
@@ -3738,6 +3828,9 @@ static int dpaa2_eth_bind_dpni(struct dpaa2_eth_priv *priv)
 		case DPAA2_TX_CONF_FQ:
 			err = dpaa2_eth_setup_tx_flow(priv, &priv->fq[i]);
 			break;
+		case DPAA2_RX_ERR_FQ:
+			err = setup_rx_err_flow(priv, &priv->fq[i]);
+			break;
 		default:
 			dev_err(dev, "Invalid FQ type %d\n", priv->fq[i].type);
 			return -EINVAL;
@@ -4222,6 +4315,18 @@ static int dpaa2_eth_probe(struct fsl_mc_device *dpni_dev)
 	if (err)
 		goto err_connect_mac;
 
+	err = dpaa2_eth_dl_register(priv);
+	if (err)
+		goto err_dl_register;
+
+	err = dpaa2_eth_dl_traps_register(priv);
+	if (err)
+		goto err_dl_trap_register;
+
+	err = dpaa2_eth_dl_port_add(priv);
+	if (err)
+		goto err_dl_port_add;
+
 	err = register_netdev(net_dev);
 	if (err < 0) {
 		dev_err(dev, "register_netdev() failed\n");
@@ -4236,6 +4341,12 @@ static int dpaa2_eth_probe(struct fsl_mc_device *dpni_dev)
 	return 0;
 
 err_netdev_reg:
+	dpaa2_eth_dl_port_del(priv);
+err_dl_port_add:
+	dpaa2_eth_dl_traps_unregister(priv);
+err_dl_trap_register:
+	dpaa2_eth_dl_unregister(priv);
+err_dl_register:
 	dpaa2_eth_disconnect_mac(priv);
 err_connect_mac:
 	if (priv->do_link_poll)
@@ -4290,6 +4401,10 @@ static int dpaa2_eth_remove(struct fsl_mc_device *ls_dev)
 
 	unregister_netdev(net_dev);
 
+	dpaa2_eth_dl_port_del(priv);
+	dpaa2_eth_dl_traps_unregister(priv);
+	dpaa2_eth_dl_unregister(priv);
+
 	if (priv->do_link_poll)
 		kthread_stop(priv->poll_thread);
 	else
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
index 6436fa3b25cb..d236b8695c39 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
@@ -11,6 +11,7 @@
 #include <linux/if_vlan.h>
 #include <linux/fsl/mc.h>
 #include <linux/net_tstamp.h>
+#include <net/devlink.h>
 
 #include <soc/fsl/dpaa2-io.h>
 #include <soc/fsl/dpaa2-fd.h>
@@ -181,6 +182,49 @@ struct dpaa2_fas {
  */
 #define DPAA2_TS_OFFSET			0x8
 
+/* Frame annotation parse results */
+struct dpaa2_fapr {
+	/* 64-bit word 1 */
+	__le32 faf_lo;
+	__le16 faf_ext;
+	__le16 nxt_hdr;
+	/* 64-bit word 2 */
+	__le64 faf_hi;
+	/* 64-bit word 3 */
+	u8 last_ethertype_offset;
+	u8 vlan_tci_offset_n;
+	u8 vlan_tci_offset_1;
+	u8 llc_snap_offset;
+	u8 eth_offset;
+	u8 ip1_pid_offset;
+	u8 shim_offset_2;
+	u8 shim_offset_1;
+	/* 64-bit word 4 */
+	u8 l5_offset;
+	u8 l4_offset;
+	u8 gre_offset;
+	u8 l3_offset_n;
+	u8 l3_offset_1;
+	u8 mpls_offset_n;
+	u8 mpls_offset_1;
+	u8 pppoe_offset;
+	/* 64-bit word 5 */
+	__le16 running_sum;
+	__le16 gross_running_sum;
+	u8 ipv6_frag_offset;
+	u8 nxt_hdr_offset;
+	u8 routing_hdr_offset_2;
+	u8 routing_hdr_offset_1;
+	/* 64-bit word 6 */
+	u8 reserved[5]; /* Soft-parsing context */
+	u8 ip_proto_offset_n;
+	u8 nxt_hdr_frag_offset;
+	u8 parse_error_code;
+};
+
+#define DPAA2_FAPR_OFFSET		0x10
+#define DPAA2_FAPR_SIZE			sizeof((struct dpaa2_fapr))
+
 /* Frame annotation egress action descriptor */
 #define DPAA2_FAEAD_OFFSET		0x58
 
@@ -229,6 +273,11 @@ static inline __le64 *dpaa2_get_ts(void *buf_addr, bool swa)
 	return dpaa2_get_hwa(buf_addr, swa) + DPAA2_TS_OFFSET;
 }
 
+static inline struct dpaa2_fapr *dpaa2_get_fapr(void *buf_addr, bool swa)
+{
+	return dpaa2_get_hwa(buf_addr, swa) + DPAA2_FAPR_OFFSET;
+}
+
 static inline struct dpaa2_faead *dpaa2_get_faead(void *buf_addr, bool swa)
 {
 	return dpaa2_get_hwa(buf_addr, swa) + DPAA2_FAEAD_OFFSET;
@@ -343,8 +392,10 @@ struct dpaa2_eth_ch_stats {
 #define DPAA2_ETH_MAX_RX_QUEUES		\
 	(DPAA2_ETH_MAX_RX_QUEUES_PER_TC * DPAA2_ETH_MAX_TCS)
 #define DPAA2_ETH_MAX_TX_QUEUES		16
+#define DPAA2_ETH_MAX_RX_ERR_QUEUES	1
 #define DPAA2_ETH_MAX_QUEUES		(DPAA2_ETH_MAX_RX_QUEUES + \
-					DPAA2_ETH_MAX_TX_QUEUES)
+					DPAA2_ETH_MAX_TX_QUEUES + \
+					DPAA2_ETH_MAX_RX_ERR_QUEUES)
 #define DPAA2_ETH_MAX_NETDEV_QUEUES	\
 	(DPAA2_ETH_MAX_TX_QUEUES * DPAA2_ETH_MAX_TCS)
 
@@ -353,6 +404,7 @@ struct dpaa2_eth_ch_stats {
 enum dpaa2_eth_fq_type {
 	DPAA2_RX_FQ = 0,
 	DPAA2_TX_CONF_FQ,
+	DPAA2_RX_ERR_FQ
 };
 
 struct dpaa2_eth_priv;
@@ -426,6 +478,15 @@ struct dpaa2_eth_sgt_cache {
 	u16 count;
 };
 
+struct dpaa2_eth_trap_item {
+	void *trap_ctx;
+};
+
+struct dpaa2_eth_trap_data {
+	struct dpaa2_eth_trap_item *trap_items_arr;
+	struct dpaa2_eth_priv *priv;
+};
+
 /* Driver private data */
 struct dpaa2_eth_priv {
 	struct net_device *net_dev;
@@ -503,6 +564,13 @@ struct dpaa2_eth_priv {
 	 * queue before transmit current packet.
 	 */
 	struct mutex		onestep_tstamp_lock;
+	struct devlink *devlink;
+	struct dpaa2_eth_trap_data *trap_data;
+	struct devlink_port devlink_port;
+};
+
+struct dpaa2_eth_devlink_priv {
+	struct dpaa2_eth_priv *dpaa2_priv;
 };
 
 #define TX_TSTAMP		0x1
@@ -636,4 +704,15 @@ void dpaa2_eth_set_rx_taildrop(struct dpaa2_eth_priv *priv,
 
 extern const struct dcbnl_rtnl_ops dpaa2_eth_dcbnl_ops;
 
+int dpaa2_eth_dl_register(struct dpaa2_eth_priv *priv);
+void dpaa2_eth_dl_unregister(struct dpaa2_eth_priv *priv);
+
+int dpaa2_eth_dl_port_add(struct dpaa2_eth_priv *priv);
+void dpaa2_eth_dl_port_del(struct dpaa2_eth_priv *priv);
+
+int dpaa2_eth_dl_traps_register(struct dpaa2_eth_priv *priv);
+void dpaa2_eth_dl_traps_unregister(struct dpaa2_eth_priv *priv);
+
+struct dpaa2_eth_trap_item *dpaa2_eth_dl_get_trap(struct dpaa2_eth_priv *priv,
+						  struct dpaa2_fapr *fapr);
 #endif	/* __DPAA2_H */
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
index 11e0c047dbd2..f981a523e13a 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
@@ -618,7 +618,7 @@ static int dpaa2_eth_do_cls_rule(struct net_device *net_dev,
 			err = dpni_remove_fs_entry(priv->mc_io, 0,
 						   priv->mc_token, i,
 						   &rule_cfg);
-		if (err)
+		if (err || priv->dpni_attrs.options & DPNI_OPT_SHARED_FS)
 			break;
 	}
 
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c
index 3ee236c5fc37..90cd243070d7 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c
@@ -15,6 +15,18 @@ static int phy_mode(enum dpmac_eth_if eth_if, phy_interface_t *if_mode)
 	case DPMAC_ETH_IF_RGMII:
 		*if_mode = PHY_INTERFACE_MODE_RGMII;
 		break;
+	case DPMAC_ETH_IF_USXGMII:
+		*if_mode = PHY_INTERFACE_MODE_USXGMII;
+		break;
+	case DPMAC_ETH_IF_QSGMII:
+		*if_mode = PHY_INTERFACE_MODE_QSGMII;
+		break;
+	case DPMAC_ETH_IF_SGMII:
+		*if_mode = PHY_INTERFACE_MODE_SGMII;
+		break;
+	case DPMAC_ETH_IF_XFI:
+		*if_mode = PHY_INTERFACE_MODE_10GBASER;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -67,6 +79,10 @@ static bool dpaa2_mac_phy_mode_mismatch(struct dpaa2_mac *mac,
 					phy_interface_t interface)
 {
 	switch (interface) {
+	case PHY_INTERFACE_MODE_10GBASER:
+	case PHY_INTERFACE_MODE_USXGMII:
+	case PHY_INTERFACE_MODE_QSGMII:
+	case PHY_INTERFACE_MODE_SGMII:
 	case PHY_INTERFACE_MODE_RGMII:
 	case PHY_INTERFACE_MODE_RGMII_ID:
 	case PHY_INTERFACE_MODE_RGMII_RXID:
@@ -95,6 +111,17 @@ static void dpaa2_mac_validate(struct phylink_config *config,
 	phylink_set(mask, Asym_Pause);
 
 	switch (state->interface) {
+	case PHY_INTERFACE_MODE_NA:
+	case PHY_INTERFACE_MODE_10GBASER:
+	case PHY_INTERFACE_MODE_USXGMII:
+		phylink_set(mask, 10000baseT_Full);
+		if (state->interface == PHY_INTERFACE_MODE_10GBASER)
+			break;
+		phylink_set(mask, 5000baseT_Full);
+		phylink_set(mask, 2500baseT_Full);
+		fallthrough;
+	case PHY_INTERFACE_MODE_SGMII:
+	case PHY_INTERFACE_MODE_QSGMII:
 	case PHY_INTERFACE_MODE_RGMII:
 	case PHY_INTERFACE_MODE_RGMII_ID:
 	case PHY_INTERFACE_MODE_RGMII_RXID:
@@ -227,6 +254,51 @@ out:
 	return fixed;
 }
 
+static int dpaa2_pcs_create(struct dpaa2_mac *mac,
+			    struct device_node *dpmac_node, int id)
+{
+	struct mdio_device *mdiodev;
+	struct device_node *node;
+
+	node = of_parse_phandle(dpmac_node, "pcs-handle", 0);
+	if (!node) {
+		/* do not error out on old DTS files */
+		netdev_warn(mac->net_dev, "pcs-handle node not found\n");
+		return 0;
+	}
+
+	if (!of_device_is_available(node)) {
+		netdev_err(mac->net_dev, "pcs-handle node not available\n");
+		return -ENODEV;
+	}
+
+	mdiodev = of_mdio_find_device(node);
+	of_node_put(node);
+	if (!mdiodev)
+		return -EPROBE_DEFER;
+
+	mac->pcs = lynx_pcs_create(mdiodev);
+	if (!mac->pcs) {
+		netdev_err(mac->net_dev, "lynx_pcs_create() failed\n");
+		put_device(&mdiodev->dev);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void dpaa2_pcs_destroy(struct dpaa2_mac *mac)
+{
+	struct lynx_pcs *pcs = mac->pcs;
+
+	if (pcs) {
+		struct device *dev = &pcs->mdio->dev;
+		lynx_pcs_destroy(pcs);
+		put_device(dev);
+		mac->pcs = NULL;
+	}
+}
+
 int dpaa2_mac_connect(struct dpaa2_mac *mac)
 {
 	struct fsl_mc_device *dpmac_dev = mac->mc_dev;
@@ -278,6 +350,13 @@ int dpaa2_mac_connect(struct dpaa2_mac *mac)
 		goto err_put_node;
 	}
 
+	if (attr.link_type == DPMAC_LINK_TYPE_PHY &&
+	    attr.eth_if != DPMAC_ETH_IF_RGMII) {
+		err = dpaa2_pcs_create(mac, dpmac_node, attr.id);
+		if (err)
+			goto err_put_node;
+	}
+
 	mac->phylink_config.dev = &net_dev->dev;
 	mac->phylink_config.type = PHYLINK_NETDEV;
 
@@ -286,10 +365,13 @@ int dpaa2_mac_connect(struct dpaa2_mac *mac)
 				 &dpaa2_mac_phylink_ops);
 	if (IS_ERR(phylink)) {
 		err = PTR_ERR(phylink);
-		goto err_put_node;
+		goto err_pcs_destroy;
 	}
 	mac->phylink = phylink;
 
+	if (mac->pcs)
+		phylink_set_pcs(mac->phylink, &mac->pcs->pcs);
+
 	err = phylink_of_phy_connect(mac->phylink, dpmac_node, 0);
 	if (err) {
 		netdev_err(net_dev, "phylink_of_phy_connect() = %d\n", err);
@@ -302,6 +384,8 @@ int dpaa2_mac_connect(struct dpaa2_mac *mac)
 
 err_phylink_destroy:
 	phylink_destroy(mac->phylink);
+err_pcs_destroy:
+	dpaa2_pcs_destroy(mac);
 err_put_node:
 	of_node_put(dpmac_node);
 err_close_dpmac:
@@ -316,6 +400,8 @@ void dpaa2_mac_disconnect(struct dpaa2_mac *mac)
 
 	phylink_disconnect_phy(mac->phylink);
 	phylink_destroy(mac->phylink);
+	dpaa2_pcs_destroy(mac);
+
 	dpmac_close(mac->mc_io, 0, mac->mc_dev->mc_handle);
 }
 
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.h
index 2130d9c7d40e..955a52856210 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.h
@@ -7,6 +7,7 @@
 #include <linux/of_mdio.h>
 #include <linux/of_net.h>
 #include <linux/phylink.h>
+#include <linux/pcs-lynx.h>
 
 #include "dpmac.h"
 #include "dpmac-cmd.h"
@@ -21,6 +22,7 @@ struct dpaa2_mac {
 	struct phylink *phylink;
 	phy_interface_t if_mode;
 	enum dpmac_link_type if_link_type;
+	struct lynx_pcs *pcs;
 };
 
 bool dpaa2_mac_is_type_fixed(struct fsl_mc_device *dpmac_dev,
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpmac-cmd.h b/drivers/net/ethernet/freescale/dpaa2/dpmac-cmd.h
index 3ea51dd9374b..a24b20f76938 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpmac-cmd.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpmac-cmd.h
@@ -66,8 +66,8 @@ struct dpmac_cmd_get_counter {
 };
 
 struct dpmac_rsp_get_counter {
-	u64 pad;
-	u64 counter;
+	__le64 pad;
+	__le64 counter;
 };
 
 #endif /* _FSL_DPMAC_CMD_H */
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpni.h b/drivers/net/ethernet/freescale/dpaa2/dpni.h
index 74456a37a997..e7b9e195b534 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpni.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpni.h
@@ -75,6 +75,10 @@ struct fsl_mc_io;
  * Disables the flow steering table.
  */
 #define DPNI_OPT_NO_FS				0x000020
+/**
+ * Flow steering table is shared between all traffic classes
+ */
+#define DPNI_OPT_SHARED_FS			0x001000
 
 int dpni_open(struct fsl_mc_io	*mc_io,
 	      u32		cmd_flags,
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
index 26d5981b798f..177334f0adb1 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
@@ -1053,7 +1053,6 @@ static int enetc_pf_probe(struct pci_dev *pdev,
 
 err_reg_netdev:
 	enetc_teardown_serdes(priv);
-	enetc_mdio_remove(pf);
 	enetc_free_msix(priv);
 err_alloc_msix:
 	enetc_free_si_resources(priv);
@@ -1061,6 +1060,7 @@ err_alloc_si_res:
 	si->ndev = NULL;
 	free_netdev(ndev);
 err_alloc_netdev:
+	enetc_mdio_remove(pf);
 	enetc_of_put_phy(pf);
 err_map_pf_space:
 	enetc_pci_remove(pdev);
diff --git a/drivers/net/ethernet/freescale/fec_mpc52xx.c b/drivers/net/ethernet/freescale/fec_mpc52xx.c
index 7a3f066e611d..b3bad429e03b 100644
--- a/drivers/net/ethernet/freescale/fec_mpc52xx.c
+++ b/drivers/net/ethernet/freescale/fec_mpc52xx.c
@@ -74,7 +74,7 @@ struct mpc52xx_fec_priv {
 static irqreturn_t mpc52xx_fec_interrupt(int, void *);
 static irqreturn_t mpc52xx_fec_rx_interrupt(int, void *);
 static irqreturn_t mpc52xx_fec_tx_interrupt(int, void *);
-static void mpc52xx_fec_stop(struct net_device *dev);
+static void mpc52xx_fec_stop(struct net_device *dev, bool may_sleep);
 static void mpc52xx_fec_start(struct net_device *dev);
 static void mpc52xx_fec_reset(struct net_device *dev);
 
@@ -283,7 +283,7 @@ static int mpc52xx_fec_close(struct net_device *dev)
 
 	netif_stop_queue(dev);
 
-	mpc52xx_fec_stop(dev);
+	mpc52xx_fec_stop(dev, true);
 
 	mpc52xx_fec_free_rx_buffers(dev, priv->rx_dmatsk);
 
@@ -693,7 +693,7 @@ static void mpc52xx_fec_start(struct net_device *dev)
  *
  * stop all activity on fec and empty dma buffers
  */
-static void mpc52xx_fec_stop(struct net_device *dev)
+static void mpc52xx_fec_stop(struct net_device *dev, bool may_sleep)
 {
 	struct mpc52xx_fec_priv *priv = netdev_priv(dev);
 	struct mpc52xx_fec __iomem *fec = priv->fec;
@@ -706,7 +706,7 @@ static void mpc52xx_fec_stop(struct net_device *dev)
 	bcom_disable(priv->rx_dmatsk);
 
 	/* Wait for tx queue to drain, but only if we're in process context */
-	if (!in_interrupt()) {
+	if (may_sleep) {
 		timeout = jiffies + msecs_to_jiffies(2000);
 		while (time_before(jiffies, timeout) &&
 				!bcom_queue_empty(priv->tx_dmatsk))
@@ -738,7 +738,7 @@ static void mpc52xx_fec_reset(struct net_device *dev)
 	struct mpc52xx_fec_priv *priv = netdev_priv(dev);
 	struct mpc52xx_fec __iomem *fec = priv->fec;
 
-	mpc52xx_fec_stop(dev);
+	mpc52xx_fec_stop(dev, false);
 
 	out_be32(&fec->rfifo_status, in_be32(&fec->rfifo_status));
 	out_be32(&fec->reset_cntrl, FEC_RESET_CNTRL_RESET_FIFO);
diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c
index 0405a3975f3f..2e344aada4c6 100644
--- a/drivers/net/ethernet/freescale/fec_ptp.c
+++ b/drivers/net/ethernet/freescale/fec_ptp.c
@@ -512,7 +512,7 @@ int fec_ptp_get(struct net_device *ndev, struct ifreq *ifr)
 		-EFAULT : 0;
 }
 
-/**
+/*
  * fec_time_keep - call timecounter_read every second to avoid timer overrun
  *                 because ENET just support 32bit counter, will timeout in 4s
  */
@@ -566,7 +566,8 @@ static irqreturn_t fec_pps_interrupt(int irq, void *dev_id)
 
 /**
  * fec_ptp_init
- * @ndev: The FEC network adapter
+ * @pdev: The FEC network adapter
+ * @irq_idx: the interrupt index
  *
  * This function performs the required steps for enabling ptp
  * support. If ptp support has already been loaded it simply calls the
diff --git a/drivers/net/ethernet/freescale/fman/fman.c b/drivers/net/ethernet/freescale/fman/fman.c
index ef67e8599b39..ce0a121580f6 100644
--- a/drivers/net/ethernet/freescale/fman/fman.c
+++ b/drivers/net/ethernet/freescale/fman/fman.c
@@ -2063,11 +2063,11 @@ static int fman_set_exception(struct fman *fman,
 /**
  * fman_register_intr
  * @fman:	A Pointer to FMan device
- * @mod:	Calling module
+ * @module:	Calling module
  * @mod_id:	Module id (if more than 1 exists, '0' if not)
  * @intr_type:	Interrupt type (error/normal) selection.
- * @f_isr:	The interrupt service routine.
- * @h_src_arg:	Argument to be passed to f_isr.
+ * @isr_cb:	The interrupt service routine.
+ * @src_arg:	Argument to be passed to isr_cb.
  *
  * Used to register an event handler to be processed by FMan
  *
@@ -2091,7 +2091,7 @@ EXPORT_SYMBOL(fman_register_intr);
 /**
  * fman_unregister_intr
  * @fman:	A Pointer to FMan device
- * @mod:	Calling module
+ * @module:	Calling module
  * @mod_id:	Module id (if more than 1 exists, '0' if not)
  * @intr_type:	Interrupt type (error/normal) selection.
  *
@@ -2342,8 +2342,8 @@ EXPORT_SYMBOL(fman_get_bmi_max_fifo_size);
 
 /**
  * fman_get_revision
- * @fman		- Pointer to the FMan module
- * @rev_info		- A structure of revision information parameters.
+ * @fman:		- Pointer to the FMan module
+ * @rev_info:		- A structure of revision information parameters.
  *
  * Returns the FM revision
  *
@@ -2508,7 +2508,7 @@ EXPORT_SYMBOL(fman_get_rx_extra_headroom);
 
 /**
  * fman_bind
- * @dev:	FMan OF device pointer
+ * @fm_dev:	FMan OF device pointer
  *
  * Bind to a specific FMan device.
  *
diff --git a/drivers/net/ethernet/freescale/fman/fman_muram.c b/drivers/net/ethernet/freescale/fman/fman_muram.c
index 5ec94d243da0..7ad317e622bc 100644
--- a/drivers/net/ethernet/freescale/fman/fman_muram.c
+++ b/drivers/net/ethernet/freescale/fman/fman_muram.c
@@ -144,9 +144,9 @@ unsigned long fman_muram_alloc(struct muram_info *muram, size_t size)
 
 /**
  * fman_muram_free_mem
- * muram:	FM-MURAM module pointer.
- * offset:	offset of the memory region to be freed.
- * size:	size of the memory to be freed.
+ * @muram:	FM-MURAM module pointer.
+ * @offset:	offset of the memory region to be freed.
+ * @size:	size of the memory to be freed.
  *
  * Free an allocated memory from FM-MURAM partition.
  */
diff --git a/drivers/net/ethernet/freescale/fman/fman_port.c b/drivers/net/ethernet/freescale/fman/fman_port.c
index 624b2eb6f01d..d9baac0dbc7d 100644
--- a/drivers/net/ethernet/freescale/fman/fman_port.c
+++ b/drivers/net/ethernet/freescale/fman/fman_port.c
@@ -1410,9 +1410,11 @@ err_port_cfg:
 }
 EXPORT_SYMBOL(fman_port_config);
 
-/**
+/*
  * fman_port_use_kg_hash
- * port:        A pointer to a FM Port module.
+ * @port: A pointer to a FM Port module.
+ * @enable: enable or disable
+ *
  * Sets the HW KeyGen or the BMI as HW Parser next engine, enabling
  * or bypassing the KeyGen hashing of Rx traffic
  */
@@ -1430,7 +1432,8 @@ EXPORT_SYMBOL(fman_port_use_kg_hash);
 
 /**
  * fman_port_init
- * port:	A pointer to a FM Port module.
+ * @port:	A pointer to a FM Port module.
+ *
  * Initializes the FM PORT module by defining the software structure and
  * configuring the hardware registers.
  *
@@ -1524,8 +1527,8 @@ EXPORT_SYMBOL(fman_port_init);
 
 /**
  * fman_port_cfg_buf_prefix_content
- * @port			A pointer to a FM Port module.
- * @buffer_prefix_content	A structure of parameters describing
+ * @port:			A pointer to a FM Port module.
+ * @buffer_prefix_content:	A structure of parameters describing
  *				the structure of the buffer.
  *				Out parameter:
  *				Start margin - offset of data from
@@ -1570,7 +1573,7 @@ EXPORT_SYMBOL(fman_port_cfg_buf_prefix_content);
 
 /**
  * fman_port_disable
- * port:	A pointer to a FM Port module.
+ * @port:	A pointer to a FM Port module.
  *
  * Gracefully disable an FM port. The port will not start new	tasks after all
  * tasks associated with the port are terminated.
@@ -1651,7 +1654,7 @@ EXPORT_SYMBOL(fman_port_disable);
 
 /**
  * fman_port_enable
- * port:	A pointer to a FM Port module.
+ * @port:	A pointer to a FM Port module.
  *
  * A runtime routine provided to allow disable/enable of port.
  *
@@ -1697,7 +1700,7 @@ EXPORT_SYMBOL(fman_port_enable);
 
 /**
  * fman_port_bind
- * dev:		FMan Port OF device pointer
+ * @dev:		FMan Port OF device pointer
  *
  * Bind to a specific FMan Port.
  *
@@ -1713,7 +1716,7 @@ EXPORT_SYMBOL(fman_port_bind);
 
 /**
  * fman_port_get_qman_channel_id
- * port:	Pointer to the FMan port devuce
+ * @port:	Pointer to the FMan port devuce
  *
  * Get the QMan channel ID for the specific port
  *
@@ -1727,7 +1730,7 @@ EXPORT_SYMBOL(fman_port_get_qman_channel_id);
 
 /**
  * fman_port_get_device
- * port:	Pointer to the FMan port device
+ * @port:	Pointer to the FMan port device
  *
  * Get the 'struct device' associated to the specified FMan port device
  *
diff --git a/drivers/net/ethernet/freescale/fman/mac.c b/drivers/net/ethernet/freescale/fman/mac.c
index 43427c5b9396..901749a7a318 100644
--- a/drivers/net/ethernet/freescale/fman/mac.c
+++ b/drivers/net/ethernet/freescale/fman/mac.c
@@ -359,8 +359,8 @@ EXPORT_SYMBOL(fman_set_mac_active_pause);
 /**
  * fman_get_pause_cfg
  * @mac_dev:	A pointer to the MAC device
- * @rx:		Return value for RX setting
- * @tx:		Return value for TX setting
+ * @rx_pause:	Return value for RX setting
+ * @tx_pause:	Return value for TX setting
  *
  * Determine the MAC RX/TX PAUSE frames settings based on PHY
  * autonegotiation or values set by eththool.
diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.c b/drivers/net/ethernet/hisilicon/hns/hnae.c
index e017b7c34140..00fafc0f8512 100644
--- a/drivers/net/ethernet/hisilicon/hns/hnae.c
+++ b/drivers/net/ethernet/hisilicon/hns/hnae.c
@@ -270,7 +270,7 @@ static void hnae_fini_queue(struct hnae_queue *q)
 	hnae_fini_ring(&q->rx_ring);
 }
 
-/**
+/*
  * ae_chain - define ae chain head
  */
 static RAW_NOTIFIER_HEAD(ae_chain);
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
index 9a907947ba19..4a448138b4ec 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
@@ -374,11 +374,12 @@ static void hns_mac_param_get(struct mac_params *param,
 }
 
 /**
- *hns_mac_queue_config_bc_en - set broadcast rx&tx enable
- *@mac_cb: mac device
- *@queue: queue number
- *@en:enable
- *retuen 0 - success , negative --fail
+ * hns_mac_queue_config_bc_en - set broadcast rx&tx enable
+ * @mac_cb: mac device
+ * @port_num: queue number
+ * @vlan_id: vlan id`
+ * @enable: enable
+ * return 0 - success , negative --fail
  */
 static int hns_mac_port_config_bc_en(struct hns_mac_cb *mac_cb,
 				     u32 port_num, u16 vlan_id, bool enable)
@@ -408,11 +409,11 @@ static int hns_mac_port_config_bc_en(struct hns_mac_cb *mac_cb,
 }
 
 /**
- *hns_mac_vm_config_bc_en - set broadcast rx&tx enable
- *@mac_cb: mac device
- *@vmid: vm id
- *@en:enable
- *retuen 0 - success , negative --fail
+ * hns_mac_vm_config_bc_en - set broadcast rx&tx enable
+ * @mac_cb: mac device
+ * @vmid: vm id
+ * @enable: enable
+ * return 0 - success , negative --fail
  */
 int hns_mac_vm_config_bc_en(struct hns_mac_cb *mac_cb, u32 vmid, bool enable)
 {
@@ -542,8 +543,8 @@ void hns_mac_stop(struct hns_mac_cb *mac_cb)
 /**
  * hns_mac_get_autoneg - get auto autonegotiation
  * @mac_cb: mac control block
- * @enable: enable or not
- * retuen 0 - success , negative --fail
+ * @auto_neg: output pointer to autoneg result
+ * return 0 - success , negative --fail
  */
 void hns_mac_get_autoneg(struct hns_mac_cb *mac_cb, u32 *auto_neg)
 {
@@ -560,7 +561,7 @@ void hns_mac_get_autoneg(struct hns_mac_cb *mac_cb, u32 *auto_neg)
  * @mac_cb: mac control block
  * @rx_en: rx enable status
  * @tx_en: tx enable status
- * retuen 0 - success , negative --fail
+ * return 0 - success , negative --fail
  */
 void hns_mac_get_pauseparam(struct hns_mac_cb *mac_cb, u32 *rx_en, u32 *tx_en)
 {
@@ -578,7 +579,7 @@ void hns_mac_get_pauseparam(struct hns_mac_cb *mac_cb, u32 *rx_en, u32 *tx_en)
  * hns_mac_set_autoneg - set auto autonegotiation
  * @mac_cb: mac control block
  * @enable: enable or not
- * retuen 0 - success , negative --fail
+ * return 0 - success , negative --fail
  */
 int hns_mac_set_autoneg(struct hns_mac_cb *mac_cb, u8 enable)
 {
@@ -623,7 +624,7 @@ int hns_mac_set_pauseparam(struct hns_mac_cb *mac_cb, u32 rx_en, u32 tx_en)
 /**
  * hns_mac_init_ex - mac init
  * @mac_cb: mac control block
- * retuen 0 - success , negative --fail
+ * return 0 - success , negative --fail
  */
 static int hns_mac_init_ex(struct hns_mac_cb *mac_cb)
 {
@@ -800,7 +801,6 @@ static const struct {
 /**
  *hns_mac_get_info  - get mac information from device node
  *@mac_cb: mac device
- *@np:device node
  * return: 0 --success, negative --fail
  */
 static int hns_mac_get_info(struct hns_mac_cb *mac_cb)
@@ -951,7 +951,7 @@ static int hns_mac_get_info(struct hns_mac_cb *mac_cb)
 /**
  * hns_mac_get_mode - get mac mode
  * @phy_if: phy interface
- * retuen 0 - gmac, 1 - xgmac , negative --fail
+ * return 0 - gmac, 1 - xgmac , negative --fail
  */
 static int hns_mac_get_mode(phy_interface_t phy_if)
 {
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
index acfa86e5296f..87d3db4666df 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
@@ -207,7 +207,7 @@ static int hns_dsaf_get_cfg(struct dsaf_device *dsaf_dev)
 
 /**
  * hns_dsaf_sbm_link_sram_init_en - config dsaf_sbm_init_en
- * @dsaf_id: dsa fabric id
+ * @dsaf_dev: dsa fabric id
  */
 static void hns_dsaf_sbm_link_sram_init_en(struct dsaf_device *dsaf_dev)
 {
@@ -216,8 +216,8 @@ static void hns_dsaf_sbm_link_sram_init_en(struct dsaf_device *dsaf_dev)
 
 /**
  * hns_dsaf_reg_cnt_clr_ce - config hns_dsaf_reg_cnt_clr_ce
- * @dsaf_id: dsa fabric id
- * @hns_dsaf_reg_cnt_clr_ce: config value
+ * @dsaf_dev: dsa fabric id
+ * @reg_cnt_clr_ce: config value
  */
 static void
 hns_dsaf_reg_cnt_clr_ce(struct dsaf_device *dsaf_dev, u32 reg_cnt_clr_ce)
@@ -228,8 +228,8 @@ hns_dsaf_reg_cnt_clr_ce(struct dsaf_device *dsaf_dev, u32 reg_cnt_clr_ce)
 
 /**
  * hns_ppe_qid_cfg - config ppe qid
- * @dsaf_id: dsa fabric id
- * @pppe_qid_cfg: value array
+ * @dsaf_dev: dsa fabric id
+ * @qid_cfg: value array
  */
 static void
 hns_dsaf_ppe_qid_cfg(struct dsaf_device *dsaf_dev, u32 qid_cfg)
@@ -285,8 +285,8 @@ static void hns_dsaf_inner_qid_cfg(struct dsaf_device *dsaf_dev)
 
 /**
  * hns_dsaf_sw_port_type_cfg - cfg sw type
- * @dsaf_id: dsa fabric id
- * @psw_port_type: array
+ * @dsaf_dev: dsa fabric id
+ * @port_type: array
  */
 static void hns_dsaf_sw_port_type_cfg(struct dsaf_device *dsaf_dev,
 				      enum dsaf_sw_port_type port_type)
@@ -303,8 +303,8 @@ static void hns_dsaf_sw_port_type_cfg(struct dsaf_device *dsaf_dev,
 
 /**
  * hns_dsaf_stp_port_type_cfg - cfg stp type
- * @dsaf_id: dsa fabric id
- * @pstp_port_type: array
+ * @dsaf_dev: dsa fabric id
+ * @port_type: array
  */
 static void hns_dsaf_stp_port_type_cfg(struct dsaf_device *dsaf_dev,
 				       enum dsaf_stp_port_type port_type)
@@ -323,7 +323,7 @@ static void hns_dsaf_stp_port_type_cfg(struct dsaf_device *dsaf_dev,
 	(AE_IS_VER1((dev)->dsaf_ver) ? DSAF_SBM_NUM : DSAFV2_SBM_NUM)
 /**
  * hns_dsaf_sbm_cfg - config sbm
- * @dsaf_id: dsa fabric id
+ * @dsaf_dev: dsa fabric id
  */
 static void hns_dsaf_sbm_cfg(struct dsaf_device *dsaf_dev)
 {
@@ -342,7 +342,7 @@ static void hns_dsaf_sbm_cfg(struct dsaf_device *dsaf_dev)
 
 /**
  * hns_dsaf_sbm_cfg_mib_en - config sbm
- * @dsaf_id: dsa fabric id
+ * @dsaf_dev: dsa fabric id
  */
 static int hns_dsaf_sbm_cfg_mib_en(struct dsaf_device *dsaf_dev)
 {
@@ -387,7 +387,7 @@ static int hns_dsaf_sbm_cfg_mib_en(struct dsaf_device *dsaf_dev)
 
 /**
  * hns_dsaf_sbm_bp_wl_cfg - config sbm
- * @dsaf_id: dsa fabric id
+ * @dsaf_dev: dsa fabric id
  */
 static void hns_dsaf_sbm_bp_wl_cfg(struct dsaf_device *dsaf_dev)
 {
@@ -556,7 +556,7 @@ static void hns_dsafv2_sbm_bp_wl_cfg(struct dsaf_device *dsaf_dev)
 
 /**
  * hns_dsaf_voq_bp_all_thrd_cfg -  voq
- * @dsaf_id: dsa fabric id
+ * @dsaf_dev: dsa fabric id
  */
 static void hns_dsaf_voq_bp_all_thrd_cfg(struct dsaf_device *dsaf_dev)
 {
@@ -599,7 +599,7 @@ static void hns_dsaf_tbl_tcam_match_cfg(
 
 /**
  * hns_dsaf_tbl_tcam_data_cfg - tbl
- * @dsaf_id: dsa fabric id
+ * @dsaf_dev: dsa fabric id
  * @ptbl_tcam_data: addr
  */
 static void hns_dsaf_tbl_tcam_data_cfg(
@@ -614,8 +614,8 @@ static void hns_dsaf_tbl_tcam_data_cfg(
 
 /**
  * dsaf_tbl_tcam_mcast_cfg - tbl
- * @dsaf_id: dsa fabric id
- * @ptbl_tcam_mcast: addr
+ * @dsaf_dev: dsa fabric id
+ * @mcast: addr
  */
 static void hns_dsaf_tbl_tcam_mcast_cfg(
 	struct dsaf_device *dsaf_dev,
@@ -648,8 +648,8 @@ static void hns_dsaf_tbl_tcam_mcast_cfg(
 
 /**
  * hns_dsaf_tbl_tcam_ucast_cfg - tbl
- * @dsaf_id: dsa fabric id
- * @ptbl_tcam_ucast: addr
+ * @dsaf_dev: dsa fabric id
+ * @tbl_tcam_ucast: addr
  */
 static void hns_dsaf_tbl_tcam_ucast_cfg(
 	struct dsaf_device *dsaf_dev,
@@ -674,8 +674,8 @@ static void hns_dsaf_tbl_tcam_ucast_cfg(
 
 /**
  * hns_dsaf_tbl_line_cfg - tbl
- * @dsaf_id: dsa fabric id
- * @ptbl_lin: addr
+ * @dsaf_dev: dsa fabric id
+ * @tbl_lin: addr
  */
 static void hns_dsaf_tbl_line_cfg(struct dsaf_device *dsaf_dev,
 				  struct dsaf_tbl_line_cfg *tbl_lin)
@@ -695,7 +695,7 @@ static void hns_dsaf_tbl_line_cfg(struct dsaf_device *dsaf_dev,
 
 /**
  * hns_dsaf_tbl_tcam_mcast_pul - tbl
- * @dsaf_id: dsa fabric id
+ * @dsaf_dev: dsa fabric id
  */
 static void hns_dsaf_tbl_tcam_mcast_pul(struct dsaf_device *dsaf_dev)
 {
@@ -710,7 +710,7 @@ static void hns_dsaf_tbl_tcam_mcast_pul(struct dsaf_device *dsaf_dev)
 
 /**
  * hns_dsaf_tbl_line_pul - tbl
- * @dsaf_id: dsa fabric id
+ * @dsaf_dev: dsa fabric id
  */
 static void hns_dsaf_tbl_line_pul(struct dsaf_device *dsaf_dev)
 {
@@ -725,7 +725,7 @@ static void hns_dsaf_tbl_line_pul(struct dsaf_device *dsaf_dev)
 
 /**
  * hns_dsaf_tbl_tcam_data_mcast_pul - tbl
- * @dsaf_id: dsa fabric id
+ * @dsaf_dev: dsa fabric id
  */
 static void hns_dsaf_tbl_tcam_data_mcast_pul(
 	struct dsaf_device *dsaf_dev)
@@ -743,7 +743,7 @@ static void hns_dsaf_tbl_tcam_data_mcast_pul(
 
 /**
  * hns_dsaf_tbl_tcam_data_ucast_pul - tbl
- * @dsaf_id: dsa fabric id
+ * @dsaf_dev: dsa fabric id
  */
 static void hns_dsaf_tbl_tcam_data_ucast_pul(
 	struct dsaf_device *dsaf_dev)
@@ -768,8 +768,7 @@ void hns_dsaf_set_promisc_mode(struct dsaf_device *dsaf_dev, u32 en)
 
 /**
  * hns_dsaf_tbl_stat_en - tbl
- * @dsaf_id: dsa fabric id
- * @ptbl_stat_en: addr
+ * @dsaf_dev: dsa fabric id
  */
 static void hns_dsaf_tbl_stat_en(struct dsaf_device *dsaf_dev)
 {
@@ -785,7 +784,7 @@ static void hns_dsaf_tbl_stat_en(struct dsaf_device *dsaf_dev)
 
 /**
  * hns_dsaf_rocee_bp_en - rocee back press enable
- * @dsaf_id: dsa fabric id
+ * @dsaf_dev: dsa fabric id
  */
 static void hns_dsaf_rocee_bp_en(struct dsaf_device *dsaf_dev)
 {
@@ -852,9 +851,9 @@ static void hns_dsaf_int_tbl_src_clr(struct dsaf_device *dsaf_dev,
 
 /**
  * hns_dsaf_single_line_tbl_cfg - INT
- * @dsaf_id: dsa fabric id
- * @address:
- * @ptbl_line:
+ * @dsaf_dev: dsa fabric id
+ * @address: the address
+ * @ptbl_line: the line
  */
 static void hns_dsaf_single_line_tbl_cfg(
 	struct dsaf_device *dsaf_dev,
@@ -876,9 +875,10 @@ static void hns_dsaf_single_line_tbl_cfg(
 
 /**
  * hns_dsaf_tcam_uc_cfg - INT
- * @dsaf_id: dsa fabric id
- * @address,
- * @ptbl_tcam_data,
+ * @dsaf_dev: dsa fabric id
+ * @address: the address
+ * @ptbl_tcam_data: the data
+ * @ptbl_tcam_ucast: unicast
  */
 static void hns_dsaf_tcam_uc_cfg(
 	struct dsaf_device *dsaf_dev, u32 address,
@@ -904,7 +904,8 @@ static void hns_dsaf_tcam_uc_cfg(
  * @dsaf_dev: dsa fabric device struct pointer
  * @address: tcam index
  * @ptbl_tcam_data: tcam data struct pointer
- * @ptbl_tcam_mcast: tcam mask struct pointer, it must be null for HNSv1
+ * @ptbl_tcam_mask: tcam mask struct pointer, it must be null for HNSv1
+ * @ptbl_tcam_mcast: tcam data struct pointer
  */
 static void hns_dsaf_tcam_mc_cfg(
 	struct dsaf_device *dsaf_dev, u32 address,
@@ -933,8 +934,10 @@ static void hns_dsaf_tcam_mc_cfg(
 /**
  * hns_dsaf_tcam_uc_cfg_vague - INT
  * @dsaf_dev: dsa fabric device struct pointer
- * @address,
- * @ptbl_tcam_data,
+ * @address: the address
+ * @tcam_data: the data
+ * @tcam_mask: the mask
+ * @tcam_uc: the unicast data
  */
 static void hns_dsaf_tcam_uc_cfg_vague(struct dsaf_device *dsaf_dev,
 				       u32 address,
@@ -960,10 +963,10 @@ static void hns_dsaf_tcam_uc_cfg_vague(struct dsaf_device *dsaf_dev,
 /**
  * hns_dsaf_tcam_mc_cfg_vague - INT
  * @dsaf_dev: dsa fabric device struct pointer
- * @address,
- * @ptbl_tcam_data,
- * @ptbl_tcam_mask
- * @ptbl_tcam_mcast
+ * @address: the address
+ * @tcam_data: the data
+ * @tcam_mask: the mask
+ * @tcam_mc: the multicast data
  */
 static void hns_dsaf_tcam_mc_cfg_vague(struct dsaf_device *dsaf_dev,
 				       u32 address,
@@ -988,8 +991,8 @@ static void hns_dsaf_tcam_mc_cfg_vague(struct dsaf_device *dsaf_dev,
 
 /**
  * hns_dsaf_tcam_mc_invld - INT
- * @dsaf_id: dsa fabric id
- * @address
+ * @dsaf_dev: dsa fabric id
+ * @address: the address
  */
 static void hns_dsaf_tcam_mc_invld(struct dsaf_device *dsaf_dev, u32 address)
 {
@@ -1024,10 +1027,10 @@ hns_dsaf_tcam_addr_get(struct dsaf_drv_tbl_tcam_key *mac_key, u8 *addr)
 
 /**
  * hns_dsaf_tcam_uc_get - INT
- * @dsaf_id: dsa fabric id
- * @address
- * @ptbl_tcam_data
- * @ptbl_tcam_ucast
+ * @dsaf_dev: dsa fabric id
+ * @address: the address
+ * @ptbl_tcam_data: the data
+ * @ptbl_tcam_ucast: unicast
  */
 static void hns_dsaf_tcam_uc_get(
 	struct dsaf_device *dsaf_dev, u32 address,
@@ -1077,10 +1080,10 @@ static void hns_dsaf_tcam_uc_get(
 
 /**
  * hns_dsaf_tcam_mc_get - INT
- * @dsaf_id: dsa fabric id
- * @address
- * @ptbl_tcam_data
- * @ptbl_tcam_ucast
+ * @dsaf_dev: dsa fabric id
+ * @address: the address
+ * @ptbl_tcam_data: the data
+ * @ptbl_tcam_mcast: tcam multicast data
  */
 static void hns_dsaf_tcam_mc_get(
 	struct dsaf_device *dsaf_dev, u32 address,
@@ -1127,7 +1130,7 @@ static void hns_dsaf_tcam_mc_get(
 
 /**
  * hns_dsaf_tbl_line_init - INT
- * @dsaf_id: dsa fabric id
+ * @dsaf_dev: dsa fabric id
  */
 static void hns_dsaf_tbl_line_init(struct dsaf_device *dsaf_dev)
 {
@@ -1141,7 +1144,7 @@ static void hns_dsaf_tbl_line_init(struct dsaf_device *dsaf_dev)
 
 /**
  * hns_dsaf_tbl_tcam_init - INT
- * @dsaf_id: dsa fabric id
+ * @dsaf_dev: dsa fabric id
  */
 static void hns_dsaf_tbl_tcam_init(struct dsaf_device *dsaf_dev)
 {
@@ -1156,7 +1159,9 @@ static void hns_dsaf_tbl_tcam_init(struct dsaf_device *dsaf_dev)
 
 /**
  * hns_dsaf_pfc_en_cfg - dsaf pfc pause cfg
- * @mac_cb: mac contrl block
+ * @dsaf_dev: dsa fabric id
+ * @mac_id: mac contrl block
+ * @tc_en: traffic class
  */
 static void hns_dsaf_pfc_en_cfg(struct dsaf_device *dsaf_dev,
 				int mac_id, int tc_en)
@@ -1209,8 +1214,7 @@ void hns_dsaf_get_rx_mac_pause_en(struct dsaf_device *dsaf_dev, int mac_id,
 
 /**
  * hns_dsaf_tbl_tcam_init - INT
- * @dsaf_id: dsa fabric id
- * @dsaf_mode
+ * @dsaf_dev: dsa fabric id
  */
 static void hns_dsaf_comm_init(struct dsaf_device *dsaf_dev)
 {
@@ -1263,7 +1267,7 @@ static void hns_dsaf_comm_init(struct dsaf_device *dsaf_dev)
 
 /**
  * hns_dsaf_inode_init - INT
- * @dsaf_id: dsa fabric id
+ * @dsaf_dev: dsa fabric id
  */
 static void hns_dsaf_inode_init(struct dsaf_device *dsaf_dev)
 {
@@ -1315,7 +1319,7 @@ static void hns_dsaf_inode_init(struct dsaf_device *dsaf_dev)
 
 /**
  * hns_dsaf_sbm_init - INT
- * @dsaf_id: dsa fabric id
+ * @dsaf_dev: dsa fabric id
  */
 static int hns_dsaf_sbm_init(struct dsaf_device *dsaf_dev)
 {
@@ -1369,7 +1373,7 @@ static int hns_dsaf_sbm_init(struct dsaf_device *dsaf_dev)
 
 /**
  * hns_dsaf_tbl_init - INT
- * @dsaf_id: dsa fabric id
+ * @dsaf_dev: dsa fabric id
  */
 static void hns_dsaf_tbl_init(struct dsaf_device *dsaf_dev)
 {
@@ -1381,7 +1385,7 @@ static void hns_dsaf_tbl_init(struct dsaf_device *dsaf_dev)
 
 /**
  * hns_dsaf_voq_init - INT
- * @dsaf_id: dsa fabric id
+ * @dsaf_dev: dsa fabric id
  */
 static void hns_dsaf_voq_init(struct dsaf_device *dsaf_dev)
 {
@@ -1435,7 +1439,7 @@ static void hns_dsaf_remove_hw(struct dsaf_device *dsaf_dev)
 /**
  * hns_dsaf_init - init dsa fabric
  * @dsaf_dev: dsa fabric device struct pointer
- * retuen 0 - success , negative --fail
+ * return 0 - success , negative --fail
  */
 static int hns_dsaf_init(struct dsaf_device *dsaf_dev)
 {
@@ -2099,7 +2103,7 @@ static struct dsaf_device *hns_dsaf_alloc_dev(struct device *dev,
 
 /**
  * hns_dsaf_free_dev - free dev mem
- * @dev: struct device pointer
+ * @dsaf_dev: struct device pointer
  */
 static void hns_dsaf_free_dev(struct dsaf_device *dsaf_dev)
 {
@@ -2108,9 +2112,9 @@ static void hns_dsaf_free_dev(struct dsaf_device *dsaf_dev)
 
 /**
  * dsaf_pfc_unit_cnt - set pfc unit count
- * @dsaf_id: dsa fabric id
- * @pport_rate:  value array
- * @pdsaf_pfc_unit_cnt:  value array
+ * @dsaf_dev: dsa fabric id
+ * @mac_id: id in use
+ * @rate:  value array
  */
 static void hns_dsaf_pfc_unit_cnt(struct dsaf_device *dsaf_dev, int  mac_id,
 				  enum dsaf_port_rate_mode rate)
@@ -2139,8 +2143,9 @@ static void hns_dsaf_pfc_unit_cnt(struct dsaf_device *dsaf_dev, int  mac_id,
 
 /**
  * dsaf_port_work_rate_cfg - fifo
- * @dsaf_id: dsa fabric id
- * @xge_ge_work_mode
+ * @dsaf_dev: dsa fabric id
+ * @mac_id: mac contrl block
+ * @rate_mode: value array
  */
 static void
 hns_dsaf_port_work_rate_cfg(struct dsaf_device *dsaf_dev, int mac_id,
@@ -2253,7 +2258,8 @@ void hns_dsaf_update_stats(struct dsaf_device *dsaf_dev, u32 node_num)
 
 /**
  *hns_dsaf_get_regs - dump dsaf regs
- *@dsaf_dev: dsaf device
+ *@ddev: dsaf device
+ *@port: port
  *@data:data for value of regs
  */
 void hns_dsaf_get_regs(struct dsaf_device *ddev, u32 port, void *data)
@@ -2690,6 +2696,7 @@ void hns_dsaf_get_stats(struct dsaf_device *ddev, u64 *data, int port)
 
 /**
  *hns_dsaf_get_sset_count - get dsaf string set count
+ *@dsaf_dev: dsaf device
  *@stringset: type of values in data
  *return dsaf string name count
  */
@@ -2711,6 +2718,7 @@ int hns_dsaf_get_sset_count(struct dsaf_device *dsaf_dev, int stringset)
  *@stringset:srting set index
  *@data:strings name value
  *@port:port index
+ *@dsaf_dev: dsaf device
  */
 void hns_dsaf_get_strings(int stringset, u8 *data, int port,
 			  struct dsaf_device *dsaf_dev)
@@ -2943,7 +2951,7 @@ int hns_dsaf_wait_pkt_clean(struct dsaf_device *dsaf_dev, int port)
 /**
  * dsaf_probe - probo dsaf dev
  * @pdev: dasf platform device
- * retuen 0 - success , negative --fail
+ * return 0 - success , negative --fail
  */
 static int hns_dsaf_probe(struct platform_device *pdev)
 {
@@ -3038,8 +3046,8 @@ module_platform_driver(g_dsaf_driver);
 /**
  * hns_dsaf_roce_reset - reset dsaf and roce
  * @dsaf_fwnode: Pointer to framework node for the dasf
- * @enable: false - request reset , true - drop reset
- * retuen 0 - success , negative -fail
+ * @dereset: false - request reset , true - drop reset
+ * return 0 - success , negative -fail
  */
 int hns_dsaf_roce_reset(struct fwnode_handle *dsaf_fwnode, bool dereset)
 {
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c
index ed3829ae4ef1..a9aca8c24e90 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c
@@ -330,11 +330,12 @@ static void hns_dsaf_xge_srst_by_port_acpi(struct dsaf_device *dsaf_dev,
  * hns_dsaf_srst_chns - reset dsaf channels
  * @dsaf_dev: dsaf device struct pointer
  * @msk: xbar channels mask value:
+ * @dereset: false - request reset , true - drop reset
+ *
  * bit0-5 for xge0-5
  * bit6-11 for ppe0-5
  * bit12-17 for roce0-5
  * bit18-19 for com/dfx
- * @enable: false - request reset , true - drop reset
  */
 static void
 hns_dsaf_srst_chns(struct dsaf_device *dsaf_dev, u32 msk, bool dereset)
@@ -353,11 +354,12 @@ hns_dsaf_srst_chns(struct dsaf_device *dsaf_dev, u32 msk, bool dereset)
  * hns_dsaf_srst_chns - reset dsaf channels
  * @dsaf_dev: dsaf device struct pointer
  * @msk: xbar channels mask value:
+ * @dereset: false - request reset , true - drop reset
+ *
  * bit0-5 for xge0-5
  * bit6-11 for ppe0-5
  * bit12-17 for roce0-5
  * bit18-19 for com/dfx
- * @enable: false - request reset , true - drop reset
  */
 static void
 hns_dsaf_srst_chns_acpi(struct dsaf_device *dsaf_dev, u32 msk, bool dereset)
@@ -612,7 +614,8 @@ static int hns_mac_get_sfp_prsnt_acpi(struct hns_mac_cb *mac_cb, int *sfp_prsnt)
 /**
  * hns_mac_config_sds_loopback - set loop back for serdes
  * @mac_cb: mac control block
- * retuen 0 == success
+ * @en: enable or disable
+ * return 0 == success
  */
 static int hns_mac_config_sds_loopback(struct hns_mac_cb *mac_cb, bool en)
 {
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c
index 2b34b553acf3..d0f8b1fff333 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c
@@ -66,8 +66,8 @@ hns_ppe_common_get_ioaddr(struct ppe_common_cb *ppe_common)
 /**
  * hns_ppe_common_get_cfg - get ppe common config
  * @dsaf_dev: dasf device
- * comm_index: common index
- * retuen 0 - success , negative --fail
+ * @comm_index: common index
+ * return 0 - success , negative --fail
  */
 static int hns_ppe_common_get_cfg(struct dsaf_device *dsaf_dev, int comm_index)
 {
@@ -143,7 +143,7 @@ static void hns_ppe_set_vlan_strip(struct hns_ppe_cb *ppe_cb, int en)
 
 /**
  * hns_ppe_checksum_hw - set ppe checksum caculate
- * @ppe_device: ppe device
+ * @ppe_cb: ppe device
  * @value: value
  */
 static void hns_ppe_checksum_hw(struct hns_ppe_cb *ppe_cb, u32 value)
@@ -179,7 +179,7 @@ static void hns_ppe_set_qid(struct ppe_common_cb *ppe_common, u32 qid)
 
 /**
  * hns_ppe_set_port_mode - set port mode
- * @ppe_device: ppe device
+ * @ppe_cb: ppe device
  * @mode: port mode
  */
 static void hns_ppe_set_port_mode(struct hns_ppe_cb *ppe_cb,
@@ -344,7 +344,7 @@ static void hns_ppe_init_hw(struct hns_ppe_cb *ppe_cb)
 
 /**
  * ppe_uninit_hw - uninit ppe
- * @ppe_device: ppe device
+ * @ppe_cb: ppe device
  */
 static void hns_ppe_uninit_hw(struct hns_ppe_cb *ppe_cb)
 {
@@ -384,7 +384,8 @@ void hns_ppe_uninit(struct dsaf_device *dsaf_dev)
 /**
  * hns_ppe_reset - reinit ppe/rcb hw
  * @dsaf_dev: dasf device
- * retuen void
+ * @ppe_common_index: the index
+ * return void
  */
 void hns_ppe_reset_common(struct dsaf_device *dsaf_dev, u8 ppe_common_index)
 {
@@ -455,7 +456,7 @@ int hns_ppe_get_regs_count(void)
 
 /**
  * ppe_get_strings - get ppe srting
- * @ppe_device: ppe device
+ * @ppe_cb: ppe device
  * @stringset: string set type
  * @data: output string
  */
@@ -513,7 +514,7 @@ void hns_ppe_get_stats(struct hns_ppe_cb *ppe_cb, u64 *data)
 /**
  * hns_ppe_init - init ppe device
  * @dsaf_dev: dasf device
- * retuen 0 - success , negative --fail
+ * return 0 - success , negative --fail
  */
 int hns_ppe_init(struct dsaf_device *dsaf_dev)
 {
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c
index 5453597ec629..b6c8910cf7ba 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c
@@ -34,7 +34,7 @@
 /**
  *hns_rcb_wait_fbd_clean - clean fbd
  *@qs: ring struct pointer array
- *@qnum: num of array
+ *@q_num: num of array
  *@flag: tx or rx flag
  */
 void hns_rcb_wait_fbd_clean(struct hnae_queue **qs, int q_num, u32 flag)
@@ -191,7 +191,8 @@ void hns_rcbv2_int_clr_hw(struct hnae_queue *q, u32 flag)
 
 /**
  *hns_rcb_ring_enable_hw - enable ring
- *@ring: rcb ring
+ *@q: rcb ring
+ *@val: value to write
  */
 void hns_rcb_ring_enable_hw(struct hnae_queue *q, u32 val)
 {
@@ -844,7 +845,7 @@ void hns_rcb_update_stats(struct hnae_queue *queue)
 
 /**
  *hns_rcb_get_stats - get rcb statistic
- *@ring: rcb ring
+ *@queue: rcb ring
  *@data:statistic value
  */
 void hns_rcb_get_stats(struct hnae_queue *queue, u64 *data)
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c
index d832cd018c1c..7e3609ce112a 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c
@@ -242,7 +242,8 @@ static void hns_xgmac_config_pad_and_crc(void *mac_drv, u8 newval)
 /**
  *hns_xgmac_pausefrm_cfg - set pause param about xgmac
  *@mac_drv: mac driver
- *@newval:enable of pad and crc
+ *@rx_en: enable receive
+ *@tx_en: enable transmit
  */
 static void hns_xgmac_pausefrm_cfg(void *mac_drv, u32 rx_en, u32 tx_en)
 {
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
index 3cdc65d38fb7..858cb293152a 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
@@ -752,6 +752,8 @@ static void hns_update_rx_rate(struct hnae_ring *ring)
 
 /**
  * smooth_alg - smoothing algrithm for adjusting coalesce parameter
+ * @new_param: new value
+ * @old_param: old value
  **/
 static u32 smooth_alg(u32 new_param, u32 old_param)
 {
@@ -1829,7 +1831,7 @@ static int hns_nic_uc_unsync(struct net_device *netdev,
 }
 
 /**
- * nic_set_multicast_list - set mutl mac address
+ * hns_set_multicast_list - set mutl mac address
  * @ndev: net device
  *
  * return void
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
index 4eb50296f653..7165da0ee9aa 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
@@ -462,9 +462,9 @@ static int __lb_clean_rings(struct hns_nic_priv *priv,
 }
 
 /**
- * nic_run_loopback_test -  run loopback test
- * @nic_dev: net device
- * @loopback_type: loopback type
+ * __lb_run_test -  run loopback test
+ * @ndev: net device
+ * @loop_mode: loopback mode
  */
 static int __lb_run_test(struct net_device *ndev,
 			 enum hnae_loop loop_mode)
@@ -572,7 +572,7 @@ static int __lb_down(struct net_device *ndev, enum hnae_loop loop)
 
 /**
  * hns_nic_self_test - self test
- * @dev: net device
+ * @ndev: net device
  * @eth_test: test cmd
  * @data: test result
  */
@@ -633,7 +633,7 @@ static void hns_nic_self_test(struct net_device *ndev,
 
 /**
  * hns_nic_get_drvinfo - get net driver info
- * @dev: net device
+ * @net_dev: net device
  * @drvinfo: driver info
  */
 static void hns_nic_get_drvinfo(struct net_device *net_dev,
@@ -658,7 +658,7 @@ static void hns_nic_get_drvinfo(struct net_device *net_dev,
 
 /**
  * hns_get_ringparam - get ring parameter
- * @dev: net device
+ * @net_dev: net device
  * @param: ethtool parameter
  */
 static void hns_get_ringparam(struct net_device *net_dev,
@@ -683,7 +683,7 @@ static void hns_get_ringparam(struct net_device *net_dev,
 
 /**
  * hns_get_pauseparam - get pause parameter
- * @dev: net device
+ * @net_dev: net device
  * @param: pause parameter
  */
 static void hns_get_pauseparam(struct net_device *net_dev,
@@ -701,7 +701,7 @@ static void hns_get_pauseparam(struct net_device *net_dev,
 
 /**
  * hns_set_pauseparam - set pause parameter
- * @dev: net device
+ * @net_dev: net device
  * @param: pause parameter
  *
  * Return 0 on success, negative on failure
@@ -725,7 +725,7 @@ static int hns_set_pauseparam(struct net_device *net_dev,
 
 /**
  * hns_get_coalesce - get coalesce info.
- * @dev: net device
+ * @net_dev: net device
  * @ec: coalesce info.
  *
  * Return 0 on success, negative on failure.
@@ -769,7 +769,7 @@ static int hns_get_coalesce(struct net_device *net_dev,
 
 /**
  * hns_set_coalesce - set coalesce info.
- * @dev: net device
+ * @net_dev: net device
  * @ec: coalesce info.
  *
  * Return 0 on success, negative on failure.
@@ -808,7 +808,7 @@ static int hns_set_coalesce(struct net_device *net_dev,
 
 /**
  * hns_get_channels - get channel info.
- * @dev: net device
+ * @net_dev: net device
  * @ch: channel info.
  */
 static void
@@ -825,7 +825,7 @@ hns_get_channels(struct net_device *net_dev, struct ethtool_channels *ch)
 
 /**
  * get_ethtool_stats - get detail statistics.
- * @dev: net device
+ * @netdev: net device
  * @stats: statistics info.
  * @data: statistics data.
  */
@@ -883,8 +883,8 @@ static void hns_get_ethtool_stats(struct net_device *netdev,
 
 /**
  * get_strings: Return a set of strings that describe the requested objects
- * @dev: net device
- * @stats: string set ID.
+ * @netdev: net device
+ * @stringset: string set ID.
  * @data: objects data.
  */
 static void hns_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
@@ -971,8 +971,8 @@ static void hns_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
 }
 
 /**
- * nic_get_sset_count - get string set count witch returned by nic_get_strings.
- * @dev: net device
+ * hns_get_sset_count - get string set count returned by nic_get_strings
+ * @netdev: net device
  * @stringset: string set index, 0: self test string; 1: statistics string.
  *
  * Return string set count.
@@ -1006,7 +1006,7 @@ static int hns_get_sset_count(struct net_device *netdev, int stringset)
 
 /**
  * hns_phy_led_set - set phy LED status.
- * @dev: net device
+ * @netdev: net device
  * @value: LED state.
  *
  * Return 0 on success, negative on failure.
@@ -1027,8 +1027,8 @@ static int hns_phy_led_set(struct net_device *netdev, int value)
 }
 
 /**
- * nic_set_phys_id - set phy identify LED.
- * @dev: net device
+ * hns_set_phys_id - set phy identify LED.
+ * @netdev: net device
  * @state: LED state.
  *
  * Return 0 on success, negative on failure.
@@ -1104,9 +1104,9 @@ hns_set_phys_id(struct net_device *netdev, enum ethtool_phys_id_state state)
 
 /**
  * hns_get_regs - get net device register
- * @dev: net device
+ * @net_dev: net device
  * @cmd: ethtool cmd
- * @date: register data
+ * @data: register data
  */
 static void hns_get_regs(struct net_device *net_dev, struct ethtool_regs *cmd,
 			 void *data)
@@ -1125,8 +1125,8 @@ static void hns_get_regs(struct net_device *net_dev, struct ethtool_regs *cmd,
 }
 
 /**
- * nic_get_regs_len - get total register len.
- * @dev: net device
+ * hns_get_regs_len - get total register len.
+ * @net_dev: net device
  *
  * Return total register len.
  */
@@ -1151,7 +1151,7 @@ static int hns_get_regs_len(struct net_device *net_dev)
 
 /**
  * hns_nic_nway_reset - nway reset
- * @dev: net device
+ * @netdev: net device
  *
  * Return 0 on success, negative on failure
  */
diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index 088550db2de7..912c51e327d6 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -34,6 +34,13 @@
 
 #define HNAE3_MIN_VECTOR_NUM	2 /* first one for misc, another for IO */
 
+/* Device version */
+#define HNAE3_DEVICE_VERSION_V1   0x00020
+#define HNAE3_DEVICE_VERSION_V2   0x00021
+#define HNAE3_DEVICE_VERSION_V3   0x00030
+
+#define HNAE3_PCI_REVISION_BIT_SIZE		8
+
 /* Device IDs */
 #define HNAE3_DEV_ID_GE				0xA220
 #define HNAE3_DEV_ID_25GE			0xA221
@@ -42,8 +49,9 @@
 #define HNAE3_DEV_ID_50GE_RDMA			0xA224
 #define HNAE3_DEV_ID_50GE_RDMA_MACSEC		0xA225
 #define HNAE3_DEV_ID_100G_RDMA_MACSEC		0xA226
-#define HNAE3_DEV_ID_100G_VF			0xA22E
-#define HNAE3_DEV_ID_100G_RDMA_DCB_PFC_VF	0xA22F
+#define HNAE3_DEV_ID_200G_RDMA			0xA228
+#define HNAE3_DEV_ID_VF				0xA22E
+#define HNAE3_DEV_ID_RDMA_DCB_PFC_VF		0xA22F
 
 #define HNAE3_CLASS_NAME_SIZE 16
 
@@ -53,8 +61,6 @@
 #define HNAE3_KNIC_CLIENT_INITED_B		0x3
 #define HNAE3_UNIC_CLIENT_INITED_B		0x4
 #define HNAE3_ROCE_CLIENT_INITED_B		0x5
-#define HNAE3_DEV_SUPPORT_FD_B			0x6
-#define HNAE3_DEV_SUPPORT_GRO_B			0x7
 
 #define HNAE3_DEV_SUPPORT_ROCE_DCB_BITS (BIT(HNAE3_DEV_SUPPORT_DCB_B) |\
 		BIT(HNAE3_DEV_SUPPORT_ROCE_B))
@@ -65,11 +71,67 @@
 #define hnae3_dev_dcb_supported(hdev) \
 	hnae3_get_bit((hdev)->ae_dev->flag, HNAE3_DEV_SUPPORT_DCB_B)
 
+enum HNAE3_DEV_CAP_BITS {
+	HNAE3_DEV_SUPPORT_FD_B,
+	HNAE3_DEV_SUPPORT_GRO_B,
+	HNAE3_DEV_SUPPORT_FEC_B,
+	HNAE3_DEV_SUPPORT_UDP_GSO_B,
+	HNAE3_DEV_SUPPORT_QB_B,
+	HNAE3_DEV_SUPPORT_FD_FORWARD_TC_B,
+	HNAE3_DEV_SUPPORT_PTP_B,
+	HNAE3_DEV_SUPPORT_INT_QL_B,
+	HNAE3_DEV_SUPPORT_SIMPLE_BD_B,
+	HNAE3_DEV_SUPPORT_TX_PUSH_B,
+	HNAE3_DEV_SUPPORT_PHY_IMP_B,
+	HNAE3_DEV_SUPPORT_TQP_TXRX_INDEP_B,
+	HNAE3_DEV_SUPPORT_HW_PAD_B,
+	HNAE3_DEV_SUPPORT_STASH_B,
+};
+
 #define hnae3_dev_fd_supported(hdev) \
-	hnae3_get_bit((hdev)->ae_dev->flag, HNAE3_DEV_SUPPORT_FD_B)
+	test_bit(HNAE3_DEV_SUPPORT_FD_B, (hdev)->ae_dev->caps)
 
 #define hnae3_dev_gro_supported(hdev) \
-	hnae3_get_bit((hdev)->ae_dev->flag, HNAE3_DEV_SUPPORT_GRO_B)
+	test_bit(HNAE3_DEV_SUPPORT_GRO_B, (hdev)->ae_dev->caps)
+
+#define hnae3_dev_fec_supported(hdev) \
+	test_bit(HNAE3_DEV_SUPPORT_FEC_B, (hdev)->ae_dev->caps)
+
+#define hnae3_dev_udp_gso_supported(hdev) \
+	test_bit(HNAE3_DEV_SUPPORT_UDP_GSO_B, (hdev)->ae_dev->caps)
+
+#define hnae3_dev_qb_supported(hdev) \
+	test_bit(HNAE3_DEV_SUPPORT_QB_B, (hdev)->ae_dev->caps)
+
+#define hnae3_dev_fd_forward_tc_supported(hdev) \
+	test_bit(HNAE3_DEV_SUPPORT_FD_FORWARD_TC_B, (hdev)->ae_dev->caps)
+
+#define hnae3_dev_ptp_supported(hdev) \
+	test_bit(HNAE3_DEV_SUPPORT_PTP_B, (hdev)->ae_dev->caps)
+
+#define hnae3_dev_int_ql_supported(hdev) \
+	test_bit(HNAE3_DEV_SUPPORT_INT_QL_B, (hdev)->ae_dev->caps)
+
+#define hnae3_dev_simple_bd_supported(hdev) \
+	test_bit(HNAE3_DEV_SUPPORT_SIMPLE_BD_B, (hdev)->ae_dev->caps)
+
+#define hnae3_dev_tx_push_supported(hdev) \
+	test_bit(HNAE3_DEV_SUPPORT_TX_PUSH_B, (hdev)->ae_dev->caps)
+
+#define hnae3_dev_phy_imp_supported(hdev) \
+	test_bit(HNAE3_DEV_SUPPORT_PHY_IMP_B, (hdev)->ae_dev->caps)
+
+#define hnae3_dev_tqp_txrx_indep_supported(hdev) \
+	test_bit(HNAE3_DEV_SUPPORT_TQP_TXRX_INDEP_B, (hdev)->ae_dev->caps)
+
+#define hnae3_dev_hw_pad_supported(hdev) \
+	test_bit(HNAE3_DEV_SUPPORT_HW_PAD_B, (hdev)->ae_dev->caps)
+
+#define hnae3_dev_stash_supported(hdev) \
+	test_bit(HNAE3_DEV_SUPPORT_STASH_B, (hdev)->ae_dev->caps)
+
+#define hnae3_ae_dev_tqp_txrx_indep_supported(ae_dev) \
+	test_bit(HNAE3_DEV_SUPPORT_TQP_TXRX_INDEP_B, (ae_dev)->caps)
 
 #define ring_ptr_move_fw(ring, p) \
 	((ring)->p = ((ring)->p + 1) % (ring)->desc_num)
@@ -152,6 +214,7 @@ enum hnae3_hw_error_type {
 	HNAE3_PPU_POISON_ERROR,
 	HNAE3_CMDQ_ECC_ERROR,
 	HNAE3_IMP_RD_POISON_ERROR,
+	HNAE3_ROCEE_AXI_RESP_ERROR,
 };
 
 enum hnae3_reset_type {
@@ -207,6 +270,17 @@ struct hnae3_ring_chain_node {
 #define HNAE3_IS_TX_RING(node) \
 	(((node)->flag & (1 << HNAE3_RING_TYPE_B)) == HNAE3_RING_TYPE_TX)
 
+/* device specification info from firmware */
+struct hnae3_dev_specs {
+	u32 mac_entry_num; /* number of mac-vlan table entry */
+	u32 mng_entry_num; /* number of manager table entry */
+	u32 max_tm_rate;
+	u16 rss_ind_tbl_size;
+	u16 rss_key_size;
+	u16 int_ql_max; /* max value of interrupt coalesce based on INT_QL */
+	u8 max_non_tso_bd_num; /* max BD number of one non-TSO packet */
+};
+
 struct hnae3_client_ops {
 	int (*init_instance)(struct hnae3_handle *handle);
 	void (*uninit_instance)(struct hnae3_handle *handle, bool reset);
@@ -227,12 +301,16 @@ struct hnae3_client {
 	struct list_head node;
 };
 
+#define HNAE3_DEV_CAPS_MAX_NUM	96
 struct hnae3_ae_dev {
 	struct pci_dev *pdev;
 	const struct hnae3_ae_ops *ops;
 	struct list_head node;
 	u32 flag;
 	unsigned long hw_err_reset_req;
+	struct hnae3_dev_specs dev_specs;
+	u32 dev_version;
+	unsigned long caps[BITS_TO_LONGS(HNAE3_DEV_CAPS_MAX_NUM)];
 	void *priv;
 };
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
index fe7fb565da19..dc9a85745e62 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
@@ -15,11 +15,12 @@ static struct dentry *hns3_dbgfs_root;
 static int hns3_dbg_queue_info(struct hnae3_handle *h,
 			       const char *cmd_buf)
 {
+	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(h->pdev);
 	struct hns3_nic_priv *priv = h->priv;
 	struct hns3_enet_ring *ring;
 	u32 base_add_l, base_add_h;
 	u32 queue_num, queue_max;
-	u32 value, i = 0;
+	u32 value, i;
 	int cnt;
 
 	if (!priv->ring) {
@@ -118,8 +119,25 @@ static int hns3_dbg_queue_info(struct hnae3_handle *h,
 
 		value = readl_relaxed(ring->tqp->io_base +
 				      HNS3_RING_TX_RING_PKTNUM_RECORD_REG);
-		dev_info(&h->pdev->dev, "TX(%u) RING PKTNUM: %u\n\n", i,
-			 value);
+		dev_info(&h->pdev->dev, "TX(%u) RING PKTNUM: %u\n", i, value);
+
+		value = readl_relaxed(ring->tqp->io_base + HNS3_RING_EN_REG);
+		dev_info(&h->pdev->dev, "TX/RX(%u) RING EN: %s\n", i,
+			 value ? "enable" : "disable");
+
+		if (hnae3_ae_dev_tqp_txrx_indep_supported(ae_dev)) {
+			value = readl_relaxed(ring->tqp->io_base +
+					      HNS3_RING_TX_EN_REG);
+			dev_info(&h->pdev->dev, "TX(%u) RING EN: %s\n", i,
+				 value ? "enable" : "disable");
+
+			value = readl_relaxed(ring->tqp->io_base +
+					      HNS3_RING_RX_EN_REG);
+			dev_info(&h->pdev->dev, "RX(%u) RING EN: %s\n", i,
+				 value ? "enable" : "disable");
+		}
+
+		dev_info(&h->pdev->dev, "\n");
 	}
 
 	return 0;
@@ -244,6 +262,8 @@ static void hns3_dbg_help(struct hnae3_handle *h)
 	dev_info(&h->pdev->dev, "queue info <number>\n");
 	dev_info(&h->pdev->dev, "queue map\n");
 	dev_info(&h->pdev->dev, "bd info <q_num> <bd index>\n");
+	dev_info(&h->pdev->dev, "dev capability\n");
+	dev_info(&h->pdev->dev, "dev spec\n");
 
 	if (!hns3_is_phys_func(h->pdev))
 		return;
@@ -264,6 +284,7 @@ static void hns3_dbg_help(struct hnae3_handle *h)
 	dev_info(&h->pdev->dev, "dump qs shaper [qs id]\n");
 	dev_info(&h->pdev->dev, "dump uc mac list <func id>\n");
 	dev_info(&h->pdev->dev, "dump mc mac list <func id>\n");
+	dev_info(&h->pdev->dev, "dump intr\n");
 
 	memset(printf_buf, 0, HNS3_DBG_BUF_LEN);
 	strncat(printf_buf, "dump reg [[bios common] [ssu <port_id>]",
@@ -284,6 +305,52 @@ static void hns3_dbg_help(struct hnae3_handle *h)
 	dev_info(&h->pdev->dev, "%s", printf_buf);
 }
 
+static void hns3_dbg_dev_caps(struct hnae3_handle *h)
+{
+	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(h->pdev);
+	unsigned long *caps;
+
+	caps = ae_dev->caps;
+
+	dev_info(&h->pdev->dev, "support FD: %s\n",
+		 test_bit(HNAE3_DEV_SUPPORT_FD_B, caps) ? "yes" : "no");
+	dev_info(&h->pdev->dev, "support GRO: %s\n",
+		 test_bit(HNAE3_DEV_SUPPORT_GRO_B, caps) ? "yes" : "no");
+	dev_info(&h->pdev->dev, "support FEC: %s\n",
+		 test_bit(HNAE3_DEV_SUPPORT_FEC_B, caps) ? "yes" : "no");
+	dev_info(&h->pdev->dev, "support UDP GSO: %s\n",
+		 test_bit(HNAE3_DEV_SUPPORT_UDP_GSO_B, caps) ? "yes" : "no");
+	dev_info(&h->pdev->dev, "support PTP: %s\n",
+		 test_bit(HNAE3_DEV_SUPPORT_PTP_B, caps) ? "yes" : "no");
+	dev_info(&h->pdev->dev, "support INT QL: %s\n",
+		 test_bit(HNAE3_DEV_SUPPORT_INT_QL_B, caps) ? "yes" : "no");
+}
+
+static void hns3_dbg_dev_specs(struct hnae3_handle *h)
+{
+	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(h->pdev);
+	struct hnae3_dev_specs *dev_specs = &ae_dev->dev_specs;
+	struct hnae3_knic_private_info *kinfo = &h->kinfo;
+	struct hns3_nic_priv *priv  = h->priv;
+
+	dev_info(priv->dev, "MAC entry num: %u\n", dev_specs->mac_entry_num);
+	dev_info(priv->dev, "MNG entry num: %u\n", dev_specs->mng_entry_num);
+	dev_info(priv->dev, "MAX non tso bd num: %u\n",
+		 dev_specs->max_non_tso_bd_num);
+	dev_info(priv->dev, "RSS ind tbl size: %u\n",
+		 dev_specs->rss_ind_tbl_size);
+	dev_info(priv->dev, "RSS key size: %u\n", dev_specs->rss_key_size);
+	dev_info(priv->dev, "RSS size: %u\n", kinfo->rss_size);
+	dev_info(priv->dev, "Allocated RSS size: %u\n", kinfo->req_rss_size);
+	dev_info(priv->dev, "Task queue pairs numbers: %u\n", kinfo->num_tqps);
+
+	dev_info(priv->dev, "RX buffer length: %u\n", kinfo->rx_buf_len);
+	dev_info(priv->dev, "Desc num per TX queue: %u\n", kinfo->num_tx_desc);
+	dev_info(priv->dev, "Desc num per RX queue: %u\n", kinfo->num_rx_desc);
+	dev_info(priv->dev, "Total number of enabled TCs: %u\n", kinfo->num_tc);
+	dev_info(priv->dev, "MAX INT QL: %u\n", dev_specs->int_ql_max);
+}
+
 static ssize_t hns3_dbg_cmd_read(struct file *filp, char __user *buffer,
 				 size_t count, loff_t *ppos)
 {
@@ -359,6 +426,10 @@ static ssize_t hns3_dbg_cmd_write(struct file *filp, const char __user *buffer,
 		ret = hns3_dbg_queue_map(handle);
 	else if (strncmp(cmd_buf, "bd info", 7) == 0)
 		ret = hns3_dbg_bd_info(handle, cmd_buf);
+	else if (strncmp(cmd_buf, "dev capability", 14) == 0)
+		hns3_dbg_dev_caps(handle);
+	else if (strncmp(cmd_buf, "dev spec", 8) == 0)
+		hns3_dbg_dev_specs(handle);
 	else if (handle->ae_algo->ops->dbg_run_cmd)
 		ret = handle->ae_algo->ops->dbg_run_cmd(handle, cmd_buf);
 	else
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index feeaf758b669..a362516a3185 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -81,8 +81,10 @@ static const struct pci_device_id hns3_pci_tbl[] = {
 	 HNAE3_DEV_SUPPORT_ROCE_DCB_BITS},
 	{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_100G_RDMA_MACSEC),
 	 HNAE3_DEV_SUPPORT_ROCE_DCB_BITS},
-	{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_100G_VF), 0},
-	{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_100G_RDMA_DCB_PFC_VF),
+	{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_200G_RDMA),
+	 HNAE3_DEV_SUPPORT_ROCE_DCB_BITS},
+	{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_VF), 0},
+	{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_RDMA_DCB_PFC_VF),
 	 HNAE3_DEV_SUPPORT_ROCE_DCB_BITS},
 	/* required last entry */
 	{0, }
@@ -627,9 +629,11 @@ void hns3_enable_vlan_filter(struct net_device *netdev, bool enable)
 {
 	struct hns3_nic_priv *priv = netdev_priv(netdev);
 	struct hnae3_handle *h = priv->ae_handle;
+	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(h->pdev);
 	bool last_state;
 
-	if (h->pdev->revision >= 0x21 && h->ae_algo->ops->enable_vlan_filter) {
+	if (ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V2 &&
+	    h->ae_algo->ops->enable_vlan_filter) {
 		last_state = h->netdev_flags & HNAE3_VLAN_FLTR ? true : false;
 		if (enable != last_state) {
 			netdev_info(netdev,
@@ -692,12 +696,19 @@ static int hns3_set_tso(struct sk_buff *skb, u32 *paylen,
 
 	/* normal or tunnel packet */
 	l4_offset = l4.hdr - skb->data;
-	hdr_len = (l4.tcp->doff << 2) + l4_offset;
 
 	/* remove payload length from inner pseudo checksum when tso */
 	l4_paylen = skb->len - l4_offset;
-	csum_replace_by_diff(&l4.tcp->check,
-			     (__force __wsum)htonl(l4_paylen));
+
+	if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) {
+		hdr_len = sizeof(*l4.udp) + l4_offset;
+		csum_replace_by_diff(&l4.udp->check,
+				     (__force __wsum)htonl(l4_paylen));
+	} else {
+		hdr_len = (l4.tcp->doff << 2) + l4_offset;
+		csum_replace_by_diff(&l4.tcp->check,
+				     (__force __wsum)htonl(l4_paylen));
+	}
 
 	/* find the txbd field values */
 	*paylen = skb->len - hdr_len;
@@ -1180,21 +1191,23 @@ static unsigned int hns3_skb_bd_num(struct sk_buff *skb, unsigned int *bd_size,
 	return bd_num;
 }
 
-static unsigned int hns3_tx_bd_num(struct sk_buff *skb, unsigned int *bd_size)
+static unsigned int hns3_tx_bd_num(struct sk_buff *skb, unsigned int *bd_size,
+				   u8 max_non_tso_bd_num)
 {
 	struct sk_buff *frag_skb;
 	unsigned int bd_num = 0;
 
 	/* If the total len is within the max bd limit */
 	if (likely(skb->len <= HNS3_MAX_BD_SIZE && !skb_has_frag_list(skb) &&
-		   skb_shinfo(skb)->nr_frags < HNS3_MAX_NON_TSO_BD_NUM))
+		   skb_shinfo(skb)->nr_frags < max_non_tso_bd_num))
 		return skb_shinfo(skb)->nr_frags + 1U;
 
 	/* The below case will always be linearized, return
 	 * HNS3_MAX_BD_NUM_TSO + 1U to make sure it is linearized.
 	 */
 	if (unlikely(skb->len > HNS3_MAX_TSO_SIZE ||
-		     (!skb_is_gso(skb) && skb->len > HNS3_MAX_NON_TSO_SIZE)))
+		     (!skb_is_gso(skb) && skb->len >
+		      HNS3_MAX_NON_TSO_SIZE(max_non_tso_bd_num))))
 		return HNS3_MAX_TSO_BD_NUM + 1U;
 
 	bd_num = hns3_skb_bd_num(skb, bd_size, bd_num);
@@ -1219,31 +1232,34 @@ static unsigned int hns3_gso_hdr_len(struct sk_buff *skb)
 	return skb_inner_transport_offset(skb) + inner_tcp_hdrlen(skb);
 }
 
-/* HW need every continuous 8 buffer data to be larger than MSS,
- * we simplify it by ensuring skb_headlen + the first continuous
- * 7 frags to to be larger than gso header len + mss, and the remaining
- * continuous 7 frags to be larger than MSS except the last 7 frags.
+/* HW need every continuous max_non_tso_bd_num buffer data to be larger
+ * than MSS, we simplify it by ensuring skb_headlen + the first continuous
+ * max_non_tso_bd_num - 1 frags to be larger than gso header len + mss,
+ * and the remaining continuous max_non_tso_bd_num - 1 frags to be larger
+ * than MSS except the last max_non_tso_bd_num - 1 frags.
  */
 static bool hns3_skb_need_linearized(struct sk_buff *skb, unsigned int *bd_size,
-				     unsigned int bd_num)
+				     unsigned int bd_num, u8 max_non_tso_bd_num)
 {
 	unsigned int tot_len = 0;
 	int i;
 
-	for (i = 0; i < HNS3_MAX_NON_TSO_BD_NUM - 1U; i++)
+	for (i = 0; i < max_non_tso_bd_num - 1U; i++)
 		tot_len += bd_size[i];
 
-	/* ensure the first 8 frags is greater than mss + header */
-	if (tot_len + bd_size[HNS3_MAX_NON_TSO_BD_NUM - 1U] <
+	/* ensure the first max_non_tso_bd_num frags is greater than
+	 * mss + header
+	 */
+	if (tot_len + bd_size[max_non_tso_bd_num - 1U] <
 	    skb_shinfo(skb)->gso_size + hns3_gso_hdr_len(skb))
 		return true;
 
-	/* ensure every continuous 7 buffer is greater than mss
-	 * except the last one.
+	/* ensure every continuous max_non_tso_bd_num - 1 buffer is greater
+	 * than mss except the last one.
 	 */
-	for (i = 0; i < bd_num - HNS3_MAX_NON_TSO_BD_NUM; i++) {
+	for (i = 0; i < bd_num - max_non_tso_bd_num; i++) {
 		tot_len -= bd_size[i];
-		tot_len += bd_size[i + HNS3_MAX_NON_TSO_BD_NUM - 1U];
+		tot_len += bd_size[i + max_non_tso_bd_num - 1U];
 
 		if (tot_len < skb_shinfo(skb)->gso_size)
 			return true;
@@ -1254,7 +1270,7 @@ static bool hns3_skb_need_linearized(struct sk_buff *skb, unsigned int *bd_size,
 
 void hns3_shinfo_pack(struct skb_shared_info *shinfo, __u32 *size)
 {
-	int i = 0;
+	int i;
 
 	for (i = 0; i < MAX_SKB_FRAGS; i++)
 		size[i] = skb_frag_size(&shinfo->frags[i]);
@@ -1265,14 +1281,16 @@ static int hns3_nic_maybe_stop_tx(struct hns3_enet_ring *ring,
 				  struct sk_buff *skb)
 {
 	struct hns3_nic_priv *priv = netdev_priv(netdev);
+	u8 max_non_tso_bd_num = priv->max_non_tso_bd_num;
 	unsigned int bd_size[HNS3_MAX_TSO_BD_NUM + 1U];
 	unsigned int bd_num;
 
-	bd_num = hns3_tx_bd_num(skb, bd_size);
-	if (unlikely(bd_num > HNS3_MAX_NON_TSO_BD_NUM)) {
+	bd_num = hns3_tx_bd_num(skb, bd_size, max_non_tso_bd_num);
+	if (unlikely(bd_num > max_non_tso_bd_num)) {
 		if (bd_num <= HNS3_MAX_TSO_BD_NUM && skb_is_gso(skb) &&
-		    !hns3_skb_need_linearized(skb, bd_size, bd_num)) {
-			trace_hns3_over_8bd(skb);
+		    !hns3_skb_need_linearized(skb, bd_size, bd_num,
+					      max_non_tso_bd_num)) {
+			trace_hns3_over_max_bd(skb);
 			goto out;
 		}
 
@@ -1282,8 +1300,8 @@ static int hns3_nic_maybe_stop_tx(struct hns3_enet_ring *ring,
 		bd_num = hns3_tx_bd_count(skb->len);
 		if ((skb_is_gso(skb) && bd_num > HNS3_MAX_TSO_BD_NUM) ||
 		    (!skb_is_gso(skb) &&
-		     bd_num > HNS3_MAX_NON_TSO_BD_NUM)) {
-			trace_hns3_over_8bd(skb);
+		     bd_num > max_non_tso_bd_num)) {
+			trace_hns3_over_max_bd(skb);
 			return -ENOMEM;
 		}
 
@@ -2044,9 +2062,10 @@ bool hns3_is_phys_func(struct pci_dev *pdev)
 	case HNAE3_DEV_ID_50GE_RDMA:
 	case HNAE3_DEV_ID_50GE_RDMA_MACSEC:
 	case HNAE3_DEV_ID_100G_RDMA_MACSEC:
+	case HNAE3_DEV_ID_200G_RDMA:
 		return true;
-	case HNAE3_DEV_ID_100G_VF:
-	case HNAE3_DEV_ID_100G_RDMA_DCB_PFC_VF:
+	case HNAE3_DEV_ID_VF:
+	case HNAE3_DEV_ID_RDMA_DCB_PFC_VF:
 		return false;
 	default:
 		dev_warn(&pdev->dev, "un-recognized pci device-id %u",
@@ -2071,15 +2090,6 @@ static void hns3_disable_sriov(struct pci_dev *pdev)
 	pci_disable_sriov(pdev);
 }
 
-static void hns3_get_dev_capability(struct pci_dev *pdev,
-				    struct hnae3_ae_dev *ae_dev)
-{
-	if (pdev->revision >= 0x21) {
-		hnae3_set_bit(ae_dev->flag, HNAE3_DEV_SUPPORT_FD_B, 1);
-		hnae3_set_bit(ae_dev->flag, HNAE3_DEV_SUPPORT_GRO_B, 1);
-	}
-}
-
 /* hns3_probe - Device initialization routine
  * @pdev: PCI device information struct
  * @ent: entry in hns3_pci_tbl
@@ -2101,7 +2111,6 @@ static int hns3_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	ae_dev->pdev = pdev;
 	ae_dev->flag = ent->driver_data;
-	hns3_get_dev_capability(pdev, ae_dev);
 	pci_set_drvdata(pdev, ae_dev);
 
 	ret = hnae3_register_ae_dev(ae_dev);
@@ -2262,6 +2271,7 @@ static void hns3_set_default_feature(struct net_device *netdev)
 {
 	struct hnae3_handle *h = hns3_get_handle(netdev);
 	struct pci_dev *pdev = h->pdev;
+	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(pdev);
 
 	netdev->priv_flags |= IFF_UNICAST_FLT;
 
@@ -2299,7 +2309,7 @@ static void hns3_set_default_feature(struct net_device *netdev)
 		NETIF_F_GSO_UDP_TUNNEL_CSUM | NETIF_F_SCTP_CRC |
 		NETIF_F_FRAGLIST;
 
-	if (pdev->revision >= 0x21) {
+	if (ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V2) {
 		netdev->hw_features |= NETIF_F_GRO_HW;
 		netdev->features |= NETIF_F_GRO_HW;
 
@@ -2308,6 +2318,13 @@ static void hns3_set_default_feature(struct net_device *netdev)
 			netdev->features |= NETIF_F_NTUPLE;
 		}
 	}
+
+	if (test_bit(HNAE3_DEV_SUPPORT_UDP_GSO_B, ae_dev->caps)) {
+		netdev->hw_features |= NETIF_F_GSO_UDP_L4;
+		netdev->features |= NETIF_F_GSO_UDP_L4;
+		netdev->vlan_features |= NETIF_F_GSO_UDP_L4;
+		netdev->hw_enc_features |= NETIF_F_GSO_UDP_L4;
+	}
 }
 
 static int hns3_alloc_buffer(struct hns3_enet_ring *ring,
@@ -2798,8 +2815,9 @@ static bool hns3_parse_vlan_tag(struct hns3_enet_ring *ring,
 {
 	struct hnae3_handle *handle = ring->tqp->handle;
 	struct pci_dev *pdev = ring->tqp->handle->pdev;
+	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(pdev);
 
-	if (pdev->revision == 0x20) {
+	if (unlikely(ae_dev->dev_version < HNAE3_DEVICE_VERSION_V2)) {
 		*vlan_tag = le16_to_cpu(desc->rx.ot_vlan_tag);
 		if (!(*vlan_tag & VLAN_VID_MASK))
 			*vlan_tag = le16_to_cpu(desc->rx.vlan_tag);
@@ -3511,7 +3529,7 @@ static int hns3_nic_init_vector_data(struct hns3_nic_priv *priv)
 	struct hnae3_ring_chain_node vector_ring_chain;
 	struct hnae3_handle *h = priv->ae_handle;
 	struct hns3_enet_tqp_vector *tqp_vector;
-	int ret = 0;
+	int ret;
 	int i;
 
 	hns3_nic_set_cpumask(priv);
@@ -3994,6 +4012,7 @@ static void hns3_info_show(struct hns3_nic_priv *priv)
 static int hns3_client_init(struct hnae3_handle *handle)
 {
 	struct pci_dev *pdev = handle->pdev;
+	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(pdev);
 	u16 alloc_tqps, max_rss_size;
 	struct hns3_nic_priv *priv;
 	struct net_device *netdev;
@@ -4010,6 +4029,7 @@ static int hns3_client_init(struct hnae3_handle *handle)
 	priv->netdev = netdev;
 	priv->ae_handle = handle;
 	priv->tx_timeout_count = 0;
+	priv->max_non_tso_bd_num = ae_dev->dev_specs.max_non_tso_bd_num;
 	set_bit(HNS3_NIC_STATE_DOWN, &priv->state);
 
 	handle->msg_enable = netif_msg_init(debug, DEFAULT_MSG_LEVEL);
@@ -4600,6 +4620,8 @@ static const struct hns3_hw_error_info hns3_hw_err[] = {
 	  .msg = "IMP CMDQ error" },
 	{ .type = HNAE3_IMP_RD_POISON_ERROR,
 	  .msg = "IMP RD poison" },
+	{ .type = HNAE3_ROCEE_AXI_RESP_ERROR,
+	  .msg = "ROCEE AXI RESP error" },
 };
 
 static void hns3_process_hw_error(struct hnae3_handle *handle,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
index 8a6c8bae8fa6..1c81dea0da1e 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
@@ -43,6 +43,8 @@ enum hns3_nic_state {
 #define HNS3_RING_TX_RING_EBD_OFFSET_REG	0x00070
 #define HNS3_RING_TX_RING_BD_ERR_REG		0x00074
 #define HNS3_RING_EN_REG			0x00090
+#define HNS3_RING_RX_EN_REG			0x00098
+#define HNS3_RING_TX_EN_REG			0x000D4
 
 #define HNS3_RX_HEAD_SIZE			256
 
@@ -167,13 +169,12 @@ enum hns3_nic_state {
 #define HNS3_VECTOR_INITED			1
 
 #define HNS3_MAX_BD_SIZE			65535
-#define HNS3_MAX_NON_TSO_BD_NUM			8U
 #define HNS3_MAX_TSO_BD_NUM			63U
 #define HNS3_MAX_TSO_SIZE \
 	(HNS3_MAX_BD_SIZE * HNS3_MAX_TSO_BD_NUM)
 
-#define HNS3_MAX_NON_TSO_SIZE \
-	(HNS3_MAX_BD_SIZE * HNS3_MAX_NON_TSO_BD_NUM)
+#define HNS3_MAX_NON_TSO_SIZE(max_non_tso_bd_num) \
+	(HNS3_MAX_BD_SIZE * (max_non_tso_bd_num))
 
 #define HNS3_VECTOR_GL0_OFFSET			0x100
 #define HNS3_VECTOR_GL1_OFFSET			0x200
@@ -475,6 +476,7 @@ struct hns3_nic_priv {
 	struct hns3_enet_ring *ring;
 	struct hns3_enet_tqp_vector *tqp_vector;
 	u16 vector_num;
+	u8 max_non_tso_bd_num;
 
 	u64 tx_timeout_count;
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
index 52c780475d3a..6b07b2771172 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
@@ -77,6 +77,7 @@ static const struct hns3_stats hns3_rxq_stats[] = {
 static int hns3_lp_setup(struct net_device *ndev, enum hnae3_loop loop, bool en)
 {
 	struct hnae3_handle *h = hns3_get_handle(ndev);
+	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(h->pdev);
 	bool vlan_filter_enable;
 	int ret;
 
@@ -96,7 +97,7 @@ static int hns3_lp_setup(struct net_device *ndev, enum hnae3_loop loop, bool en)
 		break;
 	}
 
-	if (ret || h->pdev->revision >= 0x21)
+	if (ret || ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V2)
 		return ret;
 
 	if (en) {
@@ -147,6 +148,7 @@ static void hns3_lp_setup_skb(struct sk_buff *skb)
 
 	struct net_device *ndev = skb->dev;
 	struct hnae3_handle *handle;
+	struct hnae3_ae_dev *ae_dev;
 	unsigned char *packet;
 	struct ethhdr *ethh;
 	unsigned int i;
@@ -163,7 +165,8 @@ static void hns3_lp_setup_skb(struct sk_buff *skb)
 	 * the purpose of mac or serdes selftest.
 	 */
 	handle = hns3_get_handle(ndev);
-	if (handle->pdev->revision == 0x20)
+	ae_dev = pci_get_drvdata(handle->pdev);
+	if (ae_dev->dev_version < HNAE3_DEVICE_VERSION_V2)
 		ethh->h_dest[5] += HNS3_NIC_LB_DST_MAC_ADDR;
 	eth_zero_addr(ethh->h_source);
 	ethh->h_proto = htons(ETH_P_ARP);
@@ -308,9 +311,6 @@ static void hns3_self_test(struct net_device *ndev,
 	struct hnae3_handle *h = priv->ae_handle;
 	int st_param[HNS3_SELF_TEST_TYPE_NUM][2];
 	bool if_running = netif_running(ndev);
-#if IS_ENABLED(CONFIG_VLAN_8021Q)
-	bool dis_vlan_filter;
-#endif
 	int test_index = 0;
 	u32 i;
 
@@ -347,9 +347,7 @@ static void hns3_self_test(struct net_device *ndev,
 
 #if IS_ENABLED(CONFIG_VLAN_8021Q)
 	/* Disable the vlan filter for selftest does not support it */
-	dis_vlan_filter = (ndev->features & NETIF_F_HW_VLAN_CTAG_FILTER) &&
-				h->ae_algo->ops->enable_vlan_filter;
-	if (dis_vlan_filter)
+	if (h->ae_algo->ops->enable_vlan_filter)
 		h->ae_algo->ops->enable_vlan_filter(h, false);
 #endif
 
@@ -386,7 +384,7 @@ static void hns3_self_test(struct net_device *ndev,
 		h->ae_algo->ops->halt_autoneg(h, false);
 
 #if IS_ENABLED(CONFIG_VLAN_8021Q)
-	if (dis_vlan_filter)
+	if (h->ae_algo->ops->enable_vlan_filter)
 		h->ae_algo->ops->enable_vlan_filter(h, true);
 #endif
 
@@ -761,6 +759,7 @@ static int hns3_set_link_ksettings(struct net_device *netdev,
 				   const struct ethtool_link_ksettings *cmd)
 {
 	struct hnae3_handle *handle = hns3_get_handle(netdev);
+	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(handle->pdev);
 	const struct hnae3_ae_ops *ops = handle->ae_algo->ops;
 	int ret;
 
@@ -782,7 +781,7 @@ static int hns3_set_link_ksettings(struct net_device *netdev,
 		return phy_ethtool_ksettings_set(netdev->phydev, cmd);
 	}
 
-	if (handle->pdev->revision == 0x20)
+	if (ae_dev->dev_version < HNAE3_DEVICE_VERSION_V2)
 		return -EOPNOTSUPP;
 
 	ret = hns3_check_ksettings_param(netdev, cmd);
@@ -846,11 +845,12 @@ static int hns3_set_rss(struct net_device *netdev, const u32 *indir,
 			const u8 *key, const u8 hfunc)
 {
 	struct hnae3_handle *h = hns3_get_handle(netdev);
+	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(h->pdev);
 
 	if (!h->ae_algo->ops->set_rss)
 		return -EOPNOTSUPP;
 
-	if ((h->pdev->revision == 0x20 &&
+	if ((ae_dev->dev_version < HNAE3_DEVICE_VERSION_V2 &&
 	     hfunc != ETH_RSS_HASH_TOP) || (hfunc != ETH_RSS_HASH_NO_CHANGE &&
 	     hfunc != ETH_RSS_HASH_TOP && hfunc != ETH_RSS_HASH_XOR)) {
 		netdev_err(netdev, "hash func not supported\n");
@@ -1071,9 +1071,6 @@ static int hns3_nway_reset(struct net_device *netdev)
 	if (phy)
 		return genphy_restart_aneg(phy);
 
-	if (handle->pdev->revision == 0x20)
-		return -EOPNOTSUPP;
-
 	return ops->restart_autoneg(handle);
 }
 
@@ -1361,11 +1358,12 @@ static int hns3_get_fecparam(struct net_device *netdev,
 			     struct ethtool_fecparam *fec)
 {
 	struct hnae3_handle *handle = hns3_get_handle(netdev);
+	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(handle->pdev);
 	const struct hnae3_ae_ops *ops = handle->ae_algo->ops;
 	u8 fec_ability;
 	u8 fec_mode;
 
-	if (handle->pdev->revision == 0x20)
+	if (!test_bit(HNAE3_DEV_SUPPORT_FEC_B, ae_dev->caps))
 		return -EOPNOTSUPP;
 
 	if (!ops->get_fec)
@@ -1383,10 +1381,11 @@ static int hns3_set_fecparam(struct net_device *netdev,
 			     struct ethtool_fecparam *fec)
 {
 	struct hnae3_handle *handle = hns3_get_handle(netdev);
+	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(handle->pdev);
 	const struct hnae3_ae_ops *ops = handle->ae_algo->ops;
 	u32 fec_mode;
 
-	if (handle->pdev->revision == 0x20)
+	if (!test_bit(HNAE3_DEV_SUPPORT_FEC_B, ae_dev->caps))
 		return -EOPNOTSUPP;
 
 	if (!ops->set_fec)
@@ -1404,11 +1403,13 @@ static int hns3_get_module_info(struct net_device *netdev,
 #define HNS3_SFF_8636_V1_3 0x03
 
 	struct hnae3_handle *handle = hns3_get_handle(netdev);
+	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(handle->pdev);
 	const struct hnae3_ae_ops *ops = handle->ae_algo->ops;
 	struct hns3_sfp_type sfp_type;
 	int ret;
 
-	if (handle->pdev->revision == 0x20 || !ops->get_module_eeprom)
+	if (ae_dev->dev_version < HNAE3_DEVICE_VERSION_V2 ||
+	    !ops->get_module_eeprom)
 		return -EOPNOTSUPP;
 
 	memset(&sfp_type, 0, sizeof(sfp_type));
@@ -1452,9 +1453,11 @@ static int hns3_get_module_eeprom(struct net_device *netdev,
 				  struct ethtool_eeprom *ee, u8 *data)
 {
 	struct hnae3_handle *handle = hns3_get_handle(netdev);
+	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(handle->pdev);
 	const struct hnae3_ae_ops *ops = handle->ae_algo->ops;
 
-	if (handle->pdev->revision == 0x20 || !ops->get_module_eeprom)
+	if (ae_dev->dev_version < HNAE3_DEVICE_VERSION_V2 ||
+	    !ops->get_module_eeprom)
 		return -EOPNOTSUPP;
 
 	if (!ee->len)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_trace.h b/drivers/net/ethernet/hisilicon/hns3/hns3_trace.h
index 7bddcca148a5..5153e5d41bbd 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_trace.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_trace.h
@@ -53,7 +53,7 @@ DECLARE_EVENT_CLASS(hns3_skb_template,
 	)
 );
 
-DEFINE_EVENT(hns3_skb_template, hns3_over_8bd,
+DEFINE_EVENT(hns3_skb_template, hns3_over_max_bd,
 	TP_PROTO(struct sk_buff *skb),
 	TP_ARGS(skb));
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
index 1d6c328bd9fb..e6321dda0f3f 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
@@ -261,7 +261,7 @@ int hclge_cmd_send(struct hclge_hw *hw, struct hclge_desc *desc, int num)
 	bool complete = false;
 	u32 timeout = 0;
 	int handle = 0;
-	int retval = 0;
+	int retval;
 	int ntc;
 
 	spin_lock_bh(&hw->cmq.csq.lock);
@@ -330,9 +330,37 @@ int hclge_cmd_send(struct hclge_hw *hw, struct hclge_desc *desc, int num)
 	return retval;
 }
 
-static enum hclge_cmd_status hclge_cmd_query_firmware_version(
-		struct hclge_hw *hw, u32 *version)
+static void hclge_set_default_capability(struct hclge_dev *hdev)
 {
+	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev);
+
+	set_bit(HNAE3_DEV_SUPPORT_FD_B, ae_dev->caps);
+	set_bit(HNAE3_DEV_SUPPORT_GRO_B, ae_dev->caps);
+	set_bit(HNAE3_DEV_SUPPORT_FEC_B, ae_dev->caps);
+}
+
+static void hclge_parse_capability(struct hclge_dev *hdev,
+				   struct hclge_query_version_cmd *cmd)
+{
+	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev);
+	u32 caps;
+
+	caps = __le32_to_cpu(cmd->caps[0]);
+
+	if (hnae3_get_bit(caps, HCLGE_CAP_UDP_GSO_B))
+		set_bit(HNAE3_DEV_SUPPORT_UDP_GSO_B, ae_dev->caps);
+	if (hnae3_get_bit(caps, HCLGE_CAP_PTP_B))
+		set_bit(HNAE3_DEV_SUPPORT_PTP_B, ae_dev->caps);
+	if (hnae3_get_bit(caps, HCLGE_CAP_INT_QL_B))
+		set_bit(HNAE3_DEV_SUPPORT_INT_QL_B, ae_dev->caps);
+	if (hnae3_get_bit(caps, HCLGE_CAP_TQP_TXRX_INDEP_B))
+		set_bit(HNAE3_DEV_SUPPORT_TQP_TXRX_INDEP_B, ae_dev->caps);
+}
+
+static enum hclge_cmd_status
+hclge_cmd_query_version_and_capability(struct hclge_dev *hdev)
+{
+	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev);
 	struct hclge_query_version_cmd *resp;
 	struct hclge_desc desc;
 	int ret;
@@ -340,9 +368,20 @@ static enum hclge_cmd_status hclge_cmd_query_firmware_version(
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_QUERY_FW_VER, 1);
 	resp = (struct hclge_query_version_cmd *)desc.data;
 
-	ret = hclge_cmd_send(hw, &desc, 1);
-	if (!ret)
-		*version = le32_to_cpu(resp->firmware);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret)
+		return ret;
+
+	hdev->fw_version = le32_to_cpu(resp->firmware);
+
+	ae_dev->dev_version = le32_to_cpu(resp->hardware) <<
+					 HNAE3_PCI_REVISION_BIT_SIZE;
+	ae_dev->dev_version |= hdev->pdev->revision;
+
+	if (ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V2)
+		hclge_set_default_capability(hdev);
+
+	hclge_parse_capability(hdev, resp);
 
 	return ret;
 }
@@ -402,7 +441,6 @@ static int hclge_firmware_compat_config(struct hclge_dev *hdev)
 
 int hclge_cmd_init(struct hclge_dev *hdev)
 {
-	u32 version;
 	int ret;
 
 	spin_lock_bh(&hdev->hw.cmq.csq.lock);
@@ -431,22 +469,23 @@ int hclge_cmd_init(struct hclge_dev *hdev)
 		goto err_cmd_init;
 	}
 
-	ret = hclge_cmd_query_firmware_version(&hdev->hw, &version);
+	/* get version and device capabilities */
+	ret = hclge_cmd_query_version_and_capability(hdev);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
-			"firmware version query failed %d\n", ret);
+			"failed to query version and capabilities, ret = %d\n",
+			ret);
 		goto err_cmd_init;
 	}
-	hdev->fw_version = version;
 
 	dev_info(&hdev->pdev->dev, "The firmware version is %lu.%lu.%lu.%lu\n",
-		 hnae3_get_field(version, HNAE3_FW_VERSION_BYTE3_MASK,
+		 hnae3_get_field(hdev->fw_version, HNAE3_FW_VERSION_BYTE3_MASK,
 				 HNAE3_FW_VERSION_BYTE3_SHIFT),
-		 hnae3_get_field(version, HNAE3_FW_VERSION_BYTE2_MASK,
+		 hnae3_get_field(hdev->fw_version, HNAE3_FW_VERSION_BYTE2_MASK,
 				 HNAE3_FW_VERSION_BYTE2_SHIFT),
-		 hnae3_get_field(version, HNAE3_FW_VERSION_BYTE1_MASK,
+		 hnae3_get_field(hdev->fw_version, HNAE3_FW_VERSION_BYTE1_MASK,
 				 HNAE3_FW_VERSION_BYTE1_SHIFT),
-		 hnae3_get_field(version, HNAE3_FW_VERSION_BYTE0_MASK,
+		 hnae3_get_field(hdev->fw_version, HNAE3_FW_VERSION_BYTE0_MASK,
 				 HNAE3_FW_VERSION_BYTE0_SHIFT));
 
 	/* ask the firmware to enable some features, driver can work without
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
index 463f29151ef0..096e26a2e16b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
@@ -115,7 +115,8 @@ enum hclge_opcode_type {
 	HCLGE_OPC_DFX_RCB_REG		= 0x004D,
 	HCLGE_OPC_DFX_TQP_REG		= 0x004E,
 	HCLGE_OPC_DFX_SSU_REG_2		= 0x004F,
-	HCLGE_OPC_DFX_QUERY_CHIP_CAP	= 0x0050,
+
+	HCLGE_OPC_QUERY_DEV_SPECS	= 0x0050,
 
 	/* MAC command */
 	HCLGE_OPC_CONFIG_MAC_MODE	= 0x0301,
@@ -362,9 +363,26 @@ struct hclge_rx_priv_buff_cmd {
 	u8 rsv[6];
 };
 
+enum HCLGE_CAP_BITS {
+	HCLGE_CAP_UDP_GSO_B,
+	HCLGE_CAP_QB_B,
+	HCLGE_CAP_FD_FORWARD_TC_B,
+	HCLGE_CAP_PTP_B,
+	HCLGE_CAP_INT_QL_B,
+	HCLGE_CAP_SIMPLE_BD_B,
+	HCLGE_CAP_TX_PUSH_B,
+	HCLGE_CAP_PHY_IMP_B,
+	HCLGE_CAP_TQP_TXRX_INDEP_B,
+	HCLGE_CAP_HW_PAD_B,
+	HCLGE_CAP_STASH_B,
+};
+
+#define HCLGE_QUERY_CAP_LENGTH		3
 struct hclge_query_version_cmd {
 	__le32 firmware;
-	__le32 firmware_rsv[5];
+	__le32 hardware;
+	__le32 rsv;
+	__le32 caps[HCLGE_QUERY_CAP_LENGTH]; /* capabilities of device */
 };
 
 #define HCLGE_RX_PRIV_EN_B	15
@@ -491,6 +509,8 @@ struct hclge_pf_res_cmd {
 #define HCLGE_CFG_RSS_SIZE_M	GENMASK(31, 24)
 #define HCLGE_CFG_SPEED_ABILITY_S	0
 #define HCLGE_CFG_SPEED_ABILITY_M	GENMASK(7, 0)
+#define HCLGE_CFG_SPEED_ABILITY_EXT_S	10
+#define HCLGE_CFG_SPEED_ABILITY_EXT_M	GENMASK(15, 10)
 #define HCLGE_CFG_UMV_TBL_SPACE_S	16
 #define HCLGE_CFG_UMV_TBL_SPACE_M	GENMASK(31, 16)
 
@@ -1069,6 +1089,20 @@ struct hclge_sfp_info_bd0_cmd {
 	u8 data[HCLGE_SFP_INFO_BD0_LEN];
 };
 
+#define HCLGE_QUERY_DEV_SPECS_BD_NUM		4
+
+struct hclge_dev_specs_0_cmd {
+	__le32 rsv0;
+	__le32 mac_entry_num;
+	__le32 mng_entry_num;
+	__le16 rss_ind_tbl_size;
+	__le16 rss_key_size;
+	__le16 int_ql_max;
+	u8 max_non_tso_bd_num;
+	u8 rsv1;
+	__le32 max_tm_rate;
+};
+
 int hclge_cmd_init(struct hclge_dev *hdev);
 static inline void hclge_write_reg(void __iomem *base, u32 reg, u32 value)
 {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c
index f990f6915226..3606240025a8 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c
@@ -4,6 +4,7 @@
 #include "hclge_main.h"
 #include "hclge_dcb.h"
 #include "hclge_tm.h"
+#include "hclge_dcb.h"
 #include "hnae3.h"
 
 #define BW_PERCENT	100
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
index 26f6f068b01d..16df050e72cf 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
@@ -8,7 +8,7 @@
 #include "hclge_tm.h"
 #include "hnae3.h"
 
-static struct hclge_dbg_reg_type_info hclge_dbg_reg_info[] = {
+static const struct hclge_dbg_reg_type_info hclge_dbg_reg_info[] = {
 	{ .reg_type = "bios common",
 	  .dfx_msg = &hclge_dbg_bios_common_reg[0],
 	  .reg_msg = { .msg_num = ARRAY_SIZE(hclge_dbg_bios_common_reg),
@@ -115,14 +115,14 @@ static int hclge_dbg_cmd_send(struct hclge_dev *hdev,
 }
 
 static void hclge_dbg_dump_reg_common(struct hclge_dev *hdev,
-				      struct hclge_dbg_reg_type_info *reg_info,
+				      const struct hclge_dbg_reg_type_info *reg_info,
 				      const char *cmd_buf)
 {
 #define IDX_OFFSET	1
 
 	const char *s = &cmd_buf[strlen(reg_info->reg_type) + IDX_OFFSET];
-	struct hclge_dbg_dfx_message *dfx_message = reg_info->dfx_msg;
-	struct hclge_dbg_reg_common_msg *reg_msg = &reg_info->reg_msg;
+	const struct hclge_dbg_dfx_message *dfx_message = reg_info->dfx_msg;
+	const struct hclge_dbg_reg_common_msg *reg_msg = &reg_info->reg_msg;
 	struct hclge_desc *desc_src;
 	struct hclge_desc *desc;
 	int entries_per_desc;
@@ -399,7 +399,7 @@ err_dcb_cmd_send:
 
 static void hclge_dbg_dump_reg_cmd(struct hclge_dev *hdev, const char *cmd_buf)
 {
-	struct hclge_dbg_reg_type_info *reg_info;
+	const struct hclge_dbg_reg_type_info *reg_info;
 	bool has_dump = false;
 	int i;
 
@@ -428,17 +428,13 @@ static void hclge_dbg_dump_reg_cmd(struct hclge_dev *hdev, const char *cmd_buf)
 	}
 }
 
-static void hclge_title_idx_print(struct hclge_dev *hdev, bool flag, int index,
-				  char *title_buf, char *true_buf,
-				  char *false_buf)
+static void hclge_print_tc_info(struct hclge_dev *hdev, bool flag, int index)
 {
 	if (flag)
-		dev_info(&hdev->pdev->dev, "%s(%d): %s weight: %u\n",
-			 title_buf, index, true_buf,
-			 hdev->tm_info.pg_info[0].tc_dwrr[index]);
+		dev_info(&hdev->pdev->dev, "tc(%d): no sp mode weight: %u\n",
+			 index, hdev->tm_info.pg_info[0].tc_dwrr[index]);
 	else
-		dev_info(&hdev->pdev->dev, "%s(%d): %s\n", title_buf, index,
-			 false_buf);
+		dev_info(&hdev->pdev->dev, "tc(%d): sp mode\n", index);
 }
 
 static void hclge_dbg_dump_tc(struct hclge_dev *hdev)
@@ -469,8 +465,7 @@ static void hclge_dbg_dump_tc(struct hclge_dev *hdev)
 		 ets_weight->weight_offset);
 
 	for (i = 0; i < HNAE3_MAX_TC; i++)
-		hclge_title_idx_print(hdev, ets_weight->tc_weight[i], i,
-				      "tc", "no sp mode", "sp mode");
+		hclge_print_tc_info(hdev, ets_weight->tc_weight[i], i);
 }
 
 static void hclge_dbg_dump_tm_pg(struct hclge_dev *hdev)
@@ -1170,6 +1165,14 @@ static void hclge_dbg_dump_serv_info(struct hclge_dev *hdev)
 		 hdev->serv_processed_cnt);
 }
 
+static void hclge_dbg_dump_interrupt(struct hclge_dev *hdev)
+{
+	dev_info(&hdev->pdev->dev, "num_nic_msi: %u\n", hdev->num_nic_msi);
+	dev_info(&hdev->pdev->dev, "num_roce_msi: %u\n", hdev->num_roce_msi);
+	dev_info(&hdev->pdev->dev, "num_msi_used: %u\n", hdev->num_msi_used);
+	dev_info(&hdev->pdev->dev, "num_msi_left: %u\n", hdev->num_msi_left);
+}
+
 static void hclge_dbg_get_m7_stats_info(struct hclge_dev *hdev)
 {
 	struct hclge_desc *desc_src, *desc_tmp;
@@ -1494,6 +1497,7 @@ int hclge_dbg_run_cmd(struct hnae3_handle *handle, const char *cmd_buf)
 #define DUMP_REG	"dump reg"
 #define DUMP_TM_MAP	"dump tm map"
 #define DUMP_LOOPBACK	"dump loopback"
+#define DUMP_INTERRUPT	"dump intr"
 
 	struct hclge_vport *vport = hclge_get_vport(handle);
 	struct hclge_dev *hdev = vport->back;
@@ -1541,6 +1545,9 @@ int hclge_dbg_run_cmd(struct hnae3_handle *handle, const char *cmd_buf)
 		hclge_dbg_dump_mac_list(hdev,
 					&cmd_buf[sizeof("dump mc mac list")],
 					false);
+	} else if (strncmp(cmd_buf, DUMP_INTERRUPT,
+		   strlen(DUMP_INTERRUPT)) == 0) {
+		hclge_dbg_dump_interrupt(hdev);
 	} else {
 		dev_info(&hdev->pdev->dev, "unknown command\n");
 		return -EINVAL;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h
index 38b79321c4c4..a9066e6ff697 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h
@@ -81,13 +81,13 @@ struct hclge_dbg_dfx_message {
 #define HCLGE_DBG_MAC_REG_TYPE_LEN	32
 struct hclge_dbg_reg_type_info {
 	const char *reg_type;
-	struct hclge_dbg_dfx_message *dfx_msg;
+	const struct hclge_dbg_dfx_message *dfx_msg;
 	struct hclge_dbg_reg_common_msg reg_msg;
 };
 
 #pragma pack()
 
-static struct hclge_dbg_dfx_message hclge_dbg_bios_common_reg[] = {
+static const struct hclge_dbg_dfx_message hclge_dbg_bios_common_reg[] = {
 	{false, "Reserved"},
 	{true,	"BP_CPU_STATE"},
 	{true,	"DFX_MSIX_INFO_NIC_0"},
@@ -103,7 +103,7 @@ static struct hclge_dbg_dfx_message hclge_dbg_bios_common_reg[] = {
 	{false, "Reserved"},
 };
 
-static struct hclge_dbg_dfx_message hclge_dbg_ssu_reg_0[] = {
+static const struct hclge_dbg_dfx_message hclge_dbg_ssu_reg_0[] = {
 	{false, "Reserved"},
 	{true,	"SSU_ETS_PORT_STATUS"},
 	{true,	"SSU_ETS_TCG_STATUS"},
@@ -175,7 +175,7 @@ static struct hclge_dbg_dfx_message hclge_dbg_ssu_reg_0[] = {
 	{false, "Reserved"},
 };
 
-static struct hclge_dbg_dfx_message hclge_dbg_ssu_reg_1[] = {
+static const struct hclge_dbg_dfx_message hclge_dbg_ssu_reg_1[] = {
 	{true,	"prt_id"},
 	{true,	"PACKET_TC_CURR_BUFFER_CNT_0"},
 	{true,	"PACKET_TC_CURR_BUFFER_CNT_1"},
@@ -282,7 +282,7 @@ static struct hclge_dbg_dfx_message hclge_dbg_ssu_reg_1[] = {
 	{false, "Reserved"},
 };
 
-static struct hclge_dbg_dfx_message hclge_dbg_ssu_reg_2[] = {
+static const struct hclge_dbg_dfx_message hclge_dbg_ssu_reg_2[] = {
 	{true,	"OQ_INDEX"},
 	{true,	"QUEUE_CNT"},
 	{false, "Reserved"},
@@ -291,7 +291,7 @@ static struct hclge_dbg_dfx_message hclge_dbg_ssu_reg_2[] = {
 	{false, "Reserved"},
 };
 
-static struct hclge_dbg_dfx_message hclge_dbg_igu_egu_reg[] = {
+static const struct hclge_dbg_dfx_message hclge_dbg_igu_egu_reg[] = {
 	{true,	"prt_id"},
 	{true,	"IGU_RX_ERR_PKT"},
 	{true,	"IGU_RX_NO_SOF_PKT"},
@@ -356,7 +356,7 @@ static struct hclge_dbg_dfx_message hclge_dbg_igu_egu_reg[] = {
 	{false,	"Reserved"},
 };
 
-static struct hclge_dbg_dfx_message hclge_dbg_rpu_reg_0[] = {
+static const struct hclge_dbg_dfx_message hclge_dbg_rpu_reg_0[] = {
 	{true, "tc_queue_num"},
 	{true, "FSM_DFX_ST0"},
 	{true, "FSM_DFX_ST1"},
@@ -365,7 +365,7 @@ static struct hclge_dbg_dfx_message hclge_dbg_rpu_reg_0[] = {
 	{true, "BUF_WAIT_TIMEOUT_QID"},
 };
 
-static struct hclge_dbg_dfx_message hclge_dbg_rpu_reg_1[] = {
+static const struct hclge_dbg_dfx_message hclge_dbg_rpu_reg_1[] = {
 	{false, "Reserved"},
 	{true,	"FIFO_DFX_ST0"},
 	{true,	"FIFO_DFX_ST1"},
@@ -381,7 +381,7 @@ static struct hclge_dbg_dfx_message hclge_dbg_rpu_reg_1[] = {
 	{false, "Reserved"},
 };
 
-static struct hclge_dbg_dfx_message hclge_dbg_ncsi_reg[] = {
+static const struct hclge_dbg_dfx_message hclge_dbg_ncsi_reg[] = {
 	{false, "Reserved"},
 	{true,	"NCSI_EGU_TX_FIFO_STS"},
 	{true,	"NCSI_PAUSE_STATUS"},
@@ -453,7 +453,7 @@ static struct hclge_dbg_dfx_message hclge_dbg_ncsi_reg[] = {
 	{true,	"NCSI_MAC_RX_PAUSE_FRAMES"},
 };
 
-static struct hclge_dbg_dfx_message hclge_dbg_rtc_reg[] = {
+static const struct hclge_dbg_dfx_message hclge_dbg_rtc_reg[] = {
 	{false, "Reserved"},
 	{true,	"LGE_IGU_AFIFO_DFX_0"},
 	{true,	"LGE_IGU_AFIFO_DFX_1"},
@@ -483,7 +483,7 @@ static struct hclge_dbg_dfx_message hclge_dbg_rtc_reg[] = {
 	{false, "Reserved"},
 };
 
-static struct hclge_dbg_dfx_message hclge_dbg_ppp_reg[] = {
+static const struct hclge_dbg_dfx_message hclge_dbg_ppp_reg[] = {
 	{false, "Reserved"},
 	{true,	"DROP_FROM_PRT_PKT_CNT"},
 	{true,	"DROP_FROM_HOST_PKT_CNT"},
@@ -639,7 +639,7 @@ static struct hclge_dbg_dfx_message hclge_dbg_ppp_reg[] = {
 	{false, "Reserved"},
 };
 
-static struct hclge_dbg_dfx_message hclge_dbg_rcb_reg[] = {
+static const struct hclge_dbg_dfx_message hclge_dbg_rcb_reg[] = {
 	{false, "Reserved"},
 	{true,	"FSM_DFX_ST0"},
 	{true,	"FSM_DFX_ST1"},
@@ -711,7 +711,7 @@ static struct hclge_dbg_dfx_message hclge_dbg_rcb_reg[] = {
 	{false, "Reserved"},
 };
 
-static struct hclge_dbg_dfx_message hclge_dbg_tqp_reg[] = {
+static const struct hclge_dbg_dfx_message hclge_dbg_tqp_reg[] = {
 	{true, "q_num"},
 	{true, "RCB_CFG_RX_RING_TAIL"},
 	{true, "RCB_CFG_RX_RING_HEAD"},
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
index 50d5ef71756b..9ee55ee0487d 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
@@ -729,7 +729,7 @@ static int hclge_config_ncsi_hw_err_int(struct hclge_dev *hdev, bool en)
 	struct hclge_desc desc;
 	int ret;
 
-	if (hdev->pdev->revision < 0x21)
+	if (hdev->ae_dev->dev_version < HNAE3_DEVICE_VERSION_V2)
 		return 0;
 
 	/* configure NCSI error interrupts */
@@ -808,7 +808,7 @@ static int hclge_config_ppp_error_interrupt(struct hclge_dev *hdev, u32 cmd,
 			cpu_to_le32(HCLGE_PPP_MPF_ECC_ERR_INT0_EN_MASK);
 		desc[1].data[1] =
 			cpu_to_le32(HCLGE_PPP_MPF_ECC_ERR_INT1_EN_MASK);
-		if (hdev->pdev->revision >= 0x21)
+		if (hdev->ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V2)
 			desc[1].data[2] =
 				cpu_to_le32(HCLGE_PPP_PF_ERR_INT_EN_MASK);
 	} else if (cmd == HCLGE_PPP_CMD1_INT_CMD) {
@@ -1041,7 +1041,7 @@ static int hclge_config_ssu_hw_err_int(struct hclge_dev *hdev, bool en)
 	hclge_cmd_setup_basic_desc(&desc[1], HCLGE_SSU_COMMON_INT_CMD, false);
 
 	if (en) {
-		if (hdev->pdev->revision >= 0x21)
+		if (hdev->ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V2)
 			desc[0].data[0] =
 				cpu_to_le32(HCLGE_SSU_COMMON_INT_EN);
 		else
@@ -1507,6 +1507,8 @@ hclge_log_and_clear_rocee_ras_error(struct hclge_dev *hdev)
 
 		reset_type = HNAE3_FUNC_RESET;
 
+		hclge_report_hw_error(hdev, HNAE3_ROCEE_AXI_RESP_ERROR);
+
 		ret = hclge_log_rocee_axi_error(hdev);
 		if (ret)
 			return HNAE3_GLOBAL_RESET;
@@ -1548,7 +1550,8 @@ int hclge_config_rocee_ras_interrupt(struct hclge_dev *hdev, bool en)
 	struct hclge_desc desc;
 	int ret;
 
-	if (hdev->pdev->revision < 0x21 || !hnae3_dev_roce_supported(hdev))
+	if (hdev->ae_dev->dev_version < HNAE3_DEVICE_VERSION_V2 ||
+	    !hnae3_dev_roce_supported(hdev))
 		return 0;
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_CONFIG_ROCEE_RAS_INT_EN, false);
@@ -1574,8 +1577,7 @@ static void hclge_handle_rocee_ras_error(struct hnae3_ae_dev *ae_dev)
 	struct hclge_dev *hdev = ae_dev->priv;
 	enum hnae3_reset_type reset_type;
 
-	if (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state) ||
-	    hdev->pdev->revision < 0x21)
+	if (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state))
 		return;
 
 	reset_type = hclge_log_and_clear_rocee_ras_error(hdev);
@@ -1661,7 +1663,7 @@ pci_ers_result_t hclge_handle_hw_ras_error(struct hnae3_ae_dev *ae_dev)
 	}
 
 	/* Handling Non-fatal Rocee RAS errors */
-	if (hdev->pdev->revision >= 0x21 &&
+	if (hdev->ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V2 &&
 	    status & HCLGE_RAS_REG_ROCEE_ERR_MASK) {
 		dev_err(dev, "ROCEE Non-Fatal RAS error identified\n");
 		hclge_handle_rocee_ras_error(ae_dev);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 40d68a4ff83d..1f026408ad38 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -84,6 +84,7 @@ static const struct pci_device_id ae_algo_pci_tbl[] = {
 	{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_50GE_RDMA), 0},
 	{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_50GE_RDMA_MACSEC), 0},
 	{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_100G_RDMA_MACSEC), 0},
+	{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_200G_RDMA), 0},
 	/* required last entry */
 	{0, }
 };
@@ -622,7 +623,7 @@ static u8 *hclge_tqps_get_strings(struct hnae3_handle *handle, u8 *data)
 {
 	struct hnae3_knic_private_info *kinfo = &handle->kinfo;
 	u8 *buff = data;
-	int i = 0;
+	int i;
 
 	for (i = 0; i < kinfo->num_tqps; i++) {
 		struct hclge_tqp *tqp = container_of(handle->kinfo.tqp[i],
@@ -739,7 +740,7 @@ static int hclge_get_sset_count(struct hnae3_handle *handle, int stringset)
 	if (stringset == ETH_SS_TEST) {
 		/* clear loopback bit flags at first */
 		handle->flags = (handle->flags & (~HCLGE_LOOPBACK_TEST_FLAGS));
-		if (hdev->pdev->revision >= 0x21 ||
+		if (hdev->ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V2 ||
 		    hdev->hw.mac.speed == HCLGE_MAC_SPEED_10M ||
 		    hdev->hw.mac.speed == HCLGE_MAC_SPEED_100M ||
 		    hdev->hw.mac.speed == HCLGE_MAC_SPEED_1G) {
@@ -965,6 +966,9 @@ static int hclge_parse_speed(int speed_cmd, int *speed)
 	case 5:
 		*speed = HCLGE_MAC_SPEED_100G;
 		break;
+	case 8:
+		*speed = HCLGE_MAC_SPEED_200G;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -1004,6 +1008,9 @@ static int hclge_check_port_speed(struct hnae3_handle *handle, u32 speed)
 	case HCLGE_MAC_SPEED_100G:
 		speed_bit = HCLGE_SUPPORT_100G_BIT;
 		break;
+	case HCLGE_MAC_SPEED_200G:
+		speed_bit = HCLGE_SUPPORT_200G_BIT;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -1014,7 +1021,7 @@ static int hclge_check_port_speed(struct hnae3_handle *handle, u32 speed)
 	return -EINVAL;
 }
 
-static void hclge_convert_setting_sr(struct hclge_mac *mac, u8 speed_ability)
+static void hclge_convert_setting_sr(struct hclge_mac *mac, u16 speed_ability)
 {
 	if (speed_ability & HCLGE_SUPPORT_10G_BIT)
 		linkmode_set_bit(ETHTOOL_LINK_MODE_10000baseSR_Full_BIT,
@@ -1031,9 +1038,12 @@ static void hclge_convert_setting_sr(struct hclge_mac *mac, u8 speed_ability)
 	if (speed_ability & HCLGE_SUPPORT_100G_BIT)
 		linkmode_set_bit(ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT,
 				 mac->supported);
+	if (speed_ability & HCLGE_SUPPORT_200G_BIT)
+		linkmode_set_bit(ETHTOOL_LINK_MODE_200000baseSR4_Full_BIT,
+				 mac->supported);
 }
 
-static void hclge_convert_setting_lr(struct hclge_mac *mac, u8 speed_ability)
+static void hclge_convert_setting_lr(struct hclge_mac *mac, u16 speed_ability)
 {
 	if (speed_ability & HCLGE_SUPPORT_10G_BIT)
 		linkmode_set_bit(ETHTOOL_LINK_MODE_10000baseLR_Full_BIT,
@@ -1050,9 +1060,13 @@ static void hclge_convert_setting_lr(struct hclge_mac *mac, u8 speed_ability)
 	if (speed_ability & HCLGE_SUPPORT_100G_BIT)
 		linkmode_set_bit(ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT,
 				 mac->supported);
+	if (speed_ability & HCLGE_SUPPORT_200G_BIT)
+		linkmode_set_bit(
+			ETHTOOL_LINK_MODE_200000baseLR4_ER4_FR4_Full_BIT,
+			mac->supported);
 }
 
-static void hclge_convert_setting_cr(struct hclge_mac *mac, u8 speed_ability)
+static void hclge_convert_setting_cr(struct hclge_mac *mac, u16 speed_ability)
 {
 	if (speed_ability & HCLGE_SUPPORT_10G_BIT)
 		linkmode_set_bit(ETHTOOL_LINK_MODE_10000baseCR_Full_BIT,
@@ -1069,9 +1083,12 @@ static void hclge_convert_setting_cr(struct hclge_mac *mac, u8 speed_ability)
 	if (speed_ability & HCLGE_SUPPORT_100G_BIT)
 		linkmode_set_bit(ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT,
 				 mac->supported);
+	if (speed_ability & HCLGE_SUPPORT_200G_BIT)
+		linkmode_set_bit(ETHTOOL_LINK_MODE_200000baseCR4_Full_BIT,
+				 mac->supported);
 }
 
-static void hclge_convert_setting_kr(struct hclge_mac *mac, u8 speed_ability)
+static void hclge_convert_setting_kr(struct hclge_mac *mac, u16 speed_ability)
 {
 	if (speed_ability & HCLGE_SUPPORT_1G_BIT)
 		linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseKX_Full_BIT,
@@ -1091,6 +1108,9 @@ static void hclge_convert_setting_kr(struct hclge_mac *mac, u8 speed_ability)
 	if (speed_ability & HCLGE_SUPPORT_100G_BIT)
 		linkmode_set_bit(ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT,
 				 mac->supported);
+	if (speed_ability & HCLGE_SUPPORT_200G_BIT)
+		linkmode_set_bit(ETHTOOL_LINK_MODE_200000baseKR4_Full_BIT,
+				 mac->supported);
 }
 
 static void hclge_convert_setting_fec(struct hclge_mac *mac)
@@ -1115,6 +1135,7 @@ static void hclge_convert_setting_fec(struct hclge_mac *mac)
 			BIT(HNAE3_FEC_AUTO);
 		break;
 	case HCLGE_MAC_SPEED_100G:
+	case HCLGE_MAC_SPEED_200G:
 		linkmode_set_bit(ETHTOOL_LINK_MODE_FEC_RS_BIT, mac->supported);
 		mac->fec_ability = BIT(HNAE3_FEC_RS) | BIT(HNAE3_FEC_AUTO);
 		break;
@@ -1125,7 +1146,7 @@ static void hclge_convert_setting_fec(struct hclge_mac *mac)
 }
 
 static void hclge_parse_fiber_link_mode(struct hclge_dev *hdev,
-					u8 speed_ability)
+					u16 speed_ability)
 {
 	struct hclge_mac *mac = &hdev->hw.mac;
 
@@ -1136,7 +1157,7 @@ static void hclge_parse_fiber_link_mode(struct hclge_dev *hdev,
 	hclge_convert_setting_sr(mac, speed_ability);
 	hclge_convert_setting_lr(mac, speed_ability);
 	hclge_convert_setting_cr(mac, speed_ability);
-	if (hdev->pdev->revision >= 0x21)
+	if (hnae3_dev_fec_supported(hdev))
 		hclge_convert_setting_fec(mac);
 
 	linkmode_set_bit(ETHTOOL_LINK_MODE_FIBRE_BIT, mac->supported);
@@ -1145,12 +1166,12 @@ static void hclge_parse_fiber_link_mode(struct hclge_dev *hdev,
 }
 
 static void hclge_parse_backplane_link_mode(struct hclge_dev *hdev,
-					    u8 speed_ability)
+					    u16 speed_ability)
 {
 	struct hclge_mac *mac = &hdev->hw.mac;
 
 	hclge_convert_setting_kr(mac, speed_ability);
-	if (hdev->pdev->revision >= 0x21)
+	if (hnae3_dev_fec_supported(hdev))
 		hclge_convert_setting_fec(mac);
 	linkmode_set_bit(ETHTOOL_LINK_MODE_Backplane_BIT, mac->supported);
 	linkmode_set_bit(ETHTOOL_LINK_MODE_Pause_BIT, mac->supported);
@@ -1158,7 +1179,7 @@ static void hclge_parse_backplane_link_mode(struct hclge_dev *hdev,
 }
 
 static void hclge_parse_copper_link_mode(struct hclge_dev *hdev,
-					 u8 speed_ability)
+					 u16 speed_ability)
 {
 	unsigned long *supported = hdev->hw.mac.supported;
 
@@ -1188,7 +1209,7 @@ static void hclge_parse_copper_link_mode(struct hclge_dev *hdev,
 	linkmode_set_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, supported);
 }
 
-static void hclge_parse_link_mode(struct hclge_dev *hdev, u8 speed_ability)
+static void hclge_parse_link_mode(struct hclge_dev *hdev, u16 speed_ability)
 {
 	u8 media_type = hdev->hw.mac.media_type;
 
@@ -1200,8 +1221,11 @@ static void hclge_parse_link_mode(struct hclge_dev *hdev, u8 speed_ability)
 		hclge_parse_backplane_link_mode(hdev, speed_ability);
 }
 
-static u32 hclge_get_max_speed(u8 speed_ability)
+static u32 hclge_get_max_speed(u16 speed_ability)
 {
+	if (speed_ability & HCLGE_SUPPORT_200G_BIT)
+		return HCLGE_MAC_SPEED_200G;
+
 	if (speed_ability & HCLGE_SUPPORT_100G_BIT)
 		return HCLGE_MAC_SPEED_100G;
 
@@ -1231,8 +1255,11 @@ static u32 hclge_get_max_speed(u8 speed_ability)
 
 static void hclge_parse_cfg(struct hclge_cfg *cfg, struct hclge_desc *desc)
 {
+#define SPEED_ABILITY_EXT_SHIFT			8
+
 	struct hclge_cfg_param_cmd *req;
 	u64 mac_addr_tmp_high;
+	u16 speed_ability_ext;
 	u64 mac_addr_tmp;
 	unsigned int i;
 
@@ -1281,6 +1308,11 @@ static void hclge_parse_cfg(struct hclge_cfg *cfg, struct hclge_desc *desc)
 	cfg->speed_ability = hnae3_get_field(__le32_to_cpu(req->param[1]),
 					     HCLGE_CFG_SPEED_ABILITY_M,
 					     HCLGE_CFG_SPEED_ABILITY_S);
+	speed_ability_ext = hnae3_get_field(__le32_to_cpu(req->param[1]),
+					    HCLGE_CFG_SPEED_ABILITY_EXT_M,
+					    HCLGE_CFG_SPEED_ABILITY_EXT_S);
+	cfg->speed_ability |= speed_ability_ext << SPEED_ABILITY_EXT_SHIFT;
+
 	cfg->umv_space = hnae3_get_field(__le32_to_cpu(req->param[1]),
 					 HCLGE_CFG_UMV_TBL_SPACE_M,
 					 HCLGE_CFG_UMV_TBL_SPACE_S);
@@ -1324,6 +1356,78 @@ static int hclge_get_cfg(struct hclge_dev *hdev, struct hclge_cfg *hcfg)
 	return 0;
 }
 
+static void hclge_set_default_dev_specs(struct hclge_dev *hdev)
+{
+#define HCLGE_MAX_NON_TSO_BD_NUM			8U
+
+	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev);
+
+	ae_dev->dev_specs.max_non_tso_bd_num = HCLGE_MAX_NON_TSO_BD_NUM;
+	ae_dev->dev_specs.rss_ind_tbl_size = HCLGE_RSS_IND_TBL_SIZE;
+	ae_dev->dev_specs.rss_key_size = HCLGE_RSS_KEY_SIZE;
+	ae_dev->dev_specs.max_tm_rate = HCLGE_ETHER_MAX_RATE;
+}
+
+static void hclge_parse_dev_specs(struct hclge_dev *hdev,
+				  struct hclge_desc *desc)
+{
+	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev);
+	struct hclge_dev_specs_0_cmd *req0;
+
+	req0 = (struct hclge_dev_specs_0_cmd *)desc[0].data;
+
+	ae_dev->dev_specs.max_non_tso_bd_num = req0->max_non_tso_bd_num;
+	ae_dev->dev_specs.rss_ind_tbl_size =
+		le16_to_cpu(req0->rss_ind_tbl_size);
+	ae_dev->dev_specs.rss_key_size = le16_to_cpu(req0->rss_key_size);
+	ae_dev->dev_specs.max_tm_rate = le32_to_cpu(req0->max_tm_rate);
+}
+
+static void hclge_check_dev_specs(struct hclge_dev *hdev)
+{
+	struct hnae3_dev_specs *dev_specs = &hdev->ae_dev->dev_specs;
+
+	if (!dev_specs->max_non_tso_bd_num)
+		dev_specs->max_non_tso_bd_num = HCLGE_MAX_NON_TSO_BD_NUM;
+	if (!dev_specs->rss_ind_tbl_size)
+		dev_specs->rss_ind_tbl_size = HCLGE_RSS_IND_TBL_SIZE;
+	if (!dev_specs->rss_key_size)
+		dev_specs->rss_key_size = HCLGE_RSS_KEY_SIZE;
+	if (!dev_specs->max_tm_rate)
+		dev_specs->max_tm_rate = HCLGE_ETHER_MAX_RATE;
+}
+
+static int hclge_query_dev_specs(struct hclge_dev *hdev)
+{
+	struct hclge_desc desc[HCLGE_QUERY_DEV_SPECS_BD_NUM];
+	int ret;
+	int i;
+
+	/* set default specifications as devices lower than version V3 do not
+	 * support querying specifications from firmware.
+	 */
+	if (hdev->ae_dev->dev_version < HNAE3_DEVICE_VERSION_V3) {
+		hclge_set_default_dev_specs(hdev);
+		return 0;
+	}
+
+	for (i = 0; i < HCLGE_QUERY_DEV_SPECS_BD_NUM - 1; i++) {
+		hclge_cmd_setup_basic_desc(&desc[i], HCLGE_OPC_QUERY_DEV_SPECS,
+					   true);
+		desc[i].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
+	}
+	hclge_cmd_setup_basic_desc(&desc[i], HCLGE_OPC_QUERY_DEV_SPECS, true);
+
+	ret = hclge_cmd_send(&hdev->hw, desc, HCLGE_QUERY_DEV_SPECS_BD_NUM);
+	if (ret)
+		return ret;
+
+	hclge_parse_dev_specs(hdev, desc);
+	hclge_check_dev_specs(hdev);
+
+	return 0;
+}
+
 static int hclge_get_cap(struct hclge_dev *hdev)
 {
 	int ret;
@@ -2422,6 +2526,10 @@ static int hclge_cfg_mac_speed_dup_hw(struct hclge_dev *hdev, int speed,
 		hnae3_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
 				HCLGE_CFG_SPEED_S, 5);
 		break;
+	case HCLGE_MAC_SPEED_200G:
+		hnae3_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
+				HCLGE_CFG_SPEED_S, 8);
+		break;
 	default:
 		dev_err(&hdev->pdev->dev, "invalid speed (%d)\n", speed);
 		return -EINVAL;
@@ -2856,7 +2964,7 @@ static int hclge_update_port_info(struct hclge_dev *hdev)
 	if (!hdev->support_sfp_query)
 		return 0;
 
-	if (hdev->pdev->revision >= 0x21)
+	if (hdev->ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V2)
 		ret = hclge_get_sfp_info(hdev, mac);
 	else
 		ret = hclge_get_sfp_speed(hdev, &speed);
@@ -2868,7 +2976,7 @@ static int hclge_update_port_info(struct hclge_dev *hdev)
 		return ret;
 	}
 
-	if (hdev->pdev->revision >= 0x21) {
+	if (hdev->ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V2) {
 		if (mac->speed_type == QUERY_ACTIVE_SPEED) {
 			hclge_update_port_capability(mac);
 			return 0;
@@ -3211,7 +3319,7 @@ static int hclge_notify_roce_client(struct hclge_dev *hdev,
 				    enum hnae3_reset_notify_type type)
 {
 	struct hnae3_client *client = hdev->roce_client;
-	int ret = 0;
+	int ret;
 	u16 i;
 
 	if (!test_bit(HCLGE_STATE_ROCE_REGISTERED, &hdev->state) || !client)
@@ -3533,7 +3641,7 @@ static void hclge_clear_reset_cause(struct hclge_dev *hdev)
 	/* For revision 0x20, the reset interrupt source
 	 * can only be cleared after hardware reset done
 	 */
-	if (hdev->pdev->revision == 0x20)
+	if (hdev->ae_dev->dev_version < HNAE3_DEVICE_VERSION_V2)
 		hclge_write_dev(&hdev->hw, HCLGE_MISC_RESET_STS_REG,
 				clearval);
 
@@ -4540,7 +4648,7 @@ static void hclge_rss_init_cfg(struct hclge_dev *hdev)
 	int i, rss_algo = HCLGE_RSS_HASH_ALGO_TOEPLITZ;
 	struct hclge_vport *vport = hdev->vport;
 
-	if (hdev->pdev->revision >= 0x21)
+	if (hdev->ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V2)
 		rss_algo = HCLGE_RSS_HASH_ALGO_SIMPLE;
 
 	for (i = 0; i < hdev->num_vmdq_vport + 1; i++) {
@@ -4740,13 +4848,14 @@ static int hclge_set_promisc_mode(struct hnae3_handle *handle, bool en_uc_pmc,
 				  bool en_mc_pmc)
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
+	struct hclge_dev *hdev = vport->back;
 	bool en_bc_pmc = true;
 
-	/* For revision 0x20, if broadcast promisc enabled, vlan filter is
-	 * always bypassed. So broadcast promisc should be disabled until
-	 * user enable promisc mode
+	/* For device whose version below V2, if broadcast promisc enabled,
+	 * vlan filter is always bypassed. So broadcast promisc should be
+	 * disabled until user enable promisc mode
 	 */
-	if (handle->pdev->revision == 0x20)
+	if (hdev->ae_dev->dev_version < HNAE3_DEVICE_VERSION_V2)
 		en_bc_pmc = handle->netdev_flags & HNAE3_BPE ? true : false;
 
 	return hclge_set_vport_promisc_mode(vport, en_uc_pmc, en_mc_pmc,
@@ -6761,7 +6870,7 @@ static int hclge_set_loopback(struct hnae3_handle *handle,
 	 * the same, the packets are looped back in the SSU. If SSU loopback
 	 * is disabled, packets can reach MAC even if SMAC is the same as DMAC.
 	 */
-	if (hdev->pdev->revision >= 0x21) {
+	if (hdev->ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V2) {
 		u8 switch_param = en ? 0 : BIT(HCLGE_SWITCH_ALW_LPBK_B);
 
 		ret = hclge_config_switch_param(hdev, PF_VPORT_ID, switch_param,
@@ -8263,7 +8372,7 @@ static void hclge_enable_vlan_filter(struct hnae3_handle *handle, bool enable)
 	struct hclge_vport *vport = hclge_get_vport(handle);
 	struct hclge_dev *hdev = vport->back;
 
-	if (hdev->pdev->revision >= 0x21) {
+	if (hdev->ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V2) {
 		hclge_set_vlan_filter_ctrl(hdev, HCLGE_FILTER_TYPE_VF,
 					   HCLGE_FILTER_FE_EGRESS, enable, 0);
 		hclge_set_vlan_filter_ctrl(hdev, HCLGE_FILTER_TYPE_PORT,
@@ -8623,7 +8732,7 @@ static int hclge_init_vlan_config(struct hclge_dev *hdev)
 	int ret;
 	int i;
 
-	if (hdev->pdev->revision >= 0x21) {
+	if (hdev->ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V2) {
 		/* for revision 0x21, vf vlan filter is per function */
 		for (i = 0; i < hdev->num_alloc_vport; i++) {
 			vport = &hdev->vport[i];
@@ -8978,7 +9087,7 @@ static int hclge_set_vf_vlan_filter(struct hnae3_handle *handle, int vfid,
 	u16 state;
 	int ret;
 
-	if (hdev->pdev->revision == 0x20)
+	if (hdev->ae_dev->dev_version < HNAE3_DEVICE_VERSION_V2)
 		return -EOPNOTSUPP;
 
 	vport = hclge_get_vf_vport(hdev, vfid);
@@ -9953,6 +10062,13 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
 	if (ret)
 		goto err_cmd_uninit;
 
+	ret = hclge_query_dev_specs(hdev);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to query dev specifications, ret = %d.\n",
+			ret);
+		goto err_cmd_uninit;
+	}
+
 	ret = hclge_configure(hdev);
 	if (ret) {
 		dev_err(&pdev->dev, "Configure dev error, ret = %d.\n", ret);
@@ -10150,7 +10266,7 @@ static int hclge_set_vf_spoofchk(struct hnae3_handle *handle, int vf,
 	u32 new_spoofchk = enable ? 1 : 0;
 	int ret;
 
-	if (hdev->pdev->revision == 0x20)
+	if (hdev->ae_dev->dev_version < HNAE3_DEVICE_VERSION_V2)
 		return -EOPNOTSUPP;
 
 	vport = hclge_get_vf_vport(hdev, vf);
@@ -10183,7 +10299,7 @@ static int hclge_reset_vport_spoofchk(struct hclge_dev *hdev)
 	int ret;
 	int i;
 
-	if (hdev->pdev->revision == 0x20)
+	if (hdev->ae_dev->dev_version < HNAE3_DEVICE_VERSION_V2)
 		return 0;
 
 	/* resume the vf spoof check state after reset */
@@ -10203,6 +10319,7 @@ static int hclge_set_vf_trust(struct hnae3_handle *handle, int vf, bool enable)
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
 	struct hclge_dev *hdev = vport->back;
+	struct hnae3_ae_dev *ae_dev = hdev->ae_dev;
 	u32 new_trusted = enable ? 1 : 0;
 	bool en_bc_pmc;
 	int ret;
@@ -10216,7 +10333,7 @@ static int hclge_set_vf_trust(struct hnae3_handle *handle, int vf, bool enable)
 
 	/* Disable promisc mode for VF if it is not trusted any more. */
 	if (!enable && vport->vf_info.promisc_enable) {
-		en_bc_pmc = hdev->pdev->revision != 0x20;
+		en_bc_pmc = ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V2;
 		ret = hclge_set_vport_promisc_mode(vport, false, false,
 						   en_bc_pmc);
 		if (ret)
@@ -11093,7 +11210,7 @@ static void hclge_sync_promisc_mode(struct hclge_dev *hdev)
 {
 	struct hclge_vport *vport = &hdev->vport[0];
 	struct hnae3_handle *handle = &vport->nic;
-	u8 tmp_flags = 0;
+	u8 tmp_flags;
 	int ret;
 
 	if (vport->last_promisc_flags != vport->overflow_promisc_flags) {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index 3975332a1a10..64e6afdb61b8 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -199,6 +199,7 @@ enum HLCGE_PORT_TYPE {
 #define HCLGE_SUPPORT_40G_BIT		BIT(5)
 #define HCLGE_SUPPORT_100M_BIT		BIT(6)
 #define HCLGE_SUPPORT_10M_BIT		BIT(7)
+#define HCLGE_SUPPORT_200G_BIT		BIT(8)
 #define HCLGE_SUPPORT_GE \
 	(HCLGE_SUPPORT_1G_BIT | HCLGE_SUPPORT_100M_BIT | HCLGE_SUPPORT_10M_BIT)
 
@@ -238,7 +239,8 @@ enum HCLGE_MAC_SPEED {
 	HCLGE_MAC_SPEED_25G	= 25000,	/* 25000 Mbps  = 25 Gbps */
 	HCLGE_MAC_SPEED_40G	= 40000,	/* 40000 Mbps  = 40 Gbps */
 	HCLGE_MAC_SPEED_50G	= 50000,	/* 50000 Mbps  = 50 Gbps */
-	HCLGE_MAC_SPEED_100G	= 100000	/* 100000 Mbps = 100 Gbps */
+	HCLGE_MAC_SPEED_100G	= 100000,	/* 100000 Mbps = 100 Gbps */
+	HCLGE_MAC_SPEED_200G	= 200000	/* 200000 Mbps = 200 Gbps */
 };
 
 enum HCLGE_MAC_DUPLEX {
@@ -349,7 +351,7 @@ struct hclge_cfg {
 	u8 mac_addr[ETH_ALEN];
 	u8 default_speed;
 	u32 numa_node_map;
-	u8 speed_ability;
+	u16 speed_ability;
 	u16 umv_space;
 };
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
index 28db13253a5e..15f69fa86323 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
@@ -23,14 +23,11 @@ enum hclge_shaper_level {
 #define HCLGE_SHAPER_BS_U_DEF	5
 #define HCLGE_SHAPER_BS_S_DEF	20
 
-#define HCLGE_ETHER_MAX_RATE	100000
-
 /* hclge_shaper_para_calc: calculate ir parameter for the shaper
  * @ir: Rate to be config, its unit is Mbps
  * @shaper_level: the shaper level. eg: port, pg, priority, queueset
- * @ir_b: IR_B parameter of IR shaper
- * @ir_u: IR_U parameter of IR shaper
- * @ir_s: IR_S parameter of IR shaper
+ * @ir_para: parameters of IR shaper
+ * @max_tm_rate: max tm rate is available to config
  *
  * the formula:
  *
@@ -41,7 +38,8 @@ enum hclge_shaper_level {
  * @return: 0: calculate sucessful, negative: fail
  */
 static int hclge_shaper_para_calc(u32 ir, u8 shaper_level,
-				  u8 *ir_b, u8 *ir_u, u8 *ir_s)
+				  struct hclge_shaper_ir_para *ir_para,
+				  u32 max_tm_rate)
 {
 #define DIVISOR_CLK		(1000 * 8)
 #define DIVISOR_IR_B_126	(126 * DIVISOR_CLK)
@@ -59,7 +57,7 @@ static int hclge_shaper_para_calc(u32 ir, u8 shaper_level,
 
 	/* Calc tick */
 	if (shaper_level >= HCLGE_SHAPER_LVL_CNT ||
-	    ir > HCLGE_ETHER_MAX_RATE)
+	    ir > max_tm_rate)
 		return -EINVAL;
 
 	tick = tick_array[shaper_level];
@@ -74,9 +72,9 @@ static int hclge_shaper_para_calc(u32 ir, u8 shaper_level,
 	ir_calc = (DIVISOR_IR_B_126 + (tick >> 1) - 1) / tick;
 
 	if (ir_calc == ir) {
-		*ir_b = 126;
-		*ir_u = 0;
-		*ir_s = 0;
+		ir_para->ir_b = 126;
+		ir_para->ir_u = 0;
+		ir_para->ir_s = 0;
 
 		return 0;
 	} else if (ir_calc > ir) {
@@ -86,8 +84,8 @@ static int hclge_shaper_para_calc(u32 ir, u8 shaper_level,
 			ir_calc = DIVISOR_IR_B_126 / (tick * (1 << ir_s_calc));
 		}
 
-		*ir_b = (ir * tick * (1 << ir_s_calc) + (DIVISOR_CLK >> 1)) /
-			DIVISOR_CLK;
+		ir_para->ir_b = (ir * tick * (1 << ir_s_calc) +
+				(DIVISOR_CLK >> 1)) / DIVISOR_CLK;
 	} else {
 		/* Increasing the numerator to select ir_u value */
 		u32 numerator;
@@ -99,15 +97,16 @@ static int hclge_shaper_para_calc(u32 ir, u8 shaper_level,
 		}
 
 		if (ir_calc == ir) {
-			*ir_b = 126;
+			ir_para->ir_b = 126;
 		} else {
 			u32 denominator = DIVISOR_CLK * (1 << --ir_u_calc);
-			*ir_b = (ir * tick + (denominator >> 1)) / denominator;
+			ir_para->ir_b = (ir * tick + (denominator >> 1)) /
+					denominator;
 		}
 	}
 
-	*ir_u = ir_u_calc;
-	*ir_s = ir_s_calc;
+	ir_para->ir_u = ir_u_calc;
+	ir_para->ir_s = ir_s_calc;
 
 	return 0;
 }
@@ -400,21 +399,22 @@ static int hclge_tm_pg_shapping_cfg(struct hclge_dev *hdev,
 static int hclge_tm_port_shaper_cfg(struct hclge_dev *hdev)
 {
 	struct hclge_port_shapping_cmd *shap_cfg_cmd;
+	struct hclge_shaper_ir_para ir_para;
 	struct hclge_desc desc;
-	u8 ir_u, ir_b, ir_s;
 	u32 shapping_para;
 	int ret;
 
-	ret = hclge_shaper_para_calc(hdev->hw.mac.speed,
-				     HCLGE_SHAPER_LVL_PORT,
-				     &ir_b, &ir_u, &ir_s);
+	ret = hclge_shaper_para_calc(hdev->hw.mac.speed, HCLGE_SHAPER_LVL_PORT,
+				     &ir_para,
+				     hdev->ae_dev->dev_specs.max_tm_rate);
 	if (ret)
 		return ret;
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TM_PORT_SHAPPING, false);
 	shap_cfg_cmd = (struct hclge_port_shapping_cmd *)desc.data;
 
-	shapping_para = hclge_tm_get_shapping_para(ir_b, ir_u, ir_s,
+	shapping_para = hclge_tm_get_shapping_para(ir_para.ir_b, ir_para.ir_u,
+						   ir_para.ir_s,
 						   HCLGE_SHAPER_BS_U_DEF,
 						   HCLGE_SHAPER_BS_S_DEF);
 
@@ -515,21 +515,23 @@ int hclge_tm_qs_shaper_cfg(struct hclge_vport *vport, int max_tx_rate)
 {
 	struct hnae3_knic_private_info *kinfo = &vport->nic.kinfo;
 	struct hclge_qs_shapping_cmd *shap_cfg_cmd;
+	struct hclge_shaper_ir_para ir_para;
 	struct hclge_dev *hdev = vport->back;
 	struct hclge_desc desc;
-	u8 ir_b, ir_u, ir_s;
 	u32 shaper_para;
 	int ret, i;
 
 	if (!max_tx_rate)
-		max_tx_rate = HCLGE_ETHER_MAX_RATE;
+		max_tx_rate = hdev->ae_dev->dev_specs.max_tm_rate;
 
 	ret = hclge_shaper_para_calc(max_tx_rate, HCLGE_SHAPER_LVL_QSET,
-				     &ir_b, &ir_u, &ir_s);
+				     &ir_para,
+				     hdev->ae_dev->dev_specs.max_tm_rate);
 	if (ret)
 		return ret;
 
-	shaper_para = hclge_tm_get_shapping_para(ir_b, ir_u, ir_s,
+	shaper_para = hclge_tm_get_shapping_para(ir_para.ir_b, ir_para.ir_u,
+						 ir_para.ir_s,
 						 HCLGE_SHAPER_BS_U_DEF,
 						 HCLGE_SHAPER_BS_S_DEF);
 
@@ -668,7 +670,8 @@ static void hclge_tm_pg_info_init(struct hclge_dev *hdev)
 		hdev->tm_info.pg_info[i].pg_id = i;
 		hdev->tm_info.pg_info[i].pg_sch_mode = HCLGE_SCH_MODE_DWRR;
 
-		hdev->tm_info.pg_info[i].bw_limit = HCLGE_ETHER_MAX_RATE;
+		hdev->tm_info.pg_info[i].bw_limit =
+					hdev->ae_dev->dev_specs.max_tm_rate;
 
 		if (i != 0)
 			continue;
@@ -729,7 +732,8 @@ static int hclge_tm_pg_to_pri_map(struct hclge_dev *hdev)
 
 static int hclge_tm_pg_shaper_cfg(struct hclge_dev *hdev)
 {
-	u8 ir_u, ir_b, ir_s;
+	u32 max_tm_rate = hdev->ae_dev->dev_specs.max_tm_rate;
+	struct hclge_shaper_ir_para ir_para;
 	u32 shaper_para;
 	int ret;
 	u32 i;
@@ -741,10 +745,9 @@ static int hclge_tm_pg_shaper_cfg(struct hclge_dev *hdev)
 	/* Pg to pri */
 	for (i = 0; i < hdev->tm_info.num_pg; i++) {
 		/* Calc shaper para */
-		ret = hclge_shaper_para_calc(
-					hdev->tm_info.pg_info[i].bw_limit,
-					HCLGE_SHAPER_LVL_PG,
-					&ir_b, &ir_u, &ir_s);
+		ret = hclge_shaper_para_calc(hdev->tm_info.pg_info[i].bw_limit,
+					     HCLGE_SHAPER_LVL_PG,
+					     &ir_para, max_tm_rate);
 		if (ret)
 			return ret;
 
@@ -757,7 +760,9 @@ static int hclge_tm_pg_shaper_cfg(struct hclge_dev *hdev)
 		if (ret)
 			return ret;
 
-		shaper_para = hclge_tm_get_shapping_para(ir_b, ir_u, ir_s,
+		shaper_para = hclge_tm_get_shapping_para(ir_para.ir_b,
+							 ir_para.ir_u,
+							 ir_para.ir_s,
 							 HCLGE_SHAPER_BS_U_DEF,
 							 HCLGE_SHAPER_BS_S_DEF);
 		ret = hclge_tm_pg_shapping_cfg(hdev,
@@ -861,16 +866,16 @@ static int hclge_tm_pri_q_qs_cfg(struct hclge_dev *hdev)
 
 static int hclge_tm_pri_tc_base_shaper_cfg(struct hclge_dev *hdev)
 {
-	u8 ir_u, ir_b, ir_s;
+	u32 max_tm_rate = hdev->ae_dev->dev_specs.max_tm_rate;
+	struct hclge_shaper_ir_para ir_para;
 	u32 shaper_para;
 	int ret;
 	u32 i;
 
 	for (i = 0; i < hdev->tm_info.num_tc; i++) {
-		ret = hclge_shaper_para_calc(
-					hdev->tm_info.tc_info[i].bw_limit,
-					HCLGE_SHAPER_LVL_PRI,
-					&ir_b, &ir_u, &ir_s);
+		ret = hclge_shaper_para_calc(hdev->tm_info.tc_info[i].bw_limit,
+					     HCLGE_SHAPER_LVL_PRI,
+					     &ir_para, max_tm_rate);
 		if (ret)
 			return ret;
 
@@ -882,7 +887,9 @@ static int hclge_tm_pri_tc_base_shaper_cfg(struct hclge_dev *hdev)
 		if (ret)
 			return ret;
 
-		shaper_para = hclge_tm_get_shapping_para(ir_b, ir_u, ir_s,
+		shaper_para = hclge_tm_get_shapping_para(ir_para.ir_b,
+							 ir_para.ir_u,
+							 ir_para.ir_s,
 							 HCLGE_SHAPER_BS_U_DEF,
 							 HCLGE_SHAPER_BS_S_DEF);
 		ret = hclge_tm_pri_shapping_cfg(hdev, HCLGE_TM_SHAP_P_BUCKET, i,
@@ -897,12 +904,13 @@ static int hclge_tm_pri_tc_base_shaper_cfg(struct hclge_dev *hdev)
 static int hclge_tm_pri_vnet_base_shaper_pri_cfg(struct hclge_vport *vport)
 {
 	struct hclge_dev *hdev = vport->back;
-	u8 ir_u, ir_b, ir_s;
+	struct hclge_shaper_ir_para ir_para;
 	u32 shaper_para;
 	int ret;
 
 	ret = hclge_shaper_para_calc(vport->bw_limit, HCLGE_SHAPER_LVL_VF,
-				     &ir_b, &ir_u, &ir_s);
+				     &ir_para,
+				     hdev->ae_dev->dev_specs.max_tm_rate);
 	if (ret)
 		return ret;
 
@@ -914,7 +922,8 @@ static int hclge_tm_pri_vnet_base_shaper_pri_cfg(struct hclge_vport *vport)
 	if (ret)
 		return ret;
 
-	shaper_para = hclge_tm_get_shapping_para(ir_b, ir_u, ir_s,
+	shaper_para = hclge_tm_get_shapping_para(ir_para.ir_b, ir_para.ir_u,
+						 ir_para.ir_s,
 						 HCLGE_SHAPER_BS_U_DEF,
 						 HCLGE_SHAPER_BS_S_DEF);
 	ret = hclge_tm_pri_shapping_cfg(hdev, HCLGE_TM_SHAP_P_BUCKET,
@@ -929,15 +938,15 @@ static int hclge_tm_pri_vnet_base_shaper_qs_cfg(struct hclge_vport *vport)
 {
 	struct hnae3_knic_private_info *kinfo = &vport->nic.kinfo;
 	struct hclge_dev *hdev = vport->back;
-	u8 ir_u, ir_b, ir_s;
+	u32 max_tm_rate = hdev->ae_dev->dev_specs.max_tm_rate;
+	struct hclge_shaper_ir_para ir_para;
 	u32 i;
 	int ret;
 
 	for (i = 0; i < kinfo->num_tc; i++) {
-		ret = hclge_shaper_para_calc(
-					hdev->tm_info.tc_info[i].bw_limit,
-					HCLGE_SHAPER_LVL_QSET,
-					&ir_b, &ir_u, &ir_s);
+		ret = hclge_shaper_para_calc(hdev->tm_info.tc_info[i].bw_limit,
+					     HCLGE_SHAPER_LVL_QSET,
+					     &ir_para, max_tm_rate);
 		if (ret)
 			return ret;
 	}
@@ -1355,7 +1364,7 @@ static int hclge_mac_pause_setup_hw(struct hclge_dev *hdev)
 
 static int hclge_tm_bp_setup(struct hclge_dev *hdev)
 {
-	int ret = 0;
+	int ret;
 	int i;
 
 	for (i = 0; i < hdev->tm_info.num_tc; i++) {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
index 45bcb67f90fd..bb2a2d8e9259 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
@@ -19,6 +19,8 @@
 #define HCLGE_TM_TX_SCHD_DWRR_MSK	BIT(0)
 #define HCLGE_TM_TX_SCHD_SP_MSK		(0xFE)
 
+#define HCLGE_ETHER_MAX_RATE	100000
+
 struct hclge_pg_to_pri_link_cmd {
 	u8 pg_id;
 	u8 rsvd1[3];
@@ -139,6 +141,12 @@ struct hclge_port_shapping_cmd {
 	__le32 port_shapping_para;
 };
 
+struct hclge_shaper_ir_para {
+	u8 ir_b; /* IR_B parameter of IR shaper */
+	u8 ir_u; /* IR_U parameter of IR shaper */
+	u8 ir_s; /* IR_S parameter of IR shaper */
+};
+
 #define hclge_tm_set_field(dest, string, val) \
 			   hnae3_set_field((dest), \
 			   (HCLGE_TM_SHAP_##string##_MSK), \
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c
index fec65239a3c8..66866c1cfb12 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c
@@ -313,9 +313,34 @@ int hclgevf_cmd_send(struct hclgevf_hw *hw, struct hclgevf_desc *desc, int num)
 	return status;
 }
 
-static int  hclgevf_cmd_query_firmware_version(struct hclgevf_hw *hw,
-					       u32 *version)
+static void hclgevf_set_default_capability(struct hclgevf_dev *hdev)
 {
+	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev);
+
+	set_bit(HNAE3_DEV_SUPPORT_FD_B, ae_dev->caps);
+	set_bit(HNAE3_DEV_SUPPORT_GRO_B, ae_dev->caps);
+	set_bit(HNAE3_DEV_SUPPORT_FEC_B, ae_dev->caps);
+}
+
+static void hclgevf_parse_capability(struct hclgevf_dev *hdev,
+				     struct hclgevf_query_version_cmd *cmd)
+{
+	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev);
+	u32 caps;
+
+	caps = __le32_to_cpu(cmd->caps[0]);
+
+	if (hnae3_get_bit(caps, HCLGEVF_CAP_UDP_GSO_B))
+		set_bit(HNAE3_DEV_SUPPORT_UDP_GSO_B, ae_dev->caps);
+	if (hnae3_get_bit(caps, HCLGEVF_CAP_INT_QL_B))
+		set_bit(HNAE3_DEV_SUPPORT_INT_QL_B, ae_dev->caps);
+	if (hnae3_get_bit(caps, HCLGEVF_CAP_TQP_TXRX_INDEP_B))
+		set_bit(HNAE3_DEV_SUPPORT_TQP_TXRX_INDEP_B, ae_dev->caps);
+}
+
+static int hclgevf_cmd_query_version_and_capability(struct hclgevf_dev *hdev)
+{
+	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev);
 	struct hclgevf_query_version_cmd *resp;
 	struct hclgevf_desc desc;
 	int status;
@@ -323,9 +348,20 @@ static int  hclgevf_cmd_query_firmware_version(struct hclgevf_hw *hw,
 	resp = (struct hclgevf_query_version_cmd *)desc.data;
 
 	hclgevf_cmd_setup_basic_desc(&desc, HCLGEVF_OPC_QUERY_FW_VER, 1);
-	status = hclgevf_cmd_send(hw, &desc, 1);
-	if (!status)
-		*version = le32_to_cpu(resp->firmware);
+	status = hclgevf_cmd_send(&hdev->hw, &desc, 1);
+	if (status)
+		return status;
+
+	hdev->fw_version = le32_to_cpu(resp->firmware);
+
+	ae_dev->dev_version = le32_to_cpu(resp->hardware) <<
+				 HNAE3_PCI_REVISION_BIT_SIZE;
+	ae_dev->dev_version |= hdev->pdev->revision;
+
+	if (ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V2)
+		hclgevf_set_default_capability(hdev);
+
+	hclgevf_parse_capability(hdev, resp);
 
 	return status;
 }
@@ -364,7 +400,6 @@ err_csq:
 
 int hclgevf_cmd_init(struct hclgevf_dev *hdev)
 {
-	u32 version;
 	int ret;
 
 	spin_lock_bh(&hdev->hw.cmq.csq.lock);
@@ -395,23 +430,22 @@ int hclgevf_cmd_init(struct hclgevf_dev *hdev)
 		goto err_cmd_init;
 	}
 
-	/* get firmware version */
-	ret = hclgevf_cmd_query_firmware_version(&hdev->hw, &version);
+	/* get version and device capabilities */
+	ret = hclgevf_cmd_query_version_and_capability(hdev);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
-			"failed(%d) to query firmware version\n", ret);
+			"failed to query version and capabilities, ret = %d\n", ret);
 		goto err_cmd_init;
 	}
-	hdev->fw_version = version;
 
 	dev_info(&hdev->pdev->dev, "The firmware version is %lu.%lu.%lu.%lu\n",
-		 hnae3_get_field(version, HNAE3_FW_VERSION_BYTE3_MASK,
+		 hnae3_get_field(hdev->fw_version, HNAE3_FW_VERSION_BYTE3_MASK,
 				 HNAE3_FW_VERSION_BYTE3_SHIFT),
-		 hnae3_get_field(version, HNAE3_FW_VERSION_BYTE2_MASK,
+		 hnae3_get_field(hdev->fw_version, HNAE3_FW_VERSION_BYTE2_MASK,
 				 HNAE3_FW_VERSION_BYTE2_SHIFT),
-		 hnae3_get_field(version, HNAE3_FW_VERSION_BYTE1_MASK,
+		 hnae3_get_field(hdev->fw_version, HNAE3_FW_VERSION_BYTE1_MASK,
 				 HNAE3_FW_VERSION_BYTE1_SHIFT),
-		 hnae3_get_field(version, HNAE3_FW_VERSION_BYTE0_MASK,
+		 hnae3_get_field(hdev->fw_version, HNAE3_FW_VERSION_BYTE0_MASK,
 				 HNAE3_FW_VERSION_BYTE0_SHIFT));
 
 	return 0;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h
index 40d6e602ab51..9460c128c095 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h
@@ -91,6 +91,8 @@ enum hclgevf_opcode_type {
 	/* Generic command */
 	HCLGEVF_OPC_QUERY_FW_VER	= 0x0001,
 	HCLGEVF_OPC_QUERY_VF_RSRC	= 0x0024,
+	HCLGEVF_OPC_QUERY_DEV_SPECS	= 0x0050,
+
 	/* TQP command */
 	HCLGEVF_OPC_QUERY_TX_STATUS	= 0x0B03,
 	HCLGEVF_OPC_QUERY_RX_STATUS	= 0x0B13,
@@ -141,9 +143,26 @@ struct hclgevf_ctrl_vector_chain {
 	u8 resv;
 };
 
+enum HCLGEVF_CAP_BITS {
+	HCLGEVF_CAP_UDP_GSO_B,
+	HCLGEVF_CAP_QB_B,
+	HCLGEVF_CAP_FD_FORWARD_TC_B,
+	HCLGEVF_CAP_PTP_B,
+	HCLGEVF_CAP_INT_QL_B,
+	HCLGEVF_CAP_SIMPLE_BD_B,
+	HCLGEVF_CAP_TX_PUSH_B,
+	HCLGEVF_CAP_PHY_IMP_B,
+	HCLGEVF_CAP_TQP_TXRX_INDEP_B,
+	HCLGEVF_CAP_HW_PAD_B,
+	HCLGEVF_CAP_STASH_B,
+};
+
+#define HCLGEVF_QUERY_CAP_LENGTH		3
 struct hclgevf_query_version_cmd {
 	__le32 firmware;
-	__le32 firmware_rsv[5];
+	__le32 hardware;
+	__le32 rsv;
+	__le32 caps[HCLGEVF_QUERY_CAP_LENGTH]; /* capabilities of device */
 };
 
 #define HCLGEVF_MSIX_OFT_ROCEE_S       0
@@ -253,6 +272,19 @@ struct hclgevf_cfg_tx_queue_pointer_cmd {
 #define HCLGEVF_NIC_CMQ_DESC_NUM_S	3
 #define HCLGEVF_NIC_CMDQ_INT_SRC_REG	0x27100
 
+#define HCLGEVF_QUERY_DEV_SPECS_BD_NUM		4
+
+struct hclgevf_dev_specs_0_cmd {
+	__le32 rsv0;
+	__le32 mac_entry_num;
+	__le32 mng_entry_num;
+	__le16 rss_ind_tbl_size;
+	__le16 rss_key_size;
+	__le16 int_ql_max;
+	u8 max_non_tso_bd_num;
+	u8 rsv1[5];
+};
+
 static inline void hclgevf_write_reg(void __iomem *base, u32 reg, u32 value)
 {
 	writel(value, base + reg);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 8eb9af49b85c..50c84c5e65d2 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -19,8 +19,9 @@ static struct hnae3_ae_algo ae_algovf;
 static struct workqueue_struct *hclgevf_wq;
 
 static const struct pci_device_id ae_algovf_pci_tbl[] = {
-	{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_100G_VF), 0},
-	{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_100G_RDMA_DCB_PFC_VF), 0},
+	{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_VF), 0},
+	{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_RDMA_DCB_PFC_VF),
+	 HNAE3_DEV_SUPPORT_ROCE_DCB_BITS},
 	/* required last entry */
 	{0, }
 };
@@ -171,7 +172,7 @@ static u8 *hclgevf_tqps_get_strings(struct hnae3_handle *handle, u8 *data)
 {
 	struct hnae3_knic_private_info *kinfo = &handle->kinfo;
 	u8 *buff = data;
-	int i = 0;
+	int i;
 
 	for (i = 0; i < kinfo->num_tqps; i++) {
 		struct hclgevf_tqp *tqp = container_of(kinfo->tqp[i],
@@ -745,7 +746,7 @@ static int hclgevf_get_rss(struct hnae3_handle *handle, u32 *indir, u8 *key,
 	struct hclgevf_rss_cfg *rss_cfg = &hdev->rss_cfg;
 	int i, ret;
 
-	if (handle->pdev->revision >= 0x21) {
+	if (hdev->ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V2) {
 		/* Get hash algorithm */
 		if (hfunc) {
 			switch (rss_cfg->hash_algo) {
@@ -791,7 +792,7 @@ static int hclgevf_set_rss(struct hnae3_handle *handle, const u32 *indir,
 	struct hclgevf_rss_cfg *rss_cfg = &hdev->rss_cfg;
 	int ret, i;
 
-	if (handle->pdev->revision >= 0x21) {
+	if (hdev->ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V2) {
 		/* Set the RSS Hash Key if specififed by the user */
 		if (key) {
 			switch (hfunc) {
@@ -863,7 +864,7 @@ static int hclgevf_set_rss_tuple(struct hnae3_handle *handle,
 	u8 tuple_sets;
 	int ret;
 
-	if (handle->pdev->revision == 0x20)
+	if (hdev->ae_dev->dev_version < HNAE3_DEVICE_VERSION_V2)
 		return -EOPNOTSUPP;
 
 	if (nfc->data &
@@ -941,7 +942,7 @@ static int hclgevf_get_rss_tuple(struct hnae3_handle *handle,
 	struct hclgevf_rss_cfg *rss_cfg = &hdev->rss_cfg;
 	u8 tuple_sets;
 
-	if (handle->pdev->revision == 0x20)
+	if (hdev->ae_dev->dev_version < HNAE3_DEVICE_VERSION_V2)
 		return -EOPNOTSUPP;
 
 	nfc->data = 0;
@@ -1154,10 +1155,9 @@ static int hclgevf_set_promisc_mode(struct hnae3_handle *handle, bool en_uc_pmc,
 				    bool en_mc_pmc)
 {
 	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
-	struct pci_dev *pdev = hdev->pdev;
 	bool en_bc_pmc;
 
-	en_bc_pmc = pdev->revision != 0x20;
+	en_bc_pmc = hdev->ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V2;
 
 	return hclgevf_cmd_set_promisc_mode(hdev, en_uc_pmc, en_mc_pmc,
 					    en_bc_pmc);
@@ -1702,6 +1702,26 @@ static int hclgevf_notify_client(struct hclgevf_dev *hdev,
 	return ret;
 }
 
+static int hclgevf_notify_roce_client(struct hclgevf_dev *hdev,
+				      enum hnae3_reset_notify_type type)
+{
+	struct hnae3_client *client = hdev->roce_client;
+	struct hnae3_handle *handle = &hdev->roce;
+	int ret;
+
+	if (!test_bit(HCLGEVF_STATE_ROCE_REGISTERED, &hdev->state) || !client)
+		return 0;
+
+	if (!client->ops->reset_notify)
+		return -EOPNOTSUPP;
+
+	ret = client->ops->reset_notify(handle, type);
+	if (ret)
+		dev_err(&hdev->pdev->dev, "notify roce client failed %d(%d)",
+			type, ret);
+	return ret;
+}
+
 static int hclgevf_reset_wait(struct hclgevf_dev *hdev)
 {
 #define HCLGEVF_RESET_WAIT_US	20000
@@ -1865,6 +1885,11 @@ static int hclgevf_reset_prepare(struct hclgevf_dev *hdev)
 
 	hdev->rst_stats.rst_cnt++;
 
+	/* perform reset of the stack & ae device for a client */
+	ret = hclgevf_notify_roce_client(hdev, HNAE3_DOWN_CLIENT);
+	if (ret)
+		return ret;
+
 	rtnl_lock();
 	/* bring down the nic to stop any ongoing TX/RX */
 	ret = hclgevf_notify_client(hdev, HNAE3_DOWN_CLIENT);
@@ -1880,6 +1905,9 @@ static int hclgevf_reset_rebuild(struct hclgevf_dev *hdev)
 	int ret;
 
 	hdev->rst_stats.hw_rst_done_cnt++;
+	ret = hclgevf_notify_roce_client(hdev, HNAE3_UNINIT_CLIENT);
+	if (ret)
+		return ret;
 
 	rtnl_lock();
 	/* now, re-initialize the nic client and ae device */
@@ -1890,6 +1918,18 @@ static int hclgevf_reset_rebuild(struct hclgevf_dev *hdev)
 		return ret;
 	}
 
+	ret = hclgevf_notify_roce_client(hdev, HNAE3_INIT_CLIENT);
+	/* ignore RoCE notify error if it fails HCLGEVF_RESET_MAX_FAIL_CNT - 1
+	 * times
+	 */
+	if (ret &&
+	    hdev->rst_stats.rst_fail_cnt < HCLGEVF_RESET_MAX_FAIL_CNT - 1)
+		return ret;
+
+	ret = hclgevf_notify_roce_client(hdev, HNAE3_UP_CLIENT);
+	if (ret)
+		return ret;
+
 	hdev->last_reset_time = jiffies;
 	hdev->rst_stats.rst_done_cnt++;
 	hdev->rst_stats.rst_fail_cnt = 0;
@@ -2287,7 +2327,7 @@ static enum hclgevf_evt_cause hclgevf_check_evt_cause(struct hclgevf_dev *hdev,
 		 * register, so we should just write 0 to the bit we are
 		 * handling, and keep other bits as cmdq_stat_reg.
 		 */
-		if (hdev->pdev->revision >= 0x21)
+		if (hdev->ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V2)
 			*clearval = ~(1U << HCLGEVF_VECTOR0_RX_CMDQ_INT_B);
 		else
 			*clearval = cmdq_stat_reg &
@@ -2430,7 +2470,7 @@ static void hclgevf_rss_init_cfg(struct hclgevf_dev *hdev)
 	rss_cfg->hash_algo = HCLGEVF_RSS_HASH_ALGO_TOEPLITZ;
 	rss_cfg->rss_size = hdev->nic.kinfo.rss_size;
 	tuple_sets = &rss_cfg->rss_tuple_sets;
-	if (hdev->pdev->revision >= 0x21) {
+	if (hdev->ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V2) {
 		rss_cfg->hash_algo = HCLGEVF_RSS_HASH_ALGO_SIMPLE;
 		memcpy(rss_cfg->rss_hash_key, hclgevf_hash_key,
 		       HCLGEVF_RSS_KEY_SIZE);
@@ -2455,7 +2495,7 @@ static int hclgevf_rss_init_hw(struct hclgevf_dev *hdev)
 	struct hclgevf_rss_cfg *rss_cfg = &hdev->rss_cfg;
 	int ret;
 
-	if (hdev->pdev->revision >= 0x21) {
+	if (hdev->ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V2) {
 		ret = hclgevf_set_rss_algo_key(hdev, rss_cfg->hash_algo,
 					       rss_cfg->rss_hash_key);
 		if (ret)
@@ -2757,6 +2797,7 @@ static int hclgevf_init_roce_client_instance(struct hnae3_ae_dev *ae_dev,
 	if (ret)
 		return ret;
 
+	set_bit(HCLGEVF_STATE_ROCE_REGISTERED, &hdev->state);
 	hnae3_set_client_init_flag(client, ae_dev, 1);
 
 	return 0;
@@ -2817,6 +2858,7 @@ static void hclgevf_uninit_client_instance(struct hnae3_client *client,
 
 	/* un-init roce, if it exists */
 	if (hdev->roce_client) {
+		clear_bit(HCLGEVF_STATE_ROCE_REGISTERED, &hdev->state);
 		hdev->roce_client->ops->uninit_instance(&hdev->roce, 0);
 		hdev->roce_client = NULL;
 		hdev->roce.client = NULL;
@@ -2939,6 +2981,76 @@ static int hclgevf_query_vf_resource(struct hclgevf_dev *hdev)
 	return 0;
 }
 
+static void hclgevf_set_default_dev_specs(struct hclgevf_dev *hdev)
+{
+#define HCLGEVF_MAX_NON_TSO_BD_NUM			8U
+
+	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev);
+
+	ae_dev->dev_specs.max_non_tso_bd_num =
+					HCLGEVF_MAX_NON_TSO_BD_NUM;
+	ae_dev->dev_specs.rss_ind_tbl_size = HCLGEVF_RSS_IND_TBL_SIZE;
+	ae_dev->dev_specs.rss_key_size = HCLGEVF_RSS_KEY_SIZE;
+}
+
+static void hclgevf_parse_dev_specs(struct hclgevf_dev *hdev,
+				    struct hclgevf_desc *desc)
+{
+	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev);
+	struct hclgevf_dev_specs_0_cmd *req0;
+
+	req0 = (struct hclgevf_dev_specs_0_cmd *)desc[0].data;
+
+	ae_dev->dev_specs.max_non_tso_bd_num = req0->max_non_tso_bd_num;
+	ae_dev->dev_specs.rss_ind_tbl_size =
+					le16_to_cpu(req0->rss_ind_tbl_size);
+	ae_dev->dev_specs.rss_key_size = le16_to_cpu(req0->rss_key_size);
+}
+
+static void hclgevf_check_dev_specs(struct hclgevf_dev *hdev)
+{
+	struct hnae3_dev_specs *dev_specs = &hdev->ae_dev->dev_specs;
+
+	if (!dev_specs->max_non_tso_bd_num)
+		dev_specs->max_non_tso_bd_num = HCLGEVF_MAX_NON_TSO_BD_NUM;
+	if (!dev_specs->rss_ind_tbl_size)
+		dev_specs->rss_ind_tbl_size = HCLGEVF_RSS_IND_TBL_SIZE;
+	if (!dev_specs->rss_key_size)
+		dev_specs->rss_key_size = HCLGEVF_RSS_KEY_SIZE;
+}
+
+static int hclgevf_query_dev_specs(struct hclgevf_dev *hdev)
+{
+	struct hclgevf_desc desc[HCLGEVF_QUERY_DEV_SPECS_BD_NUM];
+	int ret;
+	int i;
+
+	/* set default specifications as devices lower than version V3 do not
+	 * support querying specifications from firmware.
+	 */
+	if (hdev->ae_dev->dev_version < HNAE3_DEVICE_VERSION_V3) {
+		hclgevf_set_default_dev_specs(hdev);
+		return 0;
+	}
+
+	for (i = 0; i < HCLGEVF_QUERY_DEV_SPECS_BD_NUM - 1; i++) {
+		hclgevf_cmd_setup_basic_desc(&desc[i],
+					     HCLGEVF_OPC_QUERY_DEV_SPECS, true);
+		desc[i].flag |= cpu_to_le16(HCLGEVF_CMD_FLAG_NEXT);
+	}
+	hclgevf_cmd_setup_basic_desc(&desc[i], HCLGEVF_OPC_QUERY_DEV_SPECS,
+				     true);
+
+	ret = hclgevf_cmd_send(&hdev->hw, desc, HCLGEVF_QUERY_DEV_SPECS_BD_NUM);
+	if (ret)
+		return ret;
+
+	hclgevf_parse_dev_specs(hdev, desc);
+	hclgevf_check_dev_specs(hdev);
+
+	return 0;
+}
+
 static int hclgevf_pci_reset(struct hclgevf_dev *hdev)
 {
 	struct pci_dev *pdev = hdev->pdev;
@@ -3047,6 +3159,13 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev)
 	if (ret)
 		goto err_cmd_init;
 
+	ret = hclgevf_query_dev_specs(hdev);
+	if (ret) {
+		dev_err(&pdev->dev,
+			"failed to query dev specifications, ret = %d\n", ret);
+		goto err_cmd_init;
+	}
+
 	ret = hclgevf_init_msi(hdev);
 	if (ret) {
 		dev_err(&pdev->dev, "failed(%d) to init MSI/MSI-X\n", ret);
@@ -3342,6 +3461,13 @@ static bool hclgevf_get_hw_reset_stat(struct hnae3_handle *handle)
 	return !!hclgevf_read_dev(&hdev->hw, HCLGEVF_RST_ING);
 }
 
+static bool hclgevf_get_cmdq_stat(struct hnae3_handle *handle)
+{
+	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+
+	return test_bit(HCLGEVF_STATE_CMD_DISABLE, &hdev->state);
+}
+
 static bool hclgevf_ae_dev_resetting(struct hnae3_handle *handle)
 {
 	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
@@ -3527,6 +3653,7 @@ static const struct hnae3_ae_ops hclgevf_ops = {
 	.get_link_mode = hclgevf_get_link_mode,
 	.set_promisc_mode = hclgevf_set_promisc_mode,
 	.request_update_promisc_mode = hclgevf_request_update_promisc_mode,
+	.get_cmdq_stat = hclgevf_get_cmdq_stat,
 };
 
 static struct hnae3_ae_algo ae_algovf = {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
index c1fac8920ae3..c5bcc3894fd5 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
@@ -139,6 +139,7 @@ enum hclgevf_states {
 	HCLGEVF_STATE_IRQ_INITED,
 	HCLGEVF_STATE_REMOVING,
 	HCLGEVF_STATE_NIC_REGISTERED,
+	HCLGEVF_STATE_ROCE_REGISTERED,
 	/* task states */
 	HCLGEVF_STATE_RST_SERVICE_SCHED,
 	HCLGEVF_STATE_RST_HANDLING,
diff --git a/drivers/net/ethernet/hisilicon/hns_mdio.c b/drivers/net/ethernet/hisilicon/hns_mdio.c
index 7df5d7d211d4..883d0d7c6858 100644
--- a/drivers/net/ethernet/hisilicon/hns_mdio.c
+++ b/drivers/net/ethernet/hisilicon/hns_mdio.c
@@ -210,7 +210,7 @@ static void hns_mdio_cmd_write(struct hns_mdio_device *mdio_dev,
  * @bus: mdio bus
  * @phy_id: phy id
  * @regnum: register num
- * @value: register value
+ * @data: register value
  *
  * Return 0 on success, negative on failure
  */
@@ -273,7 +273,6 @@ static int hns_mdio_write(struct mii_bus *bus,
  * @bus: mdio bus
  * @phy_id: phy id
  * @regnum: register num
- * @value: register value
  *
  * Return phy register value
  */
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_devlink.c b/drivers/net/ethernet/huawei/hinic/hinic_devlink.c
index 16bda7381ba0..2630d667f393 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_devlink.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_devlink.c
@@ -281,18 +281,14 @@ static int hinic_firmware_update(struct hinic_devlink_priv *priv,
 }
 
 static int hinic_devlink_flash_update(struct devlink *devlink,
-				      const char *file_name,
-				      const char *component,
+				      struct devlink_flash_update_params *params,
 				      struct netlink_ext_ack *extack)
 {
 	struct hinic_devlink_priv *priv = devlink_priv(devlink);
 	const struct firmware *fw;
 	int err;
 
-	if (component)
-		return -EOPNOTSUPP;
-
-	err = request_firmware_direct(&fw, file_name,
+	err = request_firmware_direct(&fw, params->file_name,
 				      &priv->hwdev->hwif->pdev->dev);
 	if (err)
 		return err;
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c b/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c
index 6bb65ade1d77..c340d9acba80 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c
@@ -1654,6 +1654,7 @@ static void hinic_diag_test(struct net_device *netdev,
 	}
 
 	netif_carrier_off(netdev);
+	netif_tx_disable(netdev);
 
 	err = do_lp_test(nic_dev, eth_test->flags, LP_DEFAULT_TIME,
 			 &test_index);
@@ -1662,9 +1663,12 @@ static void hinic_diag_test(struct net_device *netdev,
 		data[test_index] = 1;
 	}
 
+	netif_tx_wake_all_queues(netdev);
+
 	err = hinic_port_link_state(nic_dev, &link_state);
 	if (!err && link_state == HINIC_LINK_STATE_UP)
 		netif_carrier_on(netdev);
+
 }
 
 static int hinic_set_phys_id(struct net_device *netdev,
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c
index e0eb294779ec..5a6bbee819cd 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c
@@ -784,7 +784,7 @@ static void free_cmdq(struct hinic_cmdq *cmdq)
  * init_cmdqs_ctxt - write the cmdq ctxt to HW after init all cmdq
  * @hwdev: the NIC HW device
  * @cmdqs: cmdqs to write the ctxts for
- * &db_area: db_area for all the cmdqs
+ * @db_area: db_area for all the cmdqs
  *
  * Return 0 - Success, negative - Failure
  **/
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
index 239685152f6e..0c74f6674634 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
@@ -437,6 +437,8 @@ static int get_base_qpn(struct hinic_hwdev *hwdev, u16 *base_qpn)
 /**
  * hinic_hwdev_ifup - Preparing the HW for passing IO
  * @hwdev: the NIC HW device
+ * @sq_depth: the send queue depth
+ * @rq_depth: the receive queue depth
  *
  * Return 0 - Success, negative - Failure
  **/
@@ -582,6 +584,7 @@ void hinic_hwdev_cb_unregister(struct hinic_hwdev *hwdev,
 /**
  * nic_mgmt_msg_handler - nic mgmt event handler
  * @handle: private data for the handler
+ * @cmd: message command
  * @buf_in: input buffer
  * @in_size: input size
  * @buf_out: output buffer
@@ -909,6 +912,7 @@ int hinic_set_interrupt_cfg(struct hinic_hwdev *hwdev,
 /**
  * hinic_init_hwdev - Initialize the NIC HW
  * @pdev: the NIC pci device
+ * @devlink: the poniter of hinic devlink
  *
  * Return initialized NIC HW device
  *
@@ -1121,7 +1125,7 @@ int hinic_hwdev_msix_cnt_set(struct hinic_hwdev *hwdev, u16 msix_index)
  * @msix_index: msix_index
  * @pending_limit: the maximum pending interrupt events (unit 8)
  * @coalesc_timer: coalesc period for interrupt (unit 8 us)
- * @lli_timer: replenishing period for low latency credit (unit 8 us)
+ * @lli_timer_cfg: replenishing period for low latency credit (unit 8 us)
  * @lli_credit_limit: maximum credits for low latency msix messages (unit 8)
  * @resend_timer: maximum wait for resending msix (unit coalesc period)
  *
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c
index f108b0c9228e..19942fef99d9 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c
@@ -188,6 +188,7 @@ static u8 eq_cons_idx_checksum_set(u32 val)
 /**
  * eq_update_ci - update the HW cons idx of event queue
  * @eq: the event queue to update the cons idx for
+ * @arm_state: the arm bit value of eq's interrupt
  **/
 static void eq_update_ci(struct hinic_eq *eq, u32 arm_state)
 {
@@ -368,7 +369,7 @@ static void eq_irq_work(struct work_struct *work)
 
 /**
  * ceq_tasklet - the tasklet of the EQ that received the event
- * @ceq_data: the eq
+ * @t: the tasklet struct pointer
  **/
 static void ceq_tasklet(struct tasklet_struct *t)
 {
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.c
index bc8925c0c982..efbaed389440 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.c
@@ -230,6 +230,7 @@ static int wait_hwif_ready(struct hinic_hwif *hwif)
  * @hwif: the HW interface of a pci function device
  * @attr0: the first attribute that was read from the hw
  * @attr1: the second attribute that was read from the hw
+ * @attr2: the third attribute that was read from the hw
  **/
 static void set_hwif_attr(struct hinic_hwif *hwif, u32 attr0, u32 attr1,
 			  u32 attr2)
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c
index c6ce5966284c..819fa13034c0 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c
@@ -47,8 +47,12 @@
 
 #define MGMT_MSG_TIMEOUT                5000
 
+#define SET_FUNC_PORT_MBOX_TIMEOUT	30000
+
 #define SET_FUNC_PORT_MGMT_TIMEOUT	25000
 
+#define UPDATE_FW_MGMT_TIMEOUT		20000
+
 #define mgmt_to_pfhwdev(pf_mgmt)        \
 		container_of(pf_mgmt, struct hinic_pfhwdev, pf_to_mgmt)
 
@@ -234,6 +238,7 @@ static int send_msg_to_mgmt(struct hinic_pf_to_mgmt *pf_to_mgmt,
  * @out_size: response length
  * @direction: the direction of the original message
  * @resp_msg_id: msg id to response for
+ * @timeout: time-out period of waiting for response
  *
  * Return 0 - Success, negative - Failure
  **/
@@ -361,16 +366,22 @@ int hinic_msg_to_mgmt(struct hinic_pf_to_mgmt *pf_to_mgmt,
 		return -EINVAL;
 	}
 
-	if (cmd == HINIC_PORT_CMD_SET_FUNC_STATE)
-		timeout = SET_FUNC_PORT_MGMT_TIMEOUT;
+	if (HINIC_IS_VF(hwif)) {
+		if (cmd == HINIC_PORT_CMD_SET_FUNC_STATE)
+			timeout = SET_FUNC_PORT_MBOX_TIMEOUT;
 
-	if (HINIC_IS_VF(hwif))
 		return hinic_mbox_to_pf(pf_to_mgmt->hwdev, mod, cmd, buf_in,
-					in_size, buf_out, out_size, 0);
-	else
+					in_size, buf_out, out_size, timeout);
+	} else {
+		if (cmd == HINIC_PORT_CMD_SET_FUNC_STATE)
+			timeout = SET_FUNC_PORT_MGMT_TIMEOUT;
+		else if (cmd == HINIC_PORT_CMD_UPDATE_FW)
+			timeout = UPDATE_FW_MGMT_TIMEOUT;
+
 		return msg_to_mgmt_sync(pf_to_mgmt, mod, cmd, buf_in, in_size,
 				buf_out, out_size, MGMT_DIRECT_SEND,
 				MSG_NOT_RESP, timeout);
+	}
 }
 
 static void recv_mgmt_msg_work_handler(struct work_struct *work)
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c
index 2c63e3a690cd..350225bbe0be 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_main.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c
@@ -191,6 +191,24 @@ err_init_txq:
 	return err;
 }
 
+static void enable_txqs_napi(struct hinic_dev *nic_dev)
+{
+	int num_txqs = hinic_hwdev_num_qps(nic_dev->hwdev);
+	int i;
+
+	for (i = 0; i < num_txqs; i++)
+		napi_enable(&nic_dev->txqs[i].napi);
+}
+
+static void disable_txqs_napi(struct hinic_dev *nic_dev)
+{
+	int num_txqs = hinic_hwdev_num_qps(nic_dev->hwdev);
+	int i;
+
+	for (i = 0; i < num_txqs; i++)
+		napi_disable(&nic_dev->txqs[i].napi);
+}
+
 /**
  * free_txqs - Free the Logical Tx Queues of specific NIC device
  * @nic_dev: the specific NIC device
@@ -440,6 +458,8 @@ int hinic_open(struct net_device *netdev)
 		goto err_create_txqs;
 	}
 
+	enable_txqs_napi(nic_dev);
+
 	err = create_rxqs(nic_dev);
 	if (err) {
 		netif_err(nic_dev, drv, netdev,
@@ -524,6 +544,7 @@ err_port_state:
 	}
 
 err_create_rxqs:
+	disable_txqs_napi(nic_dev);
 	free_txqs(nic_dev);
 
 err_create_txqs:
@@ -537,6 +558,9 @@ int hinic_close(struct net_device *netdev)
 	struct hinic_dev *nic_dev = netdev_priv(netdev);
 	unsigned int flags;
 
+	/* Disable txq napi firstly to aviod rewaking txq in free_tx_poll */
+	disable_txqs_napi(nic_dev);
+
 	down(&nic_dev->mgmt_lock);
 
 	flags = nic_dev->flags;
@@ -966,7 +990,7 @@ static void hinic_refresh_nic_cfg(struct hinic_dev *nic_dev)
  * @handle: nic device for the handler
  * @buf_in: input buffer
  * @in_size: input size
- * @buf_in: output buffer
+ * @buf_out: output buffer
  * @out_size: returned output size
  *
  * Return 0 - Success, negative - Failure
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_rx.c b/drivers/net/ethernet/huawei/hinic/hinic_rx.c
index f403a6711e97..070a7cc6392e 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_rx.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_rx.c
@@ -543,18 +543,25 @@ static int rx_request_irq(struct hinic_rxq *rxq)
 	if (err) {
 		netif_err(nic_dev, drv, rxq->netdev,
 			  "Failed to set RX interrupt coalescing attribute\n");
-		rx_del_napi(rxq);
-		return err;
+		goto err_req_irq;
 	}
 
 	err = request_irq(rq->irq, rx_irq, 0, rxq->irq_name, rxq);
-	if (err) {
-		rx_del_napi(rxq);
-		return err;
-	}
+	if (err)
+		goto err_req_irq;
 
 	cpumask_set_cpu(qp->q_id % num_online_cpus(), &rq->affinity_mask);
-	return irq_set_affinity_hint(rq->irq, &rq->affinity_mask);
+	err = irq_set_affinity_hint(rq->irq, &rq->affinity_mask);
+	if (err)
+		goto err_irq_affinity;
+
+	return 0;
+
+err_irq_affinity:
+	free_irq(rq->irq, rxq);
+err_req_irq:
+	rx_del_napi(rxq);
+	return err;
 }
 
 static void rx_free_irq(struct hinic_rxq *rxq)
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_tx.c b/drivers/net/ethernet/huawei/hinic/hinic_tx.c
index c249b7e6e432..8da7d46363b2 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_tx.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_tx.c
@@ -746,8 +746,8 @@ static int free_tx_poll(struct napi_struct *napi, int budget)
 		netdev_txq = netdev_get_tx_queue(txq->netdev, qp->q_id);
 
 		__netif_tx_lock(netdev_txq, smp_processor_id());
-
-		netif_wake_subqueue(nic_dev->netdev, qp->q_id);
+		if (!netif_testing(nic_dev->netdev))
+			netif_wake_subqueue(nic_dev->netdev, qp->q_id);
 
 		__netif_tx_unlock(netdev_txq);
 
@@ -774,18 +774,6 @@ static int free_tx_poll(struct napi_struct *napi, int budget)
 	return budget;
 }
 
-static void tx_napi_add(struct hinic_txq *txq, int weight)
-{
-	netif_napi_add(txq->netdev, &txq->napi, free_tx_poll, weight);
-	napi_enable(&txq->napi);
-}
-
-static void tx_napi_del(struct hinic_txq *txq)
-{
-	napi_disable(&txq->napi);
-	netif_napi_del(&txq->napi);
-}
-
 static irqreturn_t tx_irq(int irq, void *data)
 {
 	struct hinic_txq *txq = data;
@@ -819,7 +807,7 @@ static int tx_request_irq(struct hinic_txq *txq)
 
 	qp = container_of(sq, struct hinic_qp, sq);
 
-	tx_napi_add(txq, nic_dev->tx_weight);
+	netif_napi_add(txq->netdev, &txq->napi, free_tx_poll, nic_dev->tx_weight);
 
 	hinic_hwdev_msix_set(nic_dev->hwdev, sq->msix_entry,
 			     TX_IRQ_NO_PENDING, TX_IRQ_NO_COALESC,
@@ -836,14 +824,14 @@ static int tx_request_irq(struct hinic_txq *txq)
 	if (err) {
 		netif_err(nic_dev, drv, txq->netdev,
 			  "Failed to set TX interrupt coalescing attribute\n");
-		tx_napi_del(txq);
+		netif_napi_del(&txq->napi);
 		return err;
 	}
 
 	err = request_irq(sq->irq, tx_irq, 0, txq->irq_name, txq);
 	if (err) {
 		dev_err(&pdev->dev, "Failed to request Tx irq\n");
-		tx_napi_del(txq);
+		netif_napi_del(&txq->napi);
 		return err;
 	}
 
@@ -855,7 +843,7 @@ static void tx_free_irq(struct hinic_txq *txq)
 	struct hinic_sq *sq = txq->sq;
 
 	free_irq(sq->irq, txq);
-	tx_napi_del(txq);
+	netif_napi_del(&txq->napi);
 }
 
 /**
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 6d320be47e60..1f7fe6b3dd5a 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -97,11 +97,11 @@ static int pending_scrq(struct ibmvnic_adapter *,
 static union sub_crq *ibmvnic_next_scrq(struct ibmvnic_adapter *,
 					struct ibmvnic_sub_crq_queue *);
 static int ibmvnic_poll(struct napi_struct *napi, int data);
-static void send_map_query(struct ibmvnic_adapter *adapter);
+static void send_query_map(struct ibmvnic_adapter *adapter);
 static int send_request_map(struct ibmvnic_adapter *, dma_addr_t, __be32, u8);
 static int send_request_unmap(struct ibmvnic_adapter *, u8);
 static int send_login(struct ibmvnic_adapter *adapter);
-static void send_cap_queries(struct ibmvnic_adapter *adapter);
+static void send_query_cap(struct ibmvnic_adapter *adapter);
 static int init_sub_crqs(struct ibmvnic_adapter *);
 static int init_sub_crq_irqs(struct ibmvnic_adapter *adapter);
 static int ibmvnic_reset_init(struct ibmvnic_adapter *, bool reset);
@@ -882,7 +882,7 @@ static int ibmvnic_login(struct net_device *netdev)
 				   "Received partial success, retrying...\n");
 			adapter->init_done_rc = 0;
 			reinit_completion(&adapter->init_done);
-			send_cap_queries(adapter);
+			send_query_cap(adapter);
 			if (!wait_for_completion_timeout(&adapter->init_done,
 							 timeout)) {
 				netdev_warn(netdev,
@@ -1113,7 +1113,7 @@ static int init_resources(struct ibmvnic_adapter *adapter)
 	if (rc)
 		return rc;
 
-	send_map_query(adapter);
+	send_query_map(adapter);
 
 	rc = init_rx_pools(netdev);
 	if (rc)
@@ -2019,16 +2019,18 @@ static int do_reset(struct ibmvnic_adapter *adapter,
 
 		} else {
 			rc = reset_tx_pools(adapter);
-			if (rc)
+			if (rc) {
 				netdev_dbg(adapter->netdev, "reset tx pools failed (%d)\n",
 						rc);
 				goto out;
+			}
 
 			rc = reset_rx_pools(adapter);
-			if (rc)
+			if (rc) {
 				netdev_dbg(adapter->netdev, "reset rx pools failed (%d)\n",
 						rc);
 				goto out;
+			}
 		}
 		ibmvnic_disable_irqs(adapter);
 	}
@@ -3297,7 +3299,7 @@ tx_failed:
 	return -1;
 }
 
-static void ibmvnic_send_req_caps(struct ibmvnic_adapter *adapter, int retry)
+static void send_request_cap(struct ibmvnic_adapter *adapter, int retry)
 {
 	struct device *dev = &adapter->vdev->dev;
 	union ibmvnic_crq crq;
@@ -3823,7 +3825,7 @@ static int send_request_unmap(struct ibmvnic_adapter *adapter, u8 map_id)
 	return ibmvnic_send_crq(adapter, &crq);
 }
 
-static void send_map_query(struct ibmvnic_adapter *adapter)
+static void send_query_map(struct ibmvnic_adapter *adapter)
 {
 	union ibmvnic_crq crq;
 
@@ -3834,7 +3836,7 @@ static void send_map_query(struct ibmvnic_adapter *adapter)
 }
 
 /* Send a series of CRQs requesting various capabilities of the VNIC server */
-static void send_cap_queries(struct ibmvnic_adapter *adapter)
+static void send_query_cap(struct ibmvnic_adapter *adapter)
 {
 	union ibmvnic_crq crq;
 
@@ -3951,6 +3953,113 @@ static void send_cap_queries(struct ibmvnic_adapter *adapter)
 	ibmvnic_send_crq(adapter, &crq);
 }
 
+static void send_query_ip_offload(struct ibmvnic_adapter *adapter)
+{
+	int buf_sz = sizeof(struct ibmvnic_query_ip_offload_buffer);
+	struct device *dev = &adapter->vdev->dev;
+	union ibmvnic_crq crq;
+
+	adapter->ip_offload_tok =
+		dma_map_single(dev,
+			       &adapter->ip_offload_buf,
+			       buf_sz,
+			       DMA_FROM_DEVICE);
+
+	if (dma_mapping_error(dev, adapter->ip_offload_tok)) {
+		if (!firmware_has_feature(FW_FEATURE_CMO))
+			dev_err(dev, "Couldn't map offload buffer\n");
+		return;
+	}
+
+	memset(&crq, 0, sizeof(crq));
+	crq.query_ip_offload.first = IBMVNIC_CRQ_CMD;
+	crq.query_ip_offload.cmd = QUERY_IP_OFFLOAD;
+	crq.query_ip_offload.len = cpu_to_be32(buf_sz);
+	crq.query_ip_offload.ioba =
+	    cpu_to_be32(adapter->ip_offload_tok);
+
+	ibmvnic_send_crq(adapter, &crq);
+}
+
+static void send_control_ip_offload(struct ibmvnic_adapter *adapter)
+{
+	struct ibmvnic_control_ip_offload_buffer *ctrl_buf = &adapter->ip_offload_ctrl;
+	struct ibmvnic_query_ip_offload_buffer *buf = &adapter->ip_offload_buf;
+	struct device *dev = &adapter->vdev->dev;
+	netdev_features_t old_hw_features = 0;
+	union ibmvnic_crq crq;
+
+	adapter->ip_offload_ctrl_tok =
+		dma_map_single(dev,
+			       ctrl_buf,
+			       sizeof(adapter->ip_offload_ctrl),
+			       DMA_TO_DEVICE);
+
+	if (dma_mapping_error(dev, adapter->ip_offload_ctrl_tok)) {
+		dev_err(dev, "Couldn't map ip offload control buffer\n");
+		return;
+	}
+
+	ctrl_buf->len = cpu_to_be32(sizeof(adapter->ip_offload_ctrl));
+	ctrl_buf->version = cpu_to_be32(INITIAL_VERSION_IOB);
+	ctrl_buf->ipv4_chksum = buf->ipv4_chksum;
+	ctrl_buf->ipv6_chksum = buf->ipv6_chksum;
+	ctrl_buf->tcp_ipv4_chksum = buf->tcp_ipv4_chksum;
+	ctrl_buf->udp_ipv4_chksum = buf->udp_ipv4_chksum;
+	ctrl_buf->tcp_ipv6_chksum = buf->tcp_ipv6_chksum;
+	ctrl_buf->udp_ipv6_chksum = buf->udp_ipv6_chksum;
+	ctrl_buf->large_tx_ipv4 = buf->large_tx_ipv4;
+	ctrl_buf->large_tx_ipv6 = buf->large_tx_ipv6;
+
+	/* large_rx disabled for now, additional features needed */
+	ctrl_buf->large_rx_ipv4 = 0;
+	ctrl_buf->large_rx_ipv6 = 0;
+
+	if (adapter->state != VNIC_PROBING) {
+		old_hw_features = adapter->netdev->hw_features;
+		adapter->netdev->hw_features = 0;
+	}
+
+	adapter->netdev->hw_features = NETIF_F_SG | NETIF_F_GSO | NETIF_F_GRO;
+
+	if (buf->tcp_ipv4_chksum || buf->udp_ipv4_chksum)
+		adapter->netdev->hw_features |= NETIF_F_IP_CSUM;
+
+	if (buf->tcp_ipv6_chksum || buf->udp_ipv6_chksum)
+		adapter->netdev->hw_features |= NETIF_F_IPV6_CSUM;
+
+	if ((adapter->netdev->features &
+	    (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM)))
+		adapter->netdev->hw_features |= NETIF_F_RXCSUM;
+
+	if (buf->large_tx_ipv4)
+		adapter->netdev->hw_features |= NETIF_F_TSO;
+	if (buf->large_tx_ipv6)
+		adapter->netdev->hw_features |= NETIF_F_TSO6;
+
+	if (adapter->state == VNIC_PROBING) {
+		adapter->netdev->features |= adapter->netdev->hw_features;
+	} else if (old_hw_features != adapter->netdev->hw_features) {
+		netdev_features_t tmp = 0;
+
+		/* disable features no longer supported */
+		adapter->netdev->features &= adapter->netdev->hw_features;
+		/* turn on features now supported if previously enabled */
+		tmp = (old_hw_features ^ adapter->netdev->hw_features) &
+			adapter->netdev->hw_features;
+		adapter->netdev->features |=
+				tmp & adapter->netdev->wanted_features;
+	}
+
+	memset(&crq, 0, sizeof(crq));
+	crq.control_ip_offload.first = IBMVNIC_CRQ_CMD;
+	crq.control_ip_offload.cmd = CONTROL_IP_OFFLOAD;
+	crq.control_ip_offload.len =
+	    cpu_to_be32(sizeof(adapter->ip_offload_ctrl));
+	crq.control_ip_offload.ioba = cpu_to_be32(adapter->ip_offload_ctrl_tok);
+	ibmvnic_send_crq(adapter, &crq);
+}
+
 static void handle_vpd_size_rsp(union ibmvnic_crq *crq,
 				struct ibmvnic_adapter *adapter)
 {
@@ -4020,8 +4129,6 @@ static void handle_query_ip_offload_rsp(struct ibmvnic_adapter *adapter)
 {
 	struct device *dev = &adapter->vdev->dev;
 	struct ibmvnic_query_ip_offload_buffer *buf = &adapter->ip_offload_buf;
-	netdev_features_t old_hw_features = 0;
-	union ibmvnic_crq crq;
 	int i;
 
 	dma_unmap_single(dev, adapter->ip_offload_tok,
@@ -4071,74 +4178,7 @@ static void handle_query_ip_offload_rsp(struct ibmvnic_adapter *adapter)
 	netdev_dbg(adapter->netdev, "off_ipv6_ext_hd = %d\n",
 		   buf->off_ipv6_ext_headers);
 
-	adapter->ip_offload_ctrl_tok =
-	    dma_map_single(dev, &adapter->ip_offload_ctrl,
-			   sizeof(adapter->ip_offload_ctrl), DMA_TO_DEVICE);
-
-	if (dma_mapping_error(dev, adapter->ip_offload_ctrl_tok)) {
-		dev_err(dev, "Couldn't map ip offload control buffer\n");
-		return;
-	}
-
-	adapter->ip_offload_ctrl.len =
-	    cpu_to_be32(sizeof(adapter->ip_offload_ctrl));
-	adapter->ip_offload_ctrl.version = cpu_to_be32(INITIAL_VERSION_IOB);
-	adapter->ip_offload_ctrl.ipv4_chksum = buf->ipv4_chksum;
-	adapter->ip_offload_ctrl.ipv6_chksum = buf->ipv6_chksum;
-	adapter->ip_offload_ctrl.tcp_ipv4_chksum = buf->tcp_ipv4_chksum;
-	adapter->ip_offload_ctrl.udp_ipv4_chksum = buf->udp_ipv4_chksum;
-	adapter->ip_offload_ctrl.tcp_ipv6_chksum = buf->tcp_ipv6_chksum;
-	adapter->ip_offload_ctrl.udp_ipv6_chksum = buf->udp_ipv6_chksum;
-	adapter->ip_offload_ctrl.large_tx_ipv4 = buf->large_tx_ipv4;
-	adapter->ip_offload_ctrl.large_tx_ipv6 = buf->large_tx_ipv6;
-
-	/* large_rx disabled for now, additional features needed */
-	adapter->ip_offload_ctrl.large_rx_ipv4 = 0;
-	adapter->ip_offload_ctrl.large_rx_ipv6 = 0;
-
-	if (adapter->state != VNIC_PROBING) {
-		old_hw_features = adapter->netdev->hw_features;
-		adapter->netdev->hw_features = 0;
-	}
-
-	adapter->netdev->hw_features = NETIF_F_SG | NETIF_F_GSO | NETIF_F_GRO;
-
-	if (buf->tcp_ipv4_chksum || buf->udp_ipv4_chksum)
-		adapter->netdev->hw_features |= NETIF_F_IP_CSUM;
-
-	if (buf->tcp_ipv6_chksum || buf->udp_ipv6_chksum)
-		adapter->netdev->hw_features |= NETIF_F_IPV6_CSUM;
-
-	if ((adapter->netdev->features &
-	    (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM)))
-		adapter->netdev->hw_features |= NETIF_F_RXCSUM;
-
-	if (buf->large_tx_ipv4)
-		adapter->netdev->hw_features |= NETIF_F_TSO;
-	if (buf->large_tx_ipv6)
-		adapter->netdev->hw_features |= NETIF_F_TSO6;
-
-	if (adapter->state == VNIC_PROBING) {
-		adapter->netdev->features |= adapter->netdev->hw_features;
-	} else if (old_hw_features != adapter->netdev->hw_features) {
-		netdev_features_t tmp = 0;
-
-		/* disable features no longer supported */
-		adapter->netdev->features &= adapter->netdev->hw_features;
-		/* turn on features now supported if previously enabled */
-		tmp = (old_hw_features ^ adapter->netdev->hw_features) &
-			adapter->netdev->hw_features;
-		adapter->netdev->features |=
-				tmp & adapter->netdev->wanted_features;
-	}
-
-	memset(&crq, 0, sizeof(crq));
-	crq.control_ip_offload.first = IBMVNIC_CRQ_CMD;
-	crq.control_ip_offload.cmd = CONTROL_IP_OFFLOAD;
-	crq.control_ip_offload.len =
-	    cpu_to_be32(sizeof(adapter->ip_offload_ctrl));
-	crq.control_ip_offload.ioba = cpu_to_be32(adapter->ip_offload_ctrl_tok);
-	ibmvnic_send_crq(adapter, &crq);
+	send_control_ip_offload(adapter);
 }
 
 static const char *ibmvnic_fw_err_cause(u16 cause)
@@ -4264,7 +4304,7 @@ static void handle_request_cap_rsp(union ibmvnic_crq *crq,
 				be64_to_cpu(crq->request_capability_rsp.number);
 		}
 
-		ibmvnic_send_req_caps(adapter, 1);
+		send_request_cap(adapter, 1);
 		return;
 	default:
 		dev_err(dev, "Error %d in request cap rsp\n",
@@ -4274,30 +4314,8 @@ static void handle_request_cap_rsp(union ibmvnic_crq *crq,
 
 	/* Done receiving requested capabilities, query IP offload support */
 	if (atomic_read(&adapter->running_cap_crqs) == 0) {
-		union ibmvnic_crq newcrq;
-		int buf_sz = sizeof(struct ibmvnic_query_ip_offload_buffer);
-		struct ibmvnic_query_ip_offload_buffer *ip_offload_buf =
-		    &adapter->ip_offload_buf;
-
 		adapter->wait_capability = false;
-		adapter->ip_offload_tok = dma_map_single(dev, ip_offload_buf,
-							 buf_sz,
-							 DMA_FROM_DEVICE);
-
-		if (dma_mapping_error(dev, adapter->ip_offload_tok)) {
-			if (!firmware_has_feature(FW_FEATURE_CMO))
-				dev_err(dev, "Couldn't map offload buffer\n");
-			return;
-		}
-
-		memset(&newcrq, 0, sizeof(newcrq));
-		newcrq.query_ip_offload.first = IBMVNIC_CRQ_CMD;
-		newcrq.query_ip_offload.cmd = QUERY_IP_OFFLOAD;
-		newcrq.query_ip_offload.len = cpu_to_be32(buf_sz);
-		newcrq.query_ip_offload.ioba =
-		    cpu_to_be32(adapter->ip_offload_tok);
-
-		ibmvnic_send_crq(adapter, &newcrq);
+		send_query_ip_offload(adapter);
 	}
 }
 
@@ -4580,7 +4598,7 @@ static void handle_query_cap_rsp(union ibmvnic_crq *crq,
 out:
 	if (atomic_read(&adapter->running_cap_crqs) == 0) {
 		adapter->wait_capability = false;
-		ibmvnic_send_req_caps(adapter, 0);
+		send_request_cap(adapter, 0);
 	}
 }
 
@@ -4635,7 +4653,7 @@ static int handle_query_phys_parms_rsp(union ibmvnic_crq *crq,
 	case IBMVNIC_1GBPS:
 		adapter->speed = SPEED_1000;
 		break;
-	case IBMVNIC_10GBP:
+	case IBMVNIC_10GBPS:
 		adapter->speed = SPEED_10000;
 		break;
 	case IBMVNIC_25GBPS:
@@ -4650,6 +4668,9 @@ static int handle_query_phys_parms_rsp(union ibmvnic_crq *crq,
 	case IBMVNIC_100GBPS:
 		adapter->speed = SPEED_100000;
 		break;
+	case IBMVNIC_200GBPS:
+		adapter->speed = SPEED_200000;
+		break;
 	default:
 		if (netif_carrier_ok(netdev))
 			netdev_warn(netdev, "Unknown speed 0x%08x\n", rspeed);
@@ -4745,7 +4766,7 @@ static void ibmvnic_handle_crq(union ibmvnic_crq *crq,
 			    be16_to_cpu(crq->version_exchange_rsp.version);
 		dev_info(dev, "Partner protocol version is %d\n",
 			 ibmvnic_version);
-		send_cap_queries(adapter);
+		send_query_cap(adapter);
 		break;
 	case QUERY_CAPABILITY_RSP:
 		handle_query_cap_rsp(crq, adapter);
diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h
index 8da98794eda9..217dcc7ded70 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.h
+++ b/drivers/net/ethernet/ibm/ibmvnic.h
@@ -373,7 +373,7 @@ struct ibmvnic_phys_parms {
 #define IBMVNIC_10MBPS		0x40000000
 #define IBMVNIC_100MBPS		0x20000000
 #define IBMVNIC_1GBPS		0x10000000
-#define IBMVNIC_10GBP		0x08000000
+#define IBMVNIC_10GBPS		0x08000000
 #define IBMVNIC_40GBPS		0x04000000
 #define IBMVNIC_100GBPS		0x02000000
 #define IBMVNIC_25GBPS		0x01000000
diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c
index 36da059388dc..8cc651d37a7f 100644
--- a/drivers/net/ethernet/intel/e100.c
+++ b/drivers/net/ethernet/intel/e100.c
@@ -384,7 +384,7 @@ enum cb_status {
 	cb_ok       = 0x2000,
 };
 
-/**
+/*
  * cb_command - Command Block flags
  * @cb_tx_nc:  0: controller does CRC (normal),  1: CRC from skb memory
  */
@@ -1531,7 +1531,7 @@ static int e100_hw_init(struct nic *nic)
 	e100_hw_reset(nic);
 
 	netif_err(nic, hw, nic->netdev, "e100_hw_init\n");
-	if (!in_interrupt() && (err = e100_self_test(nic)))
+	if ((err = e100_self_test(nic)))
 		return err;
 
 	if ((err = e100_phy_init(nic)))
@@ -2155,7 +2155,7 @@ static int e100_rx_alloc_list(struct nic *nic)
 	nic->rx_to_use = nic->rx_to_clean = NULL;
 	nic->ru_running = RU_UNINITIALIZED;
 
-	if (!(nic->rxs = kcalloc(count, sizeof(struct rx), GFP_ATOMIC)))
+	if (!(nic->rxs = kcalloc(count, sizeof(struct rx), GFP_KERNEL)))
 		return -ENOMEM;
 
 	for (rx = nic->rxs, i = 0; i < count; rx++, i++) {
@@ -2593,7 +2593,7 @@ static void e100_diag_test(struct net_device *netdev,
 {
 	struct ethtool_cmd cmd;
 	struct nic *nic = netdev_priv(netdev);
-	int i, err;
+	int i;
 
 	memset(data, 0, E100_TEST_LEN * sizeof(u64));
 	data[0] = !mii_link_ok(&nic->mii);
@@ -2601,7 +2601,7 @@ static void e100_diag_test(struct net_device *netdev,
 	if (test->flags & ETH_TEST_FL_OFFLINE) {
 
 		/* save speed, duplex & autoneg settings */
-		err = mii_ethtool_gset(&nic->mii, &cmd);
+		mii_ethtool_gset(&nic->mii, &cmd);
 
 		if (netif_running(netdev))
 			e100_down(nic);
@@ -2610,7 +2610,7 @@ static void e100_diag_test(struct net_device *netdev,
 		data[4] = e100_loopback_test(nic, lb_phy);
 
 		/* restore speed, duplex & autoneg settings */
-		err = mii_ethtool_sset(&nic->mii, &cmd);
+		mii_ethtool_sset(&nic->mii, &cmd);
 
 		if (netif_running(netdev))
 			e100_up(nic);
diff --git a/drivers/net/ethernet/intel/e1000/e1000_hw.c b/drivers/net/ethernet/intel/e1000/e1000_hw.c
index f1dbd7b8ee32..fb5af23880c3 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_hw.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_hw.c
@@ -376,7 +376,6 @@ s32 e1000_reset_hw(struct e1000_hw *hw)
 {
 	u32 ctrl;
 	u32 ctrl_ext;
-	u32 icr;
 	u32 manc;
 	u32 led_ctrl;
 	s32 ret_val;
@@ -501,7 +500,7 @@ s32 e1000_reset_hw(struct e1000_hw *hw)
 	ew32(IMC, 0xffffffff);
 
 	/* Clear any pending interrupt events. */
-	icr = er32(ICR);
+	er32(ICR);
 
 	/* If MWI was previously enabled, reenable it. */
 	if (hw->mac_type == e1000_82542_rev2_0) {
@@ -1896,7 +1895,6 @@ void e1000_config_collision_dist(struct e1000_hw *hw)
 /**
  * e1000_config_mac_to_phy - sync phy and mac settings
  * @hw: Struct containing variables accessed by shared code
- * @mii_reg: data to write to the MII control register
  *
  * Sets MAC speed and duplex settings to reflect the those in the PHY
  * The contents of the PHY register containing the needed information need to
@@ -2369,16 +2367,13 @@ static s32 e1000_check_for_serdes_link_generic(struct e1000_hw *hw)
  */
 s32 e1000_check_for_link(struct e1000_hw *hw)
 {
-	u32 rxcw = 0;
-	u32 ctrl;
 	u32 status;
 	u32 rctl;
 	u32 icr;
-	u32 signal = 0;
 	s32 ret_val;
 	u16 phy_data;
 
-	ctrl = er32(CTRL);
+	er32(CTRL);
 	status = er32(STATUS);
 
 	/* On adapters with a MAC newer than 82544, SW Definable pin 1 will be
@@ -2387,12 +2382,9 @@ s32 e1000_check_for_link(struct e1000_hw *hw)
 	 */
 	if ((hw->media_type == e1000_media_type_fiber) ||
 	    (hw->media_type == e1000_media_type_internal_serdes)) {
-		rxcw = er32(RXCW);
+		er32(RXCW);
 
 		if (hw->media_type == e1000_media_type_fiber) {
-			signal =
-			    (hw->mac_type >
-			     e1000_82544) ? E1000_CTRL_SWDPIN1 : 0;
 			if (status & E1000_STATUS_LU)
 				hw->get_link_status = false;
 		}
@@ -2921,7 +2913,7 @@ static s32 e1000_read_phy_reg_ex(struct e1000_hw *hw, u32 reg_addr,
  *
  * @hw: Struct containing variables accessed by shared code
  * @reg_addr: address of the PHY register to write
- * @data: data to write to the PHY
+ * @phy_data: data to write to the PHY
  *
  * Writes a value to a PHY register
  */
@@ -4674,78 +4666,76 @@ s32 e1000_led_off(struct e1000_hw *hw)
  */
 static void e1000_clear_hw_cntrs(struct e1000_hw *hw)
 {
-	volatile u32 temp;
-
-	temp = er32(CRCERRS);
-	temp = er32(SYMERRS);
-	temp = er32(MPC);
-	temp = er32(SCC);
-	temp = er32(ECOL);
-	temp = er32(MCC);
-	temp = er32(LATECOL);
-	temp = er32(COLC);
-	temp = er32(DC);
-	temp = er32(SEC);
-	temp = er32(RLEC);
-	temp = er32(XONRXC);
-	temp = er32(XONTXC);
-	temp = er32(XOFFRXC);
-	temp = er32(XOFFTXC);
-	temp = er32(FCRUC);
-
-	temp = er32(PRC64);
-	temp = er32(PRC127);
-	temp = er32(PRC255);
-	temp = er32(PRC511);
-	temp = er32(PRC1023);
-	temp = er32(PRC1522);
-
-	temp = er32(GPRC);
-	temp = er32(BPRC);
-	temp = er32(MPRC);
-	temp = er32(GPTC);
-	temp = er32(GORCL);
-	temp = er32(GORCH);
-	temp = er32(GOTCL);
-	temp = er32(GOTCH);
-	temp = er32(RNBC);
-	temp = er32(RUC);
-	temp = er32(RFC);
-	temp = er32(ROC);
-	temp = er32(RJC);
-	temp = er32(TORL);
-	temp = er32(TORH);
-	temp = er32(TOTL);
-	temp = er32(TOTH);
-	temp = er32(TPR);
-	temp = er32(TPT);
-
-	temp = er32(PTC64);
-	temp = er32(PTC127);
-	temp = er32(PTC255);
-	temp = er32(PTC511);
-	temp = er32(PTC1023);
-	temp = er32(PTC1522);
-
-	temp = er32(MPTC);
-	temp = er32(BPTC);
+	er32(CRCERRS);
+	er32(SYMERRS);
+	er32(MPC);
+	er32(SCC);
+	er32(ECOL);
+	er32(MCC);
+	er32(LATECOL);
+	er32(COLC);
+	er32(DC);
+	er32(SEC);
+	er32(RLEC);
+	er32(XONRXC);
+	er32(XONTXC);
+	er32(XOFFRXC);
+	er32(XOFFTXC);
+	er32(FCRUC);
+
+	er32(PRC64);
+	er32(PRC127);
+	er32(PRC255);
+	er32(PRC511);
+	er32(PRC1023);
+	er32(PRC1522);
+
+	er32(GPRC);
+	er32(BPRC);
+	er32(MPRC);
+	er32(GPTC);
+	er32(GORCL);
+	er32(GORCH);
+	er32(GOTCL);
+	er32(GOTCH);
+	er32(RNBC);
+	er32(RUC);
+	er32(RFC);
+	er32(ROC);
+	er32(RJC);
+	er32(TORL);
+	er32(TORH);
+	er32(TOTL);
+	er32(TOTH);
+	er32(TPR);
+	er32(TPT);
+
+	er32(PTC64);
+	er32(PTC127);
+	er32(PTC255);
+	er32(PTC511);
+	er32(PTC1023);
+	er32(PTC1522);
+
+	er32(MPTC);
+	er32(BPTC);
 
 	if (hw->mac_type < e1000_82543)
 		return;
 
-	temp = er32(ALGNERRC);
-	temp = er32(RXERRC);
-	temp = er32(TNCRS);
-	temp = er32(CEXTERR);
-	temp = er32(TSCTC);
-	temp = er32(TSCTFC);
+	er32(ALGNERRC);
+	er32(RXERRC);
+	er32(TNCRS);
+	er32(CEXTERR);
+	er32(TSCTC);
+	er32(TSCTFC);
 
 	if (hw->mac_type <= e1000_82544)
 		return;
 
-	temp = er32(MGTPRC);
-	temp = er32(MGTPDC);
-	temp = er32(MGTPTC);
+	er32(MGTPRC);
+	er32(MGTPDC);
+	er32(MGTPTC);
 }
 
 /**
@@ -4777,8 +4767,6 @@ void e1000_reset_adaptive(struct e1000_hw *hw)
 /**
  * e1000_update_adaptive - update adaptive IFS
  * @hw: Struct containing variables accessed by shared code
- * @tx_packets: Number of transmits since last callback
- * @total_collisions: Number of collisions since last callback
  *
  * Called during the callback/watchdog routine to update IFS value based on
  * the ratio of transmits to collisions.
@@ -5063,8 +5051,6 @@ static s32 e1000_check_polarity(struct e1000_hw *hw,
 /**
  * e1000_check_downshift - Check if Downshift occurred
  * @hw: Struct containing variables accessed by shared code
- * @downshift: output parameter : 0 - No Downshift occurred.
- *                                1 - Downshift occurred.
  *
  * returns: - E1000_ERR_XXX
  *            E1000_SUCCESS
diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c
index 1e6ec081fd9d..5e28cf4fa2cd 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_main.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_main.c
@@ -199,8 +199,10 @@ module_param(debug, int, 0);
 MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)");
 
 /**
- * e1000_get_hw_dev - return device
- * used by hardware layer to print debugging information
+ * e1000_get_hw_dev - helper function for getting netdev
+ * @hw: pointer to HW struct
+ *
+ * return device used by hardware layer to print debugging information
  *
  **/
 struct net_device *e1000_get_hw_dev(struct e1000_hw *hw)
@@ -354,7 +356,7 @@ static void e1000_release_manageability(struct e1000_adapter *adapter)
 
 /**
  * e1000_configure - configure the hardware for RX and TX
- * @adapter = private board structure
+ * @adapter: private board structure
  **/
 static void e1000_configure(struct e1000_adapter *adapter)
 {
@@ -534,7 +536,6 @@ void e1000_down(struct e1000_adapter *adapter)
 
 void e1000_reinit_locked(struct e1000_adapter *adapter)
 {
-	WARN_ON(in_interrupt());
 	while (test_and_set_bit(__E1000_RESETTING, &adapter->flags))
 		msleep(1);
 
@@ -3489,8 +3490,9 @@ exit:
 /**
  * e1000_tx_timeout - Respond to a Tx Hang
  * @netdev: network interface device structure
+ * @txqueue: number of the Tx queue that hung (unused)
  **/
-static void e1000_tx_timeout(struct net_device *netdev, unsigned int txqueue)
+static void e1000_tx_timeout(struct net_device *netdev, unsigned int __always_unused txqueue)
 {
 	struct e1000_adapter *adapter = netdev_priv(netdev);
 
@@ -3787,7 +3789,8 @@ static irqreturn_t e1000_intr(int irq, void *data)
 
 /**
  * e1000_clean - NAPI Rx polling callback
- * @adapter: board private structure
+ * @napi: napi struct containing references to driver info
+ * @budget: budget given to driver for receive packets
  **/
 static int e1000_clean(struct napi_struct *napi, int budget)
 {
@@ -3818,6 +3821,7 @@ static int e1000_clean(struct napi_struct *napi, int budget)
 /**
  * e1000_clean_tx_irq - Reclaim resources after transmit completes
  * @adapter: board private structure
+ * @tx_ring: ring to clean
  **/
 static bool e1000_clean_tx_irq(struct e1000_adapter *adapter,
 			       struct e1000_tx_ring *tx_ring)
@@ -3933,7 +3937,7 @@ static bool e1000_clean_tx_irq(struct e1000_adapter *adapter,
  * @adapter:     board private structure
  * @status_err:  receive descriptor status and error fields
  * @csum:        receive descriptor csum field
- * @sk_buff:     socket buffer with received data
+ * @skb:         socket buffer with received data
  **/
 static void e1000_rx_checksum(struct e1000_adapter *adapter, u32 status_err,
 			      u32 csum, struct sk_buff *skb)
@@ -3970,6 +3974,9 @@ static void e1000_rx_checksum(struct e1000_adapter *adapter, u32 status_err,
 
 /**
  * e1000_consume_page - helper function for jumbo Rx path
+ * @bi: software descriptor shadow data
+ * @skb: skb being modified
+ * @length: length of data being added
  **/
 static void e1000_consume_page(struct e1000_rx_buffer *bi, struct sk_buff *skb,
 			       u16 length)
@@ -4003,6 +4010,7 @@ static void e1000_receive_skb(struct e1000_adapter *adapter, u8 status,
 /**
  * e1000_tbi_adjust_stats
  * @hw: Struct containing variables accessed by shared code
+ * @stats: point to stats struct
  * @frame_len: The length of the frame in question
  * @mac_addr: The Ethernet destination address of the frame in question
  *
@@ -4548,6 +4556,8 @@ e1000_alloc_jumbo_rx_buffers(struct e1000_adapter *adapter,
 /**
  * e1000_alloc_rx_buffers - Replace used receive buffers; legacy & extended
  * @adapter: address of board private structure
+ * @rx_ring: pointer to ring struct
+ * @cleaned_count: number of new Rx buffers to try to allocate
  **/
 static void e1000_alloc_rx_buffers(struct e1000_adapter *adapter,
 				   struct e1000_rx_ring *rx_ring,
@@ -4662,7 +4672,7 @@ static void e1000_alloc_rx_buffers(struct e1000_adapter *adapter,
 
 /**
  * e1000_smartspeed - Workaround for SmartSpeed on 82541 and 82547 controllers.
- * @adapter:
+ * @adapter: address of board private structure
  **/
 static void e1000_smartspeed(struct e1000_adapter *adapter)
 {
@@ -4718,10 +4728,10 @@ static void e1000_smartspeed(struct e1000_adapter *adapter)
 }
 
 /**
- * e1000_ioctl -
- * @netdev:
- * @ifreq:
- * @cmd:
+ * e1000_ioctl - handle ioctl calls
+ * @netdev: pointer to our netdev
+ * @ifr: pointer to interface request structure
+ * @cmd: ioctl data
  **/
 static int e1000_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
 {
@@ -4737,9 +4747,9 @@ static int e1000_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
 
 /**
  * e1000_mii_ioctl -
- * @netdev:
- * @ifreq:
- * @cmd:
+ * @netdev: pointer to our netdev
+ * @ifr: pointer to interface request structure
+ * @cmd: ioctl data
  **/
 static int e1000_mii_ioctl(struct net_device *netdev, struct ifreq *ifr,
 			   int cmd)
diff --git a/drivers/net/ethernet/intel/e1000e/80003es2lan.c b/drivers/net/ethernet/intel/e1000e/80003es2lan.c
index 4b103cca8a39..be9c695dde12 100644
--- a/drivers/net/ethernet/intel/e1000e/80003es2lan.c
+++ b/drivers/net/ethernet/intel/e1000e/80003es2lan.c
@@ -1072,7 +1072,6 @@ static s32 e1000_setup_copper_link_80003es2lan(struct e1000_hw *hw)
 /**
  *  e1000_cfg_on_link_up_80003es2lan - es2 link configuration after link-up
  *  @hw: pointer to the HW structure
- *  @duplex: current duplex setting
  *
  *  Configure the KMRN interface by applying last minute quirks for
  *  10/100 operation.
diff --git a/drivers/net/ethernet/intel/e1000e/ethtool.c b/drivers/net/ethernet/intel/e1000e/ethtool.c
index a8fc9208382c..03215b0aee4b 100644
--- a/drivers/net/ethernet/intel/e1000e/ethtool.c
+++ b/drivers/net/ethernet/intel/e1000e/ethtool.c
@@ -895,6 +895,7 @@ static int e1000_reg_test(struct e1000_adapter *adapter, u64 *data)
 	case e1000_pch_cnp:
 	case e1000_pch_tgp:
 	case e1000_pch_adp:
+	case e1000_pch_mtp:
 		mask |= BIT(18);
 		break;
 	default:
@@ -1560,6 +1561,7 @@ static void e1000_loopback_cleanup(struct e1000_adapter *adapter)
 	case e1000_pch_cnp:
 	case e1000_pch_tgp:
 	case e1000_pch_adp:
+	case e1000_pch_mtp:
 		fext_nvm11 = er32(FEXTNVM11);
 		fext_nvm11 &= ~E1000_FEXTNVM11_DISABLE_MULR_FIX;
 		ew32(FEXTNVM11, fext_nvm11);
diff --git a/drivers/net/ethernet/intel/e1000e/hw.h b/drivers/net/ethernet/intel/e1000e/hw.h
index b1447221669e..69a2329ea463 100644
--- a/drivers/net/ethernet/intel/e1000e/hw.h
+++ b/drivers/net/ethernet/intel/e1000e/hw.h
@@ -102,6 +102,10 @@ struct e1000_hw;
 #define E1000_DEV_ID_PCH_ADP_I219_V16		0x1A1F
 #define E1000_DEV_ID_PCH_ADP_I219_LM17		0x1A1C
 #define E1000_DEV_ID_PCH_ADP_I219_V17		0x1A1D
+#define E1000_DEV_ID_PCH_MTP_I219_LM18		0x550A
+#define E1000_DEV_ID_PCH_MTP_I219_V18		0x550B
+#define E1000_DEV_ID_PCH_MTP_I219_LM19		0x550C
+#define E1000_DEV_ID_PCH_MTP_I219_V19		0x550D
 
 #define E1000_REVISION_4	4
 
@@ -127,6 +131,7 @@ enum e1000_mac_type {
 	e1000_pch_cnp,
 	e1000_pch_tgp,
 	e1000_pch_adp,
+	e1000_pch_mtp,
 };
 
 enum e1000_media_type {
diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c
index b2f2fcfdf732..9aa6fad8ed47 100644
--- a/drivers/net/ethernet/intel/e1000e/ich8lan.c
+++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c
@@ -320,6 +320,7 @@ static s32 e1000_init_phy_workarounds_pchlan(struct e1000_hw *hw)
 	case e1000_pch_cnp:
 	case e1000_pch_tgp:
 	case e1000_pch_adp:
+	case e1000_pch_mtp:
 		if (e1000_phy_is_accessible_pchlan(hw))
 			break;
 
@@ -464,6 +465,7 @@ static s32 e1000_init_phy_params_pchlan(struct e1000_hw *hw)
 		case e1000_pch_cnp:
 		case e1000_pch_tgp:
 		case e1000_pch_adp:
+		case e1000_pch_mtp:
 			/* In case the PHY needs to be in mdio slow mode,
 			 * set slow mode and try to get the PHY id again.
 			 */
@@ -708,6 +710,7 @@ static s32 e1000_init_mac_params_ich8lan(struct e1000_hw *hw)
 	case e1000_pch_cnp:
 	case e1000_pch_tgp:
 	case e1000_pch_adp:
+	case e1000_pch_mtp:
 	case e1000_pchlan:
 		/* check management mode */
 		mac->ops.check_mng_mode = e1000_check_mng_mode_pchlan;
@@ -743,7 +746,7 @@ static s32 e1000_init_mac_params_ich8lan(struct e1000_hw *hw)
 /**
  *  __e1000_access_emi_reg_locked - Read/write EMI register
  *  @hw: pointer to the HW structure
- *  @addr: EMI address to program
+ *  @address: EMI address to program
  *  @data: pointer to value to read/write from/to the EMI address
  *  @read: boolean flag to indicate read or write
  *
@@ -1648,6 +1651,7 @@ static s32 e1000_get_variants_ich8lan(struct e1000_adapter *adapter)
 	case e1000_pch_cnp:
 	case e1000_pch_tgp:
 	case e1000_pch_adp:
+	case e1000_pch_mtp:
 		rc = e1000_init_phy_params_pchlan(hw);
 		break;
 	default:
@@ -2102,6 +2106,7 @@ static s32 e1000_sw_lcd_config_ich8lan(struct e1000_hw *hw)
 	case e1000_pch_cnp:
 	case e1000_pch_tgp:
 	case e1000_pch_adp:
+	case e1000_pch_mtp:
 		sw_cfg_mask = E1000_FEXTNVM_SW_CONFIG_ICH8M;
 		break;
 	default:
@@ -2266,7 +2271,7 @@ release:
 /**
  *  e1000_configure_k1_ich8lan - Configure K1 power state
  *  @hw: pointer to the HW structure
- *  @enable: K1 state to configure
+ *  @k1_enable: K1 state to configure
  *
  *  Configure the K1 power state based on the provided parameter.
  *  Assumes semaphore already acquired.
@@ -2405,8 +2410,10 @@ static s32 e1000_set_mdio_slow_mode_hv(struct e1000_hw *hw)
 }
 
 /**
- *  e1000_hv_phy_workarounds_ich8lan - A series of Phy workarounds to be
- *  done after every PHY reset.
+ *  e1000_hv_phy_workarounds_ich8lan - apply PHY workarounds
+ *  @hw: pointer to the HW structure
+ *
+ *  A series of PHY workarounds to be done after every PHY reset.
  **/
 static s32 e1000_hv_phy_workarounds_ich8lan(struct e1000_hw *hw)
 {
@@ -2694,8 +2701,10 @@ s32 e1000_lv_jumbo_workaround_ich8lan(struct e1000_hw *hw, bool enable)
 }
 
 /**
- *  e1000_lv_phy_workarounds_ich8lan - A series of Phy workarounds to be
- *  done after every PHY reset.
+ *  e1000_lv_phy_workarounds_ich8lan - apply ich8 specific workarounds
+ *  @hw: pointer to the HW structure
+ *
+ *  A series of PHY workarounds to be done after every PHY reset.
  **/
 static s32 e1000_lv_phy_workarounds_ich8lan(struct e1000_hw *hw)
 {
@@ -3141,6 +3150,7 @@ static s32 e1000_valid_nvm_bank_detect_ich8lan(struct e1000_hw *hw, u32 *bank)
 	case e1000_pch_cnp:
 	case e1000_pch_tgp:
 	case e1000_pch_adp:
+	case e1000_pch_mtp:
 		bank1_offset = nvm->flash_bank_size;
 		act_offset = E1000_ICH_NVM_SIG_WORD;
 
@@ -4086,6 +4096,7 @@ static s32 e1000_validate_nvm_checksum_ich8lan(struct e1000_hw *hw)
 	case e1000_pch_cnp:
 	case e1000_pch_tgp:
 	case e1000_pch_adp:
+	case e1000_pch_mtp:
 		word = NVM_COMPAT;
 		valid_csum_mask = NVM_COMPAT_VALID_CSUM;
 		break;
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 664e8ccc88d2..b30f00891c03 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -501,6 +501,7 @@ rx_ring_summary:
 
 /**
  * e1000_desc_unused - calculate if we have unused descriptors
+ * @ring: pointer to ring struct to perform calculation on
  **/
 static int e1000_desc_unused(struct e1000_ring *ring)
 {
@@ -577,6 +578,7 @@ static void e1000e_rx_hwtstamp(struct e1000_adapter *adapter, u32 status,
 /**
  * e1000_receive_skb - helper function to handle Rx indications
  * @adapter: board private structure
+ * @netdev: pointer to netdev struct
  * @staterr: descriptor extended error and status field as written by hardware
  * @vlan: descriptor vlan field as written by hardware (no le/be conversion)
  * @skb: pointer to sk_buff to be indicated to stack
@@ -601,8 +603,7 @@ static void e1000_receive_skb(struct e1000_adapter *adapter,
  * e1000_rx_checksum - Receive Checksum Offload
  * @adapter: board private structure
  * @status_err: receive descriptor status and error fields
- * @csum: receive descriptor csum field
- * @sk_buff: socket buffer with received data
+ * @skb: socket buffer with received data
  **/
 static void e1000_rx_checksum(struct e1000_adapter *adapter, u32 status_err,
 			      struct sk_buff *skb)
@@ -673,6 +674,8 @@ static void e1000e_update_tdt_wa(struct e1000_ring *tx_ring, unsigned int i)
 /**
  * e1000_alloc_rx_buffers - Replace used receive buffers
  * @rx_ring: Rx descriptor ring
+ * @cleaned_count: number to reallocate
+ * @gfp: flags for allocation
  **/
 static void e1000_alloc_rx_buffers(struct e1000_ring *rx_ring,
 				   int cleaned_count, gfp_t gfp)
@@ -741,6 +744,8 @@ map_skb:
 /**
  * e1000_alloc_rx_buffers_ps - Replace used receive buffers; packet split
  * @rx_ring: Rx descriptor ring
+ * @cleaned_count: number to reallocate
+ * @gfp: flags for allocation
  **/
 static void e1000_alloc_rx_buffers_ps(struct e1000_ring *rx_ring,
 				      int cleaned_count, gfp_t gfp)
@@ -844,6 +849,7 @@ no_buffers:
  * e1000_alloc_jumbo_rx_buffers - Replace used jumbo receive buffers
  * @rx_ring: Rx descriptor ring
  * @cleaned_count: number of buffers to allocate this pass
+ * @gfp: flags for allocation
  **/
 
 static void e1000_alloc_jumbo_rx_buffers(struct e1000_ring *rx_ring,
@@ -933,6 +939,8 @@ static inline void e1000_rx_hash(struct net_device *netdev, __le32 rss,
 /**
  * e1000_clean_rx_irq - Send received data up the network stack
  * @rx_ring: Rx descriptor ring
+ * @work_done: output parameter for indicating completed work
+ * @work_to_do: how many packets we can clean
  *
  * the return value indicates whether actual cleaning was done, there
  * is no guarantee that everything was cleaned
@@ -1327,6 +1335,8 @@ static bool e1000_clean_tx_irq(struct e1000_ring *tx_ring)
 /**
  * e1000_clean_rx_irq_ps - Send received data up the network stack; packet split
  * @rx_ring: Rx descriptor ring
+ * @work_done: output parameter for indicating completed work
+ * @work_to_do: how many packets we can clean
  *
  * the return value indicates whether actual cleaning was done, there
  * is no guarantee that everything was cleaned
@@ -1517,9 +1527,6 @@ next_desc:
 	return cleaned;
 }
 
-/**
- * e1000_consume_page - helper function
- **/
 static void e1000_consume_page(struct e1000_buffer *bi, struct sk_buff *skb,
 			       u16 length)
 {
@@ -1531,7 +1538,9 @@ static void e1000_consume_page(struct e1000_buffer *bi, struct sk_buff *skb,
 
 /**
  * e1000_clean_jumbo_rx_irq - Send received data up the network stack; legacy
- * @adapter: board private structure
+ * @rx_ring: Rx descriptor ring
+ * @work_done: output parameter for indicating completed work
+ * @work_to_do: how many packets we can clean
  *
  * the return value indicates whether actual cleaning was done, there
  * is no guarantee that everything was cleaned
@@ -1994,6 +2003,7 @@ static irqreturn_t e1000_intr_msix_rx(int __always_unused irq, void *data)
 
 /**
  * e1000_configure_msix - Configure MSI-X hardware
+ * @adapter: board private structure
  *
  * e1000_configure_msix sets up the hardware to properly
  * generate MSI-X interrupts.
@@ -2072,6 +2082,7 @@ void e1000e_reset_interrupt_capability(struct e1000_adapter *adapter)
 
 /**
  * e1000e_set_interrupt_capability - set MSI or MSI-X if supported
+ * @adapter: board private structure
  *
  * Attempt to configure interrupts using the best available
  * capabilities of the hardware and kernel.
@@ -2127,6 +2138,7 @@ void e1000e_set_interrupt_capability(struct e1000_adapter *adapter)
 
 /**
  * e1000_request_msix - Initialize MSI-X interrupts
+ * @adapter: board private structure
  *
  * e1000_request_msix allocates MSI-X vectors and requests interrupts from the
  * kernel.
@@ -2180,6 +2192,7 @@ static int e1000_request_msix(struct e1000_adapter *adapter)
 
 /**
  * e1000_request_irq - initialize interrupts
+ * @adapter: board private structure
  *
  * Attempts to configure interrupts using the best available
  * capabilities of the hardware and kernel.
@@ -2240,6 +2253,7 @@ static void e1000_free_irq(struct e1000_adapter *adapter)
 
 /**
  * e1000_irq_disable - Mask off interrupt generation on the NIC
+ * @adapter: board private structure
  **/
 static void e1000_irq_disable(struct e1000_adapter *adapter)
 {
@@ -2262,6 +2276,7 @@ static void e1000_irq_disable(struct e1000_adapter *adapter)
 
 /**
  * e1000_irq_enable - Enable default interrupt generation settings
+ * @adapter: board private structure
  **/
 static void e1000_irq_enable(struct e1000_adapter *adapter)
 {
@@ -2332,6 +2347,8 @@ void e1000e_release_hw_control(struct e1000_adapter *adapter)
 
 /**
  * e1000_alloc_ring_dma - allocate memory for a ring structure
+ * @adapter: board private structure
+ * @ring: ring struct for which to allocate dma
  **/
 static int e1000_alloc_ring_dma(struct e1000_adapter *adapter,
 				struct e1000_ring *ring)
@@ -2507,7 +2524,6 @@ void e1000e_free_rx_resources(struct e1000_ring *rx_ring)
 
 /**
  * e1000_update_itr - update the dynamic ITR value based on statistics
- * @adapter: pointer to adapter
  * @itr_setting: current adapter->itr
  * @packets: the number of packets during this measurement interval
  * @bytes: the number of bytes during this measurement interval
@@ -3049,12 +3065,13 @@ static void e1000_configure_tx(struct e1000_adapter *adapter)
 	}
 }
 
+#define PAGE_USE_COUNT(S) (((S) >> PAGE_SHIFT) + \
+			   (((S) & (PAGE_SIZE - 1)) ? 1 : 0))
+
 /**
  * e1000_setup_rctl - configure the receive control registers
  * @adapter: Board private structure
  **/
-#define PAGE_USE_COUNT(S) (((S) >> PAGE_SHIFT) + \
-			   (((S) & (PAGE_SIZE - 1)) ? 1 : 0))
 static void e1000_setup_rctl(struct e1000_adapter *adapter)
 {
 	struct e1000_hw *hw = &adapter->hw;
@@ -3570,6 +3587,7 @@ s32 e1000e_get_base_timinca(struct e1000_adapter *adapter, u32 *timinca)
 	case e1000_pch_cnp:
 	case e1000_pch_tgp:
 	case e1000_pch_adp:
+	case e1000_pch_mtp:
 		if (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI) {
 			/* Stable 24MHz frequency */
 			incperiod = INCPERIOD_24MHZ;
@@ -3605,6 +3623,7 @@ s32 e1000e_get_base_timinca(struct e1000_adapter *adapter, u32 *timinca)
 /**
  * e1000e_config_hwtstamp - configure the hwtstamp registers and enable/disable
  * @adapter: board private structure
+ * @config: timestamp configuration
  *
  * Outgoing time stamping can be enabled and disabled. Play nice and
  * disable it when requested, although it shouldn't cause any overhead
@@ -3808,6 +3827,7 @@ void e1000e_power_up_phy(struct e1000_adapter *adapter)
 
 /**
  * e1000_power_down_phy - Power down the PHY
+ * @adapter: board private structure
  *
  * Power down the PHY so no link is implied when interface is down.
  * The PHY cannot be powered down if management or WoL is active.
@@ -3820,6 +3840,7 @@ static void e1000_power_down_phy(struct e1000_adapter *adapter)
 
 /**
  * e1000_flush_tx_ring - remove all descriptors from the tx_ring
+ * @adapter: board private structure
  *
  * We want to clear all pending descriptors from the TX ring.
  * zeroing happens when the HW reads the regs. We  assign the ring itself as
@@ -3854,6 +3875,7 @@ static void e1000_flush_tx_ring(struct e1000_adapter *adapter)
 
 /**
  * e1000_flush_rx_ring - remove all descriptors from the rx_ring
+ * @adapter: board private structure
  *
  * Mark all descriptors in the RX ring as consumed and disable the rx ring
  */
@@ -3886,6 +3908,7 @@ static void e1000_flush_rx_ring(struct e1000_adapter *adapter)
 
 /**
  * e1000_flush_desc_rings - remove all descriptors from the descriptor rings
+ * @adapter: board private structure
  *
  * In i219, the descriptor rings must be emptied before resetting the HW
  * or before changing the device state to D3 during runtime (runtime PM).
@@ -3968,6 +3991,7 @@ static void e1000e_systim_reset(struct e1000_adapter *adapter)
 
 /**
  * e1000e_reset - bring the hardware into a known good state
+ * @adapter: board private structure
  *
  * This function boots the hardware and enables some settings that
  * require a configuration cycle of the hardware - those cannot be
@@ -4081,6 +4105,7 @@ void e1000e_reset(struct e1000_adapter *adapter)
 	case e1000_pch_cnp:
 	case e1000_pch_tgp:
 	case e1000_pch_adp:
+	case e1000_pch_mtp:
 		fc->refresh_time = 0xFFFF;
 		fc->pause_time = 0xFFFF;
 
@@ -4847,7 +4872,7 @@ static void e1000e_update_phy_task(struct work_struct *work)
 
 /**
  * e1000_update_phy_info - timre call-back to update PHY info
- * @data: pointer to adapter cast into an unsigned long
+ * @t: pointer to timer_list containing private info adapter
  *
  * Need to wait a few seconds after link up to get diagnostic information from
  * the phy
@@ -5187,7 +5212,7 @@ static void e1000e_check_82574_phy_workaround(struct e1000_adapter *adapter)
 
 /**
  * e1000_watchdog - Timer Call-back
- * @data: pointer to adapter cast into an unsigned long
+ * @t: pointer to timer_list containing private info adapter
  **/
 static void e1000_watchdog(struct timer_list *t)
 {
@@ -5972,8 +5997,9 @@ static netdev_tx_t e1000_xmit_frame(struct sk_buff *skb,
 /**
  * e1000_tx_timeout - Respond to a Tx Hang
  * @netdev: network interface device structure
+ * @txqueue: index of the hung queue (unused)
  **/
-static void e1000_tx_timeout(struct net_device *netdev, unsigned int txqueue)
+static void e1000_tx_timeout(struct net_device *netdev, unsigned int __always_unused txqueue)
 {
 	struct e1000_adapter *adapter = netdev_priv(netdev);
 
@@ -6174,7 +6200,7 @@ static int e1000_mii_ioctl(struct net_device *netdev, struct ifreq *ifr,
 /**
  * e1000e_hwtstamp_ioctl - control hardware time stamping
  * @netdev: network interface device structure
- * @ifreq: interface request
+ * @ifr: interface request
  *
  * Outgoing time stamping can be enabled and disabled. Play nice and
  * disable it when requested, although it shouldn't cause any overhead
@@ -7853,6 +7879,10 @@ static const struct pci_device_id e1000_pci_tbl[] = {
 	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_V16), board_pch_cnp },
 	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_LM17), board_pch_cnp },
 	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_V17), board_pch_cnp },
+	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_LM18), board_pch_cnp },
+	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_V18), board_pch_cnp },
+	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_LM19), board_pch_cnp },
+	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_V19), board_pch_cnp },
 
 	{ 0, 0, 0, 0, 0, 0, 0 }	/* terminate list */
 };
diff --git a/drivers/net/ethernet/intel/e1000e/phy.c b/drivers/net/ethernet/intel/e1000e/phy.c
index e11c877595fb..bdd9dc163f15 100644
--- a/drivers/net/ethernet/intel/e1000e/phy.c
+++ b/drivers/net/ethernet/intel/e1000e/phy.c
@@ -2311,6 +2311,7 @@ s32 e1000e_determine_phy_address(struct e1000_hw *hw)
 /**
  *  e1000_get_phy_addr_for_bm_page - Retrieve PHY page address
  *  @page: page to access
+ *  @reg: register to check
  *
  *  Returns the phy address for the page requested.
  **/
@@ -2728,6 +2729,7 @@ void e1000_power_down_phy_copper(struct e1000_hw *hw)
  *  @offset: register offset to be read
  *  @data: pointer to the read data
  *  @locked: semaphore has already been acquired or not
+ *  @page_set: BM_WUC_PAGE already set and access enabled
  *
  *  Acquires semaphore, if necessary, then reads the PHY register at offset
  *  and stores the retrieved information in data.  Release any acquired
@@ -2836,6 +2838,7 @@ s32 e1000_read_phy_reg_page_hv(struct e1000_hw *hw, u32 offset, u16 *data)
  *  @offset: register offset to write to
  *  @data: data to write at register offset
  *  @locked: semaphore has already been acquired or not
+ *  @page_set: BM_WUC_PAGE already set and access enabled
  *
  *  Acquires semaphore, if necessary, then writes the data to PHY register
  *  at the offset.  Release any acquired semaphores before exiting.
diff --git a/drivers/net/ethernet/intel/e1000e/ptp.c b/drivers/net/ethernet/intel/e1000e/ptp.c
index 34b988d70488..f3f671311855 100644
--- a/drivers/net/ethernet/intel/e1000e/ptp.c
+++ b/drivers/net/ethernet/intel/e1000e/ptp.c
@@ -144,7 +144,7 @@ static int e1000e_phc_get_syncdevicetime(ktime_t *device,
 /**
  * e1000e_phc_getsynctime - Reads the current system/device cross timestamp
  * @ptp: ptp clock structure
- * @cts: structure containing timestamp
+ * @xtstamp: structure containing timestamp
  *
  * Read device and system (ART) clock simultaneously and return the scaled
  * clock values in ns.
@@ -297,6 +297,7 @@ void e1000e_ptp_init(struct e1000_adapter *adapter)
 	case e1000_pch_cnp:
 	case e1000_pch_tgp:
 	case e1000_pch_adp:
+	case e1000_pch_mtp:
 		if ((hw->mac.type < e1000_pch_lpt) ||
 		    (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI)) {
 			adapter->ptp_clock_info.max_adj = 24000000 - 1;
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c
index 140212bfe08b..9e3103fae723 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c
@@ -221,8 +221,6 @@ static bool fm10k_prepare_for_reset(struct fm10k_intfc *interface)
 {
 	struct net_device *netdev = interface->netdev;
 
-	WARN_ON(in_interrupt());
-
 	/* put off any impending NetWatchDogTimeout */
 	netif_trans_update(netdev);
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index ada0e93c38f0..537300e762f0 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -35,6 +35,7 @@
 #include <net/pkt_cls.h>
 #include <net/tc_act/tc_gact.h>
 #include <net/tc_act/tc_mirred.h>
+#include <net/udp_tunnel.h>
 #include <net/xdp_sock.h>
 #include "i40e_type.h"
 #include "i40e_prototype.h"
@@ -133,7 +134,6 @@ enum i40e_state_t {
 	__I40E_PORT_SUSPENDED,
 	__I40E_VF_DISABLE,
 	__I40E_MACVLAN_SYNC_PENDING,
-	__I40E_UDP_FILTER_SYNC_PENDING,
 	__I40E_TEMP_LINK_POLLING,
 	__I40E_CLIENT_SERVICE_REQUESTED,
 	__I40E_CLIENT_L2_CHANGE,
@@ -478,8 +478,8 @@ struct i40e_pf {
 	struct list_head l3_flex_pit_list;
 	struct list_head l4_flex_pit_list;
 
-	struct i40e_udp_port_config udp_ports[I40E_MAX_PF_UDP_OFFLOAD_PORTS];
-	u16 pending_udp_bitmap;
+	struct udp_tunnel_nic_shared udp_tunnel_shared;
+	struct udp_tunnel_nic_info udp_tunnel_nic;
 
 	struct hlist_head cloud_filter_list;
 	u16 num_cloud_filters;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.h b/drivers/net/ethernet/intel/i40e/i40e_adminq.h
index edec3df78971..ee394aacef4d 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.h
@@ -85,8 +85,8 @@ struct i40e_adminq_info {
 
 /**
  * i40e_aq_rc_to_posix - convert errors to user-land codes
- * aq_ret: AdminQ handler error code can override aq_rc
- * aq_rc: AdminQ firmware error code to convert
+ * @aq_ret: AdminQ handler error code can override aq_rc
+ * @aq_rc: AdminQ firmware error code to convert
  **/
 static inline int i40e_aq_rc_to_posix(int aq_ret, int aq_rc)
 {
diff --git a/drivers/net/ethernet/intel/i40e/i40e_client.c b/drivers/net/ethernet/intel/i40e/i40e_client.c
index befd3018183f..a2dba32383f6 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_client.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_client.c
@@ -278,8 +278,6 @@ void i40e_client_update_msix_info(struct i40e_pf *pf)
 /**
  * i40e_client_add_instance - add a client instance struct to the instance list
  * @pf: pointer to the board struct
- * @client: pointer to a client struct in the client list.
- * @existing: if there was already an existing instance
  *
  **/
 static void i40e_client_add_instance(struct i40e_pf *pf)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c
index 6ab52cbd697a..adc9e4fa4789 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_common.c
@@ -3766,9 +3766,7 @@ i40e_status i40e_aq_stop_lldp(struct i40e_hw *hw, bool shutdown_agent,
 /**
  * i40e_aq_start_lldp
  * @hw: pointer to the hw struct
- * @buff: buffer for result
  * @persist: True if start of LLDP should be persistent across power cycles
- * @buff_size: buffer size
  * @cmd_details: pointer to command details structure or NULL
  *
  * Start the embedded LLDP Agent on all ports.
@@ -5395,6 +5393,7 @@ static void i40e_mdio_if_number_selection(struct i40e_hw *hw, bool set_mdio,
  * @hw: pointer to the hw struct
  * @phy_select: select which phy should be accessed
  * @dev_addr: PHY device address
+ * @page_change: flag to indicate if phy page should be updated
  * @set_mdio: use MDIO I/F number specified by mdio_num
  * @mdio_num: MDIO I/F number
  * @reg_addr: PHY register address
@@ -5439,6 +5438,7 @@ enum i40e_status_code i40e_aq_set_phy_register_ext(struct i40e_hw *hw,
  * @hw: pointer to the hw struct
  * @phy_select: select which phy should be accessed
  * @dev_addr: PHY device address
+ * @page_change: flag to indicate if phy page should be updated
  * @set_mdio: use MDIO I/F number specified by mdio_num
  * @mdio_num: MDIO I/F number
  * @reg_addr: PHY register address
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 07207e21874f..929c64789119 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -287,6 +287,7 @@ void i40e_service_event_schedule(struct i40e_pf *pf)
 /**
  * i40e_tx_timeout - Respond to a Tx Hang
  * @netdev: network interface device structure
+ * @txqueue: queue number timing out
  *
  * If any port has noticed a Tx timeout, it is likely that the whole
  * device is munged, not just the one netdev port, so go for the full
@@ -1609,6 +1610,8 @@ static int i40e_set_mac(struct net_device *netdev, void *p)
  * i40e_config_rss_aq - Prepare for RSS using AQ commands
  * @vsi: vsi structure
  * @seed: RSS hash seed
+ * @lut: pointer to lookup table of lut_size
+ * @lut_size: size of the lookup table
  **/
 static int i40e_config_rss_aq(struct i40e_vsi *vsi, const u8 *seed,
 			      u8 *lut, u16 lut_size)
@@ -5815,7 +5818,6 @@ static int i40e_vsi_reconfig_rss(struct i40e_vsi *vsi, u16 rss_size)
 /**
  * i40e_channel_setup_queue_map - Setup a channel queue map
  * @pf: ptr to PF device
- * @vsi: the VSI being setup
  * @ctxt: VSI context structure
  * @ch: ptr to channel structure
  *
@@ -6058,8 +6060,7 @@ static inline int i40e_setup_hw_channel(struct i40e_pf *pf,
 /**
  * i40e_setup_channel - setup new channel using uplink element
  * @pf: ptr to PF device
- * @type: type of channel to be created (VMDq2/VF)
- * @uplink_seid: underlying HW switching element (VEB) ID
+ * @vsi: pointer to the VSI to set up the channel within
  * @ch: ptr to channel structure
  *
  * Setup new channel (VSI) based on specified type (VMDq2/VF)
@@ -6690,7 +6691,6 @@ static void i40e_vsi_reinit_locked(struct i40e_vsi *vsi)
 {
 	struct i40e_pf *pf = vsi->back;
 
-	WARN_ON(in_interrupt());
 	while (test_and_set_bit(__I40E_CONFIG_BUSY, pf->state))
 		usleep_range(1000, 2000);
 	i40e_down(vsi);
@@ -7780,7 +7780,7 @@ int i40e_add_del_cloud_filter_big_buf(struct i40e_vsi *vsi,
 /**
  * i40e_parse_cls_flower - Parse tc flower filters provided by kernel
  * @vsi: Pointer to VSI
- * @cls_flower: Pointer to struct flow_cls_offload
+ * @f: Pointer to struct flow_cls_offload
  * @filter: Pointer to cloud filter structure
  *
  **/
@@ -8161,8 +8161,8 @@ static int i40e_delete_clsflower(struct i40e_vsi *vsi,
 
 /**
  * i40e_setup_tc_cls_flower - flower classifier offloads
- * @netdev: net device to configure
- * @type_data: offload data
+ * @np: net device to configure
+ * @cls_flower: offload data
  **/
 static int i40e_setup_tc_cls_flower(struct i40e_netdev_priv *np,
 				    struct flow_cls_offload *cls_flower)
@@ -8463,9 +8463,6 @@ void i40e_do_reset(struct i40e_pf *pf, u32 reset_flags, bool lock_acquired)
 {
 	u32 val;
 
-	WARN_ON(in_interrupt());
-
-
 	/* do the biggest reset indicated */
 	if (reset_flags & BIT_ULL(__I40E_GLOBAL_RESET_REQUESTED)) {
 
@@ -9586,6 +9583,7 @@ end_reconstitute:
 /**
  * i40e_get_capabilities - get info about the HW
  * @pf: the PF struct
+ * @list_type: AQ capability to be queried
  **/
 static int i40e_get_capabilities(struct i40e_pf *pf,
 				 enum i40e_admin_queue_opc list_type)
@@ -10384,106 +10382,6 @@ static void i40e_handle_mdd_event(struct i40e_pf *pf)
 	i40e_flush(hw);
 }
 
-static const char *i40e_tunnel_name(u8 type)
-{
-	switch (type) {
-	case UDP_TUNNEL_TYPE_VXLAN:
-		return "vxlan";
-	case UDP_TUNNEL_TYPE_GENEVE:
-		return "geneve";
-	default:
-		return "unknown";
-	}
-}
-
-/**
- * i40e_sync_udp_filters - Trigger a sync event for existing UDP filters
- * @pf: board private structure
- **/
-static void i40e_sync_udp_filters(struct i40e_pf *pf)
-{
-	int i;
-
-	/* loop through and set pending bit for all active UDP filters */
-	for (i = 0; i < I40E_MAX_PF_UDP_OFFLOAD_PORTS; i++) {
-		if (pf->udp_ports[i].port)
-			pf->pending_udp_bitmap |= BIT_ULL(i);
-	}
-
-	set_bit(__I40E_UDP_FILTER_SYNC_PENDING, pf->state);
-}
-
-/**
- * i40e_sync_udp_filters_subtask - Sync the VSI filter list with HW
- * @pf: board private structure
- **/
-static void i40e_sync_udp_filters_subtask(struct i40e_pf *pf)
-{
-	struct i40e_hw *hw = &pf->hw;
-	u8 filter_index, type;
-	u16 port;
-	int i;
-
-	if (!test_and_clear_bit(__I40E_UDP_FILTER_SYNC_PENDING, pf->state))
-		return;
-
-	/* acquire RTNL to maintain state of flags and port requests */
-	rtnl_lock();
-
-	for (i = 0; i < I40E_MAX_PF_UDP_OFFLOAD_PORTS; i++) {
-		if (pf->pending_udp_bitmap & BIT_ULL(i)) {
-			struct i40e_udp_port_config *udp_port;
-			i40e_status ret = 0;
-
-			udp_port = &pf->udp_ports[i];
-			pf->pending_udp_bitmap &= ~BIT_ULL(i);
-
-			port = READ_ONCE(udp_port->port);
-			type = READ_ONCE(udp_port->type);
-			filter_index = READ_ONCE(udp_port->filter_index);
-
-			/* release RTNL while we wait on AQ command */
-			rtnl_unlock();
-
-			if (port)
-				ret = i40e_aq_add_udp_tunnel(hw, port,
-							     type,
-							     &filter_index,
-							     NULL);
-			else if (filter_index != I40E_UDP_PORT_INDEX_UNUSED)
-				ret = i40e_aq_del_udp_tunnel(hw, filter_index,
-							     NULL);
-
-			/* reacquire RTNL so we can update filter_index */
-			rtnl_lock();
-
-			if (ret) {
-				dev_info(&pf->pdev->dev,
-					 "%s %s port %d, index %d failed, err %s aq_err %s\n",
-					 i40e_tunnel_name(type),
-					 port ? "add" : "delete",
-					 port,
-					 filter_index,
-					 i40e_stat_str(&pf->hw, ret),
-					 i40e_aq_str(&pf->hw,
-						     pf->hw.aq.asq_last_status));
-				if (port) {
-					/* failed to add, just reset port,
-					 * drop pending bit for any deletion
-					 */
-					udp_port->port = 0;
-					pf->pending_udp_bitmap &= ~BIT_ULL(i);
-				}
-			} else if (port) {
-				/* record filter index on success */
-				udp_port->filter_index = filter_index;
-			}
-		}
-	}
-
-	rtnl_unlock();
-}
-
 /**
  * i40e_service_task - Run the driver's async subtasks
  * @work: pointer to work_struct containing our data
@@ -10523,7 +10421,6 @@ static void i40e_service_task(struct work_struct *work)
 								pf->vsi[pf->lan_vsi]);
 		}
 		i40e_sync_filters_subtask(pf);
-		i40e_sync_udp_filters_subtask(pf);
 	} else {
 		i40e_reset_subtask(pf);
 	}
@@ -10547,7 +10444,7 @@ static void i40e_service_task(struct work_struct *work)
 
 /**
  * i40e_service_timer - timer callback
- * @data: pointer to PF struct
+ * @t: timer list pointer
  **/
 static void i40e_service_timer(struct timer_list *t)
 {
@@ -12223,131 +12120,48 @@ static int i40e_set_features(struct net_device *netdev,
 	return 0;
 }
 
-/**
- * i40e_get_udp_port_idx - Lookup a possibly offloaded for Rx UDP port
- * @pf: board private structure
- * @port: The UDP port to look up
- *
- * Returns the index number or I40E_MAX_PF_UDP_OFFLOAD_PORTS if port not found
- **/
-static u8 i40e_get_udp_port_idx(struct i40e_pf *pf, u16 port)
-{
-	u8 i;
-
-	for (i = 0; i < I40E_MAX_PF_UDP_OFFLOAD_PORTS; i++) {
-		/* Do not report ports with pending deletions as
-		 * being available.
-		 */
-		if (!port && (pf->pending_udp_bitmap & BIT_ULL(i)))
-			continue;
-		if (pf->udp_ports[i].port == port)
-			return i;
-	}
-
-	return i;
-}
-
-/**
- * i40e_udp_tunnel_add - Get notifications about UDP tunnel ports that come up
- * @netdev: This physical port's netdev
- * @ti: Tunnel endpoint information
- **/
-static void i40e_udp_tunnel_add(struct net_device *netdev,
-				struct udp_tunnel_info *ti)
+static int i40e_udp_tunnel_set_port(struct net_device *netdev,
+				    unsigned int table, unsigned int idx,
+				    struct udp_tunnel_info *ti)
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
-	struct i40e_vsi *vsi = np->vsi;
-	struct i40e_pf *pf = vsi->back;
-	u16 port = ntohs(ti->port);
-	u8 next_idx;
-	u8 idx;
-
-	idx = i40e_get_udp_port_idx(pf, port);
-
-	/* Check if port already exists */
-	if (idx < I40E_MAX_PF_UDP_OFFLOAD_PORTS) {
-		netdev_info(netdev, "port %d already offloaded\n", port);
-		return;
-	}
-
-	/* Now check if there is space to add the new port */
-	next_idx = i40e_get_udp_port_idx(pf, 0);
+	struct i40e_hw *hw = &np->vsi->back->hw;
+	u8 type, filter_index;
+	i40e_status ret;
 
-	if (next_idx == I40E_MAX_PF_UDP_OFFLOAD_PORTS) {
-		netdev_info(netdev, "maximum number of offloaded UDP ports reached, not adding port %d\n",
-			    port);
-		return;
-	}
+	type = ti->type == UDP_TUNNEL_TYPE_VXLAN ? I40E_AQC_TUNNEL_TYPE_VXLAN :
+						   I40E_AQC_TUNNEL_TYPE_NGE;
 
-	switch (ti->type) {
-	case UDP_TUNNEL_TYPE_VXLAN:
-		pf->udp_ports[next_idx].type = I40E_AQC_TUNNEL_TYPE_VXLAN;
-		break;
-	case UDP_TUNNEL_TYPE_GENEVE:
-		if (!(pf->hw_features & I40E_HW_GENEVE_OFFLOAD_CAPABLE))
-			return;
-		pf->udp_ports[next_idx].type = I40E_AQC_TUNNEL_TYPE_NGE;
-		break;
-	default:
-		return;
+	ret = i40e_aq_add_udp_tunnel(hw, ntohs(ti->port), type, &filter_index,
+				     NULL);
+	if (ret) {
+		netdev_info(netdev, "add UDP port failed, err %s aq_err %s\n",
+			    i40e_stat_str(hw, ret),
+			    i40e_aq_str(hw, hw->aq.asq_last_status));
+		return -EIO;
 	}
 
-	/* New port: add it and mark its index in the bitmap */
-	pf->udp_ports[next_idx].port = port;
-	pf->udp_ports[next_idx].filter_index = I40E_UDP_PORT_INDEX_UNUSED;
-	pf->pending_udp_bitmap |= BIT_ULL(next_idx);
-	set_bit(__I40E_UDP_FILTER_SYNC_PENDING, pf->state);
+	udp_tunnel_nic_set_port_priv(netdev, table, idx, filter_index);
+	return 0;
 }
 
-/**
- * i40e_udp_tunnel_del - Get notifications about UDP tunnel ports that go away
- * @netdev: This physical port's netdev
- * @ti: Tunnel endpoint information
- **/
-static void i40e_udp_tunnel_del(struct net_device *netdev,
-				struct udp_tunnel_info *ti)
+static int i40e_udp_tunnel_unset_port(struct net_device *netdev,
+				      unsigned int table, unsigned int idx,
+				      struct udp_tunnel_info *ti)
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
-	struct i40e_vsi *vsi = np->vsi;
-	struct i40e_pf *pf = vsi->back;
-	u16 port = ntohs(ti->port);
-	u8 idx;
-
-	idx = i40e_get_udp_port_idx(pf, port);
-
-	/* Check if port already exists */
-	if (idx >= I40E_MAX_PF_UDP_OFFLOAD_PORTS)
-		goto not_found;
+	struct i40e_hw *hw = &np->vsi->back->hw;
+	i40e_status ret;
 
-	switch (ti->type) {
-	case UDP_TUNNEL_TYPE_VXLAN:
-		if (pf->udp_ports[idx].type != I40E_AQC_TUNNEL_TYPE_VXLAN)
-			goto not_found;
-		break;
-	case UDP_TUNNEL_TYPE_GENEVE:
-		if (pf->udp_ports[idx].type != I40E_AQC_TUNNEL_TYPE_NGE)
-			goto not_found;
-		break;
-	default:
-		goto not_found;
+	ret = i40e_aq_del_udp_tunnel(hw, ti->hw_priv, NULL);
+	if (ret) {
+		netdev_info(netdev, "delete UDP port failed, err %s aq_err %s\n",
+			    i40e_stat_str(hw, ret),
+			    i40e_aq_str(hw, hw->aq.asq_last_status));
+		return -EIO;
 	}
 
-	/* if port exists, set it to 0 (mark for deletion)
-	 * and make it pending
-	 */
-	pf->udp_ports[idx].port = 0;
-
-	/* Toggle pending bit instead of setting it. This way if we are
-	 * deleting a port that has yet to be added we just clear the pending
-	 * bit and don't have to worry about it.
-	 */
-	pf->pending_udp_bitmap ^= BIT_ULL(idx);
-	set_bit(__I40E_UDP_FILTER_SYNC_PENDING, pf->state);
-
-	return;
-not_found:
-	netdev_warn(netdev, "UDP port %d was not found, not deleting\n",
-		    port);
+	return 0;
 }
 
 static int i40e_get_phys_port_id(struct net_device *netdev,
@@ -12374,6 +12188,7 @@ static int i40e_get_phys_port_id(struct net_device *netdev,
  * @addr: the MAC address entry being added
  * @vid: VLAN ID
  * @flags: instructions from stack about fdb operation
+ * @extack: netlink extended ack, unused currently
  */
 static int i40e_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 			    struct net_device *dev,
@@ -12952,8 +12767,8 @@ static const struct net_device_ops i40e_netdev_ops = {
 	.ndo_set_vf_link_state	= i40e_ndo_set_vf_link_state,
 	.ndo_set_vf_spoofchk	= i40e_ndo_set_vf_spoofchk,
 	.ndo_set_vf_trust	= i40e_ndo_set_vf_trust,
-	.ndo_udp_tunnel_add	= i40e_udp_tunnel_add,
-	.ndo_udp_tunnel_del	= i40e_udp_tunnel_del,
+	.ndo_udp_tunnel_add	= udp_tunnel_nic_add_port,
+	.ndo_udp_tunnel_del	= udp_tunnel_nic_del_port,
 	.ndo_get_phys_port_id	= i40e_get_phys_port_id,
 	.ndo_fdb_add		= i40e_ndo_fdb_add,
 	.ndo_features_check	= i40e_features_check,
@@ -13017,6 +12832,8 @@ static int i40e_config_netdev(struct i40e_vsi *vsi)
 	if (!(pf->hw_features & I40E_HW_OUTER_UDP_CSUM_CAPABLE))
 		netdev->gso_partial_features |= NETIF_F_GSO_UDP_TUNNEL_CSUM;
 
+	netdev->udp_tunnel_nic_info = &pf->udp_tunnel_nic;
+
 	netdev->gso_partial_features |= NETIF_F_GSO_GRE_CSUM;
 
 	netdev->hw_enc_features |= hw_enc_features;
@@ -14417,7 +14234,7 @@ static int i40e_setup_pf_switch(struct i40e_pf *pf, bool reinit)
 	i40e_ptp_init(pf);
 
 	/* repopulate tunnel port filters */
-	i40e_sync_udp_filters(pf);
+	udp_tunnel_nic_reset_ntf(pf->vsi[pf->lan_vsi]->netdev);
 
 	return ret;
 }
@@ -15146,6 +14963,14 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (err)
 		goto err_switch_setup;
 
+	pf->udp_tunnel_nic.set_port = i40e_udp_tunnel_set_port;
+	pf->udp_tunnel_nic.unset_port = i40e_udp_tunnel_unset_port;
+	pf->udp_tunnel_nic.flags = UDP_TUNNEL_NIC_INFO_MAY_SLEEP;
+	pf->udp_tunnel_nic.shared = &pf->udp_tunnel_shared;
+	pf->udp_tunnel_nic.tables[0].n_entries = I40E_MAX_PF_UDP_OFFLOAD_PORTS;
+	pf->udp_tunnel_nic.tables[0].tunnel_types = UDP_TUNNEL_TYPE_VXLAN |
+						    UDP_TUNNEL_TYPE_GENEVE;
+
 	/* The number of VSIs reported by the FW is the minimum guaranteed
 	 * to us; HW supports far more and we share the remaining pool with
 	 * the other PFs. We allocate space for more than the guarantee with
@@ -15155,6 +14980,12 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		pf->num_alloc_vsi = I40E_MIN_VSI_ALLOC;
 	else
 		pf->num_alloc_vsi = pf->hw.func_caps.num_vsis;
+	if (pf->num_alloc_vsi > UDP_TUNNEL_NIC_MAX_SHARING_DEVICES) {
+		dev_warn(&pf->pdev->dev,
+			 "limiting the VSI count due to UDP tunnel limitation %d > %d\n",
+			 pf->num_alloc_vsi, UDP_TUNNEL_NIC_MAX_SHARING_DEVICES);
+		pf->num_alloc_vsi = UDP_TUNNEL_NIC_MAX_SHARING_DEVICES;
+	}
 
 	/* Set up the *vsi struct and our local tracking of the MAIN PF vsi. */
 	pf->vsi = kcalloc(pf->num_alloc_vsi, sizeof(struct i40e_vsi *),
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ptp.c b/drivers/net/ethernet/intel/i40e/i40e_ptp.c
index ff7b19c6bc73..7a879614ca55 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ptp.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ptp.c
@@ -259,7 +259,6 @@ static u32 i40e_ptp_get_rx_events(struct i40e_pf *pf)
 /**
  * i40e_ptp_rx_hang - Detect error case when Rx timestamp registers are hung
  * @pf: The PF private data structure
- * @vsi: The VSI with the rings relevant to 1588
  *
  * This watchdog task is scheduled to detect error case where hardware has
  * dropped an Rx packet that was timestamped when the ring is full. The
diff --git a/drivers/net/ethernet/intel/i40e/i40e_trace.h b/drivers/net/ethernet/intel/i40e/i40e_trace.h
index 983f8b98b275..b5b12299931f 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_trace.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_trace.h
@@ -22,7 +22,7 @@
 
 #include <linux/tracepoint.h>
 
-/**
+/*
  * i40e_trace() macro enables shared code to refer to trace points
  * like:
  *
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 1606ba5318f7..d43ce13a93c9 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -1755,7 +1755,6 @@ static inline void i40e_rx_hash(struct i40e_ring *ring,
  * @rx_ring: rx descriptor ring packet is being transacted on
  * @rx_desc: pointer to the EOP Rx descriptor
  * @skb: pointer to current skb being populated
- * @rx_ptype: the packet type decoded by hardware
  *
  * This function checks the ring, descriptor, and packet information in
  * order to populate the hash, checksum, VLAN, protocol, and
@@ -3512,7 +3511,7 @@ dma_error:
 
 /**
  * i40e_xmit_xdp_ring - transmits an XDP buffer to an XDP Tx ring
- * @xdp: data to transmit
+ * @xdpf: data to transmit
  * @xdp_ring: XDP Tx ring
  **/
 static int i40e_xmit_xdp_ring(struct xdp_frame *xdpf,
@@ -3707,7 +3706,9 @@ netdev_tx_t i40e_lan_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
 /**
  * i40e_xdp_xmit - Implements ndo_xdp_xmit
  * @dev: netdev
- * @xdp: XDP buffer
+ * @n: number of frames
+ * @frames: array of XDP buffer pointers
+ * @flags: XDP extra info
  *
  * Returns number of frames successfully sent. Frames that fail are
  * free'ed via XDP return API.
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
index 66c2b92c0d10..2feed920ef8a 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
@@ -482,7 +482,6 @@ static inline u32 i40e_get_head(struct i40e_ring *tx_ring)
 /**
  * i40e_xmit_descriptor_count - calculate number of Tx descriptors needed
  * @skb:     send buffer
- * @tx_ring: ring to send buffer on
  *
  * Returns number of data descriptors needed for this skb. Returns 0 to indicate
  * there is not enough descriptors available in this ring since we need at least
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h b/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h
index 1397dd3c1c57..19da3b22160f 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h
@@ -21,9 +21,9 @@ void i40e_release_rx_desc(struct i40e_ring *rx_ring, u32 val);
 #define I40E_XDP_TX		BIT(1)
 #define I40E_XDP_REDIR		BIT(2)
 
-/**
+/*
  * build_ctob - Builds the Tx descriptor (cmd, offset and type) qword
- **/
+ */
 static inline __le64 build_ctob(u32 td_cmd, u32 td_offset, unsigned int size,
 				u32 td_tag)
 {
@@ -37,7 +37,7 @@ static inline __le64 build_ctob(u32 td_cmd, u32 td_offset, unsigned int size,
 /**
  * i40e_update_tx_stats - Update the egress statistics for the Tx ring
  * @tx_ring: Tx ring to update
- * @total_packet: total packets sent
+ * @total_packets: total packets sent
  * @total_bytes: total bytes sent
  **/
 static inline void i40e_update_tx_stats(struct i40e_ring *tx_ring,
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index 8e133d6545bd..c96e2f2d4cba 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -1115,7 +1115,7 @@ static int i40e_quiesce_vf_pci(struct i40e_vf *vf)
 static int i40e_getnum_vf_vsi_vlan_filters(struct i40e_vsi *vsi)
 {
 	struct i40e_mac_filter *f;
-	int num_vlans = 0, bkt;
+	u16 num_vlans = 0, bkt;
 
 	hash_for_each(vsi->mac_filter_hash, bkt, f, hlist) {
 		if (f->vlan >= 0 && f->vlan <= I40E_MAX_VLANID)
@@ -1134,8 +1134,8 @@ static int i40e_getnum_vf_vsi_vlan_filters(struct i40e_vsi *vsi)
  *
  * Called to get number of VLANs and VLAN list present in mac_filter_hash.
  **/
-static void i40e_get_vlan_list_sync(struct i40e_vsi *vsi, int *num_vlans,
-					   s16 **vlan_list)
+static void i40e_get_vlan_list_sync(struct i40e_vsi *vsi, u16 *num_vlans,
+				    s16 **vlan_list)
 {
 	struct i40e_mac_filter *f;
 	int i = 0;
@@ -1169,11 +1169,11 @@ err:
  **/
 static i40e_status
 i40e_set_vsi_promisc(struct i40e_vf *vf, u16 seid, bool multi_enable,
-		     bool unicast_enable, s16 *vl, int num_vlans)
+		     bool unicast_enable, s16 *vl, u16 num_vlans)
 {
+	i40e_status aq_ret, aq_tmp = 0;
 	struct i40e_pf *pf = vf->pf;
 	struct i40e_hw *hw = &pf->hw;
-	i40e_status aq_ret;
 	int i;
 
 	/* No VLAN to set promisc on, set on VSI */
@@ -1222,6 +1222,9 @@ i40e_set_vsi_promisc(struct i40e_vf *vf, u16 seid, bool multi_enable,
 				vf->vf_id,
 				i40e_stat_str(&pf->hw, aq_ret),
 				i40e_aq_str(&pf->hw, aq_err));
+
+			if (!aq_tmp)
+				aq_tmp = aq_ret;
 		}
 
 		aq_ret = i40e_aq_set_vsi_uc_promisc_on_vlan(hw, seid,
@@ -1235,8 +1238,15 @@ i40e_set_vsi_promisc(struct i40e_vf *vf, u16 seid, bool multi_enable,
 				vf->vf_id,
 				i40e_stat_str(&pf->hw, aq_ret),
 				i40e_aq_str(&pf->hw, aq_err));
+
+			if (!aq_tmp)
+				aq_tmp = aq_ret;
 		}
 	}
+
+	if (aq_tmp)
+		aq_ret = aq_tmp;
+
 	return aq_ret;
 }
 
@@ -1258,7 +1268,7 @@ static i40e_status i40e_config_vf_promiscuous_mode(struct i40e_vf *vf,
 	i40e_status aq_ret = I40E_SUCCESS;
 	struct i40e_pf *pf = vf->pf;
 	struct i40e_vsi *vsi;
-	int num_vlans;
+	u16 num_vlans;
 	s16 *vl;
 
 	vsi = i40e_find_vsi_from_id(pf, vsi_id);
@@ -2234,7 +2244,8 @@ error_param:
 }
 
 /**
- * i40e_validate_queue_map
+ * i40e_validate_queue_map - check queue map is valid
+ * @vf: the VF structure pointer
  * @vsi_id: vsi id
  * @queuemap: Tx or Rx queue map
  *
@@ -3150,8 +3161,8 @@ err:
 
 /**
  * i40e_validate_cloud_filter
- * @mask: mask for TC filter
- * @data: data for TC filter
+ * @vf: pointer to VF structure
+ * @tc_filter: pointer to filter requested
  *
  * This function validates cloud filter programmed as TC filter for ADq
  **/
@@ -3284,7 +3295,7 @@ err:
 /**
  * i40e_find_vsi_from_seid - searches for the vsi with the given seid
  * @vf: pointer to the VF info
- * @seid - seid of the vsi it is searching for
+ * @seid: seid of the vsi it is searching for
  **/
 static struct i40e_vsi *i40e_find_vsi_from_seid(struct i40e_vf *vf, u16 seid)
 {
diff --git a/drivers/net/ethernet/intel/iavf/iavf_adminq.h b/drivers/net/ethernet/intel/iavf/iavf_adminq.h
index baf2fe26f302..1f60518eb0e5 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_adminq.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_adminq.h
@@ -85,8 +85,8 @@ struct iavf_adminq_info {
 
 /**
  * iavf_aq_rc_to_posix - convert errors to user-land codes
- * aq_ret: AdminQ handler error code can override aq_rc
- * aq_rc: AdminQ firmware error code to convert
+ * @aq_ret: AdminQ handler error code can override aq_rc
+ * @aq_rc: AdminQ firmware error code to convert
  **/
 static inline int iavf_aq_rc_to_posix(int aq_ret, int aq_rc)
 {
diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index d870343cf689..08610a3f978a 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -147,6 +147,7 @@ void iavf_schedule_reset(struct iavf_adapter *adapter)
 /**
  * iavf_tx_timeout - Respond to a Tx Hang
  * @netdev: network interface device structure
+ * @txqueue: queue number that is timing out
  **/
 static void iavf_tx_timeout(struct net_device *netdev, unsigned int txqueue)
 {
@@ -2572,8 +2573,8 @@ static int iavf_validate_ch_config(struct iavf_adapter *adapter,
 }
 
 /**
- * iavf_del_all_cloud_filters - delete all cloud filters
- * on the traffic classes
+ * iavf_del_all_cloud_filters - delete all cloud filters on the traffic classes
+ * @adapter: board private structure
  **/
 static void iavf_del_all_cloud_filters(struct iavf_adapter *adapter)
 {
@@ -2592,7 +2593,7 @@ static void iavf_del_all_cloud_filters(struct iavf_adapter *adapter)
 /**
  * __iavf_setup_tc - configure multiple traffic classes
  * @netdev: network interface device structure
- * @type_date: tc offload data
+ * @type_data: tc offload data
  *
  * This function processes the config information provided by the
  * user to configure traffic classes/queue channels and packages the
@@ -2690,7 +2691,7 @@ exit:
 /**
  * iavf_parse_cls_flower - Parse tc flower filters provided by kernel
  * @adapter: board private structure
- * @cls_flower: pointer to struct flow_cls_offload
+ * @f: pointer to struct flow_cls_offload
  * @filter: pointer to cloud filter structure
  */
 static int iavf_parse_cls_flower(struct iavf_adapter *adapter,
@@ -3064,8 +3065,8 @@ static int iavf_delete_clsflower(struct iavf_adapter *adapter,
 
 /**
  * iavf_setup_tc_cls_flower - flower classifier offloads
- * @netdev: net device to configure
- * @type_data: offload data
+ * @adapter: board private structure
+ * @cls_flower: pointer to flow_cls_offload struct with flow info
  */
 static int iavf_setup_tc_cls_flower(struct iavf_adapter *adapter,
 				    struct flow_cls_offload *cls_flower)
@@ -3112,7 +3113,7 @@ static LIST_HEAD(iavf_block_cb_list);
  * iavf_setup_tc - configure multiple traffic classes
  * @netdev: network interface device structure
  * @type: type of offload
- * @type_date: tc offload data
+ * @type_data: tc offload data
  *
  * This function is the callback to ndo_setup_tc in the
  * netdev_ops.
@@ -3768,8 +3769,7 @@ err_dma:
 
 /**
  * iavf_suspend - Power management suspend routine
- * @pdev: PCI device information struct
- * @state: unused
+ * @dev_d: device info pointer
  *
  * Called when the system (VM) is entering sleep/suspend.
  **/
@@ -3799,7 +3799,7 @@ static int __maybe_unused iavf_suspend(struct device *dev_d)
 
 /**
  * iavf_resume - Power management resume routine
- * @pdev: PCI device information struct
+ * @dev_d: device info pointer
  *
  * Called when the system (VM) is resumed from sleep/suspend.
  **/
diff --git a/drivers/net/ethernet/intel/iavf/iavf_trace.h b/drivers/net/ethernet/intel/iavf/iavf_trace.h
index 1058e68a02b4..82fda6f5abf0 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_trace.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_trace.h
@@ -22,7 +22,7 @@
 
 #include <linux/tracepoint.h>
 
-/**
+/*
  * iavf_trace() macro enables shared code to refer to trace points
  * like:
  *
diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.h b/drivers/net/ethernet/intel/iavf/iavf_txrx.h
index dd3348f9da9d..e5b9ba42dd00 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_txrx.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.h
@@ -454,7 +454,6 @@ bool __iavf_chk_linearize(struct sk_buff *skb);
 /**
  * iavf_xmit_descriptor_count - calculate number of Tx descriptors needed
  * @skb:     send buffer
- * @tx_ring: ring to send buffer on
  *
  * Returns number of data descriptors needed for this skb. Returns 0 to indicate
  * there is not enough descriptors available in this ring since we need at least
@@ -514,6 +513,7 @@ static inline bool iavf_chk_linearize(struct sk_buff *skb, int count)
 	return count != IAVF_MAX_BUFFER_TXD;
 }
 /**
+ * txring_txq - helper to convert from a ring to a queue
  * @ring: Tx ring to find the netdev equivalent of
  **/
 static inline struct netdev_queue *txring_txq(const struct iavf_ring *ring)
diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index 65583f0a1797..148f389b48a8 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -508,7 +508,7 @@ static inline void ice_set_ring_xdp(struct ice_ring *ring)
 
 /**
  * ice_xsk_pool - get XSK buffer pool bound to a ring
- * @ring - ring to use
+ * @ring: ring to use
  *
  * Returns a pointer to xdp_umem structure if there is a buffer pool present,
  * NULL otherwise.
diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
index ba9375218fef..b06fbe99d8e9 100644
--- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
@@ -1422,7 +1422,7 @@ struct ice_aqc_nvm_comp_tbl {
 	u8 cvs[]; /* Component Version String */
 } __packed;
 
-/**
+/*
  * Send to PF command (indirect 0x0801) ID is only used by PF
  *
  * Send to VF command (indirect 0x0802) ID is only used by PF
@@ -1826,8 +1826,8 @@ struct ice_aqc_event_lan_overflow {
  * @opcode: AQ command opcode
  * @datalen: length in bytes of indirect/external data buffer
  * @retval: return value from firmware
- * @cookie_h: opaque data high-half
- * @cookie_l: opaque data low-half
+ * @cookie_high: opaque data high-half
+ * @cookie_low: opaque data low-half
  * @params: command-specific parameters
  *
  * Descriptor format for commands the driver posts on the Admin Transmit Queue
diff --git a/drivers/net/ethernet/intel/ice/ice_devlink.c b/drivers/net/ethernet/intel/ice/ice_devlink.c
index 67d1190cb164..e17b44059eae 100644
--- a/drivers/net/ethernet/intel/ice/ice_devlink.c
+++ b/drivers/net/ethernet/intel/ice/ice_devlink.c
@@ -233,8 +233,7 @@ static int ice_devlink_info_get(struct devlink *devlink,
 /**
  * ice_devlink_flash_update - Update firmware stored in flash on the device
  * @devlink: pointer to devlink associated with device to update
- * @path: the path of the firmware file to use via request_firmware
- * @component: name of the component to update, or NULL
+ * @params: flash update parameters
  * @extack: netlink extended ACK structure
  *
  * Perform a device flash update. The bulk of the update logic is contained
@@ -243,38 +242,50 @@ static int ice_devlink_info_get(struct devlink *devlink,
  * Returns: zero on success, or an error code on failure.
  */
 static int
-ice_devlink_flash_update(struct devlink *devlink, const char *path,
-			 const char *component, struct netlink_ext_ack *extack)
+ice_devlink_flash_update(struct devlink *devlink,
+			 struct devlink_flash_update_params *params,
+			 struct netlink_ext_ack *extack)
 {
 	struct ice_pf *pf = devlink_priv(devlink);
 	struct device *dev = &pf->pdev->dev;
 	struct ice_hw *hw = &pf->hw;
 	const struct firmware *fw;
+	u8 preservation;
 	int err;
 
-	/* individual component update is not yet supported */
-	if (component)
+	if (!params->overwrite_mask) {
+		/* preserve all settings and identifiers */
+		preservation = ICE_AQC_NVM_PRESERVE_ALL;
+	} else if (params->overwrite_mask == DEVLINK_FLASH_OVERWRITE_SETTINGS) {
+		/* overwrite settings, but preserve the vital device identifiers */
+		preservation = ICE_AQC_NVM_PRESERVE_SELECTED;
+	} else if (params->overwrite_mask == (DEVLINK_FLASH_OVERWRITE_SETTINGS |
+					      DEVLINK_FLASH_OVERWRITE_IDENTIFIERS)) {
+		/* overwrite both settings and identifiers, preserve nothing */
+		preservation = ICE_AQC_NVM_NO_PRESERVATION;
+	} else {
+		NL_SET_ERR_MSG_MOD(extack, "Requested overwrite mask is not supported");
 		return -EOPNOTSUPP;
+	}
 
 	if (!hw->dev_caps.common_cap.nvm_unified_update) {
 		NL_SET_ERR_MSG_MOD(extack, "Current firmware does not support unified update");
 		return -EOPNOTSUPP;
 	}
 
-	err = ice_check_for_pending_update(pf, component, extack);
+	err = ice_check_for_pending_update(pf, NULL, extack);
 	if (err)
 		return err;
 
-	err = request_firmware(&fw, path, dev);
+	err = request_firmware(&fw, params->file_name, dev);
 	if (err) {
 		NL_SET_ERR_MSG_MOD(extack, "Unable to read file from disk");
 		return err;
 	}
 
 	devlink_flash_update_begin_notify(devlink);
-	devlink_flash_update_status_notify(devlink, "Preparing to flash",
-					   component, 0, 0);
-	err = ice_flash_pldm_image(pf, fw, extack);
+	devlink_flash_update_status_notify(devlink, "Preparing to flash", NULL, 0, 0);
+	err = ice_flash_pldm_image(pf, fw, preservation, extack);
 	devlink_flash_update_end_notify(devlink);
 
 	release_firmware(fw);
@@ -283,6 +294,7 @@ ice_devlink_flash_update(struct devlink *devlink, const char *path,
 }
 
 static const struct devlink_ops ice_devlink_ops = {
+	.supported_flash_update_params = DEVLINK_SUPPORT_FLASH_UPDATE_OVERWRITE_MASK,
 	.info_get = ice_devlink_info_get,
 	.flash_update = ice_devlink_flash_update,
 };
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
index d7430ce6af26..2d27f66ac853 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
@@ -1268,8 +1268,7 @@ ice_fdir_write_all_fltr(struct ice_pf *pf, struct ice_fdir_fltr *input,
 		bool is_tun = tun == ICE_FD_HW_SEG_TUN;
 		int err;
 
-		if (is_tun && !ice_get_open_tunnel_port(&pf->hw, TNL_ALL,
-							&port_num))
+		if (is_tun && !ice_get_open_tunnel_port(&pf->hw, &port_num))
 			continue;
 		err = ice_fdir_write_fltr(pf, input, add, is_tun);
 		if (err)
@@ -1647,8 +1646,7 @@ int ice_add_fdir_ethtool(struct ice_vsi *vsi, struct ethtool_rxnfc *cmd)
 	}
 
 	/* return error if not an update and no available filters */
-	fltrs_needed = ice_get_open_tunnel_port(hw, TNL_ALL, &tunnel_port) ?
-		2 : 1;
+	fltrs_needed = ice_get_open_tunnel_port(hw, &tunnel_port) ? 2 : 1;
 	if (!ice_fdir_find_fltr_by_idx(hw, fsp->location) &&
 	    ice_fdir_num_avail_fltr(hw, pf->vsi[vsi->idx]) < fltrs_needed) {
 		dev_err(dev, "Failed to add filter.  The maximum number of flow director filters has been reached.\n");
diff --git a/drivers/net/ethernet/intel/ice/ice_fdir.c b/drivers/net/ethernet/intel/ice/ice_fdir.c
index 6834df14332f..59c0c6a0f8c5 100644
--- a/drivers/net/ethernet/intel/ice/ice_fdir.c
+++ b/drivers/net/ethernet/intel/ice/ice_fdir.c
@@ -556,7 +556,7 @@ ice_fdir_get_gen_prgm_pkt(struct ice_hw *hw, struct ice_fdir_fltr *input,
 		memcpy(pkt, ice_fdir_pkt[idx].pkt, ice_fdir_pkt[idx].pkt_len);
 		loc = pkt;
 	} else {
-		if (!ice_get_open_tunnel_port(hw, TNL_ALL, &tnl_port))
+		if (!ice_get_open_tunnel_port(hw, &tnl_port))
 			return ICE_ERR_DOES_NOT_EXIST;
 		if (!ice_fdir_pkt[idx].tun_pkt)
 			return ICE_ERR_PARAM;
diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c
index b17ae3e20157..ac448d223e9a 100644
--- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c
+++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c
@@ -489,8 +489,6 @@ static void ice_init_pkg_hints(struct ice_hw *hw, struct ice_seg *ice_seg)
 			if ((label_name[len] - '0') == hw->pf_id) {
 				hw->tnl.tbl[hw->tnl.count].type = tnls[i].type;
 				hw->tnl.tbl[hw->tnl.count].valid = false;
-				hw->tnl.tbl[hw->tnl.count].in_use = false;
-				hw->tnl.tbl[hw->tnl.count].marked = false;
 				hw->tnl.tbl[hw->tnl.count].boost_addr = val;
 				hw->tnl.tbl[hw->tnl.count].port = 0;
 				hw->tnl.count++;
@@ -505,8 +503,11 @@ static void ice_init_pkg_hints(struct ice_hw *hw, struct ice_seg *ice_seg)
 	for (i = 0; i < hw->tnl.count; i++) {
 		ice_find_boost_entry(ice_seg, hw->tnl.tbl[i].boost_addr,
 				     &hw->tnl.tbl[i].boost_entry);
-		if (hw->tnl.tbl[i].boost_entry)
+		if (hw->tnl.tbl[i].boost_entry) {
 			hw->tnl.tbl[i].valid = true;
+			if (hw->tnl.tbl[i].type < __TNL_TYPE_CNT)
+				hw->tnl.valid_count[hw->tnl.tbl[i].type]++;
+		}
 	}
 }
 
@@ -1626,104 +1627,59 @@ static struct ice_buf *ice_pkg_buf(struct ice_buf_build *bld)
 }
 
 /**
- * ice_tunnel_port_in_use_hlpr - helper function to determine tunnel usage
+ * ice_get_open_tunnel_port - retrieve an open tunnel port
  * @hw: pointer to the HW structure
- * @port: port to search for
- * @index: optionally returns index
- *
- * Returns whether a port is already in use as a tunnel, and optionally its
- * index
+ * @port: returns open port
  */
-static bool ice_tunnel_port_in_use_hlpr(struct ice_hw *hw, u16 port, u16 *index)
+bool
+ice_get_open_tunnel_port(struct ice_hw *hw, u16 *port)
 {
+	bool res = false;
 	u16 i;
 
+	mutex_lock(&hw->tnl_lock);
+
 	for (i = 0; i < hw->tnl.count && i < ICE_TUNNEL_MAX_ENTRIES; i++)
-		if (hw->tnl.tbl[i].in_use && hw->tnl.tbl[i].port == port) {
-			if (index)
-				*index = i;
-			return true;
+		if (hw->tnl.tbl[i].valid && hw->tnl.tbl[i].port) {
+			*port = hw->tnl.tbl[i].port;
+			res = true;
+			break;
 		}
 
-	return false;
-}
-
-/**
- * ice_tunnel_port_in_use
- * @hw: pointer to the HW structure
- * @port: port to search for
- * @index: optionally returns index
- *
- * Returns whether a port is already in use as a tunnel, and optionally its
- * index
- */
-bool ice_tunnel_port_in_use(struct ice_hw *hw, u16 port, u16 *index)
-{
-	bool res;
-
-	mutex_lock(&hw->tnl_lock);
-	res = ice_tunnel_port_in_use_hlpr(hw, port, index);
 	mutex_unlock(&hw->tnl_lock);
 
 	return res;
 }
 
 /**
- * ice_find_free_tunnel_entry
+ * ice_tunnel_idx_to_entry - convert linear index to the sparse one
  * @hw: pointer to the HW structure
- * @type: tunnel type
- * @index: optionally returns index
+ * @type: type of tunnel
+ * @idx: linear index
  *
- * Returns whether there is a free tunnel entry, and optionally its index
+ * Stack assumes we have 2 linear tables with indexes [0, count_valid),
+ * but really the port table may be sprase, and types are mixed, so convert
+ * the stack index into the device index.
  */
-static bool
-ice_find_free_tunnel_entry(struct ice_hw *hw, enum ice_tunnel_type type,
-			   u16 *index)
+static u16 ice_tunnel_idx_to_entry(struct ice_hw *hw, enum ice_tunnel_type type,
+				   u16 idx)
 {
 	u16 i;
 
 	for (i = 0; i < hw->tnl.count && i < ICE_TUNNEL_MAX_ENTRIES; i++)
-		if (hw->tnl.tbl[i].valid && !hw->tnl.tbl[i].in_use &&
-		    hw->tnl.tbl[i].type == type) {
-			if (index)
-				*index = i;
-			return true;
-		}
+		if (hw->tnl.tbl[i].valid &&
+		    hw->tnl.tbl[i].type == type &&
+		    idx--)
+			return i;
 
-	return false;
-}
-
-/**
- * ice_get_open_tunnel_port - retrieve an open tunnel port
- * @hw: pointer to the HW structure
- * @type: tunnel type (TNL_ALL will return any open port)
- * @port: returns open port
- */
-bool
-ice_get_open_tunnel_port(struct ice_hw *hw, enum ice_tunnel_type type,
-			 u16 *port)
-{
-	bool res = false;
-	u16 i;
-
-	mutex_lock(&hw->tnl_lock);
-
-	for (i = 0; i < hw->tnl.count && i < ICE_TUNNEL_MAX_ENTRIES; i++)
-		if (hw->tnl.tbl[i].valid && hw->tnl.tbl[i].in_use &&
-		    (type == TNL_ALL || hw->tnl.tbl[i].type == type)) {
-			*port = hw->tnl.tbl[i].port;
-			res = true;
-			break;
-		}
-
-	mutex_unlock(&hw->tnl_lock);
-
-	return res;
+	WARN_ON_ONCE(1);
+	return 0;
 }
 
 /**
  * ice_create_tunnel
  * @hw: pointer to the HW structure
+ * @index: device table entry
  * @type: type of tunnel
  * @port: port of tunnel to create
  *
@@ -1731,27 +1687,16 @@ ice_get_open_tunnel_port(struct ice_hw *hw, enum ice_tunnel_type type,
  * creating a package buffer with the tunnel info and issuing an update package
  * command.
  */
-enum ice_status
-ice_create_tunnel(struct ice_hw *hw, enum ice_tunnel_type type, u16 port)
+static enum ice_status
+ice_create_tunnel(struct ice_hw *hw, u16 index,
+		  enum ice_tunnel_type type, u16 port)
 {
 	struct ice_boost_tcam_section *sect_rx, *sect_tx;
 	enum ice_status status = ICE_ERR_MAX_LIMIT;
 	struct ice_buf_build *bld;
-	u16 index;
 
 	mutex_lock(&hw->tnl_lock);
 
-	if (ice_tunnel_port_in_use_hlpr(hw, port, &index)) {
-		hw->tnl.tbl[index].ref++;
-		status = 0;
-		goto ice_create_tunnel_end;
-	}
-
-	if (!ice_find_free_tunnel_entry(hw, type, &index)) {
-		status = ICE_ERR_OUT_OF_RANGE;
-		goto ice_create_tunnel_end;
-	}
-
 	bld = ice_pkg_buf_alloc(hw);
 	if (!bld) {
 		status = ICE_ERR_NO_MEMORY;
@@ -1790,11 +1735,8 @@ ice_create_tunnel(struct ice_hw *hw, enum ice_tunnel_type type, u16 port)
 	memcpy(sect_tx->tcam, sect_rx->tcam, sizeof(*sect_tx->tcam));
 
 	status = ice_update_pkg(hw, ice_pkg_buf(bld), 1);
-	if (!status) {
+	if (!status)
 		hw->tnl.tbl[index].port = port;
-		hw->tnl.tbl[index].in_use = true;
-		hw->tnl.tbl[index].ref = 1;
-	}
 
 ice_create_tunnel_err:
 	ice_pkg_buf_free(hw, bld);
@@ -1808,46 +1750,31 @@ ice_create_tunnel_end:
 /**
  * ice_destroy_tunnel
  * @hw: pointer to the HW structure
+ * @index: device table entry
+ * @type: type of tunnel
  * @port: port of tunnel to destroy (ignored if the all parameter is true)
- * @all: flag that states to destroy all tunnels
  *
  * Destroys a tunnel or all tunnels by creating an update package buffer
  * targeting the specific updates requested and then performing an update
  * package.
  */
-enum ice_status ice_destroy_tunnel(struct ice_hw *hw, u16 port, bool all)
+static enum ice_status
+ice_destroy_tunnel(struct ice_hw *hw, u16 index, enum ice_tunnel_type type,
+		   u16 port)
 {
 	struct ice_boost_tcam_section *sect_rx, *sect_tx;
 	enum ice_status status = ICE_ERR_MAX_LIMIT;
 	struct ice_buf_build *bld;
-	u16 count = 0;
-	u16 index;
-	u16 size;
-	u16 i;
 
 	mutex_lock(&hw->tnl_lock);
 
-	if (!all && ice_tunnel_port_in_use_hlpr(hw, port, &index))
-		if (hw->tnl.tbl[index].ref > 1) {
-			hw->tnl.tbl[index].ref--;
-			status = 0;
-			goto ice_destroy_tunnel_end;
-		}
-
-	/* determine count */
-	for (i = 0; i < hw->tnl.count && i < ICE_TUNNEL_MAX_ENTRIES; i++)
-		if (hw->tnl.tbl[i].valid && hw->tnl.tbl[i].in_use &&
-		    (all || hw->tnl.tbl[i].port == port))
-			count++;
-
-	if (!count) {
-		status = ICE_ERR_PARAM;
+	if (WARN_ON(!hw->tnl.tbl[index].valid ||
+		    hw->tnl.tbl[index].type != type ||
+		    hw->tnl.tbl[index].port != port)) {
+		status = ICE_ERR_OUT_OF_RANGE;
 		goto ice_destroy_tunnel_end;
 	}
 
-	/* size of section - there is at least one entry */
-	size = struct_size(sect_rx, tcam, count);
-
 	bld = ice_pkg_buf_alloc(hw);
 	if (!bld) {
 		status = ICE_ERR_NO_MEMORY;
@@ -1859,13 +1786,13 @@ enum ice_status ice_destroy_tunnel(struct ice_hw *hw, u16 port, bool all)
 		goto ice_destroy_tunnel_err;
 
 	sect_rx = ice_pkg_buf_alloc_section(bld, ICE_SID_RXPARSER_BOOST_TCAM,
-					    size);
+					    struct_size(sect_rx, tcam, 1));
 	if (!sect_rx)
 		goto ice_destroy_tunnel_err;
 	sect_rx->count = cpu_to_le16(1);
 
 	sect_tx = ice_pkg_buf_alloc_section(bld, ICE_SID_TXPARSER_BOOST_TCAM,
-					    size);
+					    struct_size(sect_tx, tcam, 1));
 	if (!sect_tx)
 		goto ice_destroy_tunnel_err;
 	sect_tx->count = cpu_to_le16(1);
@@ -1873,26 +1800,14 @@ enum ice_status ice_destroy_tunnel(struct ice_hw *hw, u16 port, bool all)
 	/* copy original boost entry to update package buffer, one copy to Rx
 	 * section, another copy to the Tx section
 	 */
-	for (i = 0; i < hw->tnl.count && i < ICE_TUNNEL_MAX_ENTRIES; i++)
-		if (hw->tnl.tbl[i].valid && hw->tnl.tbl[i].in_use &&
-		    (all || hw->tnl.tbl[i].port == port)) {
-			memcpy(sect_rx->tcam + i, hw->tnl.tbl[i].boost_entry,
-			       sizeof(*sect_rx->tcam));
-			memcpy(sect_tx->tcam + i, hw->tnl.tbl[i].boost_entry,
-			       sizeof(*sect_tx->tcam));
-			hw->tnl.tbl[i].marked = true;
-		}
+	memcpy(sect_rx->tcam, hw->tnl.tbl[index].boost_entry,
+	       sizeof(*sect_rx->tcam));
+	memcpy(sect_tx->tcam, hw->tnl.tbl[index].boost_entry,
+	       sizeof(*sect_tx->tcam));
 
 	status = ice_update_pkg(hw, ice_pkg_buf(bld), 1);
 	if (!status)
-		for (i = 0; i < hw->tnl.count &&
-		     i < ICE_TUNNEL_MAX_ENTRIES; i++)
-			if (hw->tnl.tbl[i].marked) {
-				hw->tnl.tbl[i].ref = 0;
-				hw->tnl.tbl[i].port = 0;
-				hw->tnl.tbl[i].in_use = false;
-				hw->tnl.tbl[i].marked = false;
-			}
+		hw->tnl.tbl[index].port = 0;
 
 ice_destroy_tunnel_err:
 	ice_pkg_buf_free(hw, bld);
@@ -1903,6 +1818,52 @@ ice_destroy_tunnel_end:
 	return status;
 }
 
+int ice_udp_tunnel_set_port(struct net_device *netdev, unsigned int table,
+			    unsigned int idx, struct udp_tunnel_info *ti)
+{
+	struct ice_netdev_priv *np = netdev_priv(netdev);
+	struct ice_vsi *vsi = np->vsi;
+	struct ice_pf *pf = vsi->back;
+	enum ice_tunnel_type tnl_type;
+	enum ice_status status;
+	u16 index;
+
+	tnl_type = ti->type == UDP_TUNNEL_TYPE_VXLAN ? TNL_VXLAN : TNL_GENEVE;
+	index = ice_tunnel_idx_to_entry(&pf->hw, idx, tnl_type);
+
+	status = ice_create_tunnel(&pf->hw, index, tnl_type, ntohs(ti->port));
+	if (status) {
+		netdev_err(netdev, "Error adding UDP tunnel - %s\n",
+			   ice_stat_str(status));
+		return -EIO;
+	}
+
+	udp_tunnel_nic_set_port_priv(netdev, table, idx, index);
+	return 0;
+}
+
+int ice_udp_tunnel_unset_port(struct net_device *netdev, unsigned int table,
+			      unsigned int idx, struct udp_tunnel_info *ti)
+{
+	struct ice_netdev_priv *np = netdev_priv(netdev);
+	struct ice_vsi *vsi = np->vsi;
+	struct ice_pf *pf = vsi->back;
+	enum ice_tunnel_type tnl_type;
+	enum ice_status status;
+
+	tnl_type = ti->type == UDP_TUNNEL_TYPE_VXLAN ? TNL_VXLAN : TNL_GENEVE;
+
+	status = ice_destroy_tunnel(&pf->hw, ti->hw_priv, tnl_type,
+				    ntohs(ti->port));
+	if (status) {
+		netdev_err(netdev, "Error removing UDP tunnel - %s\n",
+			   ice_stat_str(status));
+		return -EIO;
+	}
+
+	return 0;
+}
+
 /* PTG Management */
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.h b/drivers/net/ethernet/intel/ice/ice_flex_pipe.h
index 568ea519af51..20deddb807c5 100644
--- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.h
+++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.h
@@ -19,12 +19,11 @@
 #define ICE_PKG_CNT 4
 
 bool
-ice_get_open_tunnel_port(struct ice_hw *hw, enum ice_tunnel_type type,
-			 u16 *port);
-enum ice_status
-ice_create_tunnel(struct ice_hw *hw, enum ice_tunnel_type type, u16 port);
-enum ice_status ice_destroy_tunnel(struct ice_hw *hw, u16 port, bool all);
-bool ice_tunnel_port_in_use(struct ice_hw *hw, u16 port, u16 *index);
+ice_get_open_tunnel_port(struct ice_hw *hw, u16 *port);
+int ice_udp_tunnel_set_port(struct net_device *netdev, unsigned int table,
+			    unsigned int idx, struct udp_tunnel_info *ti);
+int ice_udp_tunnel_unset_port(struct net_device *netdev, unsigned int table,
+			      unsigned int idx, struct udp_tunnel_info *ti);
 
 enum ice_status
 ice_add_prof(struct ice_hw *hw, enum ice_block blk, u64 id, u8 ptypes[],
diff --git a/drivers/net/ethernet/intel/ice/ice_flex_type.h b/drivers/net/ethernet/intel/ice/ice_flex_type.h
index c1c99a267a98..24063c1351b2 100644
--- a/drivers/net/ethernet/intel/ice/ice_flex_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_flex_type.h
@@ -298,6 +298,7 @@ struct ice_pkg_enum {
 enum ice_tunnel_type {
 	TNL_VXLAN = 0,
 	TNL_GENEVE,
+	__TNL_TYPE_CNT,
 	TNL_LAST = 0xFF,
 	TNL_ALL = 0xFF,
 };
@@ -311,11 +312,8 @@ struct ice_tunnel_entry {
 	enum ice_tunnel_type type;
 	u16 boost_addr;
 	u16 port;
-	u16 ref;
 	struct ice_boost_tcam_entry *boost_entry;
 	u8 valid;
-	u8 in_use;
-	u8 marked;
 };
 
 #define ICE_TUNNEL_MAX_ENTRIES	16
@@ -323,6 +321,7 @@ struct ice_tunnel_entry {
 struct ice_tunnel_table {
 	struct ice_tunnel_entry tbl[ICE_TUNNEL_MAX_ENTRIES];
 	u16 count;
+	u16 valid_count[__TNL_TYPE_CNT];
 };
 
 struct ice_pkg_es {
diff --git a/drivers/net/ethernet/intel/ice/ice_fw_update.c b/drivers/net/ethernet/intel/ice/ice_fw_update.c
index 292d87b996ab..142123155a0f 100644
--- a/drivers/net/ethernet/intel/ice/ice_fw_update.c
+++ b/drivers/net/ethernet/intel/ice/ice_fw_update.c
@@ -625,6 +625,7 @@ static const struct pldmfw_ops ice_fwu_ops = {
  * ice_flash_pldm_image - Write a PLDM-formatted firmware image to the device
  * @pf: private device driver structure
  * @fw: firmware object pointing to the relevant firmware file
+ * @preservation: preservation level to request from firmware
  * @extack: netlink extended ACK structure
  *
  * Parse the data for a given firmware file, verifying that it is a valid PLDM
@@ -638,7 +639,7 @@ static const struct pldmfw_ops ice_fwu_ops = {
  * Returns: zero on success or a negative error code on failure.
  */
 int ice_flash_pldm_image(struct ice_pf *pf, const struct firmware *fw,
-			 struct netlink_ext_ack *extack)
+			 u8 preservation, struct netlink_ext_ack *extack)
 {
 	struct device *dev = ice_pf_to_dev(pf);
 	struct ice_hw *hw = &pf->hw;
@@ -646,13 +647,24 @@ int ice_flash_pldm_image(struct ice_pf *pf, const struct firmware *fw,
 	enum ice_status status;
 	int err;
 
+	switch (preservation) {
+	case ICE_AQC_NVM_PRESERVE_ALL:
+	case ICE_AQC_NVM_PRESERVE_SELECTED:
+	case ICE_AQC_NVM_NO_PRESERVATION:
+	case ICE_AQC_NVM_FACTORY_DEFAULT:
+		break;
+	default:
+		WARN(1, "Unexpected preservation level request %u", preservation);
+		return -EINVAL;
+	}
+
 	memset(&priv, 0, sizeof(priv));
 
 	priv.context.ops = &ice_fwu_ops;
 	priv.context.dev = dev;
 	priv.extack = extack;
 	priv.pf = pf;
-	priv.activate_flags = ICE_AQC_NVM_PRESERVE_ALL;
+	priv.activate_flags = preservation;
 
 	status = ice_acquire_nvm(hw, ICE_RES_WRITE);
 	if (status) {
diff --git a/drivers/net/ethernet/intel/ice/ice_fw_update.h b/drivers/net/ethernet/intel/ice/ice_fw_update.h
index 79472cc618b4..c6390f6851ff 100644
--- a/drivers/net/ethernet/intel/ice/ice_fw_update.h
+++ b/drivers/net/ethernet/intel/ice/ice_fw_update.h
@@ -5,7 +5,7 @@
 #define _ICE_FW_UPDATE_H_
 
 int ice_flash_pldm_image(struct ice_pf *pf, const struct firmware *fw,
-			 struct netlink_ext_ack *extack);
+			 u8 preservation, struct netlink_ext_ack *extack);
 int ice_check_for_pending_update(struct ice_pf *pf, const char *component,
 				 struct netlink_ext_ack *extack);
 
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 2297ee7dba26..1d74466ce77f 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -486,7 +486,6 @@ static void ice_do_reset(struct ice_pf *pf, enum ice_reset_req reset_type)
 	struct ice_hw *hw = &pf->hw;
 
 	dev_dbg(dev, "reset_type 0x%x requested\n", reset_type);
-	WARN_ON(in_interrupt());
 
 	ice_prepare_for_reset(pf);
 
@@ -2873,6 +2872,7 @@ static void ice_set_ops(struct net_device *netdev)
 	}
 
 	netdev->netdev_ops = &ice_netdev_ops;
+	netdev->udp_tunnel_nic_info = &pf->hw.udp_tunnel_nic;
 	ice_set_ethtool_ops(netdev);
 }
 
@@ -3978,7 +3978,7 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
 	struct device *dev = &pdev->dev;
 	struct ice_pf *pf;
 	struct ice_hw *hw;
-	int err;
+	int i, err;
 
 	/* this driver uses devres, see
 	 * Documentation/driver-api/driver-model/devres.rst
@@ -4073,11 +4073,37 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
 
 	ice_devlink_init_regions(pf);
 
+	pf->hw.udp_tunnel_nic.set_port = ice_udp_tunnel_set_port;
+	pf->hw.udp_tunnel_nic.unset_port = ice_udp_tunnel_unset_port;
+	pf->hw.udp_tunnel_nic.flags = UDP_TUNNEL_NIC_INFO_MAY_SLEEP;
+	pf->hw.udp_tunnel_nic.shared = &pf->hw.udp_tunnel_shared;
+	i = 0;
+	if (pf->hw.tnl.valid_count[TNL_VXLAN]) {
+		pf->hw.udp_tunnel_nic.tables[i].n_entries =
+			pf->hw.tnl.valid_count[TNL_VXLAN];
+		pf->hw.udp_tunnel_nic.tables[i].tunnel_types =
+			UDP_TUNNEL_TYPE_VXLAN;
+		i++;
+	}
+	if (pf->hw.tnl.valid_count[TNL_GENEVE]) {
+		pf->hw.udp_tunnel_nic.tables[i].n_entries =
+			pf->hw.tnl.valid_count[TNL_GENEVE];
+		pf->hw.udp_tunnel_nic.tables[i].tunnel_types =
+			UDP_TUNNEL_TYPE_GENEVE;
+		i++;
+	}
+
 	pf->num_alloc_vsi = hw->func_caps.guar_num_vsi;
 	if (!pf->num_alloc_vsi) {
 		err = -EIO;
 		goto err_init_pf_unroll;
 	}
+	if (pf->num_alloc_vsi > UDP_TUNNEL_NIC_MAX_SHARING_DEVICES) {
+		dev_warn(&pf->pdev->dev,
+			 "limiting the VSI count due to UDP tunnel limitation %d > %d\n",
+			 pf->num_alloc_vsi, UDP_TUNNEL_NIC_MAX_SHARING_DEVICES);
+		pf->num_alloc_vsi = UDP_TUNNEL_NIC_MAX_SHARING_DEVICES;
+	}
 
 	pf->vsi = devm_kcalloc(dev, pf->num_alloc_vsi, sizeof(*pf->vsi),
 			       GFP_KERNEL);
@@ -6575,70 +6601,6 @@ static void ice_tx_timeout(struct net_device *netdev, unsigned int txqueue)
 }
 
 /**
- * ice_udp_tunnel_add - Get notifications about UDP tunnel ports that come up
- * @netdev: This physical port's netdev
- * @ti: Tunnel endpoint information
- */
-static void
-ice_udp_tunnel_add(struct net_device *netdev, struct udp_tunnel_info *ti)
-{
-	struct ice_netdev_priv *np = netdev_priv(netdev);
-	struct ice_vsi *vsi = np->vsi;
-	struct ice_pf *pf = vsi->back;
-	enum ice_tunnel_type tnl_type;
-	u16 port = ntohs(ti->port);
-	enum ice_status status;
-
-	switch (ti->type) {
-	case UDP_TUNNEL_TYPE_VXLAN:
-		tnl_type = TNL_VXLAN;
-		break;
-	case UDP_TUNNEL_TYPE_GENEVE:
-		tnl_type = TNL_GENEVE;
-		break;
-	default:
-		netdev_err(netdev, "Unknown tunnel type\n");
-		return;
-	}
-
-	status = ice_create_tunnel(&pf->hw, tnl_type, port);
-	if (status == ICE_ERR_OUT_OF_RANGE)
-		netdev_info(netdev, "Max tunneled UDP ports reached, port %d not added\n",
-			    port);
-	else if (status)
-		netdev_err(netdev, "Error adding UDP tunnel - %s\n",
-			   ice_stat_str(status));
-}
-
-/**
- * ice_udp_tunnel_del - Get notifications about UDP tunnel ports that go away
- * @netdev: This physical port's netdev
- * @ti: Tunnel endpoint information
- */
-static void
-ice_udp_tunnel_del(struct net_device *netdev, struct udp_tunnel_info *ti)
-{
-	struct ice_netdev_priv *np = netdev_priv(netdev);
-	struct ice_vsi *vsi = np->vsi;
-	struct ice_pf *pf = vsi->back;
-	u16 port = ntohs(ti->port);
-	enum ice_status status;
-	bool retval;
-
-	retval = ice_tunnel_port_in_use(&pf->hw, port, NULL);
-	if (!retval) {
-		netdev_info(netdev, "port %d not found in UDP tunnels list\n",
-			    port);
-		return;
-	}
-
-	status = ice_destroy_tunnel(&pf->hw, port, false);
-	if (status)
-		netdev_err(netdev, "error deleting port %d from UDP tunnels list\n",
-			   port);
-}
-
-/**
  * ice_open - Called when a network interface becomes active
  * @netdev: network interface device structure
  *
@@ -6830,6 +6792,6 @@ static const struct net_device_ops ice_netdev_ops = {
 	.ndo_bpf = ice_xdp,
 	.ndo_xdp_xmit = ice_xdp_xmit,
 	.ndo_xsk_wakeup = ice_xsk_wakeup,
-	.ndo_udp_tunnel_add = ice_udp_tunnel_add,
-	.ndo_udp_tunnel_del = ice_udp_tunnel_del,
+	.ndo_udp_tunnel_add = udp_tunnel_nic_add_port,
+	.ndo_udp_tunnel_del = udp_tunnel_nic_del_port,
 };
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h
index e9f60d550fcb..ff1a1cbd078e 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.h
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.h
@@ -43,7 +43,7 @@
 
 /**
  * ice_compute_pad - compute the padding
- * rx_buf_len: buffer length
+ * @rx_buf_len: buffer length
  *
  * Figure out the size of half page based on given buffer length and
  * then subtract the skb_shared_info followed by subtraction of the
diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h
index 4cdccfadf274..2226a291a394 100644
--- a/drivers/net/ethernet/intel/ice/ice_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_type.h
@@ -676,6 +676,9 @@ struct ice_hw {
 	struct mutex tnl_lock;
 	struct ice_tunnel_table tnl;
 
+	struct udp_tunnel_nic_shared udp_tunnel_shared;
+	struct udp_tunnel_nic_info udp_tunnel_nic;
+
 	/* HW block tables */
 	struct ice_blk_info blk[ICE_BLK_COUNT];
 	struct mutex fl_profs_locks[ICE_BLK_COUNT];	/* lock fltr profiles */
diff --git a/drivers/net/ethernet/intel/igb/e1000_82575.c b/drivers/net/ethernet/intel/igb/e1000_82575.c
index a32391e82762..50863fd87d53 100644
--- a/drivers/net/ethernet/intel/igb/e1000_82575.c
+++ b/drivers/net/ethernet/intel/igb/e1000_82575.c
@@ -2554,7 +2554,7 @@ out:
 /**
  *  __igb_access_emi_reg - Read/write EMI register
  *  @hw: pointer to the HW structure
- *  @addr: EMI address to program
+ *  @address: EMI address to program
  *  @data: pointer to value to read/write from/to the EMI address
  *  @read: boolean flag to indicate read or write
  **/
@@ -2590,7 +2590,7 @@ s32 igb_read_emi_reg(struct e1000_hw *hw, u16 addr, u16 *data)
  *  igb_set_eee_i350 - Enable/disable EEE support
  *  @hw: pointer to the HW structure
  *  @adv1G: boolean flag enabling 1G EEE advertisement
- *  @adv100m: boolean flag enabling 100M EEE advertisement
+ *  @adv100M: boolean flag enabling 100M EEE advertisement
  *
  *  Enable/disable EEE based on setting in dev_spec structure.
  *
@@ -2646,7 +2646,7 @@ out:
  *  igb_set_eee_i354 - Enable/disable EEE support
  *  @hw: pointer to the HW structure
  *  @adv1G: boolean flag enabling 1G EEE advertisement
- *  @adv100m: boolean flag enabling 100M EEE advertisement
+ *  @adv100M: boolean flag enabling 100M EEE advertisement
  *
  *  Enable/disable EEE legacy mode based on setting in dev_spec structure.
  *
diff --git a/drivers/net/ethernet/intel/igb/e1000_i210.c b/drivers/net/ethernet/intel/igb/e1000_i210.c
index c393cb2c0f16..9265901455cd 100644
--- a/drivers/net/ethernet/intel/igb/e1000_i210.c
+++ b/drivers/net/ethernet/intel/igb/e1000_i210.c
@@ -357,13 +357,14 @@ static s32 igb_read_invm_word_i210(struct e1000_hw *hw, u8 address, u16 *data)
 /**
  * igb_read_invm_i210 - Read invm wrapper function for I210/I211
  *  @hw: pointer to the HW structure
- *  @words: number of words to read
+ *  @offset: offset to read from
+ *  @words: number of words to read (unused)
  *  @data: pointer to the data read
  *
  *  Wrapper function to return data formerly found in the NVM.
  **/
 static s32 igb_read_invm_i210(struct e1000_hw *hw, u16 offset,
-				u16 words __always_unused, u16 *data)
+				u16 __always_unused words, u16 *data)
 {
 	s32 ret_val = 0;
 
diff --git a/drivers/net/ethernet/intel/igb/e1000_mac.c b/drivers/net/ethernet/intel/igb/e1000_mac.c
index 3254737c07a3..fd8eb2f9ab9d 100644
--- a/drivers/net/ethernet/intel/igb/e1000_mac.c
+++ b/drivers/net/ethernet/intel/igb/e1000_mac.c
@@ -166,6 +166,7 @@ static s32 igb_find_vlvf_slot(struct e1000_hw *hw, u32 vlan, bool vlvf_bypass)
  *  @vlan: VLAN id to add or remove
  *  @vind: VMDq output index that maps queue to VLAN id
  *  @vlan_on: if true add filter, if false remove
+ *  @vlvf_bypass: skip VLVF if no match is found
  *
  *  Sets or clears a bit in the VLAN filter table array based on VLAN id
  *  and if we are adding or removing the filter
diff --git a/drivers/net/ethernet/intel/igb/e1000_mbx.c b/drivers/net/ethernet/intel/igb/e1000_mbx.c
index 46debd991bfe..33cceb77e960 100644
--- a/drivers/net/ethernet/intel/igb/e1000_mbx.c
+++ b/drivers/net/ethernet/intel/igb/e1000_mbx.c
@@ -9,6 +9,7 @@
  *  @msg: The message buffer
  *  @size: Length of buffer
  *  @mbx_id: id of mailbox to read
+ *  @unlock: skip locking or not
  *
  *  returns SUCCESS if it successfully read message from buffer
  **/
diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h
index 2f015b60a995..0286d2fceee4 100644
--- a/drivers/net/ethernet/intel/igb/igb.h
+++ b/drivers/net/ethernet/intel/igb/igb.h
@@ -19,6 +19,8 @@
 #include <linux/pci.h>
 #include <linux/mdio.h>
 
+#include <net/xdp.h>
+
 struct igb_adapter;
 
 #define E1000_PCS_CFG_IGN_SD	1
@@ -79,6 +81,12 @@ struct igb_adapter;
 #define IGB_I210_RX_LATENCY_100		2213
 #define IGB_I210_RX_LATENCY_1000	448
 
+/* XDP */
+#define IGB_XDP_PASS		0
+#define IGB_XDP_CONSUMED	BIT(0)
+#define IGB_XDP_TX		BIT(1)
+#define IGB_XDP_REDIR		BIT(2)
+
 struct vf_data_storage {
 	unsigned char vf_mac_addresses[ETH_ALEN];
 	u16 vf_mc_hashes[IGB_MAX_VF_MC_ENTRIES];
@@ -132,17 +140,62 @@ struct vf_mac_filter {
 
 /* Supported Rx Buffer Sizes */
 #define IGB_RXBUFFER_256	256
+#define IGB_RXBUFFER_1536	1536
 #define IGB_RXBUFFER_2048	2048
 #define IGB_RXBUFFER_3072	3072
 #define IGB_RX_HDR_LEN		IGB_RXBUFFER_256
 #define IGB_TS_HDR_LEN		16
 
-#define IGB_SKB_PAD		(NET_SKB_PAD + NET_IP_ALIGN)
+/* Attempt to maximize the headroom available for incoming frames.  We
+ * use a 2K buffer for receives and need 1536/1534 to store the data for
+ * the frame.  This leaves us with 512 bytes of room.  From that we need
+ * to deduct the space needed for the shared info and the padding needed
+ * to IP align the frame.
+ *
+ * Note: For cache line sizes 256 or larger this value is going to end
+ *	 up negative.  In these cases we should fall back to the 3K
+ *	 buffers.
+ */
 #if (PAGE_SIZE < 8192)
-#define IGB_MAX_FRAME_BUILD_SKB \
-	(SKB_WITH_OVERHEAD(IGB_RXBUFFER_2048) - IGB_SKB_PAD - IGB_TS_HDR_LEN)
+#define IGB_MAX_FRAME_BUILD_SKB (IGB_RXBUFFER_1536 - NET_IP_ALIGN)
+#define IGB_2K_TOO_SMALL_WITH_PADDING \
+((NET_SKB_PAD + IGB_TS_HDR_LEN + IGB_RXBUFFER_1536) > SKB_WITH_OVERHEAD(IGB_RXBUFFER_2048))
+
+static inline int igb_compute_pad(int rx_buf_len)
+{
+	int page_size, pad_size;
+
+	page_size = ALIGN(rx_buf_len, PAGE_SIZE / 2);
+	pad_size = SKB_WITH_OVERHEAD(page_size) - rx_buf_len;
+
+	return pad_size;
+}
+
+static inline int igb_skb_pad(void)
+{
+	int rx_buf_len;
+
+	/* If a 2K buffer cannot handle a standard Ethernet frame then
+	 * optimize padding for a 3K buffer instead of a 1.5K buffer.
+	 *
+	 * For a 3K buffer we need to add enough padding to allow for
+	 * tailroom due to NET_IP_ALIGN possibly shifting us out of
+	 * cache-line alignment.
+	 */
+	if (IGB_2K_TOO_SMALL_WITH_PADDING)
+		rx_buf_len = IGB_RXBUFFER_3072 + SKB_DATA_ALIGN(NET_IP_ALIGN);
+	else
+		rx_buf_len = IGB_RXBUFFER_1536;
+
+	/* if needed make room for NET_IP_ALIGN */
+	rx_buf_len -= NET_IP_ALIGN;
+
+	return igb_compute_pad(rx_buf_len);
+}
+
+#define IGB_SKB_PAD	igb_skb_pad()
 #else
-#define IGB_MAX_FRAME_BUILD_SKB (IGB_RXBUFFER_2048 - IGB_TS_HDR_LEN)
+#define IGB_SKB_PAD	(NET_SKB_PAD + NET_IP_ALIGN)
 #endif
 
 /* How many Rx Buffers do we bundle into one write to the hardware ? */
@@ -194,13 +247,22 @@ enum igb_tx_flags {
 #define IGB_SFF_ADDRESSING_MODE		0x4
 #define IGB_SFF_8472_UNSUP		0x00
 
+enum igb_tx_buf_type {
+	IGB_TYPE_SKB = 0,
+	IGB_TYPE_XDP,
+};
+
 /* wrapper around a pointer to a socket buffer,
  * so a DMA handle can be stored along with the buffer
  */
 struct igb_tx_buffer {
 	union e1000_adv_tx_desc *next_to_watch;
 	unsigned long time_stamp;
-	struct sk_buff *skb;
+	enum igb_tx_buf_type type;
+	union {
+		struct sk_buff *skb;
+		struct xdp_frame *xdpf;
+	};
 	unsigned int bytecount;
 	u16 gso_segs;
 	__be16 protocol;
@@ -248,6 +310,7 @@ struct igb_ring_container {
 struct igb_ring {
 	struct igb_q_vector *q_vector;	/* backlink to q_vector */
 	struct net_device *netdev;	/* back pointer to net_device */
+	struct bpf_prog *xdp_prog;
 	struct device *dev;		/* device pointer for dma mapping */
 	union {				/* array of buffer info structs */
 		struct igb_tx_buffer *tx_buffer_info;
@@ -288,6 +351,7 @@ struct igb_ring {
 			struct u64_stats_sync rx_syncp;
 		};
 	};
+	struct xdp_rxq_info xdp_rxq;
 } ____cacheline_internodealigned_in_smp;
 
 struct igb_q_vector {
@@ -339,7 +403,7 @@ static inline unsigned int igb_rx_bufsz(struct igb_ring *ring)
 		return IGB_RXBUFFER_3072;
 
 	if (ring_uses_build_skb(ring))
-		return IGB_MAX_FRAME_BUILD_SKB + IGB_TS_HDR_LEN;
+		return IGB_MAX_FRAME_BUILD_SKB;
 #endif
 	return IGB_RXBUFFER_2048;
 }
@@ -467,6 +531,7 @@ struct igb_adapter {
 	unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)];
 
 	struct net_device *netdev;
+	struct bpf_prog *xdp_prog;
 
 	unsigned long state;
 	unsigned int flags;
@@ -643,6 +708,9 @@ enum igb_boards {
 
 extern char igb_driver_name[];
 
+int igb_xmit_xdp_ring(struct igb_adapter *adapter,
+		      struct igb_ring *ring,
+		      struct xdp_frame *xdpf);
 int igb_open(struct net_device *netdev);
 int igb_close(struct net_device *netdev);
 int igb_up(struct igb_adapter *);
diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c
index 6e8231c1ddf0..28baf203459a 100644
--- a/drivers/net/ethernet/intel/igb/igb_ethtool.c
+++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c
@@ -961,6 +961,10 @@ static int igb_set_ringparam(struct net_device *netdev,
 			memcpy(&temp_ring[i], adapter->rx_ring[i],
 			       sizeof(struct igb_ring));
 
+			/* Clear copied XDP RX-queue info */
+			memset(&temp_ring[i].xdp_rxq, 0,
+			       sizeof(temp_ring[i].xdp_rxq));
+
 			temp_ring[i].count = new_rx_count;
 			err = igb_setup_rx_resources(&temp_ring[i]);
 			if (err) {
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index e1e37d0b7703..5fc2c381da55 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -30,6 +30,8 @@
 #include <linux/if_ether.h>
 #include <linux/aer.h>
 #include <linux/prefetch.h>
+#include <linux/bpf.h>
+#include <linux/bpf_trace.h>
 #include <linux/pm_runtime.h>
 #include <linux/etherdevice.h>
 #ifdef CONFIG_IGB_DCA
@@ -549,8 +551,7 @@ exit:
 
 /**
  *  igb_get_i2c_data - Reads the I2C SDA data bit
- *  @hw: pointer to hardware structure
- *  @i2cctl: Current value of I2CCTL register
+ *  @data: opaque pointer to adapter struct
  *
  *  Returns the I2C data bit value
  **/
@@ -2220,7 +2221,6 @@ void igb_down(struct igb_adapter *adapter)
 
 void igb_reinit_locked(struct igb_adapter *adapter)
 {
-	WARN_ON(in_interrupt());
 	while (test_and_set_bit(__IGB_RESETTING, &adapter->state))
 		usleep_range(1000, 2000);
 	igb_down(adapter);
@@ -2824,6 +2824,147 @@ static int igb_setup_tc(struct net_device *dev, enum tc_setup_type type,
 	}
 }
 
+static int igb_xdp_setup(struct net_device *dev, struct bpf_prog *prog)
+{
+	int i, frame_size = dev->mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN;
+	struct igb_adapter *adapter = netdev_priv(dev);
+	bool running = netif_running(dev);
+	struct bpf_prog *old_prog;
+	bool need_reset;
+
+	/* verify igb ring attributes are sufficient for XDP */
+	for (i = 0; i < adapter->num_rx_queues; i++) {
+		struct igb_ring *ring = adapter->rx_ring[i];
+
+		if (frame_size > igb_rx_bufsz(ring))
+			return -EINVAL;
+	}
+
+	old_prog = xchg(&adapter->xdp_prog, prog);
+	need_reset = (!!prog != !!old_prog);
+
+	/* device is up and bpf is added/removed, must setup the RX queues */
+	if (need_reset && running) {
+		igb_close(dev);
+	} else {
+		for (i = 0; i < adapter->num_rx_queues; i++)
+			(void)xchg(&adapter->rx_ring[i]->xdp_prog,
+			    adapter->xdp_prog);
+	}
+
+	if (old_prog)
+		bpf_prog_put(old_prog);
+
+	/* bpf is just replaced, RXQ and MTU are already setup */
+	if (!need_reset)
+		return 0;
+
+	if (running)
+		igb_open(dev);
+
+	return 0;
+}
+
+static int igb_xdp(struct net_device *dev, struct netdev_bpf *xdp)
+{
+	switch (xdp->command) {
+	case XDP_SETUP_PROG:
+		return igb_xdp_setup(dev, xdp->prog);
+	default:
+		return -EINVAL;
+	}
+}
+
+static void igb_xdp_ring_update_tail(struct igb_ring *ring)
+{
+	/* Force memory writes to complete before letting h/w know there
+	 * are new descriptors to fetch.
+	 */
+	wmb();
+	writel(ring->next_to_use, ring->tail);
+}
+
+static struct igb_ring *igb_xdp_tx_queue_mapping(struct igb_adapter *adapter)
+{
+	unsigned int r_idx = smp_processor_id();
+
+	if (r_idx >= adapter->num_tx_queues)
+		r_idx = r_idx % adapter->num_tx_queues;
+
+	return adapter->tx_ring[r_idx];
+}
+
+static int igb_xdp_xmit_back(struct igb_adapter *adapter, struct xdp_buff *xdp)
+{
+	struct xdp_frame *xdpf = xdp_convert_buff_to_frame(xdp);
+	int cpu = smp_processor_id();
+	struct igb_ring *tx_ring;
+	struct netdev_queue *nq;
+	u32 ret;
+
+	if (unlikely(!xdpf))
+		return IGB_XDP_CONSUMED;
+
+	/* During program transitions its possible adapter->xdp_prog is assigned
+	 * but ring has not been configured yet. In this case simply abort xmit.
+	 */
+	tx_ring = adapter->xdp_prog ? igb_xdp_tx_queue_mapping(adapter) : NULL;
+	if (unlikely(!tx_ring))
+		return -ENXIO;
+
+	nq = txring_txq(tx_ring);
+	__netif_tx_lock(nq, cpu);
+	ret = igb_xmit_xdp_ring(adapter, tx_ring, xdpf);
+	__netif_tx_unlock(nq);
+
+	return ret;
+}
+
+static int igb_xdp_xmit(struct net_device *dev, int n,
+			struct xdp_frame **frames, u32 flags)
+{
+	struct igb_adapter *adapter = netdev_priv(dev);
+	int cpu = smp_processor_id();
+	struct igb_ring *tx_ring;
+	struct netdev_queue *nq;
+	int drops = 0;
+	int i;
+
+	if (unlikely(test_bit(__IGB_DOWN, &adapter->state)))
+		return -ENETDOWN;
+
+	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
+		return -EINVAL;
+
+	/* During program transitions its possible adapter->xdp_prog is assigned
+	 * but ring has not been configured yet. In this case simply abort xmit.
+	 */
+	tx_ring = adapter->xdp_prog ? igb_xdp_tx_queue_mapping(adapter) : NULL;
+	if (unlikely(!tx_ring))
+		return -ENXIO;
+
+	nq = txring_txq(tx_ring);
+	__netif_tx_lock(nq, cpu);
+
+	for (i = 0; i < n; i++) {
+		struct xdp_frame *xdpf = frames[i];
+		int err;
+
+		err = igb_xmit_xdp_ring(adapter, tx_ring, xdpf);
+		if (err != IGB_XDP_TX) {
+			xdp_return_frame_rx_napi(xdpf);
+			drops++;
+		}
+	}
+
+	__netif_tx_unlock(nq);
+
+	if (unlikely(flags & XDP_XMIT_FLUSH))
+		igb_xdp_ring_update_tail(tx_ring);
+
+	return n - drops;
+}
+
 static const struct net_device_ops igb_netdev_ops = {
 	.ndo_open		= igb_open,
 	.ndo_stop		= igb_close,
@@ -2848,6 +2989,8 @@ static const struct net_device_ops igb_netdev_ops = {
 	.ndo_fdb_add		= igb_ndo_fdb_add,
 	.ndo_features_check	= igb_features_check,
 	.ndo_setup_tc		= igb_setup_tc,
+	.ndo_bpf		= igb_xdp,
+	.ndo_xdp_xmit		= igb_xdp_xmit,
 };
 
 /**
@@ -3388,7 +3531,9 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 			  "Width x1" : "unknown"), netdev->dev_addr);
 	}
 
-	if ((hw->mac.type >= e1000_i210 ||
+	if ((hw->mac.type == e1000_82576 &&
+	     rd32(E1000_EECD) & E1000_EECD_PRES) ||
+	    (hw->mac.type >= e1000_i210 ||
 	     igb_get_flash_presence_i210(hw))) {
 		ret_val = igb_read_part_string(hw, part_str,
 					       E1000_PBANUM_LENGTH);
@@ -3868,6 +4013,7 @@ static int igb_sw_init(struct igb_adapter *adapter)
 /**
  *  igb_open - Called when a network interface is made active
  *  @netdev: network interface device structure
+ *  @resuming: indicates whether we are in a resume call
  *
  *  Returns 0 on success, negative value on failure
  *
@@ -3985,6 +4131,7 @@ int igb_open(struct net_device *netdev)
 /**
  *  igb_close - Disables a network interface
  *  @netdev: network interface device structure
+ *  @suspending: indicates we are in a suspend call
  *
  *  Returns 0, this is not allowed to fail
  *
@@ -4178,6 +4325,7 @@ static void igb_configure_tx(struct igb_adapter *adapter)
  **/
 int igb_setup_rx_resources(struct igb_ring *rx_ring)
 {
+	struct igb_adapter *adapter = netdev_priv(rx_ring->netdev);
 	struct device *dev = rx_ring->dev;
 	int size;
 
@@ -4200,6 +4348,13 @@ int igb_setup_rx_resources(struct igb_ring *rx_ring)
 	rx_ring->next_to_clean = 0;
 	rx_ring->next_to_use = 0;
 
+	rx_ring->xdp_prog = adapter->xdp_prog;
+
+	/* XDP RX-queue info */
+	if (xdp_rxq_info_reg(&rx_ring->xdp_rxq, rx_ring->netdev,
+			     rx_ring->queue_index) < 0)
+		goto err;
+
 	return 0;
 
 err:
@@ -4504,6 +4659,10 @@ void igb_configure_rx_ring(struct igb_adapter *adapter,
 	int reg_idx = ring->reg_idx;
 	u32 rxdctl = 0;
 
+	xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq);
+	WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
+					   MEM_TYPE_PAGE_SHARED, NULL));
+
 	/* disable the queue */
 	wr32(E1000_RXDCTL(reg_idx), 0);
 
@@ -4708,6 +4867,8 @@ void igb_free_rx_resources(struct igb_ring *rx_ring)
 {
 	igb_clean_rx_ring(rx_ring);
 
+	rx_ring->xdp_prog = NULL;
+	xdp_rxq_info_unreg(&rx_ring->xdp_rxq);
 	vfree(rx_ring->rx_buffer_info);
 	rx_ring->rx_buffer_info = NULL;
 
@@ -5219,7 +5380,7 @@ static void igb_check_lvmmc(struct igb_adapter *adapter)
 
 /**
  *  igb_watchdog - Timer Call-back
- *  @data: pointer to adapter cast into an unsigned long
+ *  @t: pointer to timer_list containing our private info pointer
  **/
 static void igb_watchdog(struct timer_list *t)
 {
@@ -6077,6 +6238,80 @@ dma_error:
 	return -1;
 }
 
+int igb_xmit_xdp_ring(struct igb_adapter *adapter,
+		      struct igb_ring *tx_ring,
+		      struct xdp_frame *xdpf)
+{
+	union e1000_adv_tx_desc *tx_desc;
+	u32 len, cmd_type, olinfo_status;
+	struct igb_tx_buffer *tx_buffer;
+	dma_addr_t dma;
+	u16 i;
+
+	len = xdpf->len;
+
+	if (unlikely(!igb_desc_unused(tx_ring)))
+		return IGB_XDP_CONSUMED;
+
+	dma = dma_map_single(tx_ring->dev, xdpf->data, len, DMA_TO_DEVICE);
+	if (dma_mapping_error(tx_ring->dev, dma))
+		return IGB_XDP_CONSUMED;
+
+	/* record the location of the first descriptor for this packet */
+	tx_buffer = &tx_ring->tx_buffer_info[tx_ring->next_to_use];
+	tx_buffer->bytecount = len;
+	tx_buffer->gso_segs = 1;
+	tx_buffer->protocol = 0;
+
+	i = tx_ring->next_to_use;
+	tx_desc = IGB_TX_DESC(tx_ring, i);
+
+	dma_unmap_len_set(tx_buffer, len, len);
+	dma_unmap_addr_set(tx_buffer, dma, dma);
+	tx_buffer->type = IGB_TYPE_XDP;
+	tx_buffer->xdpf = xdpf;
+
+	tx_desc->read.buffer_addr = cpu_to_le64(dma);
+
+	/* put descriptor type bits */
+	cmd_type = E1000_ADVTXD_DTYP_DATA |
+		   E1000_ADVTXD_DCMD_DEXT |
+		   E1000_ADVTXD_DCMD_IFCS;
+	cmd_type |= len | IGB_TXD_DCMD;
+	tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type);
+
+	olinfo_status = cpu_to_le32(len << E1000_ADVTXD_PAYLEN_SHIFT);
+	/* 82575 requires a unique index per ring */
+	if (test_bit(IGB_RING_FLAG_TX_CTX_IDX, &tx_ring->flags))
+		olinfo_status |= tx_ring->reg_idx << 4;
+
+	tx_desc->read.olinfo_status = olinfo_status;
+
+	netdev_tx_sent_queue(txring_txq(tx_ring), tx_buffer->bytecount);
+
+	/* set the timestamp */
+	tx_buffer->time_stamp = jiffies;
+
+	/* Avoid any potential race with xdp_xmit and cleanup */
+	smp_wmb();
+
+	/* set next_to_watch value indicating a packet is present */
+	i++;
+	if (i == tx_ring->count)
+		i = 0;
+
+	tx_buffer->next_to_watch = tx_desc;
+	tx_ring->next_to_use = i;
+
+	/* Make sure there is space in the ring for the next send. */
+	igb_maybe_stop_tx(tx_ring, DESC_NEEDED);
+
+	if (netif_xmit_stopped(txring_txq(tx_ring)) || !netdev_xmit_more())
+		writel(i, tx_ring->tail);
+
+	return IGB_XDP_TX;
+}
+
 netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb,
 				struct igb_ring *tx_ring)
 {
@@ -6105,6 +6340,7 @@ netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb,
 
 	/* record the location of the first descriptor for this packet */
 	first = &tx_ring->tx_buffer_info[tx_ring->next_to_use];
+	first->type = IGB_TYPE_SKB;
 	first->skb = skb;
 	first->bytecount = skb->len;
 	first->gso_segs = 1;
@@ -6192,8 +6428,9 @@ static netdev_tx_t igb_xmit_frame(struct sk_buff *skb,
 /**
  *  igb_tx_timeout - Respond to a Tx Hang
  *  @netdev: network interface device structure
+ *  @txqueue: number of the Tx queue that hung (unused)
  **/
-static void igb_tx_timeout(struct net_device *netdev, unsigned int txqueue)
+static void igb_tx_timeout(struct net_device *netdev, unsigned int __always_unused txqueue)
 {
 	struct igb_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
@@ -6256,6 +6493,19 @@ static int igb_change_mtu(struct net_device *netdev, int new_mtu)
 	struct igb_adapter *adapter = netdev_priv(netdev);
 	int max_frame = new_mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN;
 
+	if (adapter->xdp_prog) {
+		int i;
+
+		for (i = 0; i < adapter->num_rx_queues; i++) {
+			struct igb_ring *ring = adapter->rx_ring[i];
+
+			if (max_frame > igb_rx_bufsz(ring)) {
+				netdev_warn(adapter->netdev, "Requested MTU size is not supported with XDP\n");
+				return -EINVAL;
+			}
+		}
+	}
+
 	/* adjust max frame to be at least the size of a standard frame */
 	if (max_frame < (ETH_FRAME_LEN + ETH_FCS_LEN))
 		max_frame = ETH_FRAME_LEN + ETH_FCS_LEN;
@@ -7809,7 +8059,10 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector, int napi_budget)
 		total_packets += tx_buffer->gso_segs;
 
 		/* free the skb */
-		napi_consume_skb(tx_buffer->skb, napi_budget);
+		if (tx_buffer->type == IGB_TYPE_SKB)
+			napi_consume_skb(tx_buffer->skb, napi_budget);
+		else
+			xdp_return_frame(tx_buffer->xdpf);
 
 		/* unmap skb header data */
 		dma_unmap_single(tx_ring->dev,
@@ -7993,8 +8246,8 @@ static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer)
 	 * the pagecnt_bias and page count so that we fully restock the
 	 * number of references the driver holds.
 	 */
-	if (unlikely(!pagecnt_bias)) {
-		page_ref_add(page, USHRT_MAX);
+	if (unlikely(pagecnt_bias == 1)) {
+		page_ref_add(page, USHRT_MAX - 1);
 		rx_buffer->pagecnt_bias = USHRT_MAX;
 	}
 
@@ -8033,20 +8286,21 @@ static void igb_add_rx_frag(struct igb_ring *rx_ring,
 
 static struct sk_buff *igb_construct_skb(struct igb_ring *rx_ring,
 					 struct igb_rx_buffer *rx_buffer,
-					 union e1000_adv_rx_desc *rx_desc,
-					 unsigned int size)
+					 struct xdp_buff *xdp,
+					 union e1000_adv_rx_desc *rx_desc)
 {
-	void *va = page_address(rx_buffer->page) + rx_buffer->page_offset;
 #if (PAGE_SIZE < 8192)
 	unsigned int truesize = igb_rx_pg_size(rx_ring) / 2;
 #else
-	unsigned int truesize = SKB_DATA_ALIGN(size);
+	unsigned int truesize = SKB_DATA_ALIGN(xdp->data_end -
+					       xdp->data_hard_start);
 #endif
+	unsigned int size = xdp->data_end - xdp->data;
 	unsigned int headlen;
 	struct sk_buff *skb;
 
 	/* prefetch first cache line of first page */
-	net_prefetch(va);
+	net_prefetch(xdp->data);
 
 	/* allocate a skb to store the frags */
 	skb = napi_alloc_skb(&rx_ring->q_vector->napi, IGB_RX_HDR_LEN);
@@ -8054,24 +8308,24 @@ static struct sk_buff *igb_construct_skb(struct igb_ring *rx_ring,
 		return NULL;
 
 	if (unlikely(igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP))) {
-		igb_ptp_rx_pktstamp(rx_ring->q_vector, va, skb);
-		va += IGB_TS_HDR_LEN;
+		igb_ptp_rx_pktstamp(rx_ring->q_vector, xdp->data, skb);
+		xdp->data += IGB_TS_HDR_LEN;
 		size -= IGB_TS_HDR_LEN;
 	}
 
 	/* Determine available headroom for copy */
 	headlen = size;
 	if (headlen > IGB_RX_HDR_LEN)
-		headlen = eth_get_headlen(skb->dev, va, IGB_RX_HDR_LEN);
+		headlen = eth_get_headlen(skb->dev, xdp->data, IGB_RX_HDR_LEN);
 
 	/* align pull length to size of long to optimize memcpy performance */
-	memcpy(__skb_put(skb, headlen), va, ALIGN(headlen, sizeof(long)));
+	memcpy(__skb_put(skb, headlen), xdp->data, ALIGN(headlen, sizeof(long)));
 
 	/* update all of the pointers */
 	size -= headlen;
 	if (size) {
 		skb_add_rx_frag(skb, 0, rx_buffer->page,
-				(va + headlen) - page_address(rx_buffer->page),
+				(xdp->data + headlen) - page_address(rx_buffer->page),
 				size, truesize);
 #if (PAGE_SIZE < 8192)
 		rx_buffer->page_offset ^= truesize;
@@ -8087,29 +8341,29 @@ static struct sk_buff *igb_construct_skb(struct igb_ring *rx_ring,
 
 static struct sk_buff *igb_build_skb(struct igb_ring *rx_ring,
 				     struct igb_rx_buffer *rx_buffer,
-				     union e1000_adv_rx_desc *rx_desc,
-				     unsigned int size)
+				     struct xdp_buff *xdp,
+				     union e1000_adv_rx_desc *rx_desc)
 {
-	void *va = page_address(rx_buffer->page) + rx_buffer->page_offset;
 #if (PAGE_SIZE < 8192)
 	unsigned int truesize = igb_rx_pg_size(rx_ring) / 2;
 #else
 	unsigned int truesize = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) +
-				SKB_DATA_ALIGN(IGB_SKB_PAD + size);
+				SKB_DATA_ALIGN(xdp->data_end -
+					       xdp->data_hard_start);
 #endif
 	struct sk_buff *skb;
 
 	/* prefetch first cache line of first page */
-	net_prefetch(va);
+	net_prefetch(xdp->data_meta);
 
 	/* build an skb around the page buffer */
-	skb = build_skb(va - IGB_SKB_PAD, truesize);
+	skb = build_skb(xdp->data_hard_start, truesize);
 	if (unlikely(!skb))
 		return NULL;
 
 	/* update pointers within the skb to store the data */
-	skb_reserve(skb, IGB_SKB_PAD);
-	__skb_put(skb, size);
+	skb_reserve(skb, xdp->data - xdp->data_hard_start);
+	__skb_put(skb, xdp->data_end - xdp->data);
 
 	/* pull timestamp out of packet data */
 	if (igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP)) {
@@ -8127,6 +8381,79 @@ static struct sk_buff *igb_build_skb(struct igb_ring *rx_ring,
 	return skb;
 }
 
+static struct sk_buff *igb_run_xdp(struct igb_adapter *adapter,
+				   struct igb_ring *rx_ring,
+				   struct xdp_buff *xdp)
+{
+	int err, result = IGB_XDP_PASS;
+	struct bpf_prog *xdp_prog;
+	u32 act;
+
+	rcu_read_lock();
+	xdp_prog = READ_ONCE(rx_ring->xdp_prog);
+
+	if (!xdp_prog)
+		goto xdp_out;
+
+	prefetchw(xdp->data_hard_start); /* xdp_frame write */
+
+	act = bpf_prog_run_xdp(xdp_prog, xdp);
+	switch (act) {
+	case XDP_PASS:
+		break;
+	case XDP_TX:
+		result = igb_xdp_xmit_back(adapter, xdp);
+		break;
+	case XDP_REDIRECT:
+		err = xdp_do_redirect(adapter->netdev, xdp, xdp_prog);
+		if (!err)
+			result = IGB_XDP_REDIR;
+		else
+			result = IGB_XDP_CONSUMED;
+		break;
+	default:
+		bpf_warn_invalid_xdp_action(act);
+		fallthrough;
+	case XDP_ABORTED:
+		trace_xdp_exception(rx_ring->netdev, xdp_prog, act);
+		fallthrough;
+	case XDP_DROP:
+		result = IGB_XDP_CONSUMED;
+		break;
+	}
+xdp_out:
+	rcu_read_unlock();
+	return ERR_PTR(-result);
+}
+
+static unsigned int igb_rx_frame_truesize(struct igb_ring *rx_ring,
+					  unsigned int size)
+{
+	unsigned int truesize;
+
+#if (PAGE_SIZE < 8192)
+	truesize = igb_rx_pg_size(rx_ring) / 2; /* Must be power-of-2 */
+#else
+	truesize = ring_uses_build_skb(rx_ring) ?
+		SKB_DATA_ALIGN(IGB_SKB_PAD + size) +
+		SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) :
+		SKB_DATA_ALIGN(size);
+#endif
+	return truesize;
+}
+
+static void igb_rx_buffer_flip(struct igb_ring *rx_ring,
+			       struct igb_rx_buffer *rx_buffer,
+			       unsigned int size)
+{
+	unsigned int truesize = igb_rx_frame_truesize(rx_ring, size);
+#if (PAGE_SIZE < 8192)
+	rx_buffer->page_offset ^= truesize;
+#else
+	rx_buffer->page_offset += truesize;
+#endif
+}
+
 static inline void igb_rx_checksum(struct igb_ring *ring,
 				   union e1000_adv_rx_desc *rx_desc,
 				   struct sk_buff *skb)
@@ -8181,7 +8508,6 @@ static inline void igb_rx_hash(struct igb_ring *ring,
  *  igb_is_non_eop - process handling of non-EOP buffers
  *  @rx_ring: Rx ring being processed
  *  @rx_desc: Rx descriptor for current buffer
- *  @skb: current socket buffer containing buffer in progress
  *
  *  This function updates next to clean.  If the buffer is an EOP buffer
  *  this function exits returning false, otherwise it will place the
@@ -8223,6 +8549,10 @@ static bool igb_cleanup_headers(struct igb_ring *rx_ring,
 				union e1000_adv_rx_desc *rx_desc,
 				struct sk_buff *skb)
 {
+	/* XDP packets use error pointer so abort at this point */
+	if (IS_ERR(skb))
+		return true;
+
 	if (unlikely((igb_test_staterr(rx_desc,
 				       E1000_RXDEXT_ERR_FRAME_ERR_MASK)))) {
 		struct net_device *netdev = rx_ring->netdev;
@@ -8281,6 +8611,11 @@ static void igb_process_skb_fields(struct igb_ring *rx_ring,
 	skb->protocol = eth_type_trans(skb, rx_ring->netdev);
 }
 
+static unsigned int igb_rx_offset(struct igb_ring *rx_ring)
+{
+	return ring_uses_build_skb(rx_ring) ? IGB_SKB_PAD : 0;
+}
+
 static struct igb_rx_buffer *igb_get_rx_buffer(struct igb_ring *rx_ring,
 					       const unsigned int size)
 {
@@ -8324,10 +8659,20 @@ static void igb_put_rx_buffer(struct igb_ring *rx_ring,
 
 static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
 {
+	struct igb_adapter *adapter = q_vector->adapter;
 	struct igb_ring *rx_ring = q_vector->rx.ring;
 	struct sk_buff *skb = rx_ring->skb;
 	unsigned int total_bytes = 0, total_packets = 0;
 	u16 cleaned_count = igb_desc_unused(rx_ring);
+	unsigned int xdp_xmit = 0;
+	struct xdp_buff xdp;
+
+	xdp.rxq = &rx_ring->xdp_rxq;
+
+	/* Frame size depend on rx_ring setup when PAGE_SIZE=4K */
+#if (PAGE_SIZE < 8192)
+	xdp.frame_sz = igb_rx_frame_truesize(rx_ring, 0);
+#endif
 
 	while (likely(total_packets < budget)) {
 		union e1000_adv_rx_desc *rx_desc;
@@ -8354,13 +8699,38 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
 		rx_buffer = igb_get_rx_buffer(rx_ring, size);
 
 		/* retrieve a buffer from the ring */
-		if (skb)
+		if (!skb) {
+			xdp.data = page_address(rx_buffer->page) +
+				   rx_buffer->page_offset;
+			xdp.data_meta = xdp.data;
+			xdp.data_hard_start = xdp.data -
+					      igb_rx_offset(rx_ring);
+			xdp.data_end = xdp.data + size;
+#if (PAGE_SIZE > 4096)
+			/* At larger PAGE_SIZE, frame_sz depend on len size */
+			xdp.frame_sz = igb_rx_frame_truesize(rx_ring, size);
+#endif
+			skb = igb_run_xdp(adapter, rx_ring, &xdp);
+		}
+
+		if (IS_ERR(skb)) {
+			unsigned int xdp_res = -PTR_ERR(skb);
+
+			if (xdp_res & (IGB_XDP_TX | IGB_XDP_REDIR)) {
+				xdp_xmit |= xdp_res;
+				igb_rx_buffer_flip(rx_ring, rx_buffer, size);
+			} else {
+				rx_buffer->pagecnt_bias++;
+			}
+			total_packets++;
+			total_bytes += size;
+		} else if (skb)
 			igb_add_rx_frag(rx_ring, rx_buffer, skb, size);
 		else if (ring_uses_build_skb(rx_ring))
-			skb = igb_build_skb(rx_ring, rx_buffer, rx_desc, size);
+			skb = igb_build_skb(rx_ring, rx_buffer, &xdp, rx_desc);
 		else
 			skb = igb_construct_skb(rx_ring, rx_buffer,
-						rx_desc, size);
+						&xdp, rx_desc);
 
 		/* exit if we failed to retrieve a buffer */
 		if (!skb) {
@@ -8400,6 +8770,15 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
 	/* place incomplete frames back on ring for completion */
 	rx_ring->skb = skb;
 
+	if (xdp_xmit & IGB_XDP_REDIR)
+		xdp_do_flush_map();
+
+	if (xdp_xmit & IGB_XDP_TX) {
+		struct igb_ring *tx_ring = igb_xdp_tx_queue_mapping(adapter);
+
+		igb_xdp_ring_update_tail(tx_ring);
+	}
+
 	u64_stats_update_begin(&rx_ring->rx_syncp);
 	rx_ring->rx_stats.packets += total_packets;
 	rx_ring->rx_stats.bytes += total_bytes;
@@ -8413,11 +8792,6 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
 	return total_packets;
 }
 
-static inline unsigned int igb_rx_offset(struct igb_ring *rx_ring)
-{
-	return ring_uses_build_skb(rx_ring) ? IGB_SKB_PAD : 0;
-}
-
 static bool igb_alloc_mapped_page(struct igb_ring *rx_ring,
 				  struct igb_rx_buffer *bi)
 {
@@ -8454,14 +8828,16 @@ static bool igb_alloc_mapped_page(struct igb_ring *rx_ring,
 	bi->dma = dma;
 	bi->page = page;
 	bi->page_offset = igb_rx_offset(rx_ring);
-	bi->pagecnt_bias = 1;
+	page_ref_add(page, USHRT_MAX - 1);
+	bi->pagecnt_bias = USHRT_MAX;
 
 	return true;
 }
 
 /**
- *  igb_alloc_rx_buffers - Replace used receive buffers; packet split
- *  @adapter: address of board private structure
+ *  igb_alloc_rx_buffers - Replace used receive buffers
+ *  @rx_ring: rx descriptor ring to allocate new receive buffers
+ *  @cleaned_count: count of buffers to allocate
  **/
 void igb_alloc_rx_buffers(struct igb_ring *rx_ring, u16 cleaned_count)
 {
@@ -8530,9 +8906,9 @@ void igb_alloc_rx_buffers(struct igb_ring *rx_ring, u16 cleaned_count)
 
 /**
  * igb_mii_ioctl -
- * @netdev:
- * @ifreq:
- * @cmd:
+ * @netdev: pointer to netdev struct
+ * @ifr: interface structure
+ * @cmd: ioctl command to execute
  **/
 static int igb_mii_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
 {
@@ -8560,9 +8936,9 @@ static int igb_mii_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
 
 /**
  * igb_ioctl -
- * @netdev:
- * @ifreq:
- * @cmd:
+ * @netdev: pointer to netdev struct
+ * @ifr: interface structure
+ * @cmd: ioctl command to execute
  **/
 static int igb_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
 {
diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c
index 490368d3d03c..7cc5428c3b3d 100644
--- a/drivers/net/ethernet/intel/igb/igb_ptp.c
+++ b/drivers/net/ethernet/intel/igb/igb_ptp.c
@@ -957,8 +957,8 @@ void igb_ptp_rx_rgtstamp(struct igb_q_vector *q_vector,
 
 /**
  * igb_ptp_get_ts_config - get hardware time stamping config
- * @netdev:
- * @ifreq:
+ * @netdev: netdev struct
+ * @ifr: interface struct
  *
  * Get the hwtstamp_config settings to return to the user. Rather than attempt
  * to deconstruct the settings from the registers, just return a shadow copy
@@ -1141,8 +1141,8 @@ static int igb_ptp_set_timestamp_mode(struct igb_adapter *adapter,
 
 /**
  * igb_ptp_set_ts_config - set hardware time stamping config
- * @netdev:
- * @ifreq:
+ * @netdev: netdev struct
+ * @ifr: interface struct
  *
  **/
 int igb_ptp_set_ts_config(struct net_device *netdev, struct ifreq *ifr)
diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c
index 19269f5d52bc..ee9f8c1dca83 100644
--- a/drivers/net/ethernet/intel/igbvf/netdev.c
+++ b/drivers/net/ethernet/intel/igbvf/netdev.c
@@ -61,7 +61,7 @@ static const struct igbvf_info *igbvf_info_tbl[] = {
 
 /**
  * igbvf_desc_unused - calculate if we have unused descriptors
- * @rx_ring: address of receive ring structure
+ * @ring: address of receive ring structure
  **/
 static int igbvf_desc_unused(struct igbvf_ring *ring)
 {
@@ -74,6 +74,8 @@ static int igbvf_desc_unused(struct igbvf_ring *ring)
 /**
  * igbvf_receive_skb - helper function to handle Rx indications
  * @adapter: board private structure
+ * @netdev: pointer to netdev struct
+ * @skb: skb to indicate to stack
  * @status: descriptor status field as written by hardware
  * @vlan: descriptor vlan field as written by hardware (no le/be conversion)
  * @skb: pointer to sk_buff to be indicated to stack
@@ -233,6 +235,8 @@ no_buffers:
 /**
  * igbvf_clean_rx_irq - Send received data up the network stack; legacy
  * @adapter: board private structure
+ * @work_done: output parameter used to indicate completed work
+ * @work_to_do: input parameter setting limit of work
  *
  * the return value indicates whether actual cleaning was done, there
  * is no guarantee that everything was cleaned
@@ -406,6 +410,7 @@ static void igbvf_put_txbuf(struct igbvf_adapter *adapter,
 /**
  * igbvf_setup_tx_resources - allocate Tx resources (Descriptors)
  * @adapter: board private structure
+ * @tx_ring: ring being initialized
  *
  * Return 0 on success, negative on failure
  **/
@@ -444,6 +449,7 @@ err:
 /**
  * igbvf_setup_rx_resources - allocate Rx resources (Descriptors)
  * @adapter: board private structure
+ * @rx_ring: ring being initialized
  *
  * Returns 0 on success, negative on failure
  **/
@@ -540,7 +546,7 @@ void igbvf_free_tx_resources(struct igbvf_ring *tx_ring)
 
 /**
  * igbvf_clean_rx_ring - Free Rx Buffers per Queue
- * @adapter: board private structure
+ * @rx_ring: ring structure pointer to free buffers from
  **/
 static void igbvf_clean_rx_ring(struct igbvf_ring *rx_ring)
 {
@@ -760,7 +766,7 @@ static void igbvf_set_itr(struct igbvf_adapter *adapter)
 
 /**
  * igbvf_clean_tx_irq - Reclaim resources after transmit completes
- * @adapter: board private structure
+ * @tx_ring: ring structure to clean descriptors from
  *
  * returns true if ring is completely cleaned
  **/
@@ -1891,7 +1897,7 @@ static bool igbvf_has_link(struct igbvf_adapter *adapter)
 
 /**
  * igbvf_watchdog - Timer Call-back
- * @data: pointer to adapter cast into an unsigned long
+ * @t: timer list pointer containing private struct
  **/
 static void igbvf_watchdog(struct timer_list *t)
 {
@@ -2372,8 +2378,9 @@ static netdev_tx_t igbvf_xmit_frame(struct sk_buff *skb,
 /**
  * igbvf_tx_timeout - Respond to a Tx Hang
  * @netdev: network interface device structure
+ * @txqueue: queue timing out (unused)
  **/
-static void igbvf_tx_timeout(struct net_device *netdev, unsigned int txqueue)
+static void igbvf_tx_timeout(struct net_device *netdev, unsigned int __always_unused txqueue)
 {
 	struct igbvf_adapter *adapter = netdev_priv(netdev);
 
diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
index 3070dfdb7eb4..35baae900c1f 100644
--- a/drivers/net/ethernet/intel/igc/igc.h
+++ b/drivers/net/ethernet/intel/igc/igc.h
@@ -215,6 +215,8 @@ struct igc_adapter {
 	spinlock_t tmreg_lock;
 	struct cyclecounter cc;
 	struct timecounter tc;
+	struct timespec64 prev_ptp_time; /* Pre-reset PTP clock */
+	ktime_t ptp_reset_start; /* Reset time in clock mono */
 };
 
 void igc_up(struct igc_adapter *adapter);
@@ -299,18 +301,14 @@ extern char igc_driver_name[];
 #define IGC_RX_HDR_LEN			IGC_RXBUFFER_256
 
 /* Transmit and receive latency (for PTP timestamps) */
-/* FIXME: These values were estimated using the ones that i225 has as
- * basis, they seem to provide good numbers with ptp4l/phc2sys, but we
- * need to confirm them.
- */
-#define IGC_I225_TX_LATENCY_10		9542
-#define IGC_I225_TX_LATENCY_100		1024
-#define IGC_I225_TX_LATENCY_1000	178
-#define IGC_I225_TX_LATENCY_2500	64
-#define IGC_I225_RX_LATENCY_10		20662
-#define IGC_I225_RX_LATENCY_100		2213
-#define IGC_I225_RX_LATENCY_1000	448
-#define IGC_I225_RX_LATENCY_2500	160
+#define IGC_I225_TX_LATENCY_10		240
+#define IGC_I225_TX_LATENCY_100		58
+#define IGC_I225_TX_LATENCY_1000	80
+#define IGC_I225_TX_LATENCY_2500	1325
+#define IGC_I225_RX_LATENCY_10		6450
+#define IGC_I225_RX_LATENCY_100		185
+#define IGC_I225_RX_LATENCY_1000	300
+#define IGC_I225_RX_LATENCY_2500	1485
 
 /* RX and TX descriptor control thresholds.
  * PTHRESH - MAC will consider prefetch if it has fewer than this number of
@@ -552,6 +550,7 @@ void igc_ptp_rx_pktstamp(struct igc_q_vector *q_vector, void *va,
 int igc_ptp_set_ts_config(struct net_device *netdev, struct ifreq *ifr);
 int igc_ptp_get_ts_config(struct net_device *netdev, struct ifreq *ifr);
 void igc_ptp_tx_hang(struct igc_adapter *adapter);
+void igc_ptp_read(struct igc_adapter *adapter, struct timespec64 *ts);
 
 #define igc_rx_pg_size(_ring) (PAGE_SIZE << igc_rx_pg_order(_ring))
 
diff --git a/drivers/net/ethernet/intel/igc/igc_base.c b/drivers/net/ethernet/intel/igc/igc_base.c
index cc5a6cf531c7..fd37d2c203af 100644
--- a/drivers/net/ethernet/intel/igc/igc_base.c
+++ b/drivers/net/ethernet/intel/igc/igc_base.c
@@ -215,6 +215,11 @@ static s32 igc_get_invariants_base(struct igc_hw *hw)
 	case IGC_DEV_ID_I225_K2:
 	case IGC_DEV_ID_I225_LMVP:
 	case IGC_DEV_ID_I225_IT:
+	case IGC_DEV_ID_I226_LM:
+	case IGC_DEV_ID_I226_V:
+	case IGC_DEV_ID_I226_IT:
+	case IGC_DEV_ID_I221_V:
+	case IGC_DEV_ID_I226_BLANK_NVM:
 	case IGC_DEV_ID_I225_BLANK_NVM:
 		mac->type = igc_i225;
 		break;
diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h
index f1f464967f87..32f5fd684139 100644
--- a/drivers/net/ethernet/intel/igc/igc_defines.h
+++ b/drivers/net/ethernet/intel/igc/igc_defines.h
@@ -324,22 +324,10 @@
 /* Advanced Receive Descriptor bit definitions */
 #define IGC_RXDADV_STAT_TSIP	0x08000 /* timestamp in packet */
 
-#define IGC_RXDEXT_STATERR_CE		0x01000000
-#define IGC_RXDEXT_STATERR_SE		0x02000000
-#define IGC_RXDEXT_STATERR_SEQ		0x04000000
-#define IGC_RXDEXT_STATERR_CXE		0x10000000
-#define IGC_RXDEXT_STATERR_TCPE		0x20000000
+#define IGC_RXDEXT_STATERR_L4E		0x20000000
 #define IGC_RXDEXT_STATERR_IPE		0x40000000
 #define IGC_RXDEXT_STATERR_RXE		0x80000000
 
-/* Same mask, but for extended and packet split descriptors */
-#define IGC_RXDEXT_ERR_FRAME_ERR_MASK ( \
-	IGC_RXDEXT_STATERR_CE  |	\
-	IGC_RXDEXT_STATERR_SE  |	\
-	IGC_RXDEXT_STATERR_SEQ |	\
-	IGC_RXDEXT_STATERR_CXE |	\
-	IGC_RXDEXT_STATERR_RXE)
-
 #define IGC_MRQC_RSS_FIELD_IPV4_TCP	0x00010000
 #define IGC_MRQC_RSS_FIELD_IPV4		0x00020000
 #define IGC_MRQC_RSS_FIELD_IPV6_TCP_EX	0x00040000
@@ -409,7 +397,7 @@
 #define IGC_IMIREXT_SIZE_BP	0x00001000  /* Packet size bypass */
 
 /* Time Sync Transmit Control bit definitions */
-#define IGC_TSYNCTXCTL_VALID			0x00000001  /* Tx timestamp valid */
+#define IGC_TSYNCTXCTL_TXTT_0			0x00000001  /* Tx timestamp reg 0 valid */
 #define IGC_TSYNCTXCTL_ENABLED			0x00000010  /* enable Tx timestamping */
 #define IGC_TSYNCTXCTL_MAX_ALLOWED_DLY_MASK	0x0000F000  /* max delay */
 #define IGC_TSYNCTXCTL_SYNC_COMP_ERR		0x20000000  /* sync err */
diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c
index 44410c2265d6..61d331ce38cd 100644
--- a/drivers/net/ethernet/intel/igc/igc_ethtool.c
+++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c
@@ -321,6 +321,9 @@ static void igc_ethtool_get_regs(struct net_device *netdev,
 
 	for (i = 0; i < 8; i++)
 		regs_buff[205 + i] = rd32(IGC_ETQF(i));
+
+	regs_buff[213] = adapter->stats.tlpic;
+	regs_buff[214] = adapter->stats.rlpic;
 }
 
 static void igc_ethtool_get_wol(struct net_device *netdev,
diff --git a/drivers/net/ethernet/intel/igc/igc_hw.h b/drivers/net/ethernet/intel/igc/igc_hw.h
index b9fe51b91c47..55dae7c4703f 100644
--- a/drivers/net/ethernet/intel/igc/igc_hw.h
+++ b/drivers/net/ethernet/intel/igc/igc_hw.h
@@ -24,6 +24,11 @@
 #define IGC_DEV_ID_I225_K2			0x3101
 #define IGC_DEV_ID_I225_LMVP			0x5502
 #define IGC_DEV_ID_I225_IT			0x0D9F
+#define IGC_DEV_ID_I226_LM			0x125B
+#define IGC_DEV_ID_I226_V			0x125C
+#define IGC_DEV_ID_I226_IT			0x125D
+#define IGC_DEV_ID_I221_V			0x125E
+#define IGC_DEV_ID_I226_BLANK_NVM		0x125F
 #define IGC_DEV_ID_I225_BLANK_NVM		0x15FD
 
 /* Function pointers for the MAC. */
@@ -125,9 +130,6 @@ struct igc_nvm_info {
 	struct igc_nvm_operations ops;
 	enum igc_nvm_type type;
 
-	u32 flash_bank_size;
-	u32 flash_base_addr;
-
 	u16 word_size;
 	u16 delay_usec;
 	u16 address_bits;
@@ -153,7 +155,6 @@ struct igc_phy_info {
 	u8 mdix;
 
 	bool is_mdix;
-	bool reset_disable;
 	bool speed_downgraded;
 	bool autoneg_wait_to_complete;
 };
@@ -239,6 +240,8 @@ struct igc_hw_stats {
 	u64 prc511;
 	u64 prc1023;
 	u64 prc1522;
+	u64 tlpic;
+	u64 rlpic;
 	u64 gprc;
 	u64 bprc;
 	u64 mprc;
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index c6968fdb6caa..9112dff075cf 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -47,6 +47,11 @@ static const struct pci_device_id igc_pci_tbl[] = {
 	{ PCI_VDEVICE(INTEL, IGC_DEV_ID_I225_K2), board_base },
 	{ PCI_VDEVICE(INTEL, IGC_DEV_ID_I225_LMVP), board_base },
 	{ PCI_VDEVICE(INTEL, IGC_DEV_ID_I225_IT), board_base },
+	{ PCI_VDEVICE(INTEL, IGC_DEV_ID_I226_LM), board_base },
+	{ PCI_VDEVICE(INTEL, IGC_DEV_ID_I226_V), board_base },
+	{ PCI_VDEVICE(INTEL, IGC_DEV_ID_I226_IT), board_base },
+	{ PCI_VDEVICE(INTEL, IGC_DEV_ID_I221_V), board_base },
+	{ PCI_VDEVICE(INTEL, IGC_DEV_ID_I226_BLANK_NVM), board_base },
 	{ PCI_VDEVICE(INTEL, IGC_DEV_ID_I225_BLANK_NVM), board_base },
 	/* required last entry */
 	{0, }
@@ -1428,7 +1433,7 @@ static void igc_rx_checksum(struct igc_ring *ring,
 
 	/* TCP/UDP checksum error bit is set */
 	if (igc_test_staterr(rx_desc,
-			     IGC_RXDEXT_STATERR_TCPE |
+			     IGC_RXDEXT_STATERR_L4E |
 			     IGC_RXDEXT_STATERR_IPE)) {
 		/* work around errata with sctp packets where the TCPE aka
 		 * L4E bit is set incorrectly on 64 byte (60 byte w/o crc)
@@ -1737,8 +1742,7 @@ static bool igc_cleanup_headers(struct igc_ring *rx_ring,
 				union igc_adv_rx_desc *rx_desc,
 				struct sk_buff *skb)
 {
-	if (unlikely((igc_test_staterr(rx_desc,
-				       IGC_RXDEXT_ERR_FRAME_ERR_MASK)))) {
+	if (unlikely(igc_test_staterr(rx_desc, IGC_RXDEXT_STATERR_RXE))) {
 		struct net_device *netdev = rx_ring->netdev;
 
 		if (!(netdev->features & NETIF_F_RXALL)) {
@@ -3679,6 +3683,8 @@ void igc_update_stats(struct igc_adapter *adapter)
 	adapter->stats.prc511 += rd32(IGC_PRC511);
 	adapter->stats.prc1023 += rd32(IGC_PRC1023);
 	adapter->stats.prc1522 += rd32(IGC_PRC1522);
+	adapter->stats.tlpic += rd32(IGC_TLPIC);
+	adapter->stats.rlpic += rd32(IGC_RLPIC);
 
 	mpc = rd32(IGC_MPC);
 	adapter->stats.mpc += mpc;
@@ -3772,6 +3778,8 @@ void igc_down(struct igc_adapter *adapter)
 
 	set_bit(__IGC_DOWN, &adapter->state);
 
+	igc_ptp_suspend(adapter);
+
 	/* disable receives in the hardware */
 	rctl = rd32(IGC_RCTL);
 	wr32(IGC_RCTL, rctl & ~IGC_RCTL_EN);
@@ -3825,7 +3833,6 @@ void igc_down(struct igc_adapter *adapter)
 
 void igc_reinit_locked(struct igc_adapter *adapter)
 {
-	WARN_ON(in_interrupt());
 	while (test_and_set_bit(__IGC_RESETTING, &adapter->state))
 		usleep_range(1000, 2000);
 	igc_down(adapter);
@@ -4653,7 +4660,7 @@ int igc_close(struct net_device *netdev)
 /**
  * igc_ioctl - Access the hwtstamp interface
  * @netdev: network interface device structure
- * @ifreq: interface request data
+ * @ifr: interface request data
  * @cmd: ioctl command
  **/
 static int igc_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
@@ -4694,14 +4701,35 @@ static int igc_save_launchtime_params(struct igc_adapter *adapter, int queue,
 	return 0;
 }
 
-static bool validate_schedule(const struct tc_taprio_qopt_offload *qopt)
+static bool is_base_time_past(ktime_t base_time, const struct timespec64 *now)
+{
+	struct timespec64 b;
+
+	b = ktime_to_timespec64(base_time);
+
+	return timespec64_compare(now, &b) > 0;
+}
+
+static bool validate_schedule(struct igc_adapter *adapter,
+			      const struct tc_taprio_qopt_offload *qopt)
 {
 	int queue_uses[IGC_MAX_TX_QUEUES] = { };
+	struct timespec64 now;
 	size_t n;
 
 	if (qopt->cycle_time_extension)
 		return false;
 
+	igc_ptp_read(adapter, &now);
+
+	/* If we program the controller's BASET registers with a time
+	 * in the future, it will hold all the packets until that
+	 * time, causing a lot of TX Hangs, so to avoid that, we
+	 * reject schedules that would start in the future.
+	 */
+	if (!is_base_time_past(qopt->base_time, &now))
+		return false;
+
 	for (n = 0; n < qopt->num_entries; n++) {
 		const struct tc_taprio_sched_entry *e;
 		int i;
@@ -4756,7 +4784,7 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter,
 	if (adapter->base_time)
 		return -EALREADY;
 
-	if (!validate_schedule(qopt))
+	if (!validate_schedule(adapter, qopt))
 		return -EINVAL;
 
 	adapter->cycle_time = qopt->cycle_time;
diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c
index 36c999250fcc..ac0b9c85da7c 100644
--- a/drivers/net/ethernet/intel/igc/igc_ptp.c
+++ b/drivers/net/ethernet/intel/igc/igc_ptp.c
@@ -8,6 +8,7 @@
 #include <linux/pci.h>
 #include <linux/ptp_classify.h>
 #include <linux/clocksource.h>
+#include <linux/ktime.h>
 
 #define INCVALUE_MASK		0x7fffffff
 #define ISGN			0x80000000
@@ -16,17 +17,12 @@
 #define IGC_PTP_TX_TIMEOUT		(HZ * 15)
 
 /* SYSTIM read access for I225 */
-static void igc_ptp_read_i225(struct igc_adapter *adapter,
-			      struct timespec64 *ts)
+void igc_ptp_read(struct igc_adapter *adapter, struct timespec64 *ts)
 {
 	struct igc_hw *hw = &adapter->hw;
 	u32 sec, nsec;
 
-	/* The timestamp latches on lowest register read. For I210/I211, the
-	 * lowest register is SYSTIMR. Since we only need to provide nanosecond
-	 * resolution, we can ignore it.
-	 */
-	rd32(IGC_SYSTIMR);
+	/* The timestamp is latched when SYSTIML is read. */
 	nsec = rd32(IGC_SYSTIML);
 	sec = rd32(IGC_SYSTIMH);
 
@@ -39,9 +35,6 @@ static void igc_ptp_write_i225(struct igc_adapter *adapter,
 {
 	struct igc_hw *hw = &adapter->hw;
 
-	/* Writing the SYSTIMR register is not necessary as it only
-	 * provides sub-nanosecond resolution.
-	 */
 	wr32(IGC_SYSTIML, ts->tv_nsec);
 	wr32(IGC_SYSTIMH, ts->tv_sec);
 }
@@ -81,7 +74,7 @@ static int igc_ptp_adjtime_i225(struct ptp_clock_info *ptp, s64 delta)
 
 	spin_lock_irqsave(&igc->tmreg_lock, flags);
 
-	igc_ptp_read_i225(igc, &now);
+	igc_ptp_read(igc, &now);
 	now = timespec64_add(now, then);
 	igc_ptp_write_i225(igc, (const struct timespec64 *)&now);
 
@@ -102,10 +95,9 @@ static int igc_ptp_gettimex64_i225(struct ptp_clock_info *ptp,
 	spin_lock_irqsave(&igc->tmreg_lock, flags);
 
 	ptp_read_system_prets(sts);
-	rd32(IGC_SYSTIMR);
-	ptp_read_system_postts(sts);
 	ts->tv_nsec = rd32(IGC_SYSTIML);
 	ts->tv_sec = rd32(IGC_SYSTIMH);
+	ptp_read_system_postts(sts);
 
 	spin_unlock_irqrestore(&igc->tmreg_lock, flags);
 
@@ -364,6 +356,7 @@ static void igc_ptp_tx_hwtstamp(struct igc_adapter *adapter)
 	struct sk_buff *skb = adapter->ptp_tx_skb;
 	struct skb_shared_hwtstamps shhwtstamps;
 	struct igc_hw *hw = &adapter->hw;
+	int adjust = 0;
 	u64 regval;
 
 	if (WARN_ON_ONCE(!skb))
@@ -373,6 +366,24 @@ static void igc_ptp_tx_hwtstamp(struct igc_adapter *adapter)
 	regval |= (u64)rd32(IGC_TXSTMPH) << 32;
 	igc_ptp_systim_to_hwtstamp(adapter, &shhwtstamps, regval);
 
+	switch (adapter->link_speed) {
+	case SPEED_10:
+		adjust = IGC_I225_TX_LATENCY_10;
+		break;
+	case SPEED_100:
+		adjust = IGC_I225_TX_LATENCY_100;
+		break;
+	case SPEED_1000:
+		adjust = IGC_I225_TX_LATENCY_1000;
+		break;
+	case SPEED_2500:
+		adjust = IGC_I225_TX_LATENCY_2500;
+		break;
+	}
+
+	shhwtstamps.hwtstamp =
+		ktime_add_ns(shhwtstamps.hwtstamp, adjust);
+
 	/* Clear the lock early before calling skb_tstamp_tx so that
 	 * applications are not woken up before the lock bit is clear. We use
 	 * a copy of the skb pointer to ensure other threads can't change it
@@ -403,24 +414,17 @@ static void igc_ptp_tx_work(struct work_struct *work)
 	if (!test_bit(__IGC_PTP_TX_IN_PROGRESS, &adapter->state))
 		return;
 
-	if (time_is_before_jiffies(adapter->ptp_tx_start +
-				   IGC_PTP_TX_TIMEOUT)) {
-		igc_ptp_tx_timeout(adapter);
+	tsynctxctl = rd32(IGC_TSYNCTXCTL);
+	if (WARN_ON_ONCE(!(tsynctxctl & IGC_TSYNCTXCTL_TXTT_0)))
 		return;
-	}
 
-	tsynctxctl = rd32(IGC_TSYNCTXCTL);
-	if (tsynctxctl & IGC_TSYNCTXCTL_VALID)
-		igc_ptp_tx_hwtstamp(adapter);
-	else
-		/* reschedule to check later */
-		schedule_work(&adapter->ptp_tx_work);
+	igc_ptp_tx_hwtstamp(adapter);
 }
 
 /**
  * igc_ptp_set_ts_config - set hardware time stamping config
  * @netdev: network interface device structure
- * @ifreq: interface request data
+ * @ifr: interface request data
  *
  **/
 int igc_ptp_set_ts_config(struct net_device *netdev, struct ifreq *ifr)
@@ -447,7 +451,7 @@ int igc_ptp_set_ts_config(struct net_device *netdev, struct ifreq *ifr)
 /**
  * igc_ptp_get_ts_config - get hardware time stamping config
  * @netdev: network interface device structure
- * @ifreq: interface request data
+ * @ifr: interface request data
  *
  * Get the hwtstamp_config settings to return to the user. Rather than attempt
  * to deconstruct the settings from the registers, just return a shadow copy
@@ -496,6 +500,9 @@ void igc_ptp_init(struct igc_adapter *adapter)
 	adapter->tstamp_config.rx_filter = HWTSTAMP_FILTER_NONE;
 	adapter->tstamp_config.tx_type = HWTSTAMP_TX_OFF;
 
+	adapter->prev_ptp_time = ktime_to_timespec64(ktime_get_real());
+	adapter->ptp_reset_start = ktime_get();
+
 	adapter->ptp_clock = ptp_clock_register(&adapter->ptp_caps,
 						&adapter->pdev->dev);
 	if (IS_ERR(adapter->ptp_clock)) {
@@ -507,6 +514,24 @@ void igc_ptp_init(struct igc_adapter *adapter)
 	}
 }
 
+static void igc_ptp_time_save(struct igc_adapter *adapter)
+{
+	igc_ptp_read(adapter, &adapter->prev_ptp_time);
+	adapter->ptp_reset_start = ktime_get();
+}
+
+static void igc_ptp_time_restore(struct igc_adapter *adapter)
+{
+	struct timespec64 ts = adapter->prev_ptp_time;
+	ktime_t delta;
+
+	delta = ktime_sub(ktime_get(), adapter->ptp_reset_start);
+
+	timespec64_add_ns(&ts, ktime_to_ns(delta));
+
+	igc_ptp_write_i225(adapter, &ts);
+}
+
 /**
  * igc_ptp_suspend - Disable PTP work items and prepare for suspend
  * @adapter: Board private structure
@@ -523,6 +548,8 @@ void igc_ptp_suspend(struct igc_adapter *adapter)
 	dev_kfree_skb_any(adapter->ptp_tx_skb);
 	adapter->ptp_tx_skb = NULL;
 	clear_bit_unlock(__IGC_PTP_TX_IN_PROGRESS, &adapter->state);
+
+	igc_ptp_time_save(adapter);
 }
 
 /**
@@ -572,9 +599,7 @@ void igc_ptp_reset(struct igc_adapter *adapter)
 
 	/* Re-initialize the timer. */
 	if (hw->mac.type == igc_i225) {
-		struct timespec64 ts64 = ktime_to_timespec64(ktime_get_real());
-
-		igc_ptp_write_i225(adapter, &ts64);
+		igc_ptp_time_restore(adapter);
 	} else {
 		timecounter_init(&adapter->tc, &adapter->cc,
 				 ktime_to_ns(ktime_get_real()));
diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_hw.c b/drivers/net/ethernet/intel/ixgb/ixgb_hw.c
index cbaa933ef30d..a430871d1c27 100644
--- a/drivers/net/ethernet/intel/ixgb/ixgb_hw.c
+++ b/drivers/net/ethernet/intel/ixgb/ixgb_hw.c
@@ -98,7 +98,6 @@ bool
 ixgb_adapter_stop(struct ixgb_hw *hw)
 {
 	u32 ctrl_reg;
-	u32 icr_reg;
 
 	ENTER();
 
@@ -142,7 +141,7 @@ ixgb_adapter_stop(struct ixgb_hw *hw)
 	IXGB_WRITE_REG(hw, IMC, 0xffffffff);
 
 	/* Clear any pending interrupt events. */
-	icr_reg = IXGB_READ_REG(hw, ICR);
+	IXGB_READ_REG(hw, ICR);
 
 	return ctrl_reg & IXGB_CTRL0_RST;
 }
@@ -274,7 +273,6 @@ bool
 ixgb_init_hw(struct ixgb_hw *hw)
 {
 	u32 i;
-	u32 ctrl_reg;
 	bool status;
 
 	ENTER();
@@ -286,7 +284,7 @@ ixgb_init_hw(struct ixgb_hw *hw)
 	 */
 	pr_debug("Issuing a global reset to MAC\n");
 
-	ctrl_reg = ixgb_mac_reset(hw);
+	ixgb_mac_reset(hw);
 
 	pr_debug("Issuing an EE reset to MAC\n");
 #ifdef HP_ZX1
@@ -949,8 +947,6 @@ bool ixgb_check_for_bad_link(struct ixgb_hw *hw)
 static void
 ixgb_clear_hw_cntrs(struct ixgb_hw *hw)
 {
-	volatile u32 temp_reg;
-
 	ENTER();
 
 	/* if we are stopped or resetting exit gracefully */
@@ -959,66 +955,66 @@ ixgb_clear_hw_cntrs(struct ixgb_hw *hw)
 		return;
 	}
 
-	temp_reg = IXGB_READ_REG(hw, TPRL);
-	temp_reg = IXGB_READ_REG(hw, TPRH);
-	temp_reg = IXGB_READ_REG(hw, GPRCL);
-	temp_reg = IXGB_READ_REG(hw, GPRCH);
-	temp_reg = IXGB_READ_REG(hw, BPRCL);
-	temp_reg = IXGB_READ_REG(hw, BPRCH);
-	temp_reg = IXGB_READ_REG(hw, MPRCL);
-	temp_reg = IXGB_READ_REG(hw, MPRCH);
-	temp_reg = IXGB_READ_REG(hw, UPRCL);
-	temp_reg = IXGB_READ_REG(hw, UPRCH);
-	temp_reg = IXGB_READ_REG(hw, VPRCL);
-	temp_reg = IXGB_READ_REG(hw, VPRCH);
-	temp_reg = IXGB_READ_REG(hw, JPRCL);
-	temp_reg = IXGB_READ_REG(hw, JPRCH);
-	temp_reg = IXGB_READ_REG(hw, GORCL);
-	temp_reg = IXGB_READ_REG(hw, GORCH);
-	temp_reg = IXGB_READ_REG(hw, TORL);
-	temp_reg = IXGB_READ_REG(hw, TORH);
-	temp_reg = IXGB_READ_REG(hw, RNBC);
-	temp_reg = IXGB_READ_REG(hw, RUC);
-	temp_reg = IXGB_READ_REG(hw, ROC);
-	temp_reg = IXGB_READ_REG(hw, RLEC);
-	temp_reg = IXGB_READ_REG(hw, CRCERRS);
-	temp_reg = IXGB_READ_REG(hw, ICBC);
-	temp_reg = IXGB_READ_REG(hw, ECBC);
-	temp_reg = IXGB_READ_REG(hw, MPC);
-	temp_reg = IXGB_READ_REG(hw, TPTL);
-	temp_reg = IXGB_READ_REG(hw, TPTH);
-	temp_reg = IXGB_READ_REG(hw, GPTCL);
-	temp_reg = IXGB_READ_REG(hw, GPTCH);
-	temp_reg = IXGB_READ_REG(hw, BPTCL);
-	temp_reg = IXGB_READ_REG(hw, BPTCH);
-	temp_reg = IXGB_READ_REG(hw, MPTCL);
-	temp_reg = IXGB_READ_REG(hw, MPTCH);
-	temp_reg = IXGB_READ_REG(hw, UPTCL);
-	temp_reg = IXGB_READ_REG(hw, UPTCH);
-	temp_reg = IXGB_READ_REG(hw, VPTCL);
-	temp_reg = IXGB_READ_REG(hw, VPTCH);
-	temp_reg = IXGB_READ_REG(hw, JPTCL);
-	temp_reg = IXGB_READ_REG(hw, JPTCH);
-	temp_reg = IXGB_READ_REG(hw, GOTCL);
-	temp_reg = IXGB_READ_REG(hw, GOTCH);
-	temp_reg = IXGB_READ_REG(hw, TOTL);
-	temp_reg = IXGB_READ_REG(hw, TOTH);
-	temp_reg = IXGB_READ_REG(hw, DC);
-	temp_reg = IXGB_READ_REG(hw, PLT64C);
-	temp_reg = IXGB_READ_REG(hw, TSCTC);
-	temp_reg = IXGB_READ_REG(hw, TSCTFC);
-	temp_reg = IXGB_READ_REG(hw, IBIC);
-	temp_reg = IXGB_READ_REG(hw, RFC);
-	temp_reg = IXGB_READ_REG(hw, LFC);
-	temp_reg = IXGB_READ_REG(hw, PFRC);
-	temp_reg = IXGB_READ_REG(hw, PFTC);
-	temp_reg = IXGB_READ_REG(hw, MCFRC);
-	temp_reg = IXGB_READ_REG(hw, MCFTC);
-	temp_reg = IXGB_READ_REG(hw, XONRXC);
-	temp_reg = IXGB_READ_REG(hw, XONTXC);
-	temp_reg = IXGB_READ_REG(hw, XOFFRXC);
-	temp_reg = IXGB_READ_REG(hw, XOFFTXC);
-	temp_reg = IXGB_READ_REG(hw, RJC);
+	IXGB_READ_REG(hw, TPRL);
+	IXGB_READ_REG(hw, TPRH);
+	IXGB_READ_REG(hw, GPRCL);
+	IXGB_READ_REG(hw, GPRCH);
+	IXGB_READ_REG(hw, BPRCL);
+	IXGB_READ_REG(hw, BPRCH);
+	IXGB_READ_REG(hw, MPRCL);
+	IXGB_READ_REG(hw, MPRCH);
+	IXGB_READ_REG(hw, UPRCL);
+	IXGB_READ_REG(hw, UPRCH);
+	IXGB_READ_REG(hw, VPRCL);
+	IXGB_READ_REG(hw, VPRCH);
+	IXGB_READ_REG(hw, JPRCL);
+	IXGB_READ_REG(hw, JPRCH);
+	IXGB_READ_REG(hw, GORCL);
+	IXGB_READ_REG(hw, GORCH);
+	IXGB_READ_REG(hw, TORL);
+	IXGB_READ_REG(hw, TORH);
+	IXGB_READ_REG(hw, RNBC);
+	IXGB_READ_REG(hw, RUC);
+	IXGB_READ_REG(hw, ROC);
+	IXGB_READ_REG(hw, RLEC);
+	IXGB_READ_REG(hw, CRCERRS);
+	IXGB_READ_REG(hw, ICBC);
+	IXGB_READ_REG(hw, ECBC);
+	IXGB_READ_REG(hw, MPC);
+	IXGB_READ_REG(hw, TPTL);
+	IXGB_READ_REG(hw, TPTH);
+	IXGB_READ_REG(hw, GPTCL);
+	IXGB_READ_REG(hw, GPTCH);
+	IXGB_READ_REG(hw, BPTCL);
+	IXGB_READ_REG(hw, BPTCH);
+	IXGB_READ_REG(hw, MPTCL);
+	IXGB_READ_REG(hw, MPTCH);
+	IXGB_READ_REG(hw, UPTCL);
+	IXGB_READ_REG(hw, UPTCH);
+	IXGB_READ_REG(hw, VPTCL);
+	IXGB_READ_REG(hw, VPTCH);
+	IXGB_READ_REG(hw, JPTCL);
+	IXGB_READ_REG(hw, JPTCH);
+	IXGB_READ_REG(hw, GOTCL);
+	IXGB_READ_REG(hw, GOTCH);
+	IXGB_READ_REG(hw, TOTL);
+	IXGB_READ_REG(hw, TOTH);
+	IXGB_READ_REG(hw, DC);
+	IXGB_READ_REG(hw, PLT64C);
+	IXGB_READ_REG(hw, TSCTC);
+	IXGB_READ_REG(hw, TSCTFC);
+	IXGB_READ_REG(hw, IBIC);
+	IXGB_READ_REG(hw, RFC);
+	IXGB_READ_REG(hw, LFC);
+	IXGB_READ_REG(hw, PFRC);
+	IXGB_READ_REG(hw, PFTC);
+	IXGB_READ_REG(hw, MCFRC);
+	IXGB_READ_REG(hw, MCFTC);
+	IXGB_READ_REG(hw, XONRXC);
+	IXGB_READ_REG(hw, XONTXC);
+	IXGB_READ_REG(hw, XOFFRXC);
+	IXGB_READ_REG(hw, XOFFTXC);
+	IXGB_READ_REG(hw, RJC);
 }
 
 /******************************************************************************
@@ -1161,18 +1157,13 @@ static void
 ixgb_optics_reset(struct ixgb_hw *hw)
 {
 	if (hw->phy_type == ixgb_phy_type_txn17401) {
-		u16 mdio_reg;
-
 		ixgb_write_phy_reg(hw,
 				   MDIO_CTRL1,
 				   IXGB_PHY_ADDRESS,
 				   MDIO_MMD_PMAPMD,
 				   MDIO_CTRL1_RESET);
 
-		mdio_reg = ixgb_read_phy_reg(hw,
-					     MDIO_CTRL1,
-					     IXGB_PHY_ADDRESS,
-					     MDIO_MMD_PMAPMD);
+		ixgb_read_phy_reg(hw, MDIO_CTRL1, IXGB_PHY_ADDRESS, MDIO_MMD_PMAPMD);
 	}
 }
 
diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_main.c b/drivers/net/ethernet/intel/ixgb/ixgb_main.c
index 048351cf0e4a..1588376d4c67 100644
--- a/drivers/net/ethernet/intel/ixgb/ixgb_main.c
+++ b/drivers/net/ethernet/intel/ixgb/ixgb_main.c
@@ -1109,7 +1109,7 @@ alloc_failed:
 
 /**
  * ixgb_watchdog - Timer Call-back
- * @data: pointer to netdev cast into an unsigned long
+ * @t: pointer to timer_list containing our private info pointer
  **/
 
 static void
@@ -1531,10 +1531,11 @@ ixgb_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
 /**
  * ixgb_tx_timeout - Respond to a Tx Hang
  * @netdev: network interface device structure
+ * @txqueue: queue hanging (unused)
  **/
 
 static void
-ixgb_tx_timeout(struct net_device *netdev, unsigned int txqueue)
+ixgb_tx_timeout(struct net_device *netdev, unsigned int __always_unused txqueue)
 {
 	struct ixgb_adapter *adapter = netdev_priv(netdev);
 
@@ -1746,7 +1747,8 @@ ixgb_intr(int irq, void *data)
 
 /**
  * ixgb_clean - NAPI Rx polling callback
- * @adapter: board private structure
+ * @napi: napi struct pointer
+ * @budget: max number of receives to clean
  **/
 
 static int
@@ -1865,7 +1867,7 @@ ixgb_clean_tx_irq(struct ixgb_adapter *adapter)
  * ixgb_rx_checksum - Receive Checksum Offload for 82597.
  * @adapter: board private structure
  * @rx_desc: receive descriptor
- * @sk_buff: socket buffer with received data
+ * @skb: socket buffer with received data
  **/
 
 static void
@@ -1923,6 +1925,8 @@ static void ixgb_check_copybreak(struct napi_struct *napi,
 /**
  * ixgb_clean_rx_irq - Send received data up the network stack,
  * @adapter: board private structure
+ * @work_done: output pointer to amount of packets cleaned
+ * @work_to_do: how much work we can complete
  **/
 
 static bool
@@ -2042,6 +2046,7 @@ rxdesc_done:
 /**
  * ixgb_alloc_rx_buffers - Replace used receive buffers
  * @adapter: address of board private structure
+ * @cleaned_count: how many buffers to allocate
  **/
 
 static void
@@ -2211,7 +2216,7 @@ static pci_ers_result_t ixgb_io_error_detected(struct pci_dev *pdev,
 
 /**
  * ixgb_io_slot_reset - called after the pci bus has been reset.
- * @pdev    pointer to pci device with error
+ * @pdev: pointer to pci device with error
  *
  * This callback is called after the PCI bus has been reset.
  * Basically, this tries to restart the card from scratch.
@@ -2259,7 +2264,7 @@ static pci_ers_result_t ixgb_io_slot_reset(struct pci_dev *pdev)
 
 /**
  * ixgb_io_resume - called when its OK to resume normal operations
- * @pdev    pointer to pci device with error
+ * @pdev: pointer to pci device with error
  *
  * The error recovery driver tells us that its OK to resume
  * normal operation. Implementation resembles the second-half
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 0b675c34ce49..a190d5c616fc 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -5672,7 +5672,6 @@ static void ixgbe_up_complete(struct ixgbe_adapter *adapter)
 
 void ixgbe_reinit_locked(struct ixgbe_adapter *adapter)
 {
-	WARN_ON(in_interrupt());
 	/* put off any impending NetWatchDogTimeout */
 	netif_trans_update(adapter->netdev);
 
@@ -6175,8 +6174,9 @@ static void ixgbe_set_eee_capable(struct ixgbe_adapter *adapter)
 /**
  * ixgbe_tx_timeout - Respond to a Tx Hang
  * @netdev: network interface device structure
+ * @txqueue: queue number that timed out
  **/
-static void ixgbe_tx_timeout(struct net_device *netdev, unsigned int txqueue)
+static void ixgbe_tx_timeout(struct net_device *netdev, unsigned int __always_unused txqueue)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
index 7980d7265e10..f77fa3e4fdd1 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
@@ -771,7 +771,7 @@ mii_bus_write_done:
 
 /**
  *  ixgbe_mii_bus_read - Read a clause 22/45 register
- *  @hw: pointer to hardware structure
+ *  @bus: pointer to mii_bus structure which points to our driver private
  *  @addr: address
  *  @regnum: register number
  **/
@@ -786,7 +786,7 @@ static s32 ixgbe_mii_bus_read(struct mii_bus *bus, int addr, int regnum)
 
 /**
  *  ixgbe_mii_bus_write - Write a clause 22/45 register
- *  @hw: pointer to hardware structure
+ *  @bus: pointer to mii_bus structure which points to our driver private
  *  @addr: address
  *  @regnum: register number
  *  @val: value to write
@@ -803,7 +803,7 @@ static s32 ixgbe_mii_bus_write(struct mii_bus *bus, int addr, int regnum,
 
 /**
  *  ixgbe_x550em_a_mii_bus_read - Read a clause 22/45 register on x550em_a
- *  @hw: pointer to hardware structure
+ *  @bus: pointer to mii_bus structure which points to our driver private
  *  @addr: address
  *  @regnum: register number
  **/
@@ -820,7 +820,7 @@ static s32 ixgbe_x550em_a_mii_bus_read(struct mii_bus *bus, int addr,
 
 /**
  *  ixgbe_x550em_a_mii_bus_write - Write a clause 22/45 register on x550em_a
- *  @hw: pointer to hardware structure
+ *  @bus: pointer to mii_bus structure which points to our driver private
  *  @addr: address
  *  @regnum: register number
  *  @val: value to write
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index 50afec43e001..82fce27f682b 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -246,8 +246,9 @@ static void ixgbevf_tx_timeout_reset(struct ixgbevf_adapter *adapter)
 /**
  * ixgbevf_tx_timeout - Respond to a Tx Hang
  * @netdev: network interface device structure
+ * @txqueue: transmit queue hanging (unused)
  **/
-static void ixgbevf_tx_timeout(struct net_device *netdev, unsigned int txqueue)
+static void ixgbevf_tx_timeout(struct net_device *netdev, unsigned int __always_unused txqueue)
 {
 	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
 
@@ -2521,8 +2522,6 @@ void ixgbevf_down(struct ixgbevf_adapter *adapter)
 
 void ixgbevf_reinit_locked(struct ixgbevf_adapter *adapter)
 {
-	WARN_ON(in_interrupt());
-
 	while (test_and_set_bit(__IXGBEVF_RESETTING, &adapter->state))
 		msleep(1);
 
diff --git a/drivers/net/ethernet/lantiq_xrx200.c b/drivers/net/ethernet/lantiq_xrx200.c
index 1645e4e7ebdb..635ff3a5dcfb 100644
--- a/drivers/net/ethernet/lantiq_xrx200.c
+++ b/drivers/net/ethernet/lantiq_xrx200.c
@@ -230,8 +230,8 @@ static int xrx200_poll_rx(struct napi_struct *napi, int budget)
 	}
 
 	if (rx < budget) {
-		napi_complete(&ch->napi);
-		ltq_dma_enable_irq(&ch->dma);
+		if (napi_complete_done(&ch->napi, rx))
+			ltq_dma_enable_irq(&ch->dma);
 	}
 
 	return rx;
@@ -268,9 +268,12 @@ static int xrx200_tx_housekeeping(struct napi_struct *napi, int budget)
 	net_dev->stats.tx_bytes += bytes;
 	netdev_completed_queue(ch->priv->net_dev, pkts, bytes);
 
+	if (netif_queue_stopped(net_dev))
+		netif_wake_queue(net_dev);
+
 	if (pkts < budget) {
-		napi_complete(&ch->napi);
-		ltq_dma_enable_irq(&ch->dma);
+		if (napi_complete_done(&ch->napi, pkts))
+			ltq_dma_enable_irq(&ch->dma);
 	}
 
 	return pkts;
@@ -342,10 +345,12 @@ static irqreturn_t xrx200_dma_irq(int irq, void *ptr)
 {
 	struct xrx200_chan *ch = ptr;
 
-	ltq_dma_disable_irq(&ch->dma);
-	ltq_dma_ack_irq(&ch->dma);
+	if (napi_schedule_prep(&ch->napi)) {
+		__napi_schedule(&ch->napi);
+		ltq_dma_disable_irq(&ch->dma);
+	}
 
-	napi_schedule(&ch->napi);
+	ltq_dma_ack_irq(&ch->dma);
 
 	return IRQ_HANDLED;
 }
@@ -499,7 +504,7 @@ static int xrx200_probe(struct platform_device *pdev)
 
 	/* setup NAPI */
 	netif_napi_add(net_dev, &priv->chan_rx.napi, xrx200_poll_rx, 32);
-	netif_napi_add(net_dev, &priv->chan_tx.napi, xrx200_tx_housekeeping, 32);
+	netif_tx_napi_add(net_dev, &priv->chan_tx.napi, xrx200_tx_housekeeping, 32);
 
 	platform_set_drvdata(pdev, priv);
 
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index e5ddefe5cade..d095718355d3 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -1831,7 +1831,7 @@ static struct mvneta_tx_queue *mvneta_tx_done_policy(struct mvneta_port *pp,
 /* Free tx queue skbuffs */
 static void mvneta_txq_bufs_free(struct mvneta_port *pp,
 				 struct mvneta_tx_queue *txq, int num,
-				 struct netdev_queue *nq)
+				 struct netdev_queue *nq, bool napi)
 {
 	unsigned int bytes_compl = 0, pkts_compl = 0;
 	int i;
@@ -1854,7 +1854,10 @@ static void mvneta_txq_bufs_free(struct mvneta_port *pp,
 			dev_kfree_skb_any(buf->skb);
 		} else if (buf->type == MVNETA_TYPE_XDP_TX ||
 			   buf->type == MVNETA_TYPE_XDP_NDO) {
-			xdp_return_frame(buf->xdpf);
+			if (napi && buf->type == MVNETA_TYPE_XDP_TX)
+				xdp_return_frame_rx_napi(buf->xdpf);
+			else
+				xdp_return_frame(buf->xdpf);
 		}
 	}
 
@@ -1872,7 +1875,7 @@ static void mvneta_txq_done(struct mvneta_port *pp,
 	if (!tx_done)
 		return;
 
-	mvneta_txq_bufs_free(pp, txq, tx_done, nq);
+	mvneta_txq_bufs_free(pp, txq, tx_done, nq, true);
 
 	txq->count -= tx_done;
 
@@ -2027,11 +2030,11 @@ mvneta_xdp_put_buff(struct mvneta_port *pp, struct mvneta_rx_queue *rxq,
 	struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
 	int i;
 
-	page_pool_put_page(rxq->page_pool, virt_to_head_page(xdp->data),
-			   sync_len, napi);
 	for (i = 0; i < sinfo->nr_frags; i++)
 		page_pool_put_full_page(rxq->page_pool,
 					skb_frag_page(&sinfo->frags[i]), napi);
+	page_pool_put_page(rxq->page_pool, virt_to_head_page(xdp->data),
+			   sync_len, napi);
 }
 
 static int
@@ -2233,19 +2236,22 @@ mvneta_swbm_rx_frame(struct mvneta_port *pp,
 	enum dma_data_direction dma_dir;
 	struct skb_shared_info *sinfo;
 
-	if (rx_desc->data_size > MVNETA_MAX_RX_BUF_SIZE) {
+	if (*size > MVNETA_MAX_RX_BUF_SIZE) {
 		len = MVNETA_MAX_RX_BUF_SIZE;
 		data_len += len;
 	} else {
-		len = rx_desc->data_size;
+		len = *size;
 		data_len += len - ETH_FCS_LEN;
 	}
+	*size = *size - len;
 
 	dma_dir = page_pool_get_dma_dir(rxq->page_pool);
 	dma_sync_single_for_cpu(dev->dev.parent,
 				rx_desc->buf_phys_addr,
 				len, dma_dir);
 
+	rx_desc->buf_phys_addr = 0;
+
 	/* Prefetch header */
 	prefetch(data);
 
@@ -2256,9 +2262,6 @@ mvneta_swbm_rx_frame(struct mvneta_port *pp,
 
 	sinfo = xdp_get_shared_info_from_buff(xdp);
 	sinfo->nr_frags = 0;
-
-	*size = rx_desc->data_size - len;
-	rx_desc->buf_phys_addr = 0;
 }
 
 static void
@@ -2372,13 +2375,17 @@ static int mvneta_rx_swbm(struct napi_struct *napi,
 
 			size = rx_desc->data_size;
 			frame_sz = size - ETH_FCS_LEN;
-			desc_status = rx_desc->status;
+			desc_status = rx_status;
 
 			mvneta_swbm_rx_frame(pp, rx_desc, rxq, &xdp_buf,
 					     &size, page);
 		} else {
-			if (unlikely(!xdp_buf.data_hard_start))
+			if (unlikely(!xdp_buf.data_hard_start)) {
+				rx_desc->buf_phys_addr = 0;
+				page_pool_put_full_page(rxq->page_pool, page,
+							true);
 				continue;
+			}
 
 			mvneta_swbm_add_rx_fragment(pp, rx_desc, rxq, &xdp_buf,
 						    &size, page);
@@ -2855,7 +2862,7 @@ static void mvneta_txq_done_force(struct mvneta_port *pp,
 	struct netdev_queue *nq = netdev_get_tx_queue(pp->dev, txq->id);
 	int tx_done = txq->count;
 
-	mvneta_txq_bufs_free(pp, txq, tx_done, nq);
+	mvneta_txq_bufs_free(pp, txq, tx_done, nq, false);
 
 	/* reset txq */
 	txq->count = 0;
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index d11d33cf3443..f6616c8933ca 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -7081,11 +7081,13 @@ static const struct of_device_id mvpp2_match[] = {
 };
 MODULE_DEVICE_TABLE(of, mvpp2_match);
 
+#ifdef CONFIG_ACPI
 static const struct acpi_device_id mvpp2_acpi_match[] = {
 	{ "MRVL0110", MVPP22 },
 	{ },
 };
 MODULE_DEVICE_TABLE(acpi, mvpp2_acpi_match);
+#endif
 
 static struct platform_driver mvpp2_driver = {
 	.probe = mvpp2_probe,
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/Makefile b/drivers/net/ethernet/marvell/octeontx2/af/Makefile
index 0bc2410c8949..2f7a861d0c7b 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/Makefile
+++ b/drivers/net/ethernet/marvell/octeontx2/af/Makefile
@@ -3,9 +3,10 @@
 # Makefile for Marvell's OcteonTX2 RVU Admin Function driver
 #
 
+ccflags-y += -I$(src)
 obj-$(CONFIG_OCTEONTX2_MBOX) += octeontx2_mbox.o
 obj-$(CONFIG_OCTEONTX2_AF) += octeontx2_af.o
 
-octeontx2_mbox-y := mbox.o
+octeontx2_mbox-y := mbox.o rvu_trace.o
 octeontx2_af-y := cgx.o rvu.o rvu_cgx.o rvu_npa.o rvu_nix.o \
 		  rvu_reg.o rvu_npc.o rvu_debugfs.o ptp.o
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.c b/drivers/net/ethernet/marvell/octeontx2/af/mbox.c
index 387e33fa417a..4b4cf7dac77f 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.c
@@ -14,6 +14,7 @@
 
 #include "rvu_reg.h"
 #include "mbox.h"
+#include "rvu_trace.h"
 
 static const u16 msgs_offset = ALIGN(sizeof(struct mbox_hdr), MBOX_MSG_ALIGN);
 
@@ -199,6 +200,9 @@ void otx2_mbox_msg_send(struct otx2_mbox *mbox, int devid)
 	 */
 	tx_hdr->num_msgs = mdev->num_msgs;
 	rx_hdr->num_msgs = 0;
+
+	trace_otx2_msg_send(mbox->pdev, tx_hdr->num_msgs, tx_hdr->msg_size);
+
 	spin_unlock(&mdev->mbox_lock);
 
 	/* The interrupt should be fired after num_msgs is written
@@ -295,10 +299,15 @@ int otx2_mbox_check_rsp_msgs(struct otx2_mbox *mbox, int devid)
 		struct mbox_msghdr *preq = mdev->mbase + ireq;
 		struct mbox_msghdr *prsp = mdev->mbase + irsp;
 
-		if (preq->id != prsp->id)
+		if (preq->id != prsp->id) {
+			trace_otx2_msg_check(mbox->pdev, preq->id,
+					     prsp->id, prsp->rc);
 			goto exit;
+		}
 		if (prsp->rc) {
 			rc = prsp->rc;
+			trace_otx2_msg_check(mbox->pdev, preq->id,
+					     prsp->id, prsp->rc);
 			goto exit;
 		}
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
index 4aaef0a2b51c..aa3bda3f34be 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
@@ -625,6 +625,7 @@ struct nix_rss_flowkey_cfg {
 #define NIX_FLOW_KEY_TYPE_INNR_UDP      BIT(15)
 #define NIX_FLOW_KEY_TYPE_INNR_SCTP     BIT(16)
 #define NIX_FLOW_KEY_TYPE_INNR_ETH_DMAC BIT(17)
+#define NIX_FLOW_KEY_TYPE_VLAN		BIT(20)
 	u32	flowkey_cfg; /* Flowkey types selected */
 	u8	group;       /* RSS context or group */
 };
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/npc.h b/drivers/net/ethernet/marvell/octeontx2/af/npc.h
index 95c646ae7e23..91a9d00e4fb5 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/npc.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/npc.h
@@ -49,6 +49,7 @@ enum npc_kpu_lb_ltype {
 	NPC_LT_LB_EDSA_VLAN,
 	NPC_LT_LB_EXDSA,
 	NPC_LT_LB_EXDSA_VLAN,
+	NPC_LT_LB_FDSA,
 	NPC_LT_LB_CUSTOM0 = 0xE,
 	NPC_LT_LB_CUSTOM1 = 0xF,
 };
@@ -77,21 +78,21 @@ enum npc_kpu_ld_ltype {
 	NPC_LT_LD_ICMP,
 	NPC_LT_LD_SCTP,
 	NPC_LT_LD_ICMP6,
+	NPC_LT_LD_CUSTOM0,
+	NPC_LT_LD_CUSTOM1,
 	NPC_LT_LD_IGMP = 8,
-	NPC_LT_LD_ESP,
 	NPC_LT_LD_AH,
 	NPC_LT_LD_GRE,
 	NPC_LT_LD_NVGRE,
 	NPC_LT_LD_NSH,
 	NPC_LT_LD_TU_MPLS_IN_NSH,
 	NPC_LT_LD_TU_MPLS_IN_IP,
-	NPC_LT_LD_CUSTOM0 = 0xE,
-	NPC_LT_LD_CUSTOM1 = 0xF,
 };
 
 enum npc_kpu_le_ltype {
 	NPC_LT_LE_VXLAN = 1,
 	NPC_LT_LE_GENEVE,
+	NPC_LT_LE_ESP,
 	NPC_LT_LE_GTPU = 4,
 	NPC_LT_LE_VXLANGPE,
 	NPC_LT_LE_GTPC,
@@ -296,6 +297,9 @@ struct nix_rx_action {
 #endif
 };
 
+/* NPC_AF_INTFX_KEX_CFG field masks */
+#define NPC_PARSE_NIBBLE		GENMASK_ULL(30, 0)
+
 /* NIX Receive Vtag Action Structure */
 #define VTAG0_VALID_BIT		BIT_ULL(15)
 #define VTAG0_TYPE_MASK		GENMASK_ULL(14, 12)
@@ -320,4 +324,37 @@ struct npc_mcam_kex {
 	u64 intf_ld_flags[NPC_MAX_INTF][NPC_MAX_LD][NPC_MAX_LFL];
 } __packed;
 
+struct npc_lt_def {
+	u8	ltype_mask;
+	u8	ltype_match;
+	u8	lid;
+};
+
+struct npc_lt_def_ipsec {
+	u8	ltype_mask;
+	u8	ltype_match;
+	u8	lid;
+	u8	spi_offset;
+	u8	spi_nz;
+};
+
+struct npc_lt_def_cfg {
+	struct npc_lt_def	rx_ol2;
+	struct npc_lt_def	rx_oip4;
+	struct npc_lt_def	rx_iip4;
+	struct npc_lt_def	rx_oip6;
+	struct npc_lt_def	rx_iip6;
+	struct npc_lt_def	rx_otcp;
+	struct npc_lt_def	rx_itcp;
+	struct npc_lt_def	rx_oudp;
+	struct npc_lt_def	rx_iudp;
+	struct npc_lt_def	rx_osctp;
+	struct npc_lt_def	rx_isctp;
+	struct npc_lt_def_ipsec	rx_ipsec[2];
+	struct npc_lt_def	pck_ol2;
+	struct npc_lt_def	pck_oip4;
+	struct npc_lt_def	pck_oip6;
+	struct npc_lt_def	pck_iip4;
+};
+
 #endif /* NPC_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/npc_profile.h b/drivers/net/ethernet/marvell/octeontx2/af/npc_profile.h
index b29c6689ace2..77bb4ed32600 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/npc_profile.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/npc_profile.h
@@ -63,6 +63,7 @@
 #define NPC_UDP_PORT_VXLANGPE	4790
 #define NPC_UDP_PORT_GENEVE	6081
 #define NPC_UDP_PORT_MPLS	6635
+#define NPC_UDP_PORT_ESP	4500
 
 #define NPC_VXLANGPE_NP_IP	0x1
 #define NPC_VXLANGPE_NP_IP6	0x2
@@ -139,6 +140,13 @@
 
 #define NPC_DSA_EXTEND		0x1000
 #define NPC_DSA_EDSA		0x8000
+#define NPC_DSA_FDSA		0xc000
+
+#define NPC_KEXOF_DMAC	8
+#define MKEX_SIGN	0x19bbfdbd15f /* strtoull of "mkexprof" with base:36 */
+#define KEX_LD_CFG(bytesm1, hdr_ofs, ena, flags_ena, key_ofs)		\
+			(((bytesm1) << 16) | ((hdr_ofs) << 8) | ((ena) << 7) | \
+			 ((flags_ena) << 6) | ((key_ofs) & 0x3F))
 
 enum npc_kpu_parser_state {
 	NPC_S_NA = 0,
@@ -166,6 +174,7 @@ enum npc_kpu_parser_state {
 	NPC_S_KPU3_DSA,
 	NPC_S_KPU4_MPLS,
 	NPC_S_KPU4_NSH,
+	NPC_S_KPU4_FDSA,
 	NPC_S_KPU5_IP,
 	NPC_S_KPU5_IP6,
 	NPC_S_KPU5_ARP,
@@ -189,7 +198,6 @@ enum npc_kpu_parser_state {
 	NPC_S_KPU8_IGMP,
 	NPC_S_KPU8_ICMP6,
 	NPC_S_KPU8_GRE,
-	NPC_S_KPU8_ESP,
 	NPC_S_KPU8_AH,
 	NPC_S_KPU9_TU_MPLS_IN_GRE,
 	NPC_S_KPU9_TU_MPLS_IN_NSH,
@@ -201,6 +209,7 @@ enum npc_kpu_parser_state {
 	NPC_S_KPU9_GENEVE,
 	NPC_S_KPU9_GTPC,
 	NPC_S_KPU9_GTPU,
+	NPC_S_KPU9_ESP,
 	NPC_S_KPU10_TU_MPLS_IN_VXLANGPE,
 	NPC_S_KPU10_TU_MPLS_PL,
 	NPC_S_KPU10_TU_MPLS,
@@ -271,6 +280,7 @@ enum npc_kpu_lb_lflag {
 	NPC_F_LB_L_EDSA_VLAN,
 	NPC_F_LB_L_EXDSA,
 	NPC_F_LB_L_EXDSA_VLAN,
+	NPC_F_LB_L_FDSA,
 };
 
 enum npc_kpu_lc_uflag {
@@ -979,7 +989,7 @@ static const struct npc_kpu_profile_action ikpu_action_entries[] = {
 	},
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		12, 16, 20, 0, 0,
+		12, 14, 20, 0, 0,
 		NPC_S_KPU1_EXDSA, 0, 0,
 		NPC_LID_LA, NPC_LT_NA,
 		0,
@@ -1351,10 +1361,19 @@ static const struct npc_kpu_profile_cam kpu1_cam_entries[] = {
 	},
 	{
 		NPC_S_KPU1_EXDSA, 0xff,
+		0x0000,
+		0x0000,
 		NPC_DSA_EXTEND,
 		NPC_DSA_EXTEND,
 		0x0000,
 		0x0000,
+	},
+	{
+		NPC_S_KPU1_EXDSA, 0xff,
+		NPC_DSA_FDSA,
+		NPC_DSA_FDSA,
+		0x0000,
+		0x0000,
 		0x0000,
 		0x0000,
 	},
@@ -3996,6 +4015,69 @@ static const struct npc_kpu_profile_cam kpu4_cam_entries[] = {
 		0x0000,
 	},
 	{
+		NPC_S_KPU4_FDSA, 0xff,
+		NPC_ETYPE_IP,
+		0xffff,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU4_FDSA, 0xff,
+		NPC_ETYPE_IP6,
+		0xffff,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU4_FDSA, 0xff,
+		NPC_ETYPE_ARP,
+		0xffff,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU4_FDSA, 0xff,
+		NPC_ETYPE_RARP,
+		0xffff,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU4_FDSA, 0xff,
+		NPC_ETYPE_PTP,
+		0xffff,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU4_FDSA, 0xff,
+		NPC_ETYPE_FCOE,
+		0xffff,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
+		NPC_S_KPU4_FDSA, 0xff,
+		0x0000,
+		NPC_DSA_FDSA,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
 		NPC_S_NA, 0X00,
 		0x0000,
 		0x0000,
@@ -5341,15 +5423,24 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = {
 	},
 	{
 		NPC_S_KPU8_UDP, 0xff,
+		NPC_UDP_PORT_ESP,
+		0xffff,
 		0x0000,
 		0x0000,
 		0x0000,
 		0x0000,
+	},
+	{
+		NPC_S_KPU8_UDP, 0xff,
+		0x0000,
+		0x0000,
+		NPC_UDP_PORT_ESP,
+		0xffff,
 		0x0000,
 		0x0000,
 	},
 	{
-		NPC_S_KPU8_SCTP, 0xff,
+		NPC_S_KPU8_UDP, 0xff,
 		0x0000,
 		0x0000,
 		0x0000,
@@ -5358,7 +5449,7 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = {
 		0x0000,
 	},
 	{
-		NPC_S_KPU8_ICMP, 0xff,
+		NPC_S_KPU8_SCTP, 0xff,
 		0x0000,
 		0x0000,
 		0x0000,
@@ -5367,7 +5458,7 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = {
 		0x0000,
 	},
 	{
-		NPC_S_KPU8_IGMP, 0xff,
+		NPC_S_KPU8_ICMP, 0xff,
 		0x0000,
 		0x0000,
 		0x0000,
@@ -5376,7 +5467,7 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = {
 		0x0000,
 	},
 	{
-		NPC_S_KPU8_ICMP6, 0xff,
+		NPC_S_KPU8_IGMP, 0xff,
 		0x0000,
 		0x0000,
 		0x0000,
@@ -5385,7 +5476,7 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = {
 		0x0000,
 	},
 	{
-		NPC_S_KPU8_ESP, 0xff,
+		NPC_S_KPU8_ICMP6, 0xff,
 		0x0000,
 		0x0000,
 		0x0000,
@@ -6324,6 +6415,15 @@ static const struct npc_kpu_profile_cam kpu9_cam_entries[] = {
 		NPC_MPLS_S,
 	},
 	{
+		NPC_S_KPU9_ESP, 0xff,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+		0x0000,
+	},
+	{
 		NPC_S_NA, 0X00,
 		0x0000,
 		0x0000,
@@ -7673,6 +7773,14 @@ static const struct npc_kpu_profile_action kpu1_action_entries[] = {
 		0, 0, 0, 0,
 	},
 	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		4, 8, 16, 2, 0,
+		NPC_S_KPU4_FDSA, 12, 1,
+		NPC_LID_LA, NPC_LT_LA_ETHER,
+		0,
+		0, 0, 0, 0,
+	},
+	{
 		NPC_ERRLEV_LA, NPC_EC_EDSA_UNK,
 		0, 0, 0, 0, 1,
 		NPC_S_NA, 0, 1,
@@ -10034,6 +10142,62 @@ static const struct npc_kpu_profile_action kpu4_action_entries[] = {
 		0, 0, 0, 0,
 	},
 	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		8, 0, 6, 0, 0,
+		NPC_S_KPU5_IP, 6, 1,
+		NPC_LID_LB, NPC_LT_LB_FDSA,
+		NPC_F_LB_L_FDSA,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		6, 0, 0, 0, 0,
+		NPC_S_KPU5_IP6, 6, 1,
+		NPC_LID_LB, NPC_LT_LB_FDSA,
+		NPC_F_LB_L_FDSA,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 0, 0,
+		NPC_S_KPU5_ARP, 6, 1,
+		NPC_LID_LB, NPC_LT_LB_FDSA,
+		NPC_F_LB_L_FDSA,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		8, 0, 6, 0, 0,
+		NPC_S_KPU5_RARP, 6, 1,
+		NPC_LID_LB, NPC_LT_LB_FDSA,
+		NPC_F_LB_L_FDSA,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		6, 0, 0, 0, 0,
+		NPC_S_KPU5_PTP, 6, 1,
+		NPC_LID_LB, NPC_LT_LB_FDSA,
+		NPC_F_LB_L_FDSA,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 0, 0,
+		NPC_S_KPU5_FCOE, 6, 1,
+		NPC_LID_LB, NPC_LT_LB_FDSA,
+		NPC_F_LB_L_FDSA,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 0, 1,
+		NPC_S_NA, 0, 1,
+		NPC_LID_LB, NPC_LT_LB_FDSA,
+		NPC_F_LB_U_UNK_ETYPE | NPC_F_LB_L_FDSA,
+		0, 0, 0, 0,
+	},
+	{
 		NPC_ERRLEV_LB, NPC_EC_L2_K4,
 		0, 0, 0, 0, 1,
 		NPC_S_NA, 0, 0,
@@ -10102,8 +10266,8 @@ static const struct npc_kpu_profile_action kpu5_action_entries[] = {
 	},
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		0, 0, 0, 2, 0,
-		NPC_S_KPU8_ESP, 20, 1,
+		0, 0, 0, 3, 0,
+		NPC_S_KPU9_ESP, 20, 1,
 		NPC_LID_LC, NPC_LT_LC_IP,
 		0,
 		0, 0, 0, 0,
@@ -10206,8 +10370,8 @@ static const struct npc_kpu_profile_action kpu5_action_entries[] = {
 	},
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		0, 0, 0, 2, 0,
-		NPC_S_KPU8_ESP, 0, 1,
+		0, 0, 0, 3, 0,
+		NPC_S_KPU9_ESP, 0, 1,
 		NPC_LID_LC, NPC_LT_LC_IP_OPT,
 		0,
 		0, 0xf, 0, 2,
@@ -10414,8 +10578,8 @@ static const struct npc_kpu_profile_action kpu5_action_entries[] = {
 	},
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		0, 0, 0, 2, 0,
-		NPC_S_KPU8_ESP, 40, 1,
+		0, 0, 0, 3, 0,
+		NPC_S_KPU9_ESP, 40, 1,
 		NPC_LID_LC, NPC_LT_LC_IP6_EXT,
 		0,
 		0, 0, 0, 0,
@@ -10561,80 +10725,80 @@ static const struct npc_kpu_profile_action kpu6_action_entries[] = {
 	},
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		2, 12, 0, 1, 0,
-		NPC_S_KPU8_TCP, 8, 0,
+		0, 0, 0, 0, 1,
+		NPC_S_NA, 0, 0,
 		NPC_LID_LC, NPC_LT_NA,
 		0,
 		0, 0, 0, 0,
 	},
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		2, 8, 10, 1, 0,
-		NPC_S_KPU8_UDP, 8, 0,
+		0, 0, 0, 0, 1,
+		NPC_S_NA, 0, 0,
 		NPC_LID_LC, NPC_LT_NA,
 		0,
 		0, 0, 0, 0,
 	},
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		0, 0, 0, 1, 0,
-		NPC_S_KPU8_SCTP, 8, 0,
+		0, 0, 0, 0, 1,
+		NPC_S_NA, 0, 0,
 		NPC_LID_LC, NPC_LT_NA,
 		0,
 		0, 0, 0, 0,
 	},
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		0, 0, 0, 1, 0,
-		NPC_S_KPU8_ICMP, 8, 0,
+		0, 0, 0, 0, 1,
+		NPC_S_NA, 0, 0,
 		NPC_LID_LC, NPC_LT_NA,
 		0,
 		0, 0, 0, 0,
 	},
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		0, 0, 0, 1, 0,
-		NPC_S_KPU8_ICMP6, 8, 0,
+		0, 0, 0, 0, 1,
+		NPC_S_NA, 0, 0,
 		NPC_LID_LC, NPC_LT_NA,
 		0,
 		0, 0, 0, 0,
 	},
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		0, 0, 0, 1, 0,
-		NPC_S_KPU8_ESP, 8, 0,
+		0, 0, 0, 0, 1,
+		NPC_S_NA, 0, 0,
 		NPC_LID_LC, NPC_LT_NA,
 		0,
 		0, 0, 0, 0,
 	},
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		0, 0, 0, 1, 0,
-		NPC_S_KPU8_AH, 8, 0,
+		0, 0, 0, 0, 1,
+		NPC_S_NA, 0, 0,
 		NPC_LID_LC, NPC_LT_NA,
 		0,
 		0, 0, 0, 0,
 	},
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		0, 0, 0, 1, 0,
-		NPC_S_KPU8_GRE, 8, 0,
+		0, 0, 0, 0, 1,
+		NPC_S_NA, 0, 0,
 		NPC_LID_LC, NPC_LT_NA,
 		0,
 		0, 0, 0, 0,
 	},
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		6, 0, 0, 5, 0,
-		NPC_S_KPU12_TU_IP6, 8, 0,
+		0, 0, 0, 0, 1,
+		NPC_S_NA, 0, 0,
 		NPC_LID_LC, NPC_LT_NA,
 		0,
 		0, 0, 0, 0,
 	},
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		2, 6, 10, 2, 0,
-		NPC_S_KPU9_TU_MPLS_IN_IP, 8, 0,
+		0, 0, 0, 0, 1,
+		NPC_S_NA, 0, 0,
 		NPC_LID_LC, NPC_LT_NA,
 		0,
 		0, 0, 0, 0,
@@ -10689,8 +10853,8 @@ static const struct npc_kpu_profile_action kpu6_action_entries[] = {
 	},
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		0, 0, 0, 1, 0,
-		NPC_S_KPU8_ESP, 8, 0,
+		0, 0, 0, 2, 0,
+		NPC_S_KPU9_ESP, 8, 0,
 		NPC_LID_LC, NPC_LT_NA,
 		0,
 		1, 0xff, 0, 3,
@@ -10793,8 +10957,8 @@ static const struct npc_kpu_profile_action kpu6_action_entries[] = {
 	},
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		0, 0, 0, 1, 0,
-		NPC_S_KPU8_ESP, 8, 0,
+		0, 0, 0, 2, 0,
+		NPC_S_KPU9_ESP, 8, 0,
 		NPC_LID_LC, NPC_LT_NA,
 		0,
 		1, 0xff, 0, 3,
@@ -10908,8 +11072,8 @@ static const struct npc_kpu_profile_action kpu7_action_entries[] = {
 	},
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		0, 0, 0, 0, 0,
-		NPC_S_KPU8_ESP, 8, 0,
+		0, 0, 0, 1, 0,
+		NPC_S_KPU9_ESP, 8, 0,
 		NPC_LID_LC, NPC_LT_NA,
 		0,
 		1, 0xff, 0, 3,
@@ -10956,80 +11120,80 @@ static const struct npc_kpu_profile_action kpu7_action_entries[] = {
 	},
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		2, 12, 0, 0, 0,
-		NPC_S_KPU8_TCP, 8, 0,
+		0, 0, 0, 0, 1,
+		NPC_S_NA, 0, 0,
 		NPC_LID_LC, NPC_LT_NA,
 		0,
 		0, 0, 0, 0,
 	},
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		2, 8, 10, 0, 0,
-		NPC_S_KPU8_UDP, 8, 0,
+		0, 0, 0, 0, 1,
+		NPC_S_NA, 0, 0,
 		NPC_LID_LC, NPC_LT_NA,
 		0,
 		0, 0, 0, 0,
 	},
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		0, 0, 0, 0, 0,
-		NPC_S_KPU8_SCTP, 8, 0,
+		0, 0, 0, 0, 1,
+		NPC_S_NA, 0, 0,
 		NPC_LID_LC, NPC_LT_NA,
 		0,
 		0, 0, 0, 0,
 	},
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		0, 0, 0, 0, 0,
-		NPC_S_KPU8_ICMP, 8, 0,
+		0, 0, 0, 0, 1,
+		NPC_S_NA, 0, 0,
 		NPC_LID_LC, NPC_LT_NA,
 		0,
 		0, 0, 0, 0,
 	},
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		0, 0, 0, 0, 0,
-		NPC_S_KPU8_ICMP6, 8, 0,
+		0, 0, 0, 0, 1,
+		NPC_S_NA, 0, 0,
 		NPC_LID_LC, NPC_LT_NA,
 		0,
 		0, 0, 0, 0,
 	},
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		0, 0, 0, 0, 0,
-		NPC_S_KPU8_ESP, 8, 0,
+		0, 0, 0, 0, 1,
+		NPC_S_NA, 0, 0,
 		NPC_LID_LC, NPC_LT_NA,
 		0,
 		0, 0, 0, 0,
 	},
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		0, 0, 0, 0, 0,
-		NPC_S_KPU8_AH, 8, 0,
+		0, 0, 0, 0, 1,
+		NPC_S_NA, 0, 0,
 		NPC_LID_LC, NPC_LT_NA,
 		0,
 		0, 0, 0, 0,
 	},
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		0, 0, 0, 0, 0,
-		NPC_S_KPU8_GRE, 8, 0,
+		0, 0, 0, 0, 1,
+		NPC_S_NA, 0, 0,
 		NPC_LID_LC, NPC_LT_NA,
 		0,
 		0, 0, 0, 0,
 	},
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		6, 0, 0, 4, 0,
-		NPC_S_KPU12_TU_IP6, 8, 0,
+		0, 0, 0, 0, 1,
+		NPC_S_NA, 0, 0,
 		NPC_LID_LC, NPC_LT_NA,
 		0,
 		0, 0, 0, 0,
 	},
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		2, 6, 10, 1, 0,
-		NPC_S_KPU9_TU_MPLS_IN_IP, 8, 0,
+		0, 0, 0, 0, 1,
+		NPC_S_NA, 0, 0,
 		NPC_LID_LC, NPC_LT_NA,
 		0,
 		0, 0, 0, 0,
@@ -11231,6 +11395,22 @@ static const struct npc_kpu_profile_action kpu8_action_entries[] = {
 	},
 	{
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 0, 0,
+		NPC_S_KPU9_ESP, 8, 1,
+		NPC_LID_LD, NPC_LT_LD_UDP,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 0, 0,
+		NPC_S_KPU9_ESP, 8, 1,
+		NPC_LID_LD, NPC_LT_LD_UDP,
+		0,
+		0, 0, 0, 0,
+	},
+	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
 		0, 0, 0, 7, 0,
 		NPC_S_KPU16_UDP_DATA, 8, 1,
 		NPC_LID_LD, NPC_LT_LD_UDP,
@@ -11273,14 +11453,6 @@ static const struct npc_kpu_profile_action kpu8_action_entries[] = {
 		NPC_ERRLEV_RE, NPC_EC_NOERR,
 		0, 0, 0, 0, 1,
 		NPC_S_NA, 0, 1,
-		NPC_LID_LD, NPC_LT_LD_ESP,
-		0,
-		0, 0, 0, 0,
-	},
-	{
-		NPC_ERRLEV_RE, NPC_EC_NOERR,
-		0, 0, 0, 0, 1,
-		NPC_S_NA, 0, 1,
 		NPC_LID_LD, NPC_LT_LD_AH,
 		0,
 		0, 0, 0, 0,
@@ -12105,6 +12277,14 @@ static const struct npc_kpu_profile_action kpu9_action_entries[] = {
 		0, 0, 0, 0,
 	},
 	{
+		NPC_ERRLEV_RE, NPC_EC_NOERR,
+		0, 0, 0, 0, 1,
+		NPC_S_NA, 0, 1,
+		NPC_LID_LE, NPC_LT_LE_ESP,
+		0,
+		0, 0, 0, 0,
+	},
+	{
 		NPC_ERRLEV_LE, NPC_EC_UNK,
 		0, 0, 0, 0, 1,
 		NPC_S_NA, 0, 0,
@@ -13114,4 +13294,163 @@ static const struct npc_kpu_profile npc_kpu_profiles[] = {
 	},
 };
 
+static const struct npc_lt_def_cfg npc_lt_defaults = {
+	.rx_ol2 = {
+		.lid = NPC_LID_LA,
+		.ltype_match = NPC_LT_LA_ETHER,
+		.ltype_mask = 0x0F,
+	},
+	.rx_oip4 = {
+		.lid = NPC_LID_LC,
+		.ltype_match = NPC_LT_LC_IP,
+		.ltype_mask = 0x0E,
+	},
+	.rx_iip4 = {
+		.lid = NPC_LID_LG,
+		.ltype_match = NPC_LT_LG_TU_IP,
+		.ltype_mask = 0x0F,
+	},
+	.rx_oip6 = {
+		.lid = NPC_LID_LC,
+		.ltype_match = NPC_LT_LC_IP6,
+		.ltype_mask = 0x0E,
+	},
+	.rx_iip6 = {
+		.lid = NPC_LID_LG,
+		.ltype_match = NPC_LT_LG_TU_IP6,
+		.ltype_mask = 0x0F,
+	},
+	.rx_otcp = {
+		.lid = NPC_LID_LD,
+		.ltype_match = NPC_LT_LD_TCP,
+		.ltype_mask = 0x0F,
+	},
+	.rx_itcp = {
+		.lid = NPC_LID_LH,
+		.ltype_match = NPC_LT_LH_TU_TCP,
+		.ltype_mask = 0x0F,
+	},
+	.rx_oudp = {
+		.lid = NPC_LID_LD,
+		.ltype_match = NPC_LT_LD_UDP,
+		.ltype_mask = 0x0F,
+	},
+	.rx_iudp = {
+		.lid = NPC_LID_LH,
+		.ltype_match = NPC_LT_LH_TU_UDP,
+		.ltype_mask = 0x0F,
+	},
+	.rx_osctp = {
+		.lid = NPC_LID_LD,
+		.ltype_match = NPC_LT_LD_SCTP,
+		.ltype_mask = 0x0F,
+	},
+	.rx_isctp = {
+		.lid = NPC_LID_LH,
+		.ltype_match = NPC_LT_LH_TU_SCTP,
+		.ltype_mask = 0x0F,
+	},
+	.rx_ipsec = {
+		{
+			.lid = NPC_LID_LE,
+			.ltype_match = NPC_LT_LE_ESP,
+			.ltype_mask = 0x0F,
+		},
+		{
+			.spi_offset = 8,
+			.lid = NPC_LID_LH,
+			.ltype_match = NPC_LT_LH_TU_ESP,
+			.ltype_mask = 0x0F,
+		},
+	},
+	.pck_ol2 = {
+			.lid = NPC_LID_LA,
+			.ltype_match = NPC_LT_LA_ETHER,
+			.ltype_mask = 0x0F,
+	},
+	.pck_oip4 = {
+			.lid = NPC_LID_LC,
+			.ltype_match = NPC_LT_LC_IP,
+			.ltype_mask = 0x0E,
+	},
+	.pck_iip4 = {
+			.lid = NPC_LID_LG,
+			.ltype_match = NPC_LT_LG_TU_IP,
+			.ltype_mask = 0x0F,
+	},
+};
+
+static const struct npc_mcam_kex npc_mkex_default = {
+	.mkex_sign = MKEX_SIGN,
+	.name = "default",
+	.kpu_version = NPC_KPU_PROFILE_VER,
+	.keyx_cfg = {
+		/* nibble: LA..LE (ltype only) + Channel */
+		[NIX_INTF_RX] = ((u64)NPC_MCAM_KEY_X2 << 32) | 0x49247,
+		[NIX_INTF_TX] = ((u64)NPC_MCAM_KEY_X2 << 32) | ((1ULL << 19) - 1),
+	},
+	.intf_lid_lt_ld = {
+	/* Default RX MCAM KEX profile */
+	[NIX_INTF_RX] = {
+		[NPC_LID_LA] = {
+			/* Layer A: Ethernet: */
+			[NPC_LT_LA_ETHER] = {
+				/* DMAC: 6 bytes, KW1[47:0] */
+				KEX_LD_CFG(0x05, 0x0, 0x1, 0x0, NPC_KEXOF_DMAC),
+				/* Ethertype: 2 bytes, KW0[47:32] */
+				KEX_LD_CFG(0x01, 0xc, 0x1, 0x0, 0x4),
+			},
+		},
+		[NPC_LID_LB] = {
+			/* Layer B: Single VLAN (CTAG) */
+			/* CTAG VLAN[2..3] + Ethertype, 4 bytes, KW0[63:32] */
+			[NPC_LT_LB_CTAG] = {
+				KEX_LD_CFG(0x03, 0x0, 0x1, 0x0, 0x4),
+			},
+			/* Layer B: Stacked VLAN (STAG|QinQ) */
+			[NPC_LT_LB_STAG_QINQ] = {
+				/* CTAG VLAN[2..3] + Ethertype, 4 bytes, KW0[63:32] */
+				KEX_LD_CFG(0x03, 0x4, 0x1, 0x0, 0x4),
+			},
+			[NPC_LT_LB_FDSA] = {
+				/* SWITCH PORT: 1 byte, KW0[63:48] */
+				KEX_LD_CFG(0x0, 0x1, 0x1, 0x0, 0x6),
+				/* Ethertype: 2 bytes, KW0[47:32] */
+				KEX_LD_CFG(0x01, 0x4, 0x1, 0x0, 0x4),
+			},
+		},
+		[NPC_LID_LC] = {
+			/* Layer C: IPv4 */
+			[NPC_LT_LC_IP] = {
+				/* SIP+DIP: 8 bytes, KW2[63:0] */
+				KEX_LD_CFG(0x07, 0xc, 0x1, 0x0, 0x10),
+				/* TOS: 1 byte, KW1[63:56] */
+				KEX_LD_CFG(0x0, 0x1, 0x1, 0x0, 0xf),
+			},
+			/* Layer C: IPv6 */
+			[NPC_LT_LC_IP6] = {
+				/* Everything up to SADDR: 8 bytes, KW2[63:0] */
+				KEX_LD_CFG(0x07, 0x0, 0x1, 0x0, 0x10),
+			},
+		},
+		[NPC_LID_LD] = {
+			/* Layer D:UDP */
+			[NPC_LT_LD_UDP] = {
+				/* SPORT: 2 bytes, KW3[15:0] */
+				KEX_LD_CFG(0x1, 0x0, 0x1, 0x0, 0x18),
+				/* DPORT: 2 bytes, KW3[31:16] */
+				KEX_LD_CFG(0x1, 0x2, 0x1, 0x0, 0x1a),
+			},
+			/* Layer D:TCP */
+			[NPC_LT_LD_TCP] = {
+				/* SPORT: 2 bytes, KW3[15:0] */
+				KEX_LD_CFG(0x1, 0x0, 0x1, 0x0, 0x18),
+				/* DPORT: 2 bytes, KW3[31:16] */
+				KEX_LD_CFG(0x1, 0x2, 0x1, 0x0, 0x1a),
+			},
+		},
+	},
+	},
+};
+
 #endif /* NPC_PROFILE_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
index c3ef73ae782c..e1f918960730 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
@@ -20,6 +20,8 @@
 #include "rvu_reg.h"
 #include "ptp.h"
 
+#include "rvu_trace.h"
+
 #define DRV_NAME	"octeontx2-af"
 #define DRV_STRING      "Marvell OcteonTX2 RVU Admin Function Driver"
 
@@ -1549,6 +1551,7 @@ static int rvu_process_mbox_msg(struct otx2_mbox *mbox, int devid,
 		if (rsp && err)						\
 			rsp->hdr.rc = err;				\
 									\
+		trace_otx2_msg_process(mbox->pdev, _id, err);		\
 		return rsp ? err : -ENOMEM;				\
 	}
 MBOX_MESSAGES
@@ -1881,6 +1884,8 @@ static irqreturn_t rvu_mbox_intr_handler(int irq, void *rvu_irq)
 	intr = rvu_read64(rvu, BLKADDR_RVUM, RVU_AF_PFAF_MBOX_INT);
 	/* Clear interrupts */
 	rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_PFAF_MBOX_INT, intr);
+	if (intr)
+		trace_otx2_msg_interrupt(rvu->pdev, "PF(s) to AF", intr);
 
 	/* Sync with mbox memory region */
 	rmb();
@@ -1898,6 +1903,8 @@ static irqreturn_t rvu_mbox_intr_handler(int irq, void *rvu_irq)
 
 	intr = rvupf_read64(rvu, RVU_PF_VFPF_MBOX_INTX(0));
 	rvupf_write64(rvu, RVU_PF_VFPF_MBOX_INTX(0), intr);
+	if (intr)
+		trace_otx2_msg_interrupt(rvu->pdev, "VF(s) to AF", intr);
 
 	rvu_queue_work(&rvu->afvf_wq_info, 0, vfs, intr);
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index 05da7a91944a..f1b03f8ab0ee 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -291,6 +291,20 @@ struct rvu_fwdata {
 
 struct ptp;
 
+/* KPU profile adapter structure gathering all KPU configuration data and abstracting out the
+ * source where it came from.
+ */
+struct npc_kpu_profile_adapter {
+	const char			*name;
+	u64				version;
+	const struct npc_lt_def_cfg	*lt_def;
+	const struct npc_kpu_profile_action	*ikpu; /* array[pkinds] */
+	const struct npc_kpu_profile	*kpu; /* array[kpus] */
+	const struct npc_mcam_kex	*mkex;
+	size_t				pkinds;
+	size_t				kpus;
+};
+
 struct rvu {
 	void __iomem		*afreg_base;
 	void __iomem		*pfreg_base;
@@ -339,6 +353,9 @@ struct rvu {
 	/* Firmware data */
 	struct rvu_fwdata	*fwdata;
 
+	/* NPC KPU data */
+	struct npc_kpu_profile_adapter kpu;
+
 	struct ptp		*ptp;
 
 #ifdef CONFIG_DEBUG_FS
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
index fe3389c144b5..fa9152ff5e2a 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
@@ -15,6 +15,7 @@
 #include "rvu.h"
 #include "cgx.h"
 #include "rvu_reg.h"
+#include "rvu_trace.h"
 
 struct cgx_evq_entry {
 	struct list_head evq_node;
@@ -34,6 +35,7 @@ static struct _req_type __maybe_unused					\
 		return NULL;						\
 	req->hdr.sig = OTX2_MBOX_REQ_SIG;				\
 	req->hdr.id = _id;						\
+	trace_otx2_msg_alloc(rvu->pdev, _id, sizeof(*req));		\
 	return req;							\
 }
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
index 08181fc5f5d4..b403c16caa2f 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
@@ -2509,6 +2509,14 @@ static int set_flowkey_fields(struct nix_rx_flowkey_alg *alg, u32 flow_cfg)
 			field->ltype_match = NPC_LT_LE_GTPU;
 			field->ltype_mask = 0xF;
 			break;
+		case NIX_FLOW_KEY_TYPE_VLAN:
+			field->lid = NPC_LID_LB;
+			field->hdr_offset = 2; /* Skip TPID (2-bytes) */
+			field->bytesm1 = 1; /* 2 Bytes (Actually 12 bits) */
+			field->ltype_match = NPC_LT_LB_CTAG;
+			field->ltype_mask = 0xF;
+			field->fn_mask = 1; /* Mask out the first nibble */
+			break;
 		}
 		field->ena = 1;
 
@@ -3104,6 +3112,7 @@ static int nix_aq_init(struct rvu *rvu, struct rvu_block *block)
 
 int rvu_nix_init(struct rvu *rvu)
 {
+	const struct npc_lt_def_cfg *ltdefs;
 	struct rvu_hwinfo *hw = rvu->hw;
 	struct rvu_block *block;
 	int blkaddr, err;
@@ -3134,6 +3143,7 @@ int rvu_nix_init(struct rvu *rvu)
 		rvu_write64(rvu, blkaddr, NIX_AF_SQM_DBG_CTL_STATUS, cfg);
 	}
 
+	ltdefs = rvu->kpu.lt_def;
 	/* Calibrate X2P bus to check if CGX/LBK links are fine */
 	err = nix_calibrate_x2p(rvu, blkaddr);
 	if (err)
@@ -3181,28 +3191,38 @@ int rvu_nix_init(struct rvu *rvu)
 		 * and validate length and checksums.
 		 */
 		rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_OL2,
-			    (NPC_LID_LA << 8) | (NPC_LT_LA_ETHER << 4) | 0x0F);
+			    (ltdefs->rx_ol2.lid << 8) | (ltdefs->rx_ol2.ltype_match << 4) |
+			    ltdefs->rx_ol2.ltype_mask);
 		rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_OIP4,
-			    (NPC_LID_LC << 8) | (NPC_LT_LC_IP << 4) | 0x0F);
+			    (ltdefs->rx_oip4.lid << 8) | (ltdefs->rx_oip4.ltype_match << 4) |
+			    ltdefs->rx_oip4.ltype_mask);
 		rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_IIP4,
-			    (NPC_LID_LG << 8) | (NPC_LT_LG_TU_IP << 4) | 0x0F);
+			    (ltdefs->rx_iip4.lid << 8) | (ltdefs->rx_iip4.ltype_match << 4) |
+			    ltdefs->rx_iip4.ltype_mask);
 		rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_OIP6,
-			    (NPC_LID_LC << 8) | (NPC_LT_LC_IP6 << 4) | 0x0F);
+			    (ltdefs->rx_oip6.lid << 8) | (ltdefs->rx_oip6.ltype_match << 4) |
+			    ltdefs->rx_oip6.ltype_mask);
 		rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_IIP6,
-			    (NPC_LID_LG << 8) | (NPC_LT_LG_TU_IP6 << 4) | 0x0F);
+			    (ltdefs->rx_iip6.lid << 8) | (ltdefs->rx_iip6.ltype_match << 4) |
+			    ltdefs->rx_iip6.ltype_mask);
 		rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_OTCP,
-			    (NPC_LID_LD << 8) | (NPC_LT_LD_TCP << 4) | 0x0F);
+			    (ltdefs->rx_otcp.lid << 8) | (ltdefs->rx_otcp.ltype_match << 4) |
+			    ltdefs->rx_otcp.ltype_mask);
 		rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_ITCP,
-			    (NPC_LID_LH << 8) | (NPC_LT_LH_TU_TCP << 4) | 0x0F);
+			    (ltdefs->rx_itcp.lid << 8) | (ltdefs->rx_itcp.ltype_match << 4) |
+			    ltdefs->rx_itcp.ltype_mask);
 		rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_OUDP,
-			    (NPC_LID_LD << 8) | (NPC_LT_LD_UDP << 4) | 0x0F);
+			    (ltdefs->rx_oudp.lid << 8) | (ltdefs->rx_oudp.ltype_match << 4) |
+			    ltdefs->rx_oudp.ltype_mask);
 		rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_IUDP,
-			    (NPC_LID_LH << 8) | (NPC_LT_LH_TU_UDP << 4) | 0x0F);
+			    (ltdefs->rx_iudp.lid << 8) | (ltdefs->rx_iudp.ltype_match << 4) |
+			    ltdefs->rx_iudp.ltype_mask);
 		rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_OSCTP,
-			    (NPC_LID_LD << 8) | (NPC_LT_LD_SCTP << 4) | 0x0F);
+			    (ltdefs->rx_osctp.lid << 8) | (ltdefs->rx_osctp.ltype_match << 4) |
+			    ltdefs->rx_osctp.ltype_mask);
 		rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_ISCTP,
-			    (NPC_LID_LH << 8) | (NPC_LT_LH_TU_SCTP << 4) |
-			    0x0F);
+			    (ltdefs->rx_isctp.lid << 8) | (ltdefs->rx_isctp.ltype_match << 4) |
+			    ltdefs->rx_isctp.ltype_mask);
 
 		err = nix_rx_flowkey_alg_cfg(rvu, blkaddr);
 		if (err)
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
index 6a1ddb2da1a5..0abe5fd12131 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
@@ -29,6 +29,8 @@
 #define NPC_PARSE_RESULT_DMAC_OFFSET	8
 #define NPC_HW_TSTAMP_OFFSET		8
 
+static const char def_pfl_name[] = "default";
+
 static void npc_mcam_free_all_entries(struct rvu *rvu, struct npc_mcam *mcam,
 				      int blkaddr, u16 pcifunc);
 static void npc_mcam_free_all_counters(struct rvu *rvu, struct npc_mcam *mcam,
@@ -448,7 +450,7 @@ void rvu_npc_install_promisc_entry(struct rvu *rvu, u16 pcifunc,
 	entry.kw_mask[0] = 0xFFFULL;
 
 	if (allmulti) {
-		kwi = NPC_PARSE_RESULT_DMAC_OFFSET / sizeof(u64);
+		kwi = NPC_KEXOF_DMAC / sizeof(u64);
 		entry.kw[kwi] = BIT_ULL(40); /* LSB bit of 1st byte in DMAC */
 		entry.kw_mask[kwi] = BIT_ULL(40);
 	}
@@ -718,88 +720,8 @@ void rvu_npc_disable_mcam_entries(struct rvu *rvu, u16 pcifunc, int nixlf)
 	rvu_write64(rvu, blkaddr,			\
 		NPC_AF_INTFX_LDATAX_FLAGSX_CFG(intf, ld, flags), cfg)
 
-#define KEX_LD_CFG(bytesm1, hdr_ofs, ena, flags_ena, key_ofs)		\
-			(((bytesm1) << 16) | ((hdr_ofs) << 8) | ((ena) << 7) | \
-			 ((flags_ena) << 6) | ((key_ofs) & 0x3F))
-
-static void npc_config_ldata_extract(struct rvu *rvu, int blkaddr)
-{
-	struct npc_mcam *mcam = &rvu->hw->mcam;
-	int lid, ltype;
-	int lid_count;
-	u64 cfg;
-
-	cfg = rvu_read64(rvu, blkaddr, NPC_AF_CONST);
-	lid_count = (cfg >> 4) & 0xF;
-
-	/* First clear any existing config i.e
-	 * disable LDATA and FLAGS extraction.
-	 */
-	for (lid = 0; lid < lid_count; lid++) {
-		for (ltype = 0; ltype < 16; ltype++) {
-			SET_KEX_LD(NIX_INTF_RX, lid, ltype, 0, 0ULL);
-			SET_KEX_LD(NIX_INTF_RX, lid, ltype, 1, 0ULL);
-			SET_KEX_LD(NIX_INTF_TX, lid, ltype, 0, 0ULL);
-			SET_KEX_LD(NIX_INTF_TX, lid, ltype, 1, 0ULL);
-
-			SET_KEX_LDFLAGS(NIX_INTF_RX, 0, ltype, 0ULL);
-			SET_KEX_LDFLAGS(NIX_INTF_RX, 1, ltype, 0ULL);
-			SET_KEX_LDFLAGS(NIX_INTF_TX, 0, ltype, 0ULL);
-			SET_KEX_LDFLAGS(NIX_INTF_TX, 1, ltype, 0ULL);
-		}
-	}
-
-	if (mcam->keysize != NPC_MCAM_KEY_X2)
-		return;
-
-	/* Default MCAM KEX profile */
-	/* Layer A: Ethernet: */
-
-	/* DMAC: 6 bytes, KW1[47:0] */
-	cfg = KEX_LD_CFG(0x05, 0x0, 0x1, 0x0, NPC_PARSE_RESULT_DMAC_OFFSET);
-	SET_KEX_LD(NIX_INTF_RX, NPC_LID_LA, NPC_LT_LA_ETHER, 0, cfg);
-
-	/* Ethertype: 2 bytes, KW0[47:32] */
-	cfg = KEX_LD_CFG(0x01, 0xc, 0x1, 0x0, 0x4);
-	SET_KEX_LD(NIX_INTF_RX, NPC_LID_LA, NPC_LT_LA_ETHER, 1, cfg);
-
-	/* Layer B: Single VLAN (CTAG) */
-	/* CTAG VLAN[2..3] + Ethertype, 4 bytes, KW0[63:32] */
-	cfg = KEX_LD_CFG(0x03, 0x0, 0x1, 0x0, 0x4);
-	SET_KEX_LD(NIX_INTF_RX, NPC_LID_LB, NPC_LT_LB_CTAG, 0, cfg);
-
-	/* Layer B: Stacked VLAN (STAG|QinQ) */
-	/* CTAG VLAN[2..3] + Ethertype, 4 bytes, KW0[63:32] */
-	cfg = KEX_LD_CFG(0x03, 0x4, 0x1, 0x0, 0x4);
-	SET_KEX_LD(NIX_INTF_RX, NPC_LID_LB, NPC_LT_LB_STAG_QINQ, 0, cfg);
-
-	/* Layer C: IPv4 */
-	/* SIP+DIP: 8 bytes, KW2[63:0] */
-	cfg = KEX_LD_CFG(0x07, 0xc, 0x1, 0x0, 0x10);
-	SET_KEX_LD(NIX_INTF_RX, NPC_LID_LC, NPC_LT_LC_IP, 0, cfg);
-	/* TOS: 1 byte, KW1[63:56] */
-	cfg = KEX_LD_CFG(0x0, 0x1, 0x1, 0x0, 0xf);
-	SET_KEX_LD(NIX_INTF_RX, NPC_LID_LC, NPC_LT_LC_IP, 1, cfg);
-
-	/* Layer D:UDP */
-	/* SPORT: 2 bytes, KW3[15:0] */
-	cfg = KEX_LD_CFG(0x1, 0x0, 0x1, 0x0, 0x18);
-	SET_KEX_LD(NIX_INTF_RX, NPC_LID_LD, NPC_LT_LD_UDP, 0, cfg);
-	/* DPORT: 2 bytes, KW3[31:16] */
-	cfg = KEX_LD_CFG(0x1, 0x2, 0x1, 0x0, 0x1a);
-	SET_KEX_LD(NIX_INTF_RX, NPC_LID_LD, NPC_LT_LD_UDP, 1, cfg);
-
-	/* Layer D:TCP */
-	/* SPORT: 2 bytes, KW3[15:0] */
-	cfg = KEX_LD_CFG(0x1, 0x0, 0x1, 0x0, 0x18);
-	SET_KEX_LD(NIX_INTF_RX, NPC_LID_LD, NPC_LT_LD_TCP, 0, cfg);
-	/* DPORT: 2 bytes, KW3[31:16] */
-	cfg = KEX_LD_CFG(0x1, 0x2, 0x1, 0x0, 0x1a);
-	SET_KEX_LD(NIX_INTF_RX, NPC_LID_LD, NPC_LT_LD_TCP, 1, cfg);
-}
-
 static void npc_program_mkex_profile(struct rvu *rvu, int blkaddr,
-				     struct npc_mcam_kex *mkex)
+				     const struct npc_mcam_kex *mkex)
 {
 	int lid, lt, ld, fl;
 
@@ -839,34 +761,31 @@ static void npc_program_mkex_profile(struct rvu *rvu, int blkaddr,
 	}
 }
 
-/* strtoull of "mkexprof" with base:36 */
-#define MKEX_SIGN      0x19bbfdbd15f
 #define MKEX_END_SIGN  0xdeadbeef
 
-static void npc_load_mkex_profile(struct rvu *rvu, int blkaddr)
+static void npc_load_mkex_profile(struct rvu *rvu, int blkaddr,
+				  const char *mkex_profile)
 {
-	const char *mkex_profile = rvu->mkex_pfl_name;
 	struct device *dev = &rvu->pdev->dev;
-	void __iomem *mkex_prfl_addr = NULL;
 	struct npc_mcam_kex *mcam_kex;
-	u64 prfl_addr;
-	u64 prfl_sz;
+	void *mkex_prfl_addr = NULL;
+	u64 prfl_addr, prfl_sz;
 
 	/* If user not selected mkex profile */
-	if (!strncmp(mkex_profile, "default", MKEX_NAME_LEN))
-		goto load_default;
+	if (!strncmp(mkex_profile, def_pfl_name, MKEX_NAME_LEN))
+		goto program_mkex;
 
 	if (!rvu->fwdata)
-		goto load_default;
+		goto program_mkex;
 	prfl_addr = rvu->fwdata->mcam_addr;
 	prfl_sz = rvu->fwdata->mcam_sz;
 
 	if (!prfl_addr || !prfl_sz)
-		goto load_default;
+		goto program_mkex;
 
-	mkex_prfl_addr = ioremap_wc(prfl_addr, prfl_sz);
+	mkex_prfl_addr = memremap(prfl_addr, prfl_sz, MEMREMAP_WC);
 	if (!mkex_prfl_addr)
-		goto load_default;
+		goto program_mkex;
 
 	mcam_kex = (struct npc_mcam_kex *)mkex_prfl_addr;
 
@@ -878,31 +797,23 @@ static void npc_load_mkex_profile(struct rvu *rvu, int blkaddr)
 			 * parse nibble enable configuration has to be
 			 * identical for both Rx and Tx interfaces.
 			 */
-			if (is_rvu_96xx_B0(rvu) &&
-			    mcam_kex->keyx_cfg[NIX_INTF_RX] !=
-			    mcam_kex->keyx_cfg[NIX_INTF_TX])
-				goto load_default;
-
-			/* Program selected mkex profile */
-			npc_program_mkex_profile(rvu, blkaddr, mcam_kex);
-
-			goto unmap;
+			if (!is_rvu_96xx_B0(rvu) ||
+			    mcam_kex->keyx_cfg[NIX_INTF_RX] == mcam_kex->keyx_cfg[NIX_INTF_TX])
+				rvu->kpu.mkex = mcam_kex;
+			goto program_mkex;
 		}
 
 		mcam_kex++;
 		prfl_sz -= sizeof(struct npc_mcam_kex);
 	}
-	dev_warn(dev, "Failed to load requested profile: %s\n",
-		 rvu->mkex_pfl_name);
+	dev_warn(dev, "Failed to load requested profile: %s\n", mkex_profile);
 
-load_default:
-	dev_info(rvu->dev, "Using default mkex profile\n");
-	/* Config packet data and flags extraction into PARSE result */
-	npc_config_ldata_extract(rvu, blkaddr);
-
-unmap:
+program_mkex:
+	dev_info(rvu->dev, "Using %s mkex profile\n", rvu->kpu.mkex->name);
+	/* Program selected mkex profile */
+	npc_program_mkex_profile(rvu, blkaddr, rvu->kpu.mkex);
 	if (mkex_prfl_addr)
-		iounmap(mkex_prfl_addr);
+		memunmap(mkex_prfl_addr);
 }
 
 static void npc_config_kpuaction(struct rvu *rvu, int blkaddr,
@@ -1014,6 +925,27 @@ static void npc_program_kpu_profile(struct rvu *rvu, int blkaddr, int kpu,
 	rvu_write64(rvu, blkaddr, NPC_AF_KPUX_CFG(kpu), 0x01);
 }
 
+static int npc_prepare_default_kpu(struct npc_kpu_profile_adapter *profile)
+{
+	profile->name = def_pfl_name;
+	profile->version = NPC_KPU_PROFILE_VER;
+	profile->ikpu = ikpu_action_entries;
+	profile->pkinds = ARRAY_SIZE(ikpu_action_entries);
+	profile->kpu = npc_kpu_profiles;
+	profile->kpus = ARRAY_SIZE(npc_kpu_profiles);
+	profile->lt_def = &npc_lt_defaults;
+	profile->mkex = &npc_mkex_default;
+
+	return 0;
+}
+
+static void npc_load_kpu_profile(struct rvu *rvu)
+{
+	struct npc_kpu_profile_adapter *profile = &rvu->kpu;
+
+	npc_prepare_default_kpu(profile);
+}
+
 static void npc_parser_profile_init(struct rvu *rvu, int blkaddr)
 {
 	struct rvu_hwinfo *hw = rvu->hw;
@@ -1032,25 +964,26 @@ static void npc_parser_profile_init(struct rvu *rvu, int blkaddr)
 		rvu_write64(rvu, blkaddr, NPC_AF_KPUX_CFG(idx), 0x00);
 	}
 
+	/* Load and customize KPU profile. */
+	npc_load_kpu_profile(rvu);
+
 	/* First program IKPU profile i.e PKIND configs.
 	 * Check HW max count to avoid configuring junk or
 	 * writing to unsupported CSR addresses.
 	 */
 	pkind = &hw->pkind;
-	num_pkinds = ARRAY_SIZE(ikpu_action_entries);
+	num_pkinds = rvu->kpu.pkinds;
 	num_pkinds = min_t(int, pkind->rsrc.max, num_pkinds);
 
 	for (idx = 0; idx < num_pkinds; idx++)
-		npc_config_kpuaction(rvu, blkaddr,
-				     &ikpu_action_entries[idx], 0, idx, true);
+		npc_config_kpuaction(rvu, blkaddr, &rvu->kpu.ikpu[idx], 0, idx, true);
 
 	/* Program KPU CAM and Action profiles */
-	num_kpus = ARRAY_SIZE(npc_kpu_profiles);
+	num_kpus = rvu->kpu.kpus;
 	num_kpus = min_t(int, hw->npc_kpus, num_kpus);
 
 	for (idx = 0; idx < num_kpus; idx++)
-		npc_program_kpu_profile(rvu, blkaddr,
-					idx, &npc_kpu_profiles[idx]);
+		npc_program_kpu_profile(rvu, blkaddr, idx, &rvu->kpu.kpu[idx]);
 }
 
 static int npc_mcam_rsrcs_init(struct rvu *rvu, int blkaddr)
@@ -1175,11 +1108,11 @@ free_mem:
 
 int rvu_npc_init(struct rvu *rvu)
 {
+	struct npc_kpu_profile_adapter *kpu = &rvu->kpu;
 	struct npc_pkind *pkind = &rvu->hw->pkind;
 	struct npc_mcam *mcam = &rvu->hw->mcam;
-	u64 keyz = NPC_MCAM_KEY_X2;
+	u64 cfg, nibble_ena, rx_kex, tx_kex;
 	int blkaddr, entry, bank, err;
-	u64 cfg, nibble_ena;
 
 	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
 	if (blkaddr < 0) {
@@ -1213,13 +1146,16 @@ int rvu_npc_init(struct rvu *rvu)
 
 	/* Config Outer L2, IPv4's NPC layer info */
 	rvu_write64(rvu, blkaddr, NPC_AF_PCK_DEF_OL2,
-		    (NPC_LID_LA << 8) | (NPC_LT_LA_ETHER << 4) | 0x0F);
+		    (kpu->lt_def->pck_ol2.lid << 8) | (kpu->lt_def->pck_ol2.ltype_match << 4) |
+		    kpu->lt_def->pck_ol2.ltype_mask);
 	rvu_write64(rvu, blkaddr, NPC_AF_PCK_DEF_OIP4,
-		    (NPC_LID_LC << 8) | (NPC_LT_LC_IP << 4) | 0x0F);
+		    (kpu->lt_def->pck_oip4.lid << 8) | (kpu->lt_def->pck_oip4.ltype_match << 4) |
+		    kpu->lt_def->pck_oip4.ltype_mask);
 
 	/* Config Inner IPV4 NPC layer info */
 	rvu_write64(rvu, blkaddr, NPC_AF_PCK_DEF_IIP4,
-		    (NPC_LID_LG << 8) | (NPC_LT_LG_TU_IP << 4) | 0x0F);
+		    (kpu->lt_def->pck_iip4.lid << 8) | (kpu->lt_def->pck_iip4.ltype_match << 4) |
+		    kpu->lt_def->pck_iip4.ltype_mask);
 
 	/* Enable below for Rx pkts.
 	 * - Outer IPv4 header checksum validation.
@@ -1235,23 +1171,25 @@ int rvu_npc_init(struct rvu *rvu)
 	/* Set RX and TX side MCAM search key size.
 	 * LA..LD (ltype only) + Channel
 	 */
-	nibble_ena = 0x49247;
-	rvu_write64(rvu, blkaddr, NPC_AF_INTFX_KEX_CFG(NIX_INTF_RX),
-			((keyz & 0x3) << 32) | nibble_ena);
+	rx_kex = npc_mkex_default.keyx_cfg[NIX_INTF_RX];
+	tx_kex = npc_mkex_default.keyx_cfg[NIX_INTF_TX];
+	nibble_ena = FIELD_GET(NPC_PARSE_NIBBLE, rx_kex);
+	rvu_write64(rvu, blkaddr, NPC_AF_INTFX_KEX_CFG(NIX_INTF_RX), rx_kex);
 	/* Due to an errata (35786) in A0 pass silicon, parse nibble enable
 	 * configuration has to be identical for both Rx and Tx interfaces.
 	 */
-	if (!is_rvu_96xx_B0(rvu))
-		nibble_ena = (1ULL << 19) - 1;
-	rvu_write64(rvu, blkaddr, NPC_AF_INTFX_KEX_CFG(NIX_INTF_TX),
-			((keyz & 0x3) << 32) | nibble_ena);
+	if (is_rvu_96xx_B0(rvu)) {
+		tx_kex &= ~NPC_PARSE_NIBBLE;
+		tx_kex |= FIELD_PREP(NPC_PARSE_NIBBLE, nibble_ena);
+	}
+	rvu_write64(rvu, blkaddr, NPC_AF_INTFX_KEX_CFG(NIX_INTF_TX), tx_kex);
 
 	err = npc_mcam_rsrcs_init(rvu, blkaddr);
 	if (err)
 		return err;
 
 	/* Configure MKEX profile */
-	npc_load_mkex_profile(rvu, blkaddr);
+	npc_load_mkex_profile(rvu, blkaddr, rvu->mkex_pfl_name);
 
 	/* Set TX miss action to UCAST_DEFAULT i.e
 	 * transmit the packet on NIX LF SQ's default channel.
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_trace.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_trace.c
new file mode 100644
index 000000000000..56f90cf9c4c0
--- /dev/null
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_trace.c
@@ -0,0 +1,12 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Marvell OcteonTx2 RVU Admin Function driver tracepoints
+ *
+ * Copyright (C) 2020 Marvell International Ltd.
+ */
+
+#define CREATE_TRACE_POINTS
+#include "rvu_trace.h"
+
+EXPORT_TRACEPOINT_SYMBOL(otx2_msg_alloc);
+EXPORT_TRACEPOINT_SYMBOL(otx2_msg_interrupt);
+EXPORT_TRACEPOINT_SYMBOL(otx2_msg_process);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_trace.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_trace.h
new file mode 100644
index 000000000000..e6609068e81b
--- /dev/null
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_trace.h
@@ -0,0 +1,103 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Marvell OcteonTx2 RVU Admin Function driver tracepoints
+ *
+ * Copyright (C) 2020 Marvell International Ltd.
+ */
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM rvu
+
+#if !defined(__RVU_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define __RVU_TRACE_H
+
+#include <linux/types.h>
+#include <linux/tracepoint.h>
+#include <linux/pci.h>
+
+TRACE_EVENT(otx2_msg_alloc,
+	    TP_PROTO(const struct pci_dev *pdev, u16 id, u64 size),
+	    TP_ARGS(pdev, id, size),
+	    TP_STRUCT__entry(__string(dev, pci_name(pdev))
+			     __field(u16, id)
+			     __field(u64, size)
+	    ),
+	    TP_fast_assign(__assign_str(dev, pci_name(pdev))
+			   __entry->id = id;
+			   __entry->size = size;
+	    ),
+	    TP_printk("[%s] msg:(0x%x) size:%lld\n", __get_str(dev),
+		      __entry->id, __entry->size)
+);
+
+TRACE_EVENT(otx2_msg_send,
+	    TP_PROTO(const struct pci_dev *pdev, u16 num_msgs, u64 msg_size),
+	    TP_ARGS(pdev, num_msgs, msg_size),
+	    TP_STRUCT__entry(__string(dev, pci_name(pdev))
+			     __field(u16, num_msgs)
+			     __field(u64, msg_size)
+	    ),
+	    TP_fast_assign(__assign_str(dev, pci_name(pdev))
+			   __entry->num_msgs = num_msgs;
+			   __entry->msg_size = msg_size;
+	    ),
+	    TP_printk("[%s] sent %d msg(s) of size:%lld\n", __get_str(dev),
+		      __entry->num_msgs, __entry->msg_size)
+);
+
+TRACE_EVENT(otx2_msg_check,
+	    TP_PROTO(const struct pci_dev *pdev, u16 reqid, u16 rspid, int rc),
+	    TP_ARGS(pdev, reqid, rspid, rc),
+	    TP_STRUCT__entry(__string(dev, pci_name(pdev))
+			     __field(u16, reqid)
+			     __field(u16, rspid)
+			     __field(int, rc)
+	    ),
+	    TP_fast_assign(__assign_str(dev, pci_name(pdev))
+			   __entry->reqid = reqid;
+			   __entry->rspid = rspid;
+			   __entry->rc = rc;
+	    ),
+	    TP_printk("[%s] req->id:0x%x rsp->id:0x%x resp_code:%d\n",
+		      __get_str(dev), __entry->reqid,
+		      __entry->rspid, __entry->rc)
+);
+
+TRACE_EVENT(otx2_msg_interrupt,
+	    TP_PROTO(const struct pci_dev *pdev, const char *msg, u64 intr),
+	    TP_ARGS(pdev, msg, intr),
+	    TP_STRUCT__entry(__string(dev, pci_name(pdev))
+			     __string(str, msg)
+			     __field(u64, intr)
+	    ),
+	    TP_fast_assign(__assign_str(dev, pci_name(pdev))
+			   __assign_str(str, msg)
+			   __entry->intr = intr;
+	    ),
+	    TP_printk("[%s] mbox interrupt %s (0x%llx)\n", __get_str(dev),
+		      __get_str(str), __entry->intr)
+);
+
+TRACE_EVENT(otx2_msg_process,
+	    TP_PROTO(const struct pci_dev *pdev, u16 id, int err),
+	    TP_ARGS(pdev, id, err),
+	    TP_STRUCT__entry(__string(dev, pci_name(pdev))
+			     __field(u16, id)
+			     __field(int, err)
+	    ),
+	    TP_fast_assign(__assign_str(dev, pci_name(pdev))
+			   __entry->id = id;
+			   __entry->err = err;
+	    ),
+	    TP_printk("[%s] msg:(0x%x) error:%d\n", __get_str(dev),
+		      __entry->id, __entry->err)
+);
+
+#endif /* __RVU_TRACE_H */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE rvu_trace
+
+#include <trace/define_trace.h>
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
index 820fc660de66..d2581090f9a4 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
@@ -355,7 +355,7 @@ int otx2_rss_init(struct otx2_nic *pfvf)
 	rss->flowkey_cfg = rss->enable ? rss->flowkey_cfg :
 			   NIX_FLOW_KEY_TYPE_IPV4 | NIX_FLOW_KEY_TYPE_IPV6 |
 			   NIX_FLOW_KEY_TYPE_TCP | NIX_FLOW_KEY_TYPE_UDP |
-			   NIX_FLOW_KEY_TYPE_SCTP;
+			   NIX_FLOW_KEY_TYPE_SCTP | NIX_FLOW_KEY_TYPE_VLAN;
 
 	ret = otx2_set_flowkey_cfg(pfvf);
 	if (ret)
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
index ac47762cce9b..d6253f2a414d 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
@@ -20,6 +20,7 @@
 #include <mbox.h>
 #include "otx2_reg.h"
 #include "otx2_txrx.h"
+#include <rvu_trace.h>
 
 /* PCI device IDs */
 #define PCI_DEVID_OCTEONTX2_RVU_PF              0xA063
@@ -523,6 +524,7 @@ static struct _req_type __maybe_unused					\
 		return NULL;						\
 	req->hdr.sig = OTX2_MBOX_REQ_SIG;				\
 	req->hdr.id = _id;						\
+	trace_otx2_msg_alloc(mbox->mbox.pdev, _id, sizeof(*req));	\
 	return req;							\
 }
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
index 0341d9694e8b..662fb80dbb9d 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
@@ -428,6 +428,8 @@ static int otx2_get_rss_hash_opts(struct otx2_nic *pfvf,
 
 	/* Mimimum is IPv4 and IPv6, SIP/DIP */
 	nfc->data = RXH_IP_SRC | RXH_IP_DST;
+	if (rss->flowkey_cfg & NIX_FLOW_KEY_TYPE_VLAN)
+		nfc->data |= RXH_VLAN;
 
 	switch (nfc->flow_type) {
 	case TCP_V4_FLOW:
@@ -477,6 +479,11 @@ static int otx2_set_rss_hash_opts(struct otx2_nic *pfvf,
 	if (!(nfc->data & RXH_IP_SRC) || !(nfc->data & RXH_IP_DST))
 		return -EINVAL;
 
+	if (nfc->data & RXH_VLAN)
+		rss_cfg |=  NIX_FLOW_KEY_TYPE_VLAN;
+	else
+		rss_cfg &= ~NIX_FLOW_KEY_TYPE_VLAN;
+
 	switch (nfc->flow_type) {
 	case TCP_V4_FLOW:
 	case TCP_V6_FLOW:
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
index aac2845c1fb1..265e4d1b4e64 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
@@ -22,6 +22,7 @@
 #include "otx2_txrx.h"
 #include "otx2_struct.h"
 #include "otx2_ptp.h"
+#include <rvu_trace.h>
 
 #define DRV_NAME	"octeontx2-nicpf"
 #define DRV_STRING	"Marvell OcteonTX2 NIC Physical Function Driver"
@@ -558,6 +559,8 @@ static irqreturn_t otx2_pfvf_mbox_intr_handler(int irq, void *pf_irq)
 
 	otx2_queue_work(mbox, pf->mbox_pfvf_wq, 0, vfs, intr, TYPE_PFVF);
 
+	trace_otx2_msg_interrupt(mbox->mbox.pdev, "VF(s) to PF", intr);
+
 	return IRQ_HANDLED;
 }
 
@@ -940,6 +943,9 @@ static irqreturn_t otx2_pfaf_mbox_intr_handler(int irq, void *pf_irq)
 	otx2_write64(pf, RVU_PF_INT, BIT_ULL(0));
 
 	mbox = &pf->mbox;
+
+	trace_otx2_msg_interrupt(mbox->mbox.pdev, "AF to PF", BIT_ULL(0));
+
 	otx2_queue_work(mbox, pf->mbox_wq, 0, 1, 1, TYPE_PFAF);
 
 	return IRQ_HANDLED;
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c
index 70e0d4ca6688..32daa3e0f296 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c
@@ -187,6 +187,8 @@ static irqreturn_t otx2vf_vfaf_mbox_intr_handler(int irq, void *vf_irq)
 	mdev = &mbox->dev[0];
 	otx2_sync_mbox_bbuf(mbox, 0);
 
+	trace_otx2_msg_interrupt(mbox->pdev, "PF to VF", BIT_ULL(0));
+
 	hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start);
 	if (hdr->num_msgs) {
 		vf->mbox.num_msgs = hdr->num_msgs;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index d55434449c0c..45869b29368f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -842,6 +842,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct mlx4_en_tx_desc *tx_desc;
 	struct mlx4_wqe_data_seg *data;
 	struct mlx4_en_tx_info *tx_info;
+	u32 __maybe_unused ring_cons;
 	int tx_ind;
 	int nr_txbb;
 	int desc_size;
@@ -855,7 +856,6 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 	bool stop_queue;
 	bool inline_ok;
 	u8 data_offset;
-	u32 ring_cons;
 	bool bf_ok;
 
 	tx_ind = skb_get_queue_mapping(skb);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 0b3eaa102751..b24aeee1db8c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -37,7 +37,7 @@ mlx5_core-$(CONFIG_PCI_HYPERV_INTERFACE) += en/hv_vhca_stats.o
 mlx5_core-$(CONFIG_MLX5_ESWITCH)     += lag_mp.o lib/geneve.o lib/port_tun.o \
 					en_rep.o en/rep/bond.o en/mod_hdr.o
 mlx5_core-$(CONFIG_MLX5_CLS_ACT)     += en_tc.o en/rep/tc.o en/rep/neigh.o \
-					en/mapping.o esw/chains.o en/tc_tun.o \
+					en/mapping.o lib/fs_chains.o en/tc_tun.o \
 					en/tc_tun_vxlan.o en/tc_tun_gre.o en/tc_tun_geneve.o \
 					en/tc_tun_mplsoudp.o diag/en_tc_tracepoint.o
 mlx5_core-$(CONFIG_MLX5_TC_CT)	     += en/tc_ct.o
@@ -49,7 +49,8 @@ mlx5_core-$(CONFIG_MLX5_ESWITCH)   += eswitch.o eswitch_offloads.o eswitch_offlo
 				      ecpf.o rdma.o
 mlx5_core-$(CONFIG_MLX5_ESWITCH)   += esw/acl/helper.o \
 				      esw/acl/egress_lgcy.o esw/acl/egress_ofld.o \
-				      esw/acl/ingress_lgcy.o esw/acl/ingress_ofld.o
+				      esw/acl/ingress_lgcy.o esw/acl/ingress_ofld.o \
+				      esw/devlink_port.o
 
 mlx5_core-$(CONFIG_MLX5_MPFS)      += lib/mpfs.o
 mlx5_core-$(CONFIG_VXLAN)          += lib/vxlan.o
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/alloc.c b/drivers/net/ethernet/mellanox/mlx5/core/alloc.c
index 8db4b5f0f963..291e427e9e4f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/alloc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/alloc.c
@@ -56,8 +56,8 @@ static void *mlx5_dma_zalloc_coherent_node(struct mlx5_core_dev *dev,
 					   size_t size, dma_addr_t *dma_handle,
 					   int node)
 {
+	struct device *device = mlx5_core_dma_dev(dev);
 	struct mlx5_priv *priv = &dev->priv;
-	struct device *device = dev->device;
 	int original_node;
 	void *cpu_handle;
 
@@ -111,7 +111,7 @@ EXPORT_SYMBOL(mlx5_buf_alloc);
 
 void mlx5_buf_free(struct mlx5_core_dev *dev, struct mlx5_frag_buf *buf)
 {
-	dma_free_coherent(dev->device, buf->size, buf->frags->buf,
+	dma_free_coherent(mlx5_core_dma_dev(dev), buf->size, buf->frags->buf,
 			  buf->frags->map);
 
 	kfree(buf->frags);
@@ -140,7 +140,7 @@ int mlx5_frag_buf_alloc_node(struct mlx5_core_dev *dev, int size,
 		if (!frag->buf)
 			goto err_free_buf;
 		if (frag->map & ((1 << buf->page_shift) - 1)) {
-			dma_free_coherent(dev->device, frag_sz,
+			dma_free_coherent(mlx5_core_dma_dev(dev), frag_sz,
 					  buf->frags[i].buf, buf->frags[i].map);
 			mlx5_core_warn(dev, "unexpected map alignment: %pad, page_shift=%d\n",
 				       &frag->map, buf->page_shift);
@@ -153,7 +153,7 @@ int mlx5_frag_buf_alloc_node(struct mlx5_core_dev *dev, int size,
 
 err_free_buf:
 	while (i--)
-		dma_free_coherent(dev->device, PAGE_SIZE, buf->frags[i].buf,
+		dma_free_coherent(mlx5_core_dma_dev(dev), PAGE_SIZE, buf->frags[i].buf,
 				  buf->frags[i].map);
 	kfree(buf->frags);
 err_out:
@@ -169,7 +169,7 @@ void mlx5_frag_buf_free(struct mlx5_core_dev *dev, struct mlx5_frag_buf *buf)
 	for (i = 0; i < buf->npages; i++) {
 		int frag_sz = min_t(int, size, PAGE_SIZE);
 
-		dma_free_coherent(dev->device, frag_sz, buf->frags[i].buf,
+		dma_free_coherent(mlx5_core_dma_dev(dev), frag_sz, buf->frags[i].buf,
 				  buf->frags[i].map);
 		size -= frag_sz;
 	}
@@ -275,7 +275,7 @@ void mlx5_db_free(struct mlx5_core_dev *dev, struct mlx5_db *db)
 	__set_bit(db->index, db->u.pgdir->bitmap);
 
 	if (bitmap_full(db->u.pgdir->bitmap, db_per_page)) {
-		dma_free_coherent(dev->device, PAGE_SIZE,
+		dma_free_coherent(mlx5_core_dma_dev(dev), PAGE_SIZE,
 				  db->u.pgdir->db_page, db->u.pgdir->db_dma);
 		list_del(&db->u.pgdir->list);
 		bitmap_free(db->u.pgdir->bitmap);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 1d91a0d0ab1d..1ccae653319f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -1899,9 +1899,7 @@ static void create_msg_cache(struct mlx5_core_dev *dev)
 
 static int alloc_cmd_page(struct mlx5_core_dev *dev, struct mlx5_cmd *cmd)
 {
-	struct device *ddev = dev->device;
-
-	cmd->cmd_alloc_buf = dma_alloc_coherent(ddev, MLX5_ADAPTER_PAGE_SIZE,
+	cmd->cmd_alloc_buf = dma_alloc_coherent(mlx5_core_dma_dev(dev), MLX5_ADAPTER_PAGE_SIZE,
 						&cmd->alloc_dma, GFP_KERNEL);
 	if (!cmd->cmd_alloc_buf)
 		return -ENOMEM;
@@ -1914,9 +1912,9 @@ static int alloc_cmd_page(struct mlx5_core_dev *dev, struct mlx5_cmd *cmd)
 		return 0;
 	}
 
-	dma_free_coherent(ddev, MLX5_ADAPTER_PAGE_SIZE, cmd->cmd_alloc_buf,
+	dma_free_coherent(mlx5_core_dma_dev(dev), MLX5_ADAPTER_PAGE_SIZE, cmd->cmd_alloc_buf,
 			  cmd->alloc_dma);
-	cmd->cmd_alloc_buf = dma_alloc_coherent(ddev,
+	cmd->cmd_alloc_buf = dma_alloc_coherent(mlx5_core_dma_dev(dev),
 						2 * MLX5_ADAPTER_PAGE_SIZE - 1,
 						&cmd->alloc_dma, GFP_KERNEL);
 	if (!cmd->cmd_alloc_buf)
@@ -1930,9 +1928,7 @@ static int alloc_cmd_page(struct mlx5_core_dev *dev, struct mlx5_cmd *cmd)
 
 static void free_cmd_page(struct mlx5_core_dev *dev, struct mlx5_cmd *cmd)
 {
-	struct device *ddev = dev->device;
-
-	dma_free_coherent(ddev, cmd->alloc_size, cmd->cmd_alloc_buf,
+	dma_free_coherent(mlx5_core_dma_dev(dev), cmd->alloc_size, cmd->cmd_alloc_buf,
 			  cmd->alloc_dma);
 }
 
@@ -1964,7 +1960,7 @@ int mlx5_cmd_init(struct mlx5_core_dev *dev)
 	if (!cmd->stats)
 		return -ENOMEM;
 
-	cmd->pool = dma_pool_create("mlx5_cmd", dev->device, size, align, 0);
+	cmd->pool = dma_pool_create("mlx5_cmd", mlx5_core_dma_dev(dev), size, align, 0);
 	if (!cmd->pool) {
 		err = -ENOMEM;
 		goto dma_pool_err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
index c709e9a385f6..9b14e3f805a2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -8,18 +8,14 @@
 #include "eswitch.h"
 
 static int mlx5_devlink_flash_update(struct devlink *devlink,
-				     const char *file_name,
-				     const char *component,
+				     struct devlink_flash_update_params *params,
 				     struct netlink_ext_ack *extack)
 {
 	struct mlx5_core_dev *dev = devlink_priv(devlink);
 	const struct firmware *fw;
 	int err;
 
-	if (component)
-		return -EOPNOTSUPP;
-
-	err = request_firmware_direct(&fw, file_name, &dev->pdev->dev);
+	err = request_firmware_direct(&fw, params->file_name, &dev->pdev->dev);
 	if (err)
 		return err;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
index ad3594c4afcb..ede4640b8428 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
@@ -124,7 +124,7 @@ static void mlx5_fw_tracer_ownership_release(struct mlx5_fw_tracer *tracer)
 static int mlx5_fw_tracer_create_log_buf(struct mlx5_fw_tracer *tracer)
 {
 	struct mlx5_core_dev *dev = tracer->dev;
-	struct device *ddev = &dev->pdev->dev;
+	struct device *ddev;
 	dma_addr_t dma;
 	void *buff;
 	gfp_t gfp;
@@ -142,6 +142,7 @@ static int mlx5_fw_tracer_create_log_buf(struct mlx5_fw_tracer *tracer)
 	}
 	tracer->buff.log_buf = buff;
 
+	ddev = mlx5_core_dma_dev(dev);
 	dma = dma_map_single(ddev, buff, tracer->buff.size, DMA_FROM_DEVICE);
 	if (dma_mapping_error(ddev, dma)) {
 		mlx5_core_warn(dev, "FWTracer: Unable to map DMA: %d\n",
@@ -162,11 +163,12 @@ free_pages:
 static void mlx5_fw_tracer_destroy_log_buf(struct mlx5_fw_tracer *tracer)
 {
 	struct mlx5_core_dev *dev = tracer->dev;
-	struct device *ddev = &dev->pdev->dev;
+	struct device *ddev;
 
 	if (!tracer->buff.log_buf)
 		return;
 
+	ddev = mlx5_core_dma_dev(dev);
 	dma_unmap_single(ddev, tracer->buff.dma, tracer->buff.size, DMA_FROM_DEVICE);
 	free_pages((unsigned long)tracer->buff.log_buf, get_order(tracer->buff.size));
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/rsc_dump.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/rsc_dump.c
index 4924a5658853..ed4fb79b4db7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/rsc_dump.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/rsc_dump.c
@@ -78,7 +78,7 @@ static int mlx5_rsc_dump_trigger(struct mlx5_core_dev *dev, struct mlx5_rsc_dump
 				 struct page *page)
 {
 	struct mlx5_rsc_dump *rsc_dump = dev->rsc_dump;
-	struct device *ddev = &dev->pdev->dev;
+	struct device *ddev = mlx5_core_dma_dev(dev);
 	u32 out_seq_num;
 	u32 in_seq_num;
 	dma_addr_t dma;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c
index a894ea98c95a..3dc9dd3f24dc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c
@@ -43,19 +43,13 @@ static void mlx5_peer_pf_cleanup(struct mlx5_core_dev *dev)
 
 int mlx5_ec_init(struct mlx5_core_dev *dev)
 {
-	int err = 0;
-
 	if (!mlx5_core_is_ecpf(dev))
 		return 0;
 
 	/* ECPF shall enable HCA for peer PF in the same way a PF
 	 * does this for its VFs.
 	 */
-	err = mlx5_peer_pf_init(dev);
-	if (err)
-		return err;
-
-	return 0;
+	return mlx5_peer_pf_init(dev);
 }
 
 void mlx5_ec_cleanup(struct mlx5_core_dev *dev)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 95aab8b429cf..5368e06cd71c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -221,6 +221,7 @@ enum mlx5e_priv_flag {
 	MLX5E_PFLAG_RX_STRIDING_RQ,
 	MLX5E_PFLAG_RX_NO_CSUM_COMPLETE,
 	MLX5E_PFLAG_XDP_TX_MPWQE,
+	MLX5E_PFLAG_SKB_TX_MPWQE,
 	MLX5E_NUM_PFLAGS, /* Keep last */
 };
 
@@ -305,6 +306,7 @@ struct mlx5e_sq_dma {
 
 enum {
 	MLX5E_SQ_STATE_ENABLED,
+	MLX5E_SQ_STATE_MPWQE,
 	MLX5E_SQ_STATE_RECOVERING,
 	MLX5E_SQ_STATE_IPSEC,
 	MLX5E_SQ_STATE_AM,
@@ -313,26 +315,40 @@ enum {
 	MLX5E_SQ_STATE_PENDING_XSK_TX,
 };
 
+struct mlx5e_tx_mpwqe {
+	/* Current MPWQE session */
+	struct mlx5e_tx_wqe *wqe;
+	u32 bytes_count;
+	u8 ds_count;
+	u8 pkt_count;
+	u8 inline_on;
+};
+
 struct mlx5e_txqsq {
 	/* data path */
 
 	/* dirtied @completion */
 	u16                        cc;
+	u16                        skb_fifo_cc;
 	u32                        dma_fifo_cc;
 	struct dim                 dim; /* Adaptive Moderation */
 
 	/* dirtied @xmit */
 	u16                        pc ____cacheline_aligned_in_smp;
+	u16                        skb_fifo_pc;
 	u32                        dma_fifo_pc;
+	struct mlx5e_tx_mpwqe      mpwqe;
 
 	struct mlx5e_cq            cq;
 
 	/* read only */
 	struct mlx5_wq_cyc         wq;
 	u32                        dma_fifo_mask;
+	u16                        skb_fifo_mask;
 	struct mlx5e_sq_stats     *stats;
 	struct {
 		struct mlx5e_sq_dma       *dma_fifo;
+		struct sk_buff           **skb_fifo;
 		struct mlx5e_tx_wqe_info  *wqe_info;
 	} db;
 	void __iomem              *uar_map;
@@ -399,7 +415,7 @@ struct mlx5e_xdp_info {
 	};
 };
 
-struct mlx5e_xdp_xmit_data {
+struct mlx5e_xmit_data {
 	dma_addr_t  dma_addr;
 	void       *data;
 	u32         len;
@@ -412,18 +428,10 @@ struct mlx5e_xdp_info_fifo {
 	u32 mask;
 };
 
-struct mlx5e_xdp_mpwqe {
-	/* Current MPWQE session */
-	struct mlx5e_tx_wqe *wqe;
-	u8                   ds_count;
-	u8                   pkt_count;
-	u8                   inline_on;
-};
-
 struct mlx5e_xdpsq;
 typedef int (*mlx5e_fp_xmit_xdp_frame_check)(struct mlx5e_xdpsq *);
 typedef bool (*mlx5e_fp_xmit_xdp_frame)(struct mlx5e_xdpsq *,
-					struct mlx5e_xdp_xmit_data *,
+					struct mlx5e_xmit_data *,
 					struct mlx5e_xdp_info *,
 					int);
 
@@ -438,7 +446,7 @@ struct mlx5e_xdpsq {
 	u32                        xdpi_fifo_pc ____cacheline_aligned_in_smp;
 	u16                        pc;
 	struct mlx5_wqe_ctrl_seg   *doorbell_cseg;
-	struct mlx5e_xdp_mpwqe     mpwqe;
+	struct mlx5e_tx_mpwqe      mpwqe;
 
 	struct mlx5e_cq            cq;
 
@@ -601,7 +609,7 @@ struct mlx5e_rq {
 	struct dim         dim; /* Dynamic Interrupt Moderation */
 
 	/* XDP */
-	struct bpf_prog       *xdp_prog;
+	struct bpf_prog __rcu *xdp_prog;
 	struct mlx5e_xdpsq    *xdpsq;
 	DECLARE_BITMAP(flags, 8);
 	struct page_pool      *page_pool;
@@ -1007,7 +1015,6 @@ int mlx5e_update_nic_rx(struct mlx5e_priv *priv);
 void mlx5e_update_carrier(struct mlx5e_priv *priv);
 int mlx5e_close(struct net_device *netdev);
 int mlx5e_open(struct net_device *netdev);
-void mlx5e_update_ndo_stats(struct mlx5e_priv *priv);
 
 void mlx5e_queue_update_stats(struct mlx5e_priv *priv);
 int mlx5e_bits_invert(unsigned long a, int size);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
index 6fdcd5e69476..6a97452dc60e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
@@ -12,9 +12,12 @@ enum {
 };
 
 struct mlx5e_tc_table {
-	/* protects flow table */
+	/* Protects the dynamic assignment of the t parameter
+	 * which is the nic tc root table.
+	 */
 	struct mutex			t_lock;
 	struct mlx5_flow_table		*t;
+	struct mlx5_fs_chains           *chains;
 
 	struct rhashtable               ht;
 
@@ -24,6 +27,8 @@ struct mlx5e_tc_table {
 
 	struct notifier_block     netdevice_nb;
 	struct netdev_net_notifier	netdevice_nn;
+
+	struct mlx5_tc_ct_priv         *ct;
 };
 
 struct mlx5e_flow_table {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c
index 8fe8b4d6ad1c..254c84739046 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c
@@ -51,7 +51,7 @@ static void mlx5e_monitor_counters_work(struct work_struct *work)
 					       monitor_counters_work);
 
 	mutex_lock(&priv->state_lock);
-	mlx5e_update_ndo_stats(priv);
+	mlx5e_stats_update_ndo_stats(priv);
 	mutex_unlock(&priv->state_lock);
 	mlx5e_monitor_counter_arm(priv);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
index 5de1cb9f5330..96608dbb9314 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
@@ -490,11 +490,8 @@ bool mlx5e_fec_in_caps(struct mlx5_core_dev *dev, int fec_policy)
 	int err;
 	int i;
 
-	if (!MLX5_CAP_GEN(dev, pcam_reg))
-		return -EOPNOTSUPP;
-
-	if (!MLX5_CAP_PCAM_REG(dev, pplm))
-		return -EOPNOTSUPP;
+	if (!MLX5_CAP_GEN(dev, pcam_reg) || !MLX5_CAP_PCAM_REG(dev, pplm))
+		return false;
 
 	MLX5_SET(pplm_reg, in, local_port, 1);
 	err =  mlx5_core_access_reg(dev, in, sz, out, sz, MLX5_REG_PPLM, 0, 0);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
index 79cc42d88eec..e36e505d38ad 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
@@ -12,7 +12,7 @@
 #include "neigh.h"
 #include "en_rep.h"
 #include "eswitch.h"
-#include "esw/chains.h"
+#include "lib/fs_chains.h"
 #include "en/tc_ct.h"
 #include "en/mapping.h"
 #include "en/tc_tun.h"
@@ -191,7 +191,7 @@ static int mlx5e_rep_setup_ft_cb(enum tc_setup_type type, void *type_data,
 	case TC_SETUP_CLSFLOWER:
 		memcpy(&tmp, f, sizeof(*f));
 
-		if (!mlx5_esw_chains_prios_supported(esw))
+		if (!mlx5_chains_prios_supported(esw_chains(esw)))
 			return -EOPNOTSUPP;
 
 		/* Re-use tc offload path by moving the ft flow to the
@@ -203,12 +203,12 @@ static int mlx5e_rep_setup_ft_cb(enum tc_setup_type type, void *type_data,
 		 *
 		 * We only support chain 0 of FT offload.
 		 */
-		if (tmp.common.prio >= mlx5_esw_chains_get_prio_range(esw))
+		if (tmp.common.prio >= mlx5_chains_get_prio_range(esw_chains(esw)))
 			return -EOPNOTSUPP;
 		if (tmp.common.chain_index != 0)
 			return -EOPNOTSUPP;
 
-		tmp.common.chain_index = mlx5_esw_chains_get_ft_chain(esw);
+		tmp.common.chain_index = mlx5_chains_get_nf_ft_chain(esw_chains(esw));
 		tmp.common.prio++;
 		err = mlx5e_rep_setup_tc_cls_flower(priv, &tmp, flags);
 		memcpy(&f->stats, &tmp.stats, sizeof(f->stats));
@@ -378,12 +378,12 @@ static int mlx5e_rep_indr_setup_ft_cb(enum tc_setup_type type,
 		 *
 		 * We only support chain 0 of FT offload.
 		 */
-		if (!mlx5_esw_chains_prios_supported(esw) ||
-		    tmp.common.prio >= mlx5_esw_chains_get_prio_range(esw) ||
+		if (!mlx5_chains_prios_supported(esw_chains(esw)) ||
+		    tmp.common.prio >= mlx5_chains_get_prio_range(esw_chains(esw)) ||
 		    tmp.common.chain_index)
 			return -EOPNOTSUPP;
 
-		tmp.common.chain_index = mlx5_esw_chains_get_ft_chain(esw);
+		tmp.common.chain_index = mlx5_chains_get_nf_ft_chain(esw_chains(esw));
 		tmp.common.prio++;
 		err = mlx5e_rep_indr_offload(priv->netdev, &tmp, priv, flags);
 		memcpy(&f->stats, &tmp.stats, sizeof(f->stats));
@@ -612,7 +612,6 @@ bool mlx5e_rep_tc_update_skb(struct mlx5_cqe64 *cqe,
 	struct tc_skb_ext *tc_skb_ext;
 	struct mlx5_eswitch *esw;
 	struct mlx5e_priv *priv;
-	int tunnel_moffset;
 	int err;
 
 	reg_c0 = (be32_to_cpu(cqe->sop_drop_qpn) & MLX5E_TC_FLOW_ID_MASK);
@@ -626,7 +625,7 @@ bool mlx5e_rep_tc_update_skb(struct mlx5_cqe64 *cqe,
 	priv = netdev_priv(skb->dev);
 	esw = priv->mdev->priv.eswitch;
 
-	err = mlx5_eswitch_get_chain_for_tag(esw, reg_c0, &chain);
+	err = mlx5_get_chain_for_tag(esw_chains(esw), reg_c0, &chain);
 	if (err) {
 		netdev_dbg(priv->netdev,
 			   "Couldn't find chain for chain tag: %d, err: %d\n",
@@ -647,13 +646,12 @@ bool mlx5e_rep_tc_update_skb(struct mlx5_cqe64 *cqe,
 
 		uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH);
 		uplink_priv = &uplink_rpriv->uplink_priv;
-		if (!mlx5e_tc_ct_restore_flow(uplink_priv, skb,
+		if (!mlx5e_tc_ct_restore_flow(uplink_priv->ct_priv, skb,
 					      zone_restore_id))
 			return false;
 	}
 
-	tunnel_moffset = mlx5e_tc_attr_to_reg_mappings[TUNNEL_TO_REG].moffset;
-	tunnel_id = reg_c1 >> (8 * tunnel_moffset);
+	tunnel_id = reg_c1 >> REG_MAPPING_SHIFT(TUNNEL_TO_REG);
 	return mlx5e_restore_tunnel(priv, skb, tc_priv, tunnel_id);
 #endif /* CONFIG_NET_TC_SKB_EXT */
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
index c6bc9224c3b1..cea2070af9af 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
@@ -14,7 +14,7 @@
 #include <linux/workqueue.h>
 #include <linux/xarray.h>
 
-#include "esw/chains.h"
+#include "lib/fs_chains.h"
 #include "en/tc_ct.h"
 #include "en/mod_hdr.h"
 #include "en/mapping.h"
@@ -39,8 +39,9 @@
 	netdev_dbg(ct_priv->netdev, "ct_debug: " fmt "\n", ##args)
 
 struct mlx5_tc_ct_priv {
-	struct mlx5_eswitch *esw;
+	struct mlx5_core_dev *dev;
 	const struct net_device *netdev;
+	struct mod_hdr_tbl *mod_hdr_tbl;
 	struct idr fte_ids;
 	struct xarray tuple_ids;
 	struct rhashtable zone_ht;
@@ -50,13 +51,16 @@ struct mlx5_tc_ct_priv {
 	struct mlx5_flow_table *ct_nat;
 	struct mlx5_flow_table *post_ct;
 	struct mutex control_lock; /* guards parallel adds/dels */
+	struct mutex shared_counter_lock;
 	struct mapping_ctx *zone_mapping;
 	struct mapping_ctx *labels_mapping;
+	enum mlx5_flow_namespace_type ns_type;
+	struct mlx5_fs_chains *chains;
 };
 
 struct mlx5_ct_flow {
-	struct mlx5_esw_flow_attr pre_ct_attr;
-	struct mlx5_esw_flow_attr post_ct_attr;
+	struct mlx5_flow_attr *pre_ct_attr;
+	struct mlx5_flow_attr *post_ct_attr;
 	struct mlx5_flow_handle *pre_ct_rule;
 	struct mlx5_flow_handle *post_ct_rule;
 	struct mlx5_ct_ft *ft;
@@ -67,12 +71,12 @@ struct mlx5_ct_flow {
 struct mlx5_ct_zone_rule {
 	struct mlx5_flow_handle *rule;
 	struct mlx5e_mod_hdr_handle *mh;
-	struct mlx5_esw_flow_attr attr;
+	struct mlx5_flow_attr *attr;
 	bool nat;
 };
 
 struct mlx5_tc_ct_pre {
-	struct mlx5_flow_table *fdb;
+	struct mlx5_flow_table *ft;
 	struct mlx5_flow_group *flow_grp;
 	struct mlx5_flow_group *miss_grp;
 	struct mlx5_flow_handle *flow_rule;
@@ -114,11 +118,16 @@ struct mlx5_ct_tuple {
 	u16 zone;
 };
 
+struct mlx5_ct_shared_counter {
+	struct mlx5_fc *counter;
+	refcount_t refcount;
+};
+
 struct mlx5_ct_entry {
 	struct rhash_head node;
 	struct rhash_head tuple_node;
 	struct rhash_head tuple_nat_node;
-	struct mlx5_fc *counter;
+	struct mlx5_ct_shared_counter *shared_counter;
 	unsigned long cookie;
 	unsigned long restore_cookie;
 	struct mlx5_ct_tuple tuple;
@@ -157,18 +166,6 @@ static const struct rhashtable_params tuples_nat_ht_params = {
 	.min_size = 16 * 1024,
 };
 
-static struct mlx5_tc_ct_priv *
-mlx5_tc_ct_get_ct_priv(struct mlx5e_priv *priv)
-{
-	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
-	struct mlx5_rep_uplink_priv *uplink_priv;
-	struct mlx5e_rep_priv *uplink_rpriv;
-
-	uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH);
-	uplink_priv = &uplink_rpriv->uplink_priv;
-	return uplink_priv->ct_priv;
-}
-
 static int
 mlx5_tc_ct_rule_to_tuple(struct mlx5_ct_tuple *tuple, struct flow_rule *rule)
 {
@@ -395,20 +392,30 @@ mlx5_tc_ct_set_tuple_match(struct mlx5e_priv *priv, struct mlx5_flow_spec *spec,
 }
 
 static void
+mlx5_tc_ct_shared_counter_put(struct mlx5_tc_ct_priv *ct_priv, struct mlx5_ct_entry *entry)
+{
+	if (!refcount_dec_and_test(&entry->shared_counter->refcount))
+		return;
+
+	mlx5_fc_destroy(ct_priv->dev, entry->shared_counter->counter);
+	kfree(entry->shared_counter);
+}
+
+static void
 mlx5_tc_ct_entry_del_rule(struct mlx5_tc_ct_priv *ct_priv,
 			  struct mlx5_ct_entry *entry,
 			  bool nat)
 {
 	struct mlx5_ct_zone_rule *zone_rule = &entry->zone_rules[nat];
-	struct mlx5_esw_flow_attr *attr = &zone_rule->attr;
-	struct mlx5_eswitch *esw = ct_priv->esw;
+	struct mlx5_flow_attr *attr = zone_rule->attr;
 
 	ct_dbg("Deleting ct entry rule in zone %d", entry->tuple.zone);
 
-	mlx5_eswitch_del_offloaded_rule(esw, zone_rule->rule, attr);
-	mlx5e_mod_hdr_detach(ct_priv->esw->dev,
-			     &esw->offloads.mod_hdr, zone_rule->mh);
+	mlx5_tc_rule_delete(netdev_priv(ct_priv->netdev), zone_rule->rule, attr);
+	mlx5e_mod_hdr_detach(ct_priv->dev,
+			     ct_priv->mod_hdr_tbl, zone_rule->mh);
 	mapping_remove(ct_priv->labels_mapping, attr->ct_attr.ct_labels_id);
+	kfree(attr);
 }
 
 static void
@@ -417,8 +424,6 @@ mlx5_tc_ct_entry_del_rules(struct mlx5_tc_ct_priv *ct_priv,
 {
 	mlx5_tc_ct_entry_del_rule(ct_priv, entry, true);
 	mlx5_tc_ct_entry_del_rule(ct_priv, entry, false);
-
-	mlx5_fc_destroy(ct_priv->esw->dev, entry->counter);
 }
 
 static struct flow_action_entry *
@@ -444,29 +449,40 @@ mlx5_tc_ct_entry_set_registers(struct mlx5_tc_ct_priv *ct_priv,
 			       u32 labels_id,
 			       u8 zone_restore_id)
 {
-	struct mlx5_eswitch *esw = ct_priv->esw;
+	enum mlx5_flow_namespace_type ns = ct_priv->ns_type;
+	struct mlx5_core_dev *dev = ct_priv->dev;
 	int err;
 
-	err = mlx5e_tc_match_to_reg_set(esw->dev, mod_acts,
+	err = mlx5e_tc_match_to_reg_set(dev, mod_acts, ns,
 					CTSTATE_TO_REG, ct_state);
 	if (err)
 		return err;
 
-	err = mlx5e_tc_match_to_reg_set(esw->dev, mod_acts,
+	err = mlx5e_tc_match_to_reg_set(dev, mod_acts, ns,
 					MARK_TO_REG, mark);
 	if (err)
 		return err;
 
-	err = mlx5e_tc_match_to_reg_set(esw->dev, mod_acts,
+	err = mlx5e_tc_match_to_reg_set(dev, mod_acts, ns,
 					LABELS_TO_REG, labels_id);
 	if (err)
 		return err;
 
-	err = mlx5e_tc_match_to_reg_set(esw->dev, mod_acts,
+	err = mlx5e_tc_match_to_reg_set(dev, mod_acts, ns,
 					ZONE_RESTORE_TO_REG, zone_restore_id);
 	if (err)
 		return err;
 
+	/* Make another copy of zone id in reg_b for
+	 * NIC rx flows since we don't copy reg_c1 to
+	 * reg_b upon miss.
+	 */
+	if (ns != MLX5_FLOW_NAMESPACE_FDB) {
+		err = mlx5e_tc_match_to_reg_set(dev, mod_acts, ns,
+						NIC_ZONE_RESTORE_TO_REG, zone_restore_id);
+		if (err)
+			return err;
+	}
 	return 0;
 }
 
@@ -547,7 +563,7 @@ mlx5_tc_ct_entry_create_nat(struct mlx5_tc_ct_priv *ct_priv,
 			    struct mlx5e_tc_mod_hdr_acts *mod_acts)
 {
 	struct flow_action *flow_action = &flow_rule->action;
-	struct mlx5_core_dev *mdev = ct_priv->esw->dev;
+	struct mlx5_core_dev *mdev = ct_priv->dev;
 	struct flow_action_entry *act;
 	size_t action_size;
 	char *modact;
@@ -558,8 +574,7 @@ mlx5_tc_ct_entry_create_nat(struct mlx5_tc_ct_priv *ct_priv,
 	flow_action_for_each(i, act, flow_action) {
 		switch (act->id) {
 		case FLOW_ACTION_MANGLE: {
-			err = alloc_mod_hdr_actions(mdev,
-						    MLX5_FLOW_NAMESPACE_FDB,
+			err = alloc_mod_hdr_actions(mdev, ct_priv->ns_type,
 						    mod_acts);
 			if (err)
 				return err;
@@ -588,7 +603,7 @@ mlx5_tc_ct_entry_create_nat(struct mlx5_tc_ct_priv *ct_priv,
 
 static int
 mlx5_tc_ct_entry_create_mod_hdr(struct mlx5_tc_ct_priv *ct_priv,
-				struct mlx5_esw_flow_attr *attr,
+				struct mlx5_flow_attr *attr,
 				struct flow_rule *flow_rule,
 				struct mlx5e_mod_hdr_handle **mh,
 				u8 zone_restore_id, bool nat)
@@ -624,9 +639,9 @@ mlx5_tc_ct_entry_create_mod_hdr(struct mlx5_tc_ct_priv *ct_priv,
 	if (err)
 		goto err_mapping;
 
-	*mh = mlx5e_mod_hdr_attach(ct_priv->esw->dev,
-				   &ct_priv->esw->offloads.mod_hdr,
-				   MLX5_FLOW_NAMESPACE_FDB,
+	*mh = mlx5e_mod_hdr_attach(ct_priv->dev,
+				   ct_priv->mod_hdr_tbl,
+				   ct_priv->ns_type,
 				   &mod_acts);
 	if (IS_ERR(*mh)) {
 		err = PTR_ERR(*mh);
@@ -650,9 +665,9 @@ mlx5_tc_ct_entry_add_rule(struct mlx5_tc_ct_priv *ct_priv,
 			  bool nat, u8 zone_restore_id)
 {
 	struct mlx5_ct_zone_rule *zone_rule = &entry->zone_rules[nat];
-	struct mlx5_esw_flow_attr *attr = &zone_rule->attr;
-	struct mlx5_eswitch *esw = ct_priv->esw;
+	struct mlx5e_priv *priv = netdev_priv(ct_priv->netdev);
 	struct mlx5_flow_spec *spec = NULL;
+	struct mlx5_flow_attr *attr;
 	int err;
 
 	zone_rule->nat = nat;
@@ -661,6 +676,12 @@ mlx5_tc_ct_entry_add_rule(struct mlx5_tc_ct_priv *ct_priv,
 	if (!spec)
 		return -ENOMEM;
 
+	attr = mlx5_alloc_flow_attr(ct_priv->ns_type);
+	if (!attr) {
+		err = -ENOMEM;
+		goto err_attr;
+	}
+
 	err = mlx5_tc_ct_entry_create_mod_hdr(ct_priv, attr, flow_rule,
 					      &zone_rule->mh,
 					      zone_restore_id, nat);
@@ -674,9 +695,9 @@ mlx5_tc_ct_entry_add_rule(struct mlx5_tc_ct_priv *ct_priv,
 		       MLX5_FLOW_CONTEXT_ACTION_COUNT;
 	attr->dest_chain = 0;
 	attr->dest_ft = ct_priv->post_ct;
-	attr->fdb = nat ? ct_priv->ct_nat : ct_priv->ct;
+	attr->ft = nat ? ct_priv->ct_nat : ct_priv->ct;
 	attr->outer_match_level = MLX5_MATCH_L4;
-	attr->counter = entry->counter;
+	attr->counter = entry->shared_counter->counter;
 	attr->flags |= MLX5_ESW_ATTR_FLAG_NO_IN_PORT;
 
 	mlx5_tc_ct_set_tuple_match(netdev_priv(ct_priv->netdev), spec, flow_rule);
@@ -684,38 +705,100 @@ mlx5_tc_ct_entry_add_rule(struct mlx5_tc_ct_priv *ct_priv,
 				    entry->tuple.zone & MLX5_CT_ZONE_MASK,
 				    MLX5_CT_ZONE_MASK);
 
-	zone_rule->rule = mlx5_eswitch_add_offloaded_rule(esw, spec, attr);
+	zone_rule->rule = mlx5_tc_rule_insert(priv, spec, attr);
 	if (IS_ERR(zone_rule->rule)) {
 		err = PTR_ERR(zone_rule->rule);
 		ct_dbg("Failed to add ct entry rule, nat: %d", nat);
 		goto err_rule;
 	}
 
+	zone_rule->attr = attr;
+
 	kfree(spec);
 	ct_dbg("Offloaded ct entry rule in zone %d", entry->tuple.zone);
 
 	return 0;
 
 err_rule:
-	mlx5e_mod_hdr_detach(ct_priv->esw->dev,
-			     &esw->offloads.mod_hdr, zone_rule->mh);
+	mlx5e_mod_hdr_detach(ct_priv->dev,
+			     ct_priv->mod_hdr_tbl, zone_rule->mh);
+	mapping_remove(ct_priv->labels_mapping, attr->ct_attr.ct_labels_id);
 err_mod_hdr:
+	kfree(attr);
+err_attr:
 	kfree(spec);
 	return err;
 }
 
+static struct mlx5_ct_shared_counter *
+mlx5_tc_ct_shared_counter_get(struct mlx5_tc_ct_priv *ct_priv,
+			      struct mlx5_ct_entry *entry)
+{
+	struct mlx5_ct_tuple rev_tuple = entry->tuple;
+	struct mlx5_ct_shared_counter *shared_counter;
+	struct mlx5_core_dev *dev = ct_priv->dev;
+	struct mlx5_ct_entry *rev_entry;
+	__be16 tmp_port;
+	int ret;
+
+	/* get the reversed tuple */
+	tmp_port = rev_tuple.port.src;
+	rev_tuple.port.src = rev_tuple.port.dst;
+	rev_tuple.port.dst = tmp_port;
+
+	if (rev_tuple.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
+		__be32 tmp_addr = rev_tuple.ip.src_v4;
+
+		rev_tuple.ip.src_v4 = rev_tuple.ip.dst_v4;
+		rev_tuple.ip.dst_v4 = tmp_addr;
+	} else if (rev_tuple.addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) {
+		struct in6_addr tmp_addr = rev_tuple.ip.src_v6;
+
+		rev_tuple.ip.src_v6 = rev_tuple.ip.dst_v6;
+		rev_tuple.ip.dst_v6 = tmp_addr;
+	} else {
+		return ERR_PTR(-EOPNOTSUPP);
+	}
+
+	/* Use the same counter as the reverse direction */
+	mutex_lock(&ct_priv->shared_counter_lock);
+	rev_entry = rhashtable_lookup_fast(&ct_priv->ct_tuples_ht, &rev_tuple,
+					   tuples_ht_params);
+	if (rev_entry) {
+		if (refcount_inc_not_zero(&rev_entry->shared_counter->refcount)) {
+			mutex_unlock(&ct_priv->shared_counter_lock);
+			return rev_entry->shared_counter;
+		}
+	}
+	mutex_unlock(&ct_priv->shared_counter_lock);
+
+	shared_counter = kzalloc(sizeof(*shared_counter), GFP_KERNEL);
+	if (!shared_counter)
+		return ERR_PTR(-ENOMEM);
+
+	shared_counter->counter = mlx5_fc_create(dev, true);
+	if (IS_ERR(shared_counter->counter)) {
+		ct_dbg("Failed to create counter for ct entry");
+		ret = PTR_ERR(shared_counter->counter);
+		kfree(shared_counter);
+		return ERR_PTR(ret);
+	}
+
+	refcount_set(&shared_counter->refcount, 1);
+	return shared_counter;
+}
+
 static int
 mlx5_tc_ct_entry_add_rules(struct mlx5_tc_ct_priv *ct_priv,
 			   struct flow_rule *flow_rule,
 			   struct mlx5_ct_entry *entry,
 			   u8 zone_restore_id)
 {
-	struct mlx5_eswitch *esw = ct_priv->esw;
 	int err;
 
-	entry->counter = mlx5_fc_create(esw->dev, true);
-	if (IS_ERR(entry->counter)) {
-		err = PTR_ERR(entry->counter);
+	entry->shared_counter = mlx5_tc_ct_shared_counter_get(ct_priv, entry);
+	if (IS_ERR(entry->shared_counter)) {
+		err = PTR_ERR(entry->shared_counter);
 		ct_dbg("Failed to create counter for ct entry");
 		return err;
 	}
@@ -735,7 +818,7 @@ mlx5_tc_ct_entry_add_rules(struct mlx5_tc_ct_priv *ct_priv,
 err_nat:
 	mlx5_tc_ct_entry_del_rule(ct_priv, entry, false);
 err_orig:
-	mlx5_fc_destroy(esw->dev, entry->counter);
+	mlx5_tc_ct_shared_counter_put(ct_priv, entry);
 	return err;
 }
 
@@ -825,12 +908,16 @@ mlx5_tc_ct_del_ft_entry(struct mlx5_tc_ct_priv *ct_priv,
 			struct mlx5_ct_entry *entry)
 {
 	mlx5_tc_ct_entry_del_rules(ct_priv, entry);
+	mutex_lock(&ct_priv->shared_counter_lock);
 	if (entry->tuple_node.next)
 		rhashtable_remove_fast(&ct_priv->ct_tuples_nat_ht,
 				       &entry->tuple_nat_node,
 				       tuples_nat_ht_params);
 	rhashtable_remove_fast(&ct_priv->ct_tuples_ht, &entry->tuple_node,
 			       tuples_ht_params);
+	mutex_unlock(&ct_priv->shared_counter_lock);
+	mlx5_tc_ct_shared_counter_put(ct_priv, entry);
+
 }
 
 static int
@@ -867,7 +954,7 @@ mlx5_tc_ct_block_flow_offload_stats(struct mlx5_ct_ft *ft,
 	if (!entry)
 		return -ENOENT;
 
-	mlx5_fc_query_cached(entry->counter, &bytes, &packets, &lastuse);
+	mlx5_fc_query_cached(entry->shared_counter->counter, &bytes, &packets, &lastuse);
 	flow_stats_update(&f->stats, bytes, packets, 0, lastuse,
 			  FLOW_ACTION_HW_STATS_DELAYED);
 
@@ -940,9 +1027,7 @@ out:
 	return false;
 }
 
-int
-mlx5_tc_ct_add_no_trk_match(struct mlx5e_priv *priv,
-			    struct mlx5_flow_spec *spec)
+int mlx5_tc_ct_add_no_trk_match(struct mlx5_flow_spec *spec)
 {
 	u32 ctstate = 0, ctstate_mask = 0;
 
@@ -958,14 +1043,21 @@ mlx5_tc_ct_add_no_trk_match(struct mlx5e_priv *priv,
 	return 0;
 }
 
+void mlx5_tc_ct_match_del(struct mlx5_tc_ct_priv *priv, struct mlx5_ct_attr *ct_attr)
+{
+	if (!priv || !ct_attr->ct_labels_id)
+		return;
+
+	mapping_remove(priv->labels_mapping, ct_attr->ct_labels_id);
+}
+
 int
-mlx5_tc_ct_parse_match(struct mlx5e_priv *priv,
-		       struct mlx5_flow_spec *spec,
-		       struct flow_cls_offload *f,
-		       struct mlx5_ct_attr *ct_attr,
-		       struct netlink_ext_ack *extack)
+mlx5_tc_ct_match_add(struct mlx5_tc_ct_priv *priv,
+		     struct mlx5_flow_spec *spec,
+		     struct flow_cls_offload *f,
+		     struct mlx5_ct_attr *ct_attr,
+		     struct netlink_ext_ack *extack)
 {
-	struct mlx5_tc_ct_priv *ct_priv = mlx5_tc_ct_get_ct_priv(priv);
 	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
 	struct flow_dissector_key_ct *mask, *key;
 	bool trk, est, untrk, unest, new;
@@ -978,7 +1070,7 @@ mlx5_tc_ct_parse_match(struct mlx5e_priv *priv,
 	if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CT))
 		return 0;
 
-	if (!ct_priv) {
+	if (!priv) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "offload of ct matching isn't available");
 		return -EOPNOTSUPP;
@@ -1034,7 +1126,7 @@ mlx5_tc_ct_parse_match(struct mlx5e_priv *priv,
 		ct_labels[1] = key->ct_labels[1] & mask->ct_labels[1];
 		ct_labels[2] = key->ct_labels[2] & mask->ct_labels[2];
 		ct_labels[3] = key->ct_labels[3] & mask->ct_labels[3];
-		if (mapping_add(ct_priv->labels_mapping, ct_labels, &ct_attr->ct_labels_id))
+		if (mapping_add(priv->labels_mapping, ct_labels, &ct_attr->ct_labels_id))
 			return -EOPNOTSUPP;
 		mlx5e_tc_match_to_reg_match(spec, LABELS_TO_REG, ct_attr->ct_labels_id,
 					    MLX5_CT_LABELS_MASK);
@@ -1044,14 +1136,12 @@ mlx5_tc_ct_parse_match(struct mlx5e_priv *priv,
 }
 
 int
-mlx5_tc_ct_parse_action(struct mlx5e_priv *priv,
-			struct mlx5_esw_flow_attr *attr,
+mlx5_tc_ct_parse_action(struct mlx5_tc_ct_priv *priv,
+			struct mlx5_flow_attr *attr,
 			const struct flow_action_entry *act,
 			struct netlink_ext_ack *extack)
 {
-	struct mlx5_tc_ct_priv *ct_priv = mlx5_tc_ct_get_ct_priv(priv);
-
-	if (!ct_priv) {
+	if (!priv) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "offload of ct action isn't available");
 		return -EOPNOTSUPP;
@@ -1070,8 +1160,8 @@ static int tc_ct_pre_ct_add_rules(struct mlx5_ct_ft *ct_ft,
 {
 	struct mlx5_tc_ct_priv *ct_priv = ct_ft->ct_priv;
 	struct mlx5e_tc_mod_hdr_acts pre_mod_acts = {};
-	struct mlx5_core_dev *dev = ct_priv->esw->dev;
-	struct mlx5_flow_table *fdb = pre_ct->fdb;
+	struct mlx5_core_dev *dev = ct_priv->dev;
+	struct mlx5_flow_table *ft = pre_ct->ft;
 	struct mlx5_flow_destination dest = {};
 	struct mlx5_flow_act flow_act = {};
 	struct mlx5_modify_hdr *mod_hdr;
@@ -1086,14 +1176,14 @@ static int tc_ct_pre_ct_add_rules(struct mlx5_ct_ft *ct_ft,
 		return -ENOMEM;
 
 	zone = ct_ft->zone & MLX5_CT_ZONE_MASK;
-	err = mlx5e_tc_match_to_reg_set(dev, &pre_mod_acts, ZONE_TO_REG, zone);
+	err = mlx5e_tc_match_to_reg_set(dev, &pre_mod_acts, ct_priv->ns_type,
+					ZONE_TO_REG, zone);
 	if (err) {
 		ct_dbg("Failed to set zone register mapping");
 		goto err_mapping;
 	}
 
-	mod_hdr = mlx5_modify_header_alloc(dev,
-					   MLX5_FLOW_NAMESPACE_FDB,
+	mod_hdr = mlx5_modify_header_alloc(dev, ct_priv->ns_type,
 					   pre_mod_acts.num_actions,
 					   pre_mod_acts.actions);
 
@@ -1119,7 +1209,7 @@ static int tc_ct_pre_ct_add_rules(struct mlx5_ct_ft *ct_ft,
 	mlx5e_tc_match_to_reg_match(spec, CTSTATE_TO_REG, ctstate, ctstate);
 
 	dest.ft = ct_priv->post_ct;
-	rule = mlx5_add_flow_rules(fdb, spec, &flow_act, &dest, 1);
+	rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1);
 	if (IS_ERR(rule)) {
 		err = PTR_ERR(rule);
 		ct_dbg("Failed to add pre ct flow rule zone %d", zone);
@@ -1130,7 +1220,7 @@ static int tc_ct_pre_ct_add_rules(struct mlx5_ct_ft *ct_ft,
 	/* add miss rule */
 	memset(spec, 0, sizeof(*spec));
 	dest.ft = nat ? ct_priv->ct_nat : ct_priv->ct;
-	rule = mlx5_add_flow_rules(fdb, spec, &flow_act, &dest, 1);
+	rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1);
 	if (IS_ERR(rule)) {
 		err = PTR_ERR(rule);
 		ct_dbg("Failed to add pre ct miss rule zone %d", zone);
@@ -1157,7 +1247,7 @@ tc_ct_pre_ct_del_rules(struct mlx5_ct_ft *ct_ft,
 		       struct mlx5_tc_ct_pre *pre_ct)
 {
 	struct mlx5_tc_ct_priv *ct_priv = ct_ft->ct_priv;
-	struct mlx5_core_dev *dev = ct_priv->esw->dev;
+	struct mlx5_core_dev *dev = ct_priv->dev;
 
 	mlx5_del_flow_rules(pre_ct->flow_rule);
 	mlx5_del_flow_rules(pre_ct->miss_rule);
@@ -1171,7 +1261,7 @@ mlx5_tc_ct_alloc_pre_ct(struct mlx5_ct_ft *ct_ft,
 {
 	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
 	struct mlx5_tc_ct_priv *ct_priv = ct_ft->ct_priv;
-	struct mlx5_core_dev *dev = ct_priv->esw->dev;
+	struct mlx5_core_dev *dev = ct_priv->dev;
 	struct mlx5_flow_table_attr ft_attr = {};
 	struct mlx5_flow_namespace *ns;
 	struct mlx5_flow_table *ft;
@@ -1181,10 +1271,10 @@ mlx5_tc_ct_alloc_pre_ct(struct mlx5_ct_ft *ct_ft,
 	void *misc;
 	int err;
 
-	ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_FDB);
+	ns = mlx5_get_flow_namespace(dev, ct_priv->ns_type);
 	if (!ns) {
 		err = -EOPNOTSUPP;
-		ct_dbg("Failed to get FDB flow namespace");
+		ct_dbg("Failed to get flow namespace");
 		return err;
 	}
 
@@ -1193,7 +1283,8 @@ mlx5_tc_ct_alloc_pre_ct(struct mlx5_ct_ft *ct_ft,
 		return -ENOMEM;
 
 	ft_attr.flags = MLX5_FLOW_TABLE_UNMANAGED;
-	ft_attr.prio = FDB_TC_OFFLOAD;
+	ft_attr.prio =  ct_priv->ns_type ==  MLX5_FLOW_NAMESPACE_FDB ?
+			FDB_TC_OFFLOAD : MLX5E_TC_PRIO;
 	ft_attr.max_fte = 2;
 	ft_attr.level = 1;
 	ft = mlx5_create_flow_table(ns, &ft_attr);
@@ -1202,7 +1293,7 @@ mlx5_tc_ct_alloc_pre_ct(struct mlx5_ct_ft *ct_ft,
 		ct_dbg("Failed to create pre ct table");
 		goto out_free;
 	}
-	pre_ct->fdb = ft;
+	pre_ct->ft = ft;
 
 	/* create flow group */
 	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 0);
@@ -1266,7 +1357,7 @@ mlx5_tc_ct_free_pre_ct(struct mlx5_ct_ft *ct_ft,
 	tc_ct_pre_ct_del_rules(ct_ft, pre_ct);
 	mlx5_destroy_flow_group(pre_ct->miss_grp);
 	mlx5_destroy_flow_group(pre_ct->flow_grp);
-	mlx5_destroy_flow_table(pre_ct->fdb);
+	mlx5_destroy_flow_table(pre_ct->ft);
 }
 
 static int
@@ -1385,7 +1476,7 @@ mlx5_tc_ct_del_ft_cb(struct mlx5_tc_ct_priv *ct_priv, struct mlx5_ct_ft *ft)
 /* We translate the tc filter with CT action to the following HW model:
  *
  * +---------------------+
- * + fdb prio (tc chain) +
+ * + ft prio (tc chain) +
  * + original match      +
  * +---------------------+
  *      | set chain miss mapping
@@ -1415,17 +1506,17 @@ mlx5_tc_ct_del_ft_cb(struct mlx5_tc_ct_priv *ct_priv, struct mlx5_ct_ft *ft)
  * +--------------+
  */
 static struct mlx5_flow_handle *
-__mlx5_tc_ct_flow_offload(struct mlx5e_priv *priv,
+__mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *ct_priv,
 			  struct mlx5e_tc_flow *flow,
 			  struct mlx5_flow_spec *orig_spec,
-			  struct mlx5_esw_flow_attr *attr)
+			  struct mlx5_flow_attr *attr)
 {
-	struct mlx5_tc_ct_priv *ct_priv = mlx5_tc_ct_get_ct_priv(priv);
 	bool nat = attr->ct_attr.ct_action & TCA_CT_ACT_NAT;
+	struct mlx5e_priv *priv = netdev_priv(ct_priv->netdev);
 	struct mlx5e_tc_mod_hdr_acts pre_mod_acts = {};
+	u32 attr_sz = ns_to_attr_sz(ct_priv->ns_type);
 	struct mlx5_flow_spec *post_ct_spec = NULL;
-	struct mlx5_eswitch *esw = ct_priv->esw;
-	struct mlx5_esw_flow_attr *pre_ct_attr;
+	struct mlx5_flow_attr *pre_ct_attr;
 	struct mlx5_modify_hdr *mod_hdr;
 	struct mlx5_flow_handle *rule;
 	struct mlx5_ct_flow *ct_flow;
@@ -1460,10 +1551,22 @@ __mlx5_tc_ct_flow_offload(struct mlx5e_priv *priv,
 	}
 	ct_flow->fte_id = fte_id;
 
-	/* Base esw attributes of both rules on original rule attribute */
-	pre_ct_attr = &ct_flow->pre_ct_attr;
-	memcpy(pre_ct_attr, attr, sizeof(*attr));
-	memcpy(&ct_flow->post_ct_attr, attr, sizeof(*attr));
+	/* Base flow attributes of both rules on original rule attribute */
+	ct_flow->pre_ct_attr = mlx5_alloc_flow_attr(ct_priv->ns_type);
+	if (!ct_flow->pre_ct_attr) {
+		err = -ENOMEM;
+		goto err_alloc_pre;
+	}
+
+	ct_flow->post_ct_attr = mlx5_alloc_flow_attr(ct_priv->ns_type);
+	if (!ct_flow->post_ct_attr) {
+		err = -ENOMEM;
+		goto err_alloc_post;
+	}
+
+	pre_ct_attr = ct_flow->pre_ct_attr;
+	memcpy(pre_ct_attr, attr, attr_sz);
+	memcpy(ct_flow->post_ct_attr, attr, attr_sz);
 
 	/* Modify the original rule's action to fwd and modify, leave decap */
 	pre_ct_attr->action = attr->action & MLX5_FLOW_CONTEXT_ACTION_DECAP;
@@ -1474,22 +1577,22 @@ __mlx5_tc_ct_flow_offload(struct mlx5e_priv *priv,
 	 * don't go though all prios of this chain as normal tc rules
 	 * miss.
 	 */
-	err = mlx5_esw_chains_get_chain_mapping(esw, attr->chain,
-						&chain_mapping);
+	err = mlx5_chains_get_chain_mapping(ct_priv->chains, attr->chain,
+					    &chain_mapping);
 	if (err) {
 		ct_dbg("Failed to get chain register mapping for chain");
 		goto err_get_chain;
 	}
 	ct_flow->chain_mapping = chain_mapping;
 
-	err = mlx5e_tc_match_to_reg_set(esw->dev, &pre_mod_acts,
+	err = mlx5e_tc_match_to_reg_set(priv->mdev, &pre_mod_acts, ct_priv->ns_type,
 					CHAIN_TO_REG, chain_mapping);
 	if (err) {
 		ct_dbg("Failed to set chain register mapping");
 		goto err_mapping;
 	}
 
-	err = mlx5e_tc_match_to_reg_set(esw->dev, &pre_mod_acts,
+	err = mlx5e_tc_match_to_reg_set(priv->mdev, &pre_mod_acts, ct_priv->ns_type,
 					FTEID_TO_REG, fte_id);
 	if (err) {
 		ct_dbg("Failed to set fte_id register mapping");
@@ -1503,7 +1606,8 @@ __mlx5_tc_ct_flow_offload(struct mlx5e_priv *priv,
 	    attr->chain == 0) {
 		u32 tun_id = mlx5e_tc_get_flow_tun_id(flow);
 
-		err = mlx5e_tc_match_to_reg_set(esw->dev, &pre_mod_acts,
+		err = mlx5e_tc_match_to_reg_set(priv->mdev, &pre_mod_acts,
+						ct_priv->ns_type,
 						TUNNEL_TO_REG,
 						tun_id);
 		if (err) {
@@ -1512,8 +1616,7 @@ __mlx5_tc_ct_flow_offload(struct mlx5e_priv *priv,
 		}
 	}
 
-	mod_hdr = mlx5_modify_header_alloc(esw->dev,
-					   MLX5_FLOW_NAMESPACE_FDB,
+	mod_hdr = mlx5_modify_header_alloc(priv->mdev, ct_priv->ns_type,
 					   pre_mod_acts.num_actions,
 					   pre_mod_acts.actions);
 	if (IS_ERR(mod_hdr)) {
@@ -1529,16 +1632,16 @@ __mlx5_tc_ct_flow_offload(struct mlx5e_priv *priv,
 	mlx5e_tc_match_to_reg_match(post_ct_spec, FTEID_TO_REG,
 				    fte_id, MLX5_FTE_ID_MASK);
 
-	/* Put post_ct rule on post_ct fdb */
-	ct_flow->post_ct_attr.chain = 0;
-	ct_flow->post_ct_attr.prio = 0;
-	ct_flow->post_ct_attr.fdb = ct_priv->post_ct;
+	/* Put post_ct rule on post_ct flow table */
+	ct_flow->post_ct_attr->chain = 0;
+	ct_flow->post_ct_attr->prio = 0;
+	ct_flow->post_ct_attr->ft = ct_priv->post_ct;
 
-	ct_flow->post_ct_attr.inner_match_level = MLX5_MATCH_NONE;
-	ct_flow->post_ct_attr.outer_match_level = MLX5_MATCH_NONE;
-	ct_flow->post_ct_attr.action &= ~(MLX5_FLOW_CONTEXT_ACTION_DECAP);
-	rule = mlx5_eswitch_add_offloaded_rule(esw, post_ct_spec,
-					       &ct_flow->post_ct_attr);
+	ct_flow->post_ct_attr->inner_match_level = MLX5_MATCH_NONE;
+	ct_flow->post_ct_attr->outer_match_level = MLX5_MATCH_NONE;
+	ct_flow->post_ct_attr->action &= ~(MLX5_FLOW_CONTEXT_ACTION_DECAP);
+	rule = mlx5_tc_rule_insert(priv, post_ct_spec,
+				   ct_flow->post_ct_attr);
 	ct_flow->post_ct_rule = rule;
 	if (IS_ERR(ct_flow->post_ct_rule)) {
 		err = PTR_ERR(ct_flow->post_ct_rule);
@@ -1548,10 +1651,9 @@ __mlx5_tc_ct_flow_offload(struct mlx5e_priv *priv,
 
 	/* Change original rule point to ct table */
 	pre_ct_attr->dest_chain = 0;
-	pre_ct_attr->dest_ft = nat ? ft->pre_ct_nat.fdb : ft->pre_ct.fdb;
-	ct_flow->pre_ct_rule = mlx5_eswitch_add_offloaded_rule(esw,
-							       orig_spec,
-							       pre_ct_attr);
+	pre_ct_attr->dest_ft = nat ? ft->pre_ct_nat.ft : ft->pre_ct.ft;
+	ct_flow->pre_ct_rule = mlx5_tc_rule_insert(priv, orig_spec,
+						   pre_ct_attr);
 	if (IS_ERR(ct_flow->pre_ct_rule)) {
 		err = PTR_ERR(ct_flow->pre_ct_rule);
 		ct_dbg("Failed to add pre ct rule");
@@ -1565,14 +1667,18 @@ __mlx5_tc_ct_flow_offload(struct mlx5e_priv *priv,
 	return rule;
 
 err_insert_orig:
-	mlx5_eswitch_del_offloaded_rule(ct_priv->esw, ct_flow->post_ct_rule,
-					&ct_flow->post_ct_attr);
+	mlx5_tc_rule_delete(priv, ct_flow->post_ct_rule,
+			    ct_flow->post_ct_attr);
 err_insert_post_ct:
 	mlx5_modify_header_dealloc(priv->mdev, pre_ct_attr->modify_hdr);
 err_mapping:
 	dealloc_mod_hdr_actions(&pre_mod_acts);
-	mlx5_esw_chains_put_chain_mapping(esw, ct_flow->chain_mapping);
+	mlx5_chains_put_chain_mapping(ct_priv->chains, ct_flow->chain_mapping);
 err_get_chain:
+	kfree(ct_flow->post_ct_attr);
+err_alloc_post:
+	kfree(ct_flow->pre_ct_attr);
+err_alloc_pre:
 	idr_remove(&ct_priv->fte_ids, fte_id);
 err_idr:
 	mlx5_tc_ct_del_ft_cb(ct_priv, ft);
@@ -1584,14 +1690,14 @@ err_ft:
 }
 
 static struct mlx5_flow_handle *
-__mlx5_tc_ct_flow_offload_clear(struct mlx5e_priv *priv,
+__mlx5_tc_ct_flow_offload_clear(struct mlx5_tc_ct_priv *ct_priv,
 				struct mlx5_flow_spec *orig_spec,
-				struct mlx5_esw_flow_attr *attr,
+				struct mlx5_flow_attr *attr,
 				struct mlx5e_tc_mod_hdr_acts *mod_acts)
 {
-	struct mlx5_tc_ct_priv *ct_priv = mlx5_tc_ct_get_ct_priv(priv);
-	struct mlx5_eswitch *esw = ct_priv->esw;
-	struct mlx5_esw_flow_attr *pre_ct_attr;
+	struct mlx5e_priv *priv = netdev_priv(ct_priv->netdev);
+	u32 attr_sz = ns_to_attr_sz(ct_priv->ns_type);
+	struct mlx5_flow_attr *pre_ct_attr;
 	struct mlx5_modify_hdr *mod_hdr;
 	struct mlx5_flow_handle *rule;
 	struct mlx5_ct_flow *ct_flow;
@@ -1602,8 +1708,13 @@ __mlx5_tc_ct_flow_offload_clear(struct mlx5e_priv *priv,
 		return ERR_PTR(-ENOMEM);
 
 	/* Base esw attributes on original rule attribute */
-	pre_ct_attr = &ct_flow->pre_ct_attr;
-	memcpy(pre_ct_attr, attr, sizeof(*attr));
+	pre_ct_attr = mlx5_alloc_flow_attr(ct_priv->ns_type);
+	if (!pre_ct_attr) {
+		err = -ENOMEM;
+		goto err_attr;
+	}
+
+	memcpy(pre_ct_attr, attr, attr_sz);
 
 	err = mlx5_tc_ct_entry_set_registers(ct_priv, mod_acts, 0, 0, 0, 0);
 	if (err) {
@@ -1611,8 +1722,7 @@ __mlx5_tc_ct_flow_offload_clear(struct mlx5e_priv *priv,
 		goto err_set_registers;
 	}
 
-	mod_hdr = mlx5_modify_header_alloc(esw->dev,
-					   MLX5_FLOW_NAMESPACE_FDB,
+	mod_hdr = mlx5_modify_header_alloc(priv->mdev, ct_priv->ns_type,
 					   mod_acts->num_actions,
 					   mod_acts->actions);
 	if (IS_ERR(mod_hdr)) {
@@ -1625,7 +1735,7 @@ __mlx5_tc_ct_flow_offload_clear(struct mlx5e_priv *priv,
 	pre_ct_attr->modify_hdr = mod_hdr;
 	pre_ct_attr->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
 
-	rule = mlx5_eswitch_add_offloaded_rule(esw, orig_spec, pre_ct_attr);
+	rule = mlx5_tc_rule_insert(priv, orig_spec, pre_ct_attr);
 	if (IS_ERR(rule)) {
 		err = PTR_ERR(rule);
 		ct_dbg("Failed to add ct clear rule");
@@ -1633,6 +1743,7 @@ __mlx5_tc_ct_flow_offload_clear(struct mlx5e_priv *priv,
 	}
 
 	attr->ct_attr.ct_flow = ct_flow;
+	ct_flow->pre_ct_attr = pre_ct_attr;
 	ct_flow->pre_ct_rule = rule;
 	return rule;
 
@@ -1641,61 +1752,67 @@ err_insert:
 err_set_registers:
 	netdev_warn(priv->netdev,
 		    "Failed to offload ct clear flow, err %d\n", err);
+	kfree(pre_ct_attr);
+err_attr:
+	kfree(ct_flow);
+
 	return ERR_PTR(err);
 }
 
 struct mlx5_flow_handle *
-mlx5_tc_ct_flow_offload(struct mlx5e_priv *priv,
+mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *priv,
 			struct mlx5e_tc_flow *flow,
 			struct mlx5_flow_spec *spec,
-			struct mlx5_esw_flow_attr *attr,
+			struct mlx5_flow_attr *attr,
 			struct mlx5e_tc_mod_hdr_acts *mod_hdr_acts)
 {
 	bool clear_action = attr->ct_attr.ct_action & TCA_CT_ACT_CLEAR;
-	struct mlx5_tc_ct_priv *ct_priv = mlx5_tc_ct_get_ct_priv(priv);
 	struct mlx5_flow_handle *rule;
 
-	if (!ct_priv)
+	if (!priv)
 		return ERR_PTR(-EOPNOTSUPP);
 
-	mutex_lock(&ct_priv->control_lock);
+	mutex_lock(&priv->control_lock);
 
 	if (clear_action)
 		rule = __mlx5_tc_ct_flow_offload_clear(priv, spec, attr, mod_hdr_acts);
 	else
 		rule = __mlx5_tc_ct_flow_offload(priv, flow, spec, attr);
-	mutex_unlock(&ct_priv->control_lock);
+	mutex_unlock(&priv->control_lock);
 
 	return rule;
 }
 
 static void
 __mlx5_tc_ct_delete_flow(struct mlx5_tc_ct_priv *ct_priv,
+			 struct mlx5e_tc_flow *flow,
 			 struct mlx5_ct_flow *ct_flow)
 {
-	struct mlx5_esw_flow_attr *pre_ct_attr = &ct_flow->pre_ct_attr;
-	struct mlx5_eswitch *esw = ct_priv->esw;
+	struct mlx5_flow_attr *pre_ct_attr = ct_flow->pre_ct_attr;
+	struct mlx5e_priv *priv = netdev_priv(ct_priv->netdev);
 
-	mlx5_eswitch_del_offloaded_rule(esw, ct_flow->pre_ct_rule,
-					pre_ct_attr);
-	mlx5_modify_header_dealloc(esw->dev, pre_ct_attr->modify_hdr);
+	mlx5_tc_rule_delete(priv, ct_flow->pre_ct_rule,
+			    pre_ct_attr);
+	mlx5_modify_header_dealloc(priv->mdev, pre_ct_attr->modify_hdr);
 
 	if (ct_flow->post_ct_rule) {
-		mlx5_eswitch_del_offloaded_rule(esw, ct_flow->post_ct_rule,
-						&ct_flow->post_ct_attr);
-		mlx5_esw_chains_put_chain_mapping(esw, ct_flow->chain_mapping);
+		mlx5_tc_rule_delete(priv, ct_flow->post_ct_rule,
+				    ct_flow->post_ct_attr);
+		mlx5_chains_put_chain_mapping(ct_priv->chains, ct_flow->chain_mapping);
 		idr_remove(&ct_priv->fte_ids, ct_flow->fte_id);
 		mlx5_tc_ct_del_ft_cb(ct_priv, ct_flow->ft);
 	}
 
+	kfree(ct_flow->pre_ct_attr);
+	kfree(ct_flow->post_ct_attr);
 	kfree(ct_flow);
 }
 
 void
-mlx5_tc_ct_delete_flow(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow,
-		       struct mlx5_esw_flow_attr *attr)
+mlx5_tc_ct_delete_flow(struct mlx5_tc_ct_priv *priv,
+		       struct mlx5e_tc_flow *flow,
+		       struct mlx5_flow_attr *attr)
 {
-	struct mlx5_tc_ct_priv *ct_priv = mlx5_tc_ct_get_ct_priv(priv);
 	struct mlx5_ct_flow *ct_flow = attr->ct_attr.ct_flow;
 
 	/* We are called on error to clean up stuff from parsing
@@ -1704,22 +1821,15 @@ mlx5_tc_ct_delete_flow(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow,
 	if (!ct_flow)
 		return;
 
-	mutex_lock(&ct_priv->control_lock);
-	__mlx5_tc_ct_delete_flow(ct_priv, ct_flow);
-	mutex_unlock(&ct_priv->control_lock);
+	mutex_lock(&priv->control_lock);
+	__mlx5_tc_ct_delete_flow(priv, flow, ct_flow);
+	mutex_unlock(&priv->control_lock);
 }
 
 static int
-mlx5_tc_ct_init_check_support(struct mlx5_eswitch *esw,
-			      const char **err_msg)
+mlx5_tc_ct_init_check_esw_support(struct mlx5_eswitch *esw,
+				  const char **err_msg)
 {
-#if !IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
-	/* cannot restore chain ID on HW miss */
-
-	*err_msg = "tc skb extension missing";
-	return -EOPNOTSUPP;
-#endif
-
 	if (!MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, ignore_flow_level)) {
 		*err_msg = "firmware level support is missing";
 		return -EOPNOTSUPP;
@@ -1753,44 +1863,61 @@ mlx5_tc_ct_init_check_support(struct mlx5_eswitch *esw,
 	return 0;
 }
 
-static void
-mlx5_tc_ct_init_err(struct mlx5e_rep_priv *rpriv, const char *msg, int err)
+static int
+mlx5_tc_ct_init_check_nic_support(struct mlx5e_priv *priv,
+				  const char **err_msg)
+{
+	if (!MLX5_CAP_FLOWTABLE_NIC_RX(priv->mdev, ignore_flow_level)) {
+		*err_msg = "firmware level support is missing";
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int
+mlx5_tc_ct_init_check_support(struct mlx5e_priv *priv,
+			      enum mlx5_flow_namespace_type ns_type,
+			      const char **err_msg)
 {
-	if (msg)
-		netdev_warn(rpriv->netdev,
-			    "tc ct offload not supported, %s, err: %d\n",
-			    msg, err);
+	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+
+#if !IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
+	/* cannot restore chain ID on HW miss */
+
+	*err_msg = "tc skb extension missing";
+	return -EOPNOTSUPP;
+#endif
+	if (ns_type == MLX5_FLOW_NAMESPACE_FDB)
+		return mlx5_tc_ct_init_check_esw_support(esw, err_msg);
 	else
-		netdev_warn(rpriv->netdev,
-			    "tc ct offload not supported, err: %d\n",
-			    err);
+		return mlx5_tc_ct_init_check_nic_support(priv, err_msg);
 }
 
-int
-mlx5_tc_ct_init(struct mlx5_rep_uplink_priv *uplink_priv)
+#define INIT_ERR_PREFIX "tc ct offload init failed"
+
+struct mlx5_tc_ct_priv *
+mlx5_tc_ct_init(struct mlx5e_priv *priv, struct mlx5_fs_chains *chains,
+		struct mod_hdr_tbl *mod_hdr,
+		enum mlx5_flow_namespace_type ns_type)
 {
 	struct mlx5_tc_ct_priv *ct_priv;
-	struct mlx5e_rep_priv *rpriv;
-	struct mlx5_eswitch *esw;
-	struct mlx5e_priv *priv;
+	struct mlx5_core_dev *dev;
 	const char *msg;
 	int err;
 
-	rpriv = container_of(uplink_priv, struct mlx5e_rep_priv, uplink_priv);
-	priv = netdev_priv(rpriv->netdev);
-	esw = priv->mdev->priv.eswitch;
-
-	err = mlx5_tc_ct_init_check_support(esw, &msg);
+	dev = priv->mdev;
+	err = mlx5_tc_ct_init_check_support(priv, ns_type, &msg);
 	if (err) {
-		mlx5_tc_ct_init_err(rpriv, msg, err);
+		mlx5_core_warn(dev,
+			       "tc ct offload not supported, %s\n",
+			       msg);
 		goto err_support;
 	}
 
 	ct_priv = kzalloc(sizeof(*ct_priv), GFP_KERNEL);
-	if (!ct_priv) {
-		mlx5_tc_ct_init_err(rpriv, NULL, -ENOMEM);
+	if (!ct_priv)
 		goto err_alloc;
-	}
 
 	ct_priv->zone_mapping = mapping_create(sizeof(u16), 0, true);
 	if (IS_ERR(ct_priv->zone_mapping)) {
@@ -1804,46 +1931,51 @@ mlx5_tc_ct_init(struct mlx5_rep_uplink_priv *uplink_priv)
 		goto err_mapping_labels;
 	}
 
-	ct_priv->esw = esw;
-	ct_priv->netdev = rpriv->netdev;
-	ct_priv->ct = mlx5_esw_chains_create_global_table(esw);
+	ct_priv->ns_type = ns_type;
+	ct_priv->chains = chains;
+	ct_priv->netdev = priv->netdev;
+	ct_priv->dev = priv->mdev;
+	ct_priv->mod_hdr_tbl = mod_hdr;
+	ct_priv->ct = mlx5_chains_create_global_table(chains);
 	if (IS_ERR(ct_priv->ct)) {
 		err = PTR_ERR(ct_priv->ct);
-		mlx5_tc_ct_init_err(rpriv, "failed to create ct table", err);
+		mlx5_core_warn(dev,
+			       "%s, failed to create ct table err: %d\n",
+			       INIT_ERR_PREFIX, err);
 		goto err_ct_tbl;
 	}
 
-	ct_priv->ct_nat = mlx5_esw_chains_create_global_table(esw);
+	ct_priv->ct_nat = mlx5_chains_create_global_table(chains);
 	if (IS_ERR(ct_priv->ct_nat)) {
 		err = PTR_ERR(ct_priv->ct_nat);
-		mlx5_tc_ct_init_err(rpriv, "failed to create ct nat table",
-				    err);
+		mlx5_core_warn(dev,
+			       "%s, failed to create ct nat table err: %d\n",
+			       INIT_ERR_PREFIX, err);
 		goto err_ct_nat_tbl;
 	}
 
-	ct_priv->post_ct = mlx5_esw_chains_create_global_table(esw);
+	ct_priv->post_ct = mlx5_chains_create_global_table(chains);
 	if (IS_ERR(ct_priv->post_ct)) {
 		err = PTR_ERR(ct_priv->post_ct);
-		mlx5_tc_ct_init_err(rpriv, "failed to create post ct table",
-				    err);
+		mlx5_core_warn(dev,
+			       "%s, failed to create post ct table err: %d\n",
+			       INIT_ERR_PREFIX, err);
 		goto err_post_ct_tbl;
 	}
 
 	idr_init(&ct_priv->fte_ids);
 	mutex_init(&ct_priv->control_lock);
+	mutex_init(&ct_priv->shared_counter_lock);
 	rhashtable_init(&ct_priv->zone_ht, &zone_params);
 	rhashtable_init(&ct_priv->ct_tuples_ht, &tuples_ht_params);
 	rhashtable_init(&ct_priv->ct_tuples_nat_ht, &tuples_nat_ht_params);
 
-	/* Done, set ct_priv to know it initializted */
-	uplink_priv->ct_priv = ct_priv;
-
-	return 0;
+	return ct_priv;
 
 err_post_ct_tbl:
-	mlx5_esw_chains_destroy_global_table(esw, ct_priv->ct_nat);
+	mlx5_chains_destroy_global_table(chains, ct_priv->ct_nat);
 err_ct_nat_tbl:
-	mlx5_esw_chains_destroy_global_table(esw, ct_priv->ct);
+	mlx5_chains_destroy_global_table(chains, ct_priv->ct);
 err_ct_tbl:
 	mapping_destroy(ct_priv->labels_mapping);
 err_mapping_labels:
@@ -1853,20 +1985,22 @@ err_mapping_zone:
 err_alloc:
 err_support:
 
-	return 0;
+	return NULL;
 }
 
 void
-mlx5_tc_ct_clean(struct mlx5_rep_uplink_priv *uplink_priv)
+mlx5_tc_ct_clean(struct mlx5_tc_ct_priv *ct_priv)
 {
-	struct mlx5_tc_ct_priv *ct_priv = uplink_priv->ct_priv;
+	struct mlx5_fs_chains *chains;
 
 	if (!ct_priv)
 		return;
 
-	mlx5_esw_chains_destroy_global_table(ct_priv->esw, ct_priv->post_ct);
-	mlx5_esw_chains_destroy_global_table(ct_priv->esw, ct_priv->ct_nat);
-	mlx5_esw_chains_destroy_global_table(ct_priv->esw, ct_priv->ct);
+	chains = ct_priv->chains;
+
+	mlx5_chains_destroy_global_table(chains, ct_priv->post_ct);
+	mlx5_chains_destroy_global_table(chains, ct_priv->ct_nat);
+	mlx5_chains_destroy_global_table(chains, ct_priv->ct);
 	mapping_destroy(ct_priv->zone_mapping);
 	mapping_destroy(ct_priv->labels_mapping);
 
@@ -1874,17 +2008,15 @@ mlx5_tc_ct_clean(struct mlx5_rep_uplink_priv *uplink_priv)
 	rhashtable_destroy(&ct_priv->ct_tuples_nat_ht);
 	rhashtable_destroy(&ct_priv->zone_ht);
 	mutex_destroy(&ct_priv->control_lock);
+	mutex_destroy(&ct_priv->shared_counter_lock);
 	idr_destroy(&ct_priv->fte_ids);
 	kfree(ct_priv);
-
-	uplink_priv->ct_priv = NULL;
 }
 
 bool
-mlx5e_tc_ct_restore_flow(struct mlx5_rep_uplink_priv *uplink_priv,
+mlx5e_tc_ct_restore_flow(struct mlx5_tc_ct_priv *ct_priv,
 			 struct sk_buff *skb, u8 zone_restore_id)
 {
-	struct mlx5_tc_ct_priv *ct_priv = uplink_priv->ct_priv;
 	struct mlx5_ct_tuple tuple = {};
 	struct mlx5_ct_entry *entry;
 	u16 zone;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h
index 3baef917a677..6503b614337c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h
@@ -10,12 +10,14 @@
 
 #include "en.h"
 
-struct mlx5_esw_flow_attr;
+struct mlx5_flow_attr;
 struct mlx5e_tc_mod_hdr_acts;
 struct mlx5_rep_uplink_priv;
 struct mlx5e_tc_flow;
 struct mlx5e_priv;
 
+struct mlx5_fs_chains;
+struct mlx5_tc_ct_priv;
 struct mlx5_ct_flow;
 
 struct nf_flowtable;
@@ -76,66 +78,82 @@ struct mlx5_ct_attr {
 				 misc_parameters_2.metadata_reg_c_1) + 3,\
 }
 
+#define nic_zone_restore_to_reg_ct {\
+	.mfield = MLX5_ACTION_IN_FIELD_METADATA_REG_B,\
+	.moffset = 2,\
+	.mlen = 1,\
+}
+
 #define REG_MAPPING_MLEN(reg) (mlx5e_tc_attr_to_reg_mappings[reg].mlen)
+#define REG_MAPPING_MOFFSET(reg) (mlx5e_tc_attr_to_reg_mappings[reg].moffset)
+#define REG_MAPPING_SHIFT(reg) (REG_MAPPING_MOFFSET(reg) * 8)
 #define ZONE_RESTORE_BITS (REG_MAPPING_MLEN(ZONE_RESTORE_TO_REG) * 8)
 #define ZONE_RESTORE_MAX GENMASK(ZONE_RESTORE_BITS - 1, 0)
 
 #if IS_ENABLED(CONFIG_MLX5_TC_CT)
 
-int
-mlx5_tc_ct_init(struct mlx5_rep_uplink_priv *uplink_priv);
+struct mlx5_tc_ct_priv *
+mlx5_tc_ct_init(struct mlx5e_priv *priv, struct mlx5_fs_chains *chains,
+		struct mod_hdr_tbl *mod_hdr,
+		enum mlx5_flow_namespace_type ns_type);
 void
-mlx5_tc_ct_clean(struct mlx5_rep_uplink_priv *uplink_priv);
+mlx5_tc_ct_clean(struct mlx5_tc_ct_priv *ct_priv);
+
+void
+mlx5_tc_ct_match_del(struct mlx5_tc_ct_priv *priv, struct mlx5_ct_attr *ct_attr);
 
 int
-mlx5_tc_ct_parse_match(struct mlx5e_priv *priv,
-		       struct mlx5_flow_spec *spec,
-		       struct flow_cls_offload *f,
-		       struct mlx5_ct_attr *ct_attr,
-		       struct netlink_ext_ack *extack);
-int
-mlx5_tc_ct_add_no_trk_match(struct mlx5e_priv *priv,
-			    struct mlx5_flow_spec *spec);
+mlx5_tc_ct_match_add(struct mlx5_tc_ct_priv *priv,
+		     struct mlx5_flow_spec *spec,
+		     struct flow_cls_offload *f,
+		     struct mlx5_ct_attr *ct_attr,
+		     struct netlink_ext_ack *extack);
+int mlx5_tc_ct_add_no_trk_match(struct mlx5_flow_spec *spec);
 int
-mlx5_tc_ct_parse_action(struct mlx5e_priv *priv,
-			struct mlx5_esw_flow_attr *attr,
+mlx5_tc_ct_parse_action(struct mlx5_tc_ct_priv *priv,
+			struct mlx5_flow_attr *attr,
 			const struct flow_action_entry *act,
 			struct netlink_ext_ack *extack);
 
 struct mlx5_flow_handle *
-mlx5_tc_ct_flow_offload(struct mlx5e_priv *priv,
+mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *priv,
 			struct mlx5e_tc_flow *flow,
 			struct mlx5_flow_spec *spec,
-			struct mlx5_esw_flow_attr *attr,
+			struct mlx5_flow_attr *attr,
 			struct mlx5e_tc_mod_hdr_acts *mod_hdr_acts);
 void
-mlx5_tc_ct_delete_flow(struct mlx5e_priv *priv,
+mlx5_tc_ct_delete_flow(struct mlx5_tc_ct_priv *priv,
 		       struct mlx5e_tc_flow *flow,
-		       struct mlx5_esw_flow_attr *attr);
+		       struct mlx5_flow_attr *attr);
 
 bool
-mlx5e_tc_ct_restore_flow(struct mlx5_rep_uplink_priv *uplink_priv,
+mlx5e_tc_ct_restore_flow(struct mlx5_tc_ct_priv *ct_priv,
 			 struct sk_buff *skb, u8 zone_restore_id);
 
 #else /* CONFIG_MLX5_TC_CT */
 
-static inline int
-mlx5_tc_ct_init(struct mlx5_rep_uplink_priv *uplink_priv)
+static inline struct mlx5_tc_ct_priv *
+mlx5_tc_ct_init(struct mlx5e_priv *priv, struct mlx5_fs_chains *chains,
+		struct mod_hdr_tbl *mod_hdr,
+		enum mlx5_flow_namespace_type ns_type)
 {
-	return 0;
+	return NULL;
 }
 
 static inline void
-mlx5_tc_ct_clean(struct mlx5_rep_uplink_priv *uplink_priv)
+mlx5_tc_ct_clean(struct mlx5_tc_ct_priv *ct_priv)
 {
 }
 
+static inline void
+mlx5_tc_ct_match_del(struct mlx5_tc_ct_priv *priv, struct mlx5_ct_attr *ct_attr) {}
+
 static inline int
-mlx5_tc_ct_parse_match(struct mlx5e_priv *priv,
-		       struct mlx5_flow_spec *spec,
-		       struct flow_cls_offload *f,
-		       struct mlx5_ct_attr *ct_attr,
-		       struct netlink_ext_ack *extack)
+mlx5_tc_ct_match_add(struct mlx5_tc_ct_priv *priv,
+		     struct mlx5_flow_spec *spec,
+		     struct flow_cls_offload *f,
+		     struct mlx5_ct_attr *ct_attr,
+		     struct netlink_ext_ack *extack)
 {
 	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
 
@@ -143,47 +161,44 @@ mlx5_tc_ct_parse_match(struct mlx5e_priv *priv,
 		return 0;
 
 	NL_SET_ERR_MSG_MOD(extack, "mlx5 tc ct offload isn't enabled.");
-	netdev_warn(priv->netdev, "mlx5 tc ct offload isn't enabled.\n");
 	return -EOPNOTSUPP;
 }
 
 static inline int
-mlx5_tc_ct_add_no_trk_match(struct mlx5e_priv *priv,
-			    struct mlx5_flow_spec *spec)
+mlx5_tc_ct_add_no_trk_match(struct mlx5_flow_spec *spec)
 {
 	return 0;
 }
 
 static inline int
-mlx5_tc_ct_parse_action(struct mlx5e_priv *priv,
-			struct mlx5_esw_flow_attr *attr,
+mlx5_tc_ct_parse_action(struct mlx5_tc_ct_priv *priv,
+			struct mlx5_flow_attr *attr,
 			const struct flow_action_entry *act,
 			struct netlink_ext_ack *extack)
 {
 	NL_SET_ERR_MSG_MOD(extack, "mlx5 tc ct offload isn't enabled.");
-	netdev_warn(priv->netdev, "mlx5 tc ct offload isn't enabled.\n");
 	return -EOPNOTSUPP;
 }
 
 static inline struct mlx5_flow_handle *
-mlx5_tc_ct_flow_offload(struct mlx5e_priv *priv,
+mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *priv,
 			struct mlx5e_tc_flow *flow,
 			struct mlx5_flow_spec *spec,
-			struct mlx5_esw_flow_attr *attr,
+			struct mlx5_flow_attr *attr,
 			struct mlx5e_tc_mod_hdr_acts *mod_hdr_acts)
 {
 	return ERR_PTR(-EOPNOTSUPP);
 }
 
 static inline void
-mlx5_tc_ct_delete_flow(struct mlx5e_priv *priv,
+mlx5_tc_ct_delete_flow(struct mlx5_tc_ct_priv *priv,
 		       struct mlx5e_tc_flow *flow,
-		       struct mlx5_esw_flow_attr *attr)
+		       struct mlx5_flow_attr *attr)
 {
 }
 
 static inline bool
-mlx5e_tc_ct_restore_flow(struct mlx5_rep_uplink_priv *uplink_priv,
+mlx5e_tc_ct_restore_flow(struct mlx5_tc_ct_priv *ct_priv,
 			 struct sk_buff *skb, u8 zone_restore_id)
 {
 	if (!zone_restore_id)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
index 9334c9c3e208..07ee1d236ab3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
@@ -7,6 +7,21 @@
 #include "en.h"
 #include <linux/indirect_call_wrapper.h>
 
+#define MLX5E_TX_WQE_EMPTY_DS_COUNT (sizeof(struct mlx5e_tx_wqe) / MLX5_SEND_WQE_DS)
+
+/* The mult of MLX5_SEND_WQE_MAX_WQEBBS * MLX5_SEND_WQEBB_NUM_DS
+ * (16 * 4 == 64) does not fit in the 6-bit DS field of Ctrl Segment.
+ * We use a bound lower that MLX5_SEND_WQE_MAX_WQEBBS to let a
+ * full-session WQE be cache-aligned.
+ */
+#if L1_CACHE_BYTES < 128
+#define MLX5E_TX_MPW_MAX_WQEBBS (MLX5_SEND_WQE_MAX_WQEBBS - 1)
+#else
+#define MLX5E_TX_MPW_MAX_WQEBBS (MLX5_SEND_WQE_MAX_WQEBBS - 2)
+#endif
+
+#define MLX5E_TX_MPW_MAX_NUM_DS (MLX5E_TX_MPW_MAX_WQEBBS * MLX5_SEND_WQEBB_NUM_DS)
+
 #define INL_HDR_START_SZ (sizeof(((struct mlx5_wqe_eth_seg *)NULL)->inline_hdr.start))
 
 enum mlx5e_icosq_wqe_type {
@@ -20,6 +35,11 @@ enum mlx5e_icosq_wqe_type {
 };
 
 /* General */
+static inline bool mlx5e_skb_is_multicast(struct sk_buff *skb)
+{
+	return skb->pkt_type == PACKET_MULTICAST || skb->pkt_type == PACKET_BROADCAST;
+}
+
 void mlx5e_trigger_irq(struct mlx5e_icosq *sq);
 void mlx5e_completion_event(struct mlx5_core_cq *mcq, struct mlx5_eqe *eqe);
 void mlx5e_cq_error_event(struct mlx5_core_cq *mcq, enum mlx5_event event);
@@ -41,8 +61,6 @@ void mlx5e_free_rx_in_progress_descs(struct mlx5e_rq *rq);
 u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb,
 		       struct net_device *sb_dev);
 netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev);
-void mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
-		   struct mlx5e_tx_wqe *wqe, u16 pi, bool xmit_more);
 bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget);
 void mlx5e_free_txqsq_descs(struct mlx5e_txqsq *sq);
 
@@ -105,6 +123,7 @@ struct mlx5e_tx_wqe_info {
 	u32 num_bytes;
 	u8 num_wqebbs;
 	u8 num_dma;
+	u8 num_fifo_pkts;
 #ifdef CONFIG_MLX5_EN_TLS
 	struct page *resync_dump_frag_page;
 #endif
@@ -189,23 +208,6 @@ static inline u16 mlx5e_icosq_get_next_pi(struct mlx5e_icosq *sq, u16 size)
 }
 
 static inline void
-mlx5e_fill_sq_frag_edge(struct mlx5e_txqsq *sq, struct mlx5_wq_cyc *wq,
-			u16 pi, u16 nnops)
-{
-	struct mlx5e_tx_wqe_info *edge_wi, *wi = &sq->db.wqe_info[pi];
-
-	edge_wi = wi + nnops;
-
-	/* fill sq frag edge with nops to avoid wqe wrapping two pages */
-	for (; wi < edge_wi; wi++) {
-		memset(wi, 0, sizeof(*wi));
-		wi->num_wqebbs = 1;
-		mlx5e_post_nop(wq, sq->sqn, &sq->pc);
-	}
-	sq->stats->nop += nnops;
-}
-
-static inline void
 mlx5e_notify_hw(struct mlx5_wq_cyc *wq, u16 pc, void __iomem *uar_map,
 		struct mlx5_wqe_ctrl_seg *ctrl)
 {
@@ -223,29 +225,6 @@ mlx5e_notify_hw(struct mlx5_wq_cyc *wq, u16 pc, void __iomem *uar_map,
 	mlx5_write64((__be32 *)ctrl, uar_map);
 }
 
-static inline bool mlx5e_transport_inline_tx_wqe(struct mlx5_wqe_ctrl_seg *cseg)
-{
-	return cseg && !!cseg->tis_tir_num;
-}
-
-static inline u8
-mlx5e_tx_wqe_inline_mode(struct mlx5e_txqsq *sq, struct mlx5_wqe_ctrl_seg *cseg,
-			 struct sk_buff *skb)
-{
-	u8 mode;
-
-	if (mlx5e_transport_inline_tx_wqe(cseg))
-		return MLX5_INLINE_MODE_TCP_UDP;
-
-	mode = sq->min_inline_mode;
-
-	if (skb_vlan_tag_present(skb) &&
-	    test_bit(MLX5E_SQ_STATE_VLAN_NEED_L2_INLINE, &sq->state))
-		mode = max_t(u8, MLX5_INLINE_MODE_L2, mode);
-
-	return mode;
-}
-
 static inline void mlx5e_cq_arm(struct mlx5e_cq *cq)
 {
 	struct mlx5_core_cq *mcq;
@@ -271,6 +250,23 @@ mlx5e_dma_push(struct mlx5e_txqsq *sq, dma_addr_t addr, u32 size,
 	dma->type = map_type;
 }
 
+static inline struct sk_buff **mlx5e_skb_fifo_get(struct mlx5e_txqsq *sq, u16 i)
+{
+	return &sq->db.skb_fifo[i & sq->skb_fifo_mask];
+}
+
+static inline void mlx5e_skb_fifo_push(struct mlx5e_txqsq *sq, struct sk_buff *skb)
+{
+	struct sk_buff **skb_item = mlx5e_skb_fifo_get(sq, sq->skb_fifo_pc++);
+
+	*skb_item = skb;
+}
+
+static inline struct sk_buff *mlx5e_skb_fifo_pop(struct mlx5e_txqsq *sq)
+{
+	return *mlx5e_skb_fifo_get(sq, sq->skb_fifo_cc++);
+}
+
 static inline void
 mlx5e_tx_dma_unmap(struct device *pdev, struct mlx5e_sq_dma *dma)
 {
@@ -286,6 +282,14 @@ mlx5e_tx_dma_unmap(struct device *pdev, struct mlx5e_sq_dma *dma)
 	}
 }
 
+void mlx5e_sq_xmit_simple(struct mlx5e_txqsq *sq, struct sk_buff *skb, bool xmit_more);
+void mlx5e_tx_mpwqe_ensure_complete(struct mlx5e_txqsq *sq);
+
+static inline bool mlx5e_tx_mpwqe_is_full(struct mlx5e_tx_mpwqe *session)
+{
+	return session->ds_count == MLX5E_TX_MPW_MAX_NUM_DS;
+}
+
 static inline void mlx5e_rqwq_reset(struct mlx5e_rq *rq)
 {
 	if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index 145592788de5..ae90d533a350 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -59,7 +59,7 @@ static inline bool
 mlx5e_xmit_xdp_buff(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq,
 		    struct mlx5e_dma_info *di, struct xdp_buff *xdp)
 {
-	struct mlx5e_xdp_xmit_data xdptxd;
+	struct mlx5e_xmit_data xdptxd;
 	struct mlx5e_xdp_info xdpi;
 	struct xdp_frame *xdpf;
 	dma_addr_t dma_addr;
@@ -122,7 +122,7 @@ mlx5e_xmit_xdp_buff(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq,
 bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di,
 		      u32 *len, struct xdp_buff *xdp)
 {
-	struct bpf_prog *prog = READ_ONCE(rq->xdp_prog);
+	struct bpf_prog *prog = rcu_dereference(rq->xdp_prog);
 	u32 act;
 	int err;
 
@@ -194,18 +194,22 @@ static u16 mlx5e_xdpsq_get_next_pi(struct mlx5e_xdpsq *sq, u16 size)
 
 static void mlx5e_xdp_mpwqe_session_start(struct mlx5e_xdpsq *sq)
 {
-	struct mlx5e_xdp_mpwqe *session = &sq->mpwqe;
+	struct mlx5e_tx_mpwqe *session = &sq->mpwqe;
 	struct mlx5e_xdpsq_stats *stats = sq->stats;
+	struct mlx5e_tx_wqe *wqe;
 	u16 pi;
 
-	pi = mlx5e_xdpsq_get_next_pi(sq, MLX5_SEND_WQE_MAX_WQEBBS);
-	session->wqe = MLX5E_TX_FETCH_WQE(sq, pi);
+	pi = mlx5e_xdpsq_get_next_pi(sq, MLX5E_TX_MPW_MAX_WQEBBS);
+	wqe = MLX5E_TX_FETCH_WQE(sq, pi);
+	net_prefetchw(wqe->data);
 
-	net_prefetchw(session->wqe->data);
-	session->ds_count  = MLX5E_XDP_TX_EMPTY_DS_COUNT;
-	session->pkt_count = 0;
-
-	mlx5e_xdp_update_inline_state(sq);
+	*session = (struct mlx5e_tx_mpwqe) {
+		.wqe = wqe,
+		.bytes_count = 0,
+		.ds_count = MLX5E_TX_WQE_EMPTY_DS_COUNT,
+		.pkt_count = 0,
+		.inline_on = mlx5e_xdp_get_inline_state(sq, session->inline_on),
+	};
 
 	stats->mpwqe++;
 }
@@ -213,7 +217,7 @@ static void mlx5e_xdp_mpwqe_session_start(struct mlx5e_xdpsq *sq)
 void mlx5e_xdp_mpwqe_complete(struct mlx5e_xdpsq *sq)
 {
 	struct mlx5_wq_cyc       *wq    = &sq->wq;
-	struct mlx5e_xdp_mpwqe *session = &sq->mpwqe;
+	struct mlx5e_tx_mpwqe *session = &sq->mpwqe;
 	struct mlx5_wqe_ctrl_seg *cseg = &session->wqe->ctrl;
 	u16 ds_count = session->ds_count;
 	u16 pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
@@ -258,10 +262,10 @@ INDIRECT_CALLABLE_SCOPE int mlx5e_xmit_xdp_frame_check_mpwqe(struct mlx5e_xdpsq
 }
 
 INDIRECT_CALLABLE_SCOPE bool
-mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_xmit_data *xdptxd,
+mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd,
 			   struct mlx5e_xdp_info *xdpi, int check_result)
 {
-	struct mlx5e_xdp_mpwqe *session = &sq->mpwqe;
+	struct mlx5e_tx_mpwqe *session = &sq->mpwqe;
 	struct mlx5e_xdpsq_stats *stats = sq->stats;
 
 	if (unlikely(xdptxd->len > sq->hw_mtu)) {
@@ -284,8 +288,7 @@ mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_xmit_data *x
 
 	mlx5e_xdp_mpwqe_add_dseg(sq, xdptxd, stats);
 
-	if (unlikely(mlx5e_xdp_no_room_for_inline_pkt(session) ||
-		     session->ds_count == MLX5E_XDP_MPW_MAX_NUM_DS))
+	if (unlikely(mlx5e_xdp_mpqwe_is_full(session)))
 		mlx5e_xdp_mpwqe_complete(sq);
 
 	mlx5e_xdpi_fifo_push(&sq->db.xdpi_fifo, xdpi);
@@ -306,7 +309,7 @@ INDIRECT_CALLABLE_SCOPE int mlx5e_xmit_xdp_frame_check(struct mlx5e_xdpsq *sq)
 }
 
 INDIRECT_CALLABLE_SCOPE bool
-mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_xmit_data *xdptxd,
+mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd,
 		     struct mlx5e_xdp_info *xdpi, int check_result)
 {
 	struct mlx5_wq_cyc       *wq   = &sq->wq;
@@ -503,7 +506,7 @@ int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 
 	for (i = 0; i < n; i++) {
 		struct xdp_frame *xdpf = frames[i];
-		struct mlx5e_xdp_xmit_data xdptxd;
+		struct mlx5e_xmit_data xdptxd;
 		struct mlx5e_xdp_info xdpi;
 		bool ret;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
index e806c13d491f..d487e5e37162 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
@@ -38,27 +38,12 @@
 #include "en/txrx.h"
 
 #define MLX5E_XDP_MIN_INLINE (ETH_HLEN + VLAN_HLEN)
-#define MLX5E_XDP_TX_EMPTY_DS_COUNT \
-	(sizeof(struct mlx5e_tx_wqe) / MLX5_SEND_WQE_DS)
-#define MLX5E_XDP_TX_DS_COUNT (MLX5E_XDP_TX_EMPTY_DS_COUNT + 1 /* SG DS */)
-
-#define MLX5E_XDP_INLINE_WQE_SZ_THRSD (256 - sizeof(struct mlx5_wqe_inline_seg))
-#define MLX5E_XDP_INLINE_WQE_MAX_DS_CNT \
-	DIV_ROUND_UP(MLX5E_XDP_INLINE_WQE_SZ_THRSD, MLX5_SEND_WQE_DS)
-
-/* The mult of MLX5_SEND_WQE_MAX_WQEBBS * MLX5_SEND_WQEBB_NUM_DS
- * (16 * 4 == 64) does not fit in the 6-bit DS field of Ctrl Segment.
- * We use a bound lower that MLX5_SEND_WQE_MAX_WQEBBS to let a
- * full-session WQE be cache-aligned.
- */
-#if L1_CACHE_BYTES < 128
-#define MLX5E_XDP_MPW_MAX_WQEBBS (MLX5_SEND_WQE_MAX_WQEBBS - 1)
-#else
-#define MLX5E_XDP_MPW_MAX_WQEBBS (MLX5_SEND_WQE_MAX_WQEBBS - 2)
-#endif
+#define MLX5E_XDP_TX_DS_COUNT (MLX5E_TX_WQE_EMPTY_DS_COUNT + 1 /* SG DS */)
 
-#define MLX5E_XDP_MPW_MAX_NUM_DS \
-	(MLX5E_XDP_MPW_MAX_WQEBBS * MLX5_SEND_WQEBB_NUM_DS)
+#define MLX5E_XDP_INLINE_WQE_MAX_DS_CNT 16
+#define MLX5E_XDP_INLINE_WQE_SZ_THRSD \
+	(MLX5E_XDP_INLINE_WQE_MAX_DS_CNT * MLX5_SEND_WQE_DS - \
+	 sizeof(struct mlx5_wqe_inline_seg))
 
 struct mlx5e_xsk_param;
 int mlx5e_xdp_max_mtu(struct mlx5e_params *params, struct mlx5e_xsk_param *xsk);
@@ -73,11 +58,11 @@ int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 		   u32 flags);
 
 INDIRECT_CALLABLE_DECLARE(bool mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq,
-							  struct mlx5e_xdp_xmit_data *xdptxd,
+							  struct mlx5e_xmit_data *xdptxd,
 							  struct mlx5e_xdp_info *xdpi,
 							  int check_result));
 INDIRECT_CALLABLE_DECLARE(bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq,
-						    struct mlx5e_xdp_xmit_data *xdptxd,
+						    struct mlx5e_xmit_data *xdptxd,
 						    struct mlx5e_xdp_info *xdpi,
 						    int check_result));
 INDIRECT_CALLABLE_DECLARE(int mlx5e_xmit_xdp_frame_check_mpwqe(struct mlx5e_xdpsq *sq));
@@ -122,30 +107,28 @@ static inline void mlx5e_xmit_xdp_doorbell(struct mlx5e_xdpsq *sq)
 /* Enable inline WQEs to shift some load from a congested HCA (HW) to
  * a less congested cpu (SW).
  */
-static inline void mlx5e_xdp_update_inline_state(struct mlx5e_xdpsq *sq)
+static inline bool mlx5e_xdp_get_inline_state(struct mlx5e_xdpsq *sq, bool cur)
 {
 	u16 outstanding = sq->xdpi_fifo_pc - sq->xdpi_fifo_cc;
-	struct mlx5e_xdp_mpwqe *session = &sq->mpwqe;
 
 #define MLX5E_XDP_INLINE_WATERMARK_LOW	10
 #define MLX5E_XDP_INLINE_WATERMARK_HIGH 128
 
-	if (session->inline_on) {
-		if (outstanding <= MLX5E_XDP_INLINE_WATERMARK_LOW)
-			session->inline_on = 0;
-		return;
-	}
+	if (cur && outstanding <= MLX5E_XDP_INLINE_WATERMARK_LOW)
+		return false;
+
+	if (!cur && outstanding >= MLX5E_XDP_INLINE_WATERMARK_HIGH)
+		return true;
 
-	/* inline is false */
-	if (outstanding >= MLX5E_XDP_INLINE_WATERMARK_HIGH)
-		session->inline_on = 1;
+	return cur;
 }
 
-static inline bool
-mlx5e_xdp_no_room_for_inline_pkt(struct mlx5e_xdp_mpwqe *session)
+static inline bool mlx5e_xdp_mpqwe_is_full(struct mlx5e_tx_mpwqe *session)
 {
-	return session->inline_on &&
-	       session->ds_count + MLX5E_XDP_INLINE_WQE_MAX_DS_CNT > MLX5E_XDP_MPW_MAX_NUM_DS;
+	if (session->inline_on)
+		return session->ds_count + MLX5E_XDP_INLINE_WQE_MAX_DS_CNT >
+		       MLX5E_TX_MPW_MAX_NUM_DS;
+	return mlx5e_tx_mpwqe_is_full(session);
 }
 
 struct mlx5e_xdp_wqe_info {
@@ -155,15 +138,16 @@ struct mlx5e_xdp_wqe_info {
 
 static inline void
 mlx5e_xdp_mpwqe_add_dseg(struct mlx5e_xdpsq *sq,
-			 struct mlx5e_xdp_xmit_data *xdptxd,
+			 struct mlx5e_xmit_data *xdptxd,
 			 struct mlx5e_xdpsq_stats *stats)
 {
-	struct mlx5e_xdp_mpwqe *session = &sq->mpwqe;
+	struct mlx5e_tx_mpwqe *session = &sq->mpwqe;
 	struct mlx5_wqe_data_seg *dseg =
 		(struct mlx5_wqe_data_seg *)session->wqe + session->ds_count;
 	u32 dma_len = xdptxd->len;
 
 	session->pkt_count++;
+	session->bytes_count += dma_len;
 
 	if (session->inline_on && dma_len <= MLX5E_XDP_INLINE_WQE_SZ_THRSD) {
 		struct mlx5_wqe_inline_seg *inline_dseg =
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.c
index 3503e7711178..71e8d66fa150 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.c
@@ -9,7 +9,7 @@
 static int mlx5e_xsk_map_pool(struct mlx5e_priv *priv,
 			      struct xsk_buff_pool *pool)
 {
-	struct device *dev = priv->mdev->device;
+	struct device *dev = mlx5_core_dma_dev(priv->mdev);
 
 	return xsk_pool_dma_map(pool, dev, 0);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c
index bb6669d2a916..8e7b877d8a12 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c
@@ -31,7 +31,6 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq,
 {
 	struct xdp_buff *xdp = wi->umr.dma_info[page_idx].xsk;
 	u32 cqe_bcnt32 = cqe_bcnt;
-	bool consumed;
 
 	/* Check packet size. Note LRO doesn't use linear SKB */
 	if (unlikely(cqe_bcnt > rq->hw_mtu)) {
@@ -51,10 +50,6 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq,
 	xsk_buff_dma_sync_for_cpu(xdp, rq->xsk_pool);
 	net_prefetch(xdp->data);
 
-	rcu_read_lock();
-	consumed = mlx5e_xdp_handle(rq, NULL, &cqe_bcnt32, xdp);
-	rcu_read_unlock();
-
 	/* Possible flows:
 	 * - XDP_REDIRECT to XSKMAP:
 	 *   The page is owned by the userspace from now.
@@ -70,7 +65,7 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq,
 	 * allocated first from the Reuse Ring, so it has enough space.
 	 */
 
-	if (likely(consumed)) {
+	if (likely(mlx5e_xdp_handle(rq, NULL, &cqe_bcnt32, xdp))) {
 		if (likely(__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)))
 			__set_bit(page_idx, wi->xdp_xmit_bitmap); /* non-atomic */
 		return NULL; /* page/packet was consumed by XDP */
@@ -88,7 +83,6 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq,
 					      u32 cqe_bcnt)
 {
 	struct xdp_buff *xdp = wi->di->xsk;
-	bool consumed;
 
 	/* wi->offset is not used in this function, because xdp->data and the
 	 * DMA address point directly to the necessary place. Furthermore, the
@@ -107,11 +101,7 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq,
 		return NULL;
 	}
 
-	rcu_read_lock();
-	consumed = mlx5e_xdp_handle(rq, NULL, &cqe_bcnt, xdp);
-	rcu_read_unlock();
-
-	if (likely(consumed))
+	if (likely(mlx5e_xdp_handle(rq, NULL, &cqe_bcnt, xdp)))
 		return NULL; /* page/packet was consumed by XDP */
 
 	/* XDP_PASS: copy the data from the UMEM to a new SKB. The frame reuse
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
index 662a1dafeaad..4e574ac73019 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
@@ -106,8 +106,7 @@ err_free_cparam:
 void mlx5e_close_xsk(struct mlx5e_channel *c)
 {
 	clear_bit(MLX5E_CHANNEL_STATE_XSK, c->state);
-	napi_synchronize(&c->napi);
-	synchronize_rcu(); /* Sync with the XSK wakeup. */
+	synchronize_rcu(); /* Sync with the XSK wakeup and with NAPI. */
 
 	mlx5e_close_rq(&c->xskrq);
 	mlx5e_close_cq(&c->xskrq.cq);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c
index aa91cbdfe969..fb671a457129 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c
@@ -67,8 +67,8 @@ static void mlx5e_xsk_tx_post_err(struct mlx5e_xdpsq *sq,
 bool mlx5e_xsk_tx(struct mlx5e_xdpsq *sq, unsigned int budget)
 {
 	struct xsk_buff_pool *pool = sq->xsk_pool;
+	struct mlx5e_xmit_data xdptxd;
 	struct mlx5e_xdp_info xdpi;
-	struct mlx5e_xdp_xmit_data xdptxd;
 	bool work_done = true;
 	bool flush = false;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
index 110476bdeffb..2ea1cdc1ca54 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
@@ -128,26 +128,38 @@ static inline bool mlx5e_accel_tx_begin(struct net_device *dev,
 	return true;
 }
 
-static inline bool mlx5e_accel_tx_finish(struct mlx5e_priv *priv,
-					 struct mlx5e_txqsq *sq,
-					 struct sk_buff *skb,
-					 struct mlx5e_tx_wqe *wqe,
-					 struct mlx5e_accel_tx_state *state)
-{
-#ifdef CONFIG_MLX5_EN_TLS
-	mlx5e_tls_handle_tx_wqe(sq, &wqe->ctrl, &state->tls);
-#endif
+/* Part of the eseg touched by TX offloads */
+#define MLX5E_ACCEL_ESEG_LEN offsetof(struct mlx5_wqe_eth_seg, mss)
 
+static inline bool mlx5e_accel_tx_eseg(struct mlx5e_priv *priv,
+				       struct mlx5e_txqsq *sq,
+				       struct sk_buff *skb,
+				       struct mlx5_wqe_eth_seg *eseg)
+{
 #ifdef CONFIG_MLX5_EN_IPSEC
 	if (test_bit(MLX5E_SQ_STATE_IPSEC, &sq->state)) {
-		if (unlikely(!mlx5e_ipsec_handle_tx_skb(priv, &wqe->eth, skb)))
+		if (unlikely(!mlx5e_ipsec_handle_tx_skb(priv, eseg, skb)))
 			return false;
 	}
 #endif
 
+#if IS_ENABLED(CONFIG_GENEVE)
+	if (skb->encapsulation)
+		mlx5e_tx_tunnel_accel(skb, eseg);
+#endif
+
 	return true;
 }
 
+static inline void mlx5e_accel_tx_finish(struct mlx5e_txqsq *sq,
+					 struct mlx5e_tx_wqe *wqe,
+					 struct mlx5e_accel_tx_state *state)
+{
+#ifdef CONFIG_MLX5_EN_TLS
+	mlx5e_tls_handle_tx_wqe(sq, &wqe->ctrl, &state->tls);
+#endif
+}
+
 static inline int mlx5e_accel_init_rx(struct mlx5e_priv *priv)
 {
 	return mlx5e_ktls_init_rx(priv);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c
index 4cdd9eac647d..97f1594cee11 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c
@@ -191,7 +191,7 @@ static int accel_fs_tcp_create_groups(struct mlx5e_flow_table *ft,
 	ft->g = kcalloc(MLX5E_ACCEL_FS_TCP_NUM_GROUPS, sizeof(*ft->g), GFP_KERNEL);
 	in = kvzalloc(inlen, GFP_KERNEL);
 	if  (!in || !ft->g) {
-		kvfree(ft->g);
+		kfree(ft->g);
 		kvfree(in);
 		return -ENOMEM;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
index 429428bbc903..b974f3cd1005 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
@@ -228,8 +228,8 @@ static int rx_fs_create(struct mlx5e_priv *priv,
 	fs_prot->miss_rule = miss_rule;
 
 out:
-	kfree(flow_group_in);
-	kfree(spec);
+	kvfree(flow_group_in);
+	kvfree(spec);
 	return err;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c
index acf6d80a6bb7..ccaccb9fc2f7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c
@@ -234,7 +234,7 @@ mlx5e_get_ktls_rx_priv_ctx(struct tls_context *tls_ctx)
 
 /* Re-sync */
 /* Runs in work context */
-static struct mlx5_wqe_ctrl_seg *
+static int
 resync_post_get_progress_params(struct mlx5e_icosq *sq,
 				struct mlx5e_ktls_offload_context_rx *priv_rx)
 {
@@ -253,20 +253,24 @@ resync_post_get_progress_params(struct mlx5e_icosq *sq,
 		goto err_out;
 	}
 
-	pdev = sq->channel->priv->mdev->device;
+	pdev = mlx5_core_dma_dev(sq->channel->priv->mdev);
 	buf->dma_addr = dma_map_single(pdev, &buf->progress,
 				       PROGRESS_PARAMS_PADDED_SIZE, DMA_FROM_DEVICE);
 	if (unlikely(dma_mapping_error(pdev, buf->dma_addr))) {
 		err = -ENOMEM;
-		goto err_out;
+		goto err_free;
 	}
 
 	buf->priv_rx = priv_rx;
 
 	BUILD_BUG_ON(MLX5E_KTLS_GET_PROGRESS_WQEBBS != 1);
+
+	spin_lock(&sq->channel->async_icosq_lock);
+
 	if (unlikely(!mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, 1))) {
+		spin_unlock(&sq->channel->async_icosq_lock);
 		err = -ENOSPC;
-		goto err_out;
+		goto err_dma_unmap;
 	}
 
 	pi = mlx5e_icosq_get_next_pi(sq, 1);
@@ -294,12 +298,18 @@ resync_post_get_progress_params(struct mlx5e_icosq *sq,
 	};
 	icosq_fill_wi(sq, pi, &wi);
 	sq->pc++;
+	mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, cseg);
+	spin_unlock(&sq->channel->async_icosq_lock);
 
-	return cseg;
+	return 0;
 
+err_dma_unmap:
+	dma_unmap_single(pdev, buf->dma_addr, PROGRESS_PARAMS_PADDED_SIZE, DMA_FROM_DEVICE);
+err_free:
+	kfree(buf);
 err_out:
 	priv_rx->stats->tls_resync_req_skip++;
-	return ERR_PTR(err);
+	return err;
 }
 
 /* Function is called with elevated refcount.
@@ -309,10 +319,8 @@ static void resync_handle_work(struct work_struct *work)
 {
 	struct mlx5e_ktls_offload_context_rx *priv_rx;
 	struct mlx5e_ktls_rx_resync_ctx *resync;
-	struct mlx5_wqe_ctrl_seg *cseg;
 	struct mlx5e_channel *c;
 	struct mlx5e_icosq *sq;
-	struct mlx5_wq_cyc *wq;
 
 	resync = container_of(work, struct mlx5e_ktls_rx_resync_ctx, work);
 	priv_rx = container_of(resync, struct mlx5e_ktls_offload_context_rx, resync);
@@ -324,18 +332,9 @@ static void resync_handle_work(struct work_struct *work)
 
 	c = resync->priv->channels.c[priv_rx->rxq];
 	sq = &c->async_icosq;
-	wq = &sq->wq;
-
-	spin_lock(&c->async_icosq_lock);
 
-	cseg = resync_post_get_progress_params(sq, priv_rx);
-	if (IS_ERR(cseg)) {
+	if (resync_post_get_progress_params(sq, priv_rx))
 		refcount_dec(&resync->refcnt);
-		goto unlock;
-	}
-	mlx5e_notify_hw(wq, sq->pc, sq->uar_map, cseg);
-unlock:
-	spin_unlock(&c->async_icosq_lock);
 }
 
 static void resync_init(struct mlx5e_ktls_rx_resync_ctx *resync,
@@ -386,16 +385,17 @@ void mlx5e_ktls_handle_get_psv_completion(struct mlx5e_icosq_wqe_info *wi,
 	struct mlx5e_ktls_offload_context_rx *priv_rx;
 	struct mlx5e_ktls_rx_resync_ctx *resync;
 	u8 tracker_state, auth_state, *ctx;
+	struct device *dev;
 	u32 hw_seq;
 
 	priv_rx = buf->priv_rx;
 	resync = &priv_rx->resync;
-
+	dev = mlx5_core_dma_dev(resync->priv->mdev);
 	if (unlikely(test_bit(MLX5E_PRIV_RX_FLAG_DELETING, priv_rx->flags)))
 		goto out;
 
-	dma_sync_single_for_cpu(resync->priv->mdev->device, buf->dma_addr,
-				PROGRESS_PARAMS_PADDED_SIZE, DMA_FROM_DEVICE);
+	dma_sync_single_for_cpu(dev, buf->dma_addr, PROGRESS_PARAMS_PADDED_SIZE,
+				DMA_FROM_DEVICE);
 
 	ctx = buf->progress.ctx;
 	tracker_state = MLX5_GET(tls_progress_params, ctx, record_tracker_state);
@@ -411,6 +411,7 @@ void mlx5e_ktls_handle_get_psv_completion(struct mlx5e_icosq_wqe_info *wi,
 	priv_rx->stats->tls_resync_req_end++;
 out:
 	refcount_dec(&resync->refcnt);
+	dma_unmap_single(dev, buf->dma_addr, PROGRESS_PARAMS_PADDED_SIZE, DMA_FROM_DEVICE);
 	kfree(buf);
 }
 
@@ -659,7 +660,7 @@ void mlx5e_ktls_del_rx(struct net_device *netdev, struct tls_context *tls_ctx)
 	priv_rx = mlx5e_get_ktls_rx_priv_ctx(tls_ctx);
 	set_bit(MLX5E_PRIV_RX_FLAG_DELETING, priv_rx->flags);
 	mlx5e_set_ktls_rx_priv_ctx(tls_ctx, NULL);
-	napi_synchronize(&priv->channels.c[priv_rx->rxq]->napi);
+	synchronize_rcu(); /* Sync with NAPI */
 	if (!cancel_work_sync(&priv_rx->rule.work))
 		/* completion is needed, as the priv_rx in the add flow
 		 * is maintained on the wqe info (wi), not on the socket.
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
index f4861545b236..b140e13fdcc8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
@@ -345,9 +345,6 @@ void mlx5e_ktls_tx_handle_resync_dump_comp(struct mlx5e_txqsq *sq,
 	struct mlx5e_sq_stats *stats;
 	struct mlx5e_sq_dma *dma;
 
-	if (!wi->resync_dump_frag_page)
-		return;
-
 	dma = mlx5e_dma_get(sq, (*dma_fifo_cc)++);
 	stats = sq->stats;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_txrx.h
index ff4c740af10b..7521c9be735b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_txrx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_txrx.h
@@ -29,12 +29,24 @@ void mlx5e_ktls_handle_get_psv_completion(struct mlx5e_icosq_wqe_info *wi,
 void mlx5e_ktls_tx_handle_resync_dump_comp(struct mlx5e_txqsq *sq,
 					   struct mlx5e_tx_wqe_info *wi,
 					   u32 *dma_fifo_cc);
+static inline bool
+mlx5e_ktls_tx_try_handle_resync_dump_comp(struct mlx5e_txqsq *sq,
+					  struct mlx5e_tx_wqe_info *wi,
+					  u32 *dma_fifo_cc)
+{
+	if (unlikely(wi->resync_dump_frag_page)) {
+		mlx5e_ktls_tx_handle_resync_dump_comp(sq, wi, dma_fifo_cc);
+		return true;
+	}
+	return false;
+}
 #else
-static inline void
-mlx5e_ktls_tx_handle_resync_dump_comp(struct mlx5e_txqsq *sq,
-				      struct mlx5e_tx_wqe_info *wi,
-				      u32 *dma_fifo_cc)
+static inline bool
+mlx5e_ktls_tx_try_handle_resync_dump_comp(struct mlx5e_txqsq *sq,
+					  struct mlx5e_tx_wqe_info *wi,
+					  u32 *dma_fifo_cc)
 {
+	return false;
 }
 
 #endif /* CONFIG_MLX5_EN_TLS */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c
index b0c31d49ff8d..6982b193ee8a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c
@@ -189,12 +189,10 @@ static bool mlx5e_tls_handle_ooo(struct mlx5e_tls_offload_context_tx *context,
 				 struct mlx5e_tls *tls)
 {
 	u32 tcp_seq = ntohl(tcp_hdr(skb)->seq);
-	struct mlx5e_tx_wqe *wqe;
 	struct sync_info info;
 	struct sk_buff *nskb;
 	int linear_len = 0;
 	int headln;
-	u16 pi;
 	int i;
 
 	sq->stats->tls_ooo++;
@@ -246,9 +244,7 @@ static bool mlx5e_tls_handle_ooo(struct mlx5e_tls_offload_context_tx *context,
 	sq->stats->tls_resync_bytes += nskb->len;
 	mlx5e_tls_complete_sync_skb(skb, nskb, tcp_seq, headln,
 				    cpu_to_be64(info.rcd_sn));
-	pi = mlx5_wq_cyc_ctr2ix(&sq->wq, sq->pc);
-	wqe = MLX5E_TX_FETCH_WQE(sq, pi);
-	mlx5e_sq_xmit(sq, nskb, wqe, pi, true);
+	mlx5e_sq_xmit_simple(sq, nskb, true);
 
 	return true;
 
@@ -274,6 +270,8 @@ bool mlx5e_tls_handle_tx_skb(struct net_device *netdev, struct mlx5e_txqsq *sq,
 	if (!datalen)
 		return true;
 
+	mlx5e_tx_mpwqe_ensure_complete(sq);
+
 	tls_ctx = tls_get_ctx(skb->sk);
 	if (WARN_ON_ONCE(tls_ctx->netdev != netdev))
 		goto err_out;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c
index 01468ec27446..b949b9a7538b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c
@@ -35,7 +35,6 @@
 #include <net/sock.h>
 
 #include "en.h"
-#include "accel/tls.h"
 #include "fpga/sdk.h"
 #include "en_accel/tls.h"
 
@@ -51,9 +50,14 @@ static const struct counter_desc mlx5e_tls_sw_stats_desc[] = {
 
 #define NUM_TLS_SW_COUNTERS ARRAY_SIZE(mlx5e_tls_sw_stats_desc)
 
+static bool is_tls_atomic_stats(struct mlx5e_priv *priv)
+{
+	return priv->tls && !mlx5_accel_is_ktls_device(priv->mdev);
+}
+
 int mlx5e_tls_get_count(struct mlx5e_priv *priv)
 {
-	if (!priv->tls)
+	if (!is_tls_atomic_stats(priv))
 		return 0;
 
 	return NUM_TLS_SW_COUNTERS;
@@ -63,7 +67,7 @@ int mlx5e_tls_get_strings(struct mlx5e_priv *priv, uint8_t *data)
 {
 	unsigned int i, idx = 0;
 
-	if (!priv->tls)
+	if (!is_tls_atomic_stats(priv))
 		return 0;
 
 	for (i = 0; i < NUM_TLS_SW_COUNTERS; i++)
@@ -77,7 +81,7 @@ int mlx5e_tls_get_stats(struct mlx5e_priv *priv, u64 *data)
 {
 	int i, idx = 0;
 
-	if (!priv->tls)
+	if (!is_tls_atomic_stats(priv))
 		return 0;
 
 	for (i = 0; i < NUM_TLS_SW_COUNTERS; i++)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 0dda80d8bdca..d25a56ec6876 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -1908,7 +1908,7 @@ static int set_pflag_rx_no_csum_complete(struct net_device *netdev, bool enable)
 	return 0;
 }
 
-static int set_pflag_xdp_tx_mpwqe(struct net_device *netdev, bool enable)
+static int set_pflag_tx_mpwqe_common(struct net_device *netdev, u32 flag, bool enable)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct mlx5_core_dev *mdev = priv->mdev;
@@ -1920,7 +1920,7 @@ static int set_pflag_xdp_tx_mpwqe(struct net_device *netdev, bool enable)
 
 	new_channels.params = priv->channels.params;
 
-	MLX5E_SET_PFLAG(&new_channels.params, MLX5E_PFLAG_XDP_TX_MPWQE, enable);
+	MLX5E_SET_PFLAG(&new_channels.params, flag, enable);
 
 	if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
 		priv->channels.params = new_channels.params;
@@ -1931,6 +1931,16 @@ static int set_pflag_xdp_tx_mpwqe(struct net_device *netdev, bool enable)
 	return err;
 }
 
+static int set_pflag_xdp_tx_mpwqe(struct net_device *netdev, bool enable)
+{
+	return set_pflag_tx_mpwqe_common(netdev, MLX5E_PFLAG_XDP_TX_MPWQE, enable);
+}
+
+static int set_pflag_skb_tx_mpwqe(struct net_device *netdev, bool enable)
+{
+	return set_pflag_tx_mpwqe_common(netdev, MLX5E_PFLAG_SKB_TX_MPWQE, enable);
+}
+
 static const struct pflag_desc mlx5e_priv_flags[MLX5E_NUM_PFLAGS] = {
 	{ "rx_cqe_moder",        set_pflag_rx_cqe_based_moder },
 	{ "tx_cqe_moder",        set_pflag_tx_cqe_based_moder },
@@ -1938,6 +1948,7 @@ static const struct pflag_desc mlx5e_priv_flags[MLX5E_NUM_PFLAGS] = {
 	{ "rx_striding_rq",      set_pflag_rx_striding_rq },
 	{ "rx_no_csum_complete", set_pflag_rx_no_csum_complete },
 	{ "xdp_tx_mpwqe",        set_pflag_xdp_tx_mpwqe },
+	{ "skb_tx_mpwqe",        set_pflag_skb_tx_mpwqe },
 };
 
 static int mlx5e_handle_pflag(struct net_device *netdev,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index b057a6c3a6d5..2c3c594a8621 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -158,16 +158,6 @@ static void mlx5e_update_carrier_work(struct work_struct *work)
 	mutex_unlock(&priv->state_lock);
 }
 
-void mlx5e_update_ndo_stats(struct mlx5e_priv *priv)
-{
-	int i;
-
-	for (i = mlx5e_nic_stats_grps_num(priv) - 1; i >= 0; i--)
-		if (mlx5e_nic_stats_grps[i]->update_stats_mask &
-		    MLX5E_NDO_UPDATE_STATS)
-			mlx5e_nic_stats_grps[i]->update_stats(priv);
-}
-
 static void mlx5e_update_stats_work(struct work_struct *work)
 {
 	struct mlx5e_priv *priv = container_of(work, struct mlx5e_priv,
@@ -399,7 +389,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 
 	if (params->xdp_prog)
 		bpf_prog_inc(params->xdp_prog);
-	rq->xdp_prog = params->xdp_prog;
+	RCU_INIT_POINTER(rq->xdp_prog, params->xdp_prog);
 
 	rq_xdp_ix = rq->ix;
 	if (xsk)
@@ -408,7 +398,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 	if (err < 0)
 		goto err_rq_wq_destroy;
 
-	rq->buff.map_dir = rq->xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE;
+	rq->buff.map_dir = params->xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE;
 	rq->buff.headroom = mlx5e_get_rq_headroom(mdev, params, xsk);
 	pool_size = 1 << params->log_rq_mtu_frames;
 
@@ -564,8 +554,8 @@ err_free:
 	}
 
 err_rq_wq_destroy:
-	if (rq->xdp_prog)
-		bpf_prog_put(rq->xdp_prog);
+	if (params->xdp_prog)
+		bpf_prog_put(params->xdp_prog);
 	xdp_rxq_info_unreg(&rq->xdp_rxq);
 	page_pool_destroy(rq->page_pool);
 	mlx5_wq_destroy(&rq->wq_ctrl);
@@ -575,10 +565,16 @@ err_rq_wq_destroy:
 
 static void mlx5e_free_rq(struct mlx5e_rq *rq)
 {
+	struct mlx5e_channel *c = rq->channel;
+	struct bpf_prog *old_prog = NULL;
 	int i;
 
-	if (rq->xdp_prog)
-		bpf_prog_put(rq->xdp_prog);
+	/* drop_rq has neither channel nor xdp_prog. */
+	if (c)
+		old_prog = rcu_dereference_protected(rq->xdp_prog,
+						     lockdep_is_held(&c->priv->state_lock));
+	if (old_prog)
+		bpf_prog_put(old_prog);
 
 	switch (rq->wq_type) {
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
@@ -874,7 +870,7 @@ void mlx5e_activate_rq(struct mlx5e_rq *rq)
 void mlx5e_deactivate_rq(struct mlx5e_rq *rq)
 {
 	clear_bit(MLX5E_RQ_STATE_ENABLED, &rq->state);
-	napi_synchronize(&rq->channel->napi); /* prevent mlx5e_post_rx_wqes */
+	synchronize_rcu(); /* Sync with NAPI to prevent mlx5e_post_rx_wqes. */
 }
 
 void mlx5e_close_rq(struct mlx5e_rq *rq)
@@ -1047,6 +1043,7 @@ static void mlx5e_free_icosq(struct mlx5e_icosq *sq)
 static void mlx5e_free_txqsq_db(struct mlx5e_txqsq *sq)
 {
 	kvfree(sq->db.wqe_info);
+	kvfree(sq->db.skb_fifo);
 	kvfree(sq->db.dma_fifo);
 }
 
@@ -1058,15 +1055,19 @@ static int mlx5e_alloc_txqsq_db(struct mlx5e_txqsq *sq, int numa)
 	sq->db.dma_fifo = kvzalloc_node(array_size(df_sz,
 						   sizeof(*sq->db.dma_fifo)),
 					GFP_KERNEL, numa);
+	sq->db.skb_fifo = kvzalloc_node(array_size(df_sz,
+						   sizeof(*sq->db.skb_fifo)),
+					GFP_KERNEL, numa);
 	sq->db.wqe_info = kvzalloc_node(array_size(wq_sz,
 						   sizeof(*sq->db.wqe_info)),
 					GFP_KERNEL, numa);
-	if (!sq->db.dma_fifo || !sq->db.wqe_info) {
+	if (!sq->db.dma_fifo || !sq->db.skb_fifo || !sq->db.wqe_info) {
 		mlx5e_free_txqsq_db(sq);
 		return -ENOMEM;
 	}
 
 	sq->dma_fifo_mask = df_sz - 1;
+	sq->skb_fifo_mask = df_sz - 1;
 
 	return 0;
 }
@@ -1077,6 +1078,12 @@ static int mlx5e_calc_sq_stop_room(struct mlx5e_txqsq *sq, u8 log_sq_size)
 
 	sq->stop_room  = mlx5e_tls_get_stop_room(sq);
 	sq->stop_room += mlx5e_stop_room_for_wqe(MLX5_SEND_WQE_MAX_WQEBBS);
+	if (test_bit(MLX5E_SQ_STATE_MPWQE, &sq->state))
+		/* A MPWQE can take up to the maximum-sized WQE + all the normal
+		 * stop room can be taken if a new packet breaks the active
+		 * MPWQE session and allocates its WQEs right away.
+		 */
+		sq->stop_room += mlx5e_stop_room_for_wqe(MLX5_SEND_WQE_MAX_WQEBBS);
 
 	if (WARN_ON(sq->stop_room >= sq_size)) {
 		netdev_err(sq->channel->netdev, "Stop room %hu is bigger than the SQ size %d\n",
@@ -1118,6 +1125,8 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c,
 		set_bit(MLX5E_SQ_STATE_IPSEC, &sq->state);
 	if (mlx5_accel_is_tls_device(c->priv->mdev))
 		set_bit(MLX5E_SQ_STATE_TLS, &sq->state);
+	if (param->is_mpw)
+		set_bit(MLX5E_SQ_STATE_MPWQE, &sq->state);
 	err = mlx5e_calc_sq_stop_room(sq, params->log_sq_size);
 	if (err)
 		return err;
@@ -1319,12 +1328,10 @@ void mlx5e_tx_disable_queue(struct netdev_queue *txq)
 
 static void mlx5e_deactivate_txqsq(struct mlx5e_txqsq *sq)
 {
-	struct mlx5e_channel *c = sq->channel;
 	struct mlx5_wq_cyc *wq = &sq->wq;
 
 	clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
-	/* prevent netif_tx_wake_queue */
-	napi_synchronize(&c->napi);
+	synchronize_rcu(); /* Sync with NAPI to prevent netif_tx_wake_queue. */
 
 	mlx5e_tx_disable_queue(sq->txq);
 
@@ -1399,10 +1406,8 @@ void mlx5e_activate_icosq(struct mlx5e_icosq *icosq)
 
 void mlx5e_deactivate_icosq(struct mlx5e_icosq *icosq)
 {
-	struct mlx5e_channel *c = icosq->channel;
-
 	clear_bit(MLX5E_SQ_STATE_ENABLED, &icosq->state);
-	napi_synchronize(&c->napi);
+	synchronize_rcu(); /* Sync with NAPI. */
 }
 
 void mlx5e_close_icosq(struct mlx5e_icosq *sq)
@@ -1481,7 +1486,7 @@ void mlx5e_close_xdpsq(struct mlx5e_xdpsq *sq)
 	struct mlx5e_channel *c = sq->channel;
 
 	clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
-	napi_synchronize(&c->napi);
+	synchronize_rcu(); /* Sync with NAPI. */
 
 	mlx5e_destroy_sq(c->mdev, sq->sqn);
 	mlx5e_free_xdpsq_descs(sq);
@@ -1938,7 +1943,7 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 	c->tstamp   = &priv->tstamp;
 	c->ix       = ix;
 	c->cpu      = cpu;
-	c->pdev     = priv->mdev->device;
+	c->pdev     = mlx5_core_dma_dev(priv->mdev);
 	c->netdev   = priv->netdev;
 	c->mkey_be  = cpu_to_be32(priv->mdev->mlx5e_res.mkey.key);
 	c->num_tc   = params->num_tc;
@@ -2126,7 +2131,7 @@ void mlx5e_build_rq_param(struct mlx5e_priv *priv,
 	MLX5_SET(rqc, rqc, vsd,            params->vlan_strip_disable);
 	MLX5_SET(rqc, rqc, scatter_fcs,    params->scatter_fcs_en);
 
-	param->wq.buf_numa_node = dev_to_node(mdev->device);
+	param->wq.buf_numa_node = dev_to_node(mlx5_core_dma_dev(mdev));
 	mlx5e_build_rx_cq_param(priv, params, xsk, &param->cqp);
 }
 
@@ -2142,7 +2147,7 @@ static void mlx5e_build_drop_rq_param(struct mlx5e_priv *priv,
 		 mlx5e_get_rqwq_log_stride(MLX5_WQ_TYPE_CYCLIC, 1));
 	MLX5_SET(rqc, rqc, counter_set_id, priv->drop_rq_q_counter);
 
-	param->wq.buf_numa_node = dev_to_node(mdev->device);
+	param->wq.buf_numa_node = dev_to_node(mlx5_core_dma_dev(mdev));
 }
 
 void mlx5e_build_sq_param_common(struct mlx5e_priv *priv,
@@ -2154,7 +2159,7 @@ void mlx5e_build_sq_param_common(struct mlx5e_priv *priv,
 	MLX5_SET(wq, wq, log_wq_stride, ilog2(MLX5_SEND_WQE_BB));
 	MLX5_SET(wq, wq, pd,            priv->mdev->mlx5e_res.pdn);
 
-	param->wq.buf_numa_node = dev_to_node(priv->mdev->device);
+	param->wq.buf_numa_node = dev_to_node(mlx5_core_dma_dev(priv->mdev));
 }
 
 static void mlx5e_build_sq_param(struct mlx5e_priv *priv,
@@ -2170,6 +2175,7 @@ static void mlx5e_build_sq_param(struct mlx5e_priv *priv,
 	mlx5e_build_sq_param_common(priv, param);
 	MLX5_SET(wq, wq, log_wq_sz, params->log_sq_size);
 	MLX5_SET(sqc, sqc, allow_swp, allow_swp);
+	param->is_mpw = MLX5E_GET_PFLAG(params, MLX5E_PFLAG_SKB_TX_MPWQE);
 	mlx5e_build_tx_cq_param(priv, params, &param->cqp);
 }
 
@@ -3191,8 +3197,8 @@ static int mlx5e_alloc_drop_cq(struct mlx5_core_dev *mdev,
 			       struct mlx5e_cq *cq,
 			       struct mlx5e_cq_param *param)
 {
-	param->wq.buf_numa_node = dev_to_node(mdev->device);
-	param->wq.db_numa_node  = dev_to_node(mdev->device);
+	param->wq.buf_numa_node = dev_to_node(mlx5_core_dma_dev(mdev));
+	param->wq.db_numa_node  = dev_to_node(mlx5_core_dma_dev(mdev));
 
 	return mlx5e_alloc_cq_common(mdev, param, cq);
 }
@@ -3577,6 +3583,7 @@ void mlx5e_fold_sw_stats64(struct mlx5e_priv *priv, struct rtnl_link_stats64 *s)
 
 		s->rx_packets   += rq_stats->packets + xskrq_stats->packets;
 		s->rx_bytes     += rq_stats->bytes + xskrq_stats->bytes;
+		s->multicast    += rq_stats->mcast_packets + xskrq_stats->mcast_packets;
 
 		for (j = 0; j < priv->max_opened_tc; j++) {
 			struct mlx5e_sq_stats *sq_stats = &channel_stats->sq[j];
@@ -3592,7 +3599,6 @@ void
 mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
-	struct mlx5e_vport_stats *vstats = &priv->stats.vport;
 	struct mlx5e_pport_stats *pstats = &priv->stats.pport;
 
 	/* In switchdev mode, monitor counters doesn't monitor
@@ -3627,12 +3633,6 @@ mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
 	stats->rx_errors = stats->rx_length_errors + stats->rx_crc_errors +
 			   stats->rx_frame_errors;
 	stats->tx_errors = stats->tx_aborted_errors + stats->tx_carrier_errors;
-
-	/* vport multicast also counts packets that are dropped due to steering
-	 * or rx out of buffer
-	 */
-	stats->multicast =
-		VPORT_COUNTER_GET(vstats, received_eth_multicast.packets);
 }
 
 static void mlx5e_set_rx_mode(struct net_device *dev)
@@ -4341,6 +4341,16 @@ static int mlx5e_xdp_allowed(struct mlx5e_priv *priv, struct bpf_prog *prog)
 	return 0;
 }
 
+static void mlx5e_rq_replace_xdp_prog(struct mlx5e_rq *rq, struct bpf_prog *prog)
+{
+	struct bpf_prog *old_prog;
+
+	old_prog = rcu_replace_pointer(rq->xdp_prog, prog,
+				       lockdep_is_held(&rq->channel->priv->state_lock));
+	if (old_prog)
+		bpf_prog_put(old_prog);
+}
+
 static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
@@ -4399,29 +4409,10 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog)
 	 */
 	for (i = 0; i < priv->channels.num; i++) {
 		struct mlx5e_channel *c = priv->channels.c[i];
-		bool xsk_open = test_bit(MLX5E_CHANNEL_STATE_XSK, c->state);
-
-		clear_bit(MLX5E_RQ_STATE_ENABLED, &c->rq.state);
-		if (xsk_open)
-			clear_bit(MLX5E_RQ_STATE_ENABLED, &c->xskrq.state);
-		napi_synchronize(&c->napi);
-		/* prevent mlx5e_poll_rx_cq from accessing rq->xdp_prog */
-
-		old_prog = xchg(&c->rq.xdp_prog, prog);
-		if (old_prog)
-			bpf_prog_put(old_prog);
-
-		if (xsk_open) {
-			old_prog = xchg(&c->xskrq.xdp_prog, prog);
-			if (old_prog)
-				bpf_prog_put(old_prog);
-		}
 
-		set_bit(MLX5E_RQ_STATE_ENABLED, &c->rq.state);
-		if (xsk_open)
-			set_bit(MLX5E_RQ_STATE_ENABLED, &c->xskrq.state);
-		/* napi_schedule in case we have missed anything */
-		napi_schedule(&c->napi);
+		mlx5e_rq_replace_xdp_prog(&c->rq, prog);
+		if (test_bit(MLX5E_CHANNEL_STATE_XSK, c->state))
+			mlx5e_rq_replace_xdp_prog(&c->xskrq, prog);
 	}
 
 unlock:
@@ -4726,6 +4717,8 @@ void mlx5e_build_nic_params(struct mlx5e_priv *priv,
 	params->log_sq_size = is_kdump_kernel() ?
 		MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE :
 		MLX5E_PARAMS_DEFAULT_LOG_SQ_SIZE;
+	MLX5E_SET_PFLAG(params, MLX5E_PFLAG_SKB_TX_MPWQE,
+			MLX5_CAP_ETH(mdev, enhanced_multi_pkt_send_wqe));
 
 	/* XDP SQ */
 	MLX5E_SET_PFLAG(params, MLX5E_PFLAG_XDP_TX_MPWQE,
@@ -5211,7 +5204,7 @@ static const struct mlx5e_profile mlx5e_nic_profile = {
 	.enable		   = mlx5e_nic_enable,
 	.disable	   = mlx5e_nic_disable,
 	.update_rx	   = mlx5e_update_nic_rx,
-	.update_stats	   = mlx5e_update_ndo_stats,
+	.update_stats	   = mlx5e_stats_update_ndo_stats,
 	.update_carrier	   = mlx5e_update_carrier,
 	.rx_handlers       = &mlx5e_rx_handlers_nic,
 	.max_tc		   = MLX5E_MAX_NUM_TC,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 110addbb8992..67247c33b9fd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -39,7 +39,6 @@
 #include <net/ipv6_stubs.h>
 
 #include "eswitch.h"
-#include "esw/chains.h"
 #include "en.h"
 #include "en_rep.h"
 #include "en/txrx.h"
@@ -375,19 +374,6 @@ static const struct ethtool_ops mlx5e_uplink_rep_ethtool_ops = {
 	.set_pauseparam    = mlx5e_uplink_rep_set_pauseparam,
 };
 
-static void mlx5e_rep_get_port_parent_id(struct net_device *dev,
-					 struct netdev_phys_item_id *ppid)
-{
-	struct mlx5e_priv *priv;
-	u64 parent_id;
-
-	priv = netdev_priv(dev);
-
-	parent_id = mlx5_query_nic_system_image_guid(priv->mdev);
-	ppid->id_len = sizeof(parent_id);
-	memcpy(ppid->id, &parent_id, sizeof(parent_id));
-}
-
 static void mlx5e_sqs2vport_stop(struct mlx5_eswitch *esw,
 				 struct mlx5_eswitch_rep *rep)
 {
@@ -612,12 +598,13 @@ static int mlx5e_uplink_rep_set_vf_vlan(struct net_device *dev, int vf, u16 vlan
 	return 0;
 }
 
-static struct devlink_port *mlx5e_rep_get_devlink_port(struct net_device *dev)
+static struct devlink_port *mlx5e_rep_get_devlink_port(struct net_device *netdev)
 {
-	struct mlx5e_priv *priv = netdev_priv(dev);
+	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+	struct mlx5_core_dev *dev = priv->mdev;
 
-	return &rpriv->dl_port;
+	return mlx5_esw_offloads_devlink_port(dev->priv.eswitch, rpriv->rep->vport);
 }
 
 static int mlx5e_rep_change_carrier(struct net_device *dev, bool new_carrier)
@@ -1180,7 +1167,7 @@ static const struct mlx5e_profile mlx5e_rep_profile = {
 	.cleanup_tx		= mlx5e_cleanup_rep_tx,
 	.enable		        = mlx5e_rep_enable,
 	.update_rx		= mlx5e_update_rep_rx,
-	.update_stats           = mlx5e_update_ndo_stats,
+	.update_stats           = mlx5e_stats_update_ndo_stats,
 	.rx_handlers            = &mlx5e_rx_handlers_rep,
 	.max_tc			= 1,
 	.rq_groups		= MLX5E_NUM_RQ_GROUPS(REGULAR),
@@ -1198,7 +1185,7 @@ static const struct mlx5e_profile mlx5e_uplink_rep_profile = {
 	.enable		        = mlx5e_uplink_rep_enable,
 	.disable	        = mlx5e_uplink_rep_disable,
 	.update_rx		= mlx5e_update_rep_rx,
-	.update_stats           = mlx5e_update_ndo_stats,
+	.update_stats           = mlx5e_stats_update_ndo_stats,
 	.update_carrier	        = mlx5e_update_carrier,
 	.rx_handlers            = &mlx5e_rx_handlers_rep,
 	.max_tc			= MLX5E_MAX_NUM_TC,
@@ -1207,70 +1194,13 @@ static const struct mlx5e_profile mlx5e_uplink_rep_profile = {
 	.stats_grps_num		= mlx5e_ul_rep_stats_grps_num,
 };
 
-static bool
-is_devlink_port_supported(const struct mlx5_core_dev *dev,
-			  const struct mlx5e_rep_priv *rpriv)
-{
-	return rpriv->rep->vport == MLX5_VPORT_UPLINK ||
-	       rpriv->rep->vport == MLX5_VPORT_PF ||
-	       mlx5_eswitch_is_vf_vport(dev->priv.eswitch, rpriv->rep->vport);
-}
-
-static int register_devlink_port(struct mlx5_core_dev *dev,
-				 struct mlx5e_rep_priv *rpriv)
-{
-	struct mlx5_esw_offload *offloads = &dev->priv.eswitch->offloads;
-	struct devlink *devlink = priv_to_devlink(dev);
-	struct mlx5_eswitch_rep *rep = rpriv->rep;
-	struct devlink_port_attrs attrs = {};
-	struct netdev_phys_item_id ppid = {};
-	unsigned int dl_port_index = 0;
-	u32 controller_num = 0;
-	bool external;
-	u16 pfnum;
-
-	if (!is_devlink_port_supported(dev, rpriv))
-		return 0;
-
-	external = mlx5_core_is_ecpf_esw_manager(dev);
-	if (external)
-		controller_num = offloads->host_number + 1;
-	mlx5e_rep_get_port_parent_id(rpriv->netdev, &ppid);
-	dl_port_index = mlx5_esw_vport_to_devlink_port_index(dev, rep->vport);
-	pfnum = PCI_FUNC(dev->pdev->devfn);
-	if (rep->vport == MLX5_VPORT_UPLINK) {
-		attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL;
-		attrs.phys.port_number = pfnum;
-		memcpy(attrs.switch_id.id, &ppid.id[0], ppid.id_len);
-		attrs.switch_id.id_len = ppid.id_len;
-		devlink_port_attrs_set(&rpriv->dl_port, &attrs);
-	} else if (rep->vport == MLX5_VPORT_PF) {
-		memcpy(rpriv->dl_port.attrs.switch_id.id, &ppid.id[0], ppid.id_len);
-		rpriv->dl_port.attrs.switch_id.id_len = ppid.id_len;
-		devlink_port_attrs_pci_pf_set(&rpriv->dl_port, controller_num,
-					      pfnum, external);
-	} else if (mlx5_eswitch_is_vf_vport(dev->priv.eswitch, rpriv->rep->vport)) {
-		memcpy(rpriv->dl_port.attrs.switch_id.id, &ppid.id[0], ppid.id_len);
-		rpriv->dl_port.attrs.switch_id.id_len = ppid.id_len;
-		devlink_port_attrs_pci_vf_set(&rpriv->dl_port, controller_num,
-					      pfnum, rep->vport - 1, external);
-	}
-	return devlink_port_register(devlink, &rpriv->dl_port, dl_port_index);
-}
-
-static void unregister_devlink_port(struct mlx5_core_dev *dev,
-				    struct mlx5e_rep_priv *rpriv)
-{
-	if (is_devlink_port_supported(dev, rpriv))
-		devlink_port_unregister(&rpriv->dl_port);
-}
-
 /* e-Switch vport representors */
 static int
 mlx5e_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
 {
 	const struct mlx5e_profile *profile;
 	struct mlx5e_rep_priv *rpriv;
+	struct devlink_port *dl_port;
 	struct net_device *netdev;
 	int nch, err;
 
@@ -1320,28 +1250,19 @@ mlx5e_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
 		goto err_detach_netdev;
 	}
 
-	err = register_devlink_port(dev, rpriv);
-	if (err) {
-		netdev_warn(netdev, "Failed to register devlink port %d\n",
-			    rep->vport);
-		goto err_neigh_cleanup;
-	}
-
 	err = register_netdev(netdev);
 	if (err) {
 		netdev_warn(netdev,
 			    "Failed to register representor netdev for vport %d\n",
 			    rep->vport);
-		goto err_devlink_cleanup;
+		goto err_neigh_cleanup;
 	}
 
-	if (is_devlink_port_supported(dev, rpriv))
-		devlink_port_type_eth_set(&rpriv->dl_port, netdev);
+	dl_port = mlx5_esw_offloads_devlink_port(dev->priv.eswitch, rpriv->rep->vport);
+	if (dl_port)
+		devlink_port_type_eth_set(dl_port, netdev);
 	return 0;
 
-err_devlink_cleanup:
-	unregister_devlink_port(dev, rpriv);
-
 err_neigh_cleanup:
 	mlx5e_rep_neigh_cleanup(rpriv);
 
@@ -1365,12 +1286,13 @@ mlx5e_vport_rep_unload(struct mlx5_eswitch_rep *rep)
 	struct net_device *netdev = rpriv->netdev;
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct mlx5_core_dev *dev = priv->mdev;
+	struct devlink_port *dl_port;
 	void *ppriv = priv->ppriv;
 
-	if (is_devlink_port_supported(dev, rpriv))
-		devlink_port_type_clear(&rpriv->dl_port);
+	dl_port = mlx5_esw_offloads_devlink_port(dev->priv.eswitch, rpriv->rep->vport);
+	if (dl_port)
+		devlink_port_type_clear(dl_port);
 	unregister_netdev(netdev);
-	unregister_devlink_port(dev, rpriv);
 	mlx5e_rep_neigh_cleanup(rpriv);
 	mlx5e_detach_netdev(priv);
 	if (rep->vport == MLX5_VPORT_UPLINK)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
index 622c27ae4ac7..8054d92ae37e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
@@ -101,7 +101,6 @@ struct mlx5e_rep_priv {
 	struct list_head       vport_sqs_list;
 	struct mlx5_rep_uplink_priv uplink_priv; /* valid for uplink rep */
 	struct rtnl_link_stats64 prev_vf_vport_stats;
-	struct devlink_port dl_port;
 };
 
 static inline
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index c9c82b14060a..599f5b5ebc97 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -52,6 +52,7 @@
 #include "en/xsk/rx.h"
 #include "en/health.h"
 #include "en/params.h"
+#include "en/txrx.h"
 
 static struct sk_buff *
 mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
@@ -1088,6 +1089,9 @@ static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe,
 		mlx5e_enable_ecn(rq, skb);
 
 	skb->protocol = eth_type_trans(skb, netdev);
+
+	if (unlikely(mlx5e_skb_is_multicast(skb)))
+		stats->mcast_packets++;
 }
 
 static inline void mlx5e_complete_rx_cqe(struct mlx5e_rq *rq,
@@ -1140,7 +1144,6 @@ mlx5e_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
 	struct xdp_buff xdp;
 	struct sk_buff *skb;
 	void *va, *data;
-	bool consumed;
 	u32 frag_size;
 
 	va             = page_address(di->page) + wi->offset;
@@ -1152,11 +1155,8 @@ mlx5e_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
 	net_prefetchw(va); /* xdp_frame data area */
 	net_prefetch(data);
 
-	rcu_read_lock();
 	mlx5e_fill_xdp_buff(rq, va, rx_headroom, cqe_bcnt, &xdp);
-	consumed = mlx5e_xdp_handle(rq, di, &cqe_bcnt, &xdp);
-	rcu_read_unlock();
-	if (consumed)
+	if (mlx5e_xdp_handle(rq, di, &cqe_bcnt, &xdp))
 		return NULL; /* page/packet was consumed by XDP */
 
 	rx_headroom = xdp.data - xdp.data_hard_start;
@@ -1260,6 +1260,11 @@ static void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 	}
 
 	mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb);
+
+	if (mlx5e_cqe_regb_chain(cqe))
+		if (!mlx5e_tc_update_skb(cqe, skb))
+			goto free_wqe;
+
 	napi_gro_receive(rq->cq.napi, skb);
 
 free_wqe:
@@ -1446,7 +1451,6 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
 	struct sk_buff *skb;
 	void *va, *data;
 	u32 frag_size;
-	bool consumed;
 
 	/* Check packet size. Note LRO doesn't use linear SKB */
 	if (unlikely(cqe_bcnt > rq->hw_mtu)) {
@@ -1463,11 +1467,8 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
 	net_prefetchw(va); /* xdp_frame data area */
 	net_prefetch(data);
 
-	rcu_read_lock();
 	mlx5e_fill_xdp_buff(rq, va, rx_headroom, cqe_bcnt32, &xdp);
-	consumed = mlx5e_xdp_handle(rq, di, &cqe_bcnt32, &xdp);
-	rcu_read_unlock();
-	if (consumed) {
+	if (mlx5e_xdp_handle(rq, di, &cqe_bcnt32, &xdp)) {
 		if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags))
 			__set_bit(page_idx, wi->xdp_xmit_bitmap); /* non-atomic */
 		return NULL; /* page/packet was consumed by XDP */
@@ -1525,6 +1526,11 @@ static void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cq
 		goto mpwrq_cqe_out;
 
 	mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb);
+
+	if (mlx5e_cqe_regb_chain(cqe))
+		if (!mlx5e_tc_update_skb(cqe, skb))
+			goto mpwrq_cqe_out;
+
 	napi_gro_receive(rq->cq.napi, skb);
 
 mpwrq_cqe_out:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index 6d5e54b964c0..78f6a6f0a7e0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -54,6 +54,18 @@ unsigned int mlx5e_stats_total_num(struct mlx5e_priv *priv)
 	return total;
 }
 
+void mlx5e_stats_update_ndo_stats(struct mlx5e_priv *priv)
+{
+	mlx5e_stats_grp_t *stats_grps = priv->profile->stats_grps;
+	const unsigned int num_stats_grps = stats_grps_num(priv);
+	int i;
+
+	for (i = num_stats_grps - 1; i >= 0; i--)
+		if (stats_grps[i]->update_stats &&
+		    stats_grps[i]->update_stats_mask & MLX5E_NDO_UPDATE_STATS)
+			stats_grps[i]->update_stats(priv);
+}
+
 void mlx5e_stats_update(struct mlx5e_priv *priv)
 {
 	mlx5e_stats_grp_t *stats_grps = priv->profile->stats_grps;
@@ -98,6 +110,8 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tso_inner_bytes) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_added_vlan_packets) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_nop) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_mpwqe_blks) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_mpwqe_pkts) },
 
 #ifdef CONFIG_MLX5_EN_TLS
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_encrypted_packets) },
@@ -353,6 +367,8 @@ static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(sw)
 			s->tx_tso_inner_bytes	+= sq_stats->tso_inner_bytes;
 			s->tx_added_vlan_packets += sq_stats->added_vlan_packets;
 			s->tx_nop               += sq_stats->nop;
+			s->tx_mpwqe_blks        += sq_stats->mpwqe_blks;
+			s->tx_mpwqe_pkts        += sq_stats->mpwqe_pkts;
 			s->tx_queue_stopped	+= sq_stats->stopped;
 			s->tx_queue_wake	+= sq_stats->wake;
 			s->tx_queue_dropped	+= sq_stats->dropped;
@@ -1556,6 +1572,8 @@ static const struct counter_desc sq_stats_desc[] = {
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, csum_partial_inner) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, added_vlan_packets) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, nop) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, mpwqe_blks) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, mpwqe_pkts) },
 #ifdef CONFIG_MLX5_EN_TLS
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_encrypted_packets) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_encrypted_bytes) },
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index 9d9ee269a041..162daaadb0d8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -103,6 +103,7 @@ unsigned int mlx5e_stats_total_num(struct mlx5e_priv *priv);
 void mlx5e_stats_update(struct mlx5e_priv *priv);
 void mlx5e_stats_fill(struct mlx5e_priv *priv, u64 *data, int idx);
 void mlx5e_stats_fill_strings(struct mlx5e_priv *priv, u8 *data);
+void mlx5e_stats_update_ndo_stats(struct mlx5e_priv *priv);
 
 void mlx5e_stats_pause_get(struct mlx5e_priv *priv,
 			   struct ethtool_pause_stats *pause_stats);
@@ -120,8 +121,11 @@ struct mlx5e_sw_stats {
 	u64 tx_tso_inner_bytes;
 	u64 tx_added_vlan_packets;
 	u64 tx_nop;
+	u64 tx_mpwqe_blks;
+	u64 tx_mpwqe_pkts;
 	u64 rx_lro_packets;
 	u64 rx_lro_bytes;
+	u64 rx_mcast_packets;
 	u64 rx_ecn_mark;
 	u64 rx_removed_vlan_packets;
 	u64 rx_csum_unnecessary;
@@ -301,6 +305,7 @@ struct mlx5e_rq_stats {
 	u64 csum_none;
 	u64 lro_packets;
 	u64 lro_bytes;
+	u64 mcast_packets;
 	u64 ecn_mark;
 	u64 removed_vlan_packets;
 	u64 xdp_drop;
@@ -348,6 +353,8 @@ struct mlx5e_sq_stats {
 	u64 csum_partial_inner;
 	u64 added_vlan_packets;
 	u64 nop;
+	u64 mpwqe_blks;
+	u64 mpwqe_pkts;
 #ifdef CONFIG_MLX5_EN_TLS
 	u64 tls_encrypted_packets;
 	u64 tls_encrypted_bytes;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 817c503693fc..a0c356987e1a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -57,7 +57,6 @@
 #include "en/rep/neigh.h"
 #include "en_tc.h"
 #include "eswitch.h"
-#include "esw/chains.h"
 #include "fs_core.h"
 #include "en/port.h"
 #include "en/tc_tun.h"
@@ -66,20 +65,11 @@
 #include "en/mod_hdr.h"
 #include "lib/devcom.h"
 #include "lib/geneve.h"
+#include "lib/fs_chains.h"
 #include "diag/en_tc_tracepoint.h"
 
+#define nic_chains(priv) ((priv)->fs.tc.chains)
 #define MLX5_MH_ACT_SZ MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)
-
-struct mlx5_nic_flow_attr {
-	u32 action;
-	u32 flow_tag;
-	struct mlx5_modify_hdr *modify_hdr;
-	u32 hairpin_tirn;
-	u8 match_level;
-	struct mlx5_flow_table	*hairpin_ft;
-	struct mlx5_fc		*counter;
-};
-
 #define MLX5E_TC_FLOW_BASE (MLX5E_TC_FLAG_LAST_EXPORTED_BIT + 1)
 
 enum {
@@ -153,11 +143,7 @@ struct mlx5e_tc_flow {
 	struct rcu_head		rcu_head;
 	struct completion	init_done;
 	int tunnel_id; /* the mapped tunnel id of this flow */
-
-	union {
-		struct mlx5_esw_flow_attr esw_attr[0];
-		struct mlx5_nic_flow_attr nic_attr[0];
-	};
+	struct mlx5_flow_attr *attr;
 };
 
 struct mlx5e_tc_flow_parse_attr {
@@ -170,7 +156,7 @@ struct mlx5e_tc_flow_parse_attr {
 };
 
 #define MLX5E_TC_TABLE_NUM_GROUPS 4
-#define MLX5E_TC_TABLE_MAX_GROUP_SIZE BIT(16)
+#define MLX5E_TC_TABLE_MAX_GROUP_SIZE BIT(18)
 
 struct mlx5e_tc_attr_to_reg_mapping mlx5e_tc_attr_to_reg_mappings[] = {
 	[CHAIN_TO_REG] = {
@@ -191,6 +177,16 @@ struct mlx5e_tc_attr_to_reg_mapping mlx5e_tc_attr_to_reg_mappings[] = {
 	[MARK_TO_REG] = mark_to_reg_ct,
 	[LABELS_TO_REG] = labels_to_reg_ct,
 	[FTEID_TO_REG] = fteid_to_reg_ct,
+	/* For NIC rules we store the retore metadata directly
+	 * into reg_b that is passed to SW since we don't
+	 * jump between steering domains.
+	 */
+	[NIC_CHAIN_TO_REG] = {
+		.mfield = MLX5_ACTION_IN_FIELD_METADATA_REG_B,
+		.moffset = 0,
+		.mlen = 2,
+	},
+	[NIC_ZONE_RESTORE_TO_REG] = nic_zone_restore_to_reg_ct,
 };
 
 static void mlx5e_put_flow_tunnel_id(struct mlx5e_tc_flow *flow);
@@ -244,6 +240,7 @@ mlx5e_tc_match_to_reg_get_match(struct mlx5_flow_spec *spec,
 int
 mlx5e_tc_match_to_reg_set(struct mlx5_core_dev *mdev,
 			  struct mlx5e_tc_mod_hdr_acts *mod_hdr_acts,
+			  enum mlx5_flow_namespace_type ns,
 			  enum mlx5e_tc_attr_to_reg type,
 			  u32 data)
 {
@@ -253,8 +250,7 @@ mlx5e_tc_match_to_reg_set(struct mlx5_core_dev *mdev,
 	char *modact;
 	int err;
 
-	err = alloc_mod_hdr_actions(mdev, MLX5_FLOW_NAMESPACE_FDB,
-				    mod_hdr_acts);
+	err = alloc_mod_hdr_actions(mdev, ns, mod_hdr_acts);
 	if (err)
 		return err;
 
@@ -275,6 +271,54 @@ mlx5e_tc_match_to_reg_set(struct mlx5_core_dev *mdev,
 	return 0;
 }
 
+#define esw_offloads_mode(esw) (mlx5_eswitch_mode(esw) == MLX5_ESWITCH_OFFLOADS)
+
+static struct mlx5_tc_ct_priv *
+get_ct_priv(struct mlx5e_priv *priv)
+{
+	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+	struct mlx5_rep_uplink_priv *uplink_priv;
+	struct mlx5e_rep_priv *uplink_rpriv;
+
+	if (esw_offloads_mode(esw)) {
+		uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH);
+		uplink_priv = &uplink_rpriv->uplink_priv;
+
+		return uplink_priv->ct_priv;
+	}
+
+	return priv->fs.tc.ct;
+}
+
+struct mlx5_flow_handle *
+mlx5_tc_rule_insert(struct mlx5e_priv *priv,
+		    struct mlx5_flow_spec *spec,
+		    struct mlx5_flow_attr *attr)
+{
+	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+
+	if (esw_offloads_mode(esw))
+		return mlx5_eswitch_add_offloaded_rule(esw, spec, attr);
+
+	return	mlx5e_add_offloaded_nic_rule(priv, spec, attr);
+}
+
+void
+mlx5_tc_rule_delete(struct mlx5e_priv *priv,
+		    struct mlx5_flow_handle *rule,
+		    struct mlx5_flow_attr *attr)
+{
+	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+
+	if (esw_offloads_mode(esw)) {
+		mlx5_eswitch_del_offloaded_rule(esw, rule, attr);
+
+		return;
+	}
+
+	mlx5e_del_offloaded_nic_rule(priv, rule, attr);
+}
+
 struct mlx5e_hairpin {
 	struct mlx5_hairpin *pair;
 
@@ -370,7 +414,7 @@ static bool __flow_flag_test(struct mlx5e_tc_flow *flow, unsigned long flag)
 #define flow_flag_test(flow, flag) __flow_flag_test(flow, \
 						    MLX5E_TC_FLOW_FLAG_##flag)
 
-static bool mlx5e_is_eswitch_flow(struct mlx5e_tc_flow *flow)
+bool mlx5e_is_eswitch_flow(struct mlx5e_tc_flow *flow)
 {
 	return flow_flag_test(flow, ESWITCH);
 }
@@ -415,10 +459,7 @@ static int mlx5e_attach_mod_hdr(struct mlx5e_priv *priv,
 		return PTR_ERR(mh);
 
 	modify_hdr = mlx5e_mod_hdr_get(mh);
-	if (mlx5e_is_eswitch_flow(flow))
-		flow->esw_attr->modify_hdr = modify_hdr;
-	else
-		flow->nic_attr->modify_hdr = modify_hdr;
+	flow->attr->modify_hdr = modify_hdr;
 	flow->mh = mh;
 
 	return 0;
@@ -858,9 +899,9 @@ static int mlx5e_hairpin_flow_add(struct mlx5e_priv *priv,
 attach_flow:
 	if (hpe->hp->num_channels > 1) {
 		flow_flag_set(flow, HAIRPIN_RSS);
-		flow->nic_attr->hairpin_ft = hpe->hp->ttc.ft.t;
+		flow->attr->nic_attr->hairpin_ft = hpe->hp->ttc.ft.t;
 	} else {
-		flow->nic_attr->hairpin_tirn = hpe->hp->tirn;
+		flow->attr->nic_attr->hairpin_tirn = hpe->hp->tirn;
 	}
 
 	flow->hpe = hpe;
@@ -890,129 +931,212 @@ static void mlx5e_hairpin_flow_del(struct mlx5e_priv *priv,
 	flow->hpe = NULL;
 }
 
-static int
-mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv,
-		      struct mlx5e_tc_flow_parse_attr *parse_attr,
-		      struct mlx5e_tc_flow *flow,
-		      struct netlink_ext_ack *extack)
+struct mlx5_flow_handle *
+mlx5e_add_offloaded_nic_rule(struct mlx5e_priv *priv,
+			     struct mlx5_flow_spec *spec,
+			     struct mlx5_flow_attr *attr)
 {
-	struct mlx5_flow_context *flow_context = &parse_attr->spec.flow_context;
-	struct mlx5_nic_flow_attr *attr = flow->nic_attr;
-	struct mlx5_core_dev *dev = priv->mdev;
+	struct mlx5_flow_context *flow_context = &spec->flow_context;
+	struct mlx5_fs_chains *nic_chains = nic_chains(priv);
+	struct mlx5_nic_flow_attr *nic_attr = attr->nic_attr;
+	struct mlx5e_tc_table *tc = &priv->fs.tc;
 	struct mlx5_flow_destination dest[2] = {};
 	struct mlx5_flow_act flow_act = {
 		.action = attr->action,
 		.flags    = FLOW_ACT_NO_APPEND,
 	};
-	struct mlx5_fc *counter = NULL;
-	int err, dest_ix = 0;
+	struct mlx5_flow_handle *rule;
+	struct mlx5_flow_table *ft;
+	int dest_ix = 0;
 
 	flow_context->flags |= FLOW_CONTEXT_HAS_TAG;
-	flow_context->flow_tag = attr->flow_tag;
+	flow_context->flow_tag = nic_attr->flow_tag;
 
-	if (flow_flag_test(flow, HAIRPIN)) {
-		err = mlx5e_hairpin_flow_add(priv, flow, parse_attr, extack);
-		if (err)
-			return err;
-
-		if (flow_flag_test(flow, HAIRPIN_RSS)) {
-			dest[dest_ix].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
-			dest[dest_ix].ft = attr->hairpin_ft;
-		} else {
-			dest[dest_ix].type = MLX5_FLOW_DESTINATION_TYPE_TIR;
-			dest[dest_ix].tir_num = attr->hairpin_tirn;
-		}
+	if (attr->dest_ft) {
+		dest[dest_ix].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
+		dest[dest_ix].ft = attr->dest_ft;
+		dest_ix++;
+	} else if (nic_attr->hairpin_ft) {
+		dest[dest_ix].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
+		dest[dest_ix].ft = nic_attr->hairpin_ft;
+		dest_ix++;
+	} else if (nic_attr->hairpin_tirn) {
+		dest[dest_ix].type = MLX5_FLOW_DESTINATION_TYPE_TIR;
+		dest[dest_ix].tir_num = nic_attr->hairpin_tirn;
 		dest_ix++;
 	} else if (attr->action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) {
 		dest[dest_ix].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
-		dest[dest_ix].ft = priv->fs.vlan.ft.t;
+		if (attr->dest_chain) {
+			dest[dest_ix].ft = mlx5_chains_get_table(nic_chains,
+								 attr->dest_chain, 1,
+								 MLX5E_TC_FT_LEVEL);
+			if (IS_ERR(dest[dest_ix].ft))
+				return ERR_CAST(dest[dest_ix].ft);
+		} else {
+			dest[dest_ix].ft = priv->fs.vlan.ft.t;
+		}
+		dest_ix++;
+	}
+
+	if (dest[0].type == MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE &&
+	    MLX5_CAP_FLOWTABLE_NIC_RX(priv->mdev, ignore_flow_level))
+		flow_act.flags |= FLOW_ACT_IGNORE_FLOW_LEVEL;
+
+	if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_COUNT) {
+		dest[dest_ix].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
+		dest[dest_ix].counter_id = mlx5_fc_id(attr->counter);
 		dest_ix++;
 	}
 
+	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
+		flow_act.modify_hdr = attr->modify_hdr;
+
+	mutex_lock(&tc->t_lock);
+	if (IS_ERR_OR_NULL(tc->t)) {
+		/* Create the root table here if doesn't exist yet */
+		tc->t =
+			mlx5_chains_get_table(nic_chains, 0, 1, MLX5E_TC_FT_LEVEL);
+
+		if (IS_ERR(tc->t)) {
+			mutex_unlock(&tc->t_lock);
+			netdev_err(priv->netdev,
+				   "Failed to create tc offload table\n");
+			rule = ERR_CAST(priv->fs.tc.t);
+			goto err_ft_get;
+		}
+	}
+	mutex_unlock(&tc->t_lock);
+
+	if (attr->chain || attr->prio)
+		ft = mlx5_chains_get_table(nic_chains,
+					   attr->chain, attr->prio,
+					   MLX5E_TC_FT_LEVEL);
+	else
+		ft = attr->ft;
+
+	if (IS_ERR(ft)) {
+		rule = ERR_CAST(ft);
+		goto err_ft_get;
+	}
+
+	if (attr->outer_match_level != MLX5_MATCH_NONE)
+		spec->match_criteria_enable |= MLX5_MATCH_OUTER_HEADERS;
+
+	rule = mlx5_add_flow_rules(ft, spec,
+				   &flow_act, dest, dest_ix);
+	if (IS_ERR(rule))
+		goto err_rule;
+
+	return rule;
+
+err_rule:
+	if (attr->chain || attr->prio)
+		mlx5_chains_put_table(nic_chains,
+				      attr->chain, attr->prio,
+				      MLX5E_TC_FT_LEVEL);
+err_ft_get:
+	if (attr->dest_chain)
+		mlx5_chains_put_table(nic_chains,
+				      attr->dest_chain, 1,
+				      MLX5E_TC_FT_LEVEL);
+
+	return ERR_CAST(rule);
+}
+
+static int
+mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv,
+		      struct mlx5e_tc_flow_parse_attr *parse_attr,
+		      struct mlx5e_tc_flow *flow,
+		      struct netlink_ext_ack *extack)
+{
+	struct mlx5_flow_attr *attr = flow->attr;
+	struct mlx5_core_dev *dev = priv->mdev;
+	struct mlx5_fc *counter = NULL;
+	int err;
+
+	if (flow_flag_test(flow, HAIRPIN)) {
+		err = mlx5e_hairpin_flow_add(priv, flow, parse_attr, extack);
+		if (err)
+			return err;
+	}
+
 	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_COUNT) {
 		counter = mlx5_fc_create(dev, true);
 		if (IS_ERR(counter))
 			return PTR_ERR(counter);
 
-		dest[dest_ix].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
-		dest[dest_ix].counter_id = mlx5_fc_id(counter);
-		dest_ix++;
 		attr->counter = counter;
 	}
 
 	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) {
 		err = mlx5e_attach_mod_hdr(priv, flow, parse_attr);
-		flow_act.modify_hdr = attr->modify_hdr;
 		dealloc_mod_hdr_actions(&parse_attr->mod_hdr_acts);
 		if (err)
 			return err;
 	}
 
-	mutex_lock(&priv->fs.tc.t_lock);
-	if (IS_ERR_OR_NULL(priv->fs.tc.t)) {
-		struct mlx5_flow_table_attr ft_attr = {};
-		int tc_grp_size, tc_tbl_size, tc_num_grps;
-		u32 max_flow_counter;
-
-		max_flow_counter = (MLX5_CAP_GEN(dev, max_flow_counter_31_16) << 16) |
-				    MLX5_CAP_GEN(dev, max_flow_counter_15_0);
-
-		tc_grp_size = min_t(int, max_flow_counter, MLX5E_TC_TABLE_MAX_GROUP_SIZE);
-
-		tc_tbl_size = min_t(int, tc_grp_size * MLX5E_TC_TABLE_NUM_GROUPS,
-				    BIT(MLX5_CAP_FLOWTABLE_NIC_RX(dev, log_max_ft_size)));
-		tc_num_grps = MLX5E_TC_TABLE_NUM_GROUPS;
-
-		ft_attr.prio = MLX5E_TC_PRIO;
-		ft_attr.max_fte = tc_tbl_size;
-		ft_attr.level = MLX5E_TC_FT_LEVEL;
-		ft_attr.autogroup.max_num_groups = tc_num_grps;
-		priv->fs.tc.t =
-			mlx5_create_auto_grouped_flow_table(priv->fs.ns,
-							    &ft_attr);
-		if (IS_ERR(priv->fs.tc.t)) {
-			mutex_unlock(&priv->fs.tc.t_lock);
-			NL_SET_ERR_MSG_MOD(extack,
-					   "Failed to create tc offload table");
-			netdev_err(priv->netdev,
-				   "Failed to create tc offload table\n");
-			return PTR_ERR(priv->fs.tc.t);
-		}
-	}
+	if (flow_flag_test(flow, CT))
+		flow->rule[0] = mlx5_tc_ct_flow_offload(get_ct_priv(priv), flow, &parse_attr->spec,
+							attr, &parse_attr->mod_hdr_acts);
+	else
+		flow->rule[0] = mlx5e_add_offloaded_nic_rule(priv, &parse_attr->spec,
+							     attr);
 
-	if (attr->match_level != MLX5_MATCH_NONE)
-		parse_attr->spec.match_criteria_enable |= MLX5_MATCH_OUTER_HEADERS;
+	return PTR_ERR_OR_ZERO(flow->rule[0]);
+}
 
-	flow->rule[0] = mlx5_add_flow_rules(priv->fs.tc.t, &parse_attr->spec,
-					    &flow_act, dest, dest_ix);
-	mutex_unlock(&priv->fs.tc.t_lock);
+void mlx5e_del_offloaded_nic_rule(struct mlx5e_priv *priv,
+				  struct mlx5_flow_handle *rule,
+				  struct mlx5_flow_attr *attr)
+{
+	struct mlx5_fs_chains *nic_chains = nic_chains(priv);
 
-	return PTR_ERR_OR_ZERO(flow->rule[0]);
+	mlx5_del_flow_rules(rule);
+
+	if (attr->chain || attr->prio)
+		mlx5_chains_put_table(nic_chains, attr->chain, attr->prio,
+				      MLX5E_TC_FT_LEVEL);
+
+	if (attr->dest_chain)
+		mlx5_chains_put_table(nic_chains, attr->dest_chain, 1,
+				      MLX5E_TC_FT_LEVEL);
 }
 
 static void mlx5e_tc_del_nic_flow(struct mlx5e_priv *priv,
 				  struct mlx5e_tc_flow *flow)
 {
-	struct mlx5_nic_flow_attr *attr = flow->nic_attr;
-	struct mlx5_fc *counter = NULL;
+	struct mlx5_flow_attr *attr = flow->attr;
+	struct mlx5e_tc_table *tc = &priv->fs.tc;
 
-	counter = attr->counter;
-	if (!IS_ERR_OR_NULL(flow->rule[0]))
-		mlx5_del_flow_rules(flow->rule[0]);
-	mlx5_fc_destroy(priv->mdev, counter);
+	flow_flag_clear(flow, OFFLOADED);
 
+	if (flow_flag_test(flow, CT))
+		mlx5_tc_ct_delete_flow(get_ct_priv(flow->priv), flow, attr);
+	else if (!IS_ERR_OR_NULL(flow->rule[0]))
+		mlx5e_del_offloaded_nic_rule(priv, flow->rule[0], attr);
+
+	/* Remove root table if no rules are left to avoid
+	 * extra steering hops.
+	 */
 	mutex_lock(&priv->fs.tc.t_lock);
-	if (!mlx5e_tc_num_filters(priv, MLX5_TC_FLAG(NIC_OFFLOAD)) && priv->fs.tc.t) {
-		mlx5_destroy_flow_table(priv->fs.tc.t);
+	if (!mlx5e_tc_num_filters(priv, MLX5_TC_FLAG(NIC_OFFLOAD)) &&
+	    !IS_ERR_OR_NULL(tc->t)) {
+		mlx5_chains_put_table(nic_chains(priv), 0, 1, MLX5E_TC_FT_LEVEL);
 		priv->fs.tc.t = NULL;
 	}
 	mutex_unlock(&priv->fs.tc.t_lock);
 
+	kvfree(attr->parse_attr);
+
 	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
 		mlx5e_detach_mod_hdr(priv, flow);
 
+	mlx5_fc_destroy(priv->mdev, attr->counter);
+
 	if (flow_flag_test(flow, HAIRPIN))
 		mlx5e_hairpin_flow_del(priv, flow);
+
+	kfree(flow->attr);
 }
 
 static void mlx5e_detach_encap(struct mlx5e_priv *priv,
@@ -1035,7 +1159,7 @@ static struct mlx5_flow_handle *
 mlx5e_tc_offload_fdb_rules(struct mlx5_eswitch *esw,
 			   struct mlx5e_tc_flow *flow,
 			   struct mlx5_flow_spec *spec,
-			   struct mlx5_esw_flow_attr *attr)
+			   struct mlx5_flow_attr *attr)
 {
 	struct mlx5e_tc_mod_hdr_acts *mod_hdr_acts;
 	struct mlx5_flow_handle *rule;
@@ -1043,7 +1167,8 @@ mlx5e_tc_offload_fdb_rules(struct mlx5_eswitch *esw,
 	if (flow_flag_test(flow, CT)) {
 		mod_hdr_acts = &attr->parse_attr->mod_hdr_acts;
 
-		return mlx5_tc_ct_flow_offload(flow->priv, flow, spec, attr,
+		return mlx5_tc_ct_flow_offload(get_ct_priv(flow->priv),
+					       flow, spec, attr,
 					       mod_hdr_acts);
 	}
 
@@ -1051,7 +1176,7 @@ mlx5e_tc_offload_fdb_rules(struct mlx5_eswitch *esw,
 	if (IS_ERR(rule))
 		return rule;
 
-	if (attr->split_count) {
+	if (attr->esw_attr->split_count) {
 		flow->rule[1] = mlx5_eswitch_add_fwd_rule(esw, spec, attr);
 		if (IS_ERR(flow->rule[1])) {
 			mlx5_eswitch_del_offloaded_rule(esw, rule, attr);
@@ -1065,16 +1190,16 @@ mlx5e_tc_offload_fdb_rules(struct mlx5_eswitch *esw,
 static void
 mlx5e_tc_unoffload_fdb_rules(struct mlx5_eswitch *esw,
 			     struct mlx5e_tc_flow *flow,
-			     struct mlx5_esw_flow_attr *attr)
+			     struct mlx5_flow_attr *attr)
 {
 	flow_flag_clear(flow, OFFLOADED);
 
 	if (flow_flag_test(flow, CT)) {
-		mlx5_tc_ct_delete_flow(flow->priv, flow, attr);
+		mlx5_tc_ct_delete_flow(get_ct_priv(flow->priv), flow, attr);
 		return;
 	}
 
-	if (attr->split_count)
+	if (attr->esw_attr->split_count)
 		mlx5_eswitch_del_fwd_rule(esw, flow->rule[1], attr);
 
 	mlx5_eswitch_del_offloaded_rule(esw, flow->rule[0], attr);
@@ -1085,18 +1210,24 @@ mlx5e_tc_offload_to_slow_path(struct mlx5_eswitch *esw,
 			      struct mlx5e_tc_flow *flow,
 			      struct mlx5_flow_spec *spec)
 {
-	struct mlx5_esw_flow_attr slow_attr;
+	struct mlx5_flow_attr *slow_attr;
 	struct mlx5_flow_handle *rule;
 
-	memcpy(&slow_attr, flow->esw_attr, sizeof(slow_attr));
-	slow_attr.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
-	slow_attr.split_count = 0;
-	slow_attr.flags |= MLX5_ESW_ATTR_FLAG_SLOW_PATH;
+	slow_attr = mlx5_alloc_flow_attr(MLX5_FLOW_NAMESPACE_FDB);
+	if (!slow_attr)
+		return ERR_PTR(-ENOMEM);
+
+	memcpy(slow_attr, flow->attr, ESW_FLOW_ATTR_SZ);
+	slow_attr->action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+	slow_attr->esw_attr->split_count = 0;
+	slow_attr->flags |= MLX5_ESW_ATTR_FLAG_SLOW_PATH;
 
-	rule = mlx5e_tc_offload_fdb_rules(esw, flow, spec, &slow_attr);
+	rule = mlx5e_tc_offload_fdb_rules(esw, flow, spec, slow_attr);
 	if (!IS_ERR(rule))
 		flow_flag_set(flow, SLOW);
 
+	kfree(slow_attr);
+
 	return rule;
 }
 
@@ -1104,14 +1235,21 @@ static void
 mlx5e_tc_unoffload_from_slow_path(struct mlx5_eswitch *esw,
 				  struct mlx5e_tc_flow *flow)
 {
-	struct mlx5_esw_flow_attr slow_attr;
+	struct mlx5_flow_attr *slow_attr;
 
-	memcpy(&slow_attr, flow->esw_attr, sizeof(slow_attr));
-	slow_attr.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
-	slow_attr.split_count = 0;
-	slow_attr.flags |= MLX5_ESW_ATTR_FLAG_SLOW_PATH;
-	mlx5e_tc_unoffload_fdb_rules(esw, flow, &slow_attr);
+	slow_attr = mlx5_alloc_flow_attr(MLX5_FLOW_NAMESPACE_FDB);
+	if (!slow_attr) {
+		mlx5_core_warn(flow->priv->mdev, "Unable to alloc attr to unoffload slow path rule\n");
+		return;
+	}
+
+	memcpy(slow_attr, flow->attr, ESW_FLOW_ATTR_SZ);
+	slow_attr->action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+	slow_attr->esw_attr->split_count = 0;
+	slow_attr->flags |= MLX5_ESW_ATTR_FLAG_SLOW_PATH;
+	mlx5e_tc_unoffload_fdb_rules(esw, flow, slow_attr);
 	flow_flag_clear(flow, SLOW);
+	kfree(slow_attr);
 }
 
 /* Caller must obtain uplink_priv->unready_flows_lock mutex before calling this
@@ -1169,9 +1307,10 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
 		      struct netlink_ext_ack *extack)
 {
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
-	struct mlx5_esw_flow_attr *attr = flow->esw_attr;
-	struct mlx5e_tc_flow_parse_attr *parse_attr = attr->parse_attr;
 	struct net_device *out_dev, *encap_dev = NULL;
+	struct mlx5e_tc_flow_parse_attr *parse_attr;
+	struct mlx5_flow_attr *attr = flow->attr;
+	struct mlx5_esw_flow_attr *esw_attr;
 	struct mlx5_fc *counter = NULL;
 	struct mlx5e_rep_priv *rpriv;
 	struct mlx5e_priv *out_priv;
@@ -1180,7 +1319,7 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
 	int err = 0;
 	int out_index;
 
-	if (!mlx5_esw_chains_prios_supported(esw) && attr->prio != 1) {
+	if (!mlx5_chains_prios_supported(esw_chains(esw)) && attr->prio != 1) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "E-switch priorities unsupported, upgrade FW");
 		return -EOPNOTSUPP;
@@ -1191,14 +1330,14 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
 	 * FDB_FT_CHAIN which is outside tc range.
 	 * See mlx5e_rep_setup_ft_cb().
 	 */
-	max_chain = mlx5_esw_chains_get_chain_range(esw);
+	max_chain = mlx5_chains_get_chain_range(esw_chains(esw));
 	if (!mlx5e_is_ft_flow(flow) && attr->chain > max_chain) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "Requested chain is out of supported range");
 		return -EOPNOTSUPP;
 	}
 
-	max_prio = mlx5_esw_chains_get_prio_range(esw);
+	max_prio = mlx5_chains_get_prio_range(esw_chains(esw));
 	if (attr->prio > max_prio) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "Requested priority is out of supported range");
@@ -1211,10 +1350,13 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
 			return err;
 	}
 
+	parse_attr = attr->parse_attr;
+	esw_attr = attr->esw_attr;
+
 	for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) {
 		int mirred_ifindex;
 
-		if (!(attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP))
+		if (!(esw_attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP))
 			continue;
 
 		mirred_ifindex = parse_attr->mirred_ifindex[out_index];
@@ -1227,8 +1369,8 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
 
 		out_priv = netdev_priv(encap_dev);
 		rpriv = out_priv->ppriv;
-		attr->dests[out_index].rep = rpriv->rep;
-		attr->dests[out_index].mdev = out_priv->mdev;
+		esw_attr->dests[out_index].rep = rpriv->rep;
+		esw_attr->dests[out_index].mdev = out_priv->mdev;
 	}
 
 	err = mlx5_eswitch_add_vlan_action(esw, attr);
@@ -1244,7 +1386,7 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
 	}
 
 	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_COUNT) {
-		counter = mlx5_fc_create(attr->counter_dev, true);
+		counter = mlx5_fc_create(esw_attr->counter_dev, true);
 		if (IS_ERR(counter))
 			return PTR_ERR(counter);
 
@@ -1270,7 +1412,7 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
 
 static bool mlx5_flow_has_geneve_opt(struct mlx5e_tc_flow *flow)
 {
-	struct mlx5_flow_spec *spec = &flow->esw_attr->parse_attr->spec;
+	struct mlx5_flow_spec *spec = &flow->attr->parse_attr->spec;
 	void *headers_v = MLX5_ADDR_OF(fte_match_param,
 				       spec->match_value,
 				       misc_parameters_3);
@@ -1285,16 +1427,13 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv,
 				  struct mlx5e_tc_flow *flow)
 {
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
-	struct mlx5_esw_flow_attr *attr = flow->esw_attr;
+	struct mlx5_flow_attr *attr = flow->attr;
 	int out_index;
 
 	mlx5e_put_flow_tunnel_id(flow);
 
-	if (flow_flag_test(flow, NOT_READY)) {
+	if (flow_flag_test(flow, NOT_READY))
 		remove_unready_flow(flow);
-		kvfree(attr->parse_attr);
-		return;
-	}
 
 	if (mlx5e_is_offloaded_flow(flow)) {
 		if (flow_flag_test(flow, SLOW))
@@ -1309,20 +1448,24 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv,
 	mlx5_eswitch_del_vlan_action(esw, attr);
 
 	for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++)
-		if (attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP) {
+		if (attr->esw_attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP) {
 			mlx5e_detach_encap(priv, flow, out_index);
 			kfree(attr->parse_attr->tun_info[out_index]);
 		}
 	kvfree(attr->parse_attr);
 
+	mlx5_tc_ct_match_del(get_ct_priv(priv), &flow->attr->ct_attr);
+
 	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
 		mlx5e_detach_mod_hdr(priv, flow);
 
 	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_COUNT)
-		mlx5_fc_destroy(attr->counter_dev, attr->counter);
+		mlx5_fc_destroy(attr->esw_attr->counter_dev, attr->counter);
 
 	if (flow_flag_test(flow, L3_TO_L2_DECAP))
 		mlx5e_detach_decap(priv, flow);
+
+	kfree(flow->attr);
 }
 
 void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv,
@@ -1332,6 +1475,7 @@ void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv,
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
 	struct mlx5_esw_flow_attr *esw_attr;
 	struct mlx5_flow_handle *rule;
+	struct mlx5_flow_attr *attr;
 	struct mlx5_flow_spec *spec;
 	struct mlx5e_tc_flow *flow;
 	int err;
@@ -1354,8 +1498,9 @@ void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv,
 
 		if (!mlx5e_is_offloaded_flow(flow))
 			continue;
-		esw_attr = flow->esw_attr;
-		spec = &esw_attr->parse_attr->spec;
+		attr = flow->attr;
+		esw_attr = attr->esw_attr;
+		spec = &attr->parse_attr->spec;
 
 		esw_attr->dests[flow->tmp_efi_index].pkt_reformat = e->pkt_reformat;
 		esw_attr->dests[flow->tmp_efi_index].flags |= MLX5_ESW_DEST_ENCAP_VALID;
@@ -1375,7 +1520,7 @@ void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv,
 		if (!all_flow_encaps_valid)
 			continue;
 		/* update from slow path rule to encap rule */
-		rule = mlx5e_tc_offload_fdb_rules(esw, flow, spec, esw_attr);
+		rule = mlx5e_tc_offload_fdb_rules(esw, flow, spec, attr);
 		if (IS_ERR(rule)) {
 			err = PTR_ERR(rule);
 			mlx5_core_warn(priv->mdev, "Failed to update cached encapsulation flow, %d\n",
@@ -1395,7 +1540,9 @@ void mlx5e_tc_encap_flows_del(struct mlx5e_priv *priv,
 			      struct list_head *flow_list)
 {
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+	struct mlx5_esw_flow_attr *esw_attr;
 	struct mlx5_flow_handle *rule;
+	struct mlx5_flow_attr *attr;
 	struct mlx5_flow_spec *spec;
 	struct mlx5e_tc_flow *flow;
 	int err;
@@ -1403,12 +1550,14 @@ void mlx5e_tc_encap_flows_del(struct mlx5e_priv *priv,
 	list_for_each_entry(flow, flow_list, tmp_list) {
 		if (!mlx5e_is_offloaded_flow(flow))
 			continue;
-		spec = &flow->esw_attr->parse_attr->spec;
+		attr = flow->attr;
+		esw_attr = attr->esw_attr;
+		spec = &attr->parse_attr->spec;
 
 		/* update from encap rule to slow path rule */
 		rule = mlx5e_tc_offload_to_slow_path(esw, flow, spec);
 		/* mark the flow's encap dest as non-valid */
-		flow->esw_attr->dests[flow->tmp_efi_index].flags &= ~MLX5_ESW_DEST_ENCAP_VALID;
+		esw_attr->dests[flow->tmp_efi_index].flags &= ~MLX5_ESW_DEST_ENCAP_VALID;
 
 		if (IS_ERR(rule)) {
 			err = PTR_ERR(rule);
@@ -1417,7 +1566,7 @@ void mlx5e_tc_encap_flows_del(struct mlx5e_priv *priv,
 			continue;
 		}
 
-		mlx5e_tc_unoffload_fdb_rules(esw, flow, flow->esw_attr);
+		mlx5e_tc_unoffload_fdb_rules(esw, flow, attr);
 		flow->rule[0] = rule;
 		/* was unset when fast path rule removed */
 		flow_flag_set(flow, OFFLOADED);
@@ -1430,10 +1579,7 @@ void mlx5e_tc_encap_flows_del(struct mlx5e_priv *priv,
 
 static struct mlx5_fc *mlx5e_tc_get_counter(struct mlx5e_tc_flow *flow)
 {
-	if (mlx5e_is_eswitch_flow(flow))
-		return flow->esw_attr->counter;
-	else
-		return flow->nic_attr->counter;
+	return flow->attr->counter;
 }
 
 /* Takes reference to all flows attached to encap and adds the flows to
@@ -1799,11 +1945,11 @@ static int mlx5e_get_flow_tunnel_id(struct mlx5e_priv *priv,
 {
 	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
 	struct netlink_ext_ack *extack = f->common.extack;
-	struct mlx5_esw_flow_attr *attr = flow->esw_attr;
 	struct mlx5e_tc_mod_hdr_acts *mod_hdr_acts;
 	struct flow_match_enc_opts enc_opts_match;
 	struct tunnel_match_enc_opts tun_enc_opts;
 	struct mlx5_rep_uplink_priv *uplink_priv;
+	struct mlx5_flow_attr *attr = flow->attr;
 	struct mlx5e_rep_priv *uplink_rpriv;
 	struct tunnel_match_key tunnel_key;
 	bool enc_opts_is_dont_care = true;
@@ -1867,7 +2013,7 @@ static int mlx5e_get_flow_tunnel_id(struct mlx5e_priv *priv,
 	} else {
 		mod_hdr_acts = &attr->parse_attr->mod_hdr_acts;
 		err = mlx5e_tc_match_to_reg_set(priv->mdev,
-						mod_hdr_acts,
+						mod_hdr_acts, MLX5_FLOW_NAMESPACE_FDB,
 						TUNNEL_TO_REG, value);
 		if (err)
 			goto err_set;
@@ -1953,8 +2099,8 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv,
 	if (!mlx5e_is_eswitch_flow(flow))
 		return -EOPNOTSUPP;
 
-	needs_mapping = !!flow->esw_attr->chain;
-	sets_mapping = !flow->esw_attr->chain && flow_has_tc_fwd_action(f);
+	needs_mapping = !!flow->attr->chain;
+	sets_mapping = !flow->attr->chain && flow_has_tc_fwd_action(f);
 	*match_inner = !needs_mapping;
 
 	if ((needs_mapping || sets_mapping) &&
@@ -1966,7 +2112,7 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv,
 		return -EOPNOTSUPP;
 	}
 
-	if (!flow->esw_attr->chain) {
+	if (!flow->attr->chain) {
 		err = mlx5e_tc_tun_parse(filter_dev, priv, spec, f,
 					 match_level);
 		if (err) {
@@ -1981,7 +2127,7 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv,
 		 * object
 		 */
 		if (!netif_is_bareudp(filter_dev))
-			flow->esw_attr->action |= MLX5_FLOW_CONTEXT_ACTION_DECAP;
+			flow->attr->action |= MLX5_FLOW_CONTEXT_ACTION_DECAP;
 	}
 
 	if (!needs_mapping && !sets_mapping)
@@ -2484,12 +2630,9 @@ static int parse_cls_flower(struct mlx5e_priv *priv,
 		}
 	}
 
-	if (is_eswitch_flow) {
-		flow->esw_attr->inner_match_level = inner_match_level;
-		flow->esw_attr->outer_match_level = outer_match_level;
-	} else {
-		flow->nic_attr->match_level = non_tunnel_match_level;
-	}
+	flow->attr->inner_match_level = inner_match_level;
+	flow->attr->outer_match_level = outer_match_level;
+
 
 	return err;
 }
@@ -2626,6 +2769,22 @@ static struct mlx5_fields fields[] = {
 	OFFLOAD(UDP_DPORT, 16, U16_MAX, udp.dest,   0, udp_dport),
 };
 
+static unsigned long mask_to_le(unsigned long mask, int size)
+{
+	__be32 mask_be32;
+	__be16 mask_be16;
+
+	if (size == 32) {
+		mask_be32 = (__force __be32)(mask);
+		mask = (__force unsigned long)cpu_to_le32(be32_to_cpu(mask_be32));
+	} else if (size == 16) {
+		mask_be32 = (__force __be32)(mask);
+		mask_be16 = *(__be16 *)&mask_be32;
+		mask = (__force unsigned long)cpu_to_le16(be16_to_cpu(mask_be16));
+	}
+
+	return mask;
+}
 static int offload_pedit_fields(struct mlx5e_priv *priv,
 				int namespace,
 				struct pedit_headers_action *hdrs,
@@ -2639,9 +2798,7 @@ static int offload_pedit_fields(struct mlx5e_priv *priv,
 	u32 *s_masks_p, *a_masks_p, s_mask, a_mask;
 	struct mlx5e_tc_mod_hdr_acts *mod_acts;
 	struct mlx5_fields *f;
-	unsigned long mask;
-	__be32 mask_be32;
-	__be16 mask_be16;
+	unsigned long mask, field_mask;
 	int err;
 	u8 cmd;
 
@@ -2707,14 +2864,7 @@ static int offload_pedit_fields(struct mlx5e_priv *priv,
 		if (skip)
 			continue;
 
-		if (f->field_bsize == 32) {
-			mask_be32 = (__force __be32)(mask);
-			mask = (__force unsigned long)cpu_to_le32(be32_to_cpu(mask_be32));
-		} else if (f->field_bsize == 16) {
-			mask_be32 = (__force __be32)(mask);
-			mask_be16 = *(__be16 *)&mask_be32;
-			mask = (__force unsigned long)cpu_to_le16(be16_to_cpu(mask_be16));
-		}
+		mask = mask_to_le(mask, f->field_bsize);
 
 		first = find_first_bit(&mask, f->field_bsize);
 		next_z = find_next_zero_bit(&mask, f->field_bsize, first);
@@ -2745,9 +2895,10 @@ static int offload_pedit_fields(struct mlx5e_priv *priv,
 		if (cmd == MLX5_ACTION_TYPE_SET) {
 			int start;
 
+			field_mask = mask_to_le(f->field_mask, f->field_bsize);
+
 			/* if field is bit sized it can start not from first bit */
-			start = find_first_bit((unsigned long *)&f->field_mask,
-					       f->field_bsize);
+			start = find_first_bit(&field_mask, f->field_bsize);
 
 			MLX5_SET(set_action_in, action, offset, first - start);
 			/* length is num of bits to be written, zero means length of 32 */
@@ -3084,7 +3235,7 @@ static bool modify_header_match_supported(struct mlx5e_priv *priv,
 	 *  we can't restore ct state
 	 */
 	if (!ct_clear && modify_tuple &&
-	    mlx5_tc_ct_add_no_trk_match(priv, spec)) {
+	    mlx5_tc_ct_add_no_trk_match(spec)) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "can't offload tuple modify header with ct matches");
 		netdev_info(priv->netdev,
@@ -3115,12 +3266,13 @@ static bool actions_match_supported(struct mlx5e_priv *priv,
 	bool ct_flow = false, ct_clear = false;
 	u32 actions;
 
+	ct_clear = flow->attr->ct_attr.ct_action &
+		TCA_CT_ACT_CLEAR;
+	ct_flow = flow_flag_test(flow, CT) && !ct_clear;
+	actions = flow->attr->action;
+
 	if (mlx5e_is_eswitch_flow(flow)) {
-		actions = flow->esw_attr->action;
-		ct_clear = flow->esw_attr->ct_attr.ct_action &
-			   TCA_CT_ACT_CLEAR;
-		ct_flow = flow_flag_test(flow, CT) && !ct_clear;
-		if (flow->esw_attr->split_count && ct_flow) {
+		if (flow->attr->esw_attr->split_count && ct_flow) {
 			/* All registers used by ct are cleared when using
 			 * split rules.
 			 */
@@ -3128,8 +3280,6 @@ static bool actions_match_supported(struct mlx5e_priv *priv,
 					   "Can't offload mirroring with action ct");
 			return false;
 		}
-	} else {
-		actions = flow->nic_attr->action;
 	}
 
 	if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
@@ -3227,15 +3377,67 @@ add_vlan_prio_tag_rewrite_action(struct mlx5e_priv *priv,
 				       extack);
 }
 
+static int validate_goto_chain(struct mlx5e_priv *priv,
+			       struct mlx5e_tc_flow *flow,
+			       const struct flow_action_entry *act,
+			       u32 actions,
+			       struct netlink_ext_ack *extack)
+{
+	bool is_esw = mlx5e_is_eswitch_flow(flow);
+	struct mlx5_flow_attr *attr = flow->attr;
+	bool ft_flow = mlx5e_is_ft_flow(flow);
+	u32 dest_chain = act->chain_index;
+	struct mlx5_fs_chains *chains;
+	struct mlx5_eswitch *esw;
+	u32 reformat_and_fwd;
+	u32 max_chain;
+
+	esw = priv->mdev->priv.eswitch;
+	chains = is_esw ? esw_chains(esw) : nic_chains(priv);
+	max_chain = mlx5_chains_get_chain_range(chains);
+	reformat_and_fwd = is_esw ?
+			   MLX5_CAP_ESW_FLOWTABLE_FDB(priv->mdev, reformat_and_fwd_to_table) :
+			   MLX5_CAP_FLOWTABLE_NIC_RX(priv->mdev, reformat_and_fwd_to_table);
+
+	if (ft_flow) {
+		NL_SET_ERR_MSG_MOD(extack, "Goto action is not supported");
+		return -EOPNOTSUPP;
+	}
+
+	if (!mlx5_chains_backwards_supported(chains) &&
+	    dest_chain <= attr->chain) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Goto lower numbered chain isn't supported");
+		return -EOPNOTSUPP;
+	}
+
+	if (dest_chain > max_chain) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Requested destination chain is out of supported range");
+		return -EOPNOTSUPP;
+	}
+
+	if (actions & (MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT |
+		       MLX5_FLOW_CONTEXT_ACTION_DECAP) &&
+	    !reformat_and_fwd) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Goto chain is not allowed if action has reformat or decap");
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
 static int parse_tc_nic_actions(struct mlx5e_priv *priv,
 				struct flow_action *flow_action,
 				struct mlx5e_tc_flow_parse_attr *parse_attr,
 				struct mlx5e_tc_flow *flow,
 				struct netlink_ext_ack *extack)
 {
-	struct mlx5_nic_flow_attr *attr = flow->nic_attr;
+	struct mlx5_flow_attr *attr = flow->attr;
 	struct pedit_headers_action hdrs[2] = {};
 	const struct flow_action_entry *act;
+	struct mlx5_nic_flow_attr *nic_attr;
 	u32 action = 0;
 	int err, i;
 
@@ -3246,7 +3448,9 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv,
 					FLOW_ACTION_HW_STATS_DELAYED_BIT))
 		return -EOPNOTSUPP;
 
-	attr->flow_tag = MLX5_FS_DEFAULT_FLOW_TAG;
+	nic_attr = attr->nic_attr;
+
+	nic_attr->flow_tag = MLX5_FS_DEFAULT_FLOW_TAG;
 
 	flow_action_for_each(i, act, flow_action) {
 		switch (act->id) {
@@ -3267,8 +3471,7 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv,
 			if (err)
 				return err;
 
-			action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR |
-				  MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+			action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
 			break;
 		case FLOW_ACTION_VLAN_MANGLE:
 			err = add_vlan_rewrite_action(priv,
@@ -3313,10 +3516,26 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv,
 				return -EINVAL;
 			}
 
-			attr->flow_tag = mark;
+			nic_attr->flow_tag = mark;
 			action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
 			}
 			break;
+		case FLOW_ACTION_GOTO:
+			err = validate_goto_chain(priv, flow, act, action,
+						  extack);
+			if (err)
+				return err;
+
+			action |= MLX5_FLOW_CONTEXT_ACTION_COUNT;
+			attr->dest_chain = act->chain_index;
+			break;
+		case FLOW_ACTION_CT:
+			err = mlx5_tc_ct_parse_action(get_ct_priv(priv), attr, act, extack);
+			if (err)
+				return err;
+
+			flow_flag_set(flow, CT);
+			break;
 		default:
 			NL_SET_ERR_MSG_MOD(extack, "The offload action is not supported");
 			return -EOPNOTSUPP;
@@ -3339,6 +3558,18 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv,
 	}
 
 	attr->action = action;
+
+	if (attr->dest_chain) {
+		if (attr->action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) {
+			NL_SET_ERR_MSG(extack, "Mirroring goto chain rules isn't supported");
+			return -EOPNOTSUPP;
+		}
+		attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+	}
+
+	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
+		attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+
 	if (!actions_match_supported(priv, flow_action, parse_attr, flow, extack))
 		return -EOPNOTSUPP;
 
@@ -3470,8 +3701,8 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv,
 			      bool *encap_valid)
 {
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
-	struct mlx5_esw_flow_attr *attr = flow->esw_attr;
 	struct mlx5e_tc_flow_parse_attr *parse_attr;
+	struct mlx5_flow_attr *attr = flow->attr;
 	const struct ip_tunnel_info *tun_info;
 	struct encap_key key;
 	struct mlx5e_encap_entry *e;
@@ -3557,8 +3788,8 @@ attach_flow:
 	flow->encaps[out_index].index = out_index;
 	*encap_dev = e->out_dev;
 	if (e->flags & MLX5_ENCAP_ENTRY_VALID) {
-		attr->dests[out_index].pkt_reformat = e->pkt_reformat;
-		attr->dests[out_index].flags |= MLX5_ESW_DEST_ENCAP_VALID;
+		attr->esw_attr->dests[out_index].pkt_reformat = e->pkt_reformat;
+		attr->esw_attr->dests[out_index].flags |= MLX5_ESW_DEST_ENCAP_VALID;
 		*encap_valid = true;
 	} else {
 		*encap_valid = false;
@@ -3585,14 +3816,14 @@ static int mlx5e_attach_decap(struct mlx5e_priv *priv,
 			      struct netlink_ext_ack *extack)
 {
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
-	struct mlx5_esw_flow_attr *attr = flow->esw_attr;
+	struct mlx5_esw_flow_attr *attr = flow->attr->esw_attr;
 	struct mlx5e_tc_flow_parse_attr *parse_attr;
 	struct mlx5e_decap_entry *d;
 	struct mlx5e_decap_key key;
 	uintptr_t hash_key;
 	int err = 0;
 
-	parse_attr = attr->parse_attr;
+	parse_attr = flow->attr->parse_attr;
 	if (sizeof(parse_attr->eth) > MLX5_CAP_ESW(priv->mdev, max_encap_header_size)) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "encap header larger than max supported");
@@ -3734,7 +3965,7 @@ static struct net_device *get_fdb_out_dev(struct net_device *uplink_dev,
 }
 
 static int add_vlan_push_action(struct mlx5e_priv *priv,
-				struct mlx5_esw_flow_attr *attr,
+				struct mlx5_flow_attr *attr,
 				struct net_device **out_dev,
 				u32 *action)
 {
@@ -3747,7 +3978,7 @@ static int add_vlan_push_action(struct mlx5e_priv *priv,
 	};
 	int err;
 
-	err = parse_tc_vlan_action(priv, &vlan_act, attr, action);
+	err = parse_tc_vlan_action(priv, &vlan_act, attr->esw_attr, action);
 	if (err)
 		return err;
 
@@ -3760,7 +3991,7 @@ static int add_vlan_push_action(struct mlx5e_priv *priv,
 }
 
 static int add_vlan_pop_action(struct mlx5e_priv *priv,
-			       struct mlx5_esw_flow_attr *attr,
+			       struct mlx5_flow_attr *attr,
 			       u32 *action)
 {
 	struct flow_action_entry vlan_act = {
@@ -3771,7 +4002,7 @@ static int add_vlan_pop_action(struct mlx5e_priv *priv,
 	nest_level = attr->parse_attr->filter_dev->lower_level -
 						priv->netdev->lower_level;
 	while (nest_level--) {
-		err = parse_tc_vlan_action(priv, &vlan_act, attr, action);
+		err = parse_tc_vlan_action(priv, &vlan_act, attr->esw_attr, action);
 		if (err)
 			return err;
 	}
@@ -3832,59 +4063,20 @@ static bool is_duplicated_output_device(struct net_device *dev,
 	return false;
 }
 
-static int mlx5_validate_goto_chain(struct mlx5_eswitch *esw,
-				    struct mlx5e_tc_flow *flow,
-				    const struct flow_action_entry *act,
-				    u32 actions,
-				    struct netlink_ext_ack *extack)
-{
-	u32 max_chain = mlx5_esw_chains_get_chain_range(esw);
-	struct mlx5_esw_flow_attr *attr = flow->esw_attr;
-	bool ft_flow = mlx5e_is_ft_flow(flow);
-	u32 dest_chain = act->chain_index;
-
-	if (ft_flow) {
-		NL_SET_ERR_MSG_MOD(extack, "Goto action is not supported");
-		return -EOPNOTSUPP;
-	}
-
-	if (!mlx5_esw_chains_backwards_supported(esw) &&
-	    dest_chain <= attr->chain) {
-		NL_SET_ERR_MSG_MOD(extack,
-				   "Goto lower numbered chain isn't supported");
-		return -EOPNOTSUPP;
-	}
-	if (dest_chain > max_chain) {
-		NL_SET_ERR_MSG_MOD(extack,
-				   "Requested destination chain is out of supported range");
-		return -EOPNOTSUPP;
-	}
-
-	if (actions & (MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT |
-		       MLX5_FLOW_CONTEXT_ACTION_DECAP) &&
-	    !MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, reformat_and_fwd_to_table)) {
-		NL_SET_ERR_MSG_MOD(extack,
-				   "Goto chain is not allowed if action has reformat or decap");
-		return -EOPNOTSUPP;
-	}
-
-	return 0;
-}
-
 static int verify_uplink_forwarding(struct mlx5e_priv *priv,
 				    struct mlx5e_tc_flow *flow,
 				    struct net_device *out_dev,
 				    struct netlink_ext_ack *extack)
 {
+	struct mlx5_esw_flow_attr *attr = flow->attr->esw_attr;
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
-	struct mlx5_esw_flow_attr *attr = flow->esw_attr;
 	struct mlx5e_rep_priv *rep_priv;
 
 	/* Forwarding non encapsulated traffic between
 	 * uplink ports is allowed only if
 	 * termination_table_raw_traffic cap is set.
 	 *
-	 * Input vport was stored esw_attr->in_rep.
+	 * Input vport was stored attr->in_rep.
 	 * In LAG case, *priv* is the private data of
 	 * uplink which may be not the input vport.
 	 */
@@ -3919,13 +4111,14 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv,
 {
 	struct pedit_headers_action hdrs[2] = {};
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
-	struct mlx5_esw_flow_attr *attr = flow->esw_attr;
-	struct mlx5e_tc_flow_parse_attr *parse_attr = attr->parse_attr;
+	struct mlx5e_tc_flow_parse_attr *parse_attr;
 	struct mlx5e_rep_priv *rpriv = priv->ppriv;
 	const struct ip_tunnel_info *info = NULL;
+	struct mlx5_flow_attr *attr = flow->attr;
 	int ifindexes[MLX5_MAX_FLOW_FWD_VPORTS];
 	bool ft_flow = mlx5e_is_ft_flow(flow);
 	const struct flow_action_entry *act;
+	struct mlx5_esw_flow_attr *esw_attr;
 	bool encap = false, decap = false;
 	u32 action = attr->action;
 	int err, i, if_count = 0;
@@ -3938,6 +4131,9 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv,
 					FLOW_ACTION_HW_STATS_DELAYED_BIT))
 		return -EOPNOTSUPP;
 
+	esw_attr = attr->esw_attr;
+	parse_attr = attr->parse_attr;
+
 	flow_action_for_each(i, act, flow_action) {
 		switch (act->id) {
 		case FLOW_ACTION_DROP:
@@ -3994,7 +4190,7 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv,
 
 			if (!flow_flag_test(flow, L3_TO_L2_DECAP)) {
 				action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
-				attr->split_count = attr->out_count;
+				esw_attr->split_count = esw_attr->out_count;
 			}
 			break;
 		case FLOW_ACTION_CSUM:
@@ -4031,27 +4227,27 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv,
 				return -EOPNOTSUPP;
 			}
 
-			if (attr->out_count >= MLX5_MAX_FLOW_FWD_VPORTS) {
+			if (esw_attr->out_count >= MLX5_MAX_FLOW_FWD_VPORTS) {
 				NL_SET_ERR_MSG_MOD(extack,
 						   "can't support more output ports, can't offload forwarding");
 				netdev_warn(priv->netdev,
 					    "can't support more than %d output ports, can't offload forwarding\n",
-					    attr->out_count);
+					    esw_attr->out_count);
 				return -EOPNOTSUPP;
 			}
 
 			action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
 				  MLX5_FLOW_CONTEXT_ACTION_COUNT;
 			if (encap) {
-				parse_attr->mirred_ifindex[attr->out_count] =
+				parse_attr->mirred_ifindex[esw_attr->out_count] =
 					out_dev->ifindex;
-				parse_attr->tun_info[attr->out_count] = dup_tun_info(info);
-				if (!parse_attr->tun_info[attr->out_count])
+				parse_attr->tun_info[esw_attr->out_count] = dup_tun_info(info);
+				if (!parse_attr->tun_info[esw_attr->out_count])
 					return -ENOMEM;
 				encap = false;
-				attr->dests[attr->out_count].flags |=
+				esw_attr->dests[esw_attr->out_count].flags |=
 					MLX5_ESW_DEST_ENCAP;
-				attr->out_count++;
+				esw_attr->out_count++;
 				/* attr->dests[].rep is resolved when we
 				 * handle encap
 				 */
@@ -4100,9 +4296,9 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv,
 
 				out_priv = netdev_priv(out_dev);
 				rpriv = out_priv->ppriv;
-				attr->dests[attr->out_count].rep = rpriv->rep;
-				attr->dests[attr->out_count].mdev = out_priv->mdev;
-				attr->out_count++;
+				esw_attr->dests[esw_attr->out_count].rep = rpriv->rep;
+				esw_attr->dests[esw_attr->out_count].mdev = out_priv->mdev;
+				esw_attr->out_count++;
 			} else if (parse_attr->filter_dev != priv->netdev) {
 				/* All mlx5 devices are called to configure
 				 * high level device filters. Therefore, the
@@ -4140,12 +4336,12 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv,
 							      act, parse_attr, hdrs,
 							      &action, extack);
 			} else {
-				err = parse_tc_vlan_action(priv, act, attr, &action);
+				err = parse_tc_vlan_action(priv, act, esw_attr, &action);
 			}
 			if (err)
 				return err;
 
-			attr->split_count = attr->out_count;
+			esw_attr->split_count = esw_attr->out_count;
 			break;
 		case FLOW_ACTION_VLAN_MANGLE:
 			err = add_vlan_rewrite_action(priv,
@@ -4155,14 +4351,14 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv,
 			if (err)
 				return err;
 
-			attr->split_count = attr->out_count;
+			esw_attr->split_count = esw_attr->out_count;
 			break;
 		case FLOW_ACTION_TUNNEL_DECAP:
 			decap = true;
 			break;
 		case FLOW_ACTION_GOTO:
-			err = mlx5_validate_goto_chain(esw, flow, act, action,
-						       extack);
+			err = validate_goto_chain(priv, flow, act, action,
+						  extack);
 			if (err)
 				return err;
 
@@ -4170,7 +4366,7 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv,
 			attr->dest_chain = act->chain_index;
 			break;
 		case FLOW_ACTION_CT:
-			err = mlx5_tc_ct_parse_action(priv, attr, act, extack);
+			err = mlx5_tc_ct_parse_action(get_ct_priv(priv), attr, act, extack);
 			if (err)
 				return err;
 
@@ -4209,7 +4405,7 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv,
 			dealloc_mod_hdr_actions(&parse_attr->mod_hdr_acts);
 			if (!((action & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP) ||
 			      (action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH)))
-				attr->split_count = 0;
+				esw_attr->split_count = 0;
 		}
 	}
 
@@ -4249,7 +4445,7 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv,
 		return -EOPNOTSUPP;
 	}
 
-	if (attr->split_count > 0 && !mlx5_esw_has_fwd_fdb(priv->mdev)) {
+	if (esw_attr->split_count > 0 && !mlx5_esw_has_fwd_fdb(priv->mdev)) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "current firmware doesn't support split rule for port mirroring");
 		netdev_warn_once(priv->netdev, "current firmware doesn't support split rule for port mirroring\n");
@@ -4300,25 +4496,37 @@ static struct rhashtable *get_tc_ht(struct mlx5e_priv *priv,
 
 static bool is_peer_flow_needed(struct mlx5e_tc_flow *flow)
 {
-	struct mlx5_esw_flow_attr *attr = flow->esw_attr;
-	bool is_rep_ingress = attr->in_rep->vport != MLX5_VPORT_UPLINK &&
+	struct mlx5_esw_flow_attr *esw_attr = flow->attr->esw_attr;
+	struct mlx5_flow_attr *attr = flow->attr;
+	bool is_rep_ingress = esw_attr->in_rep->vport != MLX5_VPORT_UPLINK &&
 		flow_flag_test(flow, INGRESS);
 	bool act_is_encap = !!(attr->action &
 			       MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT);
-	bool esw_paired = mlx5_devcom_is_paired(attr->in_mdev->priv.devcom,
+	bool esw_paired = mlx5_devcom_is_paired(esw_attr->in_mdev->priv.devcom,
 						MLX5_DEVCOM_ESW_OFFLOADS);
 
 	if (!esw_paired)
 		return false;
 
-	if ((mlx5_lag_is_sriov(attr->in_mdev) ||
-	     mlx5_lag_is_multipath(attr->in_mdev)) &&
+	if ((mlx5_lag_is_sriov(esw_attr->in_mdev) ||
+	     mlx5_lag_is_multipath(esw_attr->in_mdev)) &&
 	    (is_rep_ingress || act_is_encap))
 		return true;
 
 	return false;
 }
 
+struct mlx5_flow_attr *
+mlx5_alloc_flow_attr(enum mlx5_flow_namespace_type type)
+{
+	u32 ex_attr_size = (type == MLX5_FLOW_NAMESPACE_FDB)  ?
+				sizeof(struct mlx5_esw_flow_attr) :
+				sizeof(struct mlx5_nic_flow_attr);
+	struct mlx5_flow_attr *attr;
+
+	return kzalloc(sizeof(*attr) + ex_attr_size, GFP_KERNEL);
+}
+
 static int
 mlx5e_alloc_flow(struct mlx5e_priv *priv, int attr_size,
 		 struct flow_cls_offload *f, unsigned long flow_flags,
@@ -4326,19 +4534,26 @@ mlx5e_alloc_flow(struct mlx5e_priv *priv, int attr_size,
 		 struct mlx5e_tc_flow **__flow)
 {
 	struct mlx5e_tc_flow_parse_attr *parse_attr;
+	struct mlx5_flow_attr *attr;
 	struct mlx5e_tc_flow *flow;
-	int out_index, err;
+	int err = -ENOMEM;
+	int out_index;
 
-	flow = kzalloc(sizeof(*flow) + attr_size, GFP_KERNEL);
+	flow = kzalloc(sizeof(*flow), GFP_KERNEL);
 	parse_attr = kvzalloc(sizeof(*parse_attr), GFP_KERNEL);
-	if (!parse_attr || !flow) {
-		err = -ENOMEM;
+	if (!parse_attr || !flow)
 		goto err_free;
-	}
 
-	flow->cookie = f->cookie;
 	flow->flags = flow_flags;
+	flow->cookie = f->cookie;
 	flow->priv = priv;
+
+	attr = mlx5_alloc_flow_attr(get_flow_name_space(flow));
+	if (!attr)
+		goto err_free;
+
+	flow->attr = attr;
+
 	for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++)
 		INIT_LIST_HEAD(&flow->encaps[out_index].list);
 	INIT_LIST_HEAD(&flow->hairpin);
@@ -4354,11 +4569,22 @@ mlx5e_alloc_flow(struct mlx5e_priv *priv, int attr_size,
 err_free:
 	kfree(flow);
 	kvfree(parse_attr);
+	kfree(attr);
 	return err;
 }
 
 static void
-mlx5e_flow_esw_attr_init(struct mlx5_esw_flow_attr *esw_attr,
+mlx5e_flow_attr_init(struct mlx5_flow_attr *attr,
+		     struct mlx5e_tc_flow_parse_attr *parse_attr,
+		     struct flow_cls_offload *f)
+{
+	attr->parse_attr = parse_attr;
+	attr->chain = f->common.chain_index;
+	attr->prio = f->common.prio;
+}
+
+static void
+mlx5e_flow_esw_attr_init(struct mlx5_flow_attr *attr,
 			 struct mlx5e_priv *priv,
 			 struct mlx5e_tc_flow_parse_attr *parse_attr,
 			 struct flow_cls_offload *f,
@@ -4366,10 +4592,9 @@ mlx5e_flow_esw_attr_init(struct mlx5_esw_flow_attr *esw_attr,
 			 struct mlx5_core_dev *in_mdev)
 {
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+	struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr;
 
-	esw_attr->parse_attr = parse_attr;
-	esw_attr->chain = f->common.chain_index;
-	esw_attr->prio = f->common.prio;
+	mlx5e_flow_attr_init(attr, parse_attr, f);
 
 	esw_attr->in_rep = in_rep;
 	esw_attr->in_mdev = in_mdev;
@@ -4403,7 +4628,7 @@ __mlx5e_add_fdb_flow(struct mlx5e_priv *priv,
 		goto out;
 
 	parse_attr->filter_dev = filter_dev;
-	mlx5e_flow_esw_attr_init(flow->esw_attr,
+	mlx5e_flow_esw_attr_init(flow->attr,
 				 priv, parse_attr,
 				 f, in_rep, in_mdev);
 
@@ -4413,8 +4638,8 @@ __mlx5e_add_fdb_flow(struct mlx5e_priv *priv,
 		goto err_free;
 
 	/* actions validation depends on parsing the ct matches first */
-	err = mlx5_tc_ct_parse_match(priv, &parse_attr->spec, f,
-				     &flow->esw_attr->ct_attr, extack);
+	err = mlx5_tc_ct_match_add(get_ct_priv(priv), &parse_attr->spec, f,
+				   &flow->attr->ct_attr, extack);
 	if (err)
 		goto err_free;
 
@@ -4445,6 +4670,7 @@ static int mlx5e_tc_add_fdb_peer_flow(struct flow_cls_offload *f,
 {
 	struct mlx5e_priv *priv = flow->priv, *peer_priv;
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch, *peer_esw;
+	struct mlx5_esw_flow_attr *attr = flow->attr->esw_attr;
 	struct mlx5_devcom *devcom = priv->mdev->priv.devcom;
 	struct mlx5e_tc_flow_parse_attr *parse_attr;
 	struct mlx5e_rep_priv *peer_urpriv;
@@ -4464,15 +4690,15 @@ static int mlx5e_tc_add_fdb_peer_flow(struct flow_cls_offload *f,
 	 * original flow and packets redirected from uplink use the
 	 * peer mdev.
 	 */
-	if (flow->esw_attr->in_rep->vport == MLX5_VPORT_UPLINK)
+	if (attr->in_rep->vport == MLX5_VPORT_UPLINK)
 		in_mdev = peer_priv->mdev;
 	else
 		in_mdev = priv->mdev;
 
-	parse_attr = flow->esw_attr->parse_attr;
+	parse_attr = flow->attr->parse_attr;
 	peer_flow = __mlx5e_add_fdb_flow(peer_priv, f, flow_flags,
 					 parse_attr->filter_dev,
-					 flow->esw_attr->in_rep, in_mdev);
+					 attr->in_rep, in_mdev);
 	if (IS_ERR(peer_flow)) {
 		err = PTR_ERR(peer_flow);
 		goto out;
@@ -4536,9 +4762,12 @@ mlx5e_add_nic_flow(struct mlx5e_priv *priv,
 	struct mlx5e_tc_flow *flow;
 	int attr_size, err;
 
-	/* multi-chain not supported for NIC rules */
-	if (!tc_cls_can_offload_and_chain0(priv->netdev, &f->common))
+	if (!MLX5_CAP_FLOWTABLE_NIC_RX(priv->mdev, ignore_flow_level)) {
+		if (!tc_cls_can_offload_and_chain0(priv->netdev, &f->common))
+			return -EOPNOTSUPP;
+	} else if (!tc_can_offload_extack(priv->netdev, f->common.extack)) {
 		return -EOPNOTSUPP;
+	}
 
 	flow_flags |= BIT(MLX5E_TC_FLOW_FLAG_NIC);
 	attr_size  = sizeof(struct mlx5_nic_flow_attr);
@@ -4548,11 +4777,18 @@ mlx5e_add_nic_flow(struct mlx5e_priv *priv,
 		goto out;
 
 	parse_attr->filter_dev = filter_dev;
+	mlx5e_flow_attr_init(flow->attr, parse_attr, f);
+
 	err = parse_cls_flower(flow->priv, flow, &parse_attr->spec,
 			       f, filter_dev);
 	if (err)
 		goto err_free;
 
+	err = mlx5_tc_ct_match_add(get_ct_priv(priv), &parse_attr->spec, f,
+				   &flow->attr->ct_attr, extack);
+	if (err)
+		goto err_free;
+
 	err = parse_tc_nic_actions(priv, &rule->action, parse_attr, flow, extack);
 	if (err)
 		goto err_free;
@@ -4562,14 +4798,12 @@ mlx5e_add_nic_flow(struct mlx5e_priv *priv,
 		goto err_free;
 
 	flow_flag_set(flow, OFFLOADED);
-	kvfree(parse_attr);
 	*__flow = flow;
 
 	return 0;
 
 err_free:
 	mlx5e_flow_put(priv, flow);
-	kvfree(parse_attr);
 out:
 	return err;
 }
@@ -4944,9 +5178,27 @@ static int mlx5e_tc_netdev_event(struct notifier_block *this,
 	return NOTIFY_DONE;
 }
 
+static int mlx5e_tc_nic_get_ft_size(struct mlx5_core_dev *dev)
+{
+	int tc_grp_size, tc_tbl_size;
+	u32 max_flow_counter;
+
+	max_flow_counter = (MLX5_CAP_GEN(dev, max_flow_counter_31_16) << 16) |
+			    MLX5_CAP_GEN(dev, max_flow_counter_15_0);
+
+	tc_grp_size = min_t(int, max_flow_counter, MLX5E_TC_TABLE_MAX_GROUP_SIZE);
+
+	tc_tbl_size = min_t(int, tc_grp_size * MLX5E_TC_TABLE_NUM_GROUPS,
+			    BIT(MLX5_CAP_FLOWTABLE_NIC_RX(dev, log_max_ft_size)));
+
+	return tc_tbl_size;
+}
+
 int mlx5e_tc_nic_init(struct mlx5e_priv *priv)
 {
 	struct mlx5e_tc_table *tc = &priv->fs.tc;
+	struct mlx5_core_dev *dev = priv->mdev;
+	struct mlx5_chains_attr attr = {};
 	int err;
 
 	mlx5e_mod_hdr_tbl_init(&tc->mod_hdr);
@@ -4958,6 +5210,27 @@ int mlx5e_tc_nic_init(struct mlx5e_priv *priv)
 	if (err)
 		return err;
 
+	if (MLX5_CAP_FLOWTABLE_NIC_RX(priv->mdev, ignore_flow_level)) {
+		attr.flags = MLX5_CHAINS_AND_PRIOS_SUPPORTED |
+			MLX5_CHAINS_IGNORE_FLOW_LEVEL_SUPPORTED;
+		attr.max_restore_tag = MLX5E_TC_TABLE_CHAIN_TAG_MASK;
+	}
+	attr.ns = MLX5_FLOW_NAMESPACE_KERNEL;
+	attr.max_ft_sz = mlx5e_tc_nic_get_ft_size(dev);
+	attr.max_grp_num = MLX5E_TC_TABLE_NUM_GROUPS;
+	attr.default_ft = priv->fs.vlan.ft.t;
+
+	tc->chains = mlx5_chains_create(dev, &attr);
+	if (IS_ERR(tc->chains)) {
+		err = PTR_ERR(tc->chains);
+		goto err_chains;
+	}
+
+	tc->ct = mlx5_tc_ct_init(priv, tc->chains, &priv->fs.tc.mod_hdr,
+				 MLX5_FLOW_NAMESPACE_KERNEL);
+	if (IS_ERR(tc->ct))
+		goto err_ct;
+
 	tc->netdevice_nb.notifier_call = mlx5e_tc_netdev_event;
 	err = register_netdevice_notifier_dev_net(priv->netdev,
 						  &tc->netdevice_nb,
@@ -4965,8 +5238,17 @@ int mlx5e_tc_nic_init(struct mlx5e_priv *priv)
 	if (err) {
 		tc->netdevice_nb.notifier_call = NULL;
 		mlx5_core_warn(priv->mdev, "Failed to register netdev notifier\n");
+		goto err_reg;
 	}
 
+	return 0;
+
+err_reg:
+	mlx5_tc_ct_clean(tc->ct);
+err_ct:
+	mlx5_chains_destroy(tc->chains);
+err_chains:
+	rhashtable_destroy(&tc->ht);
 	return err;
 }
 
@@ -4991,28 +5273,38 @@ void mlx5e_tc_nic_cleanup(struct mlx5e_priv *priv)
 	mlx5e_mod_hdr_tbl_destroy(&tc->mod_hdr);
 	mutex_destroy(&tc->hairpin_tbl_lock);
 
-	rhashtable_destroy(&tc->ht);
+	rhashtable_free_and_destroy(&tc->ht, _mlx5e_tc_del_flow, NULL);
 
 	if (!IS_ERR_OR_NULL(tc->t)) {
-		mlx5_destroy_flow_table(tc->t);
+		mlx5_chains_put_table(tc->chains, 0, 1, MLX5E_TC_FT_LEVEL);
 		tc->t = NULL;
 	}
 	mutex_destroy(&tc->t_lock);
+
+	mlx5_tc_ct_clean(tc->ct);
+	mlx5_chains_destroy(tc->chains);
 }
 
 int mlx5e_tc_esw_init(struct rhashtable *tc_ht)
 {
 	const size_t sz_enc_opts = sizeof(struct tunnel_match_enc_opts);
 	struct mlx5_rep_uplink_priv *uplink_priv;
-	struct mlx5e_rep_priv *priv;
+	struct mlx5e_rep_priv *rpriv;
 	struct mapping_ctx *mapping;
-	int err;
+	struct mlx5_eswitch *esw;
+	struct mlx5e_priv *priv;
+	int err = 0;
 
 	uplink_priv = container_of(tc_ht, struct mlx5_rep_uplink_priv, tc_ht);
-	priv = container_of(uplink_priv, struct mlx5e_rep_priv, uplink_priv);
+	rpriv = container_of(uplink_priv, struct mlx5e_rep_priv, uplink_priv);
+	priv = netdev_priv(rpriv->netdev);
+	esw = priv->mdev->priv.eswitch;
 
-	err = mlx5_tc_ct_init(uplink_priv);
-	if (err)
+	uplink_priv->ct_priv = mlx5_tc_ct_init(netdev_priv(priv->netdev),
+					       esw_chains(esw),
+					       &esw->offloads.mod_hdr,
+					       MLX5_FLOW_NAMESPACE_FDB);
+	if (IS_ERR(uplink_priv->ct_priv))
 		goto err_ct;
 
 	mapping = mapping_create(sizeof(struct tunnel_match_key),
@@ -5041,7 +5333,7 @@ err_ht_init:
 err_enc_opts_mapping:
 	mapping_destroy(uplink_priv->tunnel_mapping);
 err_tun_mapping:
-	mlx5_tc_ct_clean(uplink_priv);
+	mlx5_tc_ct_clean(uplink_priv->ct_priv);
 err_ct:
 	netdev_warn(priv->netdev,
 		    "Failed to initialize tc (eswitch), err: %d", err);
@@ -5055,10 +5347,11 @@ void mlx5e_tc_esw_cleanup(struct rhashtable *tc_ht)
 	rhashtable_free_and_destroy(tc_ht, _mlx5e_tc_del_flow, NULL);
 
 	uplink_priv = container_of(tc_ht, struct mlx5_rep_uplink_priv, tc_ht);
+
 	mapping_destroy(uplink_priv->tunnel_enc_opts_mapping);
 	mapping_destroy(uplink_priv->tunnel_mapping);
 
-	mlx5_tc_ct_clean(uplink_priv);
+	mlx5_tc_ct_clean(uplink_priv->ct_priv);
 }
 
 int mlx5e_tc_num_filters(struct mlx5e_priv *priv, unsigned long flags)
@@ -5123,3 +5416,44 @@ int mlx5e_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
 		return -EOPNOTSUPP;
 	}
 }
+
+bool mlx5e_tc_update_skb(struct mlx5_cqe64 *cqe,
+			 struct sk_buff *skb)
+{
+#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
+	u32 chain = 0, chain_tag, reg_b, zone_restore_id;
+	struct mlx5e_priv *priv = netdev_priv(skb->dev);
+	struct mlx5e_tc_table *tc = &priv->fs.tc;
+	struct tc_skb_ext *tc_skb_ext;
+	int err;
+
+	reg_b = be32_to_cpu(cqe->ft_metadata);
+
+	chain_tag = reg_b & MLX5E_TC_TABLE_CHAIN_TAG_MASK;
+
+	err = mlx5_get_chain_for_tag(nic_chains(priv), chain_tag, &chain);
+	if (err) {
+		netdev_dbg(priv->netdev,
+			   "Couldn't find chain for chain tag: %d, err: %d\n",
+			   chain_tag, err);
+		return false;
+	}
+
+	if (chain) {
+		tc_skb_ext = skb_ext_add(skb, TC_SKB_EXT);
+		if (WARN_ON(!tc_skb_ext))
+			return false;
+
+		tc_skb_ext->chain = chain;
+
+		zone_restore_id = (reg_b >> REG_MAPPING_SHIFT(NIC_ZONE_RESTORE_TO_REG)) &
+				  ZONE_RESTORE_MAX;
+
+		if (!mlx5e_tc_ct_restore_flow(tc->ct, skb,
+					      zone_restore_id))
+			return false;
+	}
+#endif /* CONFIG_NET_TC_SKB_EXT */
+
+	return true;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
index 437f680728fd..3b979008143d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
@@ -35,17 +35,57 @@
 
 #include <net/pkt_cls.h>
 #include "en.h"
+#include "eswitch.h"
+#include "en/tc_ct.h"
 
 #define MLX5E_TC_FLOW_ID_MASK 0x0000ffff
 
 #ifdef CONFIG_MLX5_ESWITCH
 
+#define NIC_FLOW_ATTR_SZ (sizeof(struct mlx5_flow_attr) +\
+			  sizeof(struct mlx5_nic_flow_attr))
+#define ESW_FLOW_ATTR_SZ (sizeof(struct mlx5_flow_attr) +\
+			  sizeof(struct mlx5_esw_flow_attr))
+#define ns_to_attr_sz(ns) (((ns) == MLX5_FLOW_NAMESPACE_FDB) ?\
+			    ESW_FLOW_ATTR_SZ :\
+			    NIC_FLOW_ATTR_SZ)
+
+
 int mlx5e_tc_num_filters(struct mlx5e_priv *priv, unsigned long flags);
 
 struct mlx5e_tc_update_priv {
 	struct net_device *tun_dev;
 };
 
+struct mlx5_nic_flow_attr {
+	u32 flow_tag;
+	u32 hairpin_tirn;
+	struct mlx5_flow_table *hairpin_ft;
+};
+
+struct mlx5_flow_attr {
+	u32 action;
+	struct mlx5_fc *counter;
+	struct mlx5_modify_hdr *modify_hdr;
+	struct mlx5_ct_attr ct_attr;
+	struct mlx5e_tc_flow_parse_attr *parse_attr;
+	u32 chain;
+	u16 prio;
+	u32 dest_chain;
+	struct mlx5_flow_table *ft;
+	struct mlx5_flow_table *dest_ft;
+	u8 inner_match_level;
+	u8 outer_match_level;
+	u32 flags;
+	union {
+		struct mlx5_esw_flow_attr esw_attr[0];
+		struct mlx5_nic_flow_attr nic_attr[0];
+	};
+};
+
+#define MLX5E_TC_TABLE_CHAIN_TAG_BITS 16
+#define MLX5E_TC_TABLE_CHAIN_TAG_MASK GENMASK(MLX5E_TC_TABLE_CHAIN_TAG_BITS - 1, 0)
+
 #if IS_ENABLED(CONFIG_MLX5_CLS_ACT)
 
 struct tunnel_match_key {
@@ -90,6 +130,7 @@ enum {
 
 int mlx5e_tc_esw_init(struct rhashtable *tc_ht);
 void mlx5e_tc_esw_cleanup(struct rhashtable *tc_ht);
+bool mlx5e_is_eswitch_flow(struct mlx5e_tc_flow *flow);
 
 int mlx5e_configure_flower(struct net_device *dev, struct mlx5e_priv *priv,
 			   struct flow_cls_offload *f, unsigned long flags);
@@ -133,6 +174,8 @@ enum mlx5e_tc_attr_to_reg {
 	MARK_TO_REG,
 	LABELS_TO_REG,
 	FTEID_TO_REG,
+	NIC_CHAIN_TO_REG,
+	NIC_ZONE_RESTORE_TO_REG,
 };
 
 struct mlx5e_tc_attr_to_reg_mapping {
@@ -150,6 +193,7 @@ bool mlx5e_is_valid_eswitch_fwd_dev(struct mlx5e_priv *priv,
 
 int mlx5e_tc_match_to_reg_set(struct mlx5_core_dev *mdev,
 			      struct mlx5e_tc_mod_hdr_acts *mod_hdr_acts,
+			      enum mlx5_flow_namespace_type ns,
 			      enum mlx5e_tc_attr_to_reg type,
 			      u32 data);
 
@@ -181,14 +225,42 @@ void mlx5e_tc_nic_cleanup(struct mlx5e_priv *priv);
 int mlx5e_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
 			    void *cb_priv);
 
+struct mlx5_flow_handle *
+mlx5e_add_offloaded_nic_rule(struct mlx5e_priv *priv,
+			     struct mlx5_flow_spec *spec,
+			     struct mlx5_flow_attr *attr);
+void mlx5e_del_offloaded_nic_rule(struct mlx5e_priv *priv,
+				  struct mlx5_flow_handle *rule,
+				  struct mlx5_flow_attr *attr);
+
+struct mlx5_flow_handle *
+mlx5_tc_rule_insert(struct mlx5e_priv *priv,
+		    struct mlx5_flow_spec *spec,
+		    struct mlx5_flow_attr *attr);
+void
+mlx5_tc_rule_delete(struct mlx5e_priv *priv,
+		    struct mlx5_flow_handle *rule,
+		    struct mlx5_flow_attr *attr);
+
 #else /* CONFIG_MLX5_CLS_ACT */
 static inline int  mlx5e_tc_nic_init(struct mlx5e_priv *priv) { return 0; }
 static inline void mlx5e_tc_nic_cleanup(struct mlx5e_priv *priv) {}
 static inline int
 mlx5e_setup_tc_block_cb(enum tc_setup_type type, void *type_data, void *cb_priv)
 { return -EOPNOTSUPP; }
+
 #endif /* CONFIG_MLX5_CLS_ACT */
 
+struct mlx5_flow_attr *mlx5_alloc_flow_attr(enum mlx5_flow_namespace_type type);
+
+struct mlx5_flow_handle *
+mlx5e_add_offloaded_nic_rule(struct mlx5e_priv *priv,
+			     struct mlx5_flow_spec *spec,
+			     struct mlx5_flow_attr *attr);
+void mlx5e_del_offloaded_nic_rule(struct mlx5e_priv *priv,
+				  struct mlx5_flow_handle *rule,
+				  struct mlx5_flow_attr *attr);
+
 #else /* CONFIG_MLX5_ESWITCH */
 static inline int  mlx5e_tc_nic_init(struct mlx5e_priv *priv) { return 0; }
 static inline void mlx5e_tc_nic_cleanup(struct mlx5e_priv *priv) {}
@@ -203,4 +275,29 @@ mlx5e_setup_tc_block_cb(enum tc_setup_type type, void *type_data, void *cb_priv)
 { return -EOPNOTSUPP; }
 #endif
 
+#if IS_ENABLED(CONFIG_MLX5_CLS_ACT)
+static inline bool mlx5e_cqe_regb_chain(struct mlx5_cqe64 *cqe)
+{
+#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
+	u32 chain, reg_b;
+
+	reg_b = be32_to_cpu(cqe->ft_metadata);
+
+	chain = reg_b & MLX5E_TC_TABLE_CHAIN_TAG_MASK;
+	if (chain)
+		return true;
+#endif
+
+	return false;
+}
+
+bool mlx5e_tc_update_skb(struct mlx5_cqe64 *cqe, struct sk_buff *skb);
+#else /* CONFIG_MLX5_CLS_ACT */
+static inline bool mlx5e_cqe_regb_chain(struct mlx5_cqe64 *cqe)
+{ return false; }
+static inline bool
+mlx5e_tc_update_skb(struct mlx5_cqe64 *cqe, struct sk_buff *skb)
+{ return true; }
+#endif
+
 #endif /* __MLX5_EN_TC_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index da596de3abba..13bd4f254ed7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -232,131 +232,180 @@ dma_unmap_wqe_err:
 	return -ENOMEM;
 }
 
+struct mlx5e_tx_attr {
+	u32 num_bytes;
+	u16 headlen;
+	u16 ihs;
+	__be16 mss;
+	u8 opcode;
+};
+
+struct mlx5e_tx_wqe_attr {
+	u16 ds_cnt;
+	u16 ds_cnt_inl;
+	u8 num_wqebbs;
+};
+
+static u8
+mlx5e_tx_wqe_inline_mode(struct mlx5e_txqsq *sq, struct sk_buff *skb,
+			 struct mlx5e_accel_tx_state *accel)
+{
+	u8 mode;
+
+#ifdef CONFIG_MLX5_EN_TLS
+	if (accel && accel->tls.tls_tisn)
+		return MLX5_INLINE_MODE_TCP_UDP;
+#endif
+
+	mode = sq->min_inline_mode;
+
+	if (skb_vlan_tag_present(skb) &&
+	    test_bit(MLX5E_SQ_STATE_VLAN_NEED_L2_INLINE, &sq->state))
+		mode = max_t(u8, MLX5_INLINE_MODE_L2, mode);
+
+	return mode;
+}
+
+static void mlx5e_sq_xmit_prepare(struct mlx5e_txqsq *sq, struct sk_buff *skb,
+				  struct mlx5e_accel_tx_state *accel,
+				  struct mlx5e_tx_attr *attr)
+{
+	struct mlx5e_sq_stats *stats = sq->stats;
+
+	if (skb_is_gso(skb)) {
+		u16 ihs = mlx5e_tx_get_gso_ihs(sq, skb);
+
+		*attr = (struct mlx5e_tx_attr) {
+			.opcode    = MLX5_OPCODE_LSO,
+			.mss       = cpu_to_be16(skb_shinfo(skb)->gso_size),
+			.ihs       = ihs,
+			.num_bytes = skb->len + (skb_shinfo(skb)->gso_segs - 1) * ihs,
+			.headlen   = skb_headlen(skb) - ihs,
+		};
+
+		stats->packets += skb_shinfo(skb)->gso_segs;
+	} else {
+		u8 mode = mlx5e_tx_wqe_inline_mode(sq, skb, accel);
+		u16 ihs = mlx5e_calc_min_inline(mode, skb);
+
+		*attr = (struct mlx5e_tx_attr) {
+			.opcode    = MLX5_OPCODE_SEND,
+			.mss       = cpu_to_be16(0),
+			.ihs       = ihs,
+			.num_bytes = max_t(unsigned int, skb->len, ETH_ZLEN),
+			.headlen   = skb_headlen(skb) - ihs,
+		};
+
+		stats->packets++;
+	}
+
+	stats->bytes += attr->num_bytes;
+}
+
+static void mlx5e_sq_calc_wqe_attr(struct sk_buff *skb, const struct mlx5e_tx_attr *attr,
+				   struct mlx5e_tx_wqe_attr *wqe_attr)
+{
+	u16 ds_cnt = MLX5E_TX_WQE_EMPTY_DS_COUNT;
+	u16 ds_cnt_inl = 0;
+
+	ds_cnt += !!attr->headlen + skb_shinfo(skb)->nr_frags;
+
+	if (attr->ihs) {
+		u16 inl = attr->ihs - INL_HDR_START_SZ;
+
+		if (skb_vlan_tag_present(skb))
+			inl += VLAN_HLEN;
+
+		ds_cnt_inl = DIV_ROUND_UP(inl, MLX5_SEND_WQE_DS);
+		ds_cnt += ds_cnt_inl;
+	}
+
+	*wqe_attr = (struct mlx5e_tx_wqe_attr) {
+		.ds_cnt     = ds_cnt,
+		.ds_cnt_inl = ds_cnt_inl,
+		.num_wqebbs = DIV_ROUND_UP(ds_cnt, MLX5_SEND_WQEBB_NUM_DS),
+	};
+}
+
+static void mlx5e_tx_skb_update_hwts_flags(struct sk_buff *skb)
+{
+	if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP))
+		skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
+}
+
+static void mlx5e_tx_check_stop(struct mlx5e_txqsq *sq)
+{
+	if (unlikely(!mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, sq->stop_room))) {
+		netif_tx_stop_queue(sq->txq);
+		sq->stats->stopped++;
+	}
+}
+
 static inline void
 mlx5e_txwqe_complete(struct mlx5e_txqsq *sq, struct sk_buff *skb,
-		     u8 opcode, u16 ds_cnt, u8 num_wqebbs, u32 num_bytes, u8 num_dma,
+		     const struct mlx5e_tx_attr *attr,
+		     const struct mlx5e_tx_wqe_attr *wqe_attr, u8 num_dma,
 		     struct mlx5e_tx_wqe_info *wi, struct mlx5_wqe_ctrl_seg *cseg,
 		     bool xmit_more)
 {
 	struct mlx5_wq_cyc *wq = &sq->wq;
 	bool send_doorbell;
 
-	wi->num_bytes = num_bytes;
-	wi->num_dma = num_dma;
-	wi->num_wqebbs = num_wqebbs;
-	wi->skb = skb;
+	*wi = (struct mlx5e_tx_wqe_info) {
+		.skb = skb,
+		.num_bytes = attr->num_bytes,
+		.num_dma = num_dma,
+		.num_wqebbs = wqe_attr->num_wqebbs,
+		.num_fifo_pkts = 0,
+	};
 
-	cseg->opmod_idx_opcode = cpu_to_be32((sq->pc << 8) | opcode);
-	cseg->qpn_ds           = cpu_to_be32((sq->sqn << 8) | ds_cnt);
+	cseg->opmod_idx_opcode = cpu_to_be32((sq->pc << 8) | attr->opcode);
+	cseg->qpn_ds           = cpu_to_be32((sq->sqn << 8) | wqe_attr->ds_cnt);
 
-	if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP))
-		skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
+	mlx5e_tx_skb_update_hwts_flags(skb);
 
 	sq->pc += wi->num_wqebbs;
-	if (unlikely(!mlx5e_wqc_has_room_for(wq, sq->cc, sq->pc, sq->stop_room))) {
-		netif_tx_stop_queue(sq->txq);
-		sq->stats->stopped++;
-	}
 
-	send_doorbell = __netdev_tx_sent_queue(sq->txq, num_bytes,
-					       xmit_more);
+	mlx5e_tx_check_stop(sq);
+
+	send_doorbell = __netdev_tx_sent_queue(sq->txq, attr->num_bytes, xmit_more);
 	if (send_doorbell)
 		mlx5e_notify_hw(wq, sq->pc, sq->uar_map, cseg);
 }
 
-void mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
-		   struct mlx5e_tx_wqe *wqe, u16 pi, bool xmit_more)
+static void
+mlx5e_sq_xmit_wqe(struct mlx5e_txqsq *sq, struct sk_buff *skb,
+		  const struct mlx5e_tx_attr *attr, const struct mlx5e_tx_wqe_attr *wqe_attr,
+		  struct mlx5e_tx_wqe *wqe, u16 pi, bool xmit_more)
 {
-	struct mlx5_wq_cyc *wq = &sq->wq;
 	struct mlx5_wqe_ctrl_seg *cseg;
 	struct mlx5_wqe_eth_seg  *eseg;
 	struct mlx5_wqe_data_seg *dseg;
 	struct mlx5e_tx_wqe_info *wi;
 
 	struct mlx5e_sq_stats *stats = sq->stats;
-	u16 headlen, ihs, contig_wqebbs_room;
-	u16 ds_cnt, ds_cnt_inl = 0;
-	u8 num_wqebbs, opcode;
-	u32 num_bytes;
 	int num_dma;
-	__be16 mss;
-
-	/* Calc ihs and ds cnt, no writes to wqe yet */
-	ds_cnt = sizeof(*wqe) / MLX5_SEND_WQE_DS;
-	if (skb_is_gso(skb)) {
-		opcode    = MLX5_OPCODE_LSO;
-		mss       = cpu_to_be16(skb_shinfo(skb)->gso_size);
-		ihs       = mlx5e_tx_get_gso_ihs(sq, skb);
-		num_bytes = skb->len + (skb_shinfo(skb)->gso_segs - 1) * ihs;
-		stats->packets += skb_shinfo(skb)->gso_segs;
-	} else {
-		u8 mode = mlx5e_tx_wqe_inline_mode(sq, &wqe->ctrl, skb);
-
-		opcode    = MLX5_OPCODE_SEND;
-		mss       = 0;
-		ihs       = mlx5e_calc_min_inline(mode, skb);
-		num_bytes = max_t(unsigned int, skb->len, ETH_ZLEN);
-		stats->packets++;
-	}
 
-	stats->bytes     += num_bytes;
 	stats->xmit_more += xmit_more;
 
-	headlen = skb->len - ihs - skb->data_len;
-	ds_cnt += !!headlen;
-	ds_cnt += skb_shinfo(skb)->nr_frags;
-
-	if (ihs) {
-		ihs += !!skb_vlan_tag_present(skb) * VLAN_HLEN;
-
-		ds_cnt_inl = DIV_ROUND_UP(ihs - INL_HDR_START_SZ, MLX5_SEND_WQE_DS);
-		ds_cnt += ds_cnt_inl;
-	}
-
-	num_wqebbs = DIV_ROUND_UP(ds_cnt, MLX5_SEND_WQEBB_NUM_DS);
-	contig_wqebbs_room = mlx5_wq_cyc_get_contig_wqebbs(wq, pi);
-	if (unlikely(contig_wqebbs_room < num_wqebbs)) {
-#ifdef CONFIG_MLX5_EN_IPSEC
-		struct mlx5_wqe_eth_seg cur_eth = wqe->eth;
-#endif
-#ifdef CONFIG_MLX5_EN_TLS
-		struct mlx5_wqe_ctrl_seg cur_ctrl = wqe->ctrl;
-#endif
-		mlx5e_fill_sq_frag_edge(sq, wq, pi, contig_wqebbs_room);
-		pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
-		wqe = MLX5E_TX_FETCH_WQE(sq, pi);
-#ifdef CONFIG_MLX5_EN_IPSEC
-		wqe->eth = cur_eth;
-#endif
-#ifdef CONFIG_MLX5_EN_TLS
-		wqe->ctrl = cur_ctrl;
-#endif
-	}
-
 	/* fill wqe */
 	wi   = &sq->db.wqe_info[pi];
 	cseg = &wqe->ctrl;
 	eseg = &wqe->eth;
 	dseg =  wqe->data;
 
-#if IS_ENABLED(CONFIG_GENEVE)
-	if (skb->encapsulation)
-		mlx5e_tx_tunnel_accel(skb, eseg);
-#endif
-	mlx5e_txwqe_build_eseg_csum(sq, skb, eseg);
-
-	eseg->mss = mss;
+	eseg->mss = attr->mss;
 
-	if (ihs) {
-		eseg->inline_hdr.sz = cpu_to_be16(ihs);
+	if (attr->ihs) {
 		if (skb_vlan_tag_present(skb)) {
-			ihs -= VLAN_HLEN;
-			mlx5e_insert_vlan(eseg->inline_hdr.start, skb, ihs);
+			eseg->inline_hdr.sz = cpu_to_be16(attr->ihs + VLAN_HLEN);
+			mlx5e_insert_vlan(eseg->inline_hdr.start, skb, attr->ihs);
 			stats->added_vlan_packets++;
 		} else {
-			memcpy(eseg->inline_hdr.start, skb->data, ihs);
+			eseg->inline_hdr.sz = cpu_to_be16(attr->ihs);
+			memcpy(eseg->inline_hdr.start, skb->data, attr->ihs);
 		}
-		dseg += ds_cnt_inl;
+		dseg += wqe_attr->ds_cnt_inl;
 	} else if (skb_vlan_tag_present(skb)) {
 		eseg->insert.type = cpu_to_be16(MLX5_ETH_WQE_INSERT_VLAN);
 		if (skb->vlan_proto == cpu_to_be16(ETH_P_8021AD))
@@ -365,12 +414,12 @@ void mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 		stats->added_vlan_packets++;
 	}
 
-	num_dma = mlx5e_txwqe_build_dsegs(sq, skb, skb->data + ihs, headlen, dseg);
+	num_dma = mlx5e_txwqe_build_dsegs(sq, skb, skb->data + attr->ihs,
+					  attr->headlen, dseg);
 	if (unlikely(num_dma < 0))
 		goto err_drop;
 
-	mlx5e_txwqe_complete(sq, skb, opcode, ds_cnt, num_wqebbs, num_bytes,
-			     num_dma, wi, cseg, xmit_more);
+	mlx5e_txwqe_complete(sq, skb, attr, wqe_attr, num_dma, wi, cseg, xmit_more);
 
 	return;
 
@@ -379,10 +428,172 @@ err_drop:
 	dev_kfree_skb_any(skb);
 }
 
+static bool mlx5e_tx_skb_supports_mpwqe(struct sk_buff *skb, struct mlx5e_tx_attr *attr)
+{
+	return !skb_is_nonlinear(skb) && !skb_vlan_tag_present(skb) && !attr->ihs;
+}
+
+static bool mlx5e_tx_mpwqe_same_eseg(struct mlx5e_txqsq *sq, struct mlx5_wqe_eth_seg *eseg)
+{
+	struct mlx5e_tx_mpwqe *session = &sq->mpwqe;
+
+	/* Assumes the session is already running and has at least one packet. */
+	return !memcmp(&session->wqe->eth, eseg, MLX5E_ACCEL_ESEG_LEN);
+}
+
+static void mlx5e_tx_mpwqe_session_start(struct mlx5e_txqsq *sq,
+					 struct mlx5_wqe_eth_seg *eseg)
+{
+	struct mlx5e_tx_mpwqe *session = &sq->mpwqe;
+	struct mlx5e_tx_wqe *wqe;
+	u16 pi;
+
+	pi = mlx5e_txqsq_get_next_pi(sq, MLX5E_TX_MPW_MAX_WQEBBS);
+	wqe = MLX5E_TX_FETCH_WQE(sq, pi);
+	prefetchw(wqe->data);
+
+	*session = (struct mlx5e_tx_mpwqe) {
+		.wqe = wqe,
+		.bytes_count = 0,
+		.ds_count = MLX5E_TX_WQE_EMPTY_DS_COUNT,
+		.pkt_count = 0,
+		.inline_on = 0,
+	};
+
+	memcpy(&session->wqe->eth, eseg, MLX5E_ACCEL_ESEG_LEN);
+
+	sq->stats->mpwqe_blks++;
+}
+
+static bool mlx5e_tx_mpwqe_session_is_active(struct mlx5e_txqsq *sq)
+{
+	return sq->mpwqe.wqe;
+}
+
+static void mlx5e_tx_mpwqe_add_dseg(struct mlx5e_txqsq *sq, struct mlx5e_xmit_data *txd)
+{
+	struct mlx5e_tx_mpwqe *session = &sq->mpwqe;
+	struct mlx5_wqe_data_seg *dseg;
+
+	dseg = (struct mlx5_wqe_data_seg *)session->wqe + session->ds_count;
+
+	session->pkt_count++;
+	session->bytes_count += txd->len;
+
+	dseg->addr = cpu_to_be64(txd->dma_addr);
+	dseg->byte_count = cpu_to_be32(txd->len);
+	dseg->lkey = sq->mkey_be;
+	session->ds_count++;
+
+	sq->stats->mpwqe_pkts++;
+}
+
+static struct mlx5_wqe_ctrl_seg *mlx5e_tx_mpwqe_session_complete(struct mlx5e_txqsq *sq)
+{
+	struct mlx5e_tx_mpwqe *session = &sq->mpwqe;
+	u8 ds_count = session->ds_count;
+	struct mlx5_wqe_ctrl_seg *cseg;
+	struct mlx5e_tx_wqe_info *wi;
+	u16 pi;
+
+	cseg = &session->wqe->ctrl;
+	cseg->opmod_idx_opcode = cpu_to_be32((sq->pc << 8) | MLX5_OPCODE_ENHANCED_MPSW);
+	cseg->qpn_ds = cpu_to_be32((sq->sqn << 8) | ds_count);
+
+	pi = mlx5_wq_cyc_ctr2ix(&sq->wq, sq->pc);
+	wi = &sq->db.wqe_info[pi];
+	*wi = (struct mlx5e_tx_wqe_info) {
+		.skb = NULL,
+		.num_bytes = session->bytes_count,
+		.num_wqebbs = DIV_ROUND_UP(ds_count, MLX5_SEND_WQEBB_NUM_DS),
+		.num_dma = session->pkt_count,
+		.num_fifo_pkts = session->pkt_count,
+	};
+
+	sq->pc += wi->num_wqebbs;
+
+	session->wqe = NULL;
+
+	mlx5e_tx_check_stop(sq);
+
+	return cseg;
+}
+
+static void
+mlx5e_sq_xmit_mpwqe(struct mlx5e_txqsq *sq, struct sk_buff *skb,
+		    struct mlx5_wqe_eth_seg *eseg, bool xmit_more)
+{
+	struct mlx5_wqe_ctrl_seg *cseg;
+	struct mlx5e_xmit_data txd;
+
+	if (!mlx5e_tx_mpwqe_session_is_active(sq)) {
+		mlx5e_tx_mpwqe_session_start(sq, eseg);
+	} else if (!mlx5e_tx_mpwqe_same_eseg(sq, eseg)) {
+		mlx5e_tx_mpwqe_session_complete(sq);
+		mlx5e_tx_mpwqe_session_start(sq, eseg);
+	}
+
+	sq->stats->xmit_more += xmit_more;
+
+	txd.data = skb->data;
+	txd.len = skb->len;
+
+	txd.dma_addr = dma_map_single(sq->pdev, txd.data, txd.len, DMA_TO_DEVICE);
+	if (unlikely(dma_mapping_error(sq->pdev, txd.dma_addr)))
+		goto err_unmap;
+	mlx5e_dma_push(sq, txd.dma_addr, txd.len, MLX5E_DMA_MAP_SINGLE);
+
+	mlx5e_skb_fifo_push(sq, skb);
+
+	mlx5e_tx_mpwqe_add_dseg(sq, &txd);
+
+	mlx5e_tx_skb_update_hwts_flags(skb);
+
+	if (unlikely(mlx5e_tx_mpwqe_is_full(&sq->mpwqe))) {
+		/* Might stop the queue and affect the retval of __netdev_tx_sent_queue. */
+		cseg = mlx5e_tx_mpwqe_session_complete(sq);
+
+		if (__netdev_tx_sent_queue(sq->txq, txd.len, xmit_more))
+			mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, cseg);
+	} else if (__netdev_tx_sent_queue(sq->txq, txd.len, xmit_more)) {
+		/* Might stop the queue, but we were asked to ring the doorbell anyway. */
+		cseg = mlx5e_tx_mpwqe_session_complete(sq);
+
+		mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, cseg);
+	}
+
+	return;
+
+err_unmap:
+	mlx5e_dma_unmap_wqe_err(sq, 1);
+	sq->stats->dropped++;
+	dev_kfree_skb_any(skb);
+}
+
+void mlx5e_tx_mpwqe_ensure_complete(struct mlx5e_txqsq *sq)
+{
+	/* Unlikely in non-MPWQE workloads; not important in MPWQE workloads. */
+	if (unlikely(mlx5e_tx_mpwqe_session_is_active(sq)))
+		mlx5e_tx_mpwqe_session_complete(sq);
+}
+
+static bool mlx5e_txwqe_build_eseg(struct mlx5e_priv *priv, struct mlx5e_txqsq *sq,
+				   struct sk_buff *skb, struct mlx5_wqe_eth_seg *eseg)
+{
+	if (unlikely(!mlx5e_accel_tx_eseg(priv, sq, skb, eseg)))
+		return false;
+
+	mlx5e_txwqe_build_eseg_csum(sq, skb, eseg);
+
+	return true;
+}
+
 netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct mlx5e_accel_tx_state accel = {};
+	struct mlx5e_tx_wqe_attr wqe_attr;
+	struct mlx5e_tx_attr attr;
 	struct mlx5e_tx_wqe *wqe;
 	struct mlx5e_txqsq *sq;
 	u16 pi;
@@ -391,21 +602,91 @@ netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	/* May send SKBs and WQEs. */
 	if (unlikely(!mlx5e_accel_tx_begin(dev, sq, skb, &accel)))
-		goto out;
+		return NETDEV_TX_OK;
 
-	pi = mlx5_wq_cyc_ctr2ix(&sq->wq, sq->pc);
+	mlx5e_sq_xmit_prepare(sq, skb, &accel, &attr);
+
+	if (test_bit(MLX5E_SQ_STATE_MPWQE, &sq->state)) {
+		if (mlx5e_tx_skb_supports_mpwqe(skb, &attr)) {
+			struct mlx5_wqe_eth_seg eseg = {};
+
+			if (unlikely(!mlx5e_txwqe_build_eseg(priv, sq, skb, &eseg)))
+				return NETDEV_TX_OK;
+
+			mlx5e_sq_xmit_mpwqe(sq, skb, &eseg, netdev_xmit_more());
+			return NETDEV_TX_OK;
+		}
+
+		mlx5e_tx_mpwqe_ensure_complete(sq);
+	}
+
+	mlx5e_sq_calc_wqe_attr(skb, &attr, &wqe_attr);
+	pi = mlx5e_txqsq_get_next_pi(sq, wqe_attr.num_wqebbs);
 	wqe = MLX5E_TX_FETCH_WQE(sq, pi);
 
 	/* May update the WQE, but may not post other WQEs. */
-	if (unlikely(!mlx5e_accel_tx_finish(priv, sq, skb, wqe, &accel)))
-		goto out;
+	mlx5e_accel_tx_finish(sq, wqe, &accel);
+	if (unlikely(!mlx5e_txwqe_build_eseg(priv, sq, skb, &wqe->eth)))
+		return NETDEV_TX_OK;
 
-	mlx5e_sq_xmit(sq, skb, wqe, pi, netdev_xmit_more());
+	mlx5e_sq_xmit_wqe(sq, skb, &attr, &wqe_attr, wqe, pi, netdev_xmit_more());
 
-out:
 	return NETDEV_TX_OK;
 }
 
+void mlx5e_sq_xmit_simple(struct mlx5e_txqsq *sq, struct sk_buff *skb, bool xmit_more)
+{
+	struct mlx5e_tx_wqe_attr wqe_attr;
+	struct mlx5e_tx_attr attr;
+	struct mlx5e_tx_wqe *wqe;
+	u16 pi;
+
+	mlx5e_sq_xmit_prepare(sq, skb, NULL, &attr);
+	mlx5e_sq_calc_wqe_attr(skb, &attr, &wqe_attr);
+	pi = mlx5e_txqsq_get_next_pi(sq, wqe_attr.num_wqebbs);
+	wqe = MLX5E_TX_FETCH_WQE(sq, pi);
+	mlx5e_txwqe_build_eseg_csum(sq, skb, &wqe->eth);
+	mlx5e_sq_xmit_wqe(sq, skb, &attr, &wqe_attr, wqe, pi, xmit_more);
+}
+
+static void mlx5e_tx_wi_dma_unmap(struct mlx5e_txqsq *sq, struct mlx5e_tx_wqe_info *wi,
+				  u32 *dma_fifo_cc)
+{
+	int i;
+
+	for (i = 0; i < wi->num_dma; i++) {
+		struct mlx5e_sq_dma *dma = mlx5e_dma_get(sq, (*dma_fifo_cc)++);
+
+		mlx5e_tx_dma_unmap(sq->pdev, dma);
+	}
+}
+
+static void mlx5e_consume_skb(struct mlx5e_txqsq *sq, struct sk_buff *skb,
+			      struct mlx5_cqe64 *cqe, int napi_budget)
+{
+	if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) {
+		struct skb_shared_hwtstamps hwts = {};
+		u64 ts = get_cqe_ts(cqe);
+
+		hwts.hwtstamp = mlx5_timecounter_cyc2time(sq->clock, ts);
+		skb_tstamp_tx(skb, &hwts);
+	}
+
+	napi_consume_skb(skb, napi_budget);
+}
+
+static void mlx5e_tx_wi_consume_fifo_skbs(struct mlx5e_txqsq *sq, struct mlx5e_tx_wqe_info *wi,
+					  struct mlx5_cqe64 *cqe, int napi_budget)
+{
+	int i;
+
+	for (i = 0; i < wi->num_fifo_pkts; i++) {
+		struct sk_buff *skb = mlx5e_skb_fifo_pop(sq);
+
+		mlx5e_consume_skb(sq, skb, cqe, napi_budget);
+	}
+}
+
 bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 {
 	struct mlx5e_sq_stats *stats;
@@ -451,42 +732,33 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 		wqe_counter = be16_to_cpu(cqe->wqe_counter);
 
 		do {
-			struct sk_buff *skb;
-			int j;
-
 			last_wqe = (sqcc == wqe_counter);
 
 			ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sqcc);
 			wi = &sq->db.wqe_info[ci];
-			skb = wi->skb;
 
-			if (unlikely(!skb)) {
-				mlx5e_ktls_tx_handle_resync_dump_comp(sq, wi, &dma_fifo_cc);
-				sqcc += wi->num_wqebbs;
-				continue;
-			}
+			sqcc += wi->num_wqebbs;
 
-			if (unlikely(skb_shinfo(skb)->tx_flags &
-				     SKBTX_HW_TSTAMP)) {
-				struct skb_shared_hwtstamps hwts = {};
+			if (likely(wi->skb)) {
+				mlx5e_tx_wi_dma_unmap(sq, wi, &dma_fifo_cc);
+				mlx5e_consume_skb(sq, wi->skb, cqe, napi_budget);
 
-				hwts.hwtstamp =
-					mlx5_timecounter_cyc2time(sq->clock,
-								  get_cqe_ts(cqe));
-				skb_tstamp_tx(skb, &hwts);
+				npkts++;
+				nbytes += wi->num_bytes;
+				continue;
 			}
 
-			for (j = 0; j < wi->num_dma; j++) {
-				struct mlx5e_sq_dma *dma =
-					mlx5e_dma_get(sq, dma_fifo_cc++);
+			if (unlikely(mlx5e_ktls_tx_try_handle_resync_dump_comp(sq, wi,
+									       &dma_fifo_cc)))
+				continue;
 
-				mlx5e_tx_dma_unmap(sq->pdev, dma);
-			}
+			if (wi->num_fifo_pkts) {
+				mlx5e_tx_wi_dma_unmap(sq, wi, &dma_fifo_cc);
+				mlx5e_tx_wi_consume_fifo_skbs(sq, wi, cqe, napi_budget);
 
-			npkts++;
-			nbytes += wi->num_bytes;
-			sqcc += wi->num_wqebbs;
-			napi_consume_skb(skb, napi_budget);
+				npkts += wi->num_fifo_pkts;
+				nbytes += wi->num_bytes;
+			}
 		} while (!last_wqe);
 
 		if (unlikely(get_cqe_opcode(cqe) == MLX5_CQE_REQ_ERR)) {
@@ -525,13 +797,19 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 	return (i == MLX5E_TX_CQ_POLL_BUDGET);
 }
 
+static void mlx5e_tx_wi_kfree_fifo_skbs(struct mlx5e_txqsq *sq, struct mlx5e_tx_wqe_info *wi)
+{
+	int i;
+
+	for (i = 0; i < wi->num_fifo_pkts; i++)
+		dev_kfree_skb_any(mlx5e_skb_fifo_pop(sq));
+}
+
 void mlx5e_free_txqsq_descs(struct mlx5e_txqsq *sq)
 {
 	struct mlx5e_tx_wqe_info *wi;
 	u32 dma_fifo_cc, nbytes = 0;
 	u16 ci, sqcc, npkts = 0;
-	struct sk_buff *skb;
-	int i;
 
 	sqcc = sq->cc;
 	dma_fifo_cc = sq->dma_fifo_cc;
@@ -539,25 +817,28 @@ void mlx5e_free_txqsq_descs(struct mlx5e_txqsq *sq)
 	while (sqcc != sq->pc) {
 		ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sqcc);
 		wi = &sq->db.wqe_info[ci];
-		skb = wi->skb;
 
-		if (!skb) {
-			mlx5e_ktls_tx_handle_resync_dump_comp(sq, wi, &dma_fifo_cc);
-			sqcc += wi->num_wqebbs;
+		sqcc += wi->num_wqebbs;
+
+		if (likely(wi->skb)) {
+			mlx5e_tx_wi_dma_unmap(sq, wi, &dma_fifo_cc);
+			dev_kfree_skb_any(wi->skb);
+
+			npkts++;
+			nbytes += wi->num_bytes;
 			continue;
 		}
 
-		for (i = 0; i < wi->num_dma; i++) {
-			struct mlx5e_sq_dma *dma =
-				mlx5e_dma_get(sq, dma_fifo_cc++);
+		if (unlikely(mlx5e_ktls_tx_try_handle_resync_dump_comp(sq, wi, &dma_fifo_cc)))
+			continue;
 
-			mlx5e_tx_dma_unmap(sq->pdev, dma);
-		}
+		if (wi->num_fifo_pkts) {
+			mlx5e_tx_wi_dma_unmap(sq, wi, &dma_fifo_cc);
+			mlx5e_tx_wi_kfree_fifo_skbs(sq, wi);
 
-		dev_kfree_skb_any(skb);
-		npkts++;
-		nbytes += wi->num_bytes;
-		sqcc += wi->num_wqebbs;
+			npkts += wi->num_fifo_pkts;
+			nbytes += wi->num_bytes;
+		}
 	}
 
 	sq->dma_fifo_cc = dma_fifo_cc;
@@ -576,9 +857,34 @@ mlx5i_txwqe_build_datagram(struct mlx5_av *av, u32 dqpn, u32 dqkey,
 	dseg->av.key.qkey.qkey = cpu_to_be32(dqkey);
 }
 
+static void mlx5i_sq_calc_wqe_attr(struct sk_buff *skb,
+				   const struct mlx5e_tx_attr *attr,
+				   struct mlx5e_tx_wqe_attr *wqe_attr)
+{
+	u16 ds_cnt = sizeof(struct mlx5i_tx_wqe) / MLX5_SEND_WQE_DS;
+	u16 ds_cnt_inl = 0;
+
+	ds_cnt += !!attr->headlen + skb_shinfo(skb)->nr_frags;
+
+	if (attr->ihs) {
+		u16 inl = attr->ihs - INL_HDR_START_SZ;
+
+		ds_cnt_inl = DIV_ROUND_UP(inl, MLX5_SEND_WQE_DS);
+		ds_cnt += ds_cnt_inl;
+	}
+
+	*wqe_attr = (struct mlx5e_tx_wqe_attr) {
+		.ds_cnt     = ds_cnt,
+		.ds_cnt_inl = ds_cnt_inl,
+		.num_wqebbs = DIV_ROUND_UP(ds_cnt, MLX5_SEND_WQEBB_NUM_DS),
+	};
+}
+
 void mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 		   struct mlx5_av *av, u32 dqpn, u32 dqkey, bool xmit_more)
 {
+	struct mlx5e_tx_wqe_attr wqe_attr;
+	struct mlx5e_tx_attr attr;
 	struct mlx5i_tx_wqe *wqe;
 
 	struct mlx5_wqe_datagram_seg *datagram;
@@ -588,47 +894,17 @@ void mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 	struct mlx5e_tx_wqe_info *wi;
 
 	struct mlx5e_sq_stats *stats = sq->stats;
-	u16 ds_cnt, ds_cnt_inl = 0;
-	u8 num_wqebbs, opcode;
-	u16 headlen, ihs, pi;
-	u32 num_bytes;
 	int num_dma;
-	__be16 mss;
+	u16 pi;
 
-	/* Calc ihs and ds cnt, no writes to wqe yet */
-	ds_cnt = sizeof(*wqe) / MLX5_SEND_WQE_DS;
-	if (skb_is_gso(skb)) {
-		opcode    = MLX5_OPCODE_LSO;
-		mss       = cpu_to_be16(skb_shinfo(skb)->gso_size);
-		ihs       = mlx5e_tx_get_gso_ihs(sq, skb);
-		num_bytes = skb->len + (skb_shinfo(skb)->gso_segs - 1) * ihs;
-		stats->packets += skb_shinfo(skb)->gso_segs;
-	} else {
-		u8 mode = mlx5e_tx_wqe_inline_mode(sq, NULL, skb);
+	mlx5e_sq_xmit_prepare(sq, skb, NULL, &attr);
+	mlx5i_sq_calc_wqe_attr(skb, &attr, &wqe_attr);
 
-		opcode    = MLX5_OPCODE_SEND;
-		mss       = 0;
-		ihs       = mlx5e_calc_min_inline(mode, skb);
-		num_bytes = max_t(unsigned int, skb->len, ETH_ZLEN);
-		stats->packets++;
-	}
+	pi = mlx5e_txqsq_get_next_pi(sq, wqe_attr.num_wqebbs);
+	wqe = MLX5I_SQ_FETCH_WQE(sq, pi);
 
-	stats->bytes     += num_bytes;
 	stats->xmit_more += xmit_more;
 
-	headlen = skb->len - ihs - skb->data_len;
-	ds_cnt += !!headlen;
-	ds_cnt += skb_shinfo(skb)->nr_frags;
-
-	if (ihs) {
-		ds_cnt_inl = DIV_ROUND_UP(ihs - INL_HDR_START_SZ, MLX5_SEND_WQE_DS);
-		ds_cnt += ds_cnt_inl;
-	}
-
-	num_wqebbs = DIV_ROUND_UP(ds_cnt, MLX5_SEND_WQEBB_NUM_DS);
-	pi = mlx5e_txqsq_get_next_pi(sq, num_wqebbs);
-	wqe = MLX5I_SQ_FETCH_WQE(sq, pi);
-
 	/* fill wqe */
 	wi       = &sq->db.wqe_info[pi];
 	cseg     = &wqe->ctrl;
@@ -640,20 +916,20 @@ void mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 
 	mlx5e_txwqe_build_eseg_csum(sq, skb, eseg);
 
-	eseg->mss = mss;
+	eseg->mss = attr.mss;
 
-	if (ihs) {
-		memcpy(eseg->inline_hdr.start, skb->data, ihs);
-		eseg->inline_hdr.sz = cpu_to_be16(ihs);
-		dseg += ds_cnt_inl;
+	if (attr.ihs) {
+		memcpy(eseg->inline_hdr.start, skb->data, attr.ihs);
+		eseg->inline_hdr.sz = cpu_to_be16(attr.ihs);
+		dseg += wqe_attr.ds_cnt_inl;
 	}
 
-	num_dma = mlx5e_txwqe_build_dsegs(sq, skb, skb->data + ihs, headlen, dseg);
+	num_dma = mlx5e_txwqe_build_dsegs(sq, skb, skb->data + attr.ihs,
+					  attr.headlen, dseg);
 	if (unlikely(num_dma < 0))
 		goto err_drop;
 
-	mlx5e_txwqe_complete(sq, skb, opcode, ds_cnt, num_wqebbs, num_bytes,
-			     num_dma, wi, cseg, xmit_more);
+	mlx5e_txwqe_complete(sq, skb, &attr, &wqe_attr, num_dma, wi, cseg, xmit_more);
 
 	return;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
index de10b06bade5..d5868670f8a5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
@@ -121,13 +121,17 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget)
 	struct mlx5e_xdpsq *xsksq = &c->xsksq;
 	struct mlx5e_rq *xskrq = &c->xskrq;
 	struct mlx5e_rq *rq = &c->rq;
-	bool xsk_open = test_bit(MLX5E_CHANNEL_STATE_XSK, c->state);
 	bool aff_change = false;
 	bool busy_xsk = false;
 	bool busy = false;
 	int work_done = 0;
+	bool xsk_open;
 	int i;
 
+	rcu_read_lock();
+
+	xsk_open = test_bit(MLX5E_CHANNEL_STATE_XSK, c->state);
+
 	ch_stats->poll++;
 
 	for (i = 0; i < c->num_tc; i++)
@@ -167,8 +171,10 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget)
 	busy |= busy_xsk;
 
 	if (busy) {
-		if (likely(mlx5e_channel_no_affinity_change(c)))
-			return budget;
+		if (likely(mlx5e_channel_no_affinity_change(c))) {
+			work_done = budget;
+			goto out;
+		}
 		ch_stats->aff_change++;
 		aff_change = true;
 		if (budget && work_done == budget)
@@ -176,7 +182,7 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget)
 	}
 
 	if (unlikely(!napi_complete_done(napi, work_done)))
-		return work_done;
+		goto out;
 
 	ch_stats->arm++;
 
@@ -203,6 +209,9 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget)
 		ch_stats->force_irq++;
 	}
 
+out:
+	rcu_read_unlock();
+
 	return work_done;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_ofld.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_ofld.c
index 07b2acd7e6b3..c3faae67e4d6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_ofld.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_ofld.c
@@ -148,6 +148,11 @@ static void esw_acl_egress_ofld_groups_destroy(struct mlx5_vport *vport)
 	esw_acl_egress_vlan_grp_destroy(vport);
 }
 
+static bool esw_acl_egress_needed(const struct mlx5_eswitch *esw, u16 vport_num)
+{
+	return mlx5_eswitch_is_vf_vport(esw, vport_num);
+}
+
 int esw_acl_egress_ofld_setup(struct mlx5_eswitch *esw, struct mlx5_vport *vport)
 {
 	int table_size = 0;
@@ -157,6 +162,9 @@ int esw_acl_egress_ofld_setup(struct mlx5_eswitch *esw, struct mlx5_vport *vport
 	    !MLX5_CAP_GEN(esw->dev, prio_tag_required))
 		return 0;
 
+	if (!esw_acl_egress_needed(esw, vport->vport))
+		return 0;
+
 	esw_acl_egress_ofld_rules_destroy(vport);
 
 	if (mlx5_esw_acl_egress_fwd2vport_supported(esw))
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/chains.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/chains.c
deleted file mode 100644
index d5bf908dfecd..000000000000
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/chains.c
+++ /dev/null
@@ -1,944 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
-// Copyright (c) 2020 Mellanox Technologies.
-
-#include <linux/mlx5/driver.h>
-#include <linux/mlx5/mlx5_ifc.h>
-#include <linux/mlx5/fs.h>
-
-#include "esw/chains.h"
-#include "en/mapping.h"
-#include "mlx5_core.h"
-#include "fs_core.h"
-#include "eswitch.h"
-#include "en.h"
-#include "en_tc.h"
-
-#define esw_chains_priv(esw) ((esw)->fdb_table.offloads.esw_chains_priv)
-#define esw_chains_lock(esw) (esw_chains_priv(esw)->lock)
-#define esw_chains_ht(esw) (esw_chains_priv(esw)->chains_ht)
-#define esw_chains_mapping(esw) (esw_chains_priv(esw)->chains_mapping)
-#define esw_prios_ht(esw) (esw_chains_priv(esw)->prios_ht)
-#define fdb_pool_left(esw) (esw_chains_priv(esw)->fdb_left)
-#define tc_slow_fdb(esw) ((esw)->fdb_table.offloads.slow_fdb)
-#define tc_end_fdb(esw) (esw_chains_priv(esw)->tc_end_fdb)
-#define fdb_ignore_flow_level_supported(esw) \
-	(MLX5_CAP_ESW_FLOWTABLE_FDB((esw)->dev, ignore_flow_level))
-#define fdb_modify_header_fwd_to_table_supported(esw) \
-	(MLX5_CAP_ESW_FLOWTABLE((esw)->dev, fdb_modify_header_fwd_to_table))
-
-/* Firmware currently has 4 pool of 4 sizes that it supports (ESW_POOLS),
- * and a virtual memory region of 16M (ESW_SIZE), this region is duplicated
- * for each flow table pool. We can allocate up to 16M of each pool,
- * and we keep track of how much we used via get_next_avail_sz_from_pool.
- * Firmware doesn't report any of this for now.
- * ESW_POOL is expected to be sorted from large to small and match firmware
- * pools.
- */
-#define ESW_SIZE (16 * 1024 * 1024)
-static const unsigned int ESW_POOLS[] = { 4 * 1024 * 1024,
-					  1 * 1024 * 1024,
-					  64 * 1024,
-					  128 };
-#define ESW_FT_TBL_SZ (64 * 1024)
-
-struct mlx5_esw_chains_priv {
-	struct rhashtable chains_ht;
-	struct rhashtable prios_ht;
-	/* Protects above chains_ht and prios_ht */
-	struct mutex lock;
-
-	struct mlx5_flow_table *tc_end_fdb;
-	struct mapping_ctx *chains_mapping;
-
-	int fdb_left[ARRAY_SIZE(ESW_POOLS)];
-};
-
-struct fdb_chain {
-	struct rhash_head node;
-
-	u32 chain;
-
-	int ref;
-	int id;
-
-	struct mlx5_eswitch *esw;
-	struct list_head prios_list;
-	struct mlx5_flow_handle *restore_rule;
-	struct mlx5_modify_hdr *miss_modify_hdr;
-};
-
-struct fdb_prio_key {
-	u32 chain;
-	u32 prio;
-	u32 level;
-};
-
-struct fdb_prio {
-	struct rhash_head node;
-	struct list_head list;
-
-	struct fdb_prio_key key;
-
-	int ref;
-
-	struct fdb_chain *fdb_chain;
-	struct mlx5_flow_table *fdb;
-	struct mlx5_flow_table *next_fdb;
-	struct mlx5_flow_group *miss_group;
-	struct mlx5_flow_handle *miss_rule;
-};
-
-static const struct rhashtable_params chain_params = {
-	.head_offset = offsetof(struct fdb_chain, node),
-	.key_offset = offsetof(struct fdb_chain, chain),
-	.key_len = sizeof_field(struct fdb_chain, chain),
-	.automatic_shrinking = true,
-};
-
-static const struct rhashtable_params prio_params = {
-	.head_offset = offsetof(struct fdb_prio, node),
-	.key_offset = offsetof(struct fdb_prio, key),
-	.key_len = sizeof_field(struct fdb_prio, key),
-	.automatic_shrinking = true,
-};
-
-bool mlx5_esw_chains_prios_supported(struct mlx5_eswitch *esw)
-{
-	return esw->fdb_table.flags & ESW_FDB_CHAINS_AND_PRIOS_SUPPORTED;
-}
-
-bool mlx5_esw_chains_backwards_supported(struct mlx5_eswitch *esw)
-{
-	return mlx5_esw_chains_prios_supported(esw) &&
-	       fdb_ignore_flow_level_supported(esw);
-}
-
-u32 mlx5_esw_chains_get_chain_range(struct mlx5_eswitch *esw)
-{
-	if (!mlx5_esw_chains_prios_supported(esw))
-		return 1;
-
-	if (fdb_ignore_flow_level_supported(esw))
-		return UINT_MAX - 1;
-
-	return FDB_TC_MAX_CHAIN;
-}
-
-u32 mlx5_esw_chains_get_ft_chain(struct mlx5_eswitch *esw)
-{
-	return mlx5_esw_chains_get_chain_range(esw) + 1;
-}
-
-u32 mlx5_esw_chains_get_prio_range(struct mlx5_eswitch *esw)
-{
-	if (!mlx5_esw_chains_prios_supported(esw))
-		return 1;
-
-	if (fdb_ignore_flow_level_supported(esw))
-		return UINT_MAX;
-
-	return FDB_TC_MAX_PRIO;
-}
-
-static unsigned int mlx5_esw_chains_get_level_range(struct mlx5_eswitch *esw)
-{
-	if (fdb_ignore_flow_level_supported(esw))
-		return UINT_MAX;
-
-	return FDB_TC_LEVELS_PER_PRIO;
-}
-
-#define POOL_NEXT_SIZE 0
-static int
-mlx5_esw_chains_get_avail_sz_from_pool(struct mlx5_eswitch *esw,
-				       int desired_size)
-{
-	int i, found_i = -1;
-
-	for (i = ARRAY_SIZE(ESW_POOLS) - 1; i >= 0; i--) {
-		if (fdb_pool_left(esw)[i] && ESW_POOLS[i] > desired_size) {
-			found_i = i;
-			if (desired_size != POOL_NEXT_SIZE)
-				break;
-		}
-	}
-
-	if (found_i != -1) {
-		--fdb_pool_left(esw)[found_i];
-		return ESW_POOLS[found_i];
-	}
-
-	return 0;
-}
-
-static void
-mlx5_esw_chains_put_sz_to_pool(struct mlx5_eswitch *esw, int sz)
-{
-	int i;
-
-	for (i = ARRAY_SIZE(ESW_POOLS) - 1; i >= 0; i--) {
-		if (sz == ESW_POOLS[i]) {
-			++fdb_pool_left(esw)[i];
-			return;
-		}
-	}
-
-	WARN_ONCE(1, "Couldn't find size %d in fdb size pool", sz);
-}
-
-static void
-mlx5_esw_chains_init_sz_pool(struct mlx5_eswitch *esw)
-{
-	u32 fdb_max;
-	int i;
-
-	fdb_max = 1 << MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, log_max_ft_size);
-
-	for (i = ARRAY_SIZE(ESW_POOLS) - 1; i >= 0; i--)
-		fdb_pool_left(esw)[i] =
-			ESW_POOLS[i] <= fdb_max ? ESW_SIZE / ESW_POOLS[i] : 0;
-}
-
-static struct mlx5_flow_table *
-mlx5_esw_chains_create_fdb_table(struct mlx5_eswitch *esw,
-				 u32 chain, u32 prio, u32 level)
-{
-	struct mlx5_flow_table_attr ft_attr = {};
-	struct mlx5_flow_namespace *ns;
-	struct mlx5_flow_table *fdb;
-	int sz;
-
-	if (esw->offloads.encap != DEVLINK_ESWITCH_ENCAP_MODE_NONE)
-		ft_attr.flags |= (MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT |
-				  MLX5_FLOW_TABLE_TUNNEL_EN_DECAP);
-
-	sz = (chain == mlx5_esw_chains_get_ft_chain(esw)) ?
-	     mlx5_esw_chains_get_avail_sz_from_pool(esw, ESW_FT_TBL_SZ) :
-	     mlx5_esw_chains_get_avail_sz_from_pool(esw, POOL_NEXT_SIZE);
-	if (!sz)
-		return ERR_PTR(-ENOSPC);
-	ft_attr.max_fte = sz;
-
-	/* We use tc_slow_fdb(esw) as the table's next_ft till
-	 * ignore_flow_level is allowed on FT creation and not just for FTEs.
-	 * Instead caller should add an explicit miss rule if needed.
-	 */
-	ft_attr.next_ft = tc_slow_fdb(esw);
-
-	/* The root table(chain 0, prio 1, level 0) is required to be
-	 * connected to the previous prio (FDB_BYPASS_PATH if exists).
-	 * We always create it, as a managed table, in order to align with
-	 * fs_core logic.
-	 */
-	if (!fdb_ignore_flow_level_supported(esw) ||
-	    (chain == 0 && prio == 1 && level == 0)) {
-		ft_attr.level = level;
-		ft_attr.prio = prio - 1;
-		ns = mlx5_get_fdb_sub_ns(esw->dev, chain);
-	} else {
-		ft_attr.flags |= MLX5_FLOW_TABLE_UNMANAGED;
-		ft_attr.prio = FDB_TC_OFFLOAD;
-		/* Firmware doesn't allow us to create another level 0 table,
-		 * so we create all unmanaged tables as level 1.
-		 *
-		 * To connect them, we use explicit miss rules with
-		 * ignore_flow_level. Caller is responsible to create
-		 * these rules (if needed).
-		 */
-		ft_attr.level = 1;
-		ns = mlx5_get_flow_namespace(esw->dev, MLX5_FLOW_NAMESPACE_FDB);
-	}
-
-	ft_attr.autogroup.num_reserved_entries = 2;
-	ft_attr.autogroup.max_num_groups = esw->params.large_group_num;
-	fdb = mlx5_create_auto_grouped_flow_table(ns, &ft_attr);
-	if (IS_ERR(fdb)) {
-		esw_warn(esw->dev,
-			 "Failed to create FDB table err %d (chain: %d, prio: %d, level: %d, size: %d)\n",
-			 (int)PTR_ERR(fdb), chain, prio, level, sz);
-		mlx5_esw_chains_put_sz_to_pool(esw, sz);
-		return fdb;
-	}
-
-	return fdb;
-}
-
-static void
-mlx5_esw_chains_destroy_fdb_table(struct mlx5_eswitch *esw,
-				  struct mlx5_flow_table *fdb)
-{
-	mlx5_esw_chains_put_sz_to_pool(esw, fdb->max_fte);
-	mlx5_destroy_flow_table(fdb);
-}
-
-static int
-create_fdb_chain_restore(struct fdb_chain *fdb_chain)
-{
-	char modact[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)];
-	struct mlx5_eswitch *esw = fdb_chain->esw;
-	struct mlx5_modify_hdr *mod_hdr;
-	u32 index;
-	int err;
-
-	if (fdb_chain->chain == mlx5_esw_chains_get_ft_chain(esw) ||
-	    !mlx5_esw_chains_prios_supported(esw))
-		return 0;
-
-	err = mapping_add(esw_chains_mapping(esw), &fdb_chain->chain, &index);
-	if (err)
-		return err;
-	if (index == MLX5_FS_DEFAULT_FLOW_TAG) {
-		/* we got the special default flow tag id, so we won't know
-		 * if we actually marked the packet with the restore rule
-		 * we create.
-		 *
-		 * This case isn't possible with MLX5_FS_DEFAULT_FLOW_TAG = 0.
-		 */
-		err = mapping_add(esw_chains_mapping(esw),
-				  &fdb_chain->chain, &index);
-		mapping_remove(esw_chains_mapping(esw),
-			       MLX5_FS_DEFAULT_FLOW_TAG);
-		if (err)
-			return err;
-	}
-
-	fdb_chain->id = index;
-
-	MLX5_SET(set_action_in, modact, action_type, MLX5_ACTION_TYPE_SET);
-	MLX5_SET(set_action_in, modact, field,
-		 mlx5e_tc_attr_to_reg_mappings[CHAIN_TO_REG].mfield);
-	MLX5_SET(set_action_in, modact, offset,
-		 mlx5e_tc_attr_to_reg_mappings[CHAIN_TO_REG].moffset * 8);
-	MLX5_SET(set_action_in, modact, length,
-		 mlx5e_tc_attr_to_reg_mappings[CHAIN_TO_REG].mlen * 8);
-	MLX5_SET(set_action_in, modact, data, fdb_chain->id);
-	mod_hdr = mlx5_modify_header_alloc(esw->dev, MLX5_FLOW_NAMESPACE_FDB,
-					   1, modact);
-	if (IS_ERR(mod_hdr)) {
-		err = PTR_ERR(mod_hdr);
-		goto err_mod_hdr;
-	}
-	fdb_chain->miss_modify_hdr = mod_hdr;
-
-	fdb_chain->restore_rule = esw_add_restore_rule(esw, fdb_chain->id);
-	if (IS_ERR(fdb_chain->restore_rule)) {
-		err = PTR_ERR(fdb_chain->restore_rule);
-		goto err_rule;
-	}
-
-	return 0;
-
-err_rule:
-	mlx5_modify_header_dealloc(esw->dev, fdb_chain->miss_modify_hdr);
-err_mod_hdr:
-	/* Datapath can't find this mapping, so we can safely remove it */
-	mapping_remove(esw_chains_mapping(esw), fdb_chain->id);
-	return err;
-}
-
-static void destroy_fdb_chain_restore(struct fdb_chain *fdb_chain)
-{
-	struct mlx5_eswitch *esw = fdb_chain->esw;
-
-	if (!fdb_chain->miss_modify_hdr)
-		return;
-
-	mlx5_del_flow_rules(fdb_chain->restore_rule);
-	mlx5_modify_header_dealloc(esw->dev, fdb_chain->miss_modify_hdr);
-	mapping_remove(esw_chains_mapping(esw), fdb_chain->id);
-}
-
-static struct fdb_chain *
-mlx5_esw_chains_create_fdb_chain(struct mlx5_eswitch *esw, u32 chain)
-{
-	struct fdb_chain *fdb_chain = NULL;
-	int err;
-
-	fdb_chain = kvzalloc(sizeof(*fdb_chain), GFP_KERNEL);
-	if (!fdb_chain)
-		return ERR_PTR(-ENOMEM);
-
-	fdb_chain->esw = esw;
-	fdb_chain->chain = chain;
-	INIT_LIST_HEAD(&fdb_chain->prios_list);
-
-	err = create_fdb_chain_restore(fdb_chain);
-	if (err)
-		goto err_restore;
-
-	err = rhashtable_insert_fast(&esw_chains_ht(esw), &fdb_chain->node,
-				     chain_params);
-	if (err)
-		goto err_insert;
-
-	return fdb_chain;
-
-err_insert:
-	destroy_fdb_chain_restore(fdb_chain);
-err_restore:
-	kvfree(fdb_chain);
-	return ERR_PTR(err);
-}
-
-static void
-mlx5_esw_chains_destroy_fdb_chain(struct fdb_chain *fdb_chain)
-{
-	struct mlx5_eswitch *esw = fdb_chain->esw;
-
-	rhashtable_remove_fast(&esw_chains_ht(esw), &fdb_chain->node,
-			       chain_params);
-
-	destroy_fdb_chain_restore(fdb_chain);
-	kvfree(fdb_chain);
-}
-
-static struct fdb_chain *
-mlx5_esw_chains_get_fdb_chain(struct mlx5_eswitch *esw, u32 chain)
-{
-	struct fdb_chain *fdb_chain;
-
-	fdb_chain = rhashtable_lookup_fast(&esw_chains_ht(esw), &chain,
-					   chain_params);
-	if (!fdb_chain) {
-		fdb_chain = mlx5_esw_chains_create_fdb_chain(esw, chain);
-		if (IS_ERR(fdb_chain))
-			return fdb_chain;
-	}
-
-	fdb_chain->ref++;
-
-	return fdb_chain;
-}
-
-static struct mlx5_flow_handle *
-mlx5_esw_chains_add_miss_rule(struct fdb_chain *fdb_chain,
-			      struct mlx5_flow_table *fdb,
-			      struct mlx5_flow_table *next_fdb)
-{
-	struct mlx5_eswitch *esw = fdb_chain->esw;
-	struct mlx5_flow_destination dest = {};
-	struct mlx5_flow_act act = {};
-
-	act.flags  = FLOW_ACT_IGNORE_FLOW_LEVEL | FLOW_ACT_NO_APPEND;
-	act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
-	dest.type  = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
-	dest.ft = next_fdb;
-
-	if (next_fdb == tc_end_fdb(esw) &&
-	    mlx5_esw_chains_prios_supported(esw)) {
-		act.modify_hdr = fdb_chain->miss_modify_hdr;
-		act.action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
-	}
-
-	return mlx5_add_flow_rules(fdb, NULL, &act, &dest, 1);
-}
-
-static int
-mlx5_esw_chains_update_prio_prevs(struct fdb_prio *fdb_prio,
-				  struct mlx5_flow_table *next_fdb)
-{
-	struct mlx5_flow_handle *miss_rules[FDB_TC_LEVELS_PER_PRIO + 1] = {};
-	struct fdb_chain *fdb_chain = fdb_prio->fdb_chain;
-	struct fdb_prio *pos;
-	int n = 0, err;
-
-	if (fdb_prio->key.level)
-		return 0;
-
-	/* Iterate in reverse order until reaching the level 0 rule of
-	 * the previous priority, adding all the miss rules first, so we can
-	 * revert them if any of them fails.
-	 */
-	pos = fdb_prio;
-	list_for_each_entry_continue_reverse(pos,
-					     &fdb_chain->prios_list,
-					     list) {
-		miss_rules[n] = mlx5_esw_chains_add_miss_rule(fdb_chain,
-							      pos->fdb,
-							      next_fdb);
-		if (IS_ERR(miss_rules[n])) {
-			err = PTR_ERR(miss_rules[n]);
-			goto err_prev_rule;
-		}
-
-		n++;
-		if (!pos->key.level)
-			break;
-	}
-
-	/* Success, delete old miss rules, and update the pointers. */
-	n = 0;
-	pos = fdb_prio;
-	list_for_each_entry_continue_reverse(pos,
-					     &fdb_chain->prios_list,
-					     list) {
-		mlx5_del_flow_rules(pos->miss_rule);
-
-		pos->miss_rule = miss_rules[n];
-		pos->next_fdb = next_fdb;
-
-		n++;
-		if (!pos->key.level)
-			break;
-	}
-
-	return 0;
-
-err_prev_rule:
-	while (--n >= 0)
-		mlx5_del_flow_rules(miss_rules[n]);
-
-	return err;
-}
-
-static void
-mlx5_esw_chains_put_fdb_chain(struct fdb_chain *fdb_chain)
-{
-	if (--fdb_chain->ref == 0)
-		mlx5_esw_chains_destroy_fdb_chain(fdb_chain);
-}
-
-static struct fdb_prio *
-mlx5_esw_chains_create_fdb_prio(struct mlx5_eswitch *esw,
-				u32 chain, u32 prio, u32 level)
-{
-	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
-	struct mlx5_flow_handle *miss_rule = NULL;
-	struct mlx5_flow_group *miss_group;
-	struct fdb_prio *fdb_prio = NULL;
-	struct mlx5_flow_table *next_fdb;
-	struct fdb_chain *fdb_chain;
-	struct mlx5_flow_table *fdb;
-	struct list_head *pos;
-	u32 *flow_group_in;
-	int err;
-
-	fdb_chain = mlx5_esw_chains_get_fdb_chain(esw, chain);
-	if (IS_ERR(fdb_chain))
-		return ERR_CAST(fdb_chain);
-
-	fdb_prio = kvzalloc(sizeof(*fdb_prio), GFP_KERNEL);
-	flow_group_in = kvzalloc(inlen, GFP_KERNEL);
-	if (!fdb_prio || !flow_group_in) {
-		err = -ENOMEM;
-		goto err_alloc;
-	}
-
-	/* Chain's prio list is sorted by prio and level.
-	 * And all levels of some prio point to the next prio's level 0.
-	 * Example list (prio, level):
-	 * (3,0)->(3,1)->(5,0)->(5,1)->(6,1)->(7,0)
-	 * In hardware, we will we have the following pointers:
-	 * (3,0) -> (5,0) -> (7,0) -> Slow path
-	 * (3,1) -> (5,0)
-	 * (5,1) -> (7,0)
-	 * (6,1) -> (7,0)
-	 */
-
-	/* Default miss for each chain: */
-	next_fdb = (chain == mlx5_esw_chains_get_ft_chain(esw)) ?
-		    tc_slow_fdb(esw) :
-		    tc_end_fdb(esw);
-	list_for_each(pos, &fdb_chain->prios_list) {
-		struct fdb_prio *p = list_entry(pos, struct fdb_prio, list);
-
-		/* exit on first pos that is larger */
-		if (prio < p->key.prio || (prio == p->key.prio &&
-					   level < p->key.level)) {
-			/* Get next level 0 table */
-			next_fdb = p->key.level == 0 ? p->fdb : p->next_fdb;
-			break;
-		}
-	}
-
-	fdb = mlx5_esw_chains_create_fdb_table(esw, chain, prio, level);
-	if (IS_ERR(fdb)) {
-		err = PTR_ERR(fdb);
-		goto err_create;
-	}
-
-	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index,
-		 fdb->max_fte - 2);
-	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index,
-		 fdb->max_fte - 1);
-	miss_group = mlx5_create_flow_group(fdb, flow_group_in);
-	if (IS_ERR(miss_group)) {
-		err = PTR_ERR(miss_group);
-		goto err_group;
-	}
-
-	/* Add miss rule to next_fdb */
-	miss_rule = mlx5_esw_chains_add_miss_rule(fdb_chain, fdb, next_fdb);
-	if (IS_ERR(miss_rule)) {
-		err = PTR_ERR(miss_rule);
-		goto err_miss_rule;
-	}
-
-	fdb_prio->miss_group = miss_group;
-	fdb_prio->miss_rule = miss_rule;
-	fdb_prio->next_fdb = next_fdb;
-	fdb_prio->fdb_chain = fdb_chain;
-	fdb_prio->key.chain = chain;
-	fdb_prio->key.prio = prio;
-	fdb_prio->key.level = level;
-	fdb_prio->fdb = fdb;
-
-	err = rhashtable_insert_fast(&esw_prios_ht(esw), &fdb_prio->node,
-				     prio_params);
-	if (err)
-		goto err_insert;
-
-	list_add(&fdb_prio->list, pos->prev);
-
-	/* Table is ready, connect it */
-	err = mlx5_esw_chains_update_prio_prevs(fdb_prio, fdb);
-	if (err)
-		goto err_update;
-
-	kvfree(flow_group_in);
-	return fdb_prio;
-
-err_update:
-	list_del(&fdb_prio->list);
-	rhashtable_remove_fast(&esw_prios_ht(esw), &fdb_prio->node,
-			       prio_params);
-err_insert:
-	mlx5_del_flow_rules(miss_rule);
-err_miss_rule:
-	mlx5_destroy_flow_group(miss_group);
-err_group:
-	mlx5_esw_chains_destroy_fdb_table(esw, fdb);
-err_create:
-err_alloc:
-	kvfree(fdb_prio);
-	kvfree(flow_group_in);
-	mlx5_esw_chains_put_fdb_chain(fdb_chain);
-	return ERR_PTR(err);
-}
-
-static void
-mlx5_esw_chains_destroy_fdb_prio(struct mlx5_eswitch *esw,
-				 struct fdb_prio *fdb_prio)
-{
-	struct fdb_chain *fdb_chain = fdb_prio->fdb_chain;
-
-	WARN_ON(mlx5_esw_chains_update_prio_prevs(fdb_prio,
-						  fdb_prio->next_fdb));
-
-	list_del(&fdb_prio->list);
-	rhashtable_remove_fast(&esw_prios_ht(esw), &fdb_prio->node,
-			       prio_params);
-	mlx5_del_flow_rules(fdb_prio->miss_rule);
-	mlx5_destroy_flow_group(fdb_prio->miss_group);
-	mlx5_esw_chains_destroy_fdb_table(esw, fdb_prio->fdb);
-	mlx5_esw_chains_put_fdb_chain(fdb_chain);
-	kvfree(fdb_prio);
-}
-
-struct mlx5_flow_table *
-mlx5_esw_chains_get_table(struct mlx5_eswitch *esw, u32 chain, u32 prio,
-			  u32 level)
-{
-	struct mlx5_flow_table *prev_fts;
-	struct fdb_prio *fdb_prio;
-	struct fdb_prio_key key;
-	int l = 0;
-
-	if ((chain > mlx5_esw_chains_get_chain_range(esw) &&
-	     chain != mlx5_esw_chains_get_ft_chain(esw)) ||
-	    prio > mlx5_esw_chains_get_prio_range(esw) ||
-	    level > mlx5_esw_chains_get_level_range(esw))
-		return ERR_PTR(-EOPNOTSUPP);
-
-	/* create earlier levels for correct fs_core lookup when
-	 * connecting tables.
-	 */
-	for (l = 0; l < level; l++) {
-		prev_fts = mlx5_esw_chains_get_table(esw, chain, prio, l);
-		if (IS_ERR(prev_fts)) {
-			fdb_prio = ERR_CAST(prev_fts);
-			goto err_get_prevs;
-		}
-	}
-
-	key.chain = chain;
-	key.prio = prio;
-	key.level = level;
-
-	mutex_lock(&esw_chains_lock(esw));
-	fdb_prio = rhashtable_lookup_fast(&esw_prios_ht(esw), &key,
-					  prio_params);
-	if (!fdb_prio) {
-		fdb_prio = mlx5_esw_chains_create_fdb_prio(esw, chain,
-							   prio, level);
-		if (IS_ERR(fdb_prio))
-			goto err_create_prio;
-	}
-
-	++fdb_prio->ref;
-	mutex_unlock(&esw_chains_lock(esw));
-
-	return fdb_prio->fdb;
-
-err_create_prio:
-	mutex_unlock(&esw_chains_lock(esw));
-err_get_prevs:
-	while (--l >= 0)
-		mlx5_esw_chains_put_table(esw, chain, prio, l);
-	return ERR_CAST(fdb_prio);
-}
-
-void
-mlx5_esw_chains_put_table(struct mlx5_eswitch *esw, u32 chain, u32 prio,
-			  u32 level)
-{
-	struct fdb_prio *fdb_prio;
-	struct fdb_prio_key key;
-
-	key.chain = chain;
-	key.prio = prio;
-	key.level = level;
-
-	mutex_lock(&esw_chains_lock(esw));
-	fdb_prio = rhashtable_lookup_fast(&esw_prios_ht(esw), &key,
-					  prio_params);
-	if (!fdb_prio)
-		goto err_get_prio;
-
-	if (--fdb_prio->ref == 0)
-		mlx5_esw_chains_destroy_fdb_prio(esw, fdb_prio);
-	mutex_unlock(&esw_chains_lock(esw));
-
-	while (level-- > 0)
-		mlx5_esw_chains_put_table(esw, chain, prio, level);
-
-	return;
-
-err_get_prio:
-	mutex_unlock(&esw_chains_lock(esw));
-	WARN_ONCE(1,
-		  "Couldn't find table: (chain: %d prio: %d level: %d)",
-		  chain, prio, level);
-}
-
-struct mlx5_flow_table *
-mlx5_esw_chains_get_tc_end_ft(struct mlx5_eswitch *esw)
-{
-	return tc_end_fdb(esw);
-}
-
-struct mlx5_flow_table *
-mlx5_esw_chains_create_global_table(struct mlx5_eswitch *esw)
-{
-	u32 chain, prio, level;
-	int err;
-
-	if (!fdb_ignore_flow_level_supported(esw)) {
-		err = -EOPNOTSUPP;
-
-		esw_warn(esw->dev,
-			 "Couldn't create global flow table, ignore_flow_level not supported.");
-		goto err_ignore;
-	}
-
-	chain = mlx5_esw_chains_get_chain_range(esw),
-	prio = mlx5_esw_chains_get_prio_range(esw);
-	level = mlx5_esw_chains_get_level_range(esw);
-
-	return mlx5_esw_chains_create_fdb_table(esw, chain, prio, level);
-
-err_ignore:
-	return ERR_PTR(err);
-}
-
-void
-mlx5_esw_chains_destroy_global_table(struct mlx5_eswitch *esw,
-				     struct mlx5_flow_table *ft)
-{
-	mlx5_esw_chains_destroy_fdb_table(esw, ft);
-}
-
-static int
-mlx5_esw_chains_init(struct mlx5_eswitch *esw)
-{
-	struct mlx5_esw_chains_priv *chains_priv;
-	struct mlx5_core_dev *dev = esw->dev;
-	u32 max_flow_counter, fdb_max;
-	struct mapping_ctx *mapping;
-	int err;
-
-	chains_priv = kzalloc(sizeof(*chains_priv), GFP_KERNEL);
-	if (!chains_priv)
-		return -ENOMEM;
-	esw_chains_priv(esw) = chains_priv;
-
-	max_flow_counter = (MLX5_CAP_GEN(dev, max_flow_counter_31_16) << 16) |
-			    MLX5_CAP_GEN(dev, max_flow_counter_15_0);
-	fdb_max = 1 << MLX5_CAP_ESW_FLOWTABLE_FDB(dev, log_max_ft_size);
-
-	esw_debug(dev,
-		  "Init esw offloads chains, max counters(%d), groups(%d), max flow table size(%d)\n",
-		  max_flow_counter, esw->params.large_group_num, fdb_max);
-
-	mlx5_esw_chains_init_sz_pool(esw);
-
-	if (!MLX5_CAP_ESW_FLOWTABLE(esw->dev, multi_fdb_encap) &&
-	    esw->offloads.encap != DEVLINK_ESWITCH_ENCAP_MODE_NONE) {
-		esw->fdb_table.flags &= ~ESW_FDB_CHAINS_AND_PRIOS_SUPPORTED;
-		esw_warn(dev, "Tc chains and priorities offload aren't supported, update firmware if needed\n");
-	} else if (!mlx5_eswitch_reg_c1_loopback_enabled(esw)) {
-		esw->fdb_table.flags &= ~ESW_FDB_CHAINS_AND_PRIOS_SUPPORTED;
-		esw_warn(dev, "Tc chains and priorities offload aren't supported\n");
-	} else if (!fdb_modify_header_fwd_to_table_supported(esw)) {
-		/* Disabled when ttl workaround is needed, e.g
-		 * when ESWITCH_IPV4_TTL_MODIFY_ENABLE = true in mlxconfig
-		 */
-		esw_warn(dev,
-			 "Tc chains and priorities offload aren't supported, check firmware version, or mlxconfig settings\n");
-		esw->fdb_table.flags &= ~ESW_FDB_CHAINS_AND_PRIOS_SUPPORTED;
-	} else {
-		esw->fdb_table.flags |= ESW_FDB_CHAINS_AND_PRIOS_SUPPORTED;
-		esw_info(dev, "Supported tc offload range - chains: %u, prios: %u\n",
-			 mlx5_esw_chains_get_chain_range(esw),
-			 mlx5_esw_chains_get_prio_range(esw));
-	}
-
-	err = rhashtable_init(&esw_chains_ht(esw), &chain_params);
-	if (err)
-		goto init_chains_ht_err;
-
-	err = rhashtable_init(&esw_prios_ht(esw), &prio_params);
-	if (err)
-		goto init_prios_ht_err;
-
-	mapping = mapping_create(sizeof(u32), esw_get_max_restore_tag(esw),
-				 true);
-	if (IS_ERR(mapping)) {
-		err = PTR_ERR(mapping);
-		goto mapping_err;
-	}
-	esw_chains_mapping(esw) = mapping;
-
-	mutex_init(&esw_chains_lock(esw));
-
-	return 0;
-
-mapping_err:
-	rhashtable_destroy(&esw_prios_ht(esw));
-init_prios_ht_err:
-	rhashtable_destroy(&esw_chains_ht(esw));
-init_chains_ht_err:
-	kfree(chains_priv);
-	return err;
-}
-
-static void
-mlx5_esw_chains_cleanup(struct mlx5_eswitch *esw)
-{
-	mutex_destroy(&esw_chains_lock(esw));
-	mapping_destroy(esw_chains_mapping(esw));
-	rhashtable_destroy(&esw_prios_ht(esw));
-	rhashtable_destroy(&esw_chains_ht(esw));
-
-	kfree(esw_chains_priv(esw));
-}
-
-static int
-mlx5_esw_chains_open(struct mlx5_eswitch *esw)
-{
-	struct mlx5_flow_table *ft;
-	int err;
-
-	/* Create tc_end_fdb(esw) which is the always created ft chain */
-	ft = mlx5_esw_chains_get_table(esw, mlx5_esw_chains_get_ft_chain(esw),
-				       1, 0);
-	if (IS_ERR(ft))
-		return PTR_ERR(ft);
-
-	tc_end_fdb(esw) = ft;
-
-	/* Always open the root for fast path */
-	ft = mlx5_esw_chains_get_table(esw, 0, 1, 0);
-	if (IS_ERR(ft)) {
-		err = PTR_ERR(ft);
-		goto level_0_err;
-	}
-
-	/* Open level 1 for split rules now if prios isn't supported  */
-	if (!mlx5_esw_chains_prios_supported(esw)) {
-		err = mlx5_esw_vport_tbl_get(esw);
-		if (err)
-			goto level_1_err;
-	}
-
-	return 0;
-
-level_1_err:
-	mlx5_esw_chains_put_table(esw, 0, 1, 0);
-level_0_err:
-	mlx5_esw_chains_put_table(esw, mlx5_esw_chains_get_ft_chain(esw), 1, 0);
-	return err;
-}
-
-static void
-mlx5_esw_chains_close(struct mlx5_eswitch *esw)
-{
-	if (!mlx5_esw_chains_prios_supported(esw))
-		mlx5_esw_vport_tbl_put(esw);
-	mlx5_esw_chains_put_table(esw, 0, 1, 0);
-	mlx5_esw_chains_put_table(esw, mlx5_esw_chains_get_ft_chain(esw), 1, 0);
-}
-
-int
-mlx5_esw_chains_create(struct mlx5_eswitch *esw)
-{
-	int err;
-
-	err = mlx5_esw_chains_init(esw);
-	if (err)
-		return err;
-
-	err = mlx5_esw_chains_open(esw);
-	if (err)
-		goto err_open;
-
-	return 0;
-
-err_open:
-	mlx5_esw_chains_cleanup(esw);
-	return err;
-}
-
-void
-mlx5_esw_chains_destroy(struct mlx5_eswitch *esw)
-{
-	mlx5_esw_chains_close(esw);
-	mlx5_esw_chains_cleanup(esw);
-}
-
-int
-mlx5_esw_chains_get_chain_mapping(struct mlx5_eswitch *esw, u32 chain,
-				  u32 *chain_mapping)
-{
-	return mapping_add(esw_chains_mapping(esw), &chain, chain_mapping);
-}
-
-int
-mlx5_esw_chains_put_chain_mapping(struct mlx5_eswitch *esw, u32 chain_mapping)
-{
-	return mapping_remove(esw_chains_mapping(esw), chain_mapping);
-}
-
-int mlx5_eswitch_get_chain_for_tag(struct mlx5_eswitch *esw, u32 tag,
-				   u32 *chain)
-{
-	int err;
-
-	err = mapping_find(esw_chains_mapping(esw), tag, chain);
-	if (err) {
-		esw_warn(esw->dev, "Can't find chain for tag: %d\n", tag);
-		return -ENOENT;
-	}
-
-	return 0;
-}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/chains.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/chains.h
deleted file mode 100644
index 7679ac359e31..000000000000
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/chains.h
+++ /dev/null
@@ -1,68 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
-/* Copyright (c) 2020 Mellanox Technologies. */
-
-#ifndef __ML5_ESW_CHAINS_H__
-#define __ML5_ESW_CHAINS_H__
-
-#include "eswitch.h"
-
-#if IS_ENABLED(CONFIG_MLX5_CLS_ACT)
-
-bool
-mlx5_esw_chains_prios_supported(struct mlx5_eswitch *esw);
-bool
-mlx5_esw_chains_backwards_supported(struct mlx5_eswitch *esw);
-u32
-mlx5_esw_chains_get_prio_range(struct mlx5_eswitch *esw);
-u32
-mlx5_esw_chains_get_chain_range(struct mlx5_eswitch *esw);
-u32
-mlx5_esw_chains_get_ft_chain(struct mlx5_eswitch *esw);
-
-struct mlx5_flow_table *
-mlx5_esw_chains_get_table(struct mlx5_eswitch *esw, u32 chain, u32 prio,
-			  u32 level);
-void
-mlx5_esw_chains_put_table(struct mlx5_eswitch *esw, u32 chain, u32 prio,
-			  u32 level);
-
-struct mlx5_flow_table *
-mlx5_esw_chains_get_tc_end_ft(struct mlx5_eswitch *esw);
-
-struct mlx5_flow_table *
-mlx5_esw_chains_create_global_table(struct mlx5_eswitch *esw);
-void
-mlx5_esw_chains_destroy_global_table(struct mlx5_eswitch *esw,
-				     struct mlx5_flow_table *ft);
-
-int
-mlx5_esw_chains_get_chain_mapping(struct mlx5_eswitch *esw, u32 chain,
-				  u32 *chain_mapping);
-int
-mlx5_esw_chains_put_chain_mapping(struct mlx5_eswitch *esw,
-				  u32 chain_mapping);
-
-int mlx5_esw_chains_create(struct mlx5_eswitch *esw);
-void mlx5_esw_chains_destroy(struct mlx5_eswitch *esw);
-
-int
-mlx5_eswitch_get_chain_for_tag(struct mlx5_eswitch *esw, u32 tag, u32 *chain);
-
-#else /* CONFIG_MLX5_CLS_ACT */
-
-static inline struct mlx5_flow_table *
-mlx5_esw_chains_get_table(struct mlx5_eswitch *esw, u32 chain, u32 prio,
-			  u32 level) { return ERR_PTR(-EOPNOTSUPP); }
-static inline void
-mlx5_esw_chains_put_table(struct mlx5_eswitch *esw, u32 chain, u32 prio,
-			  u32 level) {}
-
-static inline struct mlx5_flow_table *
-mlx5_esw_chains_get_tc_end_ft(struct mlx5_eswitch *esw) { return ERR_PTR(-EOPNOTSUPP); }
-
-static inline int mlx5_esw_chains_create(struct mlx5_eswitch *esw) { return 0; }
-static inline void mlx5_esw_chains_destroy(struct mlx5_eswitch *esw) {}
-
-#endif /* CONFIG_MLX5_CLS_ACT */
-
-#endif /* __ML5_ESW_CHAINS_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
new file mode 100644
index 000000000000..ffff11baa3d0
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
@@ -0,0 +1,124 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2020 Mellanox Technologies Ltd. */
+
+#include <linux/mlx5/driver.h>
+#include "eswitch.h"
+
+static void
+mlx5_esw_get_port_parent_id(struct mlx5_core_dev *dev, struct netdev_phys_item_id *ppid)
+{
+	u64 parent_id;
+
+	parent_id = mlx5_query_nic_system_image_guid(dev);
+	ppid->id_len = sizeof(parent_id);
+	memcpy(ppid->id, &parent_id, sizeof(parent_id));
+}
+
+static bool
+mlx5_esw_devlink_port_supported(const struct mlx5_eswitch *esw, u16 vport_num)
+{
+	return vport_num == MLX5_VPORT_UPLINK ||
+	       (mlx5_core_is_ecpf(esw->dev) && vport_num == MLX5_VPORT_PF) ||
+	       mlx5_eswitch_is_vf_vport(esw, vport_num);
+}
+
+static struct devlink_port *mlx5_esw_dl_port_alloc(struct mlx5_eswitch *esw, u16 vport_num)
+{
+	struct mlx5_core_dev *dev = esw->dev;
+	struct devlink_port_attrs attrs = {};
+	struct netdev_phys_item_id ppid = {};
+	struct devlink_port *dl_port;
+	u32 controller_num = 0;
+	bool external;
+	u16 pfnum;
+
+	dl_port = kzalloc(sizeof(*dl_port), GFP_KERNEL);
+	if (!dl_port)
+		return NULL;
+
+	mlx5_esw_get_port_parent_id(dev, &ppid);
+	pfnum = PCI_FUNC(dev->pdev->devfn);
+	external = mlx5_core_is_ecpf_esw_manager(dev);
+	if (external)
+		controller_num = dev->priv.eswitch->offloads.host_number + 1;
+
+	if (vport_num == MLX5_VPORT_UPLINK) {
+		attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL;
+		attrs.phys.port_number = pfnum;
+		memcpy(attrs.switch_id.id, ppid.id, ppid.id_len);
+		attrs.switch_id.id_len = ppid.id_len;
+		devlink_port_attrs_set(dl_port, &attrs);
+	} else if (vport_num == MLX5_VPORT_PF) {
+		memcpy(dl_port->attrs.switch_id.id, ppid.id, ppid.id_len);
+		dl_port->attrs.switch_id.id_len = ppid.id_len;
+		devlink_port_attrs_pci_pf_set(dl_port, controller_num, pfnum, external);
+	} else if (mlx5_eswitch_is_vf_vport(esw, vport_num)) {
+		memcpy(dl_port->attrs.switch_id.id, ppid.id, ppid.id_len);
+		dl_port->attrs.switch_id.id_len = ppid.id_len;
+		devlink_port_attrs_pci_vf_set(dl_port, controller_num, pfnum,
+					      vport_num - 1, external);
+	}
+	return dl_port;
+}
+
+static void mlx5_esw_dl_port_free(struct devlink_port *dl_port)
+{
+	kfree(dl_port);
+}
+
+int mlx5_esw_offloads_devlink_port_register(struct mlx5_eswitch *esw, u16 vport_num)
+{
+	struct mlx5_core_dev *dev = esw->dev;
+	struct devlink_port *dl_port;
+	unsigned int dl_port_index;
+	struct mlx5_vport *vport;
+	struct devlink *devlink;
+	int err;
+
+	if (!mlx5_esw_devlink_port_supported(esw, vport_num))
+		return 0;
+
+	vport = mlx5_eswitch_get_vport(esw, vport_num);
+	if (IS_ERR(vport))
+		return PTR_ERR(vport);
+
+	dl_port = mlx5_esw_dl_port_alloc(esw, vport_num);
+	if (!dl_port)
+		return -ENOMEM;
+
+	devlink = priv_to_devlink(dev);
+	dl_port_index = mlx5_esw_vport_to_devlink_port_index(dev, vport_num);
+	err = devlink_port_register(devlink, dl_port, dl_port_index);
+	if (err)
+		goto reg_err;
+
+	vport->dl_port = dl_port;
+	return 0;
+
+reg_err:
+	mlx5_esw_dl_port_free(dl_port);
+	return err;
+}
+
+void mlx5_esw_offloads_devlink_port_unregister(struct mlx5_eswitch *esw, u16 vport_num)
+{
+	struct mlx5_vport *vport;
+
+	if (!mlx5_esw_devlink_port_supported(esw, vport_num))
+		return;
+
+	vport = mlx5_eswitch_get_vport(esw, vport_num);
+	if (IS_ERR(vport))
+		return;
+	devlink_port_unregister(vport->dl_port);
+	mlx5_esw_dl_port_free(vport->dl_port);
+	vport->dl_port = NULL;
+}
+
+struct devlink_port *mlx5_esw_offloads_devlink_port(struct mlx5_eswitch *esw, u16 vport_num)
+{
+	struct mlx5_vport *vport;
+
+	vport = mlx5_eswitch_get_vport(esw, vport_num);
+	return vport->dl_port;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 7455fbd21a0a..cf87de94418f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -42,6 +42,7 @@
 #include <linux/mlx5/vport.h>
 #include <linux/mlx5/fs.h>
 #include "lib/mpfs.h"
+#include "lib/fs_chains.h"
 #include "en/tc_ct.h"
 
 #ifdef CONFIG_MLX5_ESWITCH
@@ -62,6 +63,9 @@
 #define mlx5_esw_has_fwd_fdb(dev) \
 	MLX5_CAP_ESW_FLOWTABLE(dev, fdb_multi_path_to_table)
 
+#define esw_chains(esw) \
+	((esw)->fdb_table.offloads.esw_chains_priv)
+
 struct vport_ingress {
 	struct mlx5_flow_table *acl;
 	struct mlx5_flow_handle *allow_rule;
@@ -152,14 +156,9 @@ struct mlx5_vport {
 
 	bool                    enabled;
 	enum mlx5_eswitch_vport_event enabled_events;
+	struct devlink_port *dl_port;
 };
 
-enum offloads_fdb_flags {
-	ESW_FDB_CHAINS_AND_PRIOS_SUPPORTED = BIT(0),
-};
-
-struct mlx5_esw_chains_priv;
-
 struct mlx5_eswitch_fdb {
 	union {
 		struct legacy_fdb {
@@ -183,7 +182,7 @@ struct mlx5_eswitch_fdb {
 			struct mlx5_flow_handle *miss_rule_multi;
 			int vlan_push_pop_refcount;
 
-			struct mlx5_esw_chains_priv *esw_chains_priv;
+			struct mlx5_fs_chains *esw_chains_priv;
 			struct {
 				DECLARE_HASHTABLE(table, 8);
 				/* Protects vports.table */
@@ -330,7 +329,7 @@ struct mlx5_termtbl_handle;
 
 bool
 mlx5_eswitch_termtbl_required(struct mlx5_eswitch *esw,
-			      struct mlx5_esw_flow_attr *attr,
+			      struct mlx5_flow_attr *attr,
 			      struct mlx5_flow_act *flow_act,
 			      struct mlx5_flow_spec *spec);
 
@@ -350,19 +349,19 @@ mlx5_eswitch_termtbl_put(struct mlx5_eswitch *esw,
 struct mlx5_flow_handle *
 mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
 				struct mlx5_flow_spec *spec,
-				struct mlx5_esw_flow_attr *attr);
+				struct mlx5_flow_attr *attr);
 struct mlx5_flow_handle *
 mlx5_eswitch_add_fwd_rule(struct mlx5_eswitch *esw,
 			  struct mlx5_flow_spec *spec,
-			  struct mlx5_esw_flow_attr *attr);
+			  struct mlx5_flow_attr *attr);
 void
 mlx5_eswitch_del_offloaded_rule(struct mlx5_eswitch *esw,
 				struct mlx5_flow_handle *rule,
-				struct mlx5_esw_flow_attr *attr);
+				struct mlx5_flow_attr *attr);
 void
 mlx5_eswitch_del_fwd_rule(struct mlx5_eswitch *esw,
 			  struct mlx5_flow_handle *rule,
-			  struct mlx5_esw_flow_attr *attr);
+			  struct mlx5_flow_attr *attr);
 
 struct mlx5_flow_handle *
 mlx5_eswitch_create_vport_rx_rule(struct mlx5_eswitch *esw, u16 vport,
@@ -402,7 +401,6 @@ struct mlx5_esw_flow_attr {
 	int split_count;
 	int out_count;
 
-	int	action;
 	__be16	vlan_proto[MLX5_FS_VLAN_DEPTH];
 	u16	vlan_vid[MLX5_FS_VLAN_DEPTH];
 	u8	vlan_prio[MLX5_FS_VLAN_DEPTH];
@@ -414,19 +412,7 @@ struct mlx5_esw_flow_attr {
 		struct mlx5_core_dev *mdev;
 		struct mlx5_termtbl_handle *termtbl;
 	} dests[MLX5_MAX_FLOW_FWD_VPORTS];
-	struct  mlx5_modify_hdr *modify_hdr;
-	u8	inner_match_level;
-	u8	outer_match_level;
-	struct mlx5_fc *counter;
-	u32	chain;
-	u16	prio;
-	u32	dest_chain;
-	u32	flags;
-	struct mlx5_flow_table *fdb;
-	struct mlx5_flow_table *dest_ft;
-	struct mlx5_ct_attr ct_attr;
 	struct mlx5_pkt_reformat *decap_pkt_reformat;
-	struct mlx5e_tc_flow_parse_attr *parse_attr;
 };
 
 int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode,
@@ -452,9 +438,9 @@ int mlx5_devlink_port_function_hw_addr_set(struct devlink *devlink,
 void *mlx5_eswitch_get_uplink_priv(struct mlx5_eswitch *esw, u8 rep_type);
 
 int mlx5_eswitch_add_vlan_action(struct mlx5_eswitch *esw,
-				 struct mlx5_esw_flow_attr *attr);
+				 struct mlx5_flow_attr *attr);
 int mlx5_eswitch_del_vlan_action(struct mlx5_eswitch *esw,
-				 struct mlx5_esw_flow_attr *attr);
+				 struct mlx5_flow_attr *attr);
 int __mlx5_eswitch_set_vport_vlan(struct mlx5_eswitch *esw,
 				  u16 vport, u16 vlan, u8 qos, u8 set_flags);
 
@@ -678,6 +664,9 @@ int mlx5_eswitch_load_vf_vports(struct mlx5_eswitch *esw, u16 num_vfs,
 				enum mlx5_eswitch_vport_event enabled_events);
 void mlx5_eswitch_unload_vf_vports(struct mlx5_eswitch *esw, u16 num_vfs);
 
+int mlx5_esw_offloads_devlink_port_register(struct mlx5_eswitch *esw, u16 vport_num);
+void mlx5_esw_offloads_devlink_port_unregister(struct mlx5_eswitch *esw, u16 vport_num);
+struct devlink_port *mlx5_esw_offloads_devlink_port(struct mlx5_eswitch *esw, u16 vport_num);
 #else  /* CONFIG_MLX5_ESWITCH */
 /* eswitch API stubs */
 static inline int  mlx5_eswitch_init(struct mlx5_core_dev *dev) { return 0; }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index b23d20e16495..c9c2962ad49f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -39,12 +39,13 @@
 #include "mlx5_core.h"
 #include "eswitch.h"
 #include "esw/acl/ofld.h"
-#include "esw/chains.h"
 #include "rdma.h"
 #include "en.h"
 #include "fs_core.h"
 #include "lib/devcom.h"
 #include "lib/eq.h"
+#include "lib/fs_chains.h"
+#include "en_tc.h"
 
 /* There are two match-all miss flows, one for unicast dst mac and
  * one for multicast.
@@ -66,6 +67,12 @@ struct mlx5_vport_key {
 	u16 vhca_id;
 } __packed;
 
+struct mlx5_vport_tbl_attr {
+	u16 chain;
+	u16 prio;
+	u16 vport;
+};
+
 struct mlx5_vport_table {
 	struct hlist_node hlist;
 	struct mlx5_flow_table *fdb;
@@ -94,10 +101,10 @@ esw_vport_tbl_create(struct mlx5_eswitch *esw, struct mlx5_flow_namespace *ns)
 }
 
 static u32 flow_attr_to_vport_key(struct mlx5_eswitch *esw,
-				  struct mlx5_esw_flow_attr *attr,
+				  struct mlx5_vport_tbl_attr *attr,
 				  struct mlx5_vport_key *key)
 {
-	key->vport = attr->in_rep->vport;
+	key->vport = attr->vport;
 	key->chain = attr->chain;
 	key->prio = attr->prio;
 	key->vhca_id = MLX5_CAP_GEN(esw->dev, vhca_id);
@@ -118,7 +125,7 @@ esw_vport_tbl_lookup(struct mlx5_eswitch *esw, struct mlx5_vport_key *skey, u32
 }
 
 static void
-esw_vport_tbl_put(struct mlx5_eswitch *esw, struct mlx5_esw_flow_attr *attr)
+esw_vport_tbl_put(struct mlx5_eswitch *esw, struct mlx5_vport_tbl_attr *attr)
 {
 	struct mlx5_vport_table *e;
 	struct mlx5_vport_key key;
@@ -138,7 +145,7 @@ out:
 }
 
 static struct mlx5_flow_table *
-esw_vport_tbl_get(struct mlx5_eswitch *esw, struct mlx5_esw_flow_attr *attr)
+esw_vport_tbl_get(struct mlx5_eswitch *esw, struct mlx5_vport_tbl_attr *attr)
 {
 	struct mlx5_core_dev *dev = esw->dev;
 	struct mlx5_flow_namespace *ns;
@@ -189,16 +196,15 @@ err_alloc:
 
 int mlx5_esw_vport_tbl_get(struct mlx5_eswitch *esw)
 {
-	struct mlx5_esw_flow_attr attr = {};
-	struct mlx5_eswitch_rep rep = {};
+	struct mlx5_vport_tbl_attr attr;
 	struct mlx5_flow_table *fdb;
 	struct mlx5_vport *vport;
 	int i;
 
+	attr.chain = 0;
 	attr.prio = 1;
-	attr.in_rep = &rep;
 	mlx5_esw_for_all_vports(esw, i, vport) {
-		attr.in_rep->vport = vport->vport;
+		attr.vport = vport->vport;
 		fdb = esw_vport_tbl_get(esw, &attr);
 		if (IS_ERR(fdb))
 			goto out;
@@ -212,15 +218,14 @@ out:
 
 void mlx5_esw_vport_tbl_put(struct mlx5_eswitch *esw)
 {
-	struct mlx5_esw_flow_attr attr = {};
-	struct mlx5_eswitch_rep rep = {};
+	struct mlx5_vport_tbl_attr attr;
 	struct mlx5_vport *vport;
 	int i;
 
+	attr.chain = 0;
 	attr.prio = 1;
-	attr.in_rep = &rep;
 	mlx5_esw_for_all_vports(esw, i, vport) {
-		attr.in_rep->vport = vport->vport;
+		attr.vport = vport->vport;
 		esw_vport_tbl_put(esw, &attr);
 	}
 }
@@ -242,8 +247,11 @@ mlx5_eswitch_set_rule_flow_source(struct mlx5_eswitch *esw,
 				  struct mlx5_esw_flow_attr *attr)
 {
 	if (MLX5_CAP_ESW_FLOWTABLE(esw->dev, flow_source) &&
-	    attr && attr->in_rep && attr->in_rep->vport == MLX5_VPORT_UPLINK)
-		spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK;
+	    attr && attr->in_rep)
+		spec->flow_context.flow_source =
+			attr->in_rep->vport == MLX5_VPORT_UPLINK ?
+				MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK :
+				MLX5_FLOW_CONTEXT_FLOW_SOURCE_LOCAL_VPORT;
 }
 
 static void
@@ -290,11 +298,14 @@ mlx5_eswitch_set_rule_source_port(struct mlx5_eswitch *esw,
 struct mlx5_flow_handle *
 mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
 				struct mlx5_flow_spec *spec,
-				struct mlx5_esw_flow_attr *attr)
+				struct mlx5_flow_attr *attr)
 {
 	struct mlx5_flow_destination dest[MLX5_MAX_FLOW_FWD_VPORTS + 1] = {};
 	struct mlx5_flow_act flow_act = { .flags = FLOW_ACT_NO_APPEND, };
-	bool split = !!(attr->split_count);
+	struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr;
+	struct mlx5_fs_chains *chains = esw_chains(esw);
+	bool split = !!(esw_attr->split_count);
+	struct mlx5_vport_tbl_attr fwd_attr;
 	struct mlx5_flow_handle *rule;
 	struct mlx5_flow_table *fdb;
 	int j, i = 0;
@@ -308,13 +319,13 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
 		flow_act.action &= ~(MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH |
 				     MLX5_FLOW_CONTEXT_ACTION_VLAN_POP);
 	else if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH) {
-		flow_act.vlan[0].ethtype = ntohs(attr->vlan_proto[0]);
-		flow_act.vlan[0].vid = attr->vlan_vid[0];
-		flow_act.vlan[0].prio = attr->vlan_prio[0];
+		flow_act.vlan[0].ethtype = ntohs(esw_attr->vlan_proto[0]);
+		flow_act.vlan[0].vid = esw_attr->vlan_vid[0];
+		flow_act.vlan[0].prio = esw_attr->vlan_prio[0];
 		if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH_2) {
-			flow_act.vlan[1].ethtype = ntohs(attr->vlan_proto[1]);
-			flow_act.vlan[1].vid = attr->vlan_vid[1];
-			flow_act.vlan[1].prio = attr->vlan_prio[1];
+			flow_act.vlan[1].ethtype = ntohs(esw_attr->vlan_proto[1]);
+			flow_act.vlan[1].vid = esw_attr->vlan_vid[1];
+			flow_act.vlan[1].prio = esw_attr->vlan_prio[1];
 		}
 	}
 
@@ -329,12 +340,12 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
 		} else if (attr->flags & MLX5_ESW_ATTR_FLAG_SLOW_PATH) {
 			flow_act.flags |= FLOW_ACT_IGNORE_FLOW_LEVEL;
 			dest[i].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
-			dest[i].ft = mlx5_esw_chains_get_tc_end_ft(esw);
+			dest[i].ft = mlx5_chains_get_tc_end_ft(chains);
 			i++;
 		} else if (attr->dest_chain) {
 			flow_act.flags |= FLOW_ACT_IGNORE_FLOW_LEVEL;
-			ft = mlx5_esw_chains_get_table(esw, attr->dest_chain,
-						       1, 0);
+			ft = mlx5_chains_get_table(chains, attr->dest_chain,
+						   1, 0);
 			if (IS_ERR(ft)) {
 				rule = ERR_CAST(ft);
 				goto err_create_goto_table;
@@ -344,28 +355,29 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
 			dest[i].ft = ft;
 			i++;
 		} else {
-			for (j = attr->split_count; j < attr->out_count; j++) {
+			for (j = esw_attr->split_count; j < esw_attr->out_count; j++) {
 				dest[i].type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
-				dest[i].vport.num = attr->dests[j].rep->vport;
+				dest[i].vport.num = esw_attr->dests[j].rep->vport;
 				dest[i].vport.vhca_id =
-					MLX5_CAP_GEN(attr->dests[j].mdev, vhca_id);
+					MLX5_CAP_GEN(esw_attr->dests[j].mdev, vhca_id);
 				if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
 					dest[i].vport.flags |=
 						MLX5_FLOW_DEST_VPORT_VHCA_ID;
-				if (attr->dests[j].flags & MLX5_ESW_DEST_ENCAP) {
+				if (esw_attr->dests[j].flags & MLX5_ESW_DEST_ENCAP) {
 					flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT;
-					flow_act.pkt_reformat = attr->dests[j].pkt_reformat;
+					flow_act.pkt_reformat =
+							esw_attr->dests[j].pkt_reformat;
 					dest[i].vport.flags |= MLX5_FLOW_DEST_VPORT_REFORMAT_ID;
 					dest[i].vport.pkt_reformat =
-						attr->dests[j].pkt_reformat;
+						esw_attr->dests[j].pkt_reformat;
 				}
 				i++;
 			}
 		}
 	}
 
-	if (attr->decap_pkt_reformat)
-		flow_act.pkt_reformat = attr->decap_pkt_reformat;
+	if (esw_attr->decap_pkt_reformat)
+		flow_act.pkt_reformat = esw_attr->decap_pkt_reformat;
 
 	if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_COUNT) {
 		dest[i].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
@@ -382,26 +394,30 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
 		flow_act.modify_hdr = attr->modify_hdr;
 
 	if (split) {
-		fdb = esw_vport_tbl_get(esw, attr);
+		fwd_attr.chain = attr->chain;
+		fwd_attr.prio = attr->prio;
+		fwd_attr.vport = esw_attr->in_rep->vport;
+
+		fdb = esw_vport_tbl_get(esw, &fwd_attr);
 	} else {
 		if (attr->chain || attr->prio)
-			fdb = mlx5_esw_chains_get_table(esw, attr->chain,
-							attr->prio, 0);
+			fdb = mlx5_chains_get_table(chains, attr->chain,
+						    attr->prio, 0);
 		else
-			fdb = attr->fdb;
+			fdb = attr->ft;
 
 		if (!(attr->flags & MLX5_ESW_ATTR_FLAG_NO_IN_PORT))
-			mlx5_eswitch_set_rule_source_port(esw, spec, attr);
+			mlx5_eswitch_set_rule_source_port(esw, spec, esw_attr);
 	}
 	if (IS_ERR(fdb)) {
 		rule = ERR_CAST(fdb);
 		goto err_esw_get;
 	}
 
-	mlx5_eswitch_set_rule_flow_source(esw, spec, attr);
+	mlx5_eswitch_set_rule_flow_source(esw, spec, esw_attr);
 
 	if (mlx5_eswitch_termtbl_required(esw, attr, &flow_act, spec))
-		rule = mlx5_eswitch_add_termtbl_rule(esw, fdb, spec, attr,
+		rule = mlx5_eswitch_add_termtbl_rule(esw, fdb, spec, esw_attr,
 						     &flow_act, dest, i);
 	else
 		rule = mlx5_add_flow_rules(fdb, spec, &flow_act, dest, i);
@@ -414,12 +430,12 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
 
 err_add_rule:
 	if (split)
-		esw_vport_tbl_put(esw, attr);
+		esw_vport_tbl_put(esw, &fwd_attr);
 	else if (attr->chain || attr->prio)
-		mlx5_esw_chains_put_table(esw, attr->chain, attr->prio, 0);
+		mlx5_chains_put_table(chains, attr->chain, attr->prio, 0);
 err_esw_get:
 	if (!(attr->flags & MLX5_ESW_ATTR_FLAG_SLOW_PATH) && attr->dest_chain)
-		mlx5_esw_chains_put_table(esw, attr->dest_chain, 1, 0);
+		mlx5_chains_put_table(chains, attr->dest_chain, 1, 0);
 err_create_goto_table:
 	return rule;
 }
@@ -427,46 +443,51 @@ err_create_goto_table:
 struct mlx5_flow_handle *
 mlx5_eswitch_add_fwd_rule(struct mlx5_eswitch *esw,
 			  struct mlx5_flow_spec *spec,
-			  struct mlx5_esw_flow_attr *attr)
+			  struct mlx5_flow_attr *attr)
 {
 	struct mlx5_flow_destination dest[MLX5_MAX_FLOW_FWD_VPORTS + 1] = {};
 	struct mlx5_flow_act flow_act = { .flags = FLOW_ACT_NO_APPEND, };
+	struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr;
+	struct mlx5_fs_chains *chains = esw_chains(esw);
+	struct mlx5_vport_tbl_attr fwd_attr;
 	struct mlx5_flow_table *fast_fdb;
 	struct mlx5_flow_table *fwd_fdb;
 	struct mlx5_flow_handle *rule;
 	int i;
 
-	fast_fdb = mlx5_esw_chains_get_table(esw, attr->chain, attr->prio, 0);
+	fast_fdb = mlx5_chains_get_table(chains, attr->chain, attr->prio, 0);
 	if (IS_ERR(fast_fdb)) {
 		rule = ERR_CAST(fast_fdb);
 		goto err_get_fast;
 	}
 
-	fwd_fdb = esw_vport_tbl_get(esw, attr);
+	fwd_attr.chain = attr->chain;
+	fwd_attr.prio = attr->prio;
+	fwd_attr.vport = esw_attr->in_rep->vport;
+	fwd_fdb = esw_vport_tbl_get(esw, &fwd_attr);
 	if (IS_ERR(fwd_fdb)) {
 		rule = ERR_CAST(fwd_fdb);
 		goto err_get_fwd;
 	}
 
 	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
-	for (i = 0; i < attr->split_count; i++) {
+	for (i = 0; i < esw_attr->split_count; i++) {
 		dest[i].type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
-		dest[i].vport.num = attr->dests[i].rep->vport;
+		dest[i].vport.num = esw_attr->dests[i].rep->vport;
 		dest[i].vport.vhca_id =
-			MLX5_CAP_GEN(attr->dests[i].mdev, vhca_id);
+			MLX5_CAP_GEN(esw_attr->dests[i].mdev, vhca_id);
 		if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
 			dest[i].vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID;
-		if (attr->dests[i].flags & MLX5_ESW_DEST_ENCAP) {
+		if (esw_attr->dests[i].flags & MLX5_ESW_DEST_ENCAP) {
 			dest[i].vport.flags |= MLX5_FLOW_DEST_VPORT_REFORMAT_ID;
-			dest[i].vport.pkt_reformat = attr->dests[i].pkt_reformat;
+			dest[i].vport.pkt_reformat = esw_attr->dests[i].pkt_reformat;
 		}
 	}
 	dest[i].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
 	dest[i].ft = fwd_fdb,
 	i++;
 
-	mlx5_eswitch_set_rule_source_port(esw, spec, attr);
-	mlx5_eswitch_set_rule_flow_source(esw, spec, attr);
+	mlx5_eswitch_set_rule_source_port(esw, spec, esw_attr);
 
 	if (attr->outer_match_level != MLX5_MATCH_NONE)
 		spec->match_criteria_enable |= MLX5_MATCH_OUTER_HEADERS;
@@ -481,9 +502,9 @@ mlx5_eswitch_add_fwd_rule(struct mlx5_eswitch *esw,
 
 	return rule;
 add_err:
-	esw_vport_tbl_put(esw, attr);
+	esw_vport_tbl_put(esw, &fwd_attr);
 err_get_fwd:
-	mlx5_esw_chains_put_table(esw, attr->chain, attr->prio, 0);
+	mlx5_chains_put_table(chains, attr->chain, attr->prio, 0);
 err_get_fast:
 	return rule;
 }
@@ -491,10 +512,13 @@ err_get_fast:
 static void
 __mlx5_eswitch_del_rule(struct mlx5_eswitch *esw,
 			struct mlx5_flow_handle *rule,
-			struct mlx5_esw_flow_attr *attr,
+			struct mlx5_flow_attr *attr,
 			bool fwd_rule)
 {
-	bool split = (attr->split_count > 0);
+	struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr;
+	struct mlx5_fs_chains *chains = esw_chains(esw);
+	bool split = (esw_attr->split_count > 0);
+	struct mlx5_vport_tbl_attr fwd_attr;
 	int i;
 
 	mlx5_del_flow_rules(rule);
@@ -502,31 +526,36 @@ __mlx5_eswitch_del_rule(struct mlx5_eswitch *esw,
 	if (!(attr->flags & MLX5_ESW_ATTR_FLAG_SLOW_PATH)) {
 		/* unref the term table */
 		for (i = 0; i < MLX5_MAX_FLOW_FWD_VPORTS; i++) {
-			if (attr->dests[i].termtbl)
-				mlx5_eswitch_termtbl_put(esw, attr->dests[i].termtbl);
+			if (esw_attr->dests[i].termtbl)
+				mlx5_eswitch_termtbl_put(esw, esw_attr->dests[i].termtbl);
 		}
 	}
 
 	atomic64_dec(&esw->offloads.num_flows);
 
+	if (fwd_rule || split) {
+		fwd_attr.chain = attr->chain;
+		fwd_attr.prio = attr->prio;
+		fwd_attr.vport = esw_attr->in_rep->vport;
+	}
+
 	if (fwd_rule)  {
-		esw_vport_tbl_put(esw, attr);
-		mlx5_esw_chains_put_table(esw, attr->chain, attr->prio, 0);
+		esw_vport_tbl_put(esw, &fwd_attr);
+		mlx5_chains_put_table(chains, attr->chain, attr->prio, 0);
 	} else {
 		if (split)
-			esw_vport_tbl_put(esw, attr);
+			esw_vport_tbl_put(esw, &fwd_attr);
 		else if (attr->chain || attr->prio)
-			mlx5_esw_chains_put_table(esw, attr->chain, attr->prio,
-						  0);
+			mlx5_chains_put_table(chains, attr->chain, attr->prio, 0);
 		if (attr->dest_chain)
-			mlx5_esw_chains_put_table(esw, attr->dest_chain, 1, 0);
+			mlx5_chains_put_table(chains, attr->dest_chain, 1, 0);
 	}
 }
 
 void
 mlx5_eswitch_del_offloaded_rule(struct mlx5_eswitch *esw,
 				struct mlx5_flow_handle *rule,
-				struct mlx5_esw_flow_attr *attr)
+				struct mlx5_flow_attr *attr)
 {
 	__mlx5_eswitch_del_rule(esw, rule, attr, false);
 }
@@ -534,7 +563,7 @@ mlx5_eswitch_del_offloaded_rule(struct mlx5_eswitch *esw,
 void
 mlx5_eswitch_del_fwd_rule(struct mlx5_eswitch *esw,
 			  struct mlx5_flow_handle *rule,
-			  struct mlx5_esw_flow_attr *attr)
+			  struct mlx5_flow_attr *attr)
 {
 	__mlx5_eswitch_del_rule(esw, rule, attr, true);
 }
@@ -611,9 +640,10 @@ out_notsupp:
 }
 
 int mlx5_eswitch_add_vlan_action(struct mlx5_eswitch *esw,
-				 struct mlx5_esw_flow_attr *attr)
+				 struct mlx5_flow_attr *attr)
 {
 	struct offloads_fdb *offloads = &esw->fdb_table.offloads;
+	struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr;
 	struct mlx5_eswitch_rep *vport = NULL;
 	bool push, pop, fwd;
 	int err = 0;
@@ -629,17 +659,17 @@ int mlx5_eswitch_add_vlan_action(struct mlx5_eswitch *esw,
 
 	mutex_lock(&esw->state_lock);
 
-	err = esw_add_vlan_action_check(attr, push, pop, fwd);
+	err = esw_add_vlan_action_check(esw_attr, push, pop, fwd);
 	if (err)
 		goto unlock;
 
 	attr->flags &= ~MLX5_ESW_ATTR_FLAG_VLAN_HANDLED;
 
-	vport = esw_vlan_action_get_vport(attr, push, pop);
+	vport = esw_vlan_action_get_vport(esw_attr, push, pop);
 
 	if (!push && !pop && fwd) {
 		/* tracks VF --> wire rules without vlan push action */
-		if (attr->dests[0].rep->vport == MLX5_VPORT_UPLINK) {
+		if (esw_attr->dests[0].rep->vport == MLX5_VPORT_UPLINK) {
 			vport->vlan_refcount++;
 			attr->flags |= MLX5_ESW_ATTR_FLAG_VLAN_HANDLED;
 		}
@@ -662,11 +692,11 @@ int mlx5_eswitch_add_vlan_action(struct mlx5_eswitch *esw,
 		if (vport->vlan_refcount)
 			goto skip_set_push;
 
-		err = __mlx5_eswitch_set_vport_vlan(esw, vport->vport, attr->vlan_vid[0], 0,
-						    SET_VLAN_INSERT | SET_VLAN_STRIP);
+		err = __mlx5_eswitch_set_vport_vlan(esw, vport->vport, esw_attr->vlan_vid[0],
+						    0, SET_VLAN_INSERT | SET_VLAN_STRIP);
 		if (err)
 			goto out;
-		vport->vlan = attr->vlan_vid[0];
+		vport->vlan = esw_attr->vlan_vid[0];
 skip_set_push:
 		vport->vlan_refcount++;
 	}
@@ -679,9 +709,10 @@ unlock:
 }
 
 int mlx5_eswitch_del_vlan_action(struct mlx5_eswitch *esw,
-				 struct mlx5_esw_flow_attr *attr)
+				 struct mlx5_flow_attr *attr)
 {
 	struct offloads_fdb *offloads = &esw->fdb_table.offloads;
+	struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr;
 	struct mlx5_eswitch_rep *vport = NULL;
 	bool push, pop, fwd;
 	int err = 0;
@@ -699,11 +730,11 @@ int mlx5_eswitch_del_vlan_action(struct mlx5_eswitch *esw,
 
 	mutex_lock(&esw->state_lock);
 
-	vport = esw_vlan_action_get_vport(attr, push, pop);
+	vport = esw_vlan_action_get_vport(esw_attr, push, pop);
 
 	if (!push && !pop && fwd) {
 		/* tracks VF --> wire rules without vlan push action */
-		if (attr->dests[0].rep->vport == MLX5_VPORT_UPLINK)
+		if (esw_attr->dests[0].rep->vport == MLX5_VPORT_UPLINK)
 			vport->vlan_refcount--;
 
 		goto out;
@@ -1137,6 +1168,126 @@ static void esw_set_flow_group_source_port(struct mlx5_eswitch *esw,
 	}
 }
 
+#if IS_ENABLED(CONFIG_MLX5_CLS_ACT)
+#define fdb_modify_header_fwd_to_table_supported(esw) \
+	(MLX5_CAP_ESW_FLOWTABLE((esw)->dev, fdb_modify_header_fwd_to_table))
+static void esw_init_chains_offload_flags(struct mlx5_eswitch *esw, u32 *flags)
+{
+	struct mlx5_core_dev *dev = esw->dev;
+
+	if (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, ignore_flow_level))
+		*flags |= MLX5_CHAINS_IGNORE_FLOW_LEVEL_SUPPORTED;
+
+	if (!MLX5_CAP_ESW_FLOWTABLE(dev, multi_fdb_encap) &&
+	    esw->offloads.encap != DEVLINK_ESWITCH_ENCAP_MODE_NONE) {
+		*flags &= ~MLX5_CHAINS_AND_PRIOS_SUPPORTED;
+		esw_warn(dev, "Tc chains and priorities offload aren't supported, update firmware if needed\n");
+	} else if (!mlx5_eswitch_reg_c1_loopback_enabled(esw)) {
+		*flags &= ~MLX5_CHAINS_AND_PRIOS_SUPPORTED;
+		esw_warn(dev, "Tc chains and priorities offload aren't supported\n");
+	} else if (!fdb_modify_header_fwd_to_table_supported(esw)) {
+		/* Disabled when ttl workaround is needed, e.g
+		 * when ESWITCH_IPV4_TTL_MODIFY_ENABLE = true in mlxconfig
+		 */
+		esw_warn(dev,
+			 "Tc chains and priorities offload aren't supported, check firmware version, or mlxconfig settings\n");
+		*flags &= ~MLX5_CHAINS_AND_PRIOS_SUPPORTED;
+	} else {
+		*flags |= MLX5_CHAINS_AND_PRIOS_SUPPORTED;
+		esw_info(dev, "Supported tc chains and prios offload\n");
+	}
+
+	if (esw->offloads.encap != DEVLINK_ESWITCH_ENCAP_MODE_NONE)
+		*flags |= MLX5_CHAINS_FT_TUNNEL_SUPPORTED;
+}
+
+static int
+esw_chains_create(struct mlx5_eswitch *esw, struct mlx5_flow_table *miss_fdb)
+{
+	struct mlx5_core_dev *dev = esw->dev;
+	struct mlx5_flow_table *nf_ft, *ft;
+	struct mlx5_chains_attr attr = {};
+	struct mlx5_fs_chains *chains;
+	u32 fdb_max;
+	int err;
+
+	fdb_max = 1 << MLX5_CAP_ESW_FLOWTABLE_FDB(dev, log_max_ft_size);
+
+	esw_init_chains_offload_flags(esw, &attr.flags);
+	attr.ns = MLX5_FLOW_NAMESPACE_FDB;
+	attr.max_ft_sz = fdb_max;
+	attr.max_grp_num = esw->params.large_group_num;
+	attr.default_ft = miss_fdb;
+	attr.max_restore_tag = esw_get_max_restore_tag(esw);
+
+	chains = mlx5_chains_create(dev, &attr);
+	if (IS_ERR(chains)) {
+		err = PTR_ERR(chains);
+		esw_warn(dev, "Failed to create fdb chains err(%d)\n", err);
+		return err;
+	}
+
+	esw->fdb_table.offloads.esw_chains_priv = chains;
+
+	/* Create tc_end_ft which is the always created ft chain */
+	nf_ft = mlx5_chains_get_table(chains, mlx5_chains_get_nf_ft_chain(chains),
+				      1, 0);
+	if (IS_ERR(nf_ft)) {
+		err = PTR_ERR(nf_ft);
+		goto nf_ft_err;
+	}
+
+	/* Always open the root for fast path */
+	ft = mlx5_chains_get_table(chains, 0, 1, 0);
+	if (IS_ERR(ft)) {
+		err = PTR_ERR(ft);
+		goto level_0_err;
+	}
+
+	/* Open level 1 for split fdb rules now if prios isn't supported  */
+	if (!mlx5_chains_prios_supported(chains)) {
+		err = mlx5_esw_vport_tbl_get(esw);
+		if (err)
+			goto level_1_err;
+	}
+
+	mlx5_chains_set_end_ft(chains, nf_ft);
+
+	return 0;
+
+level_1_err:
+	mlx5_chains_put_table(chains, 0, 1, 0);
+level_0_err:
+	mlx5_chains_put_table(chains, mlx5_chains_get_nf_ft_chain(chains), 1, 0);
+nf_ft_err:
+	mlx5_chains_destroy(chains);
+	esw->fdb_table.offloads.esw_chains_priv = NULL;
+
+	return err;
+}
+
+static void
+esw_chains_destroy(struct mlx5_eswitch *esw, struct mlx5_fs_chains *chains)
+{
+	if (!mlx5_chains_prios_supported(chains))
+		mlx5_esw_vport_tbl_put(esw);
+	mlx5_chains_put_table(chains, 0, 1, 0);
+	mlx5_chains_put_table(chains, mlx5_chains_get_nf_ft_chain(chains), 1, 0);
+	mlx5_chains_destroy(chains);
+}
+
+#else /* CONFIG_MLX5_CLS_ACT */
+
+static int
+esw_chains_create(struct mlx5_eswitch *esw, struct mlx5_flow_table *miss_fdb)
+{ return 0; }
+
+static void
+esw_chains_destroy(struct mlx5_eswitch *esw, struct mlx5_fs_chains *chains)
+{}
+
+#endif
+
 static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw)
 {
 	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
@@ -1192,9 +1343,9 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw)
 	}
 	esw->fdb_table.offloads.slow_fdb = fdb;
 
-	err = mlx5_esw_chains_create(esw);
+	err = esw_chains_create(esw, fdb);
 	if (err) {
-		esw_warn(dev, "Failed to create fdb chains err(%d)\n", err);
+		esw_warn(dev, "Failed to open fdb chains err(%d)\n", err);
 		goto fdb_chains_err;
 	}
 
@@ -1219,35 +1370,37 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw)
 	}
 	esw->fdb_table.offloads.send_to_vport_grp = g;
 
-	/* create peer esw miss group */
-	memset(flow_group_in, 0, inlen);
+	if (MLX5_CAP_ESW(esw->dev, merged_eswitch)) {
+		/* create peer esw miss group */
+		memset(flow_group_in, 0, inlen);
 
-	esw_set_flow_group_source_port(esw, flow_group_in);
+		esw_set_flow_group_source_port(esw, flow_group_in);
 
-	if (!mlx5_eswitch_vport_match_metadata_enabled(esw)) {
-		match_criteria = MLX5_ADDR_OF(create_flow_group_in,
-					      flow_group_in,
-					      match_criteria);
+		if (!mlx5_eswitch_vport_match_metadata_enabled(esw)) {
+			match_criteria = MLX5_ADDR_OF(create_flow_group_in,
+						      flow_group_in,
+						      match_criteria);
 
-		MLX5_SET_TO_ONES(fte_match_param, match_criteria,
-				 misc_parameters.source_eswitch_owner_vhca_id);
+			MLX5_SET_TO_ONES(fte_match_param, match_criteria,
+					 misc_parameters.source_eswitch_owner_vhca_id);
 
-		MLX5_SET(create_flow_group_in, flow_group_in,
-			 source_eswitch_owner_vhca_id_valid, 1);
-	}
+			MLX5_SET(create_flow_group_in, flow_group_in,
+				 source_eswitch_owner_vhca_id_valid, 1);
+		}
 
-	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ix);
-	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index,
-		 ix + esw->total_vports - 1);
-	ix += esw->total_vports;
+		MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ix);
+		MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index,
+			 ix + esw->total_vports - 1);
+		ix += esw->total_vports;
 
-	g = mlx5_create_flow_group(fdb, flow_group_in);
-	if (IS_ERR(g)) {
-		err = PTR_ERR(g);
-		esw_warn(dev, "Failed to create peer miss flow group err(%d)\n", err);
-		goto peer_miss_err;
+		g = mlx5_create_flow_group(fdb, flow_group_in);
+		if (IS_ERR(g)) {
+			err = PTR_ERR(g);
+			esw_warn(dev, "Failed to create peer miss flow group err(%d)\n", err);
+			goto peer_miss_err;
+		}
+		esw->fdb_table.offloads.peer_miss_grp = g;
 	}
-	esw->fdb_table.offloads.peer_miss_grp = g;
 
 	/* create miss group */
 	memset(flow_group_in, 0, inlen);
@@ -1281,11 +1434,12 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw)
 miss_rule_err:
 	mlx5_destroy_flow_group(esw->fdb_table.offloads.miss_grp);
 miss_err:
-	mlx5_destroy_flow_group(esw->fdb_table.offloads.peer_miss_grp);
+	if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
+		mlx5_destroy_flow_group(esw->fdb_table.offloads.peer_miss_grp);
 peer_miss_err:
 	mlx5_destroy_flow_group(esw->fdb_table.offloads.send_to_vport_grp);
 send_vport_err:
-	mlx5_esw_chains_destroy(esw);
+	esw_chains_destroy(esw, esw_chains(esw));
 fdb_chains_err:
 	mlx5_destroy_flow_table(esw->fdb_table.offloads.slow_fdb);
 slow_fdb_err:
@@ -1305,10 +1459,12 @@ static void esw_destroy_offloads_fdb_tables(struct mlx5_eswitch *esw)
 	mlx5_del_flow_rules(esw->fdb_table.offloads.miss_rule_multi);
 	mlx5_del_flow_rules(esw->fdb_table.offloads.miss_rule_uni);
 	mlx5_destroy_flow_group(esw->fdb_table.offloads.send_to_vport_grp);
-	mlx5_destroy_flow_group(esw->fdb_table.offloads.peer_miss_grp);
+	if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
+		mlx5_destroy_flow_group(esw->fdb_table.offloads.peer_miss_grp);
 	mlx5_destroy_flow_group(esw->fdb_table.offloads.miss_grp);
 
-	mlx5_esw_chains_destroy(esw);
+	esw_chains_destroy(esw, esw_chains(esw));
+
 	mlx5_destroy_flow_table(esw->fdb_table.offloads.slow_fdb);
 	/* Holds true only as long as DMFS is the default */
 	mlx5_flow_namespace_set_mode(esw->fdb_table.offloads.ns,
@@ -1667,15 +1823,12 @@ static void __unload_reps_all_vport(struct mlx5_eswitch *esw, u8 rep_type)
 	__esw_offloads_unload_rep(esw, rep, rep_type);
 }
 
-int esw_offloads_load_rep(struct mlx5_eswitch *esw, u16 vport_num)
+static int mlx5_esw_offloads_rep_load(struct mlx5_eswitch *esw, u16 vport_num)
 {
 	struct mlx5_eswitch_rep *rep;
 	int rep_type;
 	int err;
 
-	if (esw->mode != MLX5_ESWITCH_OFFLOADS)
-		return 0;
-
 	rep = mlx5_eswitch_get_rep(esw, vport_num);
 	for (rep_type = 0; rep_type < NUM_REP_TYPES; rep_type++)
 		if (atomic_cmpxchg(&rep->rep_data[rep_type].state,
@@ -1694,19 +1847,46 @@ err_reps:
 	return err;
 }
 
-void esw_offloads_unload_rep(struct mlx5_eswitch *esw, u16 vport_num)
+static void mlx5_esw_offloads_rep_unload(struct mlx5_eswitch *esw, u16 vport_num)
 {
 	struct mlx5_eswitch_rep *rep;
 	int rep_type;
 
-	if (esw->mode != MLX5_ESWITCH_OFFLOADS)
-		return;
-
 	rep = mlx5_eswitch_get_rep(esw, vport_num);
 	for (rep_type = NUM_REP_TYPES - 1; rep_type >= 0; rep_type--)
 		__esw_offloads_unload_rep(esw, rep, rep_type);
 }
 
+int esw_offloads_load_rep(struct mlx5_eswitch *esw, u16 vport_num)
+{
+	int err;
+
+	if (esw->mode != MLX5_ESWITCH_OFFLOADS)
+		return 0;
+
+	err = mlx5_esw_offloads_devlink_port_register(esw, vport_num);
+	if (err)
+		return err;
+
+	err = mlx5_esw_offloads_rep_load(esw, vport_num);
+	if (err)
+		goto load_err;
+	return err;
+
+load_err:
+	mlx5_esw_offloads_devlink_port_unregister(esw, vport_num);
+	return err;
+}
+
+void esw_offloads_unload_rep(struct mlx5_eswitch *esw, u16 vport_num)
+{
+	if (esw->mode != MLX5_ESWITCH_OFFLOADS)
+		return;
+
+	mlx5_esw_offloads_rep_unload(esw, vport_num);
+	mlx5_esw_offloads_devlink_port_unregister(esw, vport_num);
+}
+
 #define ESW_OFFLOADS_DEVCOM_PAIR	(0)
 #define ESW_OFFLOADS_DEVCOM_UNPAIR	(1)
 
@@ -1866,31 +2046,31 @@ esw_check_vport_match_metadata_supported(const struct mlx5_eswitch *esw)
 
 u32 mlx5_esw_match_metadata_alloc(struct mlx5_eswitch *esw)
 {
-	u32 num_vports = GENMASK(ESW_VPORT_BITS - 1, 0) - 1;
-	u32 vhca_id_mask = GENMASK(ESW_VHCA_ID_BITS - 1, 0);
-	u32 vhca_id = MLX5_CAP_GEN(esw->dev, vhca_id);
-	u32 start;
-	u32 end;
+	u32 vport_end_ida = (1 << ESW_VPORT_BITS) - 1;
+	u32 max_pf_num = (1 << ESW_PFNUM_BITS) - 1;
+	u32 pf_num;
 	int id;
 
-	/* Make sure the vhca_id fits the ESW_VHCA_ID_BITS */
-	WARN_ON_ONCE(vhca_id >= BIT(ESW_VHCA_ID_BITS));
-
-	/* Trim vhca_id to ESW_VHCA_ID_BITS */
-	vhca_id &= vhca_id_mask;
-
-	start = (vhca_id << ESW_VPORT_BITS);
-	end = start + num_vports;
-	if (!vhca_id)
-		start += 1; /* zero is reserved/invalid metadata */
-	id = ida_alloc_range(&esw->offloads.vport_metadata_ida, start, end, GFP_KERNEL);
+	/* Only 4 bits of pf_num */
+	pf_num = PCI_FUNC(esw->dev->pdev->devfn);
+	if (pf_num > max_pf_num)
+		return 0;
 
-	return (id < 0) ? 0 : id;
+	/* Metadata is 4 bits of PFNUM and 12 bits of unique id */
+	/* Use only non-zero vport_id (1-4095) for all PF's */
+	id = ida_alloc_range(&esw->offloads.vport_metadata_ida, 1, vport_end_ida, GFP_KERNEL);
+	if (id < 0)
+		return 0;
+	id = (pf_num << ESW_VPORT_BITS) | id;
+	return id;
 }
 
 void mlx5_esw_match_metadata_free(struct mlx5_eswitch *esw, u32 metadata)
 {
-	ida_free(&esw->offloads.vport_metadata_ida, metadata);
+	u32 vport_bit_mask = (1 << ESW_VPORT_BITS) - 1;
+
+	/* Metadata contains only 12 bits of actual ida id */
+	ida_free(&esw->offloads.vport_metadata_ida, metadata & vport_bit_mask);
 }
 
 static int esw_offloads_vport_metadata_setup(struct mlx5_eswitch *esw,
@@ -1955,11 +2135,9 @@ esw_vport_create_offloads_acl_tables(struct mlx5_eswitch *esw,
 	if (err)
 		return err;
 
-	if (mlx5_eswitch_is_vf_vport(esw, vport->vport)) {
-		err = esw_acl_egress_ofld_setup(esw, vport);
-		if (err)
-			goto egress_err;
-	}
+	err = esw_acl_egress_ofld_setup(esw, vport);
+	if (err)
+		goto egress_err;
 
 	return 0;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c
index 17a0d2bc102b..ec679560a95d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c
@@ -3,6 +3,7 @@
 
 #include <linux/mlx5/fs.h>
 #include "eswitch.h"
+#include "en_tc.h"
 #include "fs_core.h"
 
 struct mlx5_termtbl_handle {
@@ -228,10 +229,11 @@ static bool mlx5_eswitch_offload_is_uplink_port(const struct mlx5_eswitch *esw,
 
 bool
 mlx5_eswitch_termtbl_required(struct mlx5_eswitch *esw,
-			      struct mlx5_esw_flow_attr *attr,
+			      struct mlx5_flow_attr *attr,
 			      struct mlx5_flow_act *flow_act,
 			      struct mlx5_flow_spec *spec)
 {
+	struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr;
 	int i;
 
 	if (!MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, termination_table) ||
@@ -244,8 +246,8 @@ mlx5_eswitch_termtbl_required(struct mlx5_eswitch *esw,
 		return true;
 
 	/* hairpin */
-	for (i = attr->split_count; i < attr->out_count; i++)
-		if (attr->dests[i].rep->vport == MLX5_VPORT_UPLINK)
+	for (i = esw_attr->split_count; i < esw_attr->out_count; i++)
+		if (esw_attr->dests[i].rep->vport == MLX5_VPORT_UPLINK)
 			return true;
 
 	return false;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c
index 9f6d97eae0ae..80da50e12915 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c
@@ -54,7 +54,7 @@ static int mlx5_fpga_conn_map_buf(struct mlx5_fpga_conn *conn,
 	if (unlikely(!buf->sg[0].data))
 		goto out;
 
-	dma_device = &conn->fdev->mdev->pdev->dev;
+	dma_device = mlx5_core_dma_dev(conn->fdev->mdev);
 	buf->sg[0].dma_addr = dma_map_single(dma_device, buf->sg[0].data,
 					     buf->sg[0].size, buf->dma_dir);
 	err = dma_mapping_error(dma_device, buf->sg[0].dma_addr);
@@ -86,7 +86,7 @@ static void mlx5_fpga_conn_unmap_buf(struct mlx5_fpga_conn *conn,
 {
 	struct device *dma_device;
 
-	dma_device = &conn->fdev->mdev->pdev->dev;
+	dma_device = mlx5_core_dma_dev(conn->fdev->mdev);
 	if (buf->sg[1].data)
 		dma_unmap_single(dma_device, buf->sg[1].dma_addr,
 				 buf->sg[1].size, buf->dma_dir);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 9ccec5f8b92a..6141e9ec8190 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -654,7 +654,7 @@ static struct fs_fte *alloc_fte(struct mlx5_flow_table *ft,
 	fte->action = *flow_act;
 	fte->flow_context = spec->flow_context;
 
-	tree_init_node(&fte->node, NULL, del_sw_fte);
+	tree_init_node(&fte->node, del_hw_fte, del_sw_fte);
 
 	return fte;
 }
@@ -1595,11 +1595,12 @@ static bool dest_is_valid(struct mlx5_flow_destination *dest,
 		return true;
 
 	if (ignore_level) {
-		if (ft->type != FS_FT_FDB)
+		if (ft->type != FS_FT_FDB &&
+		    ft->type != FS_FT_NIC_RX)
 			return false;
 
 		if (dest->type == MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE &&
-		    dest->ft->type != FS_FT_FDB)
+		    ft->type != dest->ft->type)
 			return false;
 	}
 
@@ -1792,7 +1793,6 @@ skip_search:
 		up_write_ref_node(&g->node, false);
 		rule = add_rule_fg(g, spec, flow_act, dest, dest_num, fte);
 		up_write_ref_node(&fte->node, false);
-		tree_put_node(&fte->node, false);
 		return rule;
 	}
 	rule = ERR_PTR(-ENOENT);
@@ -1891,7 +1891,6 @@ search_again_locked:
 	up_write_ref_node(&g->node, false);
 	rule = add_rule_fg(g, spec, flow_act, dest, dest_num, fte);
 	up_write_ref_node(&fte->node, false);
-	tree_put_node(&fte->node, false);
 	tree_put_node(&g->node, false);
 	return rule;
 
@@ -2001,7 +2000,9 @@ void mlx5_del_flow_rules(struct mlx5_flow_handle *handle)
 		up_write_ref_node(&fte->node, false);
 	} else {
 		del_hw_fte(&fte->node);
-		up_write(&fte->node.lock);
+		/* Avoid double call to del_hw_fte */
+		fte->node.del_hw_func = NULL;
+		up_write_ref_node(&fte->node, false);
 		tree_put_node(&fte->node, false);
 	}
 	kfree(handle);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
index 7fc59e01a353..c70c1f0ca0c1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
@@ -435,8 +435,6 @@ static int mlx5_ptp_verify(struct ptp_clock_info *ptp, unsigned int pin,
 	default:
 		return -EOPNOTSUPP;
 	}
-
-	return -EOPNOTSUPP;
 }
 
 static const struct ptp_clock_info mlx5_ptp_clock_info = {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c
new file mode 100644
index 000000000000..947f346bdc2d
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c
@@ -0,0 +1,911 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+// Copyright (c) 2020 Mellanox Technologies.
+
+#include <linux/mlx5/driver.h>
+#include <linux/mlx5/mlx5_ifc.h>
+#include <linux/mlx5/fs.h>
+
+#include "lib/fs_chains.h"
+#include "en/mapping.h"
+#include "mlx5_core.h"
+#include "fs_core.h"
+#include "eswitch.h"
+#include "en.h"
+#include "en_tc.h"
+
+#define chains_lock(chains) ((chains)->lock)
+#define chains_ht(chains) ((chains)->chains_ht)
+#define chains_mapping(chains) ((chains)->chains_mapping)
+#define prios_ht(chains) ((chains)->prios_ht)
+#define ft_pool_left(chains) ((chains)->ft_left)
+#define tc_default_ft(chains) ((chains)->tc_default_ft)
+#define tc_end_ft(chains) ((chains)->tc_end_ft)
+#define ns_to_chains_fs_prio(ns) ((ns) == MLX5_FLOW_NAMESPACE_FDB ? \
+				  FDB_TC_OFFLOAD : MLX5E_TC_PRIO)
+
+/* Firmware currently has 4 pool of 4 sizes that it supports (FT_POOLS),
+ * and a virtual memory region of 16M (MLX5_FT_SIZE), this region is duplicated
+ * for each flow table pool. We can allocate up to 16M of each pool,
+ * and we keep track of how much we used via get_next_avail_sz_from_pool.
+ * Firmware doesn't report any of this for now.
+ * ESW_POOL is expected to be sorted from large to small and match firmware
+ * pools.
+ */
+#define FT_SIZE (16 * 1024 * 1024)
+static const unsigned int FT_POOLS[] = { 4 * 1024 * 1024,
+					  1 * 1024 * 1024,
+					  64 * 1024,
+					  128 };
+#define FT_TBL_SZ (64 * 1024)
+
+struct mlx5_fs_chains {
+	struct mlx5_core_dev *dev;
+
+	struct rhashtable chains_ht;
+	struct rhashtable prios_ht;
+	/* Protects above chains_ht and prios_ht */
+	struct mutex lock;
+
+	struct mlx5_flow_table *tc_default_ft;
+	struct mlx5_flow_table *tc_end_ft;
+	struct mapping_ctx *chains_mapping;
+
+	enum mlx5_flow_namespace_type ns;
+	u32 group_num;
+	u32 flags;
+
+	int ft_left[ARRAY_SIZE(FT_POOLS)];
+};
+
+struct fs_chain {
+	struct rhash_head node;
+
+	u32 chain;
+
+	int ref;
+	int id;
+
+	struct mlx5_fs_chains *chains;
+	struct list_head prios_list;
+	struct mlx5_flow_handle *restore_rule;
+	struct mlx5_modify_hdr *miss_modify_hdr;
+};
+
+struct prio_key {
+	u32 chain;
+	u32 prio;
+	u32 level;
+};
+
+struct prio {
+	struct rhash_head node;
+	struct list_head list;
+
+	struct prio_key key;
+
+	int ref;
+
+	struct fs_chain *chain;
+	struct mlx5_flow_table *ft;
+	struct mlx5_flow_table *next_ft;
+	struct mlx5_flow_group *miss_group;
+	struct mlx5_flow_handle *miss_rule;
+};
+
+static const struct rhashtable_params chain_params = {
+	.head_offset = offsetof(struct fs_chain, node),
+	.key_offset = offsetof(struct fs_chain, chain),
+	.key_len = sizeof_field(struct fs_chain, chain),
+	.automatic_shrinking = true,
+};
+
+static const struct rhashtable_params prio_params = {
+	.head_offset = offsetof(struct prio, node),
+	.key_offset = offsetof(struct prio, key),
+	.key_len = sizeof_field(struct prio, key),
+	.automatic_shrinking = true,
+};
+
+bool mlx5_chains_prios_supported(struct mlx5_fs_chains *chains)
+{
+	return chains->flags & MLX5_CHAINS_AND_PRIOS_SUPPORTED;
+}
+
+static bool mlx5_chains_ignore_flow_level_supported(struct mlx5_fs_chains *chains)
+{
+	return chains->flags & MLX5_CHAINS_IGNORE_FLOW_LEVEL_SUPPORTED;
+}
+
+bool mlx5_chains_backwards_supported(struct mlx5_fs_chains *chains)
+{
+	return mlx5_chains_prios_supported(chains) &&
+	       mlx5_chains_ignore_flow_level_supported(chains);
+}
+
+u32 mlx5_chains_get_chain_range(struct mlx5_fs_chains *chains)
+{
+	if (!mlx5_chains_prios_supported(chains))
+		return 1;
+
+	if (mlx5_chains_ignore_flow_level_supported(chains))
+		return UINT_MAX - 1;
+
+	/* We should get here only for eswitch case */
+	return FDB_TC_MAX_CHAIN;
+}
+
+u32 mlx5_chains_get_nf_ft_chain(struct mlx5_fs_chains *chains)
+{
+	return mlx5_chains_get_chain_range(chains) + 1;
+}
+
+u32 mlx5_chains_get_prio_range(struct mlx5_fs_chains *chains)
+{
+	if (!mlx5_chains_prios_supported(chains))
+		return 1;
+
+	if (mlx5_chains_ignore_flow_level_supported(chains))
+		return UINT_MAX;
+
+	/* We should get here only for eswitch case */
+	return FDB_TC_MAX_PRIO;
+}
+
+static unsigned int mlx5_chains_get_level_range(struct mlx5_fs_chains *chains)
+{
+	if (mlx5_chains_ignore_flow_level_supported(chains))
+		return UINT_MAX;
+
+	/* Same value for FDB and NIC RX tables */
+	return FDB_TC_LEVELS_PER_PRIO;
+}
+
+void
+mlx5_chains_set_end_ft(struct mlx5_fs_chains *chains,
+		       struct mlx5_flow_table *ft)
+{
+	tc_end_ft(chains) = ft;
+}
+
+#define POOL_NEXT_SIZE 0
+static int
+mlx5_chains_get_avail_sz_from_pool(struct mlx5_fs_chains *chains,
+				   int desired_size)
+{
+	int i, found_i = -1;
+
+	for (i = ARRAY_SIZE(FT_POOLS) - 1; i >= 0; i--) {
+		if (ft_pool_left(chains)[i] && FT_POOLS[i] > desired_size) {
+			found_i = i;
+			if (desired_size != POOL_NEXT_SIZE)
+				break;
+		}
+	}
+
+	if (found_i != -1) {
+		--ft_pool_left(chains)[found_i];
+		return FT_POOLS[found_i];
+	}
+
+	return 0;
+}
+
+static void
+mlx5_chains_put_sz_to_pool(struct mlx5_fs_chains *chains, int sz)
+{
+	int i;
+
+	for (i = ARRAY_SIZE(FT_POOLS) - 1; i >= 0; i--) {
+		if (sz == FT_POOLS[i]) {
+			++ft_pool_left(chains)[i];
+			return;
+		}
+	}
+
+	WARN_ONCE(1, "Couldn't find size %d in flow table size pool", sz);
+}
+
+static void
+mlx5_chains_init_sz_pool(struct mlx5_fs_chains *chains, u32 ft_max)
+{
+	int i;
+
+	for (i = ARRAY_SIZE(FT_POOLS) - 1; i >= 0; i--)
+		ft_pool_left(chains)[i] =
+			FT_POOLS[i] <= ft_max ? FT_SIZE / FT_POOLS[i] : 0;
+}
+
+static struct mlx5_flow_table *
+mlx5_chains_create_table(struct mlx5_fs_chains *chains,
+			 u32 chain, u32 prio, u32 level)
+{
+	struct mlx5_flow_table_attr ft_attr = {};
+	struct mlx5_flow_namespace *ns;
+	struct mlx5_flow_table *ft;
+	int sz;
+
+	if (chains->flags & MLX5_CHAINS_FT_TUNNEL_SUPPORTED)
+		ft_attr.flags |= (MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT |
+				  MLX5_FLOW_TABLE_TUNNEL_EN_DECAP);
+
+	sz = (chain == mlx5_chains_get_nf_ft_chain(chains)) ?
+	     mlx5_chains_get_avail_sz_from_pool(chains, FT_TBL_SZ) :
+	     mlx5_chains_get_avail_sz_from_pool(chains, POOL_NEXT_SIZE);
+	if (!sz)
+		return ERR_PTR(-ENOSPC);
+	ft_attr.max_fte = sz;
+
+	/* We use tc_default_ft(chains) as the table's next_ft till
+	 * ignore_flow_level is allowed on FT creation and not just for FTEs.
+	 * Instead caller should add an explicit miss rule if needed.
+	 */
+	ft_attr.next_ft = tc_default_ft(chains);
+
+	/* The root table(chain 0, prio 1, level 0) is required to be
+	 * connected to the previous fs_core managed prio.
+	 * We always create it, as a managed table, in order to align with
+	 * fs_core logic.
+	 */
+	if (!mlx5_chains_ignore_flow_level_supported(chains) ||
+	    (chain == 0 && prio == 1 && level == 0)) {
+		ft_attr.level = level;
+		ft_attr.prio = prio - 1;
+		ns = (chains->ns == MLX5_FLOW_NAMESPACE_FDB) ?
+			mlx5_get_fdb_sub_ns(chains->dev, chain) :
+			mlx5_get_flow_namespace(chains->dev, chains->ns);
+	} else {
+		ft_attr.flags |= MLX5_FLOW_TABLE_UNMANAGED;
+		ft_attr.prio = ns_to_chains_fs_prio(chains->ns);
+		/* Firmware doesn't allow us to create another level 0 table,
+		 * so we create all unmanaged tables as level 1.
+		 *
+		 * To connect them, we use explicit miss rules with
+		 * ignore_flow_level. Caller is responsible to create
+		 * these rules (if needed).
+		 */
+		ft_attr.level = 1;
+		ns = mlx5_get_flow_namespace(chains->dev, chains->ns);
+	}
+
+	ft_attr.autogroup.num_reserved_entries = 2;
+	ft_attr.autogroup.max_num_groups = chains->group_num;
+	ft = mlx5_create_auto_grouped_flow_table(ns, &ft_attr);
+	if (IS_ERR(ft)) {
+		mlx5_core_warn(chains->dev, "Failed to create chains table err %d (chain: %d, prio: %d, level: %d, size: %d)\n",
+			       (int)PTR_ERR(ft), chain, prio, level, sz);
+		mlx5_chains_put_sz_to_pool(chains, sz);
+		return ft;
+	}
+
+	return ft;
+}
+
+static void
+mlx5_chains_destroy_table(struct mlx5_fs_chains *chains,
+			  struct mlx5_flow_table *ft)
+{
+	mlx5_chains_put_sz_to_pool(chains, ft->max_fte);
+	mlx5_destroy_flow_table(ft);
+}
+
+static int
+create_chain_restore(struct fs_chain *chain)
+{
+	struct mlx5_eswitch *esw = chain->chains->dev->priv.eswitch;
+	char modact[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)];
+	struct mlx5_fs_chains *chains = chain->chains;
+	enum mlx5e_tc_attr_to_reg chain_to_reg;
+	struct mlx5_modify_hdr *mod_hdr;
+	u32 index;
+	int err;
+
+	if (chain->chain == mlx5_chains_get_nf_ft_chain(chains) ||
+	    !mlx5_chains_prios_supported(chains))
+		return 0;
+
+	err = mapping_add(chains_mapping(chains), &chain->chain, &index);
+	if (err)
+		return err;
+	if (index == MLX5_FS_DEFAULT_FLOW_TAG) {
+		/* we got the special default flow tag id, so we won't know
+		 * if we actually marked the packet with the restore rule
+		 * we create.
+		 *
+		 * This case isn't possible with MLX5_FS_DEFAULT_FLOW_TAG = 0.
+		 */
+		err = mapping_add(chains_mapping(chains),
+				  &chain->chain, &index);
+		mapping_remove(chains_mapping(chains),
+			       MLX5_FS_DEFAULT_FLOW_TAG);
+		if (err)
+			return err;
+	}
+
+	chain->id = index;
+
+	if (chains->ns == MLX5_FLOW_NAMESPACE_FDB) {
+		chain_to_reg = CHAIN_TO_REG;
+		chain->restore_rule = esw_add_restore_rule(esw, chain->id);
+		if (IS_ERR(chain->restore_rule)) {
+			err = PTR_ERR(chain->restore_rule);
+			goto err_rule;
+		}
+	} else if (chains->ns == MLX5_FLOW_NAMESPACE_KERNEL) {
+		/* For NIC RX we don't need a restore rule
+		 * since we write the metadata to reg_b
+		 * that is passed to SW directly.
+		 */
+		chain_to_reg = NIC_CHAIN_TO_REG;
+	} else {
+		err = -EINVAL;
+		goto err_rule;
+	}
+
+	MLX5_SET(set_action_in, modact, action_type, MLX5_ACTION_TYPE_SET);
+	MLX5_SET(set_action_in, modact, field,
+		 mlx5e_tc_attr_to_reg_mappings[chain_to_reg].mfield);
+	MLX5_SET(set_action_in, modact, offset,
+		 mlx5e_tc_attr_to_reg_mappings[chain_to_reg].moffset * 8);
+	MLX5_SET(set_action_in, modact, length,
+		 mlx5e_tc_attr_to_reg_mappings[chain_to_reg].mlen * 8);
+	MLX5_SET(set_action_in, modact, data, chain->id);
+	mod_hdr = mlx5_modify_header_alloc(chains->dev, chains->ns,
+					   1, modact);
+	if (IS_ERR(mod_hdr)) {
+		err = PTR_ERR(mod_hdr);
+		goto err_mod_hdr;
+	}
+	chain->miss_modify_hdr = mod_hdr;
+
+	return 0;
+
+err_mod_hdr:
+	if (!IS_ERR_OR_NULL(chain->restore_rule))
+		mlx5_del_flow_rules(chain->restore_rule);
+err_rule:
+	/* Datapath can't find this mapping, so we can safely remove it */
+	mapping_remove(chains_mapping(chains), chain->id);
+	return err;
+}
+
+static void destroy_chain_restore(struct fs_chain *chain)
+{
+	struct mlx5_fs_chains *chains = chain->chains;
+
+	if (!chain->miss_modify_hdr)
+		return;
+
+	if (chain->restore_rule)
+		mlx5_del_flow_rules(chain->restore_rule);
+
+	mlx5_modify_header_dealloc(chains->dev, chain->miss_modify_hdr);
+	mapping_remove(chains_mapping(chains), chain->id);
+}
+
+static struct fs_chain *
+mlx5_chains_create_chain(struct mlx5_fs_chains *chains, u32 chain)
+{
+	struct fs_chain *chain_s = NULL;
+	int err;
+
+	chain_s = kvzalloc(sizeof(*chain_s), GFP_KERNEL);
+	if (!chain_s)
+		return ERR_PTR(-ENOMEM);
+
+	chain_s->chains = chains;
+	chain_s->chain = chain;
+	INIT_LIST_HEAD(&chain_s->prios_list);
+
+	err = create_chain_restore(chain_s);
+	if (err)
+		goto err_restore;
+
+	err = rhashtable_insert_fast(&chains_ht(chains), &chain_s->node,
+				     chain_params);
+	if (err)
+		goto err_insert;
+
+	return chain_s;
+
+err_insert:
+	destroy_chain_restore(chain_s);
+err_restore:
+	kvfree(chain_s);
+	return ERR_PTR(err);
+}
+
+static void
+mlx5_chains_destroy_chain(struct fs_chain *chain)
+{
+	struct mlx5_fs_chains *chains = chain->chains;
+
+	rhashtable_remove_fast(&chains_ht(chains), &chain->node,
+			       chain_params);
+
+	destroy_chain_restore(chain);
+	kvfree(chain);
+}
+
+static struct fs_chain *
+mlx5_chains_get_chain(struct mlx5_fs_chains *chains, u32 chain)
+{
+	struct fs_chain *chain_s;
+
+	chain_s = rhashtable_lookup_fast(&chains_ht(chains), &chain,
+					 chain_params);
+	if (!chain_s) {
+		chain_s = mlx5_chains_create_chain(chains, chain);
+		if (IS_ERR(chain_s))
+			return chain_s;
+	}
+
+	chain_s->ref++;
+
+	return chain_s;
+}
+
+static struct mlx5_flow_handle *
+mlx5_chains_add_miss_rule(struct fs_chain *chain,
+			  struct mlx5_flow_table *ft,
+			  struct mlx5_flow_table *next_ft)
+{
+	struct mlx5_fs_chains *chains = chain->chains;
+	struct mlx5_flow_destination dest = {};
+	struct mlx5_flow_act act = {};
+
+	act.flags  = FLOW_ACT_NO_APPEND;
+	if (mlx5_chains_ignore_flow_level_supported(chain->chains))
+		act.flags |= FLOW_ACT_IGNORE_FLOW_LEVEL;
+
+	act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+	dest.type  = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
+	dest.ft = next_ft;
+
+	if (next_ft == tc_end_ft(chains) &&
+	    chain->chain != mlx5_chains_get_nf_ft_chain(chains) &&
+	    mlx5_chains_prios_supported(chains)) {
+		act.modify_hdr = chain->miss_modify_hdr;
+		act.action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
+	}
+
+	return mlx5_add_flow_rules(ft, NULL, &act, &dest, 1);
+}
+
+static int
+mlx5_chains_update_prio_prevs(struct prio *prio,
+			      struct mlx5_flow_table *next_ft)
+{
+	struct mlx5_flow_handle *miss_rules[FDB_TC_LEVELS_PER_PRIO + 1] = {};
+	struct fs_chain *chain = prio->chain;
+	struct prio *pos;
+	int n = 0, err;
+
+	if (prio->key.level)
+		return 0;
+
+	/* Iterate in reverse order until reaching the level 0 rule of
+	 * the previous priority, adding all the miss rules first, so we can
+	 * revert them if any of them fails.
+	 */
+	pos = prio;
+	list_for_each_entry_continue_reverse(pos,
+					     &chain->prios_list,
+					     list) {
+		miss_rules[n] = mlx5_chains_add_miss_rule(chain,
+							  pos->ft,
+							  next_ft);
+		if (IS_ERR(miss_rules[n])) {
+			err = PTR_ERR(miss_rules[n]);
+			goto err_prev_rule;
+		}
+
+		n++;
+		if (!pos->key.level)
+			break;
+	}
+
+	/* Success, delete old miss rules, and update the pointers. */
+	n = 0;
+	pos = prio;
+	list_for_each_entry_continue_reverse(pos,
+					     &chain->prios_list,
+					     list) {
+		mlx5_del_flow_rules(pos->miss_rule);
+
+		pos->miss_rule = miss_rules[n];
+		pos->next_ft = next_ft;
+
+		n++;
+		if (!pos->key.level)
+			break;
+	}
+
+	return 0;
+
+err_prev_rule:
+	while (--n >= 0)
+		mlx5_del_flow_rules(miss_rules[n]);
+
+	return err;
+}
+
+static void
+mlx5_chains_put_chain(struct fs_chain *chain)
+{
+	if (--chain->ref == 0)
+		mlx5_chains_destroy_chain(chain);
+}
+
+static struct prio *
+mlx5_chains_create_prio(struct mlx5_fs_chains *chains,
+			u32 chain, u32 prio, u32 level)
+{
+	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
+	struct mlx5_flow_handle *miss_rule = NULL;
+	struct mlx5_flow_group *miss_group;
+	struct mlx5_flow_table *next_ft;
+	struct mlx5_flow_table *ft;
+	struct prio *prio_s = NULL;
+	struct fs_chain *chain_s;
+	struct list_head *pos;
+	u32 *flow_group_in;
+	int err;
+
+	chain_s = mlx5_chains_get_chain(chains, chain);
+	if (IS_ERR(chain_s))
+		return ERR_CAST(chain_s);
+
+	prio_s = kvzalloc(sizeof(*prio_s), GFP_KERNEL);
+	flow_group_in = kvzalloc(inlen, GFP_KERNEL);
+	if (!prio_s || !flow_group_in) {
+		err = -ENOMEM;
+		goto err_alloc;
+	}
+
+	/* Chain's prio list is sorted by prio and level.
+	 * And all levels of some prio point to the next prio's level 0.
+	 * Example list (prio, level):
+	 * (3,0)->(3,1)->(5,0)->(5,1)->(6,1)->(7,0)
+	 * In hardware, we will we have the following pointers:
+	 * (3,0) -> (5,0) -> (7,0) -> Slow path
+	 * (3,1) -> (5,0)
+	 * (5,1) -> (7,0)
+	 * (6,1) -> (7,0)
+	 */
+
+	/* Default miss for each chain: */
+	next_ft = (chain == mlx5_chains_get_nf_ft_chain(chains)) ?
+		  tc_default_ft(chains) :
+		  tc_end_ft(chains);
+	list_for_each(pos, &chain_s->prios_list) {
+		struct prio *p = list_entry(pos, struct prio, list);
+
+		/* exit on first pos that is larger */
+		if (prio < p->key.prio || (prio == p->key.prio &&
+					   level < p->key.level)) {
+			/* Get next level 0 table */
+			next_ft = p->key.level == 0 ? p->ft : p->next_ft;
+			break;
+		}
+	}
+
+	ft = mlx5_chains_create_table(chains, chain, prio, level);
+	if (IS_ERR(ft)) {
+		err = PTR_ERR(ft);
+		goto err_create;
+	}
+
+	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index,
+		 ft->max_fte - 2);
+	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index,
+		 ft->max_fte - 1);
+	miss_group = mlx5_create_flow_group(ft, flow_group_in);
+	if (IS_ERR(miss_group)) {
+		err = PTR_ERR(miss_group);
+		goto err_group;
+	}
+
+	/* Add miss rule to next_ft */
+	miss_rule = mlx5_chains_add_miss_rule(chain_s, ft, next_ft);
+	if (IS_ERR(miss_rule)) {
+		err = PTR_ERR(miss_rule);
+		goto err_miss_rule;
+	}
+
+	prio_s->miss_group = miss_group;
+	prio_s->miss_rule = miss_rule;
+	prio_s->next_ft = next_ft;
+	prio_s->chain = chain_s;
+	prio_s->key.chain = chain;
+	prio_s->key.prio = prio;
+	prio_s->key.level = level;
+	prio_s->ft = ft;
+
+	err = rhashtable_insert_fast(&prios_ht(chains), &prio_s->node,
+				     prio_params);
+	if (err)
+		goto err_insert;
+
+	list_add(&prio_s->list, pos->prev);
+
+	/* Table is ready, connect it */
+	err = mlx5_chains_update_prio_prevs(prio_s, ft);
+	if (err)
+		goto err_update;
+
+	kvfree(flow_group_in);
+	return prio_s;
+
+err_update:
+	list_del(&prio_s->list);
+	rhashtable_remove_fast(&prios_ht(chains), &prio_s->node,
+			       prio_params);
+err_insert:
+	mlx5_del_flow_rules(miss_rule);
+err_miss_rule:
+	mlx5_destroy_flow_group(miss_group);
+err_group:
+	mlx5_chains_destroy_table(chains, ft);
+err_create:
+err_alloc:
+	kvfree(prio_s);
+	kvfree(flow_group_in);
+	mlx5_chains_put_chain(chain_s);
+	return ERR_PTR(err);
+}
+
+static void
+mlx5_chains_destroy_prio(struct mlx5_fs_chains *chains,
+			 struct prio *prio)
+{
+	struct fs_chain *chain = prio->chain;
+
+	WARN_ON(mlx5_chains_update_prio_prevs(prio,
+					      prio->next_ft));
+
+	list_del(&prio->list);
+	rhashtable_remove_fast(&prios_ht(chains), &prio->node,
+			       prio_params);
+	mlx5_del_flow_rules(prio->miss_rule);
+	mlx5_destroy_flow_group(prio->miss_group);
+	mlx5_chains_destroy_table(chains, prio->ft);
+	mlx5_chains_put_chain(chain);
+	kvfree(prio);
+}
+
+struct mlx5_flow_table *
+mlx5_chains_get_table(struct mlx5_fs_chains *chains, u32 chain, u32 prio,
+		      u32 level)
+{
+	struct mlx5_flow_table *prev_fts;
+	struct prio *prio_s;
+	struct prio_key key;
+	int l = 0;
+
+	if ((chain > mlx5_chains_get_chain_range(chains) &&
+	     chain != mlx5_chains_get_nf_ft_chain(chains)) ||
+	    prio > mlx5_chains_get_prio_range(chains) ||
+	    level > mlx5_chains_get_level_range(chains))
+		return ERR_PTR(-EOPNOTSUPP);
+
+	/* create earlier levels for correct fs_core lookup when
+	 * connecting tables.
+	 */
+	for (l = 0; l < level; l++) {
+		prev_fts = mlx5_chains_get_table(chains, chain, prio, l);
+		if (IS_ERR(prev_fts)) {
+			prio_s = ERR_CAST(prev_fts);
+			goto err_get_prevs;
+		}
+	}
+
+	key.chain = chain;
+	key.prio = prio;
+	key.level = level;
+
+	mutex_lock(&chains_lock(chains));
+	prio_s = rhashtable_lookup_fast(&prios_ht(chains), &key,
+					prio_params);
+	if (!prio_s) {
+		prio_s = mlx5_chains_create_prio(chains, chain,
+						 prio, level);
+		if (IS_ERR(prio_s))
+			goto err_create_prio;
+	}
+
+	++prio_s->ref;
+	mutex_unlock(&chains_lock(chains));
+
+	return prio_s->ft;
+
+err_create_prio:
+	mutex_unlock(&chains_lock(chains));
+err_get_prevs:
+	while (--l >= 0)
+		mlx5_chains_put_table(chains, chain, prio, l);
+	return ERR_CAST(prio_s);
+}
+
+void
+mlx5_chains_put_table(struct mlx5_fs_chains *chains, u32 chain, u32 prio,
+		      u32 level)
+{
+	struct prio *prio_s;
+	struct prio_key key;
+
+	key.chain = chain;
+	key.prio = prio;
+	key.level = level;
+
+	mutex_lock(&chains_lock(chains));
+	prio_s = rhashtable_lookup_fast(&prios_ht(chains), &key,
+					prio_params);
+	if (!prio_s)
+		goto err_get_prio;
+
+	if (--prio_s->ref == 0)
+		mlx5_chains_destroy_prio(chains, prio_s);
+	mutex_unlock(&chains_lock(chains));
+
+	while (level-- > 0)
+		mlx5_chains_put_table(chains, chain, prio, level);
+
+	return;
+
+err_get_prio:
+	mutex_unlock(&chains_lock(chains));
+	WARN_ONCE(1,
+		  "Couldn't find table: (chain: %d prio: %d level: %d)",
+		  chain, prio, level);
+}
+
+struct mlx5_flow_table *
+mlx5_chains_get_tc_end_ft(struct mlx5_fs_chains *chains)
+{
+	return tc_end_ft(chains);
+}
+
+struct mlx5_flow_table *
+mlx5_chains_create_global_table(struct mlx5_fs_chains *chains)
+{
+	u32 chain, prio, level;
+	int err;
+
+	if (!mlx5_chains_ignore_flow_level_supported(chains)) {
+		err = -EOPNOTSUPP;
+
+		mlx5_core_warn(chains->dev,
+			       "Couldn't create global flow table, ignore_flow_level not supported.");
+		goto err_ignore;
+	}
+
+	chain = mlx5_chains_get_chain_range(chains),
+	prio = mlx5_chains_get_prio_range(chains);
+	level = mlx5_chains_get_level_range(chains);
+
+	return mlx5_chains_create_table(chains, chain, prio, level);
+
+err_ignore:
+	return ERR_PTR(err);
+}
+
+void
+mlx5_chains_destroy_global_table(struct mlx5_fs_chains *chains,
+				 struct mlx5_flow_table *ft)
+{
+	mlx5_chains_destroy_table(chains, ft);
+}
+
+static struct mlx5_fs_chains *
+mlx5_chains_init(struct mlx5_core_dev *dev, struct mlx5_chains_attr *attr)
+{
+	struct mlx5_fs_chains *chains_priv;
+	struct mapping_ctx *mapping;
+	u32 max_flow_counter;
+	int err;
+
+	chains_priv = kzalloc(sizeof(*chains_priv), GFP_KERNEL);
+	if (!chains_priv)
+		return ERR_PTR(-ENOMEM);
+
+	max_flow_counter = (MLX5_CAP_GEN(dev, max_flow_counter_31_16) << 16) |
+			    MLX5_CAP_GEN(dev, max_flow_counter_15_0);
+
+	mlx5_core_dbg(dev,
+		      "Init flow table chains, max counters(%d), groups(%d), max flow table size(%d)\n",
+		      max_flow_counter, attr->max_grp_num, attr->max_ft_sz);
+
+	chains_priv->dev = dev;
+	chains_priv->flags = attr->flags;
+	chains_priv->ns = attr->ns;
+	chains_priv->group_num = attr->max_grp_num;
+	tc_default_ft(chains_priv) = tc_end_ft(chains_priv) = attr->default_ft;
+
+	mlx5_core_info(dev, "Supported tc offload range - chains: %u, prios: %u\n",
+		       mlx5_chains_get_chain_range(chains_priv),
+		       mlx5_chains_get_prio_range(chains_priv));
+
+	mlx5_chains_init_sz_pool(chains_priv, attr->max_ft_sz);
+
+	err = rhashtable_init(&chains_ht(chains_priv), &chain_params);
+	if (err)
+		goto init_chains_ht_err;
+
+	err = rhashtable_init(&prios_ht(chains_priv), &prio_params);
+	if (err)
+		goto init_prios_ht_err;
+
+	mapping = mapping_create(sizeof(u32), attr->max_restore_tag,
+				 true);
+	if (IS_ERR(mapping)) {
+		err = PTR_ERR(mapping);
+		goto mapping_err;
+	}
+	chains_mapping(chains_priv) = mapping;
+
+	mutex_init(&chains_lock(chains_priv));
+
+	return chains_priv;
+
+mapping_err:
+	rhashtable_destroy(&prios_ht(chains_priv));
+init_prios_ht_err:
+	rhashtable_destroy(&chains_ht(chains_priv));
+init_chains_ht_err:
+	kfree(chains_priv);
+	return ERR_PTR(err);
+}
+
+static void
+mlx5_chains_cleanup(struct mlx5_fs_chains *chains)
+{
+	mutex_destroy(&chains_lock(chains));
+	mapping_destroy(chains_mapping(chains));
+	rhashtable_destroy(&prios_ht(chains));
+	rhashtable_destroy(&chains_ht(chains));
+
+	kfree(chains);
+}
+
+struct mlx5_fs_chains *
+mlx5_chains_create(struct mlx5_core_dev *dev, struct mlx5_chains_attr *attr)
+{
+	struct mlx5_fs_chains *chains;
+
+	chains = mlx5_chains_init(dev, attr);
+
+	return chains;
+}
+
+void
+mlx5_chains_destroy(struct mlx5_fs_chains *chains)
+{
+	mlx5_chains_cleanup(chains);
+}
+
+int
+mlx5_chains_get_chain_mapping(struct mlx5_fs_chains *chains, u32 chain,
+			      u32 *chain_mapping)
+{
+	return mapping_add(chains_mapping(chains), &chain, chain_mapping);
+}
+
+int
+mlx5_chains_put_chain_mapping(struct mlx5_fs_chains *chains, u32 chain_mapping)
+{
+	return mapping_remove(chains_mapping(chains), chain_mapping);
+}
+
+int mlx5_get_chain_for_tag(struct mlx5_fs_chains *chains, u32 tag,
+			   u32 *chain)
+{
+	int err;
+
+	err = mapping_find(chains_mapping(chains), tag, chain);
+	if (err) {
+		mlx5_core_warn(chains->dev, "Can't find chain for tag: %d\n", tag);
+		return -ENOENT;
+	}
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.h
new file mode 100644
index 000000000000..6d5be31b05dd
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.h
@@ -0,0 +1,93 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2020 Mellanox Technologies. */
+
+#ifndef __ML5_ESW_CHAINS_H__
+#define __ML5_ESW_CHAINS_H__
+
+#include <linux/mlx5/fs.h>
+
+struct mlx5_fs_chains;
+
+enum mlx5_chains_flags {
+	MLX5_CHAINS_AND_PRIOS_SUPPORTED = BIT(0),
+	MLX5_CHAINS_IGNORE_FLOW_LEVEL_SUPPORTED = BIT(1),
+	MLX5_CHAINS_FT_TUNNEL_SUPPORTED = BIT(2),
+};
+
+struct mlx5_chains_attr {
+	enum mlx5_flow_namespace_type ns;
+	u32 flags;
+	u32 max_ft_sz;
+	u32 max_grp_num;
+	struct mlx5_flow_table *default_ft;
+	u32 max_restore_tag;
+};
+
+#if IS_ENABLED(CONFIG_MLX5_CLS_ACT)
+
+bool
+mlx5_chains_prios_supported(struct mlx5_fs_chains *chains);
+bool
+mlx5_chains_backwards_supported(struct mlx5_fs_chains *chains);
+u32
+mlx5_chains_get_prio_range(struct mlx5_fs_chains *chains);
+u32
+mlx5_chains_get_chain_range(struct mlx5_fs_chains *chains);
+u32
+mlx5_chains_get_nf_ft_chain(struct mlx5_fs_chains *chains);
+
+struct mlx5_flow_table *
+mlx5_chains_get_table(struct mlx5_fs_chains *chains, u32 chain, u32 prio,
+		      u32 level);
+void
+mlx5_chains_put_table(struct mlx5_fs_chains *chains, u32 chain, u32 prio,
+		      u32 level);
+
+struct mlx5_flow_table *
+mlx5_chains_get_tc_end_ft(struct mlx5_fs_chains *chains);
+
+struct mlx5_flow_table *
+mlx5_chains_create_global_table(struct mlx5_fs_chains *chains);
+void
+mlx5_chains_destroy_global_table(struct mlx5_fs_chains *chains,
+				 struct mlx5_flow_table *ft);
+
+int
+mlx5_chains_get_chain_mapping(struct mlx5_fs_chains *chains, u32 chain,
+			      u32 *chain_mapping);
+int
+mlx5_chains_put_chain_mapping(struct mlx5_fs_chains *chains,
+			      u32 chain_mapping);
+
+struct mlx5_fs_chains *
+mlx5_chains_create(struct mlx5_core_dev *dev, struct mlx5_chains_attr *attr);
+void mlx5_chains_destroy(struct mlx5_fs_chains *chains);
+
+int
+mlx5_get_chain_for_tag(struct mlx5_fs_chains *chains, u32 tag, u32 *chain);
+
+void
+mlx5_chains_set_end_ft(struct mlx5_fs_chains *chains,
+		       struct mlx5_flow_table *ft);
+
+#else /* CONFIG_MLX5_CLS_ACT */
+
+static inline struct mlx5_flow_table *
+mlx5_chains_get_table(struct mlx5_fs_chains *chains, u32 chain, u32 prio,
+		      u32 level) { return ERR_PTR(-EOPNOTSUPP); }
+static inline void
+mlx5_chains_put_table(struct mlx5_fs_chains *chains, u32 chain, u32 prio,
+		      u32 level) {};
+
+static inline struct mlx5_flow_table *
+mlx5_chains_get_tc_end_ft(struct mlx5_fs_chains *chains) { return ERR_PTR(-EOPNOTSUPP); }
+
+static inline struct mlx5_fs_chains *
+mlx5_chains_create(struct mlx5_core_dev *dev, struct mlx5_chains_attr *attr)
+{ return NULL; }
+static inline void
+mlx5_chains_destroy(struct mlx5_fs_chains *chains) {};
+
+#endif /* CONFIG_MLX5_CLS_ACT */
+
+#endif /* __ML5_ESW_CHAINS_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index ce43e3feccd9..3bd32c05ae71 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -739,7 +739,7 @@ static int mlx5_pci_init(struct mlx5_core_dev *dev, struct pci_dev *pdev,
 	pci_set_drvdata(dev->pdev, dev);
 
 	dev->bar_addr = pci_resource_start(pdev, 0);
-	priv->numa_node = dev_to_node(&dev->pdev->dev);
+	priv->numa_node = dev_to_node(mlx5_core_dma_dev(dev));
 
 	err = mlx5_pci_enable_device(dev);
 	if (err) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index fc1649dac11b..e994f84f50b6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -100,6 +100,11 @@ do {								\
 			     __func__, __LINE__, current->pid,	\
 			     ##__VA_ARGS__)
 
+static inline struct device *mlx5_core_dma_dev(struct mlx5_core_dev *dev)
+{
+	return &dev->pdev->dev;
+}
+
 enum {
 	MLX5_CMD_DATA, /* print command payload only */
 	MLX5_CMD_TIME, /* print command execution time */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
index f9b798af6335..0809b2a14319 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
@@ -238,7 +238,7 @@ static void free_fwp(struct mlx5_core_dev *dev, struct fw_page *fwp,
 	rb_erase(&fwp->rb_node, root);
 	if (in_free_list)
 		list_del(&fwp->list);
-	dma_unmap_page(dev->device, fwp->addr & MLX5_U64_4K_PAGE_MASK,
+	dma_unmap_page(mlx5_core_dma_dev(dev), fwp->addr & MLX5_U64_4K_PAGE_MASK,
 		       PAGE_SIZE, DMA_BIDIRECTIONAL);
 	__free_page(fwp->page);
 	kfree(fwp);
@@ -265,7 +265,7 @@ static void free_4k(struct mlx5_core_dev *dev, u64 addr, u32 func_id)
 
 static int alloc_system_page(struct mlx5_core_dev *dev, u16 func_id)
 {
-	struct device *device = dev->device;
+	struct device *device = mlx5_core_dma_dev(dev);
 	int nid = dev_to_node(device);
 	struct page *page;
 	u64 zero_addr = 1;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c
index c63f727273d8..7df883686d46 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c
@@ -203,7 +203,6 @@ static int dr_matcher_set_ste_builders(struct mlx5dr_matcher *matcher,
 	struct mlx5dr_domain_rx_tx *nic_dmn = nic_matcher->nic_tbl->nic_dmn;
 	struct mlx5dr_domain *dmn = matcher->tbl->dmn;
 	struct mlx5dr_match_param mask = {};
-	struct mlx5dr_match_misc3 *misc3;
 	struct mlx5dr_ste_build *sb;
 	bool inner, rx;
 	int idx = 0;
@@ -252,18 +251,14 @@ static int dr_matcher_set_ste_builders(struct mlx5dr_matcher *matcher,
 		if (dr_mask_is_gvmi_or_qpn_set(&mask.misc) &&
 		    (dmn->type == MLX5DR_DOMAIN_TYPE_FDB ||
 		     dmn->type == MLX5DR_DOMAIN_TYPE_NIC_RX)) {
-			ret = mlx5dr_ste_build_src_gvmi_qpn(&sb[idx++], &mask,
-							    dmn, inner, rx);
-			if (ret)
-				return ret;
+			mlx5dr_ste_build_src_gvmi_qpn(&sb[idx++], &mask,
+						      dmn, inner, rx);
 		}
 
 		if (dr_mask_is_smac_set(&mask.outer) &&
 		    dr_mask_is_dmac_set(&mask.outer)) {
-			ret = mlx5dr_ste_build_eth_l2_src_des(&sb[idx++], &mask,
-							      inner, rx);
-			if (ret)
-				return ret;
+			mlx5dr_ste_build_eth_l2_src_des(&sb[idx++], &mask,
+							inner, rx);
 		}
 
 		if (dr_mask_is_smac_set(&mask.outer))
@@ -313,8 +308,7 @@ static int dr_matcher_set_ste_builders(struct mlx5dr_matcher *matcher,
 			mlx5dr_ste_build_flex_parser_0(&sb[idx++], &mask,
 						       inner, rx);
 
-		misc3 = &mask.misc3;
-		if ((DR_MASK_IS_FLEX_PARSER_ICMPV4_SET(misc3) &&
+		if ((DR_MASK_IS_FLEX_PARSER_ICMPV4_SET(&mask.misc3) &&
 		     mlx5dr_matcher_supp_flex_parser_icmp_v4(&dmn->info.caps)) ||
 		    (dr_mask_is_flex_parser_icmpv6_set(&mask.misc3) &&
 		     mlx5dr_matcher_supp_flex_parser_icmp_v6(&dmn->info.caps))) {
@@ -340,10 +334,8 @@ static int dr_matcher_set_ste_builders(struct mlx5dr_matcher *matcher,
 
 		if (dr_mask_is_smac_set(&mask.inner) &&
 		    dr_mask_is_dmac_set(&mask.inner)) {
-			ret = mlx5dr_ste_build_eth_l2_src_des(&sb[idx++],
-							      &mask, inner, rx);
-			if (ret)
-				return ret;
+			mlx5dr_ste_build_eth_l2_src_des(&sb[idx++],
+							&mask, inner, rx);
 		}
 
 		if (dr_mask_is_smac_set(&mask.inner))
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c
index 6ec5106bc472..b3c9dc032026 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c
@@ -242,7 +242,7 @@ dr_rule_rehash_copy_ste(struct mlx5dr_matcher *matcher,
 	new_idx = mlx5dr_ste_calc_hash_index(hw_ste, new_htbl);
 	new_ste = &new_htbl->ste_arr[new_idx];
 
-	if (mlx5dr_ste_not_used_ste(new_ste)) {
+	if (mlx5dr_ste_is_not_used(new_ste)) {
 		mlx5dr_htbl_get(new_htbl);
 		list_add_tail(&new_ste->miss_list_node,
 			      mlx5dr_ste_get_miss_list(new_ste));
@@ -335,7 +335,7 @@ static int dr_rule_rehash_copy_htbl(struct mlx5dr_matcher *matcher,
 
 	for (i = 0; i < cur_entries; i++) {
 		cur_ste = &cur_htbl->ste_arr[i];
-		if (mlx5dr_ste_not_used_ste(cur_ste)) /* Empty, nothing to copy */
+		if (mlx5dr_ste_is_not_used(cur_ste)) /* Empty, nothing to copy */
 			continue;
 
 		err = dr_rule_rehash_copy_miss_list(matcher,
@@ -791,7 +791,7 @@ again:
 	miss_list = &cur_htbl->chunk->miss_list[index];
 	ste = &cur_htbl->ste_arr[index];
 
-	if (mlx5dr_ste_not_used_ste(ste)) {
+	if (mlx5dr_ste_is_not_used(ste)) {
 		if (dr_rule_handle_empty_entry(matcher, nic_matcher, cur_htbl,
 					       ste, ste_location,
 					       hw_ste, miss_list,
@@ -985,31 +985,28 @@ static enum mlx5dr_ipv dr_rule_get_ipv(struct mlx5dr_match_spec *spec)
 static bool dr_rule_skip(enum mlx5dr_domain_type domain,
 			 enum mlx5dr_ste_entry_type ste_type,
 			 struct mlx5dr_match_param *mask,
-			 struct mlx5dr_match_param *value)
+			 struct mlx5dr_match_param *value,
+			 u32 flow_source)
 {
+	bool rx = ste_type == MLX5DR_STE_TYPE_RX;
+
 	if (domain != MLX5DR_DOMAIN_TYPE_FDB)
 		return false;
 
 	if (mask->misc.source_port) {
-		if (ste_type == MLX5DR_STE_TYPE_RX)
-			if (value->misc.source_port != WIRE_PORT)
-				return true;
+		if (rx && value->misc.source_port != WIRE_PORT)
+			return true;
 
-		if (ste_type == MLX5DR_STE_TYPE_TX)
-			if (value->misc.source_port == WIRE_PORT)
-				return true;
+		if (!rx && value->misc.source_port == WIRE_PORT)
+			return true;
 	}
 
-	/* Metadata C can be used to describe the source vport */
-	if (mask->misc2.metadata_reg_c_0) {
-		if (ste_type == MLX5DR_STE_TYPE_RX)
-			if ((value->misc2.metadata_reg_c_0 & WIRE_PORT) != WIRE_PORT)
-				return true;
+	if (rx && flow_source == MLX5_FLOW_CONTEXT_FLOW_SOURCE_LOCAL_VPORT)
+		return true;
+
+	if (!rx && flow_source == MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK)
+		return true;
 
-		if (ste_type == MLX5DR_STE_TYPE_TX)
-			if ((value->misc2.metadata_reg_c_0 & WIRE_PORT) == WIRE_PORT)
-				return true;
-	}
 	return false;
 }
 
@@ -1038,7 +1035,8 @@ dr_rule_create_rule_nic(struct mlx5dr_rule *rule,
 
 	INIT_LIST_HEAD(&nic_rule->rule_members_list);
 
-	if (dr_rule_skip(dmn->type, nic_dmn->ste_type, &matcher->mask, param))
+	if (dr_rule_skip(dmn->type, nic_dmn->ste_type, &matcher->mask, param,
+			 rule->flow_source))
 		return 0;
 
 	hw_ste_arr = kzalloc(DR_RULE_MAX_STE_CHAIN * DR_STE_SIZE, GFP_KERNEL);
@@ -1173,7 +1171,8 @@ static struct mlx5dr_rule *
 dr_rule_create_rule(struct mlx5dr_matcher *matcher,
 		    struct mlx5dr_match_parameters *value,
 		    size_t num_actions,
-		    struct mlx5dr_action *actions[])
+		    struct mlx5dr_action *actions[],
+		    u32 flow_source)
 {
 	struct mlx5dr_domain *dmn = matcher->tbl->dmn;
 	struct mlx5dr_match_param param = {};
@@ -1188,6 +1187,7 @@ dr_rule_create_rule(struct mlx5dr_matcher *matcher,
 		return NULL;
 
 	rule->matcher = matcher;
+	rule->flow_source = flow_source;
 	INIT_LIST_HEAD(&rule->rule_actions_list);
 
 	ret = dr_rule_add_action_members(rule, num_actions, actions);
@@ -1232,13 +1232,14 @@ free_rule:
 struct mlx5dr_rule *mlx5dr_rule_create(struct mlx5dr_matcher *matcher,
 				       struct mlx5dr_match_parameters *value,
 				       size_t num_actions,
-				       struct mlx5dr_action *actions[])
+				       struct mlx5dr_action *actions[],
+				       u32 flow_source)
 {
 	struct mlx5dr_rule *rule;
 
 	refcount_inc(&matcher->refcount);
 
-	rule = dr_rule_create_rule(matcher, value, num_actions, actions);
+	rule = dr_rule_create_rule(matcher, value, num_actions, actions, flow_source);
 	if (!rule)
 		refcount_dec(&matcher->refcount);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
index 2ca79b9bde1f..24dede1b0a20 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
@@ -466,10 +466,10 @@ int mlx5dr_send_postsend_htbl(struct mlx5dr_domain *dmn,
 		 * need to add the bit_mask
 		 */
 		for (j = 0; j < num_stes_per_iter; j++) {
-			u8 *hw_ste = htbl->ste_arr[ste_index + j].hw_ste;
+			struct mlx5dr_ste *ste = &htbl->ste_arr[ste_index + j];
 			u32 ste_off = j * DR_STE_SIZE;
 
-			if (mlx5dr_ste_is_not_valid_entry(hw_ste)) {
+			if (mlx5dr_ste_is_not_used(ste)) {
 				memcpy(data + ste_off,
 				       formatted_ste, DR_STE_SIZE);
 			} else {
@@ -831,7 +831,7 @@ static struct mlx5dr_mr *dr_reg_mr(struct mlx5_core_dev *mdev,
 	if (!mr)
 		return NULL;
 
-	dma_device = &mdev->pdev->dev;
+	dma_device = mlx5_core_dma_dev(mdev);
 	dma_addr = dma_map_single(dma_device, buf, size,
 				  DMA_BIDIRECTIONAL);
 	err = dma_mapping_error(dma_device, dma_addr);
@@ -860,7 +860,7 @@ static struct mlx5dr_mr *dr_reg_mr(struct mlx5_core_dev *mdev,
 static void dr_dereg_mr(struct mlx5_core_dev *mdev, struct mlx5dr_mr *mr)
 {
 	mlx5_core_destroy_mkey(mdev, &mr->mkey);
-	dma_unmap_single(&mdev->pdev->dev, mr->dma_addr, mr->size,
+	dma_unmap_single(mlx5_core_dma_dev(mdev), mr->dma_addr, mr->size,
 			 DMA_BIDIRECTIONAL);
 	kfree(mr);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c
index 00c2f598f034..b01aaec75622 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c
@@ -155,6 +155,13 @@ static u16 dr_ste_conv_bit_to_byte_mask(u8 *bit_mask)
 	return byte_mask;
 }
 
+static u8 *mlx5dr_ste_get_tag(u8 *hw_ste_p)
+{
+	struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
+
+	return hw_ste->tag;
+}
+
 void mlx5dr_ste_set_bit_mask(u8 *hw_ste_p, u8 *bit_mask)
 {
 	struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
@@ -549,25 +556,6 @@ void mlx5dr_ste_always_miss_addr(struct mlx5dr_ste *ste, u64 miss_addr)
 	dr_ste_set_always_miss((struct dr_hw_ste_format *)ste->hw_ste);
 }
 
-/* The assumption here is that we don't update the ste->hw_ste if it is not
- * used ste, so it will be all zero, checking the next_lu_type.
- */
-bool mlx5dr_ste_is_not_valid_entry(u8 *p_hw_ste)
-{
-	struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)p_hw_ste;
-
-	if (MLX5_GET(ste_general, hw_ste, next_lu_type) ==
-	    MLX5DR_STE_LU_TYPE_NOP)
-		return true;
-
-	return false;
-}
-
-bool mlx5dr_ste_not_used_ste(struct mlx5dr_ste *ste)
-{
-	return !ste->refcount;
-}
-
 /* Init one ste as a pattern for ste data array */
 void mlx5dr_ste_set_formatted_ste(u16 gvmi,
 				  struct mlx5dr_domain_rx_tx *nic_dmn,
@@ -728,7 +716,14 @@ int mlx5dr_ste_build_pre_check(struct mlx5dr_domain *dmn,
 {
 	if (!value && (match_criteria & DR_MATCHER_CRITERIA_MISC)) {
 		if (mask->misc.source_port && mask->misc.source_port != 0xffff) {
-			mlx5dr_err(dmn, "Partial mask source_port is not supported\n");
+			mlx5dr_err(dmn,
+				   "Partial mask source_port is not supported\n");
+			return -EINVAL;
+		}
+		if (mask->misc.source_eswitch_owner_vhca_id &&
+		    mask->misc.source_eswitch_owner_vhca_id != 0xffff) {
+			mlx5dr_err(dmn,
+				   "Partial mask source_eswitch_owner_vhca_id is not supported\n");
 			return -EINVAL;
 		}
 	}
@@ -760,7 +755,7 @@ int mlx5dr_ste_build_ste_arr(struct mlx5dr_matcher *matcher,
 
 		mlx5dr_ste_set_bit_mask(ste_arr, sb->bit_mask);
 
-		ret = sb->ste_build_tag_func(value, sb, ste_arr);
+		ret = sb->ste_build_tag_func(value, sb, mlx5dr_ste_get_tag(ste_arr));
 		if (ret)
 			return ret;
 
@@ -778,8 +773,8 @@ int mlx5dr_ste_build_ste_arr(struct mlx5dr_matcher *matcher,
 	return 0;
 }
 
-static int dr_ste_build_eth_l2_src_des_bit_mask(struct mlx5dr_match_param *value,
-						bool inner, u8 *bit_mask)
+static void dr_ste_build_eth_l2_src_des_bit_mask(struct mlx5dr_match_param *value,
+						 bool inner, u8 *bit_mask)
 {
 	struct mlx5dr_match_spec *mask = inner ? &value->inner : &value->outer;
 
@@ -807,13 +802,6 @@ static int dr_ste_build_eth_l2_src_des_bit_mask(struct mlx5dr_match_param *value
 		MLX5_SET(ste_eth_l2_src_dst, bit_mask, first_vlan_qualifier, -1);
 		mask->svlan_tag = 0;
 	}
-
-	if (mask->cvlan_tag || mask->svlan_tag) {
-		pr_info("Invalid c/svlan mask configuration\n");
-		return -EINVAL;
-	}
-
-	return 0;
 }
 
 static void dr_ste_copy_mask_misc(char *mask, struct mlx5dr_match_misc *spec)
@@ -1059,11 +1047,9 @@ void mlx5dr_ste_copy_param(u8 match_criteria,
 
 static int dr_ste_build_eth_l2_src_des_tag(struct mlx5dr_match_param *value,
 					   struct mlx5dr_ste_build *sb,
-					   u8 *hw_ste_p)
+					   u8 *tag)
 {
 	struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer;
-	struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
-	u8 *tag = hw_ste->tag;
 
 	DR_STE_SET_TAG(eth_l2_src_dst, tag, dmac_47_16, spec, dmac_47_16);
 	DR_STE_SET_TAG(eth_l2_src_dst, tag, dmac_15_0, spec, dmac_15_0);
@@ -1104,23 +1090,17 @@ static int dr_ste_build_eth_l2_src_des_tag(struct mlx5dr_match_param *value,
 	return 0;
 }
 
-int mlx5dr_ste_build_eth_l2_src_des(struct mlx5dr_ste_build *sb,
-				    struct mlx5dr_match_param *mask,
-				    bool inner, bool rx)
+void mlx5dr_ste_build_eth_l2_src_des(struct mlx5dr_ste_build *sb,
+				     struct mlx5dr_match_param *mask,
+				     bool inner, bool rx)
 {
-	int ret;
-
-	ret = dr_ste_build_eth_l2_src_des_bit_mask(mask, inner, sb->bit_mask);
-	if (ret)
-		return ret;
+	dr_ste_build_eth_l2_src_des_bit_mask(mask, inner, sb->bit_mask);
 
 	sb->rx = rx;
 	sb->inner = inner;
 	sb->lu_type = DR_STE_CALC_LU_TYPE(ETHL2_SRC_DST, rx, inner);
 	sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask);
 	sb->ste_build_tag_func = &dr_ste_build_eth_l2_src_des_tag;
-
-	return 0;
 }
 
 static void dr_ste_build_eth_l3_ipv6_dst_bit_mask(struct mlx5dr_match_param *value,
@@ -1136,11 +1116,9 @@ static void dr_ste_build_eth_l3_ipv6_dst_bit_mask(struct mlx5dr_match_param *val
 
 static int dr_ste_build_eth_l3_ipv6_dst_tag(struct mlx5dr_match_param *value,
 					    struct mlx5dr_ste_build *sb,
-					    u8 *hw_ste_p)
+					    u8 *tag)
 {
-	struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
 	struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer;
-	u8 *tag = hw_ste->tag;
 
 	DR_STE_SET_TAG(eth_l3_ipv6_dst, tag, dst_ip_127_96, spec, dst_ip_127_96);
 	DR_STE_SET_TAG(eth_l3_ipv6_dst, tag, dst_ip_95_64, spec, dst_ip_95_64);
@@ -1176,11 +1154,9 @@ static void dr_ste_build_eth_l3_ipv6_src_bit_mask(struct mlx5dr_match_param *val
 
 static int dr_ste_build_eth_l3_ipv6_src_tag(struct mlx5dr_match_param *value,
 					    struct mlx5dr_ste_build *sb,
-					    u8 *hw_ste_p)
+					    u8 *tag)
 {
 	struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer;
-	struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
-	u8 *tag = hw_ste->tag;
 
 	DR_STE_SET_TAG(eth_l3_ipv6_src, tag, src_ip_127_96, spec, src_ip_127_96);
 	DR_STE_SET_TAG(eth_l3_ipv6_src, tag, src_ip_95_64, spec, src_ip_95_64);
@@ -1238,11 +1214,9 @@ static void dr_ste_build_eth_l3_ipv4_5_tuple_bit_mask(struct mlx5dr_match_param
 
 static int dr_ste_build_eth_l3_ipv4_5_tuple_tag(struct mlx5dr_match_param *value,
 						struct mlx5dr_ste_build *sb,
-						u8 *hw_ste_p)
+						u8 *tag)
 {
-	struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
 	struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer;
-	u8 *tag = hw_ste->tag;
 
 	DR_STE_SET_TAG(eth_l3_ipv4_5_tuple, tag, destination_address, spec, dst_ip_31_0);
 	DR_STE_SET_TAG(eth_l3_ipv4_5_tuple, tag, source_address, spec, src_ip_31_0);
@@ -1328,12 +1302,10 @@ dr_ste_build_eth_l2_src_or_dst_bit_mask(struct mlx5dr_match_param *value,
 }
 
 static int dr_ste_build_eth_l2_src_or_dst_tag(struct mlx5dr_match_param *value,
-					      bool inner, u8 *hw_ste_p)
+					      bool inner, u8 *tag)
 {
-	struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
 	struct mlx5dr_match_spec *spec = inner ? &value->inner : &value->outer;
 	struct mlx5dr_match_misc *misc_spec = &value->misc;
-	u8 *tag = hw_ste->tag;
 
 	DR_STE_SET_TAG(eth_l2_src, tag, first_vlan_id, spec, first_vid);
 	DR_STE_SET_TAG(eth_l2_src, tag, first_cfi, spec, first_cfi);
@@ -1403,16 +1375,14 @@ static void dr_ste_build_eth_l2_src_bit_mask(struct mlx5dr_match_param *value,
 
 static int dr_ste_build_eth_l2_src_tag(struct mlx5dr_match_param *value,
 				       struct mlx5dr_ste_build *sb,
-				       u8 *hw_ste_p)
+				       u8 *tag)
 {
-	struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
 	struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer;
-	u8 *tag = hw_ste->tag;
 
 	DR_STE_SET_TAG(eth_l2_src, tag, smac_47_16, spec, smac_47_16);
 	DR_STE_SET_TAG(eth_l2_src, tag, smac_15_0, spec, smac_15_0);
 
-	return dr_ste_build_eth_l2_src_or_dst_tag(value, sb->inner, hw_ste_p);
+	return dr_ste_build_eth_l2_src_or_dst_tag(value, sb->inner, tag);
 }
 
 void mlx5dr_ste_build_eth_l2_src(struct mlx5dr_ste_build *sb,
@@ -1440,16 +1410,14 @@ static void dr_ste_build_eth_l2_dst_bit_mask(struct mlx5dr_match_param *value,
 
 static int dr_ste_build_eth_l2_dst_tag(struct mlx5dr_match_param *value,
 				       struct mlx5dr_ste_build *sb,
-				       u8 *hw_ste_p)
+				       u8 *tag)
 {
-	struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
 	struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer;
-	u8 *tag = hw_ste->tag;
 
 	DR_STE_SET_TAG(eth_l2_dst, tag, dmac_47_16, spec, dmac_47_16);
 	DR_STE_SET_TAG(eth_l2_dst, tag, dmac_15_0, spec, dmac_15_0);
 
-	return dr_ste_build_eth_l2_src_or_dst_tag(value, sb->inner, hw_ste_p);
+	return dr_ste_build_eth_l2_src_or_dst_tag(value, sb->inner, tag);
 }
 
 void mlx5dr_ste_build_eth_l2_dst(struct mlx5dr_ste_build *sb,
@@ -1495,12 +1463,10 @@ static void dr_ste_build_eth_l2_tnl_bit_mask(struct mlx5dr_match_param *value,
 
 static int dr_ste_build_eth_l2_tnl_tag(struct mlx5dr_match_param *value,
 				       struct mlx5dr_ste_build *sb,
-				       u8 *hw_ste_p)
+				       u8 *tag)
 {
 	struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer;
-	struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
 	struct mlx5dr_match_misc *misc = &value->misc;
-	u8 *tag = hw_ste->tag;
 
 	DR_STE_SET_TAG(eth_l2_tnl, tag, dmac_47_16, spec, dmac_47_16);
 	DR_STE_SET_TAG(eth_l2_tnl, tag, dmac_15_0, spec, dmac_15_0);
@@ -1561,11 +1527,9 @@ static void dr_ste_build_eth_l3_ipv4_misc_bit_mask(struct mlx5dr_match_param *va
 
 static int dr_ste_build_eth_l3_ipv4_misc_tag(struct mlx5dr_match_param *value,
 					     struct mlx5dr_ste_build *sb,
-					     u8 *hw_ste_p)
+					     u8 *tag)
 {
-	struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
 	struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer;
-	u8 *tag = hw_ste->tag;
 
 	DR_STE_SET_TAG(eth_l3_ipv4_misc, tag, time_to_live, spec, ttl_hoplimit);
 
@@ -1608,11 +1572,9 @@ static void dr_ste_build_ipv6_l3_l4_bit_mask(struct mlx5dr_match_param *value,
 
 static int dr_ste_build_ipv6_l3_l4_tag(struct mlx5dr_match_param *value,
 				       struct mlx5dr_ste_build *sb,
-				       u8 *hw_ste_p)
+				       u8 *tag)
 {
 	struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer;
-	struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
-	u8 *tag = hw_ste->tag;
 
 	DR_STE_SET_TAG(eth_l4, tag, dst_port, spec, tcp_dport);
 	DR_STE_SET_TAG(eth_l4, tag, src_port, spec, tcp_sport);
@@ -1647,7 +1609,7 @@ void mlx5dr_ste_build_ipv6_l3_l4(struct mlx5dr_ste_build *sb,
 
 static int dr_ste_build_empty_always_hit_tag(struct mlx5dr_match_param *value,
 					     struct mlx5dr_ste_build *sb,
-					     u8 *hw_ste_p)
+					     u8 *tag)
 {
 	return 0;
 }
@@ -1673,11 +1635,9 @@ static void dr_ste_build_mpls_bit_mask(struct mlx5dr_match_param *value,
 
 static int dr_ste_build_mpls_tag(struct mlx5dr_match_param *value,
 				 struct mlx5dr_ste_build *sb,
-				 u8 *hw_ste_p)
+				 u8 *tag)
 {
-	struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
 	struct mlx5dr_match_misc2 *misc2_mask = &value->misc2;
-	u8 *tag = hw_ste->tag;
 
 	if (sb->inner)
 		DR_STE_SET_MPLS_TAG(mpls, misc2_mask, inner, tag);
@@ -1716,11 +1676,9 @@ static void dr_ste_build_gre_bit_mask(struct mlx5dr_match_param *value,
 
 static int dr_ste_build_gre_tag(struct mlx5dr_match_param *value,
 				struct mlx5dr_ste_build *sb,
-				u8 *hw_ste_p)
+				u8 *tag)
 {
-	struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
 	struct  mlx5dr_match_misc *misc = &value->misc;
-	u8 *tag = hw_ste->tag;
 
 	DR_STE_SET_TAG(gre, tag, gre_protocol, misc, gre_protocol);
 
@@ -1781,11 +1739,9 @@ static void dr_ste_build_flex_parser_0_bit_mask(struct mlx5dr_match_param *value
 
 static int dr_ste_build_flex_parser_0_tag(struct mlx5dr_match_param *value,
 					  struct mlx5dr_ste_build *sb,
-					  u8 *hw_ste_p)
+					  u8 *tag)
 {
-	struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
 	struct mlx5dr_match_misc2 *misc_2_mask = &value->misc2;
-	u8 *tag = hw_ste->tag;
 
 	if (DR_STE_IS_OUTER_MPLS_OVER_GRE_SET(misc_2_mask)) {
 		DR_STE_SET_TAG(flex_parser_0, tag, parser_3_label,
@@ -1903,11 +1859,9 @@ static int dr_ste_build_flex_parser_1_bit_mask(struct mlx5dr_match_param *mask,
 
 static int dr_ste_build_flex_parser_1_tag(struct mlx5dr_match_param *value,
 					  struct mlx5dr_ste_build *sb,
-					  u8 *hw_ste_p)
+					  u8 *tag)
 {
-	struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
 	struct mlx5dr_match_misc3 *misc_3 = &value->misc3;
-	u8 *tag = hw_ste->tag;
 	u32 icmp_header_data;
 	int dw0_location;
 	int dw1_location;
@@ -2007,11 +1961,9 @@ static void dr_ste_build_general_purpose_bit_mask(struct mlx5dr_match_param *val
 
 static int dr_ste_build_general_purpose_tag(struct mlx5dr_match_param *value,
 					    struct mlx5dr_ste_build *sb,
-					    u8 *hw_ste_p)
+					    u8 *tag)
 {
-	struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
 	struct mlx5dr_match_misc2 *misc_2_mask = &value->misc2;
-	u8 *tag = hw_ste->tag;
 
 	DR_STE_SET_TAG(general_purpose, tag, general_purpose_lookup_field,
 		       misc_2_mask, metadata_reg_a);
@@ -2052,11 +2004,9 @@ static void dr_ste_build_eth_l4_misc_bit_mask(struct mlx5dr_match_param *value,
 
 static int dr_ste_build_eth_l4_misc_tag(struct mlx5dr_match_param *value,
 					struct mlx5dr_ste_build *sb,
-					u8 *hw_ste_p)
+					u8 *tag)
 {
-	struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
 	struct mlx5dr_match_misc3 *misc3 = &value->misc3;
-	u8 *tag = hw_ste->tag;
 
 	if (sb->inner) {
 		DR_STE_SET_TAG(eth_l4_misc, tag, seq_num, misc3, inner_tcp_seq_num);
@@ -2102,11 +2052,9 @@ dr_ste_build_flex_parser_tnl_vxlan_gpe_bit_mask(struct mlx5dr_match_param *value
 static int
 dr_ste_build_flex_parser_tnl_vxlan_gpe_tag(struct mlx5dr_match_param *value,
 					   struct mlx5dr_ste_build *sb,
-					   u8 *hw_ste_p)
+					   u8 *tag)
 {
-	struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
 	struct mlx5dr_match_misc3 *misc3 = &value->misc3;
-	u8 *tag = hw_ste->tag;
 
 	DR_STE_SET_TAG(flex_parser_tnl_vxlan_gpe, tag,
 		       outer_vxlan_gpe_flags, misc3,
@@ -2158,11 +2106,9 @@ dr_ste_build_flex_parser_tnl_geneve_bit_mask(struct mlx5dr_match_param *value,
 static int
 dr_ste_build_flex_parser_tnl_geneve_tag(struct mlx5dr_match_param *value,
 					struct mlx5dr_ste_build *sb,
-					u8 *hw_ste_p)
+					u8 *tag)
 {
-	struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
 	struct mlx5dr_match_misc *misc = &value->misc;
-	u8 *tag = hw_ste->tag;
 
 	DR_STE_SET_TAG(flex_parser_tnl_geneve, tag,
 		       geneve_protocol_type, misc, geneve_protocol_type);
@@ -2205,11 +2151,9 @@ static void dr_ste_build_register_0_bit_mask(struct mlx5dr_match_param *value,
 
 static int dr_ste_build_register_0_tag(struct mlx5dr_match_param *value,
 				       struct mlx5dr_ste_build *sb,
-				       u8 *hw_ste_p)
+				       u8 *tag)
 {
-	struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
 	struct mlx5dr_match_misc2 *misc2 = &value->misc2;
-	u8 *tag = hw_ste->tag;
 
 	DR_STE_SET_TAG(register_0, tag, register_0_h, misc2, metadata_reg_c_0);
 	DR_STE_SET_TAG(register_0, tag, register_0_l, misc2, metadata_reg_c_1);
@@ -2249,11 +2193,9 @@ static void dr_ste_build_register_1_bit_mask(struct mlx5dr_match_param *value,
 
 static int dr_ste_build_register_1_tag(struct mlx5dr_match_param *value,
 				       struct mlx5dr_ste_build *sb,
-				       u8 *hw_ste_p)
+				       u8 *tag)
 {
-	struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
 	struct mlx5dr_match_misc2 *misc2 = &value->misc2;
-	u8 *tag = hw_ste->tag;
 
 	DR_STE_SET_TAG(register_1, tag, register_2_h, misc2, metadata_reg_c_4);
 	DR_STE_SET_TAG(register_1, tag, register_2_l, misc2, metadata_reg_c_5);
@@ -2276,38 +2218,25 @@ void mlx5dr_ste_build_register_1(struct mlx5dr_ste_build *sb,
 	sb->ste_build_tag_func = &dr_ste_build_register_1_tag;
 }
 
-static int dr_ste_build_src_gvmi_qpn_bit_mask(struct mlx5dr_match_param *value,
-					      u8 *bit_mask)
+static void dr_ste_build_src_gvmi_qpn_bit_mask(struct mlx5dr_match_param *value,
+					       u8 *bit_mask)
 {
 	struct mlx5dr_match_misc *misc_mask = &value->misc;
 
-	/* Partial misc source_port is not supported */
-	if (misc_mask->source_port && misc_mask->source_port != 0xffff)
-		return -EINVAL;
-
-	/* Partial misc source_eswitch_owner_vhca_id is not supported */
-	if (misc_mask->source_eswitch_owner_vhca_id &&
-	    misc_mask->source_eswitch_owner_vhca_id != 0xffff)
-		return -EINVAL;
-
 	DR_STE_SET_MASK(src_gvmi_qp, bit_mask, source_gvmi, misc_mask, source_port);
 	DR_STE_SET_MASK(src_gvmi_qp, bit_mask, source_qp, misc_mask, source_sqn);
 	misc_mask->source_eswitch_owner_vhca_id = 0;
-
-	return 0;
 }
 
 static int dr_ste_build_src_gvmi_qpn_tag(struct mlx5dr_match_param *value,
 					 struct mlx5dr_ste_build *sb,
-					 u8 *hw_ste_p)
+					 u8 *tag)
 {
-	struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
 	struct mlx5dr_match_misc *misc = &value->misc;
 	struct mlx5dr_cmd_vport_cap *vport_cap;
 	struct mlx5dr_domain *dmn = sb->dmn;
 	struct mlx5dr_cmd_caps *caps;
 	u8 *bit_mask = sb->bit_mask;
-	u8 *tag = hw_ste->tag;
 	bool source_gvmi_set;
 
 	DR_STE_SET_TAG(src_gvmi_qp, tag, source_qp, misc, source_sqn);
@@ -2339,19 +2268,15 @@ static int dr_ste_build_src_gvmi_qpn_tag(struct mlx5dr_match_param *value,
 	return 0;
 }
 
-int mlx5dr_ste_build_src_gvmi_qpn(struct mlx5dr_ste_build *sb,
-				  struct mlx5dr_match_param *mask,
-				  struct mlx5dr_domain *dmn,
-				  bool inner, bool rx)
+void mlx5dr_ste_build_src_gvmi_qpn(struct mlx5dr_ste_build *sb,
+				   struct mlx5dr_match_param *mask,
+				   struct mlx5dr_domain *dmn,
+				   bool inner, bool rx)
 {
-	int ret;
-
 	/* Set vhca_id_valid before we reset source_eswitch_owner_vhca_id */
 	sb->vhca_id_valid = mask->misc.source_eswitch_owner_vhca_id;
 
-	ret = dr_ste_build_src_gvmi_qpn_bit_mask(mask, sb->bit_mask);
-	if (ret)
-		return ret;
+	dr_ste_build_src_gvmi_qpn_bit_mask(mask, sb->bit_mask);
 
 	sb->rx = rx;
 	sb->dmn = dmn;
@@ -2359,6 +2284,4 @@ int mlx5dr_ste_build_src_gvmi_qpn(struct mlx5dr_ste_build *sb,
 	sb->lu_type = MLX5DR_STE_LU_TYPE_SRC_GVMI_AND_QP;
 	sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask);
 	sb->ste_build_tag_func = &dr_ste_build_src_gvmi_qpn_tag;
-
-	return 0;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h
index 0883956c58c0..f50f3b107aa3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h
@@ -194,7 +194,7 @@ struct mlx5dr_ste_build {
 	u8 bit_mask[DR_STE_SIZE_MASK];
 	int (*ste_build_tag_func)(struct mlx5dr_match_param *spec,
 				  struct mlx5dr_ste_build *sb,
-				  u8 *hw_ste_p);
+				  u8 *tag);
 };
 
 struct mlx5dr_ste_htbl *
@@ -227,7 +227,6 @@ void mlx5dr_ste_set_hit_gvmi(u8 *hw_ste_p, u16 gvmi);
 void mlx5dr_ste_set_hit_addr(u8 *hw_ste, u64 icm_addr, u32 ht_size);
 void mlx5dr_ste_always_miss_addr(struct mlx5dr_ste *ste, u64 miss_addr);
 void mlx5dr_ste_set_bit_mask(u8 *hw_ste_p, u8 *bit_mask);
-bool mlx5dr_ste_not_used_ste(struct mlx5dr_ste *ste);
 bool mlx5dr_ste_is_last_in_rule(struct mlx5dr_matcher_rx_tx *nic_matcher,
 				u8 ste_location);
 void mlx5dr_ste_rx_set_flow_tag(u8 *hw_ste_p, u32 flow_tag);
@@ -266,6 +265,11 @@ static inline void mlx5dr_ste_get(struct mlx5dr_ste *ste)
 	ste->refcount++;
 }
 
+static inline bool mlx5dr_ste_is_not_used(struct mlx5dr_ste *ste)
+{
+	return !ste->refcount;
+}
+
 void mlx5dr_ste_set_hit_addr_by_next_htbl(u8 *hw_ste,
 					  struct mlx5dr_ste_htbl *next_htbl);
 bool mlx5dr_ste_equal_tag(void *src, void *dst);
@@ -284,9 +288,9 @@ int mlx5dr_ste_build_ste_arr(struct mlx5dr_matcher *matcher,
 			     struct mlx5dr_matcher_rx_tx *nic_matcher,
 			     struct mlx5dr_match_param *value,
 			     u8 *ste_arr);
-int mlx5dr_ste_build_eth_l2_src_des(struct mlx5dr_ste_build *builder,
-				    struct mlx5dr_match_param *mask,
-				    bool inner, bool rx);
+void mlx5dr_ste_build_eth_l2_src_des(struct mlx5dr_ste_build *builder,
+				     struct mlx5dr_match_param *mask,
+				     bool inner, bool rx);
 void mlx5dr_ste_build_eth_l3_ipv4_5_tuple(struct mlx5dr_ste_build *sb,
 					  struct mlx5dr_match_param *mask,
 					  bool inner, bool rx);
@@ -342,10 +346,10 @@ void mlx5dr_ste_build_register_0(struct mlx5dr_ste_build *sb,
 void mlx5dr_ste_build_register_1(struct mlx5dr_ste_build *sb,
 				 struct mlx5dr_match_param *mask,
 				 bool inner, bool rx);
-int mlx5dr_ste_build_src_gvmi_qpn(struct mlx5dr_ste_build *sb,
-				  struct mlx5dr_match_param *mask,
-				  struct mlx5dr_domain *dmn,
-				  bool inner, bool rx);
+void mlx5dr_ste_build_src_gvmi_qpn(struct mlx5dr_ste_build *sb,
+				   struct mlx5dr_match_param *mask,
+				   struct mlx5dr_domain *dmn,
+				   bool inner, bool rx);
 void mlx5dr_ste_build_empty_always_hit(struct mlx5dr_ste_build *sb, bool rx);
 
 /* Actions utils */
@@ -793,6 +797,7 @@ struct mlx5dr_rule {
 	struct mlx5dr_rule_rx_tx rx;
 	struct mlx5dr_rule_rx_tx tx;
 	struct list_head rule_actions_list;
+	u32 flow_source;
 };
 
 void mlx5dr_rule_update_rule_member(struct mlx5dr_ste *new_ste,
@@ -991,7 +996,6 @@ struct mlx5dr_icm_chunk *
 mlx5dr_icm_alloc_chunk(struct mlx5dr_icm_pool *pool,
 		       enum mlx5dr_icm_chunk_size chunk_size);
 void mlx5dr_icm_free_chunk(struct mlx5dr_icm_chunk *chunk);
-bool mlx5dr_ste_is_not_valid_entry(u8 *p_hw_ste);
 int mlx5dr_ste_htbl_init_and_postsend(struct mlx5dr_domain *dmn,
 				      struct mlx5dr_domain_rx_tx *nic_dmn,
 				      struct mlx5dr_ste_htbl *htbl,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c
index 9b08eb557a31..96c39a17d026 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c
@@ -487,7 +487,8 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns,
 	rule = mlx5dr_rule_create(group->fs_dr_matcher.dr_matcher,
 				  &params,
 				  num_actions,
-				  actions);
+				  actions,
+				  fte->flow_context.flow_source);
 	if (!rule) {
 		err = -EINVAL;
 		goto free_actions;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h
index 7deaca9ade3b..7914fe3fc68d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h
@@ -67,7 +67,8 @@ struct mlx5dr_rule *
 mlx5dr_rule_create(struct mlx5dr_matcher *matcher,
 		   struct mlx5dr_match_parameters *value,
 		   size_t num_actions,
-		   struct mlx5dr_action *actions[]);
+		   struct mlx5dr_action *actions[],
+		   u32 flow_source);
 
 int mlx5dr_rule_destroy(struct mlx5dr_rule *rule);
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index 1bb21fe295b9..a21afa56e3f7 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -26,6 +26,7 @@
 #include <trace/events/devlink.h>
 
 #include "core.h"
+#include "core_env.h"
 #include "item.h"
 #include "cmd.h"
 #include "port.h"
@@ -87,6 +88,8 @@ struct mlxsw_core {
 	struct {
 		struct devlink_health_reporter *fw_fatal;
 	} health;
+	struct mlxsw_env *env;
+	bool is_initialized; /* Denotes if core was already initialized. */
 	unsigned long driver_priv[];
 	/* driver_priv has to be always the last item */
 };
@@ -133,6 +136,11 @@ bool mlxsw_core_res_query_enabled(const struct mlxsw_core *mlxsw_core)
 }
 EXPORT_SYMBOL(mlxsw_core_res_query_enabled);
 
+bool mlxsw_core_temp_warn_enabled(const struct mlxsw_core *mlxsw_core)
+{
+	return mlxsw_core->driver->temp_warn_enabled;
+}
+
 bool
 mlxsw_core_fw_rev_minor_subminor_validate(const struct mlxsw_fw_rev *rev,
 					  const struct mlxsw_fw_rev *req_rev)
@@ -1102,16 +1110,13 @@ static int mlxsw_core_fw_rev_validate(struct mlxsw_core *mlxsw_core,
 }
 
 static int mlxsw_core_fw_flash_update(struct mlxsw_core *mlxsw_core,
-				      const char *file_name, const char *component,
+				      struct devlink_flash_update_params *params,
 				      struct netlink_ext_ack *extack)
 {
 	const struct firmware *firmware;
 	int err;
 
-	if (component)
-		return -EOPNOTSUPP;
-
-	err = request_firmware_direct(&firmware, file_name, mlxsw_core->bus_info->dev);
+	err = request_firmware_direct(&firmware, params->file_name, mlxsw_core->bus_info->dev);
 	if (err)
 		return err;
 	err = mlxsw_core_fw_flash(mlxsw_core, firmware, extack);
@@ -1434,13 +1439,12 @@ mlxsw_devlink_core_bus_device_reload_up(struct devlink *devlink,
 }
 
 static int mlxsw_devlink_flash_update(struct devlink *devlink,
-				      const char *file_name,
-				      const char *component,
+				      struct devlink_flash_update_params *params,
 				      struct netlink_ext_ack *extack)
 {
 	struct mlxsw_core *mlxsw_core = devlink_priv(devlink);
 
-	return mlxsw_core_fw_flash_update(mlxsw_core, file_name, component, extack);
+	return mlxsw_core_fw_flash_update(mlxsw_core, params, extack);
 }
 
 static int mlxsw_devlink_trap_init(struct devlink *devlink,
@@ -1947,6 +1951,11 @@ __mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
 	if (err)
 		goto err_thermal_init;
 
+	err = mlxsw_env_init(mlxsw_core, &mlxsw_core->env);
+	if (err)
+		goto err_env_init;
+
+	mlxsw_core->is_initialized = true;
 	devlink_params_publish(devlink);
 
 	if (!reload)
@@ -1954,6 +1963,8 @@ __mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
 
 	return 0;
 
+err_env_init:
+	mlxsw_thermal_fini(mlxsw_core->thermal);
 err_thermal_init:
 	mlxsw_hwmon_fini(mlxsw_core->hwmon);
 err_hwmon_init:
@@ -2030,6 +2041,8 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core,
 	}
 
 	devlink_params_unpublish(devlink);
+	mlxsw_core->is_initialized = false;
+	mlxsw_env_fini(mlxsw_core->env);
 	mlxsw_thermal_fini(mlxsw_core->thermal);
 	mlxsw_hwmon_fini(mlxsw_core->hwmon);
 	if (mlxsw_core->driver->fini)
@@ -2833,6 +2846,16 @@ mlxsw_core_port_devlink_port_get(struct mlxsw_core *mlxsw_core,
 }
 EXPORT_SYMBOL(mlxsw_core_port_devlink_port_get);
 
+struct mlxsw_env *mlxsw_core_env(const struct mlxsw_core *mlxsw_core)
+{
+	return mlxsw_core->env;
+}
+
+bool mlxsw_core_is_initialized(const struct mlxsw_core *mlxsw_core)
+{
+	return mlxsw_core->is_initialized;
+}
+
 int mlxsw_core_module_max_width(struct mlxsw_core *mlxsw_core, u8 module)
 {
 	enum mlxsw_reg_pmtm_module_type module_type;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h
index 2ca085a44774..92f7398287be 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.h
@@ -32,6 +32,8 @@ void *mlxsw_core_driver_priv(struct mlxsw_core *mlxsw_core);
 
 bool mlxsw_core_res_query_enabled(const struct mlxsw_core *mlxsw_core);
 
+bool mlxsw_core_temp_warn_enabled(const struct mlxsw_core *mlxsw_core);
+
 bool
 mlxsw_core_fw_rev_minor_subminor_validate(const struct mlxsw_fw_rev *rev,
 					  const struct mlxsw_fw_rev *req_rev);
@@ -221,6 +223,8 @@ enum devlink_port_type mlxsw_core_port_type_get(struct mlxsw_core *mlxsw_core,
 struct devlink_port *
 mlxsw_core_port_devlink_port_get(struct mlxsw_core *mlxsw_core,
 				 u8 local_port);
+struct mlxsw_env *mlxsw_core_env(const struct mlxsw_core *mlxsw_core);
+bool mlxsw_core_is_initialized(const struct mlxsw_core *mlxsw_core);
 int mlxsw_core_module_max_width(struct mlxsw_core *mlxsw_core, u8 module);
 
 int mlxsw_core_schedule_dw(struct delayed_work *dwork, unsigned long delay);
@@ -371,6 +375,7 @@ struct mlxsw_driver {
 	const struct mlxsw_config_profile *profile;
 	bool res_query_enabled;
 	bool fw_fatal_enabled;
+	bool temp_warn_enabled;
 };
 
 int mlxsw_core_kvd_sizes_get(struct mlxsw_core *mlxsw_core,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_env.c b/drivers/net/ethernet/mellanox/mlxsw/core_env.c
index 056eeb85be60..dd26865bd587 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_env.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_env.c
@@ -10,6 +10,18 @@
 #include "item.h"
 #include "reg.h"
 
+struct mlxsw_env_module_info {
+	u64 module_overheat_counter;
+	bool is_overheat;
+};
+
+struct mlxsw_env {
+	struct mlxsw_core *core;
+	u8 module_count;
+	spinlock_t module_info_lock; /* Protects 'module_info'. */
+	struct mlxsw_env_module_info module_info[];
+};
+
 static int mlxsw_env_validate_cable_ident(struct mlxsw_core *core, int id,
 					  bool *qsfp, bool *cmis)
 {
@@ -293,3 +305,359 @@ int mlxsw_env_get_module_eeprom(struct net_device *netdev,
 	return 0;
 }
 EXPORT_SYMBOL(mlxsw_env_get_module_eeprom);
+
+static int mlxsw_env_module_has_temp_sensor(struct mlxsw_core *mlxsw_core,
+					    u8 module,
+					    bool *p_has_temp_sensor)
+{
+	char mtbr_pl[MLXSW_REG_MTBR_LEN];
+	u16 temp;
+	int err;
+
+	mlxsw_reg_mtbr_pack(mtbr_pl, MLXSW_REG_MTBR_BASE_MODULE_INDEX + module,
+			    1);
+	err = mlxsw_reg_query(mlxsw_core, MLXSW_REG(mtbr), mtbr_pl);
+	if (err)
+		return err;
+
+	mlxsw_reg_mtbr_temp_unpack(mtbr_pl, 0, &temp, NULL);
+
+	switch (temp) {
+	case MLXSW_REG_MTBR_BAD_SENS_INFO:
+	case MLXSW_REG_MTBR_NO_CONN:
+	case MLXSW_REG_MTBR_NO_TEMP_SENS:
+	case MLXSW_REG_MTBR_INDEX_NA:
+		*p_has_temp_sensor = false;
+		break;
+	default:
+		*p_has_temp_sensor = temp ? true : false;
+	}
+	return 0;
+}
+
+static int mlxsw_env_temp_event_set(struct mlxsw_core *mlxsw_core,
+				    u16 sensor_index, bool enable)
+{
+	char mtmp_pl[MLXSW_REG_MTMP_LEN] = {0};
+	enum mlxsw_reg_mtmp_tee tee;
+	int err, threshold_hi;
+
+	mlxsw_reg_mtmp_sensor_index_set(mtmp_pl, sensor_index);
+	err = mlxsw_reg_query(mlxsw_core, MLXSW_REG(mtmp), mtmp_pl);
+	if (err)
+		return err;
+
+	if (enable) {
+		err = mlxsw_env_module_temp_thresholds_get(mlxsw_core,
+							   sensor_index -
+							   MLXSW_REG_MTMP_MODULE_INDEX_MIN,
+							   SFP_TEMP_HIGH_WARN,
+							   &threshold_hi);
+		/* In case it is not possible to query the module's threshold,
+		 * use the default value.
+		 */
+		if (err)
+			threshold_hi = MLXSW_REG_MTMP_THRESH_HI;
+		else
+			/* mlxsw_env_module_temp_thresholds_get() multiplies
+			 * Celsius degrees by 1000 whereas MTMP expects
+			 * temperature in 0.125 Celsius degrees units.
+			 * Convert threshold_hi to correct units.
+			 */
+			threshold_hi = threshold_hi / 1000 * 8;
+
+		mlxsw_reg_mtmp_temperature_threshold_hi_set(mtmp_pl, threshold_hi);
+		mlxsw_reg_mtmp_temperature_threshold_lo_set(mtmp_pl, threshold_hi -
+							    MLXSW_REG_MTMP_HYSTERESIS_TEMP);
+	}
+	tee = enable ? MLXSW_REG_MTMP_TEE_GENERATE_EVENT : MLXSW_REG_MTMP_TEE_NO_EVENT;
+	mlxsw_reg_mtmp_tee_set(mtmp_pl, tee);
+	return mlxsw_reg_write(mlxsw_core, MLXSW_REG(mtmp), mtmp_pl);
+}
+
+static int mlxsw_env_module_temp_event_enable(struct mlxsw_core *mlxsw_core,
+					      u8 module_count)
+{
+	int i, err, sensor_index;
+	bool has_temp_sensor;
+
+	for (i = 0; i < module_count; i++) {
+		err = mlxsw_env_module_has_temp_sensor(mlxsw_core, i,
+						       &has_temp_sensor);
+		if (err)
+			return err;
+
+		if (!has_temp_sensor)
+			continue;
+
+		sensor_index = i + MLXSW_REG_MTMP_MODULE_INDEX_MIN;
+		err = mlxsw_env_temp_event_set(mlxsw_core, sensor_index, true);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static void mlxsw_env_mtwe_event_func(const struct mlxsw_reg_info *reg,
+				      char *mtwe_pl, void *priv)
+{
+	struct mlxsw_env *mlxsw_env = priv;
+	int i, sensor_warning;
+	bool is_overheat;
+
+	for (i = 0; i < mlxsw_env->module_count; i++) {
+		/* 64-127 of sensor_index are mapped to the port modules
+		 * sequentially (module 0 is mapped to sensor_index 64,
+		 * module 1 to sensor_index 65 and so on)
+		 */
+		sensor_warning =
+			mlxsw_reg_mtwe_sensor_warning_get(mtwe_pl,
+							  i + MLXSW_REG_MTMP_MODULE_INDEX_MIN);
+		spin_lock(&mlxsw_env->module_info_lock);
+		is_overheat =
+			mlxsw_env->module_info[i].is_overheat;
+
+		if ((is_overheat && sensor_warning) ||
+		    (!is_overheat && !sensor_warning)) {
+			/* Current state is "warning" and MTWE still reports
+			 * warning OR current state in "no warning" and MTWE
+			 * does not report warning.
+			 */
+			spin_unlock(&mlxsw_env->module_info_lock);
+			continue;
+		} else if (is_overheat && !sensor_warning) {
+			/* MTWE reports "no warning", turn is_overheat off.
+			 */
+			mlxsw_env->module_info[i].is_overheat = false;
+			spin_unlock(&mlxsw_env->module_info_lock);
+		} else {
+			/* Current state is "no warning" and MTWE reports
+			 * "warning", increase the counter and turn is_overheat
+			 * on.
+			 */
+			mlxsw_env->module_info[i].is_overheat = true;
+			mlxsw_env->module_info[i].module_overheat_counter++;
+			spin_unlock(&mlxsw_env->module_info_lock);
+		}
+	}
+}
+
+static const struct mlxsw_listener mlxsw_env_temp_warn_listener =
+	MLXSW_EVENTL(mlxsw_env_mtwe_event_func, MTWE, MTWE);
+
+static int mlxsw_env_temp_warn_event_register(struct mlxsw_core *mlxsw_core)
+{
+	struct mlxsw_env *mlxsw_env = mlxsw_core_env(mlxsw_core);
+
+	if (!mlxsw_core_temp_warn_enabled(mlxsw_core))
+		return 0;
+
+	return mlxsw_core_trap_register(mlxsw_core,
+					&mlxsw_env_temp_warn_listener,
+					mlxsw_env);
+}
+
+static void mlxsw_env_temp_warn_event_unregister(struct mlxsw_env *mlxsw_env)
+{
+	if (!mlxsw_core_temp_warn_enabled(mlxsw_env->core))
+		return;
+
+	mlxsw_core_trap_unregister(mlxsw_env->core,
+				   &mlxsw_env_temp_warn_listener, mlxsw_env);
+}
+
+struct mlxsw_env_module_plug_unplug_event {
+	struct mlxsw_env *mlxsw_env;
+	u8 module;
+	struct work_struct work;
+};
+
+static void mlxsw_env_pmpe_event_work(struct work_struct *work)
+{
+	struct mlxsw_env_module_plug_unplug_event *event;
+	struct mlxsw_env *mlxsw_env;
+	bool has_temp_sensor;
+	u16 sensor_index;
+	int err;
+
+	event = container_of(work, struct mlxsw_env_module_plug_unplug_event,
+			     work);
+	mlxsw_env = event->mlxsw_env;
+
+	spin_lock_bh(&mlxsw_env->module_info_lock);
+	mlxsw_env->module_info[event->module].is_overheat = false;
+	spin_unlock_bh(&mlxsw_env->module_info_lock);
+
+	err = mlxsw_env_module_has_temp_sensor(mlxsw_env->core, event->module,
+					       &has_temp_sensor);
+	/* Do not disable events on modules without sensors or faulty sensors
+	 * because FW returns errors.
+	 */
+	if (err)
+		goto out;
+
+	if (!has_temp_sensor)
+		goto out;
+
+	sensor_index = event->module + MLXSW_REG_MTMP_MODULE_INDEX_MIN;
+	mlxsw_env_temp_event_set(mlxsw_env->core, sensor_index, true);
+
+out:
+	kfree(event);
+}
+
+static void
+mlxsw_env_pmpe_listener_func(const struct mlxsw_reg_info *reg, char *pmpe_pl,
+			     void *priv)
+{
+	struct mlxsw_env_module_plug_unplug_event *event;
+	enum mlxsw_reg_pmpe_module_status module_status;
+	u8 module = mlxsw_reg_pmpe_module_get(pmpe_pl);
+	struct mlxsw_env *mlxsw_env = priv;
+
+	if (WARN_ON_ONCE(module >= mlxsw_env->module_count))
+		return;
+
+	module_status = mlxsw_reg_pmpe_module_status_get(pmpe_pl);
+	if (module_status != MLXSW_REG_PMPE_MODULE_STATUS_PLUGGED_ENABLED)
+		return;
+
+	event = kmalloc(sizeof(*event), GFP_ATOMIC);
+	if (!event)
+		return;
+
+	event->mlxsw_env = mlxsw_env;
+	event->module = module;
+	INIT_WORK(&event->work, mlxsw_env_pmpe_event_work);
+	mlxsw_core_schedule_work(&event->work);
+}
+
+static const struct mlxsw_listener mlxsw_env_module_plug_listener =
+	MLXSW_EVENTL(mlxsw_env_pmpe_listener_func, PMPE, PMPE);
+
+static int
+mlxsw_env_module_plug_event_register(struct mlxsw_core *mlxsw_core)
+{
+	struct mlxsw_env *mlxsw_env = mlxsw_core_env(mlxsw_core);
+
+	if (!mlxsw_core_temp_warn_enabled(mlxsw_core))
+		return 0;
+
+	return mlxsw_core_trap_register(mlxsw_core,
+					&mlxsw_env_module_plug_listener,
+					mlxsw_env);
+}
+
+static void
+mlxsw_env_module_plug_event_unregister(struct mlxsw_env *mlxsw_env)
+{
+	if (!mlxsw_core_temp_warn_enabled(mlxsw_env->core))
+		return;
+
+	mlxsw_core_trap_unregister(mlxsw_env->core,
+				   &mlxsw_env_module_plug_listener,
+				   mlxsw_env);
+}
+
+static int
+mlxsw_env_module_oper_state_event_enable(struct mlxsw_core *mlxsw_core,
+					 u8 module_count)
+{
+	int i, err;
+
+	for (i = 0; i < module_count; i++) {
+		char pmaos_pl[MLXSW_REG_PMAOS_LEN];
+
+		mlxsw_reg_pmaos_pack(pmaos_pl, i,
+				     MLXSW_REG_PMAOS_E_GENERATE_EVENT);
+		err = mlxsw_reg_write(mlxsw_core, MLXSW_REG(pmaos), pmaos_pl);
+		if (err)
+			return err;
+	}
+	return 0;
+}
+
+int
+mlxsw_env_module_overheat_counter_get(struct mlxsw_core *mlxsw_core, u8 module,
+				      u64 *p_counter)
+{
+	struct mlxsw_env *mlxsw_env = mlxsw_core_env(mlxsw_core);
+
+	/* Prevent switch driver from accessing uninitialized data. */
+	if (!mlxsw_core_is_initialized(mlxsw_core)) {
+		*p_counter = 0;
+		return 0;
+	}
+
+	if (WARN_ON_ONCE(module >= mlxsw_env->module_count))
+		return -EINVAL;
+
+	spin_lock_bh(&mlxsw_env->module_info_lock);
+	*p_counter = mlxsw_env->module_info[module].module_overheat_counter;
+	spin_unlock_bh(&mlxsw_env->module_info_lock);
+
+	return 0;
+}
+EXPORT_SYMBOL(mlxsw_env_module_overheat_counter_get);
+
+int mlxsw_env_init(struct mlxsw_core *mlxsw_core, struct mlxsw_env **p_env)
+{
+	char mgpir_pl[MLXSW_REG_MGPIR_LEN];
+	struct mlxsw_env *env;
+	u8 module_count;
+	int err;
+
+	mlxsw_reg_mgpir_pack(mgpir_pl);
+	err = mlxsw_reg_query(mlxsw_core, MLXSW_REG(mgpir), mgpir_pl);
+	if (err)
+		return err;
+
+	mlxsw_reg_mgpir_unpack(mgpir_pl, NULL, NULL, NULL, &module_count);
+
+	env = kzalloc(struct_size(env, module_info, module_count), GFP_KERNEL);
+	if (!env)
+		return -ENOMEM;
+
+	spin_lock_init(&env->module_info_lock);
+	env->core = mlxsw_core;
+	env->module_count = module_count;
+	*p_env = env;
+
+	err = mlxsw_env_temp_warn_event_register(mlxsw_core);
+	if (err)
+		goto err_temp_warn_event_register;
+
+	err = mlxsw_env_module_plug_event_register(mlxsw_core);
+	if (err)
+		goto err_module_plug_event_register;
+
+	err = mlxsw_env_module_oper_state_event_enable(mlxsw_core,
+						       env->module_count);
+	if (err)
+		goto err_oper_state_event_enable;
+
+	err = mlxsw_env_module_temp_event_enable(mlxsw_core, env->module_count);
+	if (err)
+		goto err_temp_event_enable;
+
+	return 0;
+
+err_temp_event_enable:
+err_oper_state_event_enable:
+	mlxsw_env_module_plug_event_unregister(env);
+err_module_plug_event_register:
+	mlxsw_env_temp_warn_event_unregister(env);
+err_temp_warn_event_register:
+	kfree(env);
+	return err;
+}
+
+void mlxsw_env_fini(struct mlxsw_env *env)
+{
+	mlxsw_env_module_plug_event_unregister(env);
+	/* Make sure there is no more event work scheduled. */
+	mlxsw_core_flush_owq();
+	mlxsw_env_temp_warn_event_unregister(env);
+	kfree(env);
+}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_env.h b/drivers/net/ethernet/mellanox/mlxsw/core_env.h
index 064d0e770c01..8e36a2634ef5 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_env.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_env.h
@@ -14,4 +14,10 @@ int mlxsw_env_get_module_eeprom(struct net_device *netdev,
 				struct mlxsw_core *mlxsw_core, int module,
 				struct ethtool_eeprom *ee, u8 *data);
 
+int
+mlxsw_env_module_overheat_counter_get(struct mlxsw_core *mlxsw_core, u8 module,
+				      u64 *p_counter);
+int mlxsw_env_init(struct mlxsw_core *core, struct mlxsw_env **p_env);
+void mlxsw_env_fini(struct mlxsw_env *env);
+
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c b/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c
index 252e91072c5a..2196c946698a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c
@@ -106,7 +106,7 @@ static ssize_t mlxsw_hwmon_temp_rst_store(struct device *dev,
 	struct mlxsw_hwmon_attr *mlwsw_hwmon_attr =
 			container_of(attr, struct mlxsw_hwmon_attr, dev_attr);
 	struct mlxsw_hwmon *mlxsw_hwmon = mlwsw_hwmon_attr->hwmon;
-	char mtmp_pl[MLXSW_REG_MTMP_LEN];
+	char mtmp_pl[MLXSW_REG_MTMP_LEN] = {0};
 	unsigned long val;
 	int index;
 	int err;
@@ -119,7 +119,13 @@ static ssize_t mlxsw_hwmon_temp_rst_store(struct device *dev,
 
 	index = mlxsw_hwmon_get_attr_index(mlwsw_hwmon_attr->type_index,
 					   mlxsw_hwmon->module_sensor_max);
-	mlxsw_reg_mtmp_pack(mtmp_pl, index, true, true);
+
+	mlxsw_reg_mtmp_sensor_index_set(mtmp_pl, index);
+	err = mlxsw_reg_query(mlxsw_hwmon->core, MLXSW_REG(mtmp), mtmp_pl);
+	if (err)
+		return err;
+	mlxsw_reg_mtmp_mte_set(mtmp_pl, true);
+	mlxsw_reg_mtmp_mtr_set(mtmp_pl, true);
 	err = mlxsw_reg_write(mlxsw_hwmon->core, MLXSW_REG(mtmp), mtmp_pl);
 	if (err) {
 		dev_err(mlxsw_hwmon->bus_info->dev, "Failed to reset temp sensor history\n");
@@ -570,7 +576,6 @@ static void mlxsw_hwmon_attr_add(struct mlxsw_hwmon *mlxsw_hwmon,
 static int mlxsw_hwmon_temp_init(struct mlxsw_hwmon *mlxsw_hwmon)
 {
 	char mtcap_pl[MLXSW_REG_MTCAP_LEN] = {0};
-	char mtmp_pl[MLXSW_REG_MTMP_LEN];
 	int i;
 	int err;
 
@@ -581,7 +586,15 @@ static int mlxsw_hwmon_temp_init(struct mlxsw_hwmon *mlxsw_hwmon)
 	}
 	mlxsw_hwmon->sensor_count = mlxsw_reg_mtcap_sensor_count_get(mtcap_pl);
 	for (i = 0; i < mlxsw_hwmon->sensor_count; i++) {
-		mlxsw_reg_mtmp_pack(mtmp_pl, i, true, true);
+		char mtmp_pl[MLXSW_REG_MTMP_LEN] = {0};
+
+		mlxsw_reg_mtmp_sensor_index_set(mtmp_pl, i);
+		err = mlxsw_reg_query(mlxsw_hwmon->core, MLXSW_REG(mtmp),
+				      mtmp_pl);
+		if (err)
+			return err;
+		mlxsw_reg_mtmp_mte_set(mtmp_pl, true);
+		mlxsw_reg_mtmp_mtr_set(mtmp_pl, true);
 		err = mlxsw_reg_write(mlxsw_hwmon->core,
 				      MLXSW_REG(mtmp), mtmp_pl);
 		if (err) {
diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index 6e3d55006089..39eff6a57ba2 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -5405,6 +5405,64 @@ static inline void mlxsw_reg_pspa_pack(char *payload, u8 swid, u8 local_port)
 	mlxsw_reg_pspa_sub_port_set(payload, 0);
 }
 
+/* PMAOS - Ports Module Administrative and Operational Status
+ * ----------------------------------------------------------
+ * This register configures and retrieves the per module status.
+ */
+#define MLXSW_REG_PMAOS_ID 0x5012
+#define MLXSW_REG_PMAOS_LEN 0x10
+
+MLXSW_REG_DEFINE(pmaos, MLXSW_REG_PMAOS_ID, MLXSW_REG_PMAOS_LEN);
+
+/* reg_slot_index
+ * Slot index.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, pmaos, slot_index, 0x00, 24, 4);
+
+/* reg_pmaos_module
+ * Module number.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, pmaos, module, 0x00, 16, 8);
+
+/* reg_pmaos_ase
+ * Admin state update enable.
+ * If this bit is set, admin state will be updated based on admin_state field.
+ * Only relevant on Set() operations.
+ * Access: WO
+ */
+MLXSW_ITEM32(reg, pmaos, ase, 0x04, 31, 1);
+
+/* reg_pmaos_ee
+ * Event update enable.
+ * If this bit is set, event generation will be updated based on the e field.
+ * Only relevant on Set operations.
+ * Access: WO
+ */
+MLXSW_ITEM32(reg, pmaos, ee, 0x04, 30, 1);
+
+enum mlxsw_reg_pmaos_e {
+	MLXSW_REG_PMAOS_E_DO_NOT_GENERATE_EVENT,
+	MLXSW_REG_PMAOS_E_GENERATE_EVENT,
+	MLXSW_REG_PMAOS_E_GENERATE_SINGLE_EVENT,
+};
+
+/* reg_pmaos_e
+ * Event Generation on operational state change.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, pmaos, e, 0x04, 0, 2);
+
+static inline void mlxsw_reg_pmaos_pack(char *payload, u8 module,
+					enum mlxsw_reg_pmaos_e e)
+{
+	MLXSW_REG_ZERO(pmaos, payload);
+	mlxsw_reg_pmaos_module_set(payload, module);
+	mlxsw_reg_pmaos_e_set(payload, e);
+	mlxsw_reg_pmaos_ee_set(payload, true);
+}
+
 /* PPLR - Port Physical Loopback Register
  * --------------------------------------
  * This register allows configuration of the port's loopback mode.
@@ -5441,6 +5499,50 @@ static inline void mlxsw_reg_pplr_pack(char *payload, u8 local_port,
 				 MLXSW_REG_PPLR_LB_TYPE_BIT_PHY_LOCAL : 0);
 }
 
+/* PMPE - Port Module Plug/Unplug Event Register
+ * ---------------------------------------------
+ * This register reports any operational status change of a module.
+ * A change in the module’s state will generate an event only if the change
+ * happens after arming the event mechanism. Any changes to the module state
+ * while the event mechanism is not armed will not be reported. Software can
+ * query the PMPE register for module status.
+ */
+#define MLXSW_REG_PMPE_ID 0x5024
+#define MLXSW_REG_PMPE_LEN 0x10
+
+MLXSW_REG_DEFINE(pmpe, MLXSW_REG_PMPE_ID, MLXSW_REG_PMPE_LEN);
+
+/* reg_pmpe_slot_index
+ * Slot index.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, pmpe, slot_index, 0x00, 24, 4);
+
+/* reg_pmpe_module
+ * Module number.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, pmpe, module, 0x00, 16, 8);
+
+enum mlxsw_reg_pmpe_module_status {
+	MLXSW_REG_PMPE_MODULE_STATUS_PLUGGED_ENABLED = 1,
+	MLXSW_REG_PMPE_MODULE_STATUS_UNPLUGGED,
+	MLXSW_REG_PMPE_MODULE_STATUS_PLUGGED_ERROR,
+	MLXSW_REG_PMPE_MODULE_STATUS_PLUGGED_DISABLED,
+};
+
+/* reg_pmpe_module_status
+ * Module status.
+ * Access: RO
+ */
+MLXSW_ITEM32(reg, pmpe, module_status, 0x00, 0, 4);
+
+/* reg_pmpe_error_type
+ * Module error details.
+ * Access: RO
+ */
+MLXSW_ITEM32(reg, pmpe, error_type, 0x04, 8, 4);
+
 /* PDDR - Port Diagnostics Database Register
  * -----------------------------------------
  * The PDDR enables to read the Phy debug database
@@ -5580,6 +5682,8 @@ MLXSW_ITEM32(reg, htgt, type, 0x00, 8, 4);
 enum mlxsw_reg_htgt_trap_group {
 	MLXSW_REG_HTGT_TRAP_GROUP_EMAD,
 	MLXSW_REG_HTGT_TRAP_GROUP_MFDE,
+	MLXSW_REG_HTGT_TRAP_GROUP_MTWE,
+	MLXSW_REG_HTGT_TRAP_GROUP_PMPE,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_STP,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_LACP,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_LLDP,
@@ -8413,6 +8517,13 @@ MLXSW_ITEM32(reg, mtmp, max_temperature, 0x08, 0, 16);
  * 2 - Generate single event
  * Access: RW
  */
+
+enum mlxsw_reg_mtmp_tee {
+	MLXSW_REG_MTMP_TEE_NO_EVENT,
+	MLXSW_REG_MTMP_TEE_GENERATE_EVENT,
+	MLXSW_REG_MTMP_TEE_GENERATE_SINGLE_EVENT,
+};
+
 MLXSW_ITEM32(reg, mtmp, tee, 0x0C, 30, 2);
 
 #define MLXSW_REG_MTMP_THRESH_HI 0x348	/* 105 Celsius */
@@ -8423,6 +8534,7 @@ MLXSW_ITEM32(reg, mtmp, tee, 0x0C, 30, 2);
  */
 MLXSW_ITEM32(reg, mtmp, temperature_threshold_hi, 0x0C, 0, 16);
 
+#define MLXSW_REG_MTMP_HYSTERESIS_TEMP 0x28 /* 5 Celsius */
 /* reg_mtmp_temperature_threshold_lo
  * Low threshold for Temperature Warning Event. In 0.125 Celsius.
  * Access: RW
@@ -8466,6 +8578,23 @@ static inline void mlxsw_reg_mtmp_unpack(char *payload, int *p_temp,
 		mlxsw_reg_mtmp_sensor_name_memcpy_from(payload, sensor_name);
 }
 
+/* MTWE - Management Temperature Warning Event
+ * -------------------------------------------
+ * This register is used for over temperature warning.
+ */
+#define MLXSW_REG_MTWE_ID 0x900B
+#define MLXSW_REG_MTWE_LEN 0x10
+
+MLXSW_REG_DEFINE(mtwe, MLXSW_REG_MTWE_ID, MLXSW_REG_MTWE_LEN);
+
+/* reg_mtwe_sensor_warning
+ * Bit vector indicating which of the sensor reading is above threshold.
+ * Address 00h bit31 is sensor_warning[127].
+ * Address 0Ch bit0 is sensor_warning[0].
+ * Access: RO
+ */
+MLXSW_ITEM_BIT_ARRAY(reg, mtwe, sensor_warning, 0x0, 0x10, 1);
+
 /* MTBR - Management Temperature Bulk Register
  * -------------------------------------------
  * This register is used for bulk temperature reading.
@@ -11041,7 +11170,9 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = {
 	MLXSW_REG(pptb),
 	MLXSW_REG(pbmc),
 	MLXSW_REG(pspa),
+	MLXSW_REG(pmaos),
 	MLXSW_REG(pplr),
+	MLXSW_REG(pmpe),
 	MLXSW_REG(pddr),
 	MLXSW_REG(pmtm),
 	MLXSW_REG(htgt),
@@ -11071,6 +11202,7 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = {
 	MLXSW_REG(fore),
 	MLXSW_REG(mtcap),
 	MLXSW_REG(mtmp),
+	MLXSW_REG(mtwe),
 	MLXSW_REG(mtbr),
 	MLXSW_REG(mcia),
 	MLXSW_REG(mpat),
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 9d5a6f8d7438..ab7d12aad880 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -1365,6 +1365,22 @@ static int mlxsw_sp_port_tc_mc_mode_set(struct mlxsw_sp_port *mlxsw_sp_port,
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(qtctm), qtctm_pl);
 }
 
+static int mlxsw_sp_port_overheat_init_val_set(struct mlxsw_sp_port *mlxsw_sp_port)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	u8 module = mlxsw_sp_port->mapping.module;
+	u64 overheat_counter;
+	int err;
+
+	err = mlxsw_env_module_overheat_counter_get(mlxsw_sp->core, module,
+						    &overheat_counter);
+	if (err)
+		return err;
+
+	mlxsw_sp_port->module_overheat_initial_val = overheat_counter;
+	return 0;
+}
+
 static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 				u8 split_base_local_port,
 				struct mlxsw_sp_port_mapping *port_mapping)
@@ -1575,6 +1591,14 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 			  mlxsw_sp->ptp_ops->shaper_work);
 
 	mlxsw_sp->ports[local_port] = mlxsw_sp_port;
+
+	err = mlxsw_sp_port_overheat_init_val_set(mlxsw_sp_port);
+	if (err) {
+		dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to set overheat initial value\n",
+			mlxsw_sp_port->local_port);
+		goto err_port_overheat_init_val_set;
+	}
+
 	err = register_netdev(dev);
 	if (err) {
 		dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to register netdev\n",
@@ -1588,6 +1612,7 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 	return 0;
 
 err_register_netdev:
+err_port_overheat_init_val_set:
 	mlxsw_sp->ports[local_port] = NULL;
 	mlxsw_sp_port_vlan_destroy(mlxsw_sp_port_vlan);
 err_port_vlan_create:
@@ -2440,6 +2465,22 @@ static int mlxsw_sp_basic_trap_groups_set(struct mlxsw_core *mlxsw_core)
 			    MLXSW_REG_HTGT_INVALID_POLICER,
 			    MLXSW_REG_HTGT_DEFAULT_PRIORITY,
 			    MLXSW_REG_HTGT_DEFAULT_TC);
+	err = mlxsw_reg_write(mlxsw_core, MLXSW_REG(htgt), htgt_pl);
+	if (err)
+		return err;
+
+	mlxsw_reg_htgt_pack(htgt_pl, MLXSW_REG_HTGT_TRAP_GROUP_MTWE,
+			    MLXSW_REG_HTGT_INVALID_POLICER,
+			    MLXSW_REG_HTGT_DEFAULT_PRIORITY,
+			    MLXSW_REG_HTGT_DEFAULT_TC);
+	err = mlxsw_reg_write(mlxsw_core, MLXSW_REG(htgt), htgt_pl);
+	if (err)
+		return err;
+
+	mlxsw_reg_htgt_pack(htgt_pl, MLXSW_REG_HTGT_TRAP_GROUP_PMPE,
+			    MLXSW_REG_HTGT_INVALID_POLICER,
+			    MLXSW_REG_HTGT_DEFAULT_PRIORITY,
+			    MLXSW_REG_HTGT_DEFAULT_TC);
 	return mlxsw_reg_write(mlxsw_core, MLXSW_REG(htgt), htgt_pl);
 }
 
@@ -3197,6 +3238,7 @@ static struct mlxsw_driver mlxsw_sp1_driver = {
 	.profile			= &mlxsw_sp1_config_profile,
 	.res_query_enabled		= true,
 	.fw_fatal_enabled		= true,
+	.temp_warn_enabled		= true,
 };
 
 static struct mlxsw_driver mlxsw_sp2_driver = {
@@ -3237,6 +3279,7 @@ static struct mlxsw_driver mlxsw_sp2_driver = {
 	.profile			= &mlxsw_sp2_config_profile,
 	.res_query_enabled		= true,
 	.fw_fatal_enabled		= true,
+	.temp_warn_enabled		= true,
 };
 
 static struct mlxsw_driver mlxsw_sp3_driver = {
@@ -3277,6 +3320,7 @@ static struct mlxsw_driver mlxsw_sp3_driver = {
 	.profile			= &mlxsw_sp2_config_profile,
 	.res_query_enabled		= true,
 	.fw_fatal_enabled		= true,
+	.temp_warn_enabled		= true,
 };
 
 bool mlxsw_sp_port_dev_check(const struct net_device *dev)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index f0a4347acd25..3e26eb6cb140 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -319,6 +319,7 @@ struct mlxsw_sp_port {
 	int max_mtu;
 	u32 max_speed;
 	struct mlxsw_sp_hdroom *hdroom;
+	u64 module_overheat_initial_val;
 };
 
 struct mlxsw_sp_port_type_speed_ops {
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c
index 6045d3df00ef..2096b6478958 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c
@@ -2,6 +2,7 @@
 /* Copyright (c) 2020 Mellanox Technologies. All rights reserved */
 
 #include "reg.h"
+#include "core.h"
 #include "spectrum.h"
 #include "core_env.h"
 
@@ -552,6 +553,37 @@ static struct mlxsw_sp_port_hw_stats mlxsw_sp_port_hw_tc_stats[] = {
 
 #define MLXSW_SP_PORT_HW_TC_STATS_LEN ARRAY_SIZE(mlxsw_sp_port_hw_tc_stats)
 
+struct mlxsw_sp_port_stats {
+	char str[ETH_GSTRING_LEN];
+	u64 (*getter)(struct mlxsw_sp_port *mlxsw_sp_port);
+};
+
+static u64
+mlxsw_sp_port_get_transceiver_overheat_stats(struct mlxsw_sp_port *mlxsw_sp_port)
+{
+	struct mlxsw_sp_port_mapping port_mapping = mlxsw_sp_port->mapping;
+	struct mlxsw_core *mlxsw_core = mlxsw_sp_port->mlxsw_sp->core;
+	u64 stats;
+	int err;
+
+	err = mlxsw_env_module_overheat_counter_get(mlxsw_core,
+						    port_mapping.module,
+						    &stats);
+	if (err)
+		return mlxsw_sp_port->module_overheat_initial_val;
+
+	return stats - mlxsw_sp_port->module_overheat_initial_val;
+}
+
+static struct mlxsw_sp_port_stats mlxsw_sp_port_transceiver_stats[] = {
+	{
+		.str = "transceiver_overheat",
+		.getter = mlxsw_sp_port_get_transceiver_overheat_stats,
+	},
+};
+
+#define MLXSW_SP_PORT_HW_TRANSCEIVER_STATS_LEN ARRAY_SIZE(mlxsw_sp_port_transceiver_stats)
+
 #define MLXSW_SP_PORT_ETHTOOL_STATS_LEN (MLXSW_SP_PORT_HW_STATS_LEN + \
 					 MLXSW_SP_PORT_HW_RFC_2863_STATS_LEN + \
 					 MLXSW_SP_PORT_HW_RFC_2819_STATS_LEN + \
@@ -561,7 +593,8 @@ static struct mlxsw_sp_port_hw_stats mlxsw_sp_port_hw_tc_stats[] = {
 					 (MLXSW_SP_PORT_HW_PRIO_STATS_LEN * \
 					  IEEE_8021QAZ_MAX_TCS) + \
 					 (MLXSW_SP_PORT_HW_TC_STATS_LEN * \
-					  TC_MAX_QUEUE))
+					  TC_MAX_QUEUE) + \
+					  MLXSW_SP_PORT_HW_TRANSCEIVER_STATS_LEN)
 
 static void mlxsw_sp_port_get_prio_strings(u8 **p, int prio)
 {
@@ -637,6 +670,12 @@ static void mlxsw_sp_port_get_strings(struct net_device *dev,
 			mlxsw_sp_port_get_tc_strings(&p, i);
 
 		mlxsw_sp_port->mlxsw_sp->ptp_ops->get_stats_strings(&p);
+
+		for (i = 0; i < MLXSW_SP_PORT_HW_TRANSCEIVER_STATS_LEN; i++) {
+			memcpy(p, mlxsw_sp_port_transceiver_stats[i].str,
+			       ETH_GSTRING_LEN);
+			p += ETH_GSTRING_LEN;
+		}
 		break;
 	}
 }
@@ -732,6 +771,17 @@ static void __mlxsw_sp_port_get_stats(struct net_device *dev,
 	}
 }
 
+static void __mlxsw_sp_port_get_env_stats(struct net_device *dev, u64 *data, int data_index,
+					  struct mlxsw_sp_port_stats *port_stats,
+					  int len)
+{
+	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
+	int i;
+
+	for (i = 0; i < len; i++)
+		data[data_index + i] = port_stats[i].getter(mlxsw_sp_port);
+}
+
 static void mlxsw_sp_port_get_stats(struct net_device *dev,
 				    struct ethtool_stats *stats, u64 *data)
 {
@@ -786,6 +836,11 @@ static void mlxsw_sp_port_get_stats(struct net_device *dev,
 	mlxsw_sp_port->mlxsw_sp->ptp_ops->get_stats(mlxsw_sp_port,
 						    data, data_index);
 	data_index += mlxsw_sp_port->mlxsw_sp->ptp_ops->get_stats_count();
+
+	/* Transceiver counters */
+	__mlxsw_sp_port_get_env_stats(dev, data, data_index, mlxsw_sp_port_transceiver_stats,
+				      MLXSW_SP_PORT_HW_TRANSCEIVER_STATS_LEN);
+	data_index += MLXSW_SP_PORT_HW_TRANSCEIVER_STATS_LEN;
 }
 
 static int mlxsw_sp_port_get_sset_count(struct net_device *dev, int sset)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/trap.h b/drivers/net/ethernet/mellanox/mlxsw/trap.h
index fe0b8af287a7..57f9e24602d0 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/trap.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/trap.h
@@ -124,6 +124,10 @@ enum mlxsw_event_trap_id {
 	MLXSW_TRAP_ID_MFDE = 0x3,
 	/* Port Up/Down event generated by hardware */
 	MLXSW_TRAP_ID_PUDE = 0x8,
+	/* Port Module Plug/Unplug Event generated by hardware */
+	MLXSW_TRAP_ID_PMPE = 0x9,
+	/* Temperature Warning event generated by hardware */
+	MLXSW_TRAP_ID_MTWE = 0xC,
 	/* PTP Ingress FIFO has a new entry */
 	MLXSW_TRAP_ID_PTP_ING_FIFO = 0x2D,
 	/* PTP Egress FIFO has a new entry */
diff --git a/drivers/net/ethernet/micrel/ksz884x.c b/drivers/net/ethernet/micrel/ksz884x.c
index ac4cc509ae07..9ed264ed7070 100644
--- a/drivers/net/ethernet/micrel/ksz884x.c
+++ b/drivers/net/ethernet/micrel/ksz884x.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0-only
-/**
+/*
  * drivers/net/ethernet/micrel/ksx884x.c - Micrel KSZ8841/2 PCI Ethernet driver
  *
  * Copyright (c) 2009-2010 Micrel, Inc.
@@ -959,7 +959,7 @@ struct ksz_sw_desc {
  * struct ksz_dma_buf - OS dependent DMA buffer data structure
  * @skb:	Associated socket buffer.
  * @dma:	Associated physical DMA address.
- * len:		Actual len used.
+ * @len:	Actual len used.
  */
 struct ksz_dma_buf {
 	struct sk_buff *skb;
@@ -1254,6 +1254,7 @@ struct ksz_port_info {
  * @multi_list_size:	Multicast address list size.
  * @enabled:		Indication of hardware enabled.
  * @rx_stop:		Indication of receive process stop.
+ * @reserved2:		none
  * @features:		Hardware features to enable.
  * @overrides:		Hardware features to override.
  * @parent:		Pointer to parent, network device private structure.
@@ -1447,7 +1448,7 @@ struct dev_info {
  * struct dev_priv - Network device private data structure
  * @adapter:		Adapter device information.
  * @port:		Port information.
- * @monitor_time_info:	Timer to monitor ports.
+ * @monitor_timer_info:	Timer to monitor ports.
  * @proc_sem:		Semaphore for proc accessing.
  * @id:			Device ID.
  * @mii_if:		MII interface information.
@@ -1566,6 +1567,7 @@ static inline void hw_restore_intr(struct ksz_hw *hw, uint interrupt)
 
 /**
  * hw_block_intr - block hardware interrupts
+ * @hw: The hardware instance.
  *
  * This function blocks all interrupts of the hardware and returns the current
  * interrupt enable mask so that interrupts can be restored later.
@@ -1649,8 +1651,7 @@ static inline void set_tx_len(struct ksz_desc *desc, u32 len)
 
 #define HW_DELAY(hw, reg)			\
 	do {					\
-		u16 dummy;			\
-		dummy = readw(hw->io + reg);	\
+		readw(hw->io + reg);		\
 	} while (0)
 
 /**
@@ -1819,6 +1820,7 @@ static void port_r_mib_cnt(struct ksz_hw *hw, int port, u16 addr, u64 *cnt)
  * port_r_mib_pkt - read dropped packet counts
  * @hw: 	The hardware instance.
  * @port:	The port index.
+ * @last:	last one
  * @cnt:	Buffer to store the receive and transmit dropped packet counts.
  *
  * This routine reads the dropped packet counts of the port.
@@ -1972,7 +1974,7 @@ static void port_cfg(struct ksz_hw *hw, int port, int offset, u16 bits,
  * port_chk_shift - check port bit
  * @hw: 	The hardware instance.
  * @port:	The port index.
- * @offset:	The offset of the register.
+ * @addr:	The offset of the register.
  * @shift:	Number of bits to shift.
  *
  * This function checks whether the specified port is set in the register or
@@ -1994,7 +1996,7 @@ static int port_chk_shift(struct ksz_hw *hw, int port, u32 addr, int shift)
  * port_cfg_shift - set port bit
  * @hw: 	The hardware instance.
  * @port:	The port index.
- * @offset:	The offset of the register.
+ * @addr:	The offset of the register.
  * @shift:	Number of bits to shift.
  * @set:	The flag indicating whether the port is to be set or not.
  *
@@ -4425,6 +4427,8 @@ static int ksz_alloc_desc(struct dev_info *adapter)
 /**
  * free_dma_buf - release DMA buffer resources
  * @adapter:	Adapter information structure.
+ * @dma_buf:	pointer to buf
+ * @direction:	to or from device
  *
  * This routine is just a helper function to release the DMA buffer resources.
  */
@@ -4562,6 +4566,7 @@ static void ksz_free_desc(struct dev_info *adapter)
  * ksz_free_buffers - free buffers used in the descriptors
  * @adapter:	Adapter information structure.
  * @desc_info:	Descriptor information structure.
+ * @direction:	to or from device
  *
  * This local routine frees buffers used in the DMA buffers.
  */
@@ -4721,7 +4726,8 @@ static void send_packet(struct sk_buff *skb, struct net_device *dev)
 
 /**
  * transmit_cleanup - clean up transmit descriptors
- * @dev:	Network device.
+ * @hw_priv:	Network device.
+ * @normal:	break if owned
  *
  * This routine is called to clean up the transmitted buffers.
  */
@@ -4777,7 +4783,7 @@ static void transmit_cleanup(struct dev_info *hw_priv, int normal)
 
 /**
  * transmit_done - transmit done processing
- * @dev:	Network device.
+ * @hw_priv:	Network device.
  *
  * This routine is called when the transmit interrupt is triggered, indicating
  * either a packet is sent successfully or there are transmit errors.
@@ -4883,6 +4889,7 @@ unlock:
 /**
  * netdev_tx_timeout - transmit timeout processing
  * @dev:	Network device.
+ * @txqueue:	index of hanging queue
  *
  * This routine is called when the transmit timer expires.  That indicates the
  * hardware is not running correctly because transmit interrupts are not
@@ -5826,8 +5833,7 @@ static int netdev_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	/* Get address of MII PHY in use. */
 	case SIOCGMIIPHY:
 		data->phy_id = priv->id;
-
-		/* Fallthrough... */
+		fallthrough;
 
 	/* Read MII PHY register. */
 	case SIOCGMIIREG:
@@ -6075,14 +6081,6 @@ static void netdev_get_drvinfo(struct net_device *dev,
 		sizeof(info->bus_info));
 }
 
-/**
- * netdev_get_regs_len - get length of register dump
- * @dev:	Network device.
- *
- * This function returns the length of the register dump.
- *
- * Return length of the register dump.
- */
 static struct hw_regs {
 	int start;
 	int end;
@@ -6096,6 +6094,14 @@ static struct hw_regs {
 	{ 0, 0 }
 };
 
+/**
+ * netdev_get_regs_len - get length of register dump
+ * @dev:	Network device.
+ *
+ * This function returns the length of the register dump.
+ *
+ * Return length of the register dump.
+ */
 static int netdev_get_regs_len(struct net_device *dev)
 {
 	struct hw_regs *range = hw_regs_range;
@@ -6237,6 +6243,8 @@ static int netdev_get_eeprom_len(struct net_device *dev)
 	return EEPROM_SIZE * 2;
 }
 
+#define EEPROM_MAGIC			0x10A18842
+
 /**
  * netdev_get_eeprom - get EEPROM data
  * @dev:	Network device.
@@ -6247,8 +6255,6 @@ static int netdev_get_eeprom_len(struct net_device *dev)
  *
  * Return 0 if successful; otherwise an error code.
  */
-#define EEPROM_MAGIC			0x10A18842
-
 static int netdev_get_eeprom(struct net_device *dev,
 	struct ethtool_eeprom *eeprom, u8 *data)
 {
@@ -6385,7 +6391,7 @@ static int netdev_set_pauseparam(struct net_device *dev,
 /**
  * netdev_get_ringparam - get tx/rx ring parameters
  * @dev:	Network device.
- * @pause:	Ethtool RING settings data structure.
+ * @ring:	Ethtool RING settings data structure.
  *
  * This procedure returns the TX/RX ring settings.
  */
@@ -6689,7 +6695,7 @@ static void mib_monitor(struct timer_list *t)
 
 /**
  * dev_monitor - periodic monitoring
- * @ptr:	Network device pointer.
+ * @t:	timer list containing a network device pointer.
  *
  * This routine is run in a kernel timer to monitor the network device.
  */
diff --git a/drivers/net/ethernet/microchip/encx24j600-regmap.c b/drivers/net/ethernet/microchip/encx24j600-regmap.c
index 5bd7fb917b7a..796e46a53926 100644
--- a/drivers/net/ethernet/microchip/encx24j600-regmap.c
+++ b/drivers/net/ethernet/microchip/encx24j600-regmap.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0-only
-/**
+/*
  * Register map access API - ENCX24J600 support
  *
  * Copyright 2015 Gridpoint
diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c
index de93cc6ebc1a..a1938842f828 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.c
+++ b/drivers/net/ethernet/microchip/lan743x_main.c
@@ -158,9 +158,8 @@ static void lan743x_tx_isr(void *context, u32 int_sts, u32 flags)
 	struct lan743x_tx *tx = context;
 	struct lan743x_adapter *adapter = tx->adapter;
 	bool enable_flag = true;
-	u32 int_en = 0;
 
-	int_en = lan743x_csr_read(adapter, INT_EN_SET);
+	lan743x_csr_read(adapter, INT_EN_SET);
 	if (flags & LAN743X_VECTOR_FLAG_SOURCE_ENABLE_CLEAR) {
 		lan743x_csr_write(adapter, INT_EN_CLR,
 				  INT_BIT_DMA_TX_(tx->channel_number));
@@ -1699,10 +1698,9 @@ static int lan743x_tx_napi_poll(struct napi_struct *napi, int weight)
 	bool start_transmitter = false;
 	unsigned long irq_flags = 0;
 	u32 ioc_bit = 0;
-	u32 int_sts = 0;
 
 	ioc_bit = DMAC_INT_BIT_TX_IOC_(tx->channel_number);
-	int_sts = lan743x_csr_read(adapter, DMAC_INT_STS);
+	lan743x_csr_read(adapter, DMAC_INT_STS);
 	if (tx->vector_flags & LAN743X_VECTOR_FLAG_SOURCE_STATUS_W2C)
 		lan743x_csr_write(adapter, DMAC_INT_STS, ioc_bit);
 	spin_lock_irqsave(&tx->ring_lock, irq_flags);
@@ -3038,7 +3036,6 @@ static int lan743x_pm_suspend(struct device *dev)
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct net_device *netdev = pci_get_drvdata(pdev);
 	struct lan743x_adapter *adapter = netdev_priv(netdev);
-	int ret;
 
 	lan743x_pcidev_shutdown(pdev);
 
@@ -3051,9 +3048,7 @@ static int lan743x_pm_suspend(struct device *dev)
 		lan743x_pm_set_wol(adapter);
 
 	/* Host sets PME_En, put D3hot */
-	ret = pci_prepare_to_sleep(pdev);
-
-	return 0;
+	return pci_prepare_to_sleep(pdev);;
 }
 
 static int lan743x_pm_resume(struct device *dev)
diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index 5abb7d2b0a9e..e026617d6133 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -5,6 +5,7 @@
  * Copyright (c) 2017 Microsemi Corporation
  */
 #include <linux/if_bridge.h>
+#include <soc/mscc/ocelot_vcap.h>
 #include "ocelot.h"
 #include "ocelot_vcap.h"
 
@@ -107,6 +108,13 @@ static void ocelot_vcap_enable(struct ocelot *ocelot, int port)
 	ocelot_write_gix(ocelot, ANA_PORT_VCAP_S2_CFG_S2_ENA |
 			 ANA_PORT_VCAP_S2_CFG_S2_IP6_CFG(0xa),
 			 ANA_PORT_VCAP_S2_CFG, port);
+
+	ocelot_write_gix(ocelot, ANA_PORT_VCAP_CFG_S1_ENA,
+			 ANA_PORT_VCAP_CFG, port);
+
+	ocelot_rmw_gix(ocelot, REW_PORT_CFG_ES0_EN,
+		       REW_PORT_CFG_ES0_EN,
+		       REW_PORT_CFG, port);
 }
 
 static inline u32 ocelot_vlant_read_vlanaccess(struct ocelot *ocelot)
@@ -413,21 +421,20 @@ void ocelot_port_disable(struct ocelot *ocelot, int port)
 }
 EXPORT_SYMBOL(ocelot_port_disable);
 
-int ocelot_port_add_txtstamp_skb(struct ocelot_port *ocelot_port,
-				 struct sk_buff *skb)
+void ocelot_port_add_txtstamp_skb(struct ocelot *ocelot, int port,
+				  struct sk_buff *clone)
 {
-	struct skb_shared_info *shinfo = skb_shinfo(skb);
-	struct ocelot *ocelot = ocelot_port->ocelot;
-
-	if (ocelot->ptp && shinfo->tx_flags & SKBTX_HW_TSTAMP &&
-	    ocelot_port->ptp_cmd == IFH_REW_OP_TWO_STEP_PTP) {
-		shinfo->tx_flags |= SKBTX_IN_PROGRESS;
-		/* Store timestamp ID in cb[0] of sk_buff */
-		skb->cb[0] = ocelot_port->ts_id % 4;
-		skb_queue_tail(&ocelot_port->tx_skbs, skb);
-		return 0;
-	}
-	return -ENODATA;
+	struct ocelot_port *ocelot_port = ocelot->ports[port];
+
+	spin_lock(&ocelot_port->ts_id_lock);
+
+	skb_shinfo(clone)->tx_flags |= SKBTX_IN_PROGRESS;
+	/* Store timestamp ID in cb[0] of sk_buff */
+	clone->cb[0] = ocelot_port->ts_id;
+	ocelot_port->ts_id = (ocelot_port->ts_id + 1) % 4;
+	skb_queue_tail(&ocelot_port->tx_skbs, clone);
+
+	spin_unlock(&ocelot_port->ts_id_lock);
 }
 EXPORT_SYMBOL(ocelot_port_add_txtstamp_skb);
 
@@ -506,9 +513,7 @@ void ocelot_get_txtstamp(struct ocelot *ocelot)
 		/* Set the timestamp into the skb */
 		memset(&shhwtstamps, 0, sizeof(shhwtstamps));
 		shhwtstamps.hwtstamp = ktime_set(ts.tv_sec, ts.tv_nsec);
-		skb_tstamp_tx(skb_match, &shhwtstamps);
-
-		dev_kfree_skb_any(skb_match);
+		skb_complete_tx_timestamp(skb_match, &shhwtstamps);
 
 		/* Next ts */
 		ocelot_write(ocelot, SYS_PTP_NXT_PTP_NXT, SYS_PTP_NXT);
@@ -1300,6 +1305,7 @@ void ocelot_init_port(struct ocelot *ocelot, int port)
 	struct ocelot_port *ocelot_port = ocelot->ports[port];
 
 	skb_queue_head_init(&ocelot_port->tx_skbs);
+	spin_lock_init(&ocelot_port->ts_id_lock);
 
 	/* Basic L2 initialization */
 
@@ -1348,22 +1354,14 @@ void ocelot_init_port(struct ocelot *ocelot, int port)
 }
 EXPORT_SYMBOL(ocelot_init_port);
 
-/* Configure and enable the CPU port module, which is a set of queues.
- * If @npi contains a valid port index, the CPU port module is connected
- * to the Node Processor Interface (NPI). This is the mode through which
- * frames can be injected from and extracted to an external CPU,
- * over Ethernet.
+/* Configure and enable the CPU port module, which is a set of queues
+ * accessible through register MMIO, frame DMA or Ethernet (in case
+ * NPI mode is used).
  */
-void ocelot_configure_cpu(struct ocelot *ocelot, int npi,
-			  enum ocelot_tag_prefix injection,
-			  enum ocelot_tag_prefix extraction)
+static void ocelot_cpu_port_init(struct ocelot *ocelot)
 {
 	int cpu = ocelot->num_phys_ports;
 
-	ocelot->npi = npi;
-	ocelot->inj_prefix = injection;
-	ocelot->xtr_prefix = extraction;
-
 	/* The unicast destination PGID for the CPU port module is unused */
 	ocelot_write_rix(ocelot, 0, ANA_PGID_PGID, cpu);
 	/* Instead set up a multicast destination PGID for traffic copied to
@@ -1375,31 +1373,13 @@ void ocelot_configure_cpu(struct ocelot *ocelot, int npi,
 			 ANA_PORT_PORT_CFG_PORTID_VAL(cpu),
 			 ANA_PORT_PORT_CFG, cpu);
 
-	if (npi >= 0 && npi < ocelot->num_phys_ports) {
-		ocelot_write(ocelot, QSYS_EXT_CPU_CFG_EXT_CPUQ_MSK_M |
-			     QSYS_EXT_CPU_CFG_EXT_CPU_PORT(npi),
-			     QSYS_EXT_CPU_CFG);
-
-		/* Enable NPI port */
-		ocelot_fields_write(ocelot, npi,
-				    QSYS_SWITCH_PORT_MODE_PORT_ENA, 1);
-		/* NPI port Injection/Extraction configuration */
-		ocelot_fields_write(ocelot, npi, SYS_PORT_MODE_INCL_XTR_HDR,
-				    extraction);
-		ocelot_fields_write(ocelot, npi, SYS_PORT_MODE_INCL_INJ_HDR,
-				    injection);
-
-		/* Disable transmission of pause frames */
-		ocelot_fields_write(ocelot, npi, SYS_PAUSE_CFG_PAUSE_ENA, 0);
-	}
-
 	/* Enable CPU port module */
 	ocelot_fields_write(ocelot, cpu, QSYS_SWITCH_PORT_MODE_PORT_ENA, 1);
 	/* CPU port Injection/Extraction configuration */
 	ocelot_fields_write(ocelot, cpu, SYS_PORT_MODE_INCL_XTR_HDR,
-			    extraction);
+			    ocelot->xtr_prefix);
 	ocelot_fields_write(ocelot, cpu, SYS_PORT_MODE_INCL_INJ_HDR,
-			    injection);
+			    ocelot->inj_prefix);
 
 	/* Configure the CPU port to be VLAN aware */
 	ocelot_write_gix(ocelot, ANA_PORT_VLAN_CFG_VLAN_VID(0) |
@@ -1407,7 +1387,6 @@ void ocelot_configure_cpu(struct ocelot *ocelot, int npi,
 				 ANA_PORT_VLAN_CFG_VLAN_POP_CNT(1),
 			 ANA_PORT_VLAN_CFG, cpu);
 }
-EXPORT_SYMBOL(ocelot_configure_cpu);
 
 int ocelot_init(struct ocelot *ocelot)
 {
@@ -1447,6 +1426,7 @@ int ocelot_init(struct ocelot *ocelot)
 	ocelot_mact_init(ocelot);
 	ocelot_vlan_init(ocelot);
 	ocelot_vcap_init(ocelot);
+	ocelot_cpu_port_init(ocelot);
 
 	for (port = 0; port < ocelot->num_phys_ports; port++) {
 		/* Clear all counters (5 groups) */
@@ -1544,18 +1524,18 @@ EXPORT_SYMBOL(ocelot_init);
 
 void ocelot_deinit(struct ocelot *ocelot)
 {
-	struct ocelot_port *port;
-	int i;
-
 	cancel_delayed_work(&ocelot->stats_work);
 	destroy_workqueue(ocelot->stats_queue);
 	mutex_destroy(&ocelot->stats_lock);
-
-	for (i = 0; i < ocelot->num_phys_ports; i++) {
-		port = ocelot->ports[i];
-		skb_queue_purge(&port->tx_skbs);
-	}
 }
 EXPORT_SYMBOL(ocelot_deinit);
 
+void ocelot_deinit_port(struct ocelot *ocelot, int port)
+{
+	struct ocelot_port *ocelot_port = ocelot->ports[port];
+
+	skb_queue_purge(&ocelot_port->tx_skbs);
+}
+EXPORT_SYMBOL(ocelot_deinit_port);
+
 MODULE_LICENSE("Dual MIT/GPL");
diff --git a/drivers/net/ethernet/mscc/ocelot.h b/drivers/net/ethernet/mscc/ocelot.h
index dc29e05103a1..abb407dff93c 100644
--- a/drivers/net/ethernet/mscc/ocelot.h
+++ b/drivers/net/ethernet/mscc/ocelot.h
@@ -98,6 +98,8 @@ int ocelot_port_lag_join(struct ocelot *ocelot, int port,
 			 struct net_device *bond);
 void ocelot_port_lag_leave(struct ocelot *ocelot, int port,
 			   struct net_device *bond);
+struct net_device *ocelot_port_to_netdev(struct ocelot *ocelot, int port);
+int ocelot_netdev_to_port(struct net_device *dev);
 
 u32 ocelot_port_readl(struct ocelot_port *port, u32 reg);
 void ocelot_port_writel(struct ocelot_port *port, u32 val, u32 reg);
diff --git a/drivers/net/ethernet/mscc/ocelot_flower.c b/drivers/net/ethernet/mscc/ocelot_flower.c
index ec1b6e2572ba..0ea6d4f411cb 100644
--- a/drivers/net/ethernet/mscc/ocelot_flower.c
+++ b/drivers/net/ethernet/mscc/ocelot_flower.c
@@ -5,56 +5,410 @@
 
 #include <net/pkt_cls.h>
 #include <net/tc_act/tc_gact.h>
-
+#include <soc/mscc/ocelot_vcap.h>
 #include "ocelot_vcap.h"
 
-static int ocelot_flower_parse_action(struct flow_cls_offload *f,
+/* Arbitrarily chosen constants for encoding the VCAP block and lookup number
+ * into the chain number. This is UAPI.
+ */
+#define VCAP_BLOCK			10000
+#define VCAP_LOOKUP			1000
+#define VCAP_IS1_NUM_LOOKUPS		3
+#define VCAP_IS2_NUM_LOOKUPS		2
+#define VCAP_IS2_NUM_PAG		256
+#define VCAP_IS1_CHAIN(lookup)		\
+	(1 * VCAP_BLOCK + (lookup) * VCAP_LOOKUP)
+#define VCAP_IS2_CHAIN(lookup, pag)	\
+	(2 * VCAP_BLOCK + (lookup) * VCAP_LOOKUP + (pag))
+
+static int ocelot_chain_to_block(int chain, bool ingress)
+{
+	int lookup, pag;
+
+	if (!ingress) {
+		if (chain == 0)
+			return VCAP_ES0;
+		return -EOPNOTSUPP;
+	}
+
+	/* Backwards compatibility with older, single-chain tc-flower
+	 * offload support in Ocelot
+	 */
+	if (chain == 0)
+		return VCAP_IS2;
+
+	for (lookup = 0; lookup < VCAP_IS1_NUM_LOOKUPS; lookup++)
+		if (chain == VCAP_IS1_CHAIN(lookup))
+			return VCAP_IS1;
+
+	for (lookup = 0; lookup < VCAP_IS2_NUM_LOOKUPS; lookup++)
+		for (pag = 0; pag < VCAP_IS2_NUM_PAG; pag++)
+			if (chain == VCAP_IS2_CHAIN(lookup, pag))
+				return VCAP_IS2;
+
+	return -EOPNOTSUPP;
+}
+
+/* Caller must ensure this is a valid IS1 or IS2 chain first,
+ * by calling ocelot_chain_to_block.
+ */
+static int ocelot_chain_to_lookup(int chain)
+{
+	return (chain / VCAP_LOOKUP) % 10;
+}
+
+/* Caller must ensure this is a valid IS2 chain first,
+ * by calling ocelot_chain_to_block.
+ */
+static int ocelot_chain_to_pag(int chain)
+{
+	int lookup = ocelot_chain_to_lookup(chain);
+
+	/* calculate PAG value as chain index relative to the first PAG */
+	return chain - VCAP_IS2_CHAIN(lookup, 0);
+}
+
+static bool ocelot_is_goto_target_valid(int goto_target, int chain,
+					bool ingress)
+{
+	int pag;
+
+	/* Can't offload GOTO in VCAP ES0 */
+	if (!ingress)
+		return (goto_target < 0);
+
+	/* Non-optional GOTOs */
+	if (chain == 0)
+		/* VCAP IS1 can be skipped, either partially or completely */
+		return (goto_target == VCAP_IS1_CHAIN(0) ||
+			goto_target == VCAP_IS1_CHAIN(1) ||
+			goto_target == VCAP_IS1_CHAIN(2) ||
+			goto_target == VCAP_IS2_CHAIN(0, 0) ||
+			goto_target == VCAP_IS2_CHAIN(1, 0));
+
+	if (chain == VCAP_IS1_CHAIN(0))
+		return (goto_target == VCAP_IS1_CHAIN(1));
+
+	if (chain == VCAP_IS1_CHAIN(1))
+		return (goto_target == VCAP_IS1_CHAIN(2));
+
+	/* Lookup 2 of VCAP IS1 can really support non-optional GOTOs,
+	 * using a Policy Association Group (PAG) value, which is an 8-bit
+	 * value encoding a VCAP IS2 target chain.
+	 */
+	if (chain == VCAP_IS1_CHAIN(2)) {
+		for (pag = 0; pag < VCAP_IS2_NUM_PAG; pag++)
+			if (goto_target == VCAP_IS2_CHAIN(0, pag))
+				return true;
+
+		return false;
+	}
+
+	/* Non-optional GOTO from VCAP IS2 lookup 0 to lookup 1.
+	 * We cannot change the PAG at this point.
+	 */
+	for (pag = 0; pag < VCAP_IS2_NUM_PAG; pag++)
+		if (chain == VCAP_IS2_CHAIN(0, pag))
+			return (goto_target == VCAP_IS2_CHAIN(1, pag));
+
+	/* VCAP IS2 lookup 1 cannot jump anywhere */
+	return false;
+}
+
+static struct ocelot_vcap_filter *
+ocelot_find_vcap_filter_that_points_at(struct ocelot *ocelot, int chain)
+{
+	struct ocelot_vcap_filter *filter;
+	struct ocelot_vcap_block *block;
+	int block_id;
+
+	block_id = ocelot_chain_to_block(chain, true);
+	if (block_id < 0)
+		return NULL;
+
+	if (block_id == VCAP_IS2) {
+		block = &ocelot->block[VCAP_IS1];
+
+		list_for_each_entry(filter, &block->rules, list)
+			if (filter->type == OCELOT_VCAP_FILTER_PAG &&
+			    filter->goto_target == chain)
+				return filter;
+	}
+
+	list_for_each_entry(filter, &ocelot->dummy_rules, list)
+		if (filter->goto_target == chain)
+			return filter;
+
+	return NULL;
+}
+
+static int ocelot_flower_parse_action(struct ocelot *ocelot, bool ingress,
+				      struct flow_cls_offload *f,
 				      struct ocelot_vcap_filter *filter)
 {
+	struct netlink_ext_ack *extack = f->common.extack;
+	bool allow_missing_goto_target = false;
 	const struct flow_action_entry *a;
+	enum ocelot_tag_tpid_sel tpid;
+	int i, chain, egress_port;
 	u64 rate;
-	int i;
-
-	if (!flow_offload_has_one_action(&f->rule->action))
-		return -EOPNOTSUPP;
 
 	if (!flow_action_basic_hw_stats_check(&f->rule->action,
 					      f->common.extack))
 		return -EOPNOTSUPP;
 
+	chain = f->common.chain_index;
+	filter->block_id = ocelot_chain_to_block(chain, ingress);
+	if (filter->block_id < 0) {
+		NL_SET_ERR_MSG_MOD(extack, "Cannot offload to this chain");
+		return -EOPNOTSUPP;
+	}
+	if (filter->block_id == VCAP_IS1 || filter->block_id == VCAP_IS2)
+		filter->lookup = ocelot_chain_to_lookup(chain);
+	if (filter->block_id == VCAP_IS2)
+		filter->pag = ocelot_chain_to_pag(chain);
+
+	filter->goto_target = -1;
+	filter->type = OCELOT_VCAP_FILTER_DUMMY;
+
 	flow_action_for_each(i, a, &f->rule->action) {
 		switch (a->id) {
 		case FLOW_ACTION_DROP:
-			filter->action = OCELOT_VCAP_ACTION_DROP;
+			if (filter->block_id != VCAP_IS2) {
+				NL_SET_ERR_MSG_MOD(extack,
+						   "Drop action can only be offloaded to VCAP IS2");
+				return -EOPNOTSUPP;
+			}
+			if (filter->goto_target != -1) {
+				NL_SET_ERR_MSG_MOD(extack,
+						   "Last action must be GOTO");
+				return -EOPNOTSUPP;
+			}
+			filter->action.mask_mode = OCELOT_MASK_MODE_PERMIT_DENY;
+			filter->action.port_mask = 0;
+			filter->action.police_ena = true;
+			filter->action.pol_ix = OCELOT_POLICER_DISCARD;
+			filter->type = OCELOT_VCAP_FILTER_OFFLOAD;
 			break;
 		case FLOW_ACTION_TRAP:
-			filter->action = OCELOT_VCAP_ACTION_TRAP;
+			if (filter->block_id != VCAP_IS2) {
+				NL_SET_ERR_MSG_MOD(extack,
+						   "Trap action can only be offloaded to VCAP IS2");
+				return -EOPNOTSUPP;
+			}
+			if (filter->goto_target != -1) {
+				NL_SET_ERR_MSG_MOD(extack,
+						   "Last action must be GOTO");
+				return -EOPNOTSUPP;
+			}
+			filter->action.mask_mode = OCELOT_MASK_MODE_PERMIT_DENY;
+			filter->action.port_mask = 0;
+			filter->action.cpu_copy_ena = true;
+			filter->action.cpu_qu_num = 0;
+			filter->type = OCELOT_VCAP_FILTER_OFFLOAD;
 			break;
 		case FLOW_ACTION_POLICE:
-			filter->action = OCELOT_VCAP_ACTION_POLICE;
+			if (filter->block_id != VCAP_IS2 ||
+			    filter->lookup != 0) {
+				NL_SET_ERR_MSG_MOD(extack,
+						   "Police action can only be offloaded to VCAP IS2 lookup 0");
+				return -EOPNOTSUPP;
+			}
+			if (filter->goto_target != -1) {
+				NL_SET_ERR_MSG_MOD(extack,
+						   "Last action must be GOTO");
+				return -EOPNOTSUPP;
+			}
+			filter->action.police_ena = true;
 			rate = a->police.rate_bytes_ps;
-			filter->pol.rate = div_u64(rate, 1000) * 8;
-			filter->pol.burst = a->police.burst;
+			filter->action.pol.rate = div_u64(rate, 1000) * 8;
+			filter->action.pol.burst = a->police.burst;
+			filter->type = OCELOT_VCAP_FILTER_OFFLOAD;
+			break;
+		case FLOW_ACTION_REDIRECT:
+			if (filter->block_id != VCAP_IS2) {
+				NL_SET_ERR_MSG_MOD(extack,
+						   "Redirect action can only be offloaded to VCAP IS2");
+				return -EOPNOTSUPP;
+			}
+			if (filter->goto_target != -1) {
+				NL_SET_ERR_MSG_MOD(extack,
+						   "Last action must be GOTO");
+				return -EOPNOTSUPP;
+			}
+			egress_port = ocelot->ops->netdev_to_port(a->dev);
+			if (egress_port < 0) {
+				NL_SET_ERR_MSG_MOD(extack,
+						   "Destination not an ocelot port");
+				return -EOPNOTSUPP;
+			}
+			filter->action.mask_mode = OCELOT_MASK_MODE_REDIRECT;
+			filter->action.port_mask = BIT(egress_port);
+			filter->type = OCELOT_VCAP_FILTER_OFFLOAD;
+			break;
+		case FLOW_ACTION_VLAN_POP:
+			if (filter->block_id != VCAP_IS1) {
+				NL_SET_ERR_MSG_MOD(extack,
+						   "VLAN pop action can only be offloaded to VCAP IS1");
+				return -EOPNOTSUPP;
+			}
+			if (filter->goto_target != -1) {
+				NL_SET_ERR_MSG_MOD(extack,
+						   "Last action must be GOTO");
+				return -EOPNOTSUPP;
+			}
+			filter->action.vlan_pop_cnt_ena = true;
+			filter->action.vlan_pop_cnt++;
+			if (filter->action.vlan_pop_cnt > 2) {
+				NL_SET_ERR_MSG_MOD(extack,
+						   "Cannot pop more than 2 VLAN headers");
+				return -EOPNOTSUPP;
+			}
+			filter->type = OCELOT_VCAP_FILTER_OFFLOAD;
+			break;
+		case FLOW_ACTION_PRIORITY:
+			if (filter->block_id != VCAP_IS1) {
+				NL_SET_ERR_MSG_MOD(extack,
+						   "Priority action can only be offloaded to VCAP IS1");
+				return -EOPNOTSUPP;
+			}
+			if (filter->goto_target != -1) {
+				NL_SET_ERR_MSG_MOD(extack,
+						   "Last action must be GOTO");
+				return -EOPNOTSUPP;
+			}
+			filter->action.qos_ena = true;
+			filter->action.qos_val = a->priority;
+			filter->type = OCELOT_VCAP_FILTER_OFFLOAD;
+			break;
+		case FLOW_ACTION_GOTO:
+			filter->goto_target = a->chain_index;
+
+			if (filter->block_id == VCAP_IS1 && filter->lookup == 2) {
+				int pag = ocelot_chain_to_pag(filter->goto_target);
+
+				filter->action.pag_override_mask = 0xff;
+				filter->action.pag_val = pag;
+				filter->type = OCELOT_VCAP_FILTER_PAG;
+			}
+			break;
+		case FLOW_ACTION_VLAN_PUSH:
+			if (filter->block_id != VCAP_ES0) {
+				NL_SET_ERR_MSG_MOD(extack,
+						   "VLAN push action can only be offloaded to VCAP ES0");
+				return -EOPNOTSUPP;
+			}
+			switch (ntohs(a->vlan.proto)) {
+			case ETH_P_8021Q:
+				tpid = OCELOT_TAG_TPID_SEL_8021Q;
+				break;
+			case ETH_P_8021AD:
+				tpid = OCELOT_TAG_TPID_SEL_8021AD;
+				break;
+			default:
+				NL_SET_ERR_MSG_MOD(extack,
+						   "Cannot push custom TPID");
+				return -EOPNOTSUPP;
+			}
+			filter->action.tag_a_tpid_sel = tpid;
+			filter->action.push_outer_tag = OCELOT_ES0_TAG;
+			filter->action.tag_a_vid_sel = 1;
+			filter->action.vid_a_val = a->vlan.vid;
+			filter->action.pcp_a_val = a->vlan.prio;
+			filter->type = OCELOT_VCAP_FILTER_OFFLOAD;
 			break;
 		default:
+			NL_SET_ERR_MSG_MOD(extack, "Cannot offload action");
 			return -EOPNOTSUPP;
 		}
 	}
 
+	if (filter->goto_target == -1) {
+		if ((filter->block_id == VCAP_IS2 && filter->lookup == 1) ||
+		    chain == 0) {
+			allow_missing_goto_target = true;
+		} else {
+			NL_SET_ERR_MSG_MOD(extack, "Missing GOTO action");
+			return -EOPNOTSUPP;
+		}
+	}
+
+	if (!ocelot_is_goto_target_valid(filter->goto_target, chain, ingress) &&
+	    !allow_missing_goto_target) {
+		NL_SET_ERR_MSG_MOD(extack, "Cannot offload this GOTO target");
+		return -EOPNOTSUPP;
+	}
+
 	return 0;
 }
 
-static int ocelot_flower_parse(struct flow_cls_offload *f,
-			       struct ocelot_vcap_filter *filter)
+static int ocelot_flower_parse_indev(struct ocelot *ocelot, int port,
+				     struct flow_cls_offload *f,
+				     struct ocelot_vcap_filter *filter)
+{
+	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
+	const struct vcap_props *vcap = &ocelot->vcap[VCAP_ES0];
+	int key_length = vcap->keys[VCAP_ES0_IGR_PORT].length;
+	struct netlink_ext_ack *extack = f->common.extack;
+	struct net_device *dev, *indev;
+	struct flow_match_meta match;
+	int ingress_port;
+
+	flow_rule_match_meta(rule, &match);
+
+	if (!match.mask->ingress_ifindex)
+		return 0;
+
+	if (match.mask->ingress_ifindex != 0xFFFFFFFF) {
+		NL_SET_ERR_MSG_MOD(extack, "Unsupported ingress ifindex mask");
+		return -EOPNOTSUPP;
+	}
+
+	dev = ocelot->ops->port_to_netdev(ocelot, port);
+	if (!dev)
+		return -EINVAL;
+
+	indev = __dev_get_by_index(dev_net(dev), match.key->ingress_ifindex);
+	if (!indev) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Can't find the ingress port to match on");
+		return -ENOENT;
+	}
+
+	ingress_port = ocelot->ops->netdev_to_port(indev);
+	if (ingress_port < 0) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Can only offload an ocelot ingress port");
+		return -EOPNOTSUPP;
+	}
+	if (ingress_port == port) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Ingress port is equal to the egress port");
+		return -EINVAL;
+	}
+
+	filter->ingress_port.value = ingress_port;
+	filter->ingress_port.mask = GENMASK(key_length - 1, 0);
+
+	return 0;
+}
+
+static int
+ocelot_flower_parse_key(struct ocelot *ocelot, int port, bool ingress,
+			struct flow_cls_offload *f,
+			struct ocelot_vcap_filter *filter)
 {
 	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
 	struct flow_dissector *dissector = rule->match.dissector;
+	struct netlink_ext_ack *extack = f->common.extack;
 	u16 proto = ntohs(f->common.protocol);
 	bool match_protocol = true;
+	int ret;
 
 	if (dissector->used_keys &
 	    ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) |
 	      BIT(FLOW_DISSECTOR_KEY_BASIC) |
+	      BIT(FLOW_DISSECTOR_KEY_META) |
 	      BIT(FLOW_DISSECTOR_KEY_PORTS) |
 	      BIT(FLOW_DISSECTOR_KEY_VLAN) |
 	      BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) |
@@ -63,6 +417,13 @@ static int ocelot_flower_parse(struct flow_cls_offload *f,
 		return -EOPNOTSUPP;
 	}
 
+	/* For VCAP ES0 (egress rewriter) we can match on the ingress port */
+	if (!ingress) {
+		ret = ocelot_flower_parse_indev(ocelot, port, f, filter);
+		if (ret)
+			return ret;
+	}
+
 	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) {
 		struct flow_match_control match;
 
@@ -72,6 +433,19 @@ static int ocelot_flower_parse(struct flow_cls_offload *f,
 	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
 		struct flow_match_eth_addrs match;
 
+		if (filter->block_id == VCAP_ES0) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "VCAP ES0 cannot match on MAC address");
+			return -EOPNOTSUPP;
+		}
+
+		if (filter->block_id == VCAP_IS1 &&
+		    !is_zero_ether_addr(match.mask->dst)) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Key type S1_NORMAL cannot match on destination MAC");
+			return -EOPNOTSUPP;
+		}
+
 		/* The hw support mac matches only for MAC_ETYPE key,
 		 * therefore if other matches(port, tcp flags, etc) are added
 		 * then just bail out
@@ -103,6 +477,12 @@ static int ocelot_flower_parse(struct flow_cls_offload *f,
 
 		flow_rule_match_basic(rule, &match);
 		if (ntohs(match.key->n_proto) == ETH_P_IP) {
+			if (filter->block_id == VCAP_ES0) {
+				NL_SET_ERR_MSG_MOD(extack,
+						   "VCAP ES0 cannot match on IP protocol");
+				return -EOPNOTSUPP;
+			}
+
 			filter->key_type = OCELOT_VCAP_KEY_IPV4;
 			filter->key.ipv4.proto.value[0] =
 				match.key->ip_proto;
@@ -111,6 +491,12 @@ static int ocelot_flower_parse(struct flow_cls_offload *f,
 			match_protocol = false;
 		}
 		if (ntohs(match.key->n_proto) == ETH_P_IPV6) {
+			if (filter->block_id == VCAP_ES0) {
+				NL_SET_ERR_MSG_MOD(extack,
+						   "VCAP ES0 cannot match on IP protocol");
+				return -EOPNOTSUPP;
+			}
+
 			filter->key_type = OCELOT_VCAP_KEY_IPV6;
 			filter->key.ipv6.proto.value[0] =
 				match.key->ip_proto;
@@ -125,6 +511,18 @@ static int ocelot_flower_parse(struct flow_cls_offload *f,
 		struct flow_match_ipv4_addrs match;
 		u8 *tmp;
 
+		if (filter->block_id == VCAP_ES0) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "VCAP ES0 cannot match on IP address");
+			return -EOPNOTSUPP;
+		}
+
+		if (filter->block_id == VCAP_IS1 && *(u32 *)&match.mask->dst) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Key type S1_NORMAL cannot match on destination IP");
+			return -EOPNOTSUPP;
+		}
+
 		flow_rule_match_ipv4_addrs(rule, &match);
 		tmp = &filter->key.ipv4.sip.value.addr[0];
 		memcpy(tmp, &match.key->src, 4);
@@ -148,6 +546,12 @@ static int ocelot_flower_parse(struct flow_cls_offload *f,
 	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS)) {
 		struct flow_match_ports match;
 
+		if (filter->block_id == VCAP_ES0) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "VCAP ES0 cannot match on L4 ports");
+			return -EOPNOTSUPP;
+		}
+
 		flow_rule_match_ports(rule, &match);
 		filter->key.ipv4.sport.value = ntohs(match.key->src);
 		filter->key.ipv4.sport.mask = ntohs(match.mask->src);
@@ -170,6 +574,12 @@ static int ocelot_flower_parse(struct flow_cls_offload *f,
 
 finished_key_parsing:
 	if (match_protocol && proto != ETH_P_ALL) {
+		if (filter->block_id == VCAP_ES0) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "VCAP ES0 cannot match on L2 proto");
+			return -EOPNOTSUPP;
+		}
+
 		/* TODO: support SNAP, LLC etc */
 		if (proto < ETH_P_802_3_MIN)
 			return -EOPNOTSUPP;
@@ -179,14 +589,28 @@ finished_key_parsing:
 	}
 	/* else, a filter of type OCELOT_VCAP_KEY_ANY is implicitly added */
 
+	return 0;
+}
+
+static int ocelot_flower_parse(struct ocelot *ocelot, int port, bool ingress,
+			       struct flow_cls_offload *f,
+			       struct ocelot_vcap_filter *filter)
+{
+	int ret;
+
 	filter->prio = f->common.prio;
 	filter->id = f->cookie;
-	return ocelot_flower_parse_action(f, filter);
+
+	ret = ocelot_flower_parse_action(ocelot, ingress, f, filter);
+	if (ret)
+		return ret;
+
+	return ocelot_flower_parse_key(ocelot, port, ingress, f, filter);
 }
 
 static struct ocelot_vcap_filter
-*ocelot_vcap_filter_create(struct ocelot *ocelot, int port,
-			 struct flow_cls_offload *f)
+*ocelot_vcap_filter_create(struct ocelot *ocelot, int port, bool ingress,
+			   struct flow_cls_offload *f)
 {
 	struct ocelot_vcap_filter *filter;
 
@@ -194,26 +618,65 @@ static struct ocelot_vcap_filter
 	if (!filter)
 		return NULL;
 
-	filter->ingress_port_mask = BIT(port);
+	if (ingress) {
+		filter->ingress_port_mask = BIT(port);
+	} else {
+		const struct vcap_props *vcap = &ocelot->vcap[VCAP_ES0];
+		int key_length = vcap->keys[VCAP_ES0_EGR_PORT].length;
+
+		filter->egress_port.value = port;
+		filter->egress_port.mask = GENMASK(key_length - 1, 0);
+	}
+
 	return filter;
 }
 
+static int ocelot_vcap_dummy_filter_add(struct ocelot *ocelot,
+					struct ocelot_vcap_filter *filter)
+{
+	list_add(&filter->list, &ocelot->dummy_rules);
+
+	return 0;
+}
+
+static int ocelot_vcap_dummy_filter_del(struct ocelot *ocelot,
+					struct ocelot_vcap_filter *filter)
+{
+	list_del(&filter->list);
+	kfree(filter);
+
+	return 0;
+}
+
 int ocelot_cls_flower_replace(struct ocelot *ocelot, int port,
 			      struct flow_cls_offload *f, bool ingress)
 {
+	struct netlink_ext_ack *extack = f->common.extack;
 	struct ocelot_vcap_filter *filter;
+	int chain = f->common.chain_index;
 	int ret;
 
-	filter = ocelot_vcap_filter_create(ocelot, port, f);
+	if (chain && !ocelot_find_vcap_filter_that_points_at(ocelot, chain)) {
+		NL_SET_ERR_MSG_MOD(extack, "No default GOTO action points to this chain");
+		return -EOPNOTSUPP;
+	}
+
+	filter = ocelot_vcap_filter_create(ocelot, port, ingress, f);
 	if (!filter)
 		return -ENOMEM;
 
-	ret = ocelot_flower_parse(f, filter);
+	ret = ocelot_flower_parse(ocelot, port, ingress, f, filter);
 	if (ret) {
 		kfree(filter);
 		return ret;
 	}
 
+	/* The non-optional GOTOs for the TCAM skeleton don't need
+	 * to be actually offloaded.
+	 */
+	if (filter->type == OCELOT_VCAP_FILTER_DUMMY)
+		return ocelot_vcap_dummy_filter_add(ocelot, filter);
+
 	return ocelot_vcap_filter_add(ocelot, filter, f->common.extack);
 }
 EXPORT_SYMBOL_GPL(ocelot_cls_flower_replace);
@@ -221,28 +684,49 @@ EXPORT_SYMBOL_GPL(ocelot_cls_flower_replace);
 int ocelot_cls_flower_destroy(struct ocelot *ocelot, int port,
 			      struct flow_cls_offload *f, bool ingress)
 {
-	struct ocelot_vcap_filter filter;
+	struct ocelot_vcap_filter *filter;
+	struct ocelot_vcap_block *block;
+	int block_id;
+
+	block_id = ocelot_chain_to_block(f->common.chain_index, ingress);
+	if (block_id < 0)
+		return 0;
 
-	filter.prio = f->common.prio;
-	filter.id = f->cookie;
+	block = &ocelot->block[block_id];
 
-	return ocelot_vcap_filter_del(ocelot, &filter);
+	filter = ocelot_vcap_block_find_filter_by_id(block, f->cookie);
+	if (!filter)
+		return 0;
+
+	if (filter->type == OCELOT_VCAP_FILTER_DUMMY)
+		return ocelot_vcap_dummy_filter_del(ocelot, filter);
+
+	return ocelot_vcap_filter_del(ocelot, filter);
 }
 EXPORT_SYMBOL_GPL(ocelot_cls_flower_destroy);
 
 int ocelot_cls_flower_stats(struct ocelot *ocelot, int port,
 			    struct flow_cls_offload *f, bool ingress)
 {
-	struct ocelot_vcap_filter filter;
-	int ret;
+	struct ocelot_vcap_filter *filter;
+	struct ocelot_vcap_block *block;
+	int block_id, ret;
+
+	block_id = ocelot_chain_to_block(f->common.chain_index, ingress);
+	if (block_id < 0)
+		return 0;
+
+	block = &ocelot->block[block_id];
+
+	filter = ocelot_vcap_block_find_filter_by_id(block, f->cookie);
+	if (!filter || filter->type == OCELOT_VCAP_FILTER_DUMMY)
+		return 0;
 
-	filter.prio = f->common.prio;
-	filter.id = f->cookie;
-	ret = ocelot_vcap_filter_stats_update(ocelot, &filter);
+	ret = ocelot_vcap_filter_stats_update(ocelot, filter);
 	if (ret)
 		return ret;
 
-	flow_stats_update(&f->stats, 0x0, filter.stats.pkts, 0, 0x0,
+	flow_stats_update(&f->stats, 0x0, filter->stats.pkts, 0, 0x0,
 			  FLOW_ACTION_HW_STATS_IMMEDIATE);
 	return 0;
 }
diff --git a/drivers/net/ethernet/mscc/ocelot_io.c b/drivers/net/ethernet/mscc/ocelot_io.c
index d22711282183..0acb45948418 100644
--- a/drivers/net/ethernet/mscc/ocelot_io.c
+++ b/drivers/net/ethernet/mscc/ocelot_io.c
@@ -71,6 +71,23 @@ void ocelot_port_writel(struct ocelot_port *port, u32 val, u32 reg)
 }
 EXPORT_SYMBOL(ocelot_port_writel);
 
+u32 __ocelot_target_read_ix(struct ocelot *ocelot, enum ocelot_target target,
+			    u32 reg, u32 offset)
+{
+	u32 val;
+
+	regmap_read(ocelot->targets[target],
+		    ocelot->map[target][reg] + offset, &val);
+	return val;
+}
+
+void __ocelot_target_write_ix(struct ocelot *ocelot, enum ocelot_target target,
+			      u32 val, u32 reg, u32 offset)
+{
+	regmap_write(ocelot->targets[target],
+		     ocelot->map[target][reg] + offset, val);
+}
+
 int ocelot_regfields_init(struct ocelot *ocelot,
 			  const struct reg_field *const regfields)
 {
diff --git a/drivers/net/ethernet/mscc/ocelot_net.c b/drivers/net/ethernet/mscc/ocelot_net.c
index 0668d23cdbfa..64e619f0f5b2 100644
--- a/drivers/net/ethernet/mscc/ocelot_net.c
+++ b/drivers/net/ethernet/mscc/ocelot_net.c
@@ -344,10 +344,28 @@ static int ocelot_port_xmit(struct sk_buff *skb, struct net_device *dev)
 	info.vid = skb_vlan_tag_get(skb);
 
 	/* Check if timestamping is needed */
+	if (ocelot->ptp && (shinfo->tx_flags & SKBTX_HW_TSTAMP)) {
+		info.rew_op = ocelot_port->ptp_cmd;
+
+		if (ocelot_port->ptp_cmd == IFH_REW_OP_TWO_STEP_PTP) {
+			struct sk_buff *clone;
+
+			clone = skb_clone_sk(skb);
+			if (!clone) {
+				kfree_skb(skb);
+				return NETDEV_TX_OK;
+			}
+
+			ocelot_port_add_txtstamp_skb(ocelot, port, clone);
+
+			info.rew_op |= clone->cb[0] << 3;
+		}
+	}
+
 	if (ocelot->ptp && shinfo->tx_flags & SKBTX_HW_TSTAMP) {
 		info.rew_op = ocelot_port->ptp_cmd;
 		if (ocelot_port->ptp_cmd == IFH_REW_OP_TWO_STEP_PTP)
-			info.rew_op |= (ocelot_port->ts_id  % 4) << 3;
+			info.rew_op |= skb->cb[0] << 3;
 	}
 
 	ocelot_gen_ifh(ifh, &info);
@@ -380,12 +398,8 @@ static int ocelot_port_xmit(struct sk_buff *skb, struct net_device *dev)
 	dev->stats.tx_packets++;
 	dev->stats.tx_bytes += skb->len;
 
-	if (!ocelot_port_add_txtstamp_skb(ocelot_port, skb)) {
-		ocelot_port->ts_id++;
-		return NETDEV_TX_OK;
-	}
+	kfree_skb(skb);
 
-	dev_kfree_skb_any(skb);
 	return NETDEV_TX_OK;
 }
 
@@ -642,6 +656,36 @@ static const struct net_device_ops ocelot_port_netdev_ops = {
 	.ndo_do_ioctl			= ocelot_ioctl,
 };
 
+struct net_device *ocelot_port_to_netdev(struct ocelot *ocelot, int port)
+{
+	struct ocelot_port *ocelot_port = ocelot->ports[port];
+	struct ocelot_port_private *priv;
+
+	if (!ocelot_port)
+		return NULL;
+
+	priv = container_of(ocelot_port, struct ocelot_port_private, port);
+
+	return priv->dev;
+}
+
+static bool ocelot_port_dev_check(const struct net_device *dev)
+{
+	return dev->netdev_ops == &ocelot_port_netdev_ops;
+}
+
+int ocelot_netdev_to_port(struct net_device *dev)
+{
+	struct ocelot_port_private *priv;
+
+	if (!dev || !ocelot_port_dev_check(dev))
+		return -EINVAL;
+
+	priv = netdev_priv(dev);
+
+	return priv->chip_port;
+}
+
 static void ocelot_port_get_strings(struct net_device *netdev, u32 sset,
 				    u8 *data)
 {
diff --git a/drivers/net/ethernet/mscc/ocelot_s2.h b/drivers/net/ethernet/mscc/ocelot_s2.h
deleted file mode 100644
index 80107bec2e45..000000000000
--- a/drivers/net/ethernet/mscc/ocelot_s2.h
+++ /dev/null
@@ -1,64 +0,0 @@
-/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */
-/* Microsemi Ocelot Switch driver
- * Copyright (c) 2018 Microsemi Corporation
- */
-
-#ifndef _OCELOT_S2_CORE_H_
-#define _OCELOT_S2_CORE_H_
-
-#define S2_CORE_UPDATE_CTRL_UPDATE_CMD(x)      (((x) << 22) & GENMASK(24, 22))
-#define S2_CORE_UPDATE_CTRL_UPDATE_CMD_M       GENMASK(24, 22)
-#define S2_CORE_UPDATE_CTRL_UPDATE_CMD_X(x)    (((x) & GENMASK(24, 22)) >> 22)
-#define S2_CORE_UPDATE_CTRL_UPDATE_ENTRY_DIS   BIT(21)
-#define S2_CORE_UPDATE_CTRL_UPDATE_ACTION_DIS  BIT(20)
-#define S2_CORE_UPDATE_CTRL_UPDATE_CNT_DIS     BIT(19)
-#define S2_CORE_UPDATE_CTRL_UPDATE_ADDR(x)     (((x) << 3) & GENMASK(18, 3))
-#define S2_CORE_UPDATE_CTRL_UPDATE_ADDR_M      GENMASK(18, 3)
-#define S2_CORE_UPDATE_CTRL_UPDATE_ADDR_X(x)   (((x) & GENMASK(18, 3)) >> 3)
-#define S2_CORE_UPDATE_CTRL_UPDATE_SHOT        BIT(2)
-#define S2_CORE_UPDATE_CTRL_CLEAR_CACHE        BIT(1)
-#define S2_CORE_UPDATE_CTRL_MV_TRAFFIC_IGN     BIT(0)
-
-#define S2_CORE_MV_CFG_MV_NUM_POS(x)           (((x) << 16) & GENMASK(31, 16))
-#define S2_CORE_MV_CFG_MV_NUM_POS_M            GENMASK(31, 16)
-#define S2_CORE_MV_CFG_MV_NUM_POS_X(x)         (((x) & GENMASK(31, 16)) >> 16)
-#define S2_CORE_MV_CFG_MV_SIZE(x)              ((x) & GENMASK(15, 0))
-#define S2_CORE_MV_CFG_MV_SIZE_M               GENMASK(15, 0)
-
-#define S2_CACHE_ENTRY_DAT_RSZ                 0x4
-
-#define S2_CACHE_MASK_DAT_RSZ                  0x4
-
-#define S2_CACHE_ACTION_DAT_RSZ                0x4
-
-#define S2_CACHE_CNT_DAT_RSZ                   0x4
-
-#define S2_STICKY_VCAP_ROW_DELETED_STICKY      BIT(0)
-
-#define S2_BIST_CTRL_TCAM_BIST                 BIT(1)
-#define S2_BIST_CTRL_TCAM_INIT                 BIT(0)
-
-#define S2_BIST_CFG_TCAM_BIST_SOE_ENA          BIT(8)
-#define S2_BIST_CFG_TCAM_HCG_DIS               BIT(7)
-#define S2_BIST_CFG_TCAM_CG_DIS                BIT(6)
-#define S2_BIST_CFG_TCAM_BIAS(x)               ((x) & GENMASK(5, 0))
-#define S2_BIST_CFG_TCAM_BIAS_M                GENMASK(5, 0)
-
-#define S2_BIST_STAT_BIST_RT_ERR               BIT(15)
-#define S2_BIST_STAT_BIST_PENC_ERR             BIT(14)
-#define S2_BIST_STAT_BIST_COMP_ERR             BIT(13)
-#define S2_BIST_STAT_BIST_ADDR_ERR             BIT(12)
-#define S2_BIST_STAT_BIST_BL1E_ERR             BIT(11)
-#define S2_BIST_STAT_BIST_BL1_ERR              BIT(10)
-#define S2_BIST_STAT_BIST_BL0E_ERR             BIT(9)
-#define S2_BIST_STAT_BIST_BL0_ERR              BIT(8)
-#define S2_BIST_STAT_BIST_PH1_ERR              BIT(7)
-#define S2_BIST_STAT_BIST_PH0_ERR              BIT(6)
-#define S2_BIST_STAT_BIST_PV1_ERR              BIT(5)
-#define S2_BIST_STAT_BIST_PV0_ERR              BIT(4)
-#define S2_BIST_STAT_BIST_RUN                  BIT(3)
-#define S2_BIST_STAT_BIST_ERR                  BIT(2)
-#define S2_BIST_STAT_BIST_BUSY                 BIT(1)
-#define S2_BIST_STAT_TCAM_RDY                  BIT(0)
-
-#endif /* _OCELOT_S2_CORE_H_ */
diff --git a/drivers/net/ethernet/mscc/ocelot_vcap.c b/drivers/net/ethernet/mscc/ocelot_vcap.c
index 3ef620faf995..d8c778ee6f1b 100644
--- a/drivers/net/ethernet/mscc/ocelot_vcap.c
+++ b/drivers/net/ethernet/mscc/ocelot_vcap.c
@@ -9,9 +9,7 @@
 #include <soc/mscc/ocelot_vcap.h>
 #include "ocelot_police.h"
 #include "ocelot_vcap.h"
-#include "ocelot_s2.h"
 
-#define OCELOT_POLICER_DISCARD 0x17f
 #define ENTRY_WIDTH 32
 
 enum vcap_sel {
@@ -48,145 +46,174 @@ struct vcap_data {
 	u32 tg_mask; /* Current type-group mask */
 };
 
-static u32 vcap_s2_read_update_ctrl(struct ocelot *ocelot)
+static u32 vcap_read_update_ctrl(struct ocelot *ocelot,
+				 const struct vcap_props *vcap)
 {
-	return ocelot_read(ocelot, S2_CORE_UPDATE_CTRL);
+	return ocelot_target_read(ocelot, vcap->target, VCAP_CORE_UPDATE_CTRL);
 }
 
-static void vcap_cmd(struct ocelot *ocelot, u16 ix, int cmd, int sel)
+static void vcap_cmd(struct ocelot *ocelot, const struct vcap_props *vcap,
+		     u16 ix, int cmd, int sel)
 {
-	const struct vcap_props *vcap_is2 = &ocelot->vcap[VCAP_IS2];
+	u32 value = (VCAP_CORE_UPDATE_CTRL_UPDATE_CMD(cmd) |
+		     VCAP_CORE_UPDATE_CTRL_UPDATE_ADDR(ix) |
+		     VCAP_CORE_UPDATE_CTRL_UPDATE_SHOT);
 
-	u32 value = (S2_CORE_UPDATE_CTRL_UPDATE_CMD(cmd) |
-		     S2_CORE_UPDATE_CTRL_UPDATE_ADDR(ix) |
-		     S2_CORE_UPDATE_CTRL_UPDATE_SHOT);
-
-	if ((sel & VCAP_SEL_ENTRY) && ix >= vcap_is2->entry_count)
+	if ((sel & VCAP_SEL_ENTRY) && ix >= vcap->entry_count)
 		return;
 
 	if (!(sel & VCAP_SEL_ENTRY))
-		value |= S2_CORE_UPDATE_CTRL_UPDATE_ENTRY_DIS;
+		value |= VCAP_CORE_UPDATE_CTRL_UPDATE_ENTRY_DIS;
 
 	if (!(sel & VCAP_SEL_ACTION))
-		value |= S2_CORE_UPDATE_CTRL_UPDATE_ACTION_DIS;
+		value |= VCAP_CORE_UPDATE_CTRL_UPDATE_ACTION_DIS;
 
 	if (!(sel & VCAP_SEL_COUNTER))
-		value |= S2_CORE_UPDATE_CTRL_UPDATE_CNT_DIS;
+		value |= VCAP_CORE_UPDATE_CTRL_UPDATE_CNT_DIS;
+
+	ocelot_target_write(ocelot, vcap->target, value, VCAP_CORE_UPDATE_CTRL);
 
-	ocelot_write(ocelot, value, S2_CORE_UPDATE_CTRL);
-	readx_poll_timeout(vcap_s2_read_update_ctrl, ocelot, value,
-				(value & S2_CORE_UPDATE_CTRL_UPDATE_SHOT) == 0,
-				10, 100000);
+	read_poll_timeout(vcap_read_update_ctrl, value,
+			  (value & VCAP_CORE_UPDATE_CTRL_UPDATE_SHOT) == 0,
+			  10, 100000, false, ocelot, vcap);
 }
 
 /* Convert from 0-based row to VCAP entry row and run command */
-static void vcap_row_cmd(struct ocelot *ocelot, u32 row, int cmd, int sel)
+static void vcap_row_cmd(struct ocelot *ocelot, const struct vcap_props *vcap,
+			 u32 row, int cmd, int sel)
 {
-	const struct vcap_props *vcap_is2 = &ocelot->vcap[VCAP_IS2];
-
-	vcap_cmd(ocelot, vcap_is2->entry_count - row - 1, cmd, sel);
+	vcap_cmd(ocelot, vcap, vcap->entry_count - row - 1, cmd, sel);
 }
 
-static void vcap_entry2cache(struct ocelot *ocelot, struct vcap_data *data)
+static void vcap_entry2cache(struct ocelot *ocelot,
+			     const struct vcap_props *vcap,
+			     struct vcap_data *data)
 {
-	const struct vcap_props *vcap_is2 = &ocelot->vcap[VCAP_IS2];
 	u32 entry_words, i;
 
-	entry_words = DIV_ROUND_UP(vcap_is2->entry_width, ENTRY_WIDTH);
+	entry_words = DIV_ROUND_UP(vcap->entry_width, ENTRY_WIDTH);
 
 	for (i = 0; i < entry_words; i++) {
-		ocelot_write_rix(ocelot, data->entry[i], S2_CACHE_ENTRY_DAT, i);
-		ocelot_write_rix(ocelot, ~data->mask[i], S2_CACHE_MASK_DAT, i);
+		ocelot_target_write_rix(ocelot, vcap->target, data->entry[i],
+					VCAP_CACHE_ENTRY_DAT, i);
+		ocelot_target_write_rix(ocelot, vcap->target, ~data->mask[i],
+					VCAP_CACHE_MASK_DAT, i);
 	}
-	ocelot_write(ocelot, data->tg, S2_CACHE_TG_DAT);
+	ocelot_target_write(ocelot, vcap->target, data->tg, VCAP_CACHE_TG_DAT);
 }
 
-static void vcap_cache2entry(struct ocelot *ocelot, struct vcap_data *data)
+static void vcap_cache2entry(struct ocelot *ocelot,
+			     const struct vcap_props *vcap,
+			     struct vcap_data *data)
 {
-	const struct vcap_props *vcap_is2 = &ocelot->vcap[VCAP_IS2];
 	u32 entry_words, i;
 
-	entry_words = DIV_ROUND_UP(vcap_is2->entry_width, ENTRY_WIDTH);
+	entry_words = DIV_ROUND_UP(vcap->entry_width, ENTRY_WIDTH);
 
 	for (i = 0; i < entry_words; i++) {
-		data->entry[i] = ocelot_read_rix(ocelot, S2_CACHE_ENTRY_DAT, i);
+		data->entry[i] = ocelot_target_read_rix(ocelot, vcap->target,
+							VCAP_CACHE_ENTRY_DAT, i);
 		// Invert mask
-		data->mask[i] = ~ocelot_read_rix(ocelot, S2_CACHE_MASK_DAT, i);
+		data->mask[i] = ~ocelot_target_read_rix(ocelot, vcap->target,
+							VCAP_CACHE_MASK_DAT, i);
 	}
-	data->tg = ocelot_read(ocelot, S2_CACHE_TG_DAT);
+	data->tg = ocelot_target_read(ocelot, vcap->target, VCAP_CACHE_TG_DAT);
 }
 
-static void vcap_action2cache(struct ocelot *ocelot, struct vcap_data *data)
+static void vcap_action2cache(struct ocelot *ocelot,
+			      const struct vcap_props *vcap,
+			      struct vcap_data *data)
 {
-	const struct vcap_props *vcap_is2 = &ocelot->vcap[VCAP_IS2];
 	u32 action_words, mask;
 	int i, width;
 
 	/* Encode action type */
-	width = vcap_is2->action_type_width;
+	width = vcap->action_type_width;
 	if (width) {
 		mask = GENMASK(width, 0);
 		data->action[0] = ((data->action[0] & ~mask) | data->type);
 	}
 
-	action_words = DIV_ROUND_UP(vcap_is2->action_width, ENTRY_WIDTH);
+	action_words = DIV_ROUND_UP(vcap->action_width, ENTRY_WIDTH);
 
 	for (i = 0; i < action_words; i++)
-		ocelot_write_rix(ocelot, data->action[i], S2_CACHE_ACTION_DAT,
-				 i);
+		ocelot_target_write_rix(ocelot, vcap->target, data->action[i],
+					VCAP_CACHE_ACTION_DAT, i);
 
-	for (i = 0; i < vcap_is2->counter_words; i++)
-		ocelot_write_rix(ocelot, data->counter[i], S2_CACHE_CNT_DAT, i);
+	for (i = 0; i < vcap->counter_words; i++)
+		ocelot_target_write_rix(ocelot, vcap->target, data->counter[i],
+					VCAP_CACHE_CNT_DAT, i);
 }
 
-static void vcap_cache2action(struct ocelot *ocelot, struct vcap_data *data)
+static void vcap_cache2action(struct ocelot *ocelot,
+			      const struct vcap_props *vcap,
+			      struct vcap_data *data)
 {
-	const struct vcap_props *vcap_is2 = &ocelot->vcap[VCAP_IS2];
 	u32 action_words;
 	int i, width;
 
-	action_words = DIV_ROUND_UP(vcap_is2->action_width, ENTRY_WIDTH);
+	action_words = DIV_ROUND_UP(vcap->action_width, ENTRY_WIDTH);
 
 	for (i = 0; i < action_words; i++)
-		data->action[i] = ocelot_read_rix(ocelot, S2_CACHE_ACTION_DAT,
-						  i);
+		data->action[i] = ocelot_target_read_rix(ocelot, vcap->target,
+							 VCAP_CACHE_ACTION_DAT,
+							 i);
 
-	for (i = 0; i < vcap_is2->counter_words; i++)
-		data->counter[i] = ocelot_read_rix(ocelot, S2_CACHE_CNT_DAT, i);
+	for (i = 0; i < vcap->counter_words; i++)
+		data->counter[i] = ocelot_target_read_rix(ocelot, vcap->target,
+							  VCAP_CACHE_CNT_DAT,
+							  i);
 
 	/* Extract action type */
-	width = vcap_is2->action_type_width;
+	width = vcap->action_type_width;
 	data->type = (width ? (data->action[0] & GENMASK(width, 0)) : 0);
 }
 
 /* Calculate offsets for entry */
-static void is2_data_get(struct ocelot *ocelot, struct vcap_data *data, int ix)
+static void vcap_data_offset_get(const struct vcap_props *vcap,
+				 struct vcap_data *data, int ix)
 {
-	const struct vcap_props *vcap_is2 = &ocelot->vcap[VCAP_IS2];
-	int i, col, offset, count, cnt, base;
-	int width = vcap_is2->tg_width;
+	int num_subwords_per_entry, num_subwords_per_action;
+	int i, col, offset, num_entries_per_row, base;
+	u32 width = vcap->tg_width;
 
-	count = (data->tg_sw == VCAP_TG_HALF ? 2 : 4);
-	col = (ix % 2);
-	cnt = (vcap_is2->sw_count / count);
-	base = (vcap_is2->sw_count - col * cnt - cnt);
+	switch (data->tg_sw) {
+	case VCAP_TG_FULL:
+		num_entries_per_row = 1;
+		break;
+	case VCAP_TG_HALF:
+		num_entries_per_row = 2;
+		break;
+	case VCAP_TG_QUARTER:
+		num_entries_per_row = 4;
+		break;
+	default:
+		return;
+	}
+
+	col = (ix % num_entries_per_row);
+	num_subwords_per_entry = (vcap->sw_count / num_entries_per_row);
+	base = (vcap->sw_count - col * num_subwords_per_entry -
+		num_subwords_per_entry);
 	data->tg_value = 0;
 	data->tg_mask = 0;
-	for (i = 0; i < cnt; i++) {
+	for (i = 0; i < num_subwords_per_entry; i++) {
 		offset = ((base + i) * width);
 		data->tg_value |= (data->tg_sw << offset);
 		data->tg_mask |= GENMASK(offset + width - 1, offset);
 	}
 
 	/* Calculate key/action/counter offsets */
-	col = (count - col - 1);
-	data->key_offset = (base * vcap_is2->entry_width) / vcap_is2->sw_count;
-	data->counter_offset = (cnt * col * vcap_is2->counter_width);
+	col = (num_entries_per_row - col - 1);
+	data->key_offset = (base * vcap->entry_width) / vcap->sw_count;
+	data->counter_offset = (num_subwords_per_entry * col *
+				vcap->counter_width);
 	i = data->type;
-	width = vcap_is2->action_table[i].width;
-	cnt = vcap_is2->action_table[i].count;
-	data->action_offset =
-		(((cnt * col * width) / count) + vcap_is2->action_type_width);
+	width = vcap->action_table[i].width;
+	num_subwords_per_action = vcap->action_table[i].count;
+	data->action_offset = ((num_subwords_per_action * col * width) /
+				num_entries_per_row);
+	data->action_offset += vcap->action_type_width;
 }
 
 static void vcap_data_set(u32 *data, u32 offset, u32 len, u32 value)
@@ -224,22 +251,21 @@ static void vcap_key_field_set(struct vcap_data *data, u32 offset, u32 width,
 	vcap_data_set(data->mask, offset + data->key_offset, width, mask);
 }
 
-static void vcap_key_set(struct ocelot *ocelot, struct vcap_data *data,
-			 enum vcap_is2_half_key_field field,
-			 u32 value, u32 mask)
+static void vcap_key_set(const struct vcap_props *vcap, struct vcap_data *data,
+			 int field, u32 value, u32 mask)
 {
-	u32 offset = ocelot->vcap_is2_keys[field].offset;
-	u32 length = ocelot->vcap_is2_keys[field].length;
+	u32 offset = vcap->keys[field].offset;
+	u32 length = vcap->keys[field].length;
 
 	vcap_key_field_set(data, offset, length, value, mask);
 }
 
-static void vcap_key_bytes_set(struct ocelot *ocelot, struct vcap_data *data,
-			       enum vcap_is2_half_key_field field,
+static void vcap_key_bytes_set(const struct vcap_props *vcap,
+			       struct vcap_data *data, int field,
 			       u8 *val, u8 *msk)
 {
-	u32 offset = ocelot->vcap_is2_keys[field].offset;
-	u32 count  = ocelot->vcap_is2_keys[field].length;
+	u32 offset = vcap->keys[field].offset;
+	u32 count  = vcap->keys[field].length;
 	u32 i, j, n = 0, value = 0, mask = 0;
 
 	WARN_ON(count % 8);
@@ -265,37 +291,37 @@ static void vcap_key_bytes_set(struct ocelot *ocelot, struct vcap_data *data,
 	}
 }
 
-static void vcap_key_l4_port_set(struct ocelot *ocelot, struct vcap_data *data,
-				 enum vcap_is2_half_key_field field,
+static void vcap_key_l4_port_set(const struct vcap_props *vcap,
+				 struct vcap_data *data, int field,
 				 struct ocelot_vcap_udp_tcp *port)
 {
-	u32 offset = ocelot->vcap_is2_keys[field].offset;
-	u32 length = ocelot->vcap_is2_keys[field].length;
+	u32 offset = vcap->keys[field].offset;
+	u32 length = vcap->keys[field].length;
 
 	WARN_ON(length != 16);
 
 	vcap_key_field_set(data, offset, length, port->value, port->mask);
 }
 
-static void vcap_key_bit_set(struct ocelot *ocelot, struct vcap_data *data,
-			     enum vcap_is2_half_key_field field,
+static void vcap_key_bit_set(const struct vcap_props *vcap,
+			     struct vcap_data *data, int field,
 			     enum ocelot_vcap_bit val)
 {
-	u32 offset = ocelot->vcap_is2_keys[field].offset;
-	u32 length = ocelot->vcap_is2_keys[field].length;
 	u32 value = (val == OCELOT_VCAP_BIT_1 ? 1 : 0);
 	u32 msk = (val == OCELOT_VCAP_BIT_ANY ? 0 : 1);
+	u32 offset = vcap->keys[field].offset;
+	u32 length = vcap->keys[field].length;
 
 	WARN_ON(length != 1);
 
 	vcap_key_field_set(data, offset, length, value, msk);
 }
 
-static void vcap_action_set(struct ocelot *ocelot, struct vcap_data *data,
-			    enum vcap_is2_action_field field, u32 value)
+static void vcap_action_set(const struct vcap_props *vcap,
+			    struct vcap_data *data, int field, u32 value)
 {
-	int offset = ocelot->vcap_is2_actions[field].offset;
-	int length = ocelot->vcap_is2_actions[field].length;
+	int offset = vcap->actions[field].offset;
+	int length = vcap->actions[field].length;
 
 	vcap_data_set(data->action, offset + data->action_offset, length,
 		      value);
@@ -304,40 +330,21 @@ static void vcap_action_set(struct ocelot *ocelot, struct vcap_data *data,
 static void is2_action_set(struct ocelot *ocelot, struct vcap_data *data,
 			   struct ocelot_vcap_filter *filter)
 {
-	switch (filter->action) {
-	case OCELOT_VCAP_ACTION_DROP:
-		vcap_action_set(ocelot, data, VCAP_IS2_ACT_PORT_MASK, 0);
-		vcap_action_set(ocelot, data, VCAP_IS2_ACT_MASK_MODE, 1);
-		vcap_action_set(ocelot, data, VCAP_IS2_ACT_POLICE_ENA, 1);
-		vcap_action_set(ocelot, data, VCAP_IS2_ACT_POLICE_IDX,
-				OCELOT_POLICER_DISCARD);
-		vcap_action_set(ocelot, data, VCAP_IS2_ACT_CPU_QU_NUM, 0);
-		vcap_action_set(ocelot, data, VCAP_IS2_ACT_CPU_COPY_ENA, 0);
-		break;
-	case OCELOT_VCAP_ACTION_TRAP:
-		vcap_action_set(ocelot, data, VCAP_IS2_ACT_PORT_MASK, 0);
-		vcap_action_set(ocelot, data, VCAP_IS2_ACT_MASK_MODE, 1);
-		vcap_action_set(ocelot, data, VCAP_IS2_ACT_POLICE_ENA, 0);
-		vcap_action_set(ocelot, data, VCAP_IS2_ACT_POLICE_IDX, 0);
-		vcap_action_set(ocelot, data, VCAP_IS2_ACT_CPU_QU_NUM, 0);
-		vcap_action_set(ocelot, data, VCAP_IS2_ACT_CPU_COPY_ENA, 1);
-		break;
-	case OCELOT_VCAP_ACTION_POLICE:
-		vcap_action_set(ocelot, data, VCAP_IS2_ACT_PORT_MASK, 0);
-		vcap_action_set(ocelot, data, VCAP_IS2_ACT_MASK_MODE, 0);
-		vcap_action_set(ocelot, data, VCAP_IS2_ACT_POLICE_ENA, 1);
-		vcap_action_set(ocelot, data, VCAP_IS2_ACT_POLICE_IDX,
-				filter->pol_ix);
-		vcap_action_set(ocelot, data, VCAP_IS2_ACT_CPU_QU_NUM, 0);
-		vcap_action_set(ocelot, data, VCAP_IS2_ACT_CPU_COPY_ENA, 0);
-		break;
-	}
+	const struct vcap_props *vcap = &ocelot->vcap[VCAP_IS2];
+	struct ocelot_vcap_action *a = &filter->action;
+
+	vcap_action_set(vcap, data, VCAP_IS2_ACT_MASK_MODE, a->mask_mode);
+	vcap_action_set(vcap, data, VCAP_IS2_ACT_PORT_MASK, a->port_mask);
+	vcap_action_set(vcap, data, VCAP_IS2_ACT_POLICE_ENA, a->police_ena);
+	vcap_action_set(vcap, data, VCAP_IS2_ACT_POLICE_IDX, a->pol_ix);
+	vcap_action_set(vcap, data, VCAP_IS2_ACT_CPU_QU_NUM, a->cpu_qu_num);
+	vcap_action_set(vcap, data, VCAP_IS2_ACT_CPU_COPY_ENA, a->cpu_copy_ena);
 }
 
 static void is2_entry_set(struct ocelot *ocelot, int ix,
 			  struct ocelot_vcap_filter *filter)
 {
-	const struct vcap_props *vcap_is2 = &ocelot->vcap[VCAP_IS2];
+	const struct vcap_props *vcap = &ocelot->vcap[VCAP_IS2];
 	struct ocelot_vcap_key_vlan *tag = &filter->vlan;
 	u32 val, msk, type, type_mask = 0xf, i, count;
 	struct ocelot_vcap_u64 payload;
@@ -348,52 +355,55 @@ static void is2_entry_set(struct ocelot *ocelot, int ix,
 	memset(&data, 0, sizeof(data));
 
 	/* Read row */
-	vcap_row_cmd(ocelot, row, VCAP_CMD_READ, VCAP_SEL_ALL);
-	vcap_cache2entry(ocelot, &data);
-	vcap_cache2action(ocelot, &data);
+	vcap_row_cmd(ocelot, vcap, row, VCAP_CMD_READ, VCAP_SEL_ALL);
+	vcap_cache2entry(ocelot, vcap, &data);
+	vcap_cache2action(ocelot, vcap, &data);
 
 	data.tg_sw = VCAP_TG_HALF;
-	is2_data_get(ocelot, &data, ix);
+	vcap_data_offset_get(vcap, &data, ix);
 	data.tg = (data.tg & ~data.tg_mask);
 	if (filter->prio != 0)
 		data.tg |= data.tg_value;
 
 	data.type = IS2_ACTION_TYPE_NORMAL;
 
-	vcap_key_set(ocelot, &data, VCAP_IS2_HK_PAG, 0, 0);
-	vcap_key_set(ocelot, &data, VCAP_IS2_HK_IGR_PORT_MASK, 0,
+	vcap_key_set(vcap, &data, VCAP_IS2_HK_PAG, filter->pag, 0xff);
+	vcap_key_bit_set(vcap, &data, VCAP_IS2_HK_FIRST,
+			 (filter->lookup == 0) ? OCELOT_VCAP_BIT_1 :
+			 OCELOT_VCAP_BIT_0);
+	vcap_key_set(vcap, &data, VCAP_IS2_HK_IGR_PORT_MASK, 0,
 		     ~filter->ingress_port_mask);
-	vcap_key_bit_set(ocelot, &data, VCAP_IS2_HK_FIRST, OCELOT_VCAP_BIT_1);
-	vcap_key_bit_set(ocelot, &data, VCAP_IS2_HK_HOST_MATCH,
+	vcap_key_bit_set(vcap, &data, VCAP_IS2_HK_FIRST, OCELOT_VCAP_BIT_ANY);
+	vcap_key_bit_set(vcap, &data, VCAP_IS2_HK_HOST_MATCH,
 			 OCELOT_VCAP_BIT_ANY);
-	vcap_key_bit_set(ocelot, &data, VCAP_IS2_HK_L2_MC, filter->dmac_mc);
-	vcap_key_bit_set(ocelot, &data, VCAP_IS2_HK_L2_BC, filter->dmac_bc);
-	vcap_key_bit_set(ocelot, &data, VCAP_IS2_HK_VLAN_TAGGED, tag->tagged);
-	vcap_key_set(ocelot, &data, VCAP_IS2_HK_VID,
+	vcap_key_bit_set(vcap, &data, VCAP_IS2_HK_L2_MC, filter->dmac_mc);
+	vcap_key_bit_set(vcap, &data, VCAP_IS2_HK_L2_BC, filter->dmac_bc);
+	vcap_key_bit_set(vcap, &data, VCAP_IS2_HK_VLAN_TAGGED, tag->tagged);
+	vcap_key_set(vcap, &data, VCAP_IS2_HK_VID,
 		     tag->vid.value, tag->vid.mask);
-	vcap_key_set(ocelot, &data, VCAP_IS2_HK_PCP,
+	vcap_key_set(vcap, &data, VCAP_IS2_HK_PCP,
 		     tag->pcp.value[0], tag->pcp.mask[0]);
-	vcap_key_bit_set(ocelot, &data, VCAP_IS2_HK_DEI, tag->dei);
+	vcap_key_bit_set(vcap, &data, VCAP_IS2_HK_DEI, tag->dei);
 
 	switch (filter->key_type) {
 	case OCELOT_VCAP_KEY_ETYPE: {
 		struct ocelot_vcap_key_etype *etype = &filter->key.etype;
 
 		type = IS2_TYPE_ETYPE;
-		vcap_key_bytes_set(ocelot, &data, VCAP_IS2_HK_L2_DMAC,
+		vcap_key_bytes_set(vcap, &data, VCAP_IS2_HK_L2_DMAC,
 				   etype->dmac.value, etype->dmac.mask);
-		vcap_key_bytes_set(ocelot, &data, VCAP_IS2_HK_L2_SMAC,
+		vcap_key_bytes_set(vcap, &data, VCAP_IS2_HK_L2_SMAC,
 				   etype->smac.value, etype->smac.mask);
-		vcap_key_bytes_set(ocelot, &data, VCAP_IS2_HK_MAC_ETYPE_ETYPE,
+		vcap_key_bytes_set(vcap, &data, VCAP_IS2_HK_MAC_ETYPE_ETYPE,
 				   etype->etype.value, etype->etype.mask);
 		/* Clear unused bits */
-		vcap_key_set(ocelot, &data, VCAP_IS2_HK_MAC_ETYPE_L2_PAYLOAD0,
+		vcap_key_set(vcap, &data, VCAP_IS2_HK_MAC_ETYPE_L2_PAYLOAD0,
 			     0, 0);
-		vcap_key_set(ocelot, &data, VCAP_IS2_HK_MAC_ETYPE_L2_PAYLOAD1,
+		vcap_key_set(vcap, &data, VCAP_IS2_HK_MAC_ETYPE_L2_PAYLOAD1,
 			     0, 0);
-		vcap_key_set(ocelot, &data, VCAP_IS2_HK_MAC_ETYPE_L2_PAYLOAD2,
+		vcap_key_set(vcap, &data, VCAP_IS2_HK_MAC_ETYPE_L2_PAYLOAD2,
 			     0, 0);
-		vcap_key_bytes_set(ocelot, &data,
+		vcap_key_bytes_set(vcap, &data,
 				   VCAP_IS2_HK_MAC_ETYPE_L2_PAYLOAD0,
 				   etype->data.value, etype->data.mask);
 		break;
@@ -402,15 +412,15 @@ static void is2_entry_set(struct ocelot *ocelot, int ix,
 		struct ocelot_vcap_key_llc *llc = &filter->key.llc;
 
 		type = IS2_TYPE_LLC;
-		vcap_key_bytes_set(ocelot, &data, VCAP_IS2_HK_L2_DMAC,
+		vcap_key_bytes_set(vcap, &data, VCAP_IS2_HK_L2_DMAC,
 				   llc->dmac.value, llc->dmac.mask);
-		vcap_key_bytes_set(ocelot, &data, VCAP_IS2_HK_L2_SMAC,
+		vcap_key_bytes_set(vcap, &data, VCAP_IS2_HK_L2_SMAC,
 				   llc->smac.value, llc->smac.mask);
 		for (i = 0; i < 4; i++) {
 			payload.value[i] = llc->llc.value[i];
 			payload.mask[i] = llc->llc.mask[i];
 		}
-		vcap_key_bytes_set(ocelot, &data, VCAP_IS2_HK_MAC_LLC_L2_LLC,
+		vcap_key_bytes_set(vcap, &data, VCAP_IS2_HK_MAC_LLC_L2_LLC,
 				   payload.value, payload.mask);
 		break;
 	}
@@ -418,11 +428,11 @@ static void is2_entry_set(struct ocelot *ocelot, int ix,
 		struct ocelot_vcap_key_snap *snap = &filter->key.snap;
 
 		type = IS2_TYPE_SNAP;
-		vcap_key_bytes_set(ocelot, &data, VCAP_IS2_HK_L2_DMAC,
+		vcap_key_bytes_set(vcap, &data, VCAP_IS2_HK_L2_DMAC,
 				   snap->dmac.value, snap->dmac.mask);
-		vcap_key_bytes_set(ocelot, &data, VCAP_IS2_HK_L2_SMAC,
+		vcap_key_bytes_set(vcap, &data, VCAP_IS2_HK_L2_SMAC,
 				   snap->smac.value, snap->smac.mask);
-		vcap_key_bytes_set(ocelot, &data, VCAP_IS2_HK_MAC_SNAP_L2_SNAP,
+		vcap_key_bytes_set(vcap, &data, VCAP_IS2_HK_MAC_SNAP_L2_SNAP,
 				   filter->key.snap.snap.value,
 				   filter->key.snap.snap.mask);
 		break;
@@ -431,24 +441,24 @@ static void is2_entry_set(struct ocelot *ocelot, int ix,
 		struct ocelot_vcap_key_arp *arp = &filter->key.arp;
 
 		type = IS2_TYPE_ARP;
-		vcap_key_bytes_set(ocelot, &data, VCAP_IS2_HK_MAC_ARP_SMAC,
+		vcap_key_bytes_set(vcap, &data, VCAP_IS2_HK_MAC_ARP_SMAC,
 				   arp->smac.value, arp->smac.mask);
-		vcap_key_bit_set(ocelot, &data,
+		vcap_key_bit_set(vcap, &data,
 				 VCAP_IS2_HK_MAC_ARP_ADDR_SPACE_OK,
 				 arp->ethernet);
-		vcap_key_bit_set(ocelot, &data,
+		vcap_key_bit_set(vcap, &data,
 				 VCAP_IS2_HK_MAC_ARP_PROTO_SPACE_OK,
 				 arp->ip);
-		vcap_key_bit_set(ocelot, &data,
+		vcap_key_bit_set(vcap, &data,
 				 VCAP_IS2_HK_MAC_ARP_LEN_OK,
 				 arp->length);
-		vcap_key_bit_set(ocelot, &data,
+		vcap_key_bit_set(vcap, &data,
 				 VCAP_IS2_HK_MAC_ARP_TARGET_MATCH,
 				 arp->dmac_match);
-		vcap_key_bit_set(ocelot, &data,
+		vcap_key_bit_set(vcap, &data,
 				 VCAP_IS2_HK_MAC_ARP_SENDER_MATCH,
 				 arp->smac_match);
-		vcap_key_bit_set(ocelot, &data,
+		vcap_key_bit_set(vcap, &data,
 				 VCAP_IS2_HK_MAC_ARP_OPCODE_UNKNOWN,
 				 arp->unknown);
 
@@ -457,15 +467,15 @@ static void is2_entry_set(struct ocelot *ocelot, int ix,
 		       (arp->arp == OCELOT_VCAP_BIT_0 ? 2 : 0));
 		msk = ((arp->req == OCELOT_VCAP_BIT_ANY ? 0 : 1) |
 		       (arp->arp == OCELOT_VCAP_BIT_ANY ? 0 : 2));
-		vcap_key_set(ocelot, &data, VCAP_IS2_HK_MAC_ARP_OPCODE,
+		vcap_key_set(vcap, &data, VCAP_IS2_HK_MAC_ARP_OPCODE,
 			     val, msk);
-		vcap_key_bytes_set(ocelot, &data,
+		vcap_key_bytes_set(vcap, &data,
 				   VCAP_IS2_HK_MAC_ARP_L3_IP4_DIP,
 				   arp->dip.value.addr, arp->dip.mask.addr);
-		vcap_key_bytes_set(ocelot, &data,
+		vcap_key_bytes_set(vcap, &data,
 				   VCAP_IS2_HK_MAC_ARP_L3_IP4_SIP,
 				   arp->sip.value.addr, arp->sip.mask.addr);
-		vcap_key_set(ocelot, &data, VCAP_IS2_HK_MAC_ARP_DIP_EQ_SIP,
+		vcap_key_set(vcap, &data, VCAP_IS2_HK_MAC_ARP_DIP_EQ_SIP,
 			     0, 0);
 		break;
 	}
@@ -534,22 +544,22 @@ static void is2_entry_set(struct ocelot *ocelot, int ix,
 			seq_zero = ipv6->seq_zero;
 		}
 
-		vcap_key_bit_set(ocelot, &data, VCAP_IS2_HK_IP4,
+		vcap_key_bit_set(vcap, &data, VCAP_IS2_HK_IP4,
 				 ipv4 ? OCELOT_VCAP_BIT_1 : OCELOT_VCAP_BIT_0);
-		vcap_key_bit_set(ocelot, &data, VCAP_IS2_HK_L3_FRAGMENT,
+		vcap_key_bit_set(vcap, &data, VCAP_IS2_HK_L3_FRAGMENT,
 				 fragment);
-		vcap_key_set(ocelot, &data, VCAP_IS2_HK_L3_FRAG_OFS_GT0, 0, 0);
-		vcap_key_bit_set(ocelot, &data, VCAP_IS2_HK_L3_OPTIONS,
+		vcap_key_set(vcap, &data, VCAP_IS2_HK_L3_FRAG_OFS_GT0, 0, 0);
+		vcap_key_bit_set(vcap, &data, VCAP_IS2_HK_L3_OPTIONS,
 				 options);
-		vcap_key_bit_set(ocelot, &data, VCAP_IS2_HK_IP4_L3_TTL_GT0,
+		vcap_key_bit_set(vcap, &data, VCAP_IS2_HK_IP4_L3_TTL_GT0,
 				 ttl);
-		vcap_key_bytes_set(ocelot, &data, VCAP_IS2_HK_L3_TOS,
+		vcap_key_bytes_set(vcap, &data, VCAP_IS2_HK_L3_TOS,
 				   ds.value, ds.mask);
-		vcap_key_bytes_set(ocelot, &data, VCAP_IS2_HK_L3_IP4_DIP,
+		vcap_key_bytes_set(vcap, &data, VCAP_IS2_HK_L3_IP4_DIP,
 				   dip.value.addr, dip.mask.addr);
-		vcap_key_bytes_set(ocelot, &data, VCAP_IS2_HK_L3_IP4_SIP,
+		vcap_key_bytes_set(vcap, &data, VCAP_IS2_HK_L3_IP4_SIP,
 				   sip.value.addr, sip.mask.addr);
-		vcap_key_bit_set(ocelot, &data, VCAP_IS2_HK_DIP_EQ_SIP,
+		vcap_key_bit_set(vcap, &data, VCAP_IS2_HK_DIP_EQ_SIP,
 				 sip_eq_dip);
 		val = proto.value[0];
 		msk = proto.mask[0];
@@ -558,33 +568,33 @@ static void is2_entry_set(struct ocelot *ocelot, int ix,
 			/* UDP/TCP protocol match */
 			tcp = (val == 6 ?
 			       OCELOT_VCAP_BIT_1 : OCELOT_VCAP_BIT_0);
-			vcap_key_bit_set(ocelot, &data, VCAP_IS2_HK_TCP, tcp);
-			vcap_key_l4_port_set(ocelot, &data,
+			vcap_key_bit_set(vcap, &data, VCAP_IS2_HK_TCP, tcp);
+			vcap_key_l4_port_set(vcap, &data,
 					     VCAP_IS2_HK_L4_DPORT, dport);
-			vcap_key_l4_port_set(ocelot, &data,
+			vcap_key_l4_port_set(vcap, &data,
 					     VCAP_IS2_HK_L4_SPORT, sport);
-			vcap_key_set(ocelot, &data, VCAP_IS2_HK_L4_RNG, 0, 0);
-			vcap_key_bit_set(ocelot, &data,
+			vcap_key_set(vcap, &data, VCAP_IS2_HK_L4_RNG, 0, 0);
+			vcap_key_bit_set(vcap, &data,
 					 VCAP_IS2_HK_L4_SPORT_EQ_DPORT,
 					 sport_eq_dport);
-			vcap_key_bit_set(ocelot, &data,
+			vcap_key_bit_set(vcap, &data,
 					 VCAP_IS2_HK_L4_SEQUENCE_EQ0,
 					 seq_zero);
-			vcap_key_bit_set(ocelot, &data, VCAP_IS2_HK_L4_FIN,
+			vcap_key_bit_set(vcap, &data, VCAP_IS2_HK_L4_FIN,
 					 tcp_fin);
-			vcap_key_bit_set(ocelot, &data, VCAP_IS2_HK_L4_SYN,
+			vcap_key_bit_set(vcap, &data, VCAP_IS2_HK_L4_SYN,
 					 tcp_syn);
-			vcap_key_bit_set(ocelot, &data, VCAP_IS2_HK_L4_RST,
+			vcap_key_bit_set(vcap, &data, VCAP_IS2_HK_L4_RST,
 					 tcp_rst);
-			vcap_key_bit_set(ocelot, &data, VCAP_IS2_HK_L4_PSH,
+			vcap_key_bit_set(vcap, &data, VCAP_IS2_HK_L4_PSH,
 					 tcp_psh);
-			vcap_key_bit_set(ocelot, &data, VCAP_IS2_HK_L4_ACK,
+			vcap_key_bit_set(vcap, &data, VCAP_IS2_HK_L4_ACK,
 					 tcp_ack);
-			vcap_key_bit_set(ocelot, &data, VCAP_IS2_HK_L4_URG,
+			vcap_key_bit_set(vcap, &data, VCAP_IS2_HK_L4_URG,
 					 tcp_urg);
-			vcap_key_set(ocelot, &data, VCAP_IS2_HK_L4_1588_DOM,
+			vcap_key_set(vcap, &data, VCAP_IS2_HK_L4_1588_DOM,
 				     0, 0);
-			vcap_key_set(ocelot, &data, VCAP_IS2_HK_L4_1588_VER,
+			vcap_key_set(vcap, &data, VCAP_IS2_HK_L4_1588_VER,
 				     0, 0);
 		} else {
 			if (msk == 0) {
@@ -598,10 +608,10 @@ static void is2_entry_set(struct ocelot *ocelot, int ix,
 					payload.mask[i] = ip_data->mask[i];
 				}
 			}
-			vcap_key_bytes_set(ocelot, &data,
+			vcap_key_bytes_set(vcap, &data,
 					   VCAP_IS2_HK_IP4_L3_PROTO,
 					   proto.value, proto.mask);
-			vcap_key_bytes_set(ocelot, &data,
+			vcap_key_bytes_set(vcap, &data,
 					   VCAP_IS2_HK_L3_PAYLOAD,
 					   payload.value, payload.mask);
 		}
@@ -611,46 +621,271 @@ static void is2_entry_set(struct ocelot *ocelot, int ix,
 	default:
 		type = 0;
 		type_mask = 0;
-		count = vcap_is2->entry_width / 2;
+		count = vcap->entry_width / 2;
 		/* Iterate over the non-common part of the key and
 		 * clear entry data
 		 */
-		for (i = ocelot->vcap_is2_keys[VCAP_IS2_HK_L2_DMAC].offset;
+		for (i = vcap->keys[VCAP_IS2_HK_L2_DMAC].offset;
 		     i < count; i += ENTRY_WIDTH) {
 			vcap_key_field_set(&data, i, min(32u, count - i), 0, 0);
 		}
 		break;
 	}
 
-	vcap_key_set(ocelot, &data, VCAP_IS2_TYPE, type, type_mask);
+	vcap_key_set(vcap, &data, VCAP_IS2_TYPE, type, type_mask);
 	is2_action_set(ocelot, &data, filter);
 	vcap_data_set(data.counter, data.counter_offset,
-		      vcap_is2->counter_width, filter->stats.pkts);
+		      vcap->counter_width, filter->stats.pkts);
 
 	/* Write row */
-	vcap_entry2cache(ocelot, &data);
-	vcap_action2cache(ocelot, &data);
-	vcap_row_cmd(ocelot, row, VCAP_CMD_WRITE, VCAP_SEL_ALL);
+	vcap_entry2cache(ocelot, vcap, &data);
+	vcap_action2cache(ocelot, vcap, &data);
+	vcap_row_cmd(ocelot, vcap, row, VCAP_CMD_WRITE, VCAP_SEL_ALL);
+}
+
+static void is1_action_set(struct ocelot *ocelot, struct vcap_data *data,
+			   const struct ocelot_vcap_filter *filter)
+{
+	const struct vcap_props *vcap = &ocelot->vcap[VCAP_IS1];
+	const struct ocelot_vcap_action *a = &filter->action;
+
+	vcap_action_set(vcap, data, VCAP_IS1_ACT_VID_REPLACE_ENA,
+			a->vid_replace_ena);
+	vcap_action_set(vcap, data, VCAP_IS1_ACT_VID_ADD_VAL, a->vid);
+	vcap_action_set(vcap, data, VCAP_IS1_ACT_VLAN_POP_CNT_ENA,
+			a->vlan_pop_cnt_ena);
+	vcap_action_set(vcap, data, VCAP_IS1_ACT_VLAN_POP_CNT,
+			a->vlan_pop_cnt);
+	vcap_action_set(vcap, data, VCAP_IS1_ACT_PCP_DEI_ENA, a->pcp_dei_ena);
+	vcap_action_set(vcap, data, VCAP_IS1_ACT_PCP_VAL, a->pcp);
+	vcap_action_set(vcap, data, VCAP_IS1_ACT_DEI_VAL, a->dei);
+	vcap_action_set(vcap, data, VCAP_IS1_ACT_QOS_ENA, a->qos_ena);
+	vcap_action_set(vcap, data, VCAP_IS1_ACT_QOS_VAL, a->qos_val);
+	vcap_action_set(vcap, data, VCAP_IS1_ACT_PAG_OVERRIDE_MASK,
+			a->pag_override_mask);
+	vcap_action_set(vcap, data, VCAP_IS1_ACT_PAG_VAL, a->pag_val);
 }
 
-static void is2_entry_get(struct ocelot *ocelot, struct ocelot_vcap_filter *filter,
-			  int ix)
+static void is1_entry_set(struct ocelot *ocelot, int ix,
+			  struct ocelot_vcap_filter *filter)
 {
-	const struct vcap_props *vcap_is2 = &ocelot->vcap[VCAP_IS2];
+	const struct vcap_props *vcap = &ocelot->vcap[VCAP_IS1];
+	struct ocelot_vcap_key_vlan *tag = &filter->vlan;
+	struct ocelot_vcap_u64 payload;
 	struct vcap_data data;
-	int row = (ix / 2);
-	u32 cnt;
+	int row = ix / 2;
+	u32 type;
+
+	memset(&payload, 0, sizeof(payload));
+	memset(&data, 0, sizeof(data));
+
+	/* Read row */
+	vcap_row_cmd(ocelot, vcap, row, VCAP_CMD_READ, VCAP_SEL_ALL);
+	vcap_cache2entry(ocelot, vcap, &data);
+	vcap_cache2action(ocelot, vcap, &data);
 
-	vcap_row_cmd(ocelot, row, VCAP_CMD_READ, VCAP_SEL_COUNTER);
-	vcap_cache2action(ocelot, &data);
 	data.tg_sw = VCAP_TG_HALF;
-	is2_data_get(ocelot, &data, ix);
+	data.type = IS1_ACTION_TYPE_NORMAL;
+	vcap_data_offset_get(vcap, &data, ix);
+	data.tg = (data.tg & ~data.tg_mask);
+	if (filter->prio != 0)
+		data.tg |= data.tg_value;
+
+	vcap_key_set(vcap, &data, VCAP_IS1_HK_LOOKUP, filter->lookup, 0x3);
+	vcap_key_set(vcap, &data, VCAP_IS1_HK_IGR_PORT_MASK, 0,
+		     ~filter->ingress_port_mask);
+	vcap_key_bit_set(vcap, &data, VCAP_IS1_HK_L2_MC, filter->dmac_mc);
+	vcap_key_bit_set(vcap, &data, VCAP_IS1_HK_L2_BC, filter->dmac_bc);
+	vcap_key_bit_set(vcap, &data, VCAP_IS1_HK_VLAN_TAGGED, tag->tagged);
+	vcap_key_set(vcap, &data, VCAP_IS1_HK_VID,
+		     tag->vid.value, tag->vid.mask);
+	vcap_key_set(vcap, &data, VCAP_IS1_HK_PCP,
+		     tag->pcp.value[0], tag->pcp.mask[0]);
+	type = IS1_TYPE_S1_NORMAL;
+
+	switch (filter->key_type) {
+	case OCELOT_VCAP_KEY_ETYPE: {
+		struct ocelot_vcap_key_etype *etype = &filter->key.etype;
+
+		vcap_key_bytes_set(vcap, &data, VCAP_IS1_HK_L2_SMAC,
+				   etype->smac.value, etype->smac.mask);
+		vcap_key_bytes_set(vcap, &data, VCAP_IS1_HK_ETYPE,
+				   etype->etype.value, etype->etype.mask);
+		break;
+	}
+	case OCELOT_VCAP_KEY_IPV4: {
+		struct ocelot_vcap_key_ipv4 *ipv4 = &filter->key.ipv4;
+		struct ocelot_vcap_udp_tcp *sport = &ipv4->sport;
+		struct ocelot_vcap_udp_tcp *dport = &ipv4->dport;
+		enum ocelot_vcap_bit tcp_udp = OCELOT_VCAP_BIT_0;
+		struct ocelot_vcap_u8 proto = ipv4->proto;
+		struct ocelot_vcap_ipv4 sip = ipv4->sip;
+		u32 val, msk;
+
+		vcap_key_bit_set(vcap, &data, VCAP_IS1_HK_IP_SNAP,
+				 OCELOT_VCAP_BIT_1);
+		vcap_key_bit_set(vcap, &data, VCAP_IS1_HK_IP4,
+				 OCELOT_VCAP_BIT_1);
+		vcap_key_bit_set(vcap, &data, VCAP_IS1_HK_ETYPE_LEN,
+				 OCELOT_VCAP_BIT_1);
+		vcap_key_bytes_set(vcap, &data, VCAP_IS1_HK_L3_IP4_SIP,
+				   sip.value.addr, sip.mask.addr);
+
+		val = proto.value[0];
+		msk = proto.mask[0];
+
+		if ((val == NEXTHDR_TCP || val == NEXTHDR_UDP) && msk == 0xff)
+			tcp_udp = OCELOT_VCAP_BIT_1;
+		vcap_key_bit_set(vcap, &data, VCAP_IS1_HK_TCP_UDP, tcp_udp);
+
+		if (tcp_udp) {
+			enum ocelot_vcap_bit tcp = OCELOT_VCAP_BIT_0;
+
+			if (val == NEXTHDR_TCP)
+				tcp = OCELOT_VCAP_BIT_1;
+
+			vcap_key_bit_set(vcap, &data, VCAP_IS1_HK_TCP, tcp);
+			vcap_key_l4_port_set(vcap, &data, VCAP_IS1_HK_L4_SPORT,
+					     sport);
+			/* Overloaded field */
+			vcap_key_l4_port_set(vcap, &data, VCAP_IS1_HK_ETYPE,
+					     dport);
+		} else {
+			/* IPv4 "other" frame */
+			struct ocelot_vcap_u16 etype = {0};
+
+			/* Overloaded field */
+			etype.value[0] = proto.value[0];
+			etype.mask[0] = proto.mask[0];
+
+			vcap_key_bytes_set(vcap, &data, VCAP_IS1_HK_ETYPE,
+					   etype.value, etype.mask);
+		}
+	}
+	default:
+		break;
+	}
+	vcap_key_bit_set(vcap, &data, VCAP_IS1_HK_TYPE,
+			 type ? OCELOT_VCAP_BIT_1 : OCELOT_VCAP_BIT_0);
+
+	is1_action_set(ocelot, &data, filter);
+	vcap_data_set(data.counter, data.counter_offset,
+		      vcap->counter_width, filter->stats.pkts);
+
+	/* Write row */
+	vcap_entry2cache(ocelot, vcap, &data);
+	vcap_action2cache(ocelot, vcap, &data);
+	vcap_row_cmd(ocelot, vcap, row, VCAP_CMD_WRITE, VCAP_SEL_ALL);
+}
+
+static void es0_action_set(struct ocelot *ocelot, struct vcap_data *data,
+			   const struct ocelot_vcap_filter *filter)
+{
+	const struct vcap_props *vcap = &ocelot->vcap[VCAP_ES0];
+	const struct ocelot_vcap_action *a = &filter->action;
+
+	vcap_action_set(vcap, data, VCAP_ES0_ACT_PUSH_OUTER_TAG,
+			a->push_outer_tag);
+	vcap_action_set(vcap, data, VCAP_ES0_ACT_PUSH_INNER_TAG,
+			a->push_inner_tag);
+	vcap_action_set(vcap, data, VCAP_ES0_ACT_TAG_A_TPID_SEL,
+			a->tag_a_tpid_sel);
+	vcap_action_set(vcap, data, VCAP_ES0_ACT_TAG_A_VID_SEL,
+			a->tag_a_vid_sel);
+	vcap_action_set(vcap, data, VCAP_ES0_ACT_TAG_A_PCP_SEL,
+			a->tag_a_pcp_sel);
+	vcap_action_set(vcap, data, VCAP_ES0_ACT_VID_A_VAL, a->vid_a_val);
+	vcap_action_set(vcap, data, VCAP_ES0_ACT_PCP_A_VAL, a->pcp_a_val);
+	vcap_action_set(vcap, data, VCAP_ES0_ACT_TAG_B_TPID_SEL,
+			a->tag_b_tpid_sel);
+	vcap_action_set(vcap, data, VCAP_ES0_ACT_TAG_B_VID_SEL,
+			a->tag_b_vid_sel);
+	vcap_action_set(vcap, data, VCAP_ES0_ACT_TAG_B_PCP_SEL,
+			a->tag_b_pcp_sel);
+	vcap_action_set(vcap, data, VCAP_ES0_ACT_VID_B_VAL, a->vid_b_val);
+	vcap_action_set(vcap, data, VCAP_ES0_ACT_PCP_B_VAL, a->pcp_b_val);
+}
+
+static void es0_entry_set(struct ocelot *ocelot, int ix,
+			  struct ocelot_vcap_filter *filter)
+{
+	const struct vcap_props *vcap = &ocelot->vcap[VCAP_ES0];
+	struct ocelot_vcap_key_vlan *tag = &filter->vlan;
+	struct ocelot_vcap_u64 payload;
+	struct vcap_data data;
+	int row = ix;
+
+	memset(&payload, 0, sizeof(payload));
+	memset(&data, 0, sizeof(data));
+
+	/* Read row */
+	vcap_row_cmd(ocelot, vcap, row, VCAP_CMD_READ, VCAP_SEL_ALL);
+	vcap_cache2entry(ocelot, vcap, &data);
+	vcap_cache2action(ocelot, vcap, &data);
+
+	data.tg_sw = VCAP_TG_FULL;
+	data.type = ES0_ACTION_TYPE_NORMAL;
+	vcap_data_offset_get(vcap, &data, ix);
+	data.tg = (data.tg & ~data.tg_mask);
+	if (filter->prio != 0)
+		data.tg |= data.tg_value;
+
+	vcap_key_set(vcap, &data, VCAP_ES0_IGR_PORT, filter->ingress_port.value,
+		     filter->ingress_port.mask);
+	vcap_key_set(vcap, &data, VCAP_ES0_EGR_PORT, filter->egress_port.value,
+		     filter->egress_port.mask);
+	vcap_key_bit_set(vcap, &data, VCAP_ES0_L2_MC, filter->dmac_mc);
+	vcap_key_bit_set(vcap, &data, VCAP_ES0_L2_BC, filter->dmac_bc);
+	vcap_key_set(vcap, &data, VCAP_ES0_VID,
+		     tag->vid.value, tag->vid.mask);
+	vcap_key_set(vcap, &data, VCAP_ES0_PCP,
+		     tag->pcp.value[0], tag->pcp.mask[0]);
+
+	es0_action_set(ocelot, &data, filter);
+	vcap_data_set(data.counter, data.counter_offset,
+		      vcap->counter_width, filter->stats.pkts);
+
+	/* Write row */
+	vcap_entry2cache(ocelot, vcap, &data);
+	vcap_action2cache(ocelot, vcap, &data);
+	vcap_row_cmd(ocelot, vcap, row, VCAP_CMD_WRITE, VCAP_SEL_ALL);
+}
+
+static void vcap_entry_get(struct ocelot *ocelot, int ix,
+			   struct ocelot_vcap_filter *filter)
+{
+	const struct vcap_props *vcap = &ocelot->vcap[filter->block_id];
+	struct vcap_data data;
+	int row, count;
+	u32 cnt;
+
+	if (filter->block_id == VCAP_ES0)
+		data.tg_sw = VCAP_TG_FULL;
+	else
+		data.tg_sw = VCAP_TG_HALF;
+
+	count = (1 << (data.tg_sw - 1));
+	row = (ix / count);
+	vcap_row_cmd(ocelot, vcap, row, VCAP_CMD_READ, VCAP_SEL_COUNTER);
+	vcap_cache2action(ocelot, vcap, &data);
+	vcap_data_offset_get(vcap, &data, ix);
 	cnt = vcap_data_get(data.counter, data.counter_offset,
-			    vcap_is2->counter_width);
+			    vcap->counter_width);
 
 	filter->stats.pkts = cnt;
 }
 
+static void vcap_entry_set(struct ocelot *ocelot, int ix,
+			   struct ocelot_vcap_filter *filter)
+{
+	if (filter->block_id == VCAP_IS1)
+		return is1_entry_set(ocelot, ix, filter);
+	if (filter->block_id == VCAP_IS2)
+		return is2_entry_set(ocelot, ix, filter);
+	if (filter->block_id == VCAP_ES0)
+		return es0_entry_set(ocelot, ix, filter);
+}
+
 static int ocelot_vcap_policer_add(struct ocelot *ocelot, u32 pol_ix,
 				   struct ocelot_policer *pol)
 {
@@ -679,11 +914,12 @@ static void ocelot_vcap_policer_del(struct ocelot *ocelot,
 
 	list_for_each_entry(filter, &block->rules, list) {
 		index++;
-		if (filter->action == OCELOT_VCAP_ACTION_POLICE &&
-		    filter->pol_ix < pol_ix) {
-			filter->pol_ix += 1;
-			ocelot_vcap_policer_add(ocelot, filter->pol_ix,
-						&filter->pol);
+		if (filter->block_id == VCAP_IS2 &&
+		    filter->action.police_ena &&
+		    filter->action.pol_ix < pol_ix) {
+			filter->action.pol_ix += 1;
+			ocelot_vcap_policer_add(ocelot, filter->action.pol_ix,
+						&filter->action.pol);
 			is2_entry_set(ocelot, index, filter);
 		}
 	}
@@ -701,10 +937,11 @@ static void ocelot_vcap_filter_add_to_block(struct ocelot *ocelot,
 	struct ocelot_vcap_filter *tmp;
 	struct list_head *pos, *n;
 
-	if (filter->action == OCELOT_VCAP_ACTION_POLICE) {
+	if (filter->block_id == VCAP_IS2 && filter->action.police_ena) {
 		block->pol_lpr--;
-		filter->pol_ix = block->pol_lpr;
-		ocelot_vcap_policer_add(ocelot, filter->pol_ix, &filter->pol);
+		filter->action.pol_ix = block->pol_lpr;
+		ocelot_vcap_policer_add(ocelot, filter->action.pol_ix,
+					&filter->action.pol);
 	}
 
 	block->count++;
@@ -726,19 +963,20 @@ static int ocelot_vcap_block_get_filter_index(struct ocelot_vcap_block *block,
 					      struct ocelot_vcap_filter *filter)
 {
 	struct ocelot_vcap_filter *tmp;
-	int index = -1;
+	int index = 0;
 
 	list_for_each_entry(tmp, &block->rules, list) {
-		++index;
 		if (filter->id == tmp->id)
-			break;
+			return index;
+		index++;
 	}
-	return index;
+
+	return -ENOENT;
 }
 
 static struct ocelot_vcap_filter*
-ocelot_vcap_block_find_filter(struct ocelot_vcap_block *block,
-			      int index)
+ocelot_vcap_block_find_filter_by_index(struct ocelot_vcap_block *block,
+				       int index)
 {
 	struct ocelot_vcap_filter *tmp;
 	int i = 0;
@@ -752,6 +990,18 @@ ocelot_vcap_block_find_filter(struct ocelot_vcap_block *block,
 	return NULL;
 }
 
+struct ocelot_vcap_filter *
+ocelot_vcap_block_find_filter_by_id(struct ocelot_vcap_block *block, int id)
+{
+	struct ocelot_vcap_filter *filter;
+
+	list_for_each_entry(filter, &block->rules, list)
+		if (filter->id == id)
+			return filter;
+
+	return NULL;
+}
+
 /* If @on=false, then SNAP, ARP, IP and OAM frames will not match on keys based
  * on destination and source MAC addresses, but only on higher-level protocol
  * information. The only frame types to match on keys containing MAC addresses
@@ -763,23 +1013,23 @@ ocelot_vcap_block_find_filter(struct ocelot_vcap_block *block,
  * on any _other_ keys than MAC_ETYPE ones.
  */
 static void ocelot_match_all_as_mac_etype(struct ocelot *ocelot, int port,
-					  bool on)
+					  int lookup, bool on)
 {
 	u32 val = 0;
 
 	if (on)
-		val = ANA_PORT_VCAP_S2_CFG_S2_SNAP_DIS(3) |
-		      ANA_PORT_VCAP_S2_CFG_S2_ARP_DIS(3) |
-		      ANA_PORT_VCAP_S2_CFG_S2_IP_TCPUDP_DIS(3) |
-		      ANA_PORT_VCAP_S2_CFG_S2_IP_OTHER_DIS(3) |
-		      ANA_PORT_VCAP_S2_CFG_S2_OAM_DIS(3);
+		val = ANA_PORT_VCAP_S2_CFG_S2_SNAP_DIS(BIT(lookup)) |
+		      ANA_PORT_VCAP_S2_CFG_S2_ARP_DIS(BIT(lookup)) |
+		      ANA_PORT_VCAP_S2_CFG_S2_IP_TCPUDP_DIS(BIT(lookup)) |
+		      ANA_PORT_VCAP_S2_CFG_S2_IP_OTHER_DIS(BIT(lookup)) |
+		      ANA_PORT_VCAP_S2_CFG_S2_OAM_DIS(BIT(lookup));
 
 	ocelot_rmw_gix(ocelot, val,
-		       ANA_PORT_VCAP_S2_CFG_S2_SNAP_DIS_M |
-		       ANA_PORT_VCAP_S2_CFG_S2_ARP_DIS_M |
-		       ANA_PORT_VCAP_S2_CFG_S2_IP_TCPUDP_DIS_M |
-		       ANA_PORT_VCAP_S2_CFG_S2_IP_OTHER_DIS_M |
-		       ANA_PORT_VCAP_S2_CFG_S2_OAM_DIS_M,
+		       ANA_PORT_VCAP_S2_CFG_S2_SNAP_DIS(BIT(lookup)) |
+		       ANA_PORT_VCAP_S2_CFG_S2_ARP_DIS(BIT(lookup)) |
+		       ANA_PORT_VCAP_S2_CFG_S2_IP_TCPUDP_DIS(BIT(lookup)) |
+		       ANA_PORT_VCAP_S2_CFG_S2_IP_OTHER_DIS(BIT(lookup)) |
+		       ANA_PORT_VCAP_S2_CFG_S2_OAM_DIS(BIT(lookup)),
 		       ANA_PORT_VCAP_S2_CFG, port);
 }
 
@@ -825,35 +1075,43 @@ static bool
 ocelot_exclusive_mac_etype_filter_rules(struct ocelot *ocelot,
 					struct ocelot_vcap_filter *filter)
 {
-	struct ocelot_vcap_block *block = &ocelot->block;
+	struct ocelot_vcap_block *block = &ocelot->block[filter->block_id];
 	struct ocelot_vcap_filter *tmp;
 	unsigned long port;
 	int i;
 
+	/* We only have the S2_IP_TCPUDP_DIS set of knobs for VCAP IS2 */
+	if (filter->block_id != VCAP_IS2)
+		return true;
+
 	if (ocelot_vcap_is_problematic_mac_etype(filter)) {
 		/* Search for any non-MAC_ETYPE rules on the port */
 		for (i = 0; i < block->count; i++) {
-			tmp = ocelot_vcap_block_find_filter(block, i);
+			tmp = ocelot_vcap_block_find_filter_by_index(block, i);
 			if (tmp->ingress_port_mask & filter->ingress_port_mask &&
+			    tmp->lookup == filter->lookup &&
 			    ocelot_vcap_is_problematic_non_mac_etype(tmp))
 				return false;
 		}
 
 		for_each_set_bit(port, &filter->ingress_port_mask,
 				 ocelot->num_phys_ports)
-			ocelot_match_all_as_mac_etype(ocelot, port, true);
+			ocelot_match_all_as_mac_etype(ocelot, port,
+						      filter->lookup, true);
 	} else if (ocelot_vcap_is_problematic_non_mac_etype(filter)) {
 		/* Search for any MAC_ETYPE rules on the port */
 		for (i = 0; i < block->count; i++) {
-			tmp = ocelot_vcap_block_find_filter(block, i);
+			tmp = ocelot_vcap_block_find_filter_by_index(block, i);
 			if (tmp->ingress_port_mask & filter->ingress_port_mask &&
+			    tmp->lookup == filter->lookup &&
 			    ocelot_vcap_is_problematic_mac_etype(tmp))
 				return false;
 		}
 
 		for_each_set_bit(port, &filter->ingress_port_mask,
 				 ocelot->num_phys_ports)
-			ocelot_match_all_as_mac_etype(ocelot, port, false);
+			ocelot_match_all_as_mac_etype(ocelot, port,
+						      filter->lookup, false);
 	}
 
 	return true;
@@ -863,12 +1121,12 @@ int ocelot_vcap_filter_add(struct ocelot *ocelot,
 			   struct ocelot_vcap_filter *filter,
 			   struct netlink_ext_ack *extack)
 {
-	struct ocelot_vcap_block *block = &ocelot->block;
+	struct ocelot_vcap_block *block = &ocelot->block[filter->block_id];
 	int i, index;
 
 	if (!ocelot_exclusive_mac_etype_filter_rules(ocelot, filter)) {
 		NL_SET_ERR_MSG_MOD(extack,
-				   "Cannot mix MAC_ETYPE with non-MAC_ETYPE rules");
+				   "Cannot mix MAC_ETYPE with non-MAC_ETYPE rules, use the other IS2 lookup");
 		return -EBUSY;
 	}
 
@@ -877,17 +1135,19 @@ int ocelot_vcap_filter_add(struct ocelot *ocelot,
 
 	/* Get the index of the inserted filter */
 	index = ocelot_vcap_block_get_filter_index(block, filter);
+	if (index < 0)
+		return index;
 
 	/* Move down the rules to make place for the new filter */
 	for (i = block->count - 1; i > index; i--) {
 		struct ocelot_vcap_filter *tmp;
 
-		tmp = ocelot_vcap_block_find_filter(block, i);
-		is2_entry_set(ocelot, i, tmp);
+		tmp = ocelot_vcap_block_find_filter_by_index(block, i);
+		vcap_entry_set(ocelot, i, tmp);
 	}
 
 	/* Now insert the new filter */
-	is2_entry_set(ocelot, index, filter);
+	vcap_entry_set(ocelot, index, filter);
 	return 0;
 }
 
@@ -901,9 +1161,10 @@ static void ocelot_vcap_block_remove_filter(struct ocelot *ocelot,
 	list_for_each_safe(pos, q, &block->rules) {
 		tmp = list_entry(pos, struct ocelot_vcap_filter, list);
 		if (tmp->id == filter->id) {
-			if (tmp->action == OCELOT_VCAP_ACTION_POLICE)
+			if (tmp->block_id == VCAP_IS2 &&
+			    tmp->action.police_ena)
 				ocelot_vcap_policer_del(ocelot, block,
-							tmp->pol_ix);
+							tmp->action.pol_ix);
 
 			list_del(pos);
 			kfree(tmp);
@@ -916,7 +1177,7 @@ static void ocelot_vcap_block_remove_filter(struct ocelot *ocelot,
 int ocelot_vcap_filter_del(struct ocelot *ocelot,
 			   struct ocelot_vcap_filter *filter)
 {
-	struct ocelot_vcap_block *block = &ocelot->block;
+	struct ocelot_vcap_block *block = &ocelot->block[filter->block_id];
 	struct ocelot_vcap_filter del_filter;
 	int i, index;
 
@@ -924,6 +1185,8 @@ int ocelot_vcap_filter_del(struct ocelot *ocelot,
 
 	/* Gets index of the filter */
 	index = ocelot_vcap_block_get_filter_index(block, filter);
+	if (index < 0)
+		return index;
 
 	/* Delete filter */
 	ocelot_vcap_block_remove_filter(ocelot, block, filter);
@@ -932,12 +1195,12 @@ int ocelot_vcap_filter_del(struct ocelot *ocelot,
 	for (i = index; i < block->count; i++) {
 		struct ocelot_vcap_filter *tmp;
 
-		tmp = ocelot_vcap_block_find_filter(block, i);
-		is2_entry_set(ocelot, i, tmp);
+		tmp = ocelot_vcap_block_find_filter_by_index(block, i);
+		vcap_entry_set(ocelot, i, tmp);
 	}
 
 	/* Now delete the last filter, because it is duplicated */
-	is2_entry_set(ocelot, block->count, &del_filter);
+	vcap_entry_set(ocelot, block->count, &del_filter);
 
 	return 0;
 }
@@ -945,37 +1208,115 @@ int ocelot_vcap_filter_del(struct ocelot *ocelot,
 int ocelot_vcap_filter_stats_update(struct ocelot *ocelot,
 				    struct ocelot_vcap_filter *filter)
 {
-	struct ocelot_vcap_block *block = &ocelot->block;
-	struct ocelot_vcap_filter *tmp;
+	struct ocelot_vcap_block *block = &ocelot->block[filter->block_id];
+	struct ocelot_vcap_filter tmp;
 	int index;
 
 	index = ocelot_vcap_block_get_filter_index(block, filter);
-	is2_entry_get(ocelot, filter, index);
+	if (index < 0)
+		return index;
+
+	vcap_entry_get(ocelot, index, filter);
 
 	/* After we get the result we need to clear the counters */
-	tmp = ocelot_vcap_block_find_filter(block, index);
-	tmp->stats.pkts = 0;
-	is2_entry_set(ocelot, index, tmp);
+	tmp = *filter;
+	tmp.stats.pkts = 0;
+	vcap_entry_set(ocelot, index, &tmp);
 
 	return 0;
 }
 
-int ocelot_vcap_init(struct ocelot *ocelot)
+static void ocelot_vcap_init_one(struct ocelot *ocelot,
+				 const struct vcap_props *vcap)
 {
-	const struct vcap_props *vcap_is2 = &ocelot->vcap[VCAP_IS2];
-	struct ocelot_vcap_block *block = &ocelot->block;
 	struct vcap_data data;
 
 	memset(&data, 0, sizeof(data));
 
-	vcap_entry2cache(ocelot, &data);
-	ocelot_write(ocelot, vcap_is2->entry_count, S2_CORE_MV_CFG);
-	vcap_cmd(ocelot, 0, VCAP_CMD_INITIALIZE, VCAP_SEL_ENTRY);
+	vcap_entry2cache(ocelot, vcap, &data);
+	ocelot_target_write(ocelot, vcap->target, vcap->entry_count,
+			    VCAP_CORE_MV_CFG);
+	vcap_cmd(ocelot, vcap, 0, VCAP_CMD_INITIALIZE, VCAP_SEL_ENTRY);
 
-	vcap_action2cache(ocelot, &data);
-	ocelot_write(ocelot, vcap_is2->action_count, S2_CORE_MV_CFG);
-	vcap_cmd(ocelot, 0, VCAP_CMD_INITIALIZE,
+	vcap_action2cache(ocelot, vcap, &data);
+	ocelot_target_write(ocelot, vcap->target, vcap->action_count,
+			    VCAP_CORE_MV_CFG);
+	vcap_cmd(ocelot, vcap, 0, VCAP_CMD_INITIALIZE,
 		 VCAP_SEL_ACTION | VCAP_SEL_COUNTER);
+}
+
+static void ocelot_vcap_detect_constants(struct ocelot *ocelot,
+					 struct vcap_props *vcap)
+{
+	int counter_memory_width;
+	int num_default_actions;
+	int version;
+
+	version = ocelot_target_read(ocelot, vcap->target,
+				     VCAP_CONST_VCAP_VER);
+	/* Only version 0 VCAP supported for now */
+	if (WARN_ON(version != 0))
+		return;
+
+	/* Width in bits of type-group field */
+	vcap->tg_width = ocelot_target_read(ocelot, vcap->target,
+					    VCAP_CONST_ENTRY_TG_WIDTH);
+	/* Number of subwords per TCAM row */
+	vcap->sw_count = ocelot_target_read(ocelot, vcap->target,
+					    VCAP_CONST_ENTRY_SWCNT);
+	/* Number of rows in TCAM. There can be this many full keys, or double
+	 * this number half keys, or 4 times this number quarter keys.
+	 */
+	vcap->entry_count = ocelot_target_read(ocelot, vcap->target,
+					       VCAP_CONST_ENTRY_CNT);
+	/* Assuming there are 4 subwords per TCAM row, their layout in the
+	 * actual TCAM (not in the cache) would be:
+	 *
+	 * |  SW 3  | TG 3 |  SW 2  | TG 2 |  SW 1  | TG 1 |  SW 0  | TG 0 |
+	 *
+	 * (where SW=subword and TG=Type-Group).
+	 *
+	 * What VCAP_CONST_ENTRY_CNT is giving us is the width of one full TCAM
+	 * row. But when software accesses the TCAM through the cache
+	 * registers, the Type-Group values are written through another set of
+	 * registers VCAP_TG_DAT, and therefore, it appears as though the 4
+	 * subwords are contiguous in the cache memory.
+	 * Important mention: regardless of the number of key entries per row
+	 * (and therefore of key size: 1 full key or 2 half keys or 4 quarter
+	 * keys), software always has to configure 4 Type-Group values. For
+	 * example, in the case of 1 full key, the driver needs to set all 4
+	 * Type-Group to be full key.
+	 *
+	 * For this reason, we need to fix up the value that the hardware is
+	 * giving us. We don't actually care about the width of the entry in
+	 * the TCAM. What we care about is the width of the entry in the cache
+	 * registers, which is how we get to interact with it. And since the
+	 * VCAP_ENTRY_DAT cache registers access only the subwords and not the
+	 * Type-Groups, this means we need to subtract the width of the
+	 * Type-Groups when packing and unpacking key entry data in a TCAM row.
+	 */
+	vcap->entry_width = ocelot_target_read(ocelot, vcap->target,
+					       VCAP_CONST_ENTRY_WIDTH);
+	vcap->entry_width -= vcap->tg_width * vcap->sw_count;
+	num_default_actions = ocelot_target_read(ocelot, vcap->target,
+						 VCAP_CONST_ACTION_DEF_CNT);
+	vcap->action_count = vcap->entry_count + num_default_actions;
+	vcap->action_width = ocelot_target_read(ocelot, vcap->target,
+						VCAP_CONST_ACTION_WIDTH);
+	/* The width of the counter memory, this is the complete width of all
+	 * counter-fields associated with one full-word entry. There is one
+	 * counter per entry sub-word (see CAP_CORE::ENTRY_SWCNT for number of
+	 * subwords.)
+	 */
+	vcap->counter_words = vcap->sw_count;
+	counter_memory_width = ocelot_target_read(ocelot, vcap->target,
+						  VCAP_CONST_CNT_WIDTH);
+	vcap->counter_width = counter_memory_width / vcap->counter_words;
+}
+
+int ocelot_vcap_init(struct ocelot *ocelot)
+{
+	int i;
 
 	/* Create a policer that will drop the frames for the cpu.
 	 * This policer will be used as action in the acl rules to drop
@@ -992,9 +1333,18 @@ int ocelot_vcap_init(struct ocelot *ocelot)
 	ocelot_write_gix(ocelot, 0x3fffff, ANA_POL_CIR_STATE,
 			 OCELOT_POLICER_DISCARD);
 
-	block->pol_lpr = OCELOT_POLICER_DISCARD - 1;
+	for (i = 0; i < OCELOT_NUM_VCAP_BLOCKS; i++) {
+		struct ocelot_vcap_block *block = &ocelot->block[i];
+		struct vcap_props *vcap = &ocelot->vcap[i];
+
+		INIT_LIST_HEAD(&block->rules);
+		block->pol_lpr = OCELOT_POLICER_DISCARD - 1;
+
+		ocelot_vcap_detect_constants(ocelot, vcap);
+		ocelot_vcap_init_one(ocelot, vcap);
+	}
 
-	INIT_LIST_HEAD(&ocelot->block.rules);
+	INIT_LIST_HEAD(&ocelot->dummy_rules);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/mscc/ocelot_vcap.h b/drivers/net/ethernet/mscc/ocelot_vcap.h
index 0dfbfc011b2e..82fd10581a14 100644
--- a/drivers/net/ethernet/mscc/ocelot_vcap.h
+++ b/drivers/net/ethernet/mscc/ocelot_vcap.h
@@ -11,6 +11,8 @@
 #include <net/sch_generic.h>
 #include <net/pkt_cls.h>
 
+#define OCELOT_POLICER_DISCARD 0x17f
+
 struct ocelot_ipv4 {
 	u8 addr[4];
 };
@@ -76,6 +78,11 @@ struct ocelot_vcap_udp_tcp {
 	u16 mask;
 };
 
+struct ocelot_vcap_port {
+	u8 value;
+	u8 mask;
+};
+
 enum ocelot_vcap_key_type {
 	OCELOT_VCAP_KEY_ANY,
 	OCELOT_VCAP_KEY_ETYPE,
@@ -158,6 +165,7 @@ struct ocelot_vcap_key_ipv4 {
 struct ocelot_vcap_key_ipv6 {
 	struct ocelot_vcap_u8 proto; /* IPv6 protocol */
 	struct ocelot_vcap_u128 sip; /* IPv6 source (byte 0-7 ignored) */
+	struct ocelot_vcap_u128 dip; /* IPv6 destination (byte 0-7 ignored) */
 	enum ocelot_vcap_bit ttl;  /* TTL zero */
 	struct ocelot_vcap_u8 ds;
 	struct ocelot_vcap_u48 data; /* Not UDP/TCP: IP data */
@@ -174,10 +182,71 @@ struct ocelot_vcap_key_ipv6 {
 	enum ocelot_vcap_bit seq_zero;       /* TCP sequence number is zero */
 };
 
-enum ocelot_vcap_action {
-	OCELOT_VCAP_ACTION_DROP,
-	OCELOT_VCAP_ACTION_TRAP,
-	OCELOT_VCAP_ACTION_POLICE,
+enum ocelot_mask_mode {
+	OCELOT_MASK_MODE_NONE,
+	OCELOT_MASK_MODE_PERMIT_DENY,
+	OCELOT_MASK_MODE_POLICY,
+	OCELOT_MASK_MODE_REDIRECT,
+};
+
+enum ocelot_es0_tag {
+	OCELOT_NO_ES0_TAG,
+	OCELOT_ES0_TAG,
+	OCELOT_FORCE_PORT_TAG,
+	OCELOT_FORCE_UNTAG,
+};
+
+enum ocelot_tag_tpid_sel {
+	OCELOT_TAG_TPID_SEL_8021Q,
+	OCELOT_TAG_TPID_SEL_8021AD,
+};
+
+struct ocelot_vcap_action {
+	union {
+		/* VCAP ES0 */
+		struct {
+			enum ocelot_es0_tag push_outer_tag;
+			enum ocelot_es0_tag push_inner_tag;
+			enum ocelot_tag_tpid_sel tag_a_tpid_sel;
+			int tag_a_vid_sel;
+			int tag_a_pcp_sel;
+			u16 vid_a_val;
+			u8 pcp_a_val;
+			u8 dei_a_val;
+			enum ocelot_tag_tpid_sel tag_b_tpid_sel;
+			int tag_b_vid_sel;
+			int tag_b_pcp_sel;
+			u16 vid_b_val;
+			u8 pcp_b_val;
+			u8 dei_b_val;
+		};
+
+		/* VCAP IS1 */
+		struct {
+			bool vid_replace_ena;
+			u16 vid;
+			bool vlan_pop_cnt_ena;
+			int vlan_pop_cnt;
+			bool pcp_dei_ena;
+			u8 pcp;
+			u8 dei;
+			bool qos_ena;
+			u8 qos_val;
+			u8 pag_override_mask;
+			u8 pag_val;
+		};
+
+		/* VCAP IS2 */
+		struct {
+			bool cpu_copy_ena;
+			u8 cpu_qu_num;
+			enum ocelot_mask_mode mask_mode;
+			unsigned long port_mask;
+			bool police_ena;
+			struct ocelot_policer pol;
+			u32 pol_ix;
+		};
+	};
 };
 
 struct ocelot_vcap_stats {
@@ -186,15 +255,30 @@ struct ocelot_vcap_stats {
 	u64 used;
 };
 
+enum ocelot_vcap_filter_type {
+	OCELOT_VCAP_FILTER_DUMMY,
+	OCELOT_VCAP_FILTER_PAG,
+	OCELOT_VCAP_FILTER_OFFLOAD,
+};
+
 struct ocelot_vcap_filter {
 	struct list_head list;
 
+	enum ocelot_vcap_filter_type type;
+	int block_id;
+	int goto_target;
+	int lookup;
+	u8 pag;
 	u16 prio;
 	u32 id;
 
-	enum ocelot_vcap_action action;
+	struct ocelot_vcap_action action;
 	struct ocelot_vcap_stats stats;
+	/* For VCAP IS1 and IS2 */
 	unsigned long ingress_port_mask;
+	/* For VCAP ES0 */
+	struct ocelot_vcap_port ingress_port;
+	struct ocelot_vcap_port egress_port;
 
 	enum ocelot_vcap_bit dmac_mc;
 	enum ocelot_vcap_bit dmac_bc;
@@ -210,8 +294,6 @@ struct ocelot_vcap_filter {
 		struct ocelot_vcap_key_ipv4 ipv4;
 		struct ocelot_vcap_key_ipv6 ipv6;
 	} key;
-	struct ocelot_policer pol;
-	u32 pol_ix;
 };
 
 int ocelot_vcap_filter_add(struct ocelot *ocelot,
@@ -221,7 +303,10 @@ int ocelot_vcap_filter_del(struct ocelot *ocelot,
 			   struct ocelot_vcap_filter *rule);
 int ocelot_vcap_filter_stats_update(struct ocelot *ocelot,
 				    struct ocelot_vcap_filter *rule);
+struct ocelot_vcap_filter *
+ocelot_vcap_block_find_filter_by_id(struct ocelot_vcap_block *block, int id);
 
+void ocelot_detect_vcap_constants(struct ocelot *ocelot);
 int ocelot_vcap_init(struct ocelot *ocelot);
 
 int ocelot_setup_tc_cls_flower(struct ocelot_port_private *priv,
diff --git a/drivers/net/ethernet/mscc/ocelot_vsc7514.c b/drivers/net/ethernet/mscc/ocelot_vsc7514.c
index 65408bc994c4..f3e54589e6d6 100644
--- a/drivers/net/ethernet/mscc/ocelot_vsc7514.c
+++ b/drivers/net/ethernet/mscc/ocelot_vsc7514.c
@@ -19,10 +19,6 @@
 #include "ocelot.h"
 
 #define IFH_EXTRACT_BITFIELD64(x, o, w) (((x) >> (o)) & GENMASK_ULL((w) - 1, 0))
-#define VSC7514_VCAP_IS2_CNT 64
-#define VSC7514_VCAP_IS2_ENTRY_WIDTH 376
-#define VSC7514_VCAP_IS2_ACTION_WIDTH 99
-#define VSC7514_VCAP_PORT_CNT 11
 
 static const u32 ocelot_ana_regmap[] = {
 	REG(ANA_ADVLEARN,				0x009000),
@@ -241,14 +237,27 @@ static const u32 ocelot_sys_regmap[] = {
 	REG(SYS_PTP_CFG,				0x0006c4),
 };
 
-static const u32 ocelot_s2_regmap[] = {
-	REG(S2_CORE_UPDATE_CTRL,			0x000000),
-	REG(S2_CORE_MV_CFG,				0x000004),
-	REG(S2_CACHE_ENTRY_DAT,				0x000008),
-	REG(S2_CACHE_MASK_DAT,				0x000108),
-	REG(S2_CACHE_ACTION_DAT,			0x000208),
-	REG(S2_CACHE_CNT_DAT,				0x000308),
-	REG(S2_CACHE_TG_DAT,				0x000388),
+static const u32 ocelot_vcap_regmap[] = {
+	/* VCAP_CORE_CFG */
+	REG(VCAP_CORE_UPDATE_CTRL,			0x000000),
+	REG(VCAP_CORE_MV_CFG,				0x000004),
+	/* VCAP_CORE_CACHE */
+	REG(VCAP_CACHE_ENTRY_DAT,			0x000008),
+	REG(VCAP_CACHE_MASK_DAT,			0x000108),
+	REG(VCAP_CACHE_ACTION_DAT,			0x000208),
+	REG(VCAP_CACHE_CNT_DAT,				0x000308),
+	REG(VCAP_CACHE_TG_DAT,				0x000388),
+	/* VCAP_CONST */
+	REG(VCAP_CONST_VCAP_VER,			0x000398),
+	REG(VCAP_CONST_ENTRY_WIDTH,			0x00039c),
+	REG(VCAP_CONST_ENTRY_CNT,			0x0003a0),
+	REG(VCAP_CONST_ENTRY_SWCNT,			0x0003a4),
+	REG(VCAP_CONST_ENTRY_TG_WIDTH,			0x0003a8),
+	REG(VCAP_CONST_ACTION_DEF_CNT,			0x0003ac),
+	REG(VCAP_CONST_ACTION_WIDTH,			0x0003b0),
+	REG(VCAP_CONST_CNT_WIDTH,			0x0003b4),
+	REG(VCAP_CONST_CORE_CNT,			0x0003b8),
+	REG(VCAP_CONST_IF_CNT,				0x0003bc),
 };
 
 static const u32 ocelot_ptp_regmap[] = {
@@ -311,7 +320,7 @@ static const u32 *ocelot_regmap[TARGET_MAX] = {
 	[QSYS] = ocelot_qsys_regmap,
 	[REW] = ocelot_rew_regmap,
 	[SYS] = ocelot_sys_regmap,
-	[S2] = ocelot_s2_regmap,
+	[S2] = ocelot_vcap_regmap,
 	[PTP] = ocelot_ptp_regmap,
 	[DEV_GMII] = ocelot_dev_gmii_regmap,
 };
@@ -754,6 +763,115 @@ static u16 ocelot_wm_enc(u16 value)
 static const struct ocelot_ops ocelot_ops = {
 	.reset			= ocelot_reset,
 	.wm_enc			= ocelot_wm_enc,
+	.port_to_netdev		= ocelot_port_to_netdev,
+	.netdev_to_port		= ocelot_netdev_to_port,
+};
+
+static const struct vcap_field vsc7514_vcap_es0_keys[] = {
+	[VCAP_ES0_EGR_PORT]			= {  0,  4},
+	[VCAP_ES0_IGR_PORT]			= {  4,  4},
+	[VCAP_ES0_RSV]				= {  8,  2},
+	[VCAP_ES0_L2_MC]			= { 10,  1},
+	[VCAP_ES0_L2_BC]			= { 11,  1},
+	[VCAP_ES0_VID]				= { 12, 12},
+	[VCAP_ES0_DP]				= { 24,  1},
+	[VCAP_ES0_PCP]				= { 25,  3},
+};
+
+static const struct vcap_field vsc7514_vcap_es0_actions[] = {
+	[VCAP_ES0_ACT_PUSH_OUTER_TAG]		= {  0,  2},
+	[VCAP_ES0_ACT_PUSH_INNER_TAG]		= {  2,  1},
+	[VCAP_ES0_ACT_TAG_A_TPID_SEL]		= {  3,  2},
+	[VCAP_ES0_ACT_TAG_A_VID_SEL]		= {  5,  1},
+	[VCAP_ES0_ACT_TAG_A_PCP_SEL]		= {  6,  2},
+	[VCAP_ES0_ACT_TAG_A_DEI_SEL]		= {  8,  2},
+	[VCAP_ES0_ACT_TAG_B_TPID_SEL]		= { 10,  2},
+	[VCAP_ES0_ACT_TAG_B_VID_SEL]		= { 12,  1},
+	[VCAP_ES0_ACT_TAG_B_PCP_SEL]		= { 13,  2},
+	[VCAP_ES0_ACT_TAG_B_DEI_SEL]		= { 15,  2},
+	[VCAP_ES0_ACT_VID_A_VAL]		= { 17, 12},
+	[VCAP_ES0_ACT_PCP_A_VAL]		= { 29,  3},
+	[VCAP_ES0_ACT_DEI_A_VAL]		= { 32,  1},
+	[VCAP_ES0_ACT_VID_B_VAL]		= { 33, 12},
+	[VCAP_ES0_ACT_PCP_B_VAL]		= { 45,  3},
+	[VCAP_ES0_ACT_DEI_B_VAL]		= { 48,  1},
+	[VCAP_ES0_ACT_RSV]			= { 49, 24},
+	[VCAP_ES0_ACT_HIT_STICKY]		= { 73,  1},
+};
+
+static const struct vcap_field vsc7514_vcap_is1_keys[] = {
+	[VCAP_IS1_HK_TYPE]			= {  0,   1},
+	[VCAP_IS1_HK_LOOKUP]			= {  1,   2},
+	[VCAP_IS1_HK_IGR_PORT_MASK]		= {  3,  12},
+	[VCAP_IS1_HK_RSV]			= { 15,   9},
+	[VCAP_IS1_HK_OAM_Y1731]			= { 24,   1},
+	[VCAP_IS1_HK_L2_MC]			= { 25,   1},
+	[VCAP_IS1_HK_L2_BC]			= { 26,   1},
+	[VCAP_IS1_HK_IP_MC]			= { 27,   1},
+	[VCAP_IS1_HK_VLAN_TAGGED]		= { 28,   1},
+	[VCAP_IS1_HK_VLAN_DBL_TAGGED]		= { 29,   1},
+	[VCAP_IS1_HK_TPID]			= { 30,   1},
+	[VCAP_IS1_HK_VID]			= { 31,  12},
+	[VCAP_IS1_HK_DEI]			= { 43,   1},
+	[VCAP_IS1_HK_PCP]			= { 44,   3},
+	/* Specific Fields for IS1 Half Key S1_NORMAL */
+	[VCAP_IS1_HK_L2_SMAC]			= { 47,  48},
+	[VCAP_IS1_HK_ETYPE_LEN]			= { 95,   1},
+	[VCAP_IS1_HK_ETYPE]			= { 96,  16},
+	[VCAP_IS1_HK_IP_SNAP]			= {112,   1},
+	[VCAP_IS1_HK_IP4]			= {113,   1},
+	/* Layer-3 Information */
+	[VCAP_IS1_HK_L3_FRAGMENT]		= {114,   1},
+	[VCAP_IS1_HK_L3_FRAG_OFS_GT0]		= {115,   1},
+	[VCAP_IS1_HK_L3_OPTIONS]		= {116,   1},
+	[VCAP_IS1_HK_L3_DSCP]			= {117,   6},
+	[VCAP_IS1_HK_L3_IP4_SIP]		= {123,  32},
+	/* Layer-4 Information */
+	[VCAP_IS1_HK_TCP_UDP]			= {155,   1},
+	[VCAP_IS1_HK_TCP]			= {156,   1},
+	[VCAP_IS1_HK_L4_SPORT]			= {157,  16},
+	[VCAP_IS1_HK_L4_RNG]			= {173,   8},
+	/* Specific Fields for IS1 Half Key S1_5TUPLE_IP4 */
+	[VCAP_IS1_HK_IP4_INNER_TPID]            = { 47,   1},
+	[VCAP_IS1_HK_IP4_INNER_VID]		= { 48,  12},
+	[VCAP_IS1_HK_IP4_INNER_DEI]		= { 60,   1},
+	[VCAP_IS1_HK_IP4_INNER_PCP]		= { 61,   3},
+	[VCAP_IS1_HK_IP4_IP4]			= { 64,   1},
+	[VCAP_IS1_HK_IP4_L3_FRAGMENT]		= { 65,   1},
+	[VCAP_IS1_HK_IP4_L3_FRAG_OFS_GT0]	= { 66,   1},
+	[VCAP_IS1_HK_IP4_L3_OPTIONS]		= { 67,   1},
+	[VCAP_IS1_HK_IP4_L3_DSCP]		= { 68,   6},
+	[VCAP_IS1_HK_IP4_L3_IP4_DIP]		= { 74,  32},
+	[VCAP_IS1_HK_IP4_L3_IP4_SIP]		= {106,  32},
+	[VCAP_IS1_HK_IP4_L3_PROTO]		= {138,   8},
+	[VCAP_IS1_HK_IP4_TCP_UDP]		= {146,   1},
+	[VCAP_IS1_HK_IP4_TCP]			= {147,   1},
+	[VCAP_IS1_HK_IP4_L4_RNG]		= {148,   8},
+	[VCAP_IS1_HK_IP4_IP_PAYLOAD_S1_5TUPLE]	= {156,  32},
+};
+
+static const struct vcap_field vsc7514_vcap_is1_actions[] = {
+	[VCAP_IS1_ACT_DSCP_ENA]			= {  0,  1},
+	[VCAP_IS1_ACT_DSCP_VAL]			= {  1,  6},
+	[VCAP_IS1_ACT_QOS_ENA]			= {  7,  1},
+	[VCAP_IS1_ACT_QOS_VAL]			= {  8,  3},
+	[VCAP_IS1_ACT_DP_ENA]			= { 11,  1},
+	[VCAP_IS1_ACT_DP_VAL]			= { 12,  1},
+	[VCAP_IS1_ACT_PAG_OVERRIDE_MASK]	= { 13,  8},
+	[VCAP_IS1_ACT_PAG_VAL]			= { 21,  8},
+	[VCAP_IS1_ACT_RSV]			= { 29,  9},
+	/* The fields below are incorrectly shifted by 2 in the manual */
+	[VCAP_IS1_ACT_VID_REPLACE_ENA]		= { 38,  1},
+	[VCAP_IS1_ACT_VID_ADD_VAL]		= { 39, 12},
+	[VCAP_IS1_ACT_FID_SEL]			= { 51,  2},
+	[VCAP_IS1_ACT_FID_VAL]			= { 53, 13},
+	[VCAP_IS1_ACT_PCP_DEI_ENA]		= { 66,  1},
+	[VCAP_IS1_ACT_PCP_VAL]			= { 67,  3},
+	[VCAP_IS1_ACT_DEI_VAL]			= { 70,  1},
+	[VCAP_IS1_ACT_VLAN_POP_CNT_ENA]		= { 71,  1},
+	[VCAP_IS1_ACT_VLAN_POP_CNT]		= { 72,  2},
+	[VCAP_IS1_ACT_CUSTOM_ACE_TYPE_ENA]	= { 74,  4},
+	[VCAP_IS1_ACT_HIT_STICKY]		= { 78,  1},
 };
 
 static const struct vcap_field vsc7514_vcap_is2_keys[] = {
@@ -806,17 +924,17 @@ static const struct vcap_field vsc7514_vcap_is2_keys[] = {
 	[VCAP_IS2_HK_DIP_EQ_SIP]		= {123,   1},
 	/* IP4_TCP_UDP (TYPE=100) */
 	[VCAP_IS2_HK_TCP]			= {124,   1},
-	[VCAP_IS2_HK_L4_SPORT]			= {125,  16},
-	[VCAP_IS2_HK_L4_DPORT]			= {141,  16},
+	[VCAP_IS2_HK_L4_DPORT]			= {125,  16},
+	[VCAP_IS2_HK_L4_SPORT]			= {141,  16},
 	[VCAP_IS2_HK_L4_RNG]			= {157,   8},
 	[VCAP_IS2_HK_L4_SPORT_EQ_DPORT]		= {165,   1},
 	[VCAP_IS2_HK_L4_SEQUENCE_EQ0]		= {166,   1},
-	[VCAP_IS2_HK_L4_URG]			= {167,   1},
-	[VCAP_IS2_HK_L4_ACK]			= {168,   1},
-	[VCAP_IS2_HK_L4_PSH]			= {169,   1},
-	[VCAP_IS2_HK_L4_RST]			= {170,   1},
-	[VCAP_IS2_HK_L4_SYN]			= {171,   1},
-	[VCAP_IS2_HK_L4_FIN]			= {172,   1},
+	[VCAP_IS2_HK_L4_FIN]			= {167,   1},
+	[VCAP_IS2_HK_L4_SYN]			= {168,   1},
+	[VCAP_IS2_HK_L4_RST]			= {169,   1},
+	[VCAP_IS2_HK_L4_PSH]			= {170,   1},
+	[VCAP_IS2_HK_L4_ACK]			= {171,   1},
+	[VCAP_IS2_HK_L4_URG]			= {172,   1},
 	[VCAP_IS2_HK_L4_1588_DOM]		= {173,   8},
 	[VCAP_IS2_HK_L4_1588_VER]		= {181,   4},
 	/* IP4_OTHER (TYPE=101) */
@@ -854,15 +972,32 @@ static const struct vcap_field vsc7514_vcap_is2_actions[] = {
 	[VCAP_IS2_ACT_HIT_CNT]			= { 49, 32},
 };
 
-static const struct vcap_props vsc7514_vcap_props[] = {
+static struct vcap_props vsc7514_vcap_props[] = {
+	[VCAP_ES0] = {
+		.action_type_width = 0,
+		.action_table = {
+			[ES0_ACTION_TYPE_NORMAL] = {
+				.width = 73, /* HIT_STICKY not included */
+				.count = 1,
+			},
+		},
+		.target = S0,
+		.keys = vsc7514_vcap_es0_keys,
+		.actions = vsc7514_vcap_es0_actions,
+	},
+	[VCAP_IS1] = {
+		.action_type_width = 0,
+		.action_table = {
+			[IS1_ACTION_TYPE_NORMAL] = {
+				.width = 78, /* HIT_STICKY not included */
+				.count = 4,
+			},
+		},
+		.target = S1,
+		.keys = vsc7514_vcap_is1_keys,
+		.actions = vsc7514_vcap_is1_actions,
+	},
 	[VCAP_IS2] = {
-		.tg_width = 2,
-		.sw_count = 4,
-		.entry_count = VSC7514_VCAP_IS2_CNT,
-		.entry_width = VSC7514_VCAP_IS2_ENTRY_WIDTH,
-		.action_count = VSC7514_VCAP_IS2_CNT +
-				VSC7514_VCAP_PORT_CNT + 2,
-		.action_width = 99,
 		.action_type_width = 1,
 		.action_table = {
 			[IS2_ACTION_TYPE_NORMAL] = {
@@ -874,8 +1009,9 @@ static const struct vcap_props vsc7514_vcap_props[] = {
 				.count = 4
 			},
 		},
-		.counter_words = 4,
-		.counter_width = 32,
+		.target = S2,
+		.keys = vsc7514_vcap_is2_keys,
+		.actions = vsc7514_vcap_is2_actions,
 	},
 };
 
@@ -896,11 +1032,133 @@ static struct ptp_clock_info ocelot_ptp_clock_info = {
 	.enable		= ocelot_ptp_enable,
 };
 
+static void mscc_ocelot_release_ports(struct ocelot *ocelot)
+{
+	int port;
+
+	for (port = 0; port < ocelot->num_phys_ports; port++) {
+		struct ocelot_port_private *priv;
+		struct ocelot_port *ocelot_port;
+
+		ocelot_port = ocelot->ports[port];
+		if (!ocelot_port)
+			continue;
+
+		ocelot_deinit_port(ocelot, port);
+
+		priv = container_of(ocelot_port, struct ocelot_port_private,
+				    port);
+
+		unregister_netdev(priv->dev);
+		free_netdev(priv->dev);
+	}
+}
+
+static int mscc_ocelot_init_ports(struct platform_device *pdev,
+				  struct device_node *ports)
+{
+	struct ocelot *ocelot = platform_get_drvdata(pdev);
+	struct device_node *portnp;
+	int err;
+
+	ocelot->ports = devm_kcalloc(ocelot->dev, ocelot->num_phys_ports,
+				     sizeof(struct ocelot_port *), GFP_KERNEL);
+	if (!ocelot->ports)
+		return -ENOMEM;
+
+	for_each_available_child_of_node(ports, portnp) {
+		struct ocelot_port_private *priv;
+		struct ocelot_port *ocelot_port;
+		struct device_node *phy_node;
+		phy_interface_t phy_mode;
+		struct phy_device *phy;
+		struct regmap *target;
+		struct resource *res;
+		struct phy *serdes;
+		char res_name[8];
+		u32 port;
+
+		if (of_property_read_u32(portnp, "reg", &port))
+			continue;
+
+		snprintf(res_name, sizeof(res_name), "port%d", port);
+
+		res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
+						   res_name);
+		target = ocelot_regmap_init(ocelot, res);
+		if (IS_ERR(target))
+			continue;
+
+		phy_node = of_parse_phandle(portnp, "phy-handle", 0);
+		if (!phy_node)
+			continue;
+
+		phy = of_phy_find_device(phy_node);
+		of_node_put(phy_node);
+		if (!phy)
+			continue;
+
+		err = ocelot_probe_port(ocelot, port, target, phy);
+		if (err) {
+			of_node_put(portnp);
+			return err;
+		}
+
+		ocelot_port = ocelot->ports[port];
+		priv = container_of(ocelot_port, struct ocelot_port_private,
+				    port);
+
+		of_get_phy_mode(portnp, &phy_mode);
+
+		ocelot_port->phy_mode = phy_mode;
+
+		switch (ocelot_port->phy_mode) {
+		case PHY_INTERFACE_MODE_NA:
+			continue;
+		case PHY_INTERFACE_MODE_SGMII:
+			break;
+		case PHY_INTERFACE_MODE_QSGMII:
+			/* Ensure clock signals and speed is set on all
+			 * QSGMII links
+			 */
+			ocelot_port_writel(ocelot_port,
+					   DEV_CLOCK_CFG_LINK_SPEED
+					   (OCELOT_SPEED_1000),
+					   DEV_CLOCK_CFG);
+			break;
+		default:
+			dev_err(ocelot->dev,
+				"invalid phy mode for port%d, (Q)SGMII only\n",
+				port);
+			of_node_put(portnp);
+			return -EINVAL;
+		}
+
+		serdes = devm_of_phy_get(ocelot->dev, portnp, NULL);
+		if (IS_ERR(serdes)) {
+			err = PTR_ERR(serdes);
+			if (err == -EPROBE_DEFER)
+				dev_dbg(ocelot->dev, "deferring probe\n");
+			else
+				dev_err(ocelot->dev,
+					"missing SerDes phys for port%d\n",
+					port);
+
+			of_node_put(portnp);
+			return err;
+		}
+
+		priv->serdes = serdes;
+	}
+
+	return 0;
+}
+
 static int mscc_ocelot_probe(struct platform_device *pdev)
 {
 	struct device_node *np = pdev->dev.of_node;
-	struct device_node *ports, *portnp;
 	int err, irq_xtr, irq_ptp_rdy;
+	struct device_node *ports;
 	struct ocelot *ocelot;
 	struct regmap *hsio;
 	unsigned int i;
@@ -915,6 +1173,8 @@ static int mscc_ocelot_probe(struct platform_device *pdev)
 		{ QSYS, "qsys" },
 		{ ANA, "ana" },
 		{ QS, "qs" },
+		{ S0, "s0" },
+		{ S1, "s1" },
 		{ S2, "s2" },
 		{ PTP, "ptp", 1 },
 	};
@@ -985,20 +1245,25 @@ static int mscc_ocelot_probe(struct platform_device *pdev)
 
 	ports = of_get_child_by_name(np, "ethernet-ports");
 	if (!ports) {
-		dev_err(&pdev->dev, "no ethernet-ports child node found\n");
+		dev_err(ocelot->dev, "no ethernet-ports child node found\n");
 		return -ENODEV;
 	}
 
 	ocelot->num_phys_ports = of_get_child_count(ports);
 
-	ocelot->ports = devm_kcalloc(&pdev->dev, ocelot->num_phys_ports,
-				     sizeof(struct ocelot_port *), GFP_KERNEL);
-
-	ocelot->vcap_is2_keys = vsc7514_vcap_is2_keys;
-	ocelot->vcap_is2_actions = vsc7514_vcap_is2_actions;
 	ocelot->vcap = vsc7514_vcap_props;
+	ocelot->inj_prefix = OCELOT_TAG_PREFIX_NONE;
+	ocelot->xtr_prefix = OCELOT_TAG_PREFIX_NONE;
+	ocelot->npi = -1;
+
+	err = ocelot_init(ocelot);
+	if (err)
+		goto out_put_ports;
+
+	err = mscc_ocelot_init_ports(pdev, ports);
+	if (err)
+		goto out_put_ports;
 
-	ocelot_init(ocelot);
 	if (ocelot->ptp) {
 		err = ocelot_init_timestamp(ocelot, &ocelot_ptp_clock_info);
 		if (err) {
@@ -1008,96 +1273,6 @@ static int mscc_ocelot_probe(struct platform_device *pdev)
 		}
 	}
 
-	/* No NPI port */
-	ocelot_configure_cpu(ocelot, -1, OCELOT_TAG_PREFIX_NONE,
-			     OCELOT_TAG_PREFIX_NONE);
-
-	for_each_available_child_of_node(ports, portnp) {
-		struct ocelot_port_private *priv;
-		struct ocelot_port *ocelot_port;
-		struct device_node *phy_node;
-		phy_interface_t phy_mode;
-		struct phy_device *phy;
-		struct regmap *target;
-		struct resource *res;
-		struct phy *serdes;
-		char res_name[8];
-		u32 port;
-
-		if (of_property_read_u32(portnp, "reg", &port))
-			continue;
-
-		snprintf(res_name, sizeof(res_name), "port%d", port);
-
-		res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
-						   res_name);
-		target = ocelot_regmap_init(ocelot, res);
-		if (IS_ERR(target))
-			continue;
-
-		phy_node = of_parse_phandle(portnp, "phy-handle", 0);
-		if (!phy_node)
-			continue;
-
-		phy = of_phy_find_device(phy_node);
-		of_node_put(phy_node);
-		if (!phy)
-			continue;
-
-		err = ocelot_probe_port(ocelot, port, target, phy);
-		if (err) {
-			of_node_put(portnp);
-			goto out_put_ports;
-		}
-
-		ocelot_port = ocelot->ports[port];
-		priv = container_of(ocelot_port, struct ocelot_port_private,
-				    port);
-
-		of_get_phy_mode(portnp, &phy_mode);
-
-		ocelot_port->phy_mode = phy_mode;
-
-		switch (ocelot_port->phy_mode) {
-		case PHY_INTERFACE_MODE_NA:
-			continue;
-		case PHY_INTERFACE_MODE_SGMII:
-			break;
-		case PHY_INTERFACE_MODE_QSGMII:
-			/* Ensure clock signals and speed is set on all
-			 * QSGMII links
-			 */
-			ocelot_port_writel(ocelot_port,
-					   DEV_CLOCK_CFG_LINK_SPEED
-					   (OCELOT_SPEED_1000),
-					   DEV_CLOCK_CFG);
-			break;
-		default:
-			dev_err(ocelot->dev,
-				"invalid phy mode for port%d, (Q)SGMII only\n",
-				port);
-			of_node_put(portnp);
-			err = -EINVAL;
-			goto out_put_ports;
-		}
-
-		serdes = devm_of_phy_get(ocelot->dev, portnp, NULL);
-		if (IS_ERR(serdes)) {
-			err = PTR_ERR(serdes);
-			if (err == -EPROBE_DEFER)
-				dev_dbg(ocelot->dev, "deferring probe\n");
-			else
-				dev_err(ocelot->dev,
-					"missing SerDes phys for port%d\n",
-					port);
-
-			of_node_put(portnp);
-			goto out_put_ports;
-		}
-
-		priv->serdes = serdes;
-	}
-
 	register_netdevice_notifier(&ocelot_netdevice_nb);
 	register_switchdev_notifier(&ocelot_switchdev_nb);
 	register_switchdev_blocking_notifier(&ocelot_switchdev_blocking_nb);
@@ -1114,6 +1289,7 @@ static int mscc_ocelot_remove(struct platform_device *pdev)
 	struct ocelot *ocelot = platform_get_drvdata(pdev);
 
 	ocelot_deinit_timestamp(ocelot);
+	mscc_ocelot_release_ports(ocelot);
 	ocelot_deinit(ocelot);
 	unregister_switchdev_blocking_notifier(&ocelot_switchdev_blocking_nb);
 	unregister_switchdev_notifier(&ocelot_switchdev_nb);
diff --git a/drivers/net/ethernet/natsemi/ns83820.c b/drivers/net/ethernet/natsemi/ns83820.c
index 4c1f53339019..72794d158871 100644
--- a/drivers/net/ethernet/natsemi/ns83820.c
+++ b/drivers/net/ethernet/natsemi/ns83820.c
@@ -600,12 +600,14 @@ static void phy_intr(struct net_device *ndev)
 	struct ns83820 *dev = PRIV(ndev);
 	static const char *speeds[] = { "10", "100", "1000", "1000(?)", "1000F" };
 	u32 cfg, new_cfg;
-	u32 tbisr, tanar, tanlpar;
+	u32 tanar, tanlpar;
 	int speed, fullduplex, newlinkstate;
 
 	cfg = readl(dev->base + CFG) ^ SPDSTS_POLARITY;
 
 	if (dev->CFG_cache & CFG_TBI_EN) {
+		u32 __maybe_unused tbisr;
+
 		/* we have an optical transceiver */
 		tbisr = readl(dev->base + TBISR);
 		tanar = readl(dev->base + TANAR);
diff --git a/drivers/net/ethernet/natsemi/sonic.c b/drivers/net/ethernet/natsemi/sonic.c
index dd3605aa5f23..d17d1b4f2585 100644
--- a/drivers/net/ethernet/natsemi/sonic.c
+++ b/drivers/net/ethernet/natsemi/sonic.c
@@ -143,7 +143,7 @@ static int sonic_open(struct net_device *dev)
 	/*
 	 * Initialize the SONIC
 	 */
-	sonic_init(dev);
+	sonic_init(dev, true);
 
 	netif_start_queue(dev);
 
@@ -153,7 +153,7 @@ static int sonic_open(struct net_device *dev)
 }
 
 /* Wait for the SONIC to become idle. */
-static void sonic_quiesce(struct net_device *dev, u16 mask)
+static void sonic_quiesce(struct net_device *dev, u16 mask, bool may_sleep)
 {
 	struct sonic_local * __maybe_unused lp = netdev_priv(dev);
 	int i;
@@ -163,7 +163,7 @@ static void sonic_quiesce(struct net_device *dev, u16 mask)
 		bits = SONIC_READ(SONIC_CMD) & mask;
 		if (!bits)
 			return;
-		if (irqs_disabled() || in_interrupt())
+		if (!may_sleep)
 			udelay(20);
 		else
 			usleep_range(100, 200);
@@ -187,7 +187,7 @@ static int sonic_close(struct net_device *dev)
 	 * stop the SONIC, disable interrupts
 	 */
 	SONIC_WRITE(SONIC_CMD, SONIC_CR_RXDIS);
-	sonic_quiesce(dev, SONIC_CR_ALL);
+	sonic_quiesce(dev, SONIC_CR_ALL, true);
 
 	SONIC_WRITE(SONIC_IMR, 0);
 	SONIC_WRITE(SONIC_ISR, 0x7fff);
@@ -229,7 +229,7 @@ static void sonic_tx_timeout(struct net_device *dev, unsigned int txqueue)
 	 * disable all interrupts before releasing DMA buffers
 	 */
 	SONIC_WRITE(SONIC_CMD, SONIC_CR_RXDIS);
-	sonic_quiesce(dev, SONIC_CR_ALL);
+	sonic_quiesce(dev, SONIC_CR_ALL, false);
 
 	SONIC_WRITE(SONIC_IMR, 0);
 	SONIC_WRITE(SONIC_ISR, 0x7fff);
@@ -246,7 +246,7 @@ static void sonic_tx_timeout(struct net_device *dev, unsigned int txqueue)
 		}
 	}
 	/* Try to restart the adaptor. */
-	sonic_init(dev);
+	sonic_init(dev, false);
 	lp->stats.tx_errors++;
 	netif_trans_update(dev); /* prevent tx timeout */
 	netif_wake_queue(dev);
@@ -692,9 +692,9 @@ static void sonic_multicast_list(struct net_device *dev)
 
 			/* LCAM and TXP commands can't be used simultaneously */
 			spin_lock_irqsave(&lp->lock, flags);
-			sonic_quiesce(dev, SONIC_CR_TXP);
+			sonic_quiesce(dev, SONIC_CR_TXP, false);
 			SONIC_WRITE(SONIC_CMD, SONIC_CR_LCAM);
-			sonic_quiesce(dev, SONIC_CR_LCAM);
+			sonic_quiesce(dev, SONIC_CR_LCAM, false);
 			spin_unlock_irqrestore(&lp->lock, flags);
 		}
 	}
@@ -708,7 +708,7 @@ static void sonic_multicast_list(struct net_device *dev)
 /*
  * Initialize the SONIC ethernet controller.
  */
-static int sonic_init(struct net_device *dev)
+static int sonic_init(struct net_device *dev, bool may_sleep)
 {
 	struct sonic_local *lp = netdev_priv(dev);
 	int i;
@@ -730,7 +730,7 @@ static int sonic_init(struct net_device *dev)
 	 */
 	SONIC_WRITE(SONIC_CMD, 0);
 	SONIC_WRITE(SONIC_CMD, SONIC_CR_RXDIS | SONIC_CR_STP);
-	sonic_quiesce(dev, SONIC_CR_ALL);
+	sonic_quiesce(dev, SONIC_CR_ALL, may_sleep);
 
 	/*
 	 * initialize the receive resource area
@@ -759,7 +759,7 @@ static int sonic_init(struct net_device *dev)
 	netif_dbg(lp, ifup, dev, "%s: issuing RRRA command\n", __func__);
 
 	SONIC_WRITE(SONIC_CMD, SONIC_CR_RRRA);
-	sonic_quiesce(dev, SONIC_CR_RRRA);
+	sonic_quiesce(dev, SONIC_CR_RRRA, may_sleep);
 
 	/*
 	 * Initialize the receive descriptors so that they
@@ -834,7 +834,7 @@ static int sonic_init(struct net_device *dev)
 	 * load the CAM
 	 */
 	SONIC_WRITE(SONIC_CMD, SONIC_CR_LCAM);
-	sonic_quiesce(dev, SONIC_CR_LCAM);
+	sonic_quiesce(dev, SONIC_CR_LCAM, may_sleep);
 
 	/*
 	 * enable receiver, disable loopback
diff --git a/drivers/net/ethernet/natsemi/sonic.h b/drivers/net/ethernet/natsemi/sonic.h
index 3cbb62c860c8..a5b803eb8c8a 100644
--- a/drivers/net/ethernet/natsemi/sonic.h
+++ b/drivers/net/ethernet/natsemi/sonic.h
@@ -338,7 +338,7 @@ static void sonic_rx(struct net_device *dev);
 static int sonic_close(struct net_device *dev);
 static struct net_device_stats *sonic_get_stats(struct net_device *dev);
 static void sonic_multicast_list(struct net_device *dev);
-static int sonic_init(struct net_device *dev);
+static int sonic_init(struct net_device *dev, bool may_sleep);
 static void sonic_tx_timeout(struct net_device *dev, unsigned int txqueue);
 static void sonic_msg_init(struct net_device *dev);
 static int sonic_alloc_descriptors(struct net_device *dev);
diff --git a/drivers/net/ethernet/neterion/s2io.c b/drivers/net/ethernet/neterion/s2io.c
index bc94970bea45..d13d92bf7447 100644
--- a/drivers/net/ethernet/neterion/s2io.c
+++ b/drivers/net/ethernet/neterion/s2io.c
@@ -1000,7 +1000,7 @@ static void free_shared_mem(struct s2io_nic *nic)
 	}
 }
 
-/**
+/*
  * s2io_verify_pci_mode -
  */
 
@@ -1035,7 +1035,7 @@ static int s2io_on_nec_bridge(struct pci_dev *s2io_pdev)
 }
 
 static int bus_speed[8] = {33, 133, 133, 200, 266, 133, 200, 266};
-/**
+/*
  * s2io_print_pci_mode -
  */
 static int s2io_print_pci_mode(struct s2io_nic *nic)
@@ -2064,6 +2064,9 @@ static void en_dis_able_nic_intrs(struct s2io_nic *nic, u16 mask, int flag)
 
 /**
  *  verify_pcc_quiescent- Checks for PCC quiescent state
+ *  @sp : private member of the device structure, which is a pointer to the
+ *  s2io_nic structure.
+ *  @flag: boolean controlling function path
  *  Return: 1 If PCC is quiescence
  *          0 If PCC is not quiescence
  */
@@ -2099,6 +2102,8 @@ static int verify_pcc_quiescent(struct s2io_nic *sp, int flag)
 }
 /**
  *  verify_xena_quiescence - Checks whether the H/W is ready
+ *  @sp : private member of the device structure, which is a pointer to the
+ *  s2io_nic structure.
  *  Description: Returns whether the H/W is ready to go or not. Depending
  *  on whether adapter enable bit was written or not the comparison
  *  differs and the calling function passes the input argument flag to
@@ -2305,6 +2310,9 @@ static int start_nic(struct s2io_nic *nic)
 }
 /**
  * s2io_txdl_getskb - Get the skb from txdl, unmap and return skb
+ * @fifo_data: fifo data pointer
+ * @txdlp: descriptor
+ * @get_off: unused
  */
 static struct sk_buff *s2io_txdl_getskb(struct fifo_info *fifo_data,
 					struct TxD *txdlp, int get_off)
@@ -2391,7 +2399,7 @@ static void free_tx_buffers(struct s2io_nic *nic)
 
 /**
  *   stop_nic -  To stop the nic
- *   @nic ; device private variable.
+ *   @nic : device private variable.
  *   Description:
  *   This function does exactly the opposite of what the start_nic()
  *   function does. This function is called to stop the device.
@@ -2419,7 +2427,8 @@ static void stop_nic(struct s2io_nic *nic)
 
 /**
  *  fill_rx_buffers - Allocates the Rx side skbs
- *  @ring_info: per ring structure
+ *  @nic : device private variable.
+ *  @ring: per ring structure
  *  @from_card_up: If this is true, we will map the buffer to get
  *     the dma address for buf0 and buf1 to give it to the card.
  *     Else we will sync the already mapped buffer to give it to the card.
@@ -2864,7 +2873,7 @@ static void s2io_netpoll(struct net_device *dev)
 
 /**
  *  rx_intr_handler - Rx interrupt handler
- *  @ring_info: per ring structure.
+ *  @ring_data: per ring structure.
  *  @budget: budget for napi processing.
  *  Description:
  *  If the interrupt is because of a received frame or if the
@@ -2972,7 +2981,7 @@ static int rx_intr_handler(struct ring_info *ring_data, int budget)
 
 /**
  *  tx_intr_handler - Transmit interrupt handler
- *  @nic : device private variable
+ *  @fifo_data : fifo data pointer
  *  Description:
  *  If an interrupt was raised to indicate DMA complete of the
  *  Tx packet, this function is called. It identifies the last TxD
@@ -3153,6 +3162,8 @@ static u64 s2io_mdio_read(u32 mmd_type, u64 addr, struct net_device *dev)
 /**
  *  s2io_chk_xpak_counter - Function to check the status of the xpak counters
  *  @counter      : counter value to be updated
+ *  @regs_stat    : registers status
+ *  @index        : index
  *  @flag         : flag to indicate the status
  *  @type         : counter type
  *  Description:
@@ -3309,8 +3320,9 @@ static void s2io_updt_xpak_counter(struct net_device *dev)
 
 /**
  *  wait_for_cmd_complete - waits for a command to complete.
- *  @sp : private member of the device structure, which is a pointer to the
- *  s2io_nic structure.
+ *  @addr: address
+ *  @busy_bit: bit to check for busy
+ *  @bit_state: state to check
  *  Description: Function that waits for a command to Write into RMAC
  *  ADDR DATA registers to be completed and returns either success or
  *  error depending on whether the command was complete or not.
@@ -4335,7 +4347,7 @@ static int do_s2io_chk_alarm_bit(u64 value, void __iomem *addr,
 
 /**
  *  s2io_handle_errors - Xframe error indication handler
- *  @nic: device private variable
+ *  @dev_id: opaque handle to dev
  *  Description: Handle alarms such as loss of link, single or
  *  double ECC errors, critical and serious errors.
  *  Return Value:
@@ -4739,7 +4751,7 @@ static irqreturn_t s2io_isr(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-/**
+/*
  * s2io_updt_stats -
  */
 static void s2io_updt_stats(struct s2io_nic *sp)
@@ -5168,7 +5180,7 @@ static u64 do_s2io_read_unicast_mc(struct s2io_nic *sp, int offset)
 	return tmp64 >> 16;
 }
 
-/**
+/*
  * s2io_set_mac_addr - driver entry point
  */
 
@@ -5243,8 +5255,7 @@ static int do_s2io_prog_unicast(struct net_device *dev, u8 *addr)
 
 /**
  * s2io_ethtool_set_link_ksettings - Sets different link parameters.
- * @sp : private member of the device structure, which is a pointer to the
- * s2io_nic structure.
+ * @dev : pointer to netdev
  * @cmd: pointer to the structure with parameters given by ethtool to set
  * link information.
  * Description:
@@ -5273,8 +5284,7 @@ s2io_ethtool_set_link_ksettings(struct net_device *dev,
 
 /**
  * s2io_ethtol_get_link_ksettings - Return link specific information.
- * @sp : private member of the device structure, pointer to the
- *      s2io_nic structure.
+ * @dev: pointer to netdev
  * @cmd : pointer to the structure with parameters given by ethtool
  * to return link information.
  * Description:
@@ -5313,8 +5323,7 @@ s2io_ethtool_get_link_ksettings(struct net_device *dev,
 
 /**
  * s2io_ethtool_gdrvinfo - Returns driver specific information.
- * @sp : private member of the device structure, which is a pointer to the
- * s2io_nic structure.
+ * @dev: pointer to netdev
  * @info : pointer to the structure with parameters given by ethtool to
  * return driver information.
  * Description:
@@ -5335,11 +5344,10 @@ static void s2io_ethtool_gdrvinfo(struct net_device *dev,
 
 /**
  *  s2io_ethtool_gregs - dumps the entire space of Xfame into the buffer.
- *  @sp: private member of the device structure, which is a pointer to the
- *  s2io_nic structure.
+ *  @dev: pointer to netdev
  *  @regs : pointer to the structure with parameters given by ethtool for
- *  dumping the registers.
- *  @reg_space: The input argument into which all the registers are dumped.
+ *          dumping the registers.
+ *  @space: The input argument into which all the registers are dumped.
  *  Description:
  *  Dumps the entire register space of xFrame NIC into the user given
  *  buffer area.
@@ -5471,8 +5479,7 @@ static void s2io_ethtool_gringparam(struct net_device *dev,
 
 /**
  * s2io_ethtool_getpause_data -Pause frame frame generation and reception.
- * @sp : private member of the device structure, which is a pointer to the
- *	s2io_nic structure.
+ * @dev: pointer to netdev
  * @ep : pointer to the structure with pause parameters given by ethtool.
  * Description:
  * Returns the Pause frame generation and reception capability of the NIC.
@@ -5496,8 +5503,7 @@ static void s2io_ethtool_getpause_data(struct net_device *dev,
 
 /**
  * s2io_ethtool_setpause_data -  set/reset pause frame generation.
- * @sp : private member of the device structure, which is a pointer to the
- *      s2io_nic structure.
+ * @dev: pointer to netdev
  * @ep : pointer to the structure with pause parameters given by ethtool.
  * Description:
  * It can be used to set or reset Pause frame generation or reception
@@ -5526,6 +5532,7 @@ static int s2io_ethtool_setpause_data(struct net_device *dev,
 	return 0;
 }
 
+#define S2IO_DEV_ID		5
 /**
  * read_eeprom - reads 4 bytes of data from user given offset.
  * @sp : private member of the device structure, which is a pointer to the
@@ -5541,8 +5548,6 @@ static int s2io_ethtool_setpause_data(struct net_device *dev,
  * Return value:
  *  -1 on failure and 0 on success.
  */
-
-#define S2IO_DEV_ID		5
 static int read_eeprom(struct s2io_nic *sp, int off, u64 *data)
 {
 	int ret = -1;
@@ -5734,8 +5739,7 @@ static void s2io_vpd_read(struct s2io_nic *nic)
 
 /**
  *  s2io_ethtool_geeprom  - reads the value stored in the Eeprom.
- *  @sp : private member of the device structure, which is a pointer to the
- *  s2io_nic structure.
+ *  @dev: pointer to netdev
  *  @eeprom : pointer to the user level structure provided by ethtool,
  *  containing all relevant information.
  *  @data_buf : user defined value to be written into Eeprom.
@@ -5771,11 +5775,10 @@ static int s2io_ethtool_geeprom(struct net_device *dev,
 
 /**
  *  s2io_ethtool_seeprom - tries to write the user provided value in Eeprom
- *  @sp : private member of the device structure, which is a pointer to the
- *  s2io_nic structure.
+ *  @dev: pointer to netdev
  *  @eeprom : pointer to the user level structure provided by ethtool,
  *  containing all relevant information.
- *  @data_buf ; user defined value to be written into Eeprom.
+ *  @data_buf : user defined value to be written into Eeprom.
  *  Description:
  *  Tries to write the user provided value in the Eeprom, at the offset
  *  given by the user.
@@ -6027,7 +6030,7 @@ static int s2io_bist_test(struct s2io_nic *sp, uint64_t *data)
 
 /**
  * s2io_link_test - verifies the link state of the nic
- * @sp ; private member of the device structure, which is a pointer to the
+ * @sp: private member of the device structure, which is a pointer to the
  * s2io_nic structure.
  * @data: variable that returns the result of each of the test conducted by
  * the driver.
@@ -6150,8 +6153,7 @@ static int s2io_rldram_test(struct s2io_nic *sp, uint64_t *data)
 
 /**
  *  s2io_ethtool_test - conducts 6 tsets to determine the health of card.
- *  @sp : private member of the device structure, which is a pointer to the
- *  s2io_nic structure.
+ *  @dev: pointer to netdev
  *  @ethtest : pointer to a ethtool command specific structure that will be
  *  returned to the user.
  *  @data : variable that returns the result of each of the test
@@ -6597,7 +6599,7 @@ static const struct ethtool_ops netdev_ethtool_ops = {
 /**
  *  s2io_ioctl - Entry point for the Ioctl
  *  @dev :  Device pointer.
- *  @ifr :  An IOCTL specefic structure, that can contain a pointer to
+ *  @rq :  An IOCTL specefic structure, that can contain a pointer to
  *  a proprietary structure used to pass information to the driver.
  *  @cmd :  This is used to distinguish between the different commands that
  *  can be passed to the IOCTL functions.
@@ -6650,7 +6652,7 @@ static int s2io_change_mtu(struct net_device *dev, int new_mtu)
 
 /**
  * s2io_set_link - Set the LInk status
- * @data: long pointer to device private structue
+ * @work: work struct containing a pointer to device private structue
  * Description: Sets the link status for the adapter
  */
 
@@ -7187,7 +7189,7 @@ static int s2io_card_up(struct s2io_nic *sp)
 
 /**
  * s2io_restart_nic - Resets the NIC.
- * @data : long pointer to the device private structure
+ * @work : work struct containing a pointer to the device private structure
  * Description:
  * This function is scheduled to be run by the s2io_tx_watchdog
  * function after 0.5 secs to reset the NIC. The idea is to reduce
@@ -7218,6 +7220,7 @@ out_unlock:
 /**
  *  s2io_tx_watchdog - Watchdog for transmit side.
  *  @dev : Pointer to net device structure
+ *  @txqueue: index of the hanging queue
  *  Description:
  *  This function is triggered if the Tx Queue is stopped
  *  for a pre-defined amount of time when the Interface is still up.
@@ -7242,11 +7245,8 @@ static void s2io_tx_watchdog(struct net_device *dev, unsigned int txqueue)
 
 /**
  *   rx_osm_handler - To perform some OS related operations on SKB.
- *   @sp: private member of the device structure,pointer to s2io_nic structure.
- *   @skb : the socket buffer pointer.
- *   @len : length of the packet
- *   @cksum : FCS checksum of the frame.
- *   @ring_no : the ring from which this RxD was extracted.
+ *   @ring_data : the ring from which this RxD was extracted.
+ *   @rxdp: descriptor
  *   Description:
  *   This function is called by the Rx interrupt serivce routine to perform
  *   some OS related operations on the SKB before passing it to the upper
@@ -7576,9 +7576,10 @@ static int s2io_verify_parm(struct pci_dev *pdev, u8 *dev_intr_type,
 }
 
 /**
- * rts_ds_steer - Receive traffic steering based on IPv4 or IPv6 TOS
- * or Traffic class respectively.
+ * rts_ds_steer - Receive traffic steering based on IPv4 or IPv6 TOS or Traffic class respectively.
  * @nic: device private variable
+ * @ds_codepoint: data
+ * @ring: ring index
  * Description: The function configures the receive steering to
  * desired receive ring.
  * Return Value:  SUCCESS on success and
diff --git a/drivers/net/ethernet/neterion/vxge/vxge-config.c b/drivers/net/ethernet/neterion/vxge/vxge-config.c
index 78eba10300ae..f5d48d7c4ce2 100644
--- a/drivers/net/ethernet/neterion/vxge/vxge-config.c
+++ b/drivers/net/ethernet/neterion/vxge/vxge-config.c
@@ -988,6 +988,9 @@ exit:
 
 /**
  * vxge_hw_device_hw_info_get - Get the hw information
+ * @bar0: the bar
+ * @hw_info: the hw_info struct
+ *
  * Returns the vpath mask that has the bits set for each vpath allocated
  * for the driver, FW version information, and the first mac address for
  * each vpath
@@ -2303,16 +2306,9 @@ exit:
 static inline void
 vxge_os_dma_malloc_async(struct pci_dev *pdev, void *devh, unsigned long size)
 {
-	gfp_t flags;
 	void *vaddr;
 
-	if (in_interrupt())
-		flags = GFP_ATOMIC | GFP_DMA;
-	else
-		flags = GFP_KERNEL | GFP_DMA;
-
-	vaddr = kmalloc((size), flags);
-
+	vaddr = kmalloc(size, GFP_KERNEL | GFP_DMA);
 	vxge_hw_blockpool_block_add(devh, vaddr, size, pdev, pdev);
 }
 
@@ -3926,7 +3922,7 @@ exit:
 
 /**
  * vxge_hw_vpath_check_leak - Check for memory leak
- * @ringh: Handle to the ring object used for receive
+ * @ring: Handle to the ring object used for receive
  *
  * If PRC_RXD_DOORBELL_VPn.NEW_QW_CNT is larger or equal to
  * PRC_CFG6_VPn.RXD_SPAT then a leak has occurred.
diff --git a/drivers/net/ethernet/neterion/vxge/vxge-config.h b/drivers/net/ethernet/neterion/vxge/vxge-config.h
index 373165119850..0cd0750484ae 100644
--- a/drivers/net/ethernet/neterion/vxge/vxge-config.h
+++ b/drivers/net/ethernet/neterion/vxge/vxge-config.h
@@ -1899,18 +1899,13 @@ static inline void *vxge_os_dma_malloc(struct pci_dev *pdev,
 			struct pci_dev **p_dmah,
 			struct pci_dev **p_dma_acch)
 {
-	gfp_t flags;
 	void *vaddr;
 	unsigned long misaligned = 0;
 	int realloc_flag = 0;
 	*p_dma_acch = *p_dmah = NULL;
 
-	if (in_interrupt())
-		flags = GFP_ATOMIC | GFP_DMA;
-	else
-		flags = GFP_KERNEL | GFP_DMA;
 realloc:
-	vaddr = kmalloc((size), flags);
+	vaddr = kmalloc(size, GFP_KERNEL | GFP_DMA);
 	if (vaddr == NULL)
 		return vaddr;
 	misaligned = (unsigned long)VXGE_ALIGN((unsigned long)vaddr,
diff --git a/drivers/net/ethernet/neterion/vxge/vxge-ethtool.c b/drivers/net/ethernet/neterion/vxge/vxge-ethtool.c
index 03c3d1230c17..4d91026485ae 100644
--- a/drivers/net/ethernet/neterion/vxge/vxge-ethtool.c
+++ b/drivers/net/ethernet/neterion/vxge/vxge-ethtool.c
@@ -119,7 +119,7 @@ static void vxge_ethtool_gdrvinfo(struct net_device *dev,
  * @dev: device pointer.
  * @regs: pointer to the structure with parameters given by ethtool for
  * dumping the registers.
- * @reg_space: The input argument into which all the registers are dumped.
+ * @space: The input argument into which all the registers are dumped.
  *
  * Dumps the vpath register space of Titan NIC into the user given
  * buffer area.
diff --git a/drivers/net/ethernet/neterion/vxge/vxge-main.c b/drivers/net/ethernet/neterion/vxge/vxge-main.c
index 7afdb3bc631c..87892bd992b1 100644
--- a/drivers/net/ethernet/neterion/vxge/vxge-main.c
+++ b/drivers/net/ethernet/neterion/vxge/vxge-main.c
@@ -1275,6 +1275,7 @@ _set_all_mcast:
 /**
  * vxge_set_mac_addr
  * @dev: pointer to the device structure
+ * @p: socket info
  *
  * Update entry "0" (default MAC addr)
  */
@@ -1799,7 +1800,7 @@ static void vxge_reset(struct work_struct *work)
 
 /**
  * vxge_poll - Receive handler when Receive Polling is used.
- * @dev: pointer to the device structure.
+ * @napi: pointer to the napi structure.
  * @budget: Number of packets budgeted to be processed in this iteration.
  *
  * This function comes into picture only if Receive side is being handled
@@ -3096,7 +3097,7 @@ static int vxge_change_mtu(struct net_device *dev, int new_mtu)
 /**
  * vxge_get_stats64
  * @dev: pointer to the device structure
- * @stats: pointer to struct rtnl_link_stats64
+ * @net_stats: pointer to struct rtnl_link_stats64
  *
  */
 static void
@@ -3245,7 +3246,7 @@ static int vxge_hwtstamp_get(struct vxgedev *vdev, void __user *data)
 /**
  * vxge_ioctl
  * @dev: Device pointer.
- * @ifr: An IOCTL specific structure, that can contain a pointer to
+ * @rq: An IOCTL specific structure, that can contain a pointer to
  *       a proprietary structure used to pass information to the driver.
  * @cmd: This is used to distinguish between the different commands that
  *       can be passed to the IOCTL functions.
@@ -3269,6 +3270,7 @@ static int vxge_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 /**
  * vxge_tx_watchdog
  * @dev: pointer to net device structure
+ * @txqueue: index of the hanging queue
  *
  * Watchdog for transmit side.
  * This function is triggered if the Tx Queue is stopped
@@ -4002,6 +4004,7 @@ static void vxge_print_parm(struct vxgedev *vdev, u64 vpath_mask)
 
 /**
  * vxge_pm_suspend - vxge power management suspend entry point
+ * @dev_d: device pointer
  *
  */
 static int __maybe_unused vxge_pm_suspend(struct device *dev_d)
@@ -4010,6 +4013,7 @@ static int __maybe_unused vxge_pm_suspend(struct device *dev_d)
 }
 /**
  * vxge_pm_resume - vxge power management resume entry point
+ * @dev_d: device pointer
  *
  */
 static int __maybe_unused vxge_pm_resume(struct device *dev_d)
diff --git a/drivers/net/ethernet/neterion/vxge/vxge-traffic.c b/drivers/net/ethernet/neterion/vxge/vxge-traffic.c
index 709d20d9938f..ee164970b267 100644
--- a/drivers/net/ethernet/neterion/vxge/vxge-traffic.c
+++ b/drivers/net/ethernet/neterion/vxge/vxge-traffic.c
@@ -30,8 +30,6 @@
  */
 enum vxge_hw_status vxge_hw_vpath_intr_enable(struct __vxge_hw_vpath_handle *vp)
 {
-	u64 val64;
-
 	struct __vxge_hw_virtualpath *vpath;
 	struct vxge_hw_vpath_reg __iomem *vp_reg;
 	enum vxge_hw_status status = VXGE_HW_OK;
@@ -84,7 +82,7 @@ enum vxge_hw_status vxge_hw_vpath_intr_enable(struct __vxge_hw_vpath_handle *vp)
 	__vxge_hw_pio_mem_write32_upper((u32)VXGE_HW_INTR_MASK_ALL,
 			&vp_reg->xgmac_vp_int_status);
 
-	val64 = readq(&vp_reg->vpath_general_int_status);
+	readq(&vp_reg->vpath_general_int_status);
 
 	/* Mask unwanted interrupts */
 
@@ -157,8 +155,6 @@ exit:
 enum vxge_hw_status vxge_hw_vpath_intr_disable(
 			struct __vxge_hw_vpath_handle *vp)
 {
-	u64 val64;
-
 	struct __vxge_hw_virtualpath *vpath;
 	enum vxge_hw_status status = VXGE_HW_OK;
 	struct vxge_hw_vpath_reg __iomem *vp_reg;
@@ -179,8 +175,6 @@ enum vxge_hw_status vxge_hw_vpath_intr_disable(
 		(u32)VXGE_HW_INTR_MASK_ALL,
 		&vp_reg->vpath_general_int_mask);
 
-	val64 = VXGE_HW_TIM_CLR_INT_EN_VP(1 << (16 - vpath->vp_id));
-
 	writeq(VXGE_HW_INTR_MASK_ALL, &vp_reg->kdfcctl_errors_mask);
 
 	__vxge_hw_pio_mem_write32_upper((u32)VXGE_HW_INTR_MASK_ALL,
@@ -284,7 +278,7 @@ void vxge_hw_vpath_dynamic_rti_rtimer_set(struct __vxge_hw_ring *ring)
 
 /**
  * vxge_hw_channel_msix_mask - Mask MSIX Vector.
- * @channeh: Channel for rx or tx handle
+ * @channel: Channel for rx or tx handle
  * @msix_id:  MSIX ID
  *
  * The function masks the msix interrupt for the given msix_id
@@ -301,7 +295,7 @@ void vxge_hw_channel_msix_mask(struct __vxge_hw_channel *channel, int msix_id)
 
 /**
  * vxge_hw_channel_msix_unmask - Unmask the MSIX Vector.
- * @channeh: Channel for rx or tx handle
+ * @channel: Channel for rx or tx handle
  * @msix_id:  MSI ID
  *
  * The function unmasks the msix interrupt for the given msix_id
@@ -356,8 +350,6 @@ u32 vxge_hw_device_set_intr_type(struct __vxge_hw_device *hldev, u32 intr_mode)
 /**
  * vxge_hw_device_intr_enable - Enable interrupts.
  * @hldev: HW device handle.
- * @op: One of the enum vxge_hw_device_intr enumerated values specifying
- *      the type(s) of interrupts to enable.
  *
  * Enable Titan interrupts. The function is to be executed the last in
  * Titan initialization sequence.
@@ -411,8 +403,6 @@ void vxge_hw_device_intr_enable(struct __vxge_hw_device *hldev)
 /**
  * vxge_hw_device_intr_disable - Disable Titan interrupts.
  * @hldev: HW device handle.
- * @op: One of the enum vxge_hw_device_intr enumerated values specifying
- *      the type(s) of interrupts to disable.
  *
  * Disable Titan interrupts.
  *
@@ -487,9 +477,7 @@ void vxge_hw_device_unmask_all(struct __vxge_hw_device *hldev)
  */
 void vxge_hw_device_flush_io(struct __vxge_hw_device *hldev)
 {
-	u32 val32;
-
-	val32 = readl(&hldev->common_reg->titan_general_int_status);
+	readl(&hldev->common_reg->titan_general_int_status);
 }
 
 /**
@@ -1414,7 +1402,7 @@ u32 vxge_hw_fifo_free_txdl_count_get(struct __vxge_hw_fifo *fifoh)
 
 /**
  * vxge_hw_fifo_txdl_reserve - Reserve fifo descriptor.
- * @fifoh: Handle to the fifo object used for non offload send
+ * @fifo: Handle to the fifo object used for non offload send
  * @txdlh: Reserved descriptor. On success HW fills this "out" parameter
  *        with a valid handle.
  * @txdl_priv: Buffer to return the pointer to per txdl space
@@ -1525,8 +1513,6 @@ void vxge_hw_fifo_txdl_buffer_set(struct __vxge_hw_fifo *fifo,
  * vxge_hw_fifo_txdl_post - Post descriptor on the fifo channel.
  * @fifo: Handle to the fifo object used for non offload send
  * @txdlh: Descriptor obtained via vxge_hw_fifo_txdl_reserve()
- * @frags: Number of contiguous buffers that are part of a single
- *         transmit operation.
  *
  * Post descriptor on the 'fifo' type channel for transmission.
  * Prior to posting the descriptor should be filled in accordance with
@@ -1699,8 +1685,7 @@ void vxge_hw_fifo_txdl_free(struct __vxge_hw_fifo *fifo, void *txdlh)
 }
 
 /**
- * vxge_hw_vpath_mac_addr_add - Add the mac address entry for this vpath
- *               to MAC address table.
+ * vxge_hw_vpath_mac_addr_add - Add the mac address entry for this vpath to MAC address table.
  * @vp: Vpath handle.
  * @macaddr: MAC address to be added for this vpath into the list
  * @macaddr_mask: MAC address mask for macaddr
@@ -1716,8 +1701,8 @@ void vxge_hw_fifo_txdl_free(struct __vxge_hw_fifo *fifo, void *txdlh)
 enum vxge_hw_status
 vxge_hw_vpath_mac_addr_add(
 	struct __vxge_hw_vpath_handle *vp,
-	u8 (macaddr)[ETH_ALEN],
-	u8 (macaddr_mask)[ETH_ALEN],
+	u8 *macaddr,
+	u8 *macaddr_mask,
 	enum vxge_hw_vpath_mac_addr_add_mode duplicate_mode)
 {
 	u32 i;
@@ -1765,13 +1750,13 @@ exit:
 }
 
 /**
- * vxge_hw_vpath_mac_addr_get - Get the first mac address entry for this vpath
- *               from MAC address table.
+ * vxge_hw_vpath_mac_addr_get - Get the first mac address entry
  * @vp: Vpath handle.
  * @macaddr: First MAC address entry for this vpath in the list
  * @macaddr_mask: MAC address mask for macaddr
  *
- * Returns the first mac address and mac address mask in the list for this
+ * Get the first mac address entry for this vpath from MAC address table.
+ * Return: the first mac address and mac address mask in the list for this
  * vpath.
  * see also: vxge_hw_vpath_mac_addr_get_next
  *
@@ -1779,8 +1764,8 @@ exit:
 enum vxge_hw_status
 vxge_hw_vpath_mac_addr_get(
 	struct __vxge_hw_vpath_handle *vp,
-	u8 (macaddr)[ETH_ALEN],
-	u8 (macaddr_mask)[ETH_ALEN])
+	u8 *macaddr,
+	u8 *macaddr_mask)
 {
 	u32 i;
 	u64 data1 = 0ULL;
@@ -1816,14 +1801,13 @@ exit:
 }
 
 /**
- * vxge_hw_vpath_mac_addr_get_next - Get the next mac address entry for this
- * vpath
- *               from MAC address table.
+ * vxge_hw_vpath_mac_addr_get_next - Get the next mac address entry
  * @vp: Vpath handle.
  * @macaddr: Next MAC address entry for this vpath in the list
  * @macaddr_mask: MAC address mask for macaddr
  *
- * Returns the next mac address and mac address mask in the list for this
+ * Get the next mac address entry for this vpath from MAC address table.
+ * Return: the next mac address and mac address mask in the list for this
  * vpath.
  * see also: vxge_hw_vpath_mac_addr_get
  *
@@ -1831,8 +1815,8 @@ exit:
 enum vxge_hw_status
 vxge_hw_vpath_mac_addr_get_next(
 	struct __vxge_hw_vpath_handle *vp,
-	u8 (macaddr)[ETH_ALEN],
-	u8 (macaddr_mask)[ETH_ALEN])
+	u8 *macaddr,
+	u8 *macaddr_mask)
 {
 	u32 i;
 	u64 data1 = 0ULL;
@@ -1869,8 +1853,7 @@ exit:
 }
 
 /**
- * vxge_hw_vpath_mac_addr_delete - Delete the mac address entry for this vpath
- *               to MAC address table.
+ * vxge_hw_vpath_mac_addr_delete - Delete the mac address entry for this vpath to MAC address table.
  * @vp: Vpath handle.
  * @macaddr: MAC address to be added for this vpath into the list
  * @macaddr_mask: MAC address mask for macaddr
@@ -1884,8 +1867,8 @@ exit:
 enum vxge_hw_status
 vxge_hw_vpath_mac_addr_delete(
 	struct __vxge_hw_vpath_handle *vp,
-	u8 (macaddr)[ETH_ALEN],
-	u8 (macaddr_mask)[ETH_ALEN])
+	u8 *macaddr,
+	u8 *macaddr_mask)
 {
 	u32 i;
 	u64 data1 = 0ULL;
@@ -1916,8 +1899,7 @@ exit:
 }
 
 /**
- * vxge_hw_vpath_vid_add - Add the vlan id entry for this vpath
- *               to vlan id table.
+ * vxge_hw_vpath_vid_add - Add the vlan id entry for this vpath to vlan id table.
  * @vp: Vpath handle.
  * @vid: vlan id to be added for this vpath into the list
  *
@@ -2375,7 +2357,6 @@ enum vxge_hw_status vxge_hw_vpath_poll_rx(struct __vxge_hw_ring *ring)
 	u8 t_code;
 	enum vxge_hw_status status = VXGE_HW_OK;
 	void *first_rxdh;
-	u64 val64 = 0;
 	int new_count = 0;
 
 	ring->cmpl_cnt = 0;
@@ -2403,8 +2384,7 @@ enum vxge_hw_status vxge_hw_vpath_poll_rx(struct __vxge_hw_ring *ring)
 			}
 			writeq(VXGE_HW_PRC_RXD_DOORBELL_NEW_QW_CNT(new_count),
 				&ring->vp_reg->prc_rxd_doorbell);
-			val64 =
-			  readl(&ring->common_reg->titan_general_int_status);
+			readl(&ring->common_reg->titan_general_int_status);
 			ring->doorbell_cnt = 0;
 		}
 	}
@@ -2413,9 +2393,11 @@ enum vxge_hw_status vxge_hw_vpath_poll_rx(struct __vxge_hw_ring *ring)
 }
 
 /**
- * vxge_hw_vpath_poll_tx - Poll Tx for completed descriptors and process
- * the same.
+ * vxge_hw_vpath_poll_tx - Poll Tx for completed descriptors and process the same.
  * @fifo: Handle to the fifo object used for non offload send
+ * @skb_ptr: pointer to skb
+ * @nr_skb: number of skbs
+ * @more: more is coming
  *
  * The function polls the Tx for the completed descriptors and calls
  * the driver via supplied completion callback.
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/offload.c b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
index ac02369174a9..53851853562c 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
@@ -111,7 +111,9 @@ static int
 nfp_map_ptrs_record(struct nfp_app_bpf *bpf, struct nfp_prog *nfp_prog,
 		    struct bpf_prog *prog)
 {
-	int i, cnt, err;
+	int i, cnt, err = 0;
+
+	mutex_lock(&prog->aux->used_maps_mutex);
 
 	/* Quickly count the maps we will have to remember */
 	cnt = 0;
@@ -119,13 +121,15 @@ nfp_map_ptrs_record(struct nfp_app_bpf *bpf, struct nfp_prog *nfp_prog,
 		if (bpf_map_offload_neutral(prog->aux->used_maps[i]))
 			cnt++;
 	if (!cnt)
-		return 0;
+		goto out;
 
 	nfp_prog->map_records = kmalloc_array(cnt,
 					      sizeof(nfp_prog->map_records[0]),
 					      GFP_KERNEL);
-	if (!nfp_prog->map_records)
-		return -ENOMEM;
+	if (!nfp_prog->map_records) {
+		err = -ENOMEM;
+		goto out;
+	}
 
 	for (i = 0; i < prog->aux->used_map_cnt; i++)
 		if (bpf_map_offload_neutral(prog->aux->used_maps[i])) {
@@ -133,12 +137,14 @@ nfp_map_ptrs_record(struct nfp_app_bpf *bpf, struct nfp_prog *nfp_prog,
 						 prog->aux->used_maps[i]);
 			if (err) {
 				nfp_map_ptrs_forget(bpf, nfp_prog);
-				return err;
+				goto out;
 			}
 		}
 	WARN_ON(cnt != nfp_prog->map_records_cnt);
 
-	return 0;
+out:
+	mutex_unlock(&prog->aux->used_maps_mutex);
+	return err;
 }
 
 static int
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c
index be52510d446b..97d2b03208de 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c
@@ -329,12 +329,11 @@ err_close_nsp:
 }
 
 static int
-nfp_devlink_flash_update(struct devlink *devlink, const char *path,
-			 const char *component, struct netlink_ext_ack *extack)
+nfp_devlink_flash_update(struct devlink *devlink,
+			 struct devlink_flash_update_params *params,
+			 struct netlink_ext_ack *extack)
 {
-	if (component)
-		return -EOPNOTSUPP;
-	return nfp_flash_update_common(devlink_priv(devlink), path, extack);
+	return nfp_flash_update_common(devlink_priv(devlink), params->file_name, extack);
 }
 
 const struct devlink_ops nfp_devlink_ops = {
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
index 6eb9fb9a1814..9c9ae33d84ce 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
@@ -829,8 +829,8 @@ nfp_port_get_fecparam(struct net_device *netdev,
 	struct nfp_eth_table_port *eth_port;
 	struct nfp_port *port;
 
-	param->active_fec = ETHTOOL_FEC_NONE_BIT;
-	param->fec = ETHTOOL_FEC_NONE_BIT;
+	param->active_fec = ETHTOOL_FEC_NONE;
+	param->fec = ETHTOOL_FEC_NONE;
 
 	port = nfp_port_from_netdev(netdev);
 	eth_port = nfp_port_get_eth_port(port);
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c
index b36aa5bf3c5f..a58f14aca10c 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c
@@ -8,7 +8,7 @@
 #include "pch_gbe.h"
 #include "pch_gbe_phy.h"
 
-/**
+/*
  * pch_gbe_stats - Stats item information
  */
 struct pch_gbe_stats {
@@ -24,7 +24,7 @@ struct pch_gbe_stats {
 	.offset = offsetof(struct pch_gbe_hw_stats, m),		\
 }
 
-/**
+/*
  * pch_gbe_gstrings_stats - ethtool information status name list
  */
 static const struct pch_gbe_stats pch_gbe_gstrings_stats[] = {
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
index 23f7c76737c9..ade8c44c01cd 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
@@ -295,7 +295,7 @@ static s32 pch_gbe_mac_read_mac_addr(struct pch_gbe_hw *hw)
 /**
  * pch_gbe_wait_clr_bit - Wait to clear a bit
  * @reg:	Pointer of register
- * @busy:	Busy bit
+ * @bit:	Busy bit
  */
 static void pch_gbe_wait_clr_bit(void *reg, u32 bit)
 {
@@ -1034,7 +1034,7 @@ static void pch_gbe_set_mode(struct pch_gbe_adapter *adapter, u16 speed,
 
 /**
  * pch_gbe_watchdog - Watchdog process
- * @data:  Board private structure
+ * @t:  timer list containing a Board private structure
  */
 static void pch_gbe_watchdog(struct timer_list *t)
 {
@@ -2270,6 +2270,7 @@ static int pch_gbe_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
 /**
  * pch_gbe_tx_timeout - Respond to a Tx Hang
  * @netdev:   Network interface device structure
+ * @txqueue: index of hanging queue
  */
 static void pch_gbe_tx_timeout(struct net_device *netdev, unsigned int txqueue)
 {
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_param.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_param.c
index dceec80fd642..81fc5a6e3221 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_param.c
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_param.c
@@ -13,7 +13,7 @@
 #define OPTION_DISABLED 0
 #define OPTION_ENABLED  1
 
-/**
+/*
  * TxDescriptors - Transmit Descriptor Count
  * @Valid Range:   PCH_GBE_MIN_TXD - PCH_GBE_MAX_TXD
  * @Default Value: PCH_GBE_DEFAULT_TXD
@@ -22,7 +22,7 @@ static int TxDescriptors = OPTION_UNSET;
 module_param(TxDescriptors, int, 0);
 MODULE_PARM_DESC(TxDescriptors, "Number of transmit descriptors");
 
-/**
+/*
  * RxDescriptors -Receive Descriptor Count
  * @Valid Range:   PCH_GBE_MIN_RXD - PCH_GBE_MAX_RXD
  * @Default Value: PCH_GBE_DEFAULT_RXD
@@ -31,7 +31,7 @@ static int RxDescriptors = OPTION_UNSET;
 module_param(RxDescriptors, int, 0);
 MODULE_PARM_DESC(RxDescriptors, "Number of receive descriptors");
 
-/**
+/*
  * Speed - User Specified Speed Override
  * @Valid Range: 0, 10, 100, 1000
  *   - 0:    auto-negotiate at all supported speeds
@@ -44,7 +44,7 @@ static int Speed = OPTION_UNSET;
 module_param(Speed, int, 0);
 MODULE_PARM_DESC(Speed, "Speed setting");
 
-/**
+/*
  * Duplex - User Specified Duplex Override
  * @Valid Range: 0-2
  *   - 0:  auto-negotiate for duplex
@@ -59,7 +59,7 @@ MODULE_PARM_DESC(Duplex, "Duplex setting");
 #define HALF_DUPLEX 1
 #define FULL_DUPLEX 2
 
-/**
+/*
  * AutoNeg - Auto-negotiation Advertisement Override
  * @Valid Range: 0x01-0x0F, 0x20-0x2F
  *
@@ -85,7 +85,7 @@ MODULE_PARM_DESC(AutoNeg, "Advertised auto-negotiation setting");
 #define PHY_ADVERTISE_1000_FULL    0x0020
 #define PCH_AUTONEG_ADVERTISE_DEFAULT   0x2F
 
-/**
+/*
  * FlowControl - User Specified Flow Control Override
  * @Valid Range: 0-3
  *    - 0:  No Flow Control
@@ -124,7 +124,7 @@ MODULE_PARM_DESC(XsumTX, "Disable or enable Transmit Checksum offload");
 
 #define PCH_GBE_DEFAULT_TX_CSUM             true	/* trueorfalse */
 
-/**
+/*
  * pch_gbe_option - Force the MAC's flow control settings
  * @hw:	            Pointer to the HW structure
  * Returns:
diff --git a/drivers/net/ethernet/packetengines/yellowfin.c b/drivers/net/ethernet/packetengines/yellowfin.c
index 3da075307178..d1dd9bc1bc7f 100644
--- a/drivers/net/ethernet/packetengines/yellowfin.c
+++ b/drivers/net/ethernet/packetengines/yellowfin.c
@@ -1060,7 +1060,7 @@ static int yellowfin_rx(struct net_device *dev)
 		struct sk_buff *rx_skb = yp->rx_skbuff[entry];
 		s16 frame_status;
 		u16 desc_status;
-		int data_size, yf_size;
+		int data_size, __maybe_unused yf_size;
 		u8 *buf_addr;
 
 		if(!desc->result_status)
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c b/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c
index d1d6fb6669e5..b0d8499d373b 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c
@@ -266,6 +266,7 @@ static int ionic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		dev_err(dev, "Cannot identify device: %d, aborting\n", err);
 		goto err_out_teardown;
 	}
+	ionic_debugfs_add_ident(ionic);
 
 	err = ionic_init(ionic);
 	if (err) {
@@ -286,14 +287,7 @@ static int ionic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_out_reset;
 	}
 
-	/* Configure LIFs */
-	err = ionic_lif_identify(ionic, IONIC_LIF_TYPE_CLASSIC,
-				 &ionic->ident.lif);
-	if (err) {
-		dev_err(dev, "Cannot identify LIFs: %d, aborting\n", err);
-		goto err_out_port_reset;
-	}
-
+	/* Allocate and init the LIF */
 	err = ionic_lif_size(ionic);
 	if (err) {
 		dev_err(dev, "Cannot size LIF: %d, aborting\n", err);
@@ -350,7 +344,7 @@ err_out_port_reset:
 err_out_reset:
 	ionic_reset(ionic);
 err_out_teardown:
-	ionic_dev_teardown(ionic);
+	del_timer_sync(&ionic->watchdog_timer);
 	pci_clear_master(pdev);
 	/* Don't fail the probe for these errors, keep
 	 * the hw interface around for inspection
@@ -378,6 +372,8 @@ static void ionic_remove(struct pci_dev *pdev)
 	if (!ionic)
 		return;
 
+	del_timer_sync(&ionic->watchdog_timer);
+
 	if (ionic->lif) {
 		ionic_devlink_unregister(ionic);
 		ionic_lif_unregister(ionic->lif);
@@ -389,7 +385,6 @@ static void ionic_remove(struct pci_dev *pdev)
 
 	ionic_port_reset(ionic);
 	ionic_reset(ionic);
-	ionic_dev_teardown(ionic);
 	pci_clear_master(pdev);
 	ionic_unmap_bars(ionic);
 	pci_release_regions(pdev);
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.c b/drivers/net/ethernet/pensando/ionic/ionic_dev.c
index 6068f51a11d9..545c99b15df8 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_dev.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.c
@@ -19,10 +19,13 @@ static void ionic_watchdog_cb(struct timer_list *t)
 	mod_timer(&ionic->watchdog_timer,
 		  round_jiffies(jiffies + ionic->watchdog_period));
 
+	if (!ionic->lif)
+		return;
+
 	hb = ionic_heartbeat_check(ionic);
 
-	if (hb >= 0 && ionic->lif)
-		ionic_link_status_check_request(ionic->lif);
+	if (hb >= 0)
+		ionic_link_status_check_request(ionic->lif, false);
 }
 
 void ionic_init_devinfo(struct ionic *ionic)
@@ -98,11 +101,6 @@ int ionic_dev_setup(struct ionic *ionic)
 	return 0;
 }
 
-void ionic_dev_teardown(struct ionic *ionic)
-{
-	del_timer_sync(&ionic->watchdog_timer);
-}
-
 /* Devcmd Interface */
 int ionic_heartbeat_check(struct ionic *ionic)
 {
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.h b/drivers/net/ethernet/pensando/ionic/ionic_dev.h
index 8842dc4a716f..c109cd5a0471 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_dev.h
+++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.h
@@ -283,7 +283,6 @@ static inline bool ionic_q_has_space(struct ionic_queue *q, unsigned int want)
 
 void ionic_init_devinfo(struct ionic *ionic);
 int ionic_dev_setup(struct ionic *ionic);
-void ionic_dev_teardown(struct ionic *ionic);
 
 void ionic_dev_cmd_go(struct ionic_dev *idev, union ionic_dev_cmd *cmd);
 u8 ionic_dev_cmd_status(struct ionic_dev *idev);
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_devlink.c b/drivers/net/ethernet/pensando/ionic/ionic_devlink.c
index 5348f05ebc32..51d64718ed9f 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_devlink.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_devlink.c
@@ -10,16 +10,12 @@
 #include "ionic_devlink.h"
 
 static int ionic_dl_flash_update(struct devlink *dl,
-				 const char *fwname,
-				 const char *component,
+				 struct devlink_flash_update_params *params,
 				 struct netlink_ext_ack *extack)
 {
 	struct ionic *ionic = devlink_priv(dl);
 
-	if (component)
-		return -EOPNOTSUPP;
-
-	return ionic_firmware_update(ionic->lif, fwname, extack);
+	return ionic_firmware_update(ionic->lif, params->file_name, extack);
 }
 
 static int ionic_dl_info_get(struct devlink *dl, struct devlink_info_req *req,
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_if.h b/drivers/net/ethernet/pensando/ionic/ionic_if.h
index 5bb56a27a50d..31ccfcdc2b0a 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_if.h
+++ b/drivers/net/ethernet/pensando/ionic/ionic_if.h
@@ -96,6 +96,7 @@ enum ionic_status_code {
 	IONIC_RC_ERROR		= 29,	/* Generic error */
 	IONIC_RC_ERDMA		= 30,	/* Generic RDMA error */
 	IONIC_RC_EVFID		= 31,	/* VF ID does not exist */
+	IONIC_RC_EBAD_FW	= 32,	/* FW file is invalid or corrupted */
 };
 
 enum ionic_notifyq_opcode {
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
index eb6fe37c0df6..d655a7ae3058 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
@@ -62,15 +62,18 @@ static void ionic_lif_deferred_work(struct work_struct *work)
 	struct ionic_deferred *def = &lif->deferred;
 	struct ionic_deferred_work *w = NULL;
 
-	spin_lock_bh(&def->lock);
-	if (!list_empty(&def->list)) {
-		w = list_first_entry(&def->list,
-				     struct ionic_deferred_work, list);
-		list_del(&w->list);
-	}
-	spin_unlock_bh(&def->lock);
+	do {
+		spin_lock_bh(&def->lock);
+		if (!list_empty(&def->list)) {
+			w = list_first_entry(&def->list,
+					     struct ionic_deferred_work, list);
+			list_del(&w->list);
+		}
+		spin_unlock_bh(&def->lock);
+
+		if (!w)
+			break;
 
-	if (w) {
 		switch (w->type) {
 		case IONIC_DW_TYPE_RX_MODE:
 			ionic_lif_rx_mode(lif, w->rx_mode);
@@ -94,8 +97,8 @@ static void ionic_lif_deferred_work(struct work_struct *work)
 			break;
 		}
 		kfree(w);
-		schedule_work(&def->work);
-	}
+		w = NULL;
+	} while (true);
 }
 
 void ionic_lif_deferred_enqueue(struct ionic_deferred *def,
@@ -151,7 +154,7 @@ static void ionic_link_status_check(struct ionic_lif *lif)
 	clear_bit(IONIC_LIF_F_LINK_CHECK_REQUESTED, lif->state);
 }
 
-void ionic_link_status_check_request(struct ionic_lif *lif)
+void ionic_link_status_check_request(struct ionic_lif *lif, bool can_sleep)
 {
 	struct ionic_deferred_work *work;
 
@@ -159,10 +162,12 @@ void ionic_link_status_check_request(struct ionic_lif *lif)
 	if (test_and_set_bit(IONIC_LIF_F_LINK_CHECK_REQUESTED, lif->state))
 		return;
 
-	if (in_interrupt()) {
+	if (!can_sleep) {
 		work = kzalloc(sizeof(*work), GFP_ATOMIC);
-		if (!work)
+		if (!work) {
+			clear_bit(IONIC_LIF_F_LINK_CHECK_REQUESTED, lif->state);
 			return;
+		}
 
 		work->type = IONIC_DW_TYPE_LINK_STATUS;
 		ionic_lif_deferred_enqueue(&lif->deferred, work);
@@ -259,31 +264,29 @@ static int ionic_qcq_enable(struct ionic_qcq *qcq)
 	return ionic_adminq_post_wait(lif, &ctx);
 }
 
-static int ionic_qcq_disable(struct ionic_qcq *qcq)
+static int ionic_qcq_disable(struct ionic_qcq *qcq, bool send_to_hw)
 {
-	struct ionic_queue *q = &qcq->q;
-	struct ionic_lif *lif = q->lif;
-	struct ionic_dev *idev;
-	struct device *dev;
+	struct ionic_queue *q;
+	struct ionic_lif *lif;
+	int err = 0;
 
 	struct ionic_admin_ctx ctx = {
 		.work = COMPLETION_INITIALIZER_ONSTACK(ctx.work),
 		.cmd.q_control = {
 			.opcode = IONIC_CMD_Q_CONTROL,
-			.lif_index = cpu_to_le16(lif->index),
-			.type = q->type,
-			.index = cpu_to_le32(q->index),
 			.oper = IONIC_Q_DISABLE,
 		},
 	};
 
-	idev = &lif->ionic->idev;
-	dev = lif->ionic->dev;
+	if (!qcq)
+		return -ENXIO;
 
-	dev_dbg(dev, "q_disable.index %d q_disable.qtype %d\n",
-		ctx.cmd.q_control.index, ctx.cmd.q_control.type);
+	q = &qcq->q;
+	lif = q->lif;
 
 	if (qcq->flags & IONIC_QCQ_F_INTR) {
+		struct ionic_dev *idev = &lif->ionic->idev;
+
 		cancel_work_sync(&qcq->dim.work);
 		ionic_intr_mask(idev->intr_ctrl, qcq->intr.index,
 				IONIC_INTR_MASK_SET);
@@ -292,7 +295,17 @@ static int ionic_qcq_disable(struct ionic_qcq *qcq)
 		napi_disable(&qcq->napi);
 	}
 
-	return ionic_adminq_post_wait(lif, &ctx);
+	if (send_to_hw) {
+		ctx.cmd.q_control.lif_index = cpu_to_le16(lif->index);
+		ctx.cmd.q_control.type = q->type;
+		ctx.cmd.q_control.index = cpu_to_le32(q->index);
+		dev_dbg(lif->ionic->dev, "q_disable.index %d q_disable.qtype %d\n",
+			ctx.cmd.q_control.index, ctx.cmd.q_control.type);
+
+		err = ionic_adminq_post_wait(lif, &ctx);
+	}
+
+	return err;
 }
 
 static void ionic_lif_qcq_deinit(struct ionic_lif *lif, struct ionic_qcq *qcq)
@@ -518,30 +531,55 @@ static int ionic_qcq_alloc(struct ionic_lif *lif, unsigned int type,
 		goto err_out_free_cq_info;
 	}
 
-	new->q_size = PAGE_SIZE + (num_descs * desc_size);
-	new->q_base = dma_alloc_coherent(dev, new->q_size, &new->q_base_pa,
-					 GFP_KERNEL);
-	if (!new->q_base) {
-		netdev_err(lif->netdev, "Cannot allocate queue DMA memory\n");
-		err = -ENOMEM;
-		goto err_out_free_cq_info;
-	}
-	q_base = PTR_ALIGN(new->q_base, PAGE_SIZE);
-	q_base_pa = ALIGN(new->q_base_pa, PAGE_SIZE);
-	ionic_q_map(&new->q, q_base, q_base_pa);
+	if (flags & IONIC_QCQ_F_NOTIFYQ) {
+		int q_size, cq_size;
 
-	new->cq_size = PAGE_SIZE + (num_descs * cq_desc_size);
-	new->cq_base = dma_alloc_coherent(dev, new->cq_size, &new->cq_base_pa,
-					  GFP_KERNEL);
-	if (!new->cq_base) {
-		netdev_err(lif->netdev, "Cannot allocate cq DMA memory\n");
-		err = -ENOMEM;
-		goto err_out_free_q;
+		/* q & cq need to be contiguous in case of notifyq */
+		q_size = ALIGN(num_descs * desc_size, PAGE_SIZE);
+		cq_size = ALIGN(num_descs * cq_desc_size, PAGE_SIZE);
+
+		new->q_size = PAGE_SIZE + q_size + cq_size;
+		new->q_base = dma_alloc_coherent(dev, new->q_size,
+						 &new->q_base_pa, GFP_KERNEL);
+		if (!new->q_base) {
+			netdev_err(lif->netdev, "Cannot allocate qcq DMA memory\n");
+			err = -ENOMEM;
+			goto err_out_free_cq_info;
+		}
+		q_base = PTR_ALIGN(new->q_base, PAGE_SIZE);
+		q_base_pa = ALIGN(new->q_base_pa, PAGE_SIZE);
+		ionic_q_map(&new->q, q_base, q_base_pa);
+
+		cq_base = PTR_ALIGN(q_base + q_size, PAGE_SIZE);
+		cq_base_pa = ALIGN(new->q_base_pa + q_size, PAGE_SIZE);
+		ionic_cq_map(&new->cq, cq_base, cq_base_pa);
+		ionic_cq_bind(&new->cq, &new->q);
+	} else {
+		new->q_size = PAGE_SIZE + (num_descs * desc_size);
+		new->q_base = dma_alloc_coherent(dev, new->q_size, &new->q_base_pa,
+						 GFP_KERNEL);
+		if (!new->q_base) {
+			netdev_err(lif->netdev, "Cannot allocate queue DMA memory\n");
+			err = -ENOMEM;
+			goto err_out_free_cq_info;
+		}
+		q_base = PTR_ALIGN(new->q_base, PAGE_SIZE);
+		q_base_pa = ALIGN(new->q_base_pa, PAGE_SIZE);
+		ionic_q_map(&new->q, q_base, q_base_pa);
+
+		new->cq_size = PAGE_SIZE + (num_descs * cq_desc_size);
+		new->cq_base = dma_alloc_coherent(dev, new->cq_size, &new->cq_base_pa,
+						  GFP_KERNEL);
+		if (!new->cq_base) {
+			netdev_err(lif->netdev, "Cannot allocate cq DMA memory\n");
+			err = -ENOMEM;
+			goto err_out_free_q;
+		}
+		cq_base = PTR_ALIGN(new->cq_base, PAGE_SIZE);
+		cq_base_pa = ALIGN(new->cq_base_pa, PAGE_SIZE);
+		ionic_cq_map(&new->cq, cq_base, cq_base_pa);
+		ionic_cq_bind(&new->cq, &new->q);
 	}
-	cq_base = PTR_ALIGN(new->cq_base, PAGE_SIZE);
-	cq_base_pa = ALIGN(new->cq_base_pa, PAGE_SIZE);
-	ionic_cq_map(&new->cq, cq_base, cq_base_pa);
-	ionic_cq_bind(&new->cq, &new->q);
 
 	if (flags & IONIC_QCQ_F_SG) {
 		new->sg_size = PAGE_SIZE + (num_descs * sg_desc_size);
@@ -798,7 +836,7 @@ static bool ionic_notifyq_service(struct ionic_cq *cq,
 
 	switch (le16_to_cpu(comp->event.ecode)) {
 	case IONIC_EVENT_LINK_CHANGE:
-		ionic_link_status_check_request(lif);
+		ionic_link_status_check_request(lif, false);
 		break;
 	case IONIC_EVENT_RESET:
 		work = kzalloc(sizeof(*work), GFP_ATOMIC);
@@ -981,9 +1019,9 @@ static int ionic_lif_addr_del(struct ionic_lif *lif, const u8 *addr)
 	return 0;
 }
 
-static int ionic_lif_addr(struct ionic_lif *lif, const u8 *addr, bool add)
+static int ionic_lif_addr(struct ionic_lif *lif, const u8 *addr, bool add,
+			  bool can_sleep)
 {
-	struct ionic *ionic = lif->ionic;
 	struct ionic_deferred_work *work;
 	unsigned int nmfilters;
 	unsigned int nufilters;
@@ -993,8 +1031,8 @@ static int ionic_lif_addr(struct ionic_lif *lif, const u8 *addr, bool add)
 		 * here before checking the need for deferral so that we
 		 * can return an overflow error to the stack.
 		 */
-		nmfilters = le32_to_cpu(ionic->ident.lif.eth.max_mcast_filters);
-		nufilters = le32_to_cpu(ionic->ident.lif.eth.max_ucast_filters);
+		nmfilters = le32_to_cpu(lif->identity->eth.max_mcast_filters);
+		nufilters = le32_to_cpu(lif->identity->eth.max_ucast_filters);
 
 		if ((is_multicast_ether_addr(addr) && lif->nmcast < nmfilters))
 			lif->nmcast++;
@@ -1010,7 +1048,7 @@ static int ionic_lif_addr(struct ionic_lif *lif, const u8 *addr, bool add)
 			lif->nucast--;
 	}
 
-	if (in_interrupt()) {
+	if (!can_sleep) {
 		work = kzalloc(sizeof(*work), GFP_ATOMIC);
 		if (!work) {
 			netdev_err(lif->netdev, "%s OOM\n", __func__);
@@ -1036,12 +1074,22 @@ static int ionic_lif_addr(struct ionic_lif *lif, const u8 *addr, bool add)
 
 static int ionic_addr_add(struct net_device *netdev, const u8 *addr)
 {
-	return ionic_lif_addr(netdev_priv(netdev), addr, true);
+	return ionic_lif_addr(netdev_priv(netdev), addr, true, true);
+}
+
+static int ionic_ndo_addr_add(struct net_device *netdev, const u8 *addr)
+{
+	return ionic_lif_addr(netdev_priv(netdev), addr, true, false);
 }
 
 static int ionic_addr_del(struct net_device *netdev, const u8 *addr)
 {
-	return ionic_lif_addr(netdev_priv(netdev), addr, false);
+	return ionic_lif_addr(netdev_priv(netdev), addr, false, true);
+}
+
+static int ionic_ndo_addr_del(struct net_device *netdev, const u8 *addr)
+{
+	return ionic_lif_addr(netdev_priv(netdev), addr, false, false);
 }
 
 static void ionic_lif_rx_mode(struct ionic_lif *lif, unsigned int rx_mode)
@@ -1081,11 +1129,12 @@ static void ionic_lif_rx_mode(struct ionic_lif *lif, unsigned int rx_mode)
 		lif->rx_mode = rx_mode;
 }
 
-static void _ionic_lif_rx_mode(struct ionic_lif *lif, unsigned int rx_mode)
+static void _ionic_lif_rx_mode(struct ionic_lif *lif, unsigned int rx_mode,
+			       bool from_ndo)
 {
 	struct ionic_deferred_work *work;
 
-	if (in_interrupt()) {
+	if (from_ndo) {
 		work = kzalloc(sizeof(*work), GFP_ATOMIC);
 		if (!work) {
 			netdev_err(lif->netdev, "%s OOM\n", __func__);
@@ -1100,15 +1149,21 @@ static void _ionic_lif_rx_mode(struct ionic_lif *lif, unsigned int rx_mode)
 	}
 }
 
-static void ionic_set_rx_mode(struct net_device *netdev)
+static void ionic_dev_uc_sync(struct net_device *netdev, bool from_ndo)
+{
+	if (from_ndo)
+		__dev_uc_sync(netdev, ionic_ndo_addr_add, ionic_ndo_addr_del);
+	else
+		__dev_uc_sync(netdev, ionic_addr_add, ionic_addr_del);
+
+}
+
+static void ionic_set_rx_mode(struct net_device *netdev, bool from_ndo)
 {
 	struct ionic_lif *lif = netdev_priv(netdev);
-	struct ionic_identity *ident;
 	unsigned int nfilters;
 	unsigned int rx_mode;
 
-	ident = &lif->ionic->ident;
-
 	rx_mode = IONIC_RX_MODE_F_UNICAST;
 	rx_mode |= (netdev->flags & IFF_MULTICAST) ? IONIC_RX_MODE_F_MULTICAST : 0;
 	rx_mode |= (netdev->flags & IFF_BROADCAST) ? IONIC_RX_MODE_F_BROADCAST : 0;
@@ -1122,8 +1177,8 @@ static void ionic_set_rx_mode(struct net_device *netdev)
 	 *       we remove our overflow flag and check the netdev flags
 	 *       to see if we can disable NIC PROMISC
 	 */
-	__dev_uc_sync(netdev, ionic_addr_add, ionic_addr_del);
-	nfilters = le32_to_cpu(ident->lif.eth.max_ucast_filters);
+	ionic_dev_uc_sync(netdev, from_ndo);
+	nfilters = le32_to_cpu(lif->identity->eth.max_ucast_filters);
 	if (netdev_uc_count(netdev) + 1 > nfilters) {
 		rx_mode |= IONIC_RX_MODE_F_PROMISC;
 		lif->uc_overflow = true;
@@ -1134,8 +1189,8 @@ static void ionic_set_rx_mode(struct net_device *netdev)
 	}
 
 	/* same for multicast */
-	__dev_mc_sync(netdev, ionic_addr_add, ionic_addr_del);
-	nfilters = le32_to_cpu(ident->lif.eth.max_mcast_filters);
+	ionic_dev_uc_sync(netdev, from_ndo);
+	nfilters = le32_to_cpu(lif->identity->eth.max_mcast_filters);
 	if (netdev_mc_count(netdev) > nfilters) {
 		rx_mode |= IONIC_RX_MODE_F_ALLMULTI;
 		lif->mc_overflow = true;
@@ -1146,7 +1201,12 @@ static void ionic_set_rx_mode(struct net_device *netdev)
 	}
 
 	if (lif->rx_mode != rx_mode)
-		_ionic_lif_rx_mode(lif, rx_mode);
+		_ionic_lif_rx_mode(lif, rx_mode, from_ndo);
+}
+
+static void ionic_ndo_set_rx_mode(struct net_device *netdev)
+{
+	ionic_set_rx_mode(netdev, true);
 }
 
 static __le64 ionic_netdev_features_to_nic(netdev_features_t features)
@@ -1391,7 +1451,7 @@ static int ionic_start_queues_reconfig(struct ionic_lif *lif)
 	 */
 	err = ionic_txrx_init(lif);
 	mutex_unlock(&lif->queue_lock);
-	ionic_link_status_check_request(lif);
+	ionic_link_status_check_request(lif, true);
 	netif_device_attach(lif->netdev);
 
 	return err;
@@ -1568,22 +1628,16 @@ static void ionic_lif_rss_deinit(struct ionic_lif *lif)
 static void ionic_txrx_disable(struct ionic_lif *lif)
 {
 	unsigned int i;
-	int err;
+	int err = 0;
 
 	if (lif->txqcqs) {
-		for (i = 0; i < lif->nxqs; i++) {
-			err = ionic_qcq_disable(lif->txqcqs[i]);
-			if (err == -ETIMEDOUT)
-				break;
-		}
+		for (i = 0; i < lif->nxqs; i++)
+			err = ionic_qcq_disable(lif->txqcqs[i], (err != -ETIMEDOUT));
 	}
 
 	if (lif->rxqcqs) {
-		for (i = 0; i < lif->nxqs; i++) {
-			err = ionic_qcq_disable(lif->rxqcqs[i]);
-			if (err == -ETIMEDOUT)
-				break;
-		}
+		for (i = 0; i < lif->nxqs; i++)
+			err = ionic_qcq_disable(lif->rxqcqs[i], (err != -ETIMEDOUT));
 	}
 }
 
@@ -1720,7 +1774,7 @@ static int ionic_txrx_init(struct ionic_lif *lif)
 	if (lif->netdev->features & NETIF_F_RXHASH)
 		ionic_lif_rss_init(lif);
 
-	ionic_set_rx_mode(lif->netdev);
+	ionic_set_rx_mode(lif->netdev, false);
 
 	return 0;
 
@@ -1735,9 +1789,16 @@ err_out:
 
 static int ionic_txrx_enable(struct ionic_lif *lif)
 {
+	int derr = 0;
 	int i, err;
 
 	for (i = 0; i < lif->nxqs; i++) {
+		if (!(lif->rxqcqs[i] && lif->txqcqs[i])) {
+			dev_err(lif->ionic->dev, "%s: bad qcq %d\n", __func__, i);
+			err = -ENXIO;
+			goto err_out;
+		}
+
 		ionic_rx_fill(&lif->rxqcqs[i]->q);
 		err = ionic_qcq_enable(lif->rxqcqs[i]);
 		if (err)
@@ -1745,8 +1806,7 @@ static int ionic_txrx_enable(struct ionic_lif *lif)
 
 		err = ionic_qcq_enable(lif->txqcqs[i]);
 		if (err) {
-			if (err != -ETIMEDOUT)
-				ionic_qcq_disable(lif->rxqcqs[i]);
+			derr = ionic_qcq_disable(lif->rxqcqs[i], (err != -ETIMEDOUT));
 			goto err_out;
 		}
 	}
@@ -1755,12 +1815,8 @@ static int ionic_txrx_enable(struct ionic_lif *lif)
 
 err_out:
 	while (i--) {
-		err = ionic_qcq_disable(lif->txqcqs[i]);
-		if (err == -ETIMEDOUT)
-			break;
-		err = ionic_qcq_disable(lif->rxqcqs[i]);
-		if (err == -ETIMEDOUT)
-			break;
+		derr = ionic_qcq_disable(lif->txqcqs[i], (derr != -ETIMEDOUT));
+		derr = ionic_qcq_disable(lif->rxqcqs[i], (derr != -ETIMEDOUT));
 	}
 
 	return err;
@@ -2093,7 +2149,7 @@ static const struct net_device_ops ionic_netdev_ops = {
 	.ndo_stop               = ionic_stop,
 	.ndo_start_xmit		= ionic_start_xmit,
 	.ndo_get_stats64	= ionic_get_stats64,
-	.ndo_set_rx_mode	= ionic_set_rx_mode,
+	.ndo_set_rx_mode	= ionic_ndo_set_rx_mode,
 	.ndo_set_features	= ionic_set_features,
 	.ndo_set_mac_address	= ionic_set_mac_address,
 	.ndo_validate_addr	= eth_validate_addr,
@@ -2365,7 +2421,12 @@ int ionic_lif_alloc(struct ionic *ionic)
 
 	lif->identity = lid;
 	lif->lif_type = IONIC_LIF_TYPE_CLASSIC;
-	ionic_lif_identify(ionic, lif->lif_type, lif->identity);
+	err = ionic_lif_identify(ionic, lif->lif_type, lif->identity);
+	if (err) {
+		dev_err(ionic->dev, "Cannot identify type %d: %d\n",
+			lif->lif_type, err);
+		goto err_out_free_netdev;
+	}
 	lif->netdev->min_mtu = max_t(unsigned int, ETH_MIN_MTU,
 				     le32_to_cpu(lif->identity->eth.min_frame_size));
 	lif->netdev->max_mtu =
@@ -2496,7 +2557,15 @@ static void ionic_lif_handle_fw_up(struct ionic_lif *lif)
 	dev_info(ionic->dev, "FW Up: restarting LIFs\n");
 
 	ionic_init_devinfo(ionic);
-	ionic_port_init(ionic);
+	err = ionic_identify(ionic);
+	if (err)
+		goto err_out;
+	err = ionic_port_identify(ionic);
+	if (err)
+		goto err_out;
+	err = ionic_port_init(ionic);
+	if (err)
+		goto err_out;
 	err = ionic_qcqs_alloc(lif);
 	if (err)
 		goto err_out;
@@ -2521,7 +2590,7 @@ static void ionic_lif_handle_fw_up(struct ionic_lif *lif)
 	}
 
 	clear_bit(IONIC_LIF_F_FW_RESET, lif->state);
-	ionic_link_status_check_request(lif);
+	ionic_link_status_check_request(lif, true);
 	netif_device_attach(lif->netdev);
 	dev_info(ionic->dev, "FW Up: LIFs restarted\n");
 
@@ -2713,7 +2782,7 @@ static int ionic_station_set(struct ionic_lif *lif)
 		 */
 		if (!ether_addr_equal(ctx.comp.lif_getattr.mac,
 				      netdev->dev_addr))
-			ionic_lif_addr(lif, netdev->dev_addr, true);
+			ionic_lif_addr(lif, netdev->dev_addr, true, true);
 	} else {
 		/* Update the netdev mac with the device's mac */
 		memcpy(addr.sa_data, ctx.comp.lif_getattr.mac, netdev->addr_len);
@@ -2730,7 +2799,7 @@ static int ionic_station_set(struct ionic_lif *lif)
 
 	netdev_dbg(lif->netdev, "adding station MAC addr %pM\n",
 		   netdev->dev_addr);
-	ionic_lif_addr(lif, netdev->dev_addr, true);
+	ionic_lif_addr(lif, netdev->dev_addr, true, true);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.h b/drivers/net/ethernet/pensando/ionic/ionic_lif.h
index c65a5e6c26f4..0224dfd24b8a 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.h
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.h
@@ -245,7 +245,7 @@ static inline u32 ionic_coal_usec_to_hw(struct ionic *ionic, u32 usecs)
 
 typedef void (*ionic_reset_cb)(struct ionic_lif *lif, void *arg);
 
-void ionic_link_status_check_request(struct ionic_lif *lif);
+void ionic_link_status_check_request(struct ionic_lif *lif, bool can_sleep);
 void ionic_get_stats64(struct net_device *netdev,
 		       struct rtnl_link_stats64 *ns);
 void ionic_lif_deferred_enqueue(struct ionic_deferred *def,
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_main.c b/drivers/net/ethernet/pensando/ionic/ionic_main.c
index e339216949a6..ee0740881af3 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_main.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_main.c
@@ -64,6 +64,8 @@ static const char *ionic_error_to_str(enum ionic_status_code code)
 		return "IONIC_RC_ERROR";
 	case IONIC_RC_ERDMA:
 		return "IONIC_RC_ERDMA";
+	case IONIC_RC_EBAD_FW:
+		return "IONIC_RC_EBAD_FW";
 	default:
 		return "IONIC_RC_UNKNOWN";
 	}
@@ -255,8 +257,6 @@ static int ionic_adminq_post(struct ionic_lif *lif, struct ionic_admin_ctx *ctx)
 	struct ionic_queue *q;
 	int err = 0;
 
-	WARN_ON(in_interrupt());
-
 	if (!lif->adminqcq)
 		return -EIO;
 
@@ -328,8 +328,6 @@ int ionic_dev_cmd_wait(struct ionic *ionic, unsigned long max_seconds)
 	int done;
 	int err;
 
-	WARN_ON(in_interrupt());
-
 	/* Wait for dev cmd to complete, retrying if we get EAGAIN,
 	 * but don't wait any longer than max_seconds.
 	 */
@@ -433,17 +431,23 @@ int ionic_identify(struct ionic *ionic)
 		sz = min(sizeof(ident->dev), sizeof(idev->dev_cmd_regs->data));
 		memcpy_fromio(&ident->dev, &idev->dev_cmd_regs->data, sz);
 	}
-
 	mutex_unlock(&ionic->dev_cmd_lock);
 
-	if (err)
-		goto err_out_unmap;
+	if (err) {
+		dev_err(ionic->dev, "Cannot identify ionic: %dn", err);
+		goto err_out;
+	}
 
-	ionic_debugfs_add_ident(ionic);
+	err = ionic_lif_identify(ionic, IONIC_LIF_TYPE_CLASSIC,
+				 &ionic->ident.lif);
+	if (err) {
+		dev_err(ionic->dev, "Cannot identify LIFs: %d\n", err);
+		goto err_out;
+	}
 
 	return 0;
 
-err_out_unmap:
+err_out:
 	return err;
 }
 
diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic.h b/drivers/net/ethernet/qlogic/netxen/netxen_nic.h
index 86153660d245..e5c51256243a 100644
--- a/drivers/net/ethernet/qlogic/netxen/netxen_nic.h
+++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic.h
@@ -1189,9 +1189,6 @@ typedef struct {
 #define NX_FORCE_FW_RESET               0xdeaddead
 
 
-/* Fw dump levels */
-static const u32 FW_DUMP_LEVELS[] = { 0x3, 0x7, 0xf, 0x1f, 0x3f, 0x7f, 0xff };
-
 /* Flash read/write address */
 #define NX_FW_DUMP_REG1         0x00130060
 #define NX_FW_DUMP_REG2         0x001e0000
diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_ethtool.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_ethtool.c
index c3f50ddbe824..dd22cb056d03 100644
--- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_ethtool.c
+++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_ethtool.c
@@ -814,6 +814,9 @@ netxen_get_dump_flag(struct net_device *netdev, struct ethtool_dump *dump)
 	return 0;
 }
 
+/* Fw dump levels */
+static const u32 FW_DUMP_LEVELS[] = { 0x3, 0x7, 0xf, 0x1f, 0x3f, 0x7f, 0xff };
+
 static int
 netxen_set_dump(struct net_device *netdev, struct ethtool_dump *val)
 {
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c
index f7f08e6a3acf..d2f5855b2ea7 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dev.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c
@@ -4254,7 +4254,8 @@ static int qed_hw_get_nvm_info(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 			cdev->mf_bits = BIT(QED_MF_LLH_MAC_CLSS) |
 					BIT(QED_MF_LLH_PROTO_CLSS) |
 					BIT(QED_MF_LL2_NON_UNICAST) |
-					BIT(QED_MF_INTER_PF_SWITCH);
+					BIT(QED_MF_INTER_PF_SWITCH) |
+					BIT(QED_MF_DISABLE_ARFS);
 			break;
 		case NVM_CFG1_GLOB_MF_MODE_DEFAULT:
 			cdev->mf_bits = BIT(QED_MF_LLH_MAC_CLSS) |
@@ -4267,6 +4268,14 @@ static int qed_hw_get_nvm_info(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 
 		DP_INFO(p_hwfn, "Multi function mode is 0x%lx\n",
 			cdev->mf_bits);
+
+		/* In CMT the PF is unknown when the GFS block processes the
+		 * packet. Therefore cannot use searcher as it has a per PF
+		 * database, and thus ARFS must be disabled.
+		 *
+		 */
+		if (QED_IS_CMT(cdev))
+			cdev->mf_bits |= BIT(QED_MF_DISABLE_ARFS);
 	}
 
 	DP_INFO(p_hwfn, "Multi function mode is 0x%lx\n",
diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c
index 4c6ac8862744..07824bf9d68d 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_l2.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c
@@ -1980,6 +1980,9 @@ void qed_arfs_mode_configure(struct qed_hwfn *p_hwfn,
 			     struct qed_ptt *p_ptt,
 			     struct qed_arfs_config_params *p_cfg_params)
 {
+	if (test_bit(QED_MF_DISABLE_ARFS, &p_hwfn->cdev->mf_bits))
+		return;
+
 	if (p_cfg_params->mode != QED_FILTER_CONFIG_MODE_DISABLE) {
 		qed_gft_config(p_hwfn, p_ptt, p_hwfn->rel_pf_id,
 			       p_cfg_params->tcp,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c
index 0452b728c527..49783f365079 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c
@@ -1185,7 +1185,7 @@ static int qed_ll2_acquire_connection_tx(struct qed_hwfn *p_hwfn,
 		.elem_size	= sizeof(struct core_tx_bd),
 	};
 	struct qed_ll2_tx_packet *p_descq;
-	u32 desc_size;
+	size_t desc_size;
 	u32 capacity;
 	int rc = 0;
 
@@ -1198,10 +1198,9 @@ static int qed_ll2_acquire_connection_tx(struct qed_hwfn *p_hwfn,
 		goto out;
 
 	capacity = qed_chain_get_capacity(&p_ll2_info->tx_queue.txq_chain);
-	/* First element is part of the packet, rest are flexibly added */
-	desc_size = (sizeof(*p_descq) +
-		     (p_ll2_info->input.tx_max_bds_per_packet - 1) *
-		     sizeof(p_descq->bds_set));
+	/* All bds_set elements are flexibily added. */
+	desc_size = struct_size(p_descq, bds_set,
+				p_ll2_info->input.tx_max_bds_per_packet);
 
 	p_descq = kcalloc(capacity, desc_size, GFP_KERNEL);
 	if (!p_descq) {
@@ -1524,7 +1523,7 @@ int qed_ll2_establish_connection(void *cxt, u8 connection_handle)
 	struct qed_ptt *p_ptt;
 	int rc = -EINVAL;
 	u32 i, capacity;
-	u32 desc_size;
+	size_t desc_size;
 	u8 qid;
 
 	p_ptt = qed_ptt_acquire(p_hwfn);
@@ -1558,10 +1557,9 @@ int qed_ll2_establish_connection(void *cxt, u8 connection_handle)
 	INIT_LIST_HEAD(&p_tx->sending_descq);
 	spin_lock_init(&p_tx->lock);
 	capacity = qed_chain_get_capacity(&p_tx->txq_chain);
-	/* First element is part of the packet, rest are flexibly added */
-	desc_size = (sizeof(*p_pkt) +
-		     (p_ll2_conn->input.tx_max_bds_per_packet - 1) *
-		     sizeof(p_pkt->bds_set));
+	/* All bds_set elements are flexibily added. */
+	desc_size = struct_size(p_pkt, bds_set,
+				p_ll2_conn->input.tx_max_bds_per_packet);
 
 	for (i = 0; i < capacity; i++) {
 		p_pkt = p_tx->descq_mem + desc_size * i;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.h b/drivers/net/ethernet/qlogic/qed/qed_ll2.h
index 500d0c4f8077..df88d00053a2 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ll2.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.h
@@ -56,7 +56,7 @@ struct qed_ll2_tx_packet {
 		struct core_tx_bd *txq_bd;
 		dma_addr_t tx_frag;
 		u16 frag_len;
-	} bds_set[1];
+	} bds_set[];
 };
 
 struct qed_ll2_rx_queue {
@@ -86,9 +86,6 @@ struct qed_ll2_tx_queue {
 	struct list_head active_descq;
 	struct list_head free_descq;
 	struct list_head sending_descq;
-	void *descq_mem; /* memory for variable sized qed_ll2_tx_packet*/
-	struct qed_ll2_tx_packet *cur_send_packet;
-	struct qed_ll2_tx_packet cur_completing_packet;
 	u16 cur_completing_bd_idx;
 	void __iomem *doorbell_addr;
 	struct core_db_data db_msg;
@@ -96,6 +93,9 @@ struct qed_ll2_tx_queue {
 	u16 cur_send_frag_num;
 	u16 cur_completing_frag_num;
 	bool b_completing_packet;
+	void *descq_mem; /* memory for variable sized qed_ll2_tx_packet*/
+	struct qed_ll2_tx_packet *cur_send_packet;
+	struct qed_ll2_tx_packet cur_completing_packet;
 };
 
 struct qed_ll2_info {
diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c
index f2ab2b086946..5bd58c65e163 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_main.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_main.c
@@ -445,6 +445,8 @@ int qed_fill_dev_info(struct qed_dev *cdev,
 		dev_info->fw_eng = FW_ENGINEERING_VERSION;
 		dev_info->b_inter_pf_switch = test_bit(QED_MF_INTER_PF_SWITCH,
 						       &cdev->mf_bits);
+		if (!test_bit(QED_MF_DISABLE_ARFS, &cdev->mf_bits))
+			dev_info->b_arfs_capable = true;
 		dev_info->tx_switching = true;
 
 		if (hw_info->b_wol_support == QED_WOL_SUPPORT_PME)
diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c
index f1f75b6d0421..b8dc5c4591ef 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c
@@ -71,6 +71,7 @@ static int qed_sp_vf_start(struct qed_hwfn *p_hwfn, struct qed_vf_info *p_vf)
 		p_ramrod->personality = PERSONALITY_ETH;
 		break;
 	case QED_PCI_ETH_ROCE:
+	case QED_PCI_ETH_IWARP:
 		p_ramrod->personality = PERSONALITY_RDMA_AND_ETH;
 		break;
 	default:
diff --git a/drivers/net/ethernet/qlogic/qede/qede_filter.c b/drivers/net/ethernet/qlogic/qede/qede_filter.c
index f961f65d9372..c59b72c90293 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_filter.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_filter.c
@@ -311,6 +311,9 @@ int qede_alloc_arfs(struct qede_dev *edev)
 {
 	int i;
 
+	if (!edev->dev_info.common.b_arfs_capable)
+		return -EINVAL;
+
 	edev->arfs = vzalloc(sizeof(*edev->arfs));
 	if (!edev->arfs)
 		return -ENOMEM;
diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index 20d2296beb79..05e3a3b60269 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -804,7 +804,7 @@ static void qede_init_ndev(struct qede_dev *edev)
 		      NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
 		      NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_HW_TC;
 
-	if (!IS_VF(edev) && edev->dev_info.common.num_hwfns == 1)
+	if (edev->dev_info.common.b_arfs_capable)
 		hw_features |= NETIF_F_NTUPLE;
 
 	if (edev->dev_info.common.vxlan_enable ||
@@ -2295,7 +2295,7 @@ static void qede_unload(struct qede_dev *edev, enum qede_unload_mode mode,
 	qede_vlan_mark_nonconfigured(edev);
 	edev->ops->fastpath_stop(edev->cdev);
 
-	if (!IS_VF(edev) && edev->dev_info.common.num_hwfns == 1) {
+	if (edev->dev_info.common.b_arfs_capable) {
 		qede_poll_for_freeing_arfs_filters(edev);
 		qede_free_arfs(edev);
 	}
@@ -2362,10 +2362,9 @@ static int qede_load(struct qede_dev *edev, enum qede_load_mode mode,
 	if (rc)
 		goto err2;
 
-	if (!IS_VF(edev) && edev->dev_info.common.num_hwfns == 1) {
-		rc = qede_alloc_arfs(edev);
-		if (rc)
-			DP_NOTICE(edev, "aRFS memory allocation failed\n");
+	if (qede_alloc_arfs(edev)) {
+		edev->ndev->features &= ~NETIF_F_NTUPLE;
+		edev->dev_info.common.b_arfs_capable = false;
 	}
 
 	qede_napi_add_enable(edev);
diff --git a/drivers/net/ethernet/qualcomm/emac/emac.c b/drivers/net/ethernet/qualcomm/emac/emac.c
index 1166b98d8bb2..8543bf3c3484 100644
--- a/drivers/net/ethernet/qualcomm/emac/emac.c
+++ b/drivers/net/ethernet/qualcomm/emac/emac.c
@@ -292,6 +292,7 @@ static void emac_tx_timeout(struct net_device *netdev, unsigned int txqueue)
 
 /**
  * emac_update_hw_stats - read the EMAC stat registers
+ * @adpt: pointer to adapter struct
  *
  * Reads the stats registers and write the values to adpt->stats.
  *
diff --git a/drivers/net/ethernet/realtek/8139cp.c b/drivers/net/ethernet/realtek/8139cp.c
index e291e6ac40cb..4e44313b7651 100644
--- a/drivers/net/ethernet/realtek/8139cp.c
+++ b/drivers/net/ethernet/realtek/8139cp.c
@@ -1239,7 +1239,7 @@ static void cp_tx_timeout(struct net_device *dev, unsigned int txqueue)
 {
 	struct cp_private *cp = netdev_priv(dev);
 	unsigned long flags;
-	int rc, i;
+	int i;
 
 	netdev_warn(dev, "Transmit timeout, status %2x %4x %4x %4x\n",
 		    cpr8(Cmd), cpr16(CpCmd),
@@ -1260,7 +1260,7 @@ static void cp_tx_timeout(struct net_device *dev, unsigned int txqueue)
 
 	cp_stop_hw(cp);
 	cp_clean_rings(cp);
-	rc = cp_init_rings(cp);
+	cp_init_rings(cp);
 	cp_start_hw(cp);
 	__cp_set_rx_mode(dev);
 	cpw16_f(IntrMask, cp_norx_intr_mask);
diff --git a/drivers/net/ethernet/renesas/ravb.h b/drivers/net/ethernet/renesas/ravb.h
index 9f88b5db4f89..7453b17a37a2 100644
--- a/drivers/net/ethernet/renesas/ravb.h
+++ b/drivers/net/ethernet/renesas/ravb.h
@@ -1036,7 +1036,10 @@ struct ravb_private {
 	unsigned no_avb_link:1;
 	unsigned avb_link_active_low:1;
 	unsigned wol_enabled:1;
-	int num_tx_desc;	/* TX descriptors per packet */
+	unsigned rxcidm:1;		/* RX Clock Internal Delay Mode */
+	unsigned txcidm:1;		/* TX Clock Internal Delay Mode */
+	unsigned rgmii_override:1;	/* Deprecated rgmii-*id behavior */
+	int num_tx_desc;		/* TX descriptors per packet */
 };
 
 static inline u32 ravb_read(struct net_device *ndev, enum ravb_reg reg)
diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index f684296df871..5082c16bf9c0 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -1034,11 +1034,8 @@ static int ravb_phy_init(struct net_device *ndev)
 		pn = of_node_get(np);
 	}
 
-	iface = priv->phy_interface;
-	if (priv->chip_id != RCAR_GEN2 && phy_interface_mode_is_rgmii(iface)) {
-		/* ravb_set_delay_mode() takes care of internal delay mode */
-		iface = PHY_INTERFACE_MODE_RGMII;
-	}
+	iface = priv->rgmii_override ? PHY_INTERFACE_MODE_RGMII
+				     : priv->phy_interface;
 	phydev = of_phy_connect(ndev, pn, ravb_adjust_link, 0, iface);
 	of_node_put(pn);
 	if (!phydev) {
@@ -1999,23 +1996,53 @@ static const struct soc_device_attribute ravb_delay_mode_quirk_match[] = {
 };
 
 /* Set tx and rx clock internal delay modes */
-static void ravb_set_delay_mode(struct net_device *ndev)
+static void ravb_parse_delay_mode(struct device_node *np, struct net_device *ndev)
 {
 	struct ravb_private *priv = netdev_priv(ndev);
-	int set = 0;
+	bool explicit_delay = false;
+	u32 delay;
+
+	if (!of_property_read_u32(np, "rx-internal-delay-ps", &delay)) {
+		/* Valid values are 0 and 1800, according to DT bindings */
+		priv->rxcidm = !!delay;
+		explicit_delay = true;
+	}
+	if (!of_property_read_u32(np, "tx-internal-delay-ps", &delay)) {
+		/* Valid values are 0 and 2000, according to DT bindings */
+		priv->txcidm = !!delay;
+		explicit_delay = true;
+	}
 
+	if (explicit_delay)
+		return;
+
+	/* Fall back to legacy rgmii-*id behavior */
 	if (priv->phy_interface == PHY_INTERFACE_MODE_RGMII_ID ||
-	    priv->phy_interface == PHY_INTERFACE_MODE_RGMII_RXID)
-		set |= APSR_DM_RDM;
+	    priv->phy_interface == PHY_INTERFACE_MODE_RGMII_RXID) {
+		priv->rxcidm = 1;
+		priv->rgmii_override = 1;
+	}
 
 	if (priv->phy_interface == PHY_INTERFACE_MODE_RGMII_ID ||
 	    priv->phy_interface == PHY_INTERFACE_MODE_RGMII_TXID) {
 		if (!WARN(soc_device_match(ravb_delay_mode_quirk_match),
 			  "phy-mode %s requires TX clock internal delay mode which is not supported by this hardware revision. Please update device tree",
-			  phy_modes(priv->phy_interface)))
-			set |= APSR_DM_TDM;
+			  phy_modes(priv->phy_interface))) {
+			priv->txcidm = 1;
+			priv->rgmii_override = 1;
+		}
 	}
+}
+
+static void ravb_set_delay_mode(struct net_device *ndev)
+{
+	struct ravb_private *priv = netdev_priv(ndev);
+	u32 set = 0;
 
+	if (priv->rxcidm)
+		set |= APSR_DM_RDM;
+	if (priv->txcidm)
+		set |= APSR_DM_TDM;
 	ravb_modify(ndev, APSR, APSR_DM, set);
 }
 
@@ -2148,8 +2175,10 @@ static int ravb_probe(struct platform_device *pdev)
 	/* Request GTI loading */
 	ravb_modify(ndev, GCCR, GCCR_LTI, GCCR_LTI);
 
-	if (priv->chip_id != RCAR_GEN2)
+	if (priv->chip_id != RCAR_GEN2) {
+		ravb_parse_delay_mode(np, ndev);
 		ravb_set_delay_mode(ndev);
+	}
 
 	/* Allocate descriptor base address table */
 	priv->desc_bat_size = sizeof(struct ravb_desc) * DBAT_ENTRY_NUM;
diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index 586642c33d2b..c63304632935 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -45,6 +45,15 @@
 #define SH_ETH_OFFSET_DEFAULTS			\
 	[0 ... SH_ETH_MAX_REGISTER_OFFSET - 1] = SH_ETH_OFFSET_INVALID
 
+/* use some intentionally tricky logic here to initialize the whole struct to
+ * 0xffff, but then override certain fields, requiring us to indicate that we
+ * "know" that there are overrides in this structure, and we'll need to disable
+ * that warning from W=1 builds. GCC has supported this option since 4.2.X, but
+ * the macros available to do this only define GCC 8.
+ */
+__diag_push();
+__diag_ignore(GCC, 8, "-Woverride-init",
+	      "logic to initialize all and then override some is OK");
 static const u16 sh_eth_offset_gigabit[SH_ETH_MAX_REGISTER_OFFSET] = {
 	SH_ETH_OFFSET_DEFAULTS,
 
@@ -332,6 +341,7 @@ static const u16 sh_eth_offset_fast_sh3_sh2[SH_ETH_MAX_REGISTER_OFFSET] = {
 
 	[TSU_ADRH0]	= 0x0100,
 };
+__diag_pop();
 
 static void sh_eth_rcv_snd_disable(struct net_device *ndev);
 static struct net_device_stats *sh_eth_get_stats(struct net_device *ndev);
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c
index 2cc8184b7e6b..971f1e54b652 100644
--- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c
@@ -97,7 +97,7 @@ void sxgbe_disable_eee_mode(struct sxgbe_priv_data * const priv)
 
 /**
  * sxgbe_eee_ctrl_timer
- * @arg : data hook
+ * @t: timer list containing a data
  * Description:
  *  If there is no data transfer and if we are not in LPI state,
  *  then MAC Transmitter can be moved to LPI state.
@@ -255,7 +255,7 @@ static void sxgbe_adjust_link(struct net_device *dev)
 
 /**
  * sxgbe_init_phy - PHY initialization
- * @dev: net device structure
+ * @ndev: net device structure
  * Description: it initializes the driver's PHY state, and attaches the PHY
  * to the mac driver.
  *  Return value:
@@ -364,8 +364,11 @@ static int sxgbe_init_rx_buffers(struct net_device *dev,
 /**
  * sxgbe_free_rx_buffers - free what sxgbe_init_rx_buffers() allocated
  * @dev: net device structure
+ * @p: dec pointer
+ * @i: index
+ * @dma_buf_sz: size
  * @rx_ring: ring to be freed
- * @rx_rsize: ring size
+ *
  * Description:  this function initializes the DMA RX descriptor
  */
 static void sxgbe_free_rx_buffers(struct net_device *dev,
@@ -383,6 +386,7 @@ static void sxgbe_free_rx_buffers(struct net_device *dev,
 /**
  * init_tx_ring - init the TX descriptor ring
  * @dev: net device structure
+ * @queue_no: queue
  * @tx_ring: ring to be initialised
  * @tx_rsize: ring size
  * Description:  this function initializes the DMA TX descriptor
@@ -449,6 +453,7 @@ static void free_rx_ring(struct device *dev, struct sxgbe_rx_queue *rx_ring,
 /**
  * init_rx_ring - init the RX descriptor ring
  * @dev: net device structure
+ * @queue_no: queue
  * @rx_ring: ring to be initialised
  * @rx_rsize: ring size
  * Description:  this function initializes the DMA RX descriptor
@@ -548,7 +553,7 @@ static void free_tx_ring(struct device *dev, struct sxgbe_tx_queue *tx_ring,
 
 /**
  * init_dma_desc_rings - init the RX/TX descriptor rings
- * @dev: net device structure
+ * @netd: net device structure
  * Description:  this function initializes the DMA RX/TX descriptors
  * and allocates the socket buffers. It suppors the chained and ring
  * modes.
@@ -724,7 +729,7 @@ static void sxgbe_mtl_operation_mode(struct sxgbe_priv_data *priv)
 
 /**
  * sxgbe_tx_queue_clean:
- * @priv: driver private structure
+ * @tqueue: queue pointer
  * Description: it reclaims resources after transmission completes.
  */
 static void sxgbe_tx_queue_clean(struct sxgbe_tx_queue *tqueue)
@@ -807,6 +812,7 @@ static void sxgbe_tx_all_clean(struct sxgbe_priv_data * const priv)
 /**
  * sxgbe_restart_tx_queue: irq tx error mng function
  * @priv: driver private structure
+ * @queue_num: queue number
  * Description: it cleans the descriptors and restarts the transmission
  * in case of errors.
  */
@@ -1567,6 +1573,7 @@ static int sxgbe_poll(struct napi_struct *napi, int budget)
 /**
  *  sxgbe_tx_timeout
  *  @dev : Pointer to net device structure
+ *  @txqueue: index of the hanging queue
  *  Description: this function is called when a packet transmission fails to
  *   complete within a reasonable time. The driver will mark the error in the
  *   netdev structure and arrange for the device to be reset to a sane state
diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index c9df2e96ebe4..da6886dcac37 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -1871,18 +1871,9 @@ static int efx_ef10_try_update_nic_stats_vf(struct efx_nic *efx)
 
 	spin_unlock_bh(&efx->stats_lock);
 
-	if (in_interrupt()) {
-		/* If in atomic context, cannot update stats.  Just update the
-		 * software stats and return so the caller can continue.
-		 */
-		spin_lock_bh(&efx->stats_lock);
-		efx_update_sw_stats(efx, stats);
-		return 0;
-	}
-
 	efx_ef10_get_stat_mask(efx, mask);
 
-	rc = efx_nic_alloc_buffer(efx, &stats_buf, dma_len, GFP_ATOMIC);
+	rc = efx_nic_alloc_buffer(efx, &stats_buf, dma_len, GFP_KERNEL);
 	if (rc) {
 		spin_lock_bh(&efx->stats_lock);
 		return rc;
@@ -1938,6 +1929,18 @@ static size_t efx_ef10_update_stats_vf(struct efx_nic *efx, u64 *full_stats,
 	return efx_ef10_update_stats_common(efx, full_stats, core_stats);
 }
 
+static size_t efx_ef10_update_stats_atomic_vf(struct efx_nic *efx, u64 *full_stats,
+					      struct rtnl_link_stats64 *core_stats)
+{
+	struct efx_ef10_nic_data *nic_data = efx->nic_data;
+
+	/* In atomic context, cannot update HW stats.  Just update the
+	 * software stats and return so the caller can continue.
+	 */
+	efx_update_sw_stats(efx, nic_data->stats);
+	return efx_ef10_update_stats_common(efx, full_stats, core_stats);
+}
+
 static void efx_ef10_push_irq_moderation(struct efx_channel *channel)
 {
 	struct efx_nic *efx = channel->efx;
@@ -3998,6 +4001,7 @@ const struct efx_nic_type efx_hunt_a0_vf_nic_type = {
 	.finish_flr = efx_port_dummy_op_void,
 	.describe_stats = efx_ef10_describe_stats,
 	.update_stats = efx_ef10_update_stats_vf,
+	.update_stats_atomic = efx_ef10_update_stats_atomic_vf,
 	.start_stats = efx_port_dummy_op_void,
 	.pull_stats = efx_port_dummy_op_void,
 	.stop_stats = efx_port_dummy_op_void,
diff --git a/drivers/net/ethernet/sfc/ef100.c b/drivers/net/ethernet/sfc/ef100.c
index c54b7f8243f3..ffdb36715a49 100644
--- a/drivers/net/ethernet/sfc/ef100.c
+++ b/drivers/net/ethernet/sfc/ef100.c
@@ -490,6 +490,7 @@ static int ef100_pci_probe(struct pci_dev *pci_dev,
 	if (fcw.offset > pci_resource_len(efx->pci_dev, fcw.bar) - ESE_GZ_FCW_LEN) {
 		netif_err(efx, probe, efx->net_dev,
 			  "Func control window overruns BAR\n");
+		rc = -EIO;
 		goto fail;
 	}
 
diff --git a/drivers/net/ethernet/sfc/efx_common.c b/drivers/net/ethernet/sfc/efx_common.c
index c256db241570..72a3f0e09f52 100644
--- a/drivers/net/ethernet/sfc/efx_common.c
+++ b/drivers/net/ethernet/sfc/efx_common.c
@@ -602,7 +602,7 @@ void efx_net_stats(struct net_device *net_dev, struct rtnl_link_stats64 *stats)
 	struct efx_nic *efx = netdev_priv(net_dev);
 
 	spin_lock_bh(&efx->stats_lock);
-	efx->type->update_stats(efx, NULL, stats);
+	efx_nic_update_stats_atomic(efx, NULL, stats);
 	spin_unlock_bh(&efx->stats_lock);
 }
 
diff --git a/drivers/net/ethernet/sfc/falcon/farch.c b/drivers/net/ethernet/sfc/falcon/farch.c
index fa1ade856b10..2c91792cec01 100644
--- a/drivers/net/ethernet/sfc/falcon/farch.c
+++ b/drivers/net/ethernet/sfc/falcon/farch.c
@@ -870,17 +870,12 @@ static u16 ef4_farch_handle_rx_not_ok(struct ef4_rx_queue *rx_queue,
 {
 	struct ef4_channel *channel = ef4_rx_queue_channel(rx_queue);
 	struct ef4_nic *efx = rx_queue->efx;
-	bool rx_ev_buf_owner_id_err, rx_ev_ip_hdr_chksum_err;
+	bool __maybe_unused rx_ev_buf_owner_id_err, rx_ev_ip_hdr_chksum_err;
 	bool rx_ev_tcp_udp_chksum_err, rx_ev_eth_crc_err;
 	bool rx_ev_frm_trunc, rx_ev_drib_nib, rx_ev_tobe_disc;
-	bool rx_ev_other_err, rx_ev_pause_frm;
-	bool rx_ev_hdr_type, rx_ev_mcast_pkt;
-	unsigned rx_ev_pkt_type;
+	bool rx_ev_pause_frm;
 
-	rx_ev_hdr_type = EF4_QWORD_FIELD(*event, FSF_AZ_RX_EV_HDR_TYPE);
-	rx_ev_mcast_pkt = EF4_QWORD_FIELD(*event, FSF_AZ_RX_EV_MCAST_PKT);
 	rx_ev_tobe_disc = EF4_QWORD_FIELD(*event, FSF_AZ_RX_EV_TOBE_DISC);
-	rx_ev_pkt_type = EF4_QWORD_FIELD(*event, FSF_AZ_RX_EV_PKT_TYPE);
 	rx_ev_buf_owner_id_err = EF4_QWORD_FIELD(*event,
 						 FSF_AZ_RX_EV_BUF_OWNER_ID_ERR);
 	rx_ev_ip_hdr_chksum_err = EF4_QWORD_FIELD(*event,
@@ -893,10 +888,6 @@ static u16 ef4_farch_handle_rx_not_ok(struct ef4_rx_queue *rx_queue,
 			  0 : EF4_QWORD_FIELD(*event, FSF_AA_RX_EV_DRIB_NIB));
 	rx_ev_pause_frm = EF4_QWORD_FIELD(*event, FSF_AZ_RX_EV_PAUSE_FRM_ERR);
 
-	/* Every error apart from tobe_disc and pause_frm */
-	rx_ev_other_err = (rx_ev_drib_nib | rx_ev_tcp_udp_chksum_err |
-			   rx_ev_buf_owner_id_err | rx_ev_eth_crc_err |
-			   rx_ev_frm_trunc | rx_ev_ip_hdr_chksum_err);
 
 	/* Count errors that are not in MAC stats.  Ignore expected
 	 * checksum errors during self-test. */
@@ -916,6 +907,13 @@ static u16 ef4_farch_handle_rx_not_ok(struct ef4_rx_queue *rx_queue,
 	 * to a FIFO overflow.
 	 */
 #ifdef DEBUG
+	{
+	/* Every error apart from tobe_disc and pause_frm */
+
+	bool rx_ev_other_err = (rx_ev_drib_nib | rx_ev_tcp_udp_chksum_err |
+				rx_ev_buf_owner_id_err | rx_ev_eth_crc_err |
+				rx_ev_frm_trunc | rx_ev_ip_hdr_chksum_err);
+
 	if (rx_ev_other_err && net_ratelimit()) {
 		netif_dbg(efx, rx_err, efx->net_dev,
 			  " RX queue %d unexpected RX event "
@@ -932,6 +930,7 @@ static u16 ef4_farch_handle_rx_not_ok(struct ef4_rx_queue *rx_queue,
 			  rx_ev_tobe_disc ? " [TOBE_DISC]" : "",
 			  rx_ev_pause_frm ? " [PAUSE]" : "");
 	}
+	}
 #endif
 
 	/* The frame must be discarded if any of these are true. */
@@ -1643,15 +1642,11 @@ void ef4_farch_rx_push_indir_table(struct ef4_nic *efx)
  */
 void ef4_farch_dimension_resources(struct ef4_nic *efx, unsigned sram_lim_qw)
 {
-	unsigned vi_count, buftbl_min;
+	unsigned vi_count;
 
 	/* Account for the buffer table entries backing the datapath channels
 	 * and the descriptor caches for those channels.
 	 */
-	buftbl_min = ((efx->n_rx_channels * EF4_MAX_DMAQ_SIZE +
-		       efx->n_tx_channels * EF4_TXQ_TYPES * EF4_MAX_DMAQ_SIZE +
-		       efx->n_channels * EF4_MAX_EVQ_SIZE)
-		      * sizeof(ef4_qword_t) / EF4_BUF_SIZE);
 	vi_count = max(efx->n_channels, efx->n_tx_channels * EF4_TXQ_TYPES);
 
 	efx->tx_dc_base = sram_lim_qw - vi_count * TX_DC_ENTRIES;
@@ -2532,7 +2527,6 @@ int ef4_farch_filter_remove_safe(struct ef4_nic *efx,
 	enum ef4_farch_filter_table_id table_id;
 	struct ef4_farch_filter_table *table;
 	unsigned int filter_idx;
-	struct ef4_farch_filter_spec *spec;
 	int rc;
 
 	table_id = ef4_farch_filter_id_table_id(filter_id);
@@ -2543,7 +2537,6 @@ int ef4_farch_filter_remove_safe(struct ef4_nic *efx,
 	filter_idx = ef4_farch_filter_id_index(filter_id);
 	if (filter_idx >= table->size)
 		return -ENOENT;
-	spec = &table->spec[filter_idx];
 
 	spin_lock_bh(&efx->filter_lock);
 	rc = ef4_farch_filter_remove(efx, table, filter_idx, priority);
diff --git a/drivers/net/ethernet/sfc/falcon/rx.c b/drivers/net/ethernet/sfc/falcon/rx.c
index 05ea3523890a..966f13e7475d 100644
--- a/drivers/net/ethernet/sfc/falcon/rx.c
+++ b/drivers/net/ethernet/sfc/falcon/rx.c
@@ -140,6 +140,7 @@ static struct page *ef4_reuse_page(struct ef4_rx_queue *rx_queue)
  * ef4_init_rx_buffers - create EF4_RX_BATCH page-based RX buffers
  *
  * @rx_queue:		Efx RX queue
+ * @atomic:		control memory allocation flags
  *
  * This allocates a batch of pages, maps them for DMA, and populates
  * struct ef4_rx_buffers for each one. Return a negative error code or
@@ -316,6 +317,7 @@ static void ef4_discard_rx_packet(struct ef4_channel *channel,
  * This will aim to fill the RX descriptor queue up to
  * @rx_queue->@max_fill. If there is insufficient atomic
  * memory to do so, a slow fill will be scheduled.
+ * @atomic: control memory allocation flags
  *
  * The caller must provide serialisation (none is used here). In practise,
  * this means this function must run from the NAPI handler, or be called
diff --git a/drivers/net/ethernet/sfc/falcon/selftest.c b/drivers/net/ethernet/sfc/falcon/selftest.c
index 147677c7c72f..6a454ac6f876 100644
--- a/drivers/net/ethernet/sfc/falcon/selftest.c
+++ b/drivers/net/ethernet/sfc/falcon/selftest.c
@@ -65,7 +65,7 @@ static const char *const ef4_interrupt_mode_names[] = {
 	STRING_TABLE_LOOKUP(efx->interrupt_mode, ef4_interrupt_mode)
 
 /**
- * ef4_loopback_state - persistent state during a loopback selftest
+ * struct ef4_loopback_state - persistent state during a loopback selftest
  * @flush:		Drop all packets in ef4_loopback_rx_packet
  * @packet_count:	Number of packets being used in this test
  * @skbs:		An array of skbs transmitted
diff --git a/drivers/net/ethernet/sfc/mcdi.h b/drivers/net/ethernet/sfc/mcdi.h
index ef6d21e4bd0b..69c2924a147c 100644
--- a/drivers/net/ethernet/sfc/mcdi.h
+++ b/drivers/net/ethernet/sfc/mcdi.h
@@ -190,6 +190,7 @@ void efx_mcdi_sensor_event(struct efx_nic *efx, efx_qword_t *ev);
  * 32-bit-aligned.  Also, on Siena we must copy to the MC shared
  * memory strictly 32 bits at a time, so add any necessary padding.
  */
+#define MCDI_TX_BUF_LEN(_len) DIV_ROUND_UP((_len), 4)
 #define _MCDI_DECLARE_BUF(_name, _len)					\
 	efx_dword_t _name[DIV_ROUND_UP(_len, 4)]
 #define MCDI_DECLARE_BUF(_name, _len)					\
diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h
index a4c0445a3e88..9f7dfdf708cf 100644
--- a/drivers/net/ethernet/sfc/net_driver.h
+++ b/drivers/net/ethernet/sfc/net_driver.h
@@ -458,7 +458,7 @@ enum efx_sync_events_state {
  *	were checked for expiry
  * @rfs_expire_index: next accelerated RFS filter ID to check for expiry
  * @n_rfs_succeeded: number of successful accelerated RFS filter insertions
- * @n_rfs_failed; number of failed accelerated RFS filter insertions
+ * @n_rfs_failed: number of failed accelerated RFS filter insertions
  * @filter_work: Work item for efx_filter_rfs_expire()
  * @rps_flow_id: Flow IDs of filters allocated for accelerated RFS,
  *      indexed by filter ID
@@ -1172,6 +1172,9 @@ struct efx_udp_tunnel {
  * @describe_stats: Describe statistics for ethtool
  * @update_stats: Update statistics not provided by event handling.
  *	Either argument may be %NULL.
+ * @update_stats_atomic: Update statistics while in atomic context, if that
+ *	is more limiting than @update_stats.  Otherwise, leave %NULL and
+ *	driver core will call @update_stats.
  * @start_stats: Start the regular fetching of statistics
  * @pull_stats: Pull stats from the NIC and wait until they arrive.
  * @stop_stats: Stop the regular fetching of statistics
@@ -1316,6 +1319,8 @@ struct efx_nic_type {
 	size_t (*describe_stats)(struct efx_nic *efx, u8 *names);
 	size_t (*update_stats)(struct efx_nic *efx, u64 *full_stats,
 			       struct rtnl_link_stats64 *core_stats);
+	size_t (*update_stats_atomic)(struct efx_nic *efx, u64 *full_stats,
+				      struct rtnl_link_stats64 *core_stats);
 	void (*start_stats)(struct efx_nic *efx);
 	void (*pull_stats)(struct efx_nic *efx);
 	void (*stop_stats)(struct efx_nic *efx);
diff --git a/drivers/net/ethernet/sfc/nic_common.h b/drivers/net/ethernet/sfc/nic_common.h
index 82271f0b8627..b9cafe9cd568 100644
--- a/drivers/net/ethernet/sfc/nic_common.h
+++ b/drivers/net/ethernet/sfc/nic_common.h
@@ -244,6 +244,13 @@ void efx_nic_update_stats(const struct efx_hw_stat_desc *desc, size_t count,
 			  const unsigned long *mask, u64 *stats,
 			  const void *dma_buf, bool accumulate);
 void efx_nic_fix_nodesc_drop_stat(struct efx_nic *efx, u64 *stat);
+static inline size_t efx_nic_update_stats_atomic(struct efx_nic *efx, u64 *full_stats,
+						 struct rtnl_link_stats64 *core_stats)
+{
+	if (efx->type->update_stats_atomic)
+		return efx->type->update_stats_atomic(efx, full_stats, core_stats);
+	return efx->type->update_stats(efx, full_stats, core_stats);
+}
 
 #define EFX_MAX_FLUSH_TIME 5000
 
diff --git a/drivers/net/ethernet/sfc/ptp.c b/drivers/net/ethernet/sfc/ptp.c
index 2e8c4569f03b..a39c5143b386 100644
--- a/drivers/net/ethernet/sfc/ptp.c
+++ b/drivers/net/ethernet/sfc/ptp.c
@@ -173,9 +173,11 @@ struct efx_ptp_match {
 
 /**
  * struct efx_ptp_event_rx - A PTP receive event (from MC)
+ * @link: list of events
  * @seq0: First part of (PTP) UUID
  * @seq1: Second part of (PTP) UUID and sequence number
  * @hwtimestamp: Event timestamp
+ * @expiry: Time which the packet arrived
  */
 struct efx_ptp_event_rx {
 	struct list_head link;
@@ -223,11 +225,13 @@ struct efx_ptp_timeset {
  *                  reset (disable, enable).
  * @rxfilter_event: Receive filter when operating
  * @rxfilter_general: Receive filter when operating
+ * @rxfilter_installed: Receive filter installed
  * @config: Current timestamp configuration
  * @enabled: PTP operation enabled
  * @mode: Mode in which PTP operating (PTP version)
  * @ns_to_nic_time: Function to convert from scalar nanoseconds to NIC time
  * @nic_to_kernel_time: Function to convert from NIC to kernel time
+ * @nic_time: contains time details
  * @nic_time.minor_max: Wrap point for NIC minor times
  * @nic_time.sync_event_diff_min: Minimum acceptable difference between time
  * in packet prefix and last MCDI time sync event i.e. how much earlier than
@@ -239,6 +243,7 @@ struct efx_ptp_timeset {
  * field in MCDI time sync event.
  * @min_synchronisation_ns: Minimum acceptable corrected sync window
  * @capabilities: Capabilities flags from the NIC
+ * @ts_corrections: contains corrections details
  * @ts_corrections.ptp_tx: Required driver correction of PTP packet transmit
  *                         timestamps
  * @ts_corrections.ptp_rx: Required driver correction of PTP packet receive
@@ -326,7 +331,7 @@ struct efx_ptp_data {
 	struct work_struct pps_work;
 	struct workqueue_struct *pps_workwq;
 	bool nic_ts_enabled;
-	_MCDI_DECLARE_BUF(txbuf, MC_CMD_PTP_IN_TRANSMIT_LENMAX);
+	efx_dword_t txbuf[MCDI_TX_BUF_LEN(MC_CMD_PTP_IN_TRANSMIT_LENMAX)];
 
 	unsigned int good_syncs;
 	unsigned int fast_syncs;
diff --git a/drivers/net/ethernet/sis/sis900.c b/drivers/net/ethernet/sis/sis900.c
index cfa460c7db23..620c26f71be8 100644
--- a/drivers/net/ethernet/sis/sis900.c
+++ b/drivers/net/ethernet/sis/sis900.c
@@ -789,10 +789,9 @@ static u16 sis900_default_phy(struct net_device * net_dev)
 static void sis900_set_capability(struct net_device *net_dev, struct mii_phy *phy)
 {
 	u16 cap;
-	u16 status;
 
-	status = mdio_read(net_dev, phy->phy_addr, MII_STATUS);
-	status = mdio_read(net_dev, phy->phy_addr, MII_STATUS);
+	mdio_read(net_dev, phy->phy_addr, MII_STATUS);
+	mdio_read(net_dev, phy->phy_addr, MII_STATUS);
 
 	cap = MII_NWAY_CSMA_CD |
 		((phy->status & MII_STAT_CAN_TX_FDX)? MII_NWAY_TX_FDX:0) |
@@ -1302,7 +1301,7 @@ static void sis630_set_eq(struct net_device *net_dev, u8 revision)
 
 /**
  *	sis900_timer - sis900 timer routine
- *	@data: pointer to sis900 net device
+ *	@t: timer list containing a pointer to sis900 net device
  *
  *	On each timer ticks we check two things,
  *	link status (ON/OFF) and link mode (10/100/Full/Half)
@@ -1536,6 +1535,7 @@ static void sis900_read_mode(struct net_device *net_dev, int *speed, int *duplex
 /**
  *	sis900_tx_timeout - sis900 transmit timeout routine
  *	@net_dev: the net device to transmit
+ *	@txqueue: index of hanging queue
  *
  *	print transmit timeout status
  *	disable interrupts and do some tasks
diff --git a/drivers/net/ethernet/socionext/sni_ave.c b/drivers/net/ethernet/socionext/sni_ave.c
index 81b554dd7221..501b9c7aba56 100644
--- a/drivers/net/ethernet/socionext/sni_ave.c
+++ b/drivers/net/ethernet/socionext/sni_ave.c
@@ -1585,7 +1585,7 @@ static int ave_probe(struct platform_device *pdev)
 	if (IS_ERR(base))
 		return PTR_ERR(base);
 
-	ndev = alloc_etherdev(sizeof(struct ave_private));
+	ndev = devm_alloc_etherdev(dev, sizeof(struct ave_private));
 	if (!ndev) {
 		dev_err(dev, "can't allocate ethernet device\n");
 		return -ENOMEM;
@@ -1632,7 +1632,7 @@ static int ave_probe(struct platform_device *pdev)
 	}
 	ret = dma_set_mask(dev, dma_mask);
 	if (ret)
-		goto out_free_netdev;
+		return ret;
 
 	priv->tx.ndesc = AVE_NR_TXDESC;
 	priv->rx.ndesc = AVE_NR_RXDESC;
@@ -1645,10 +1645,8 @@ static int ave_probe(struct platform_device *pdev)
 		if (!name)
 			break;
 		priv->clk[i] = devm_clk_get(dev, name);
-		if (IS_ERR(priv->clk[i])) {
-			ret = PTR_ERR(priv->clk[i]);
-			goto out_free_netdev;
-		}
+		if (IS_ERR(priv->clk[i]))
+			return PTR_ERR(priv->clk[i]);
 		priv->nclks++;
 	}
 
@@ -1657,10 +1655,8 @@ static int ave_probe(struct platform_device *pdev)
 		if (!name)
 			break;
 		priv->rst[i] = devm_reset_control_get_shared(dev, name);
-		if (IS_ERR(priv->rst[i])) {
-			ret = PTR_ERR(priv->rst[i]);
-			goto out_free_netdev;
-		}
+		if (IS_ERR(priv->rst[i]))
+			return PTR_ERR(priv->rst[i]);
 		priv->nrsts++;
 	}
 
@@ -1669,26 +1665,23 @@ static int ave_probe(struct platform_device *pdev)
 					       1, 0, &args);
 	if (ret) {
 		dev_err(dev, "can't get syscon-phy-mode property\n");
-		goto out_free_netdev;
+		return ret;
 	}
 	priv->regmap = syscon_node_to_regmap(args.np);
 	of_node_put(args.np);
 	if (IS_ERR(priv->regmap)) {
 		dev_err(dev, "can't map syscon-phy-mode\n");
-		ret = PTR_ERR(priv->regmap);
-		goto out_free_netdev;
+		return PTR_ERR(priv->regmap);
 	}
 	ret = priv->data->get_pinmode(priv, phy_mode, args.args[0]);
 	if (ret) {
 		dev_err(dev, "invalid phy-mode setting\n");
-		goto out_free_netdev;
+		return ret;
 	}
 
 	priv->mdio = devm_mdiobus_alloc(dev);
-	if (!priv->mdio) {
-		ret = -ENOMEM;
-		goto out_free_netdev;
-	}
+	if (!priv->mdio)
+		return -ENOMEM;
 	priv->mdio->priv = ndev;
 	priv->mdio->parent = dev;
 	priv->mdio->read = ave_mdiobus_read;
@@ -1725,8 +1718,6 @@ static int ave_probe(struct platform_device *pdev)
 out_del_napi:
 	netif_napi_del(&priv->napi_rx);
 	netif_napi_del(&priv->napi_tx);
-out_free_netdev:
-	free_netdev(ndev);
 
 	return ret;
 }
@@ -1739,7 +1730,6 @@ static int ave_remove(struct platform_device *pdev)
 	unregister_netdev(ndev);
 	netif_napi_del(&priv->napi_rx);
 	netif_napi_del(&priv->napi_tx);
-	free_netdev(ndev);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index cafa8e3c3573..df7de50497a0 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -481,6 +481,8 @@ struct mac_device_info {
 	unsigned int num_vlan;
 	u32 vlan_filter[32];
 	unsigned int promisc;
+	bool vlan_fail_q_en;
+	u8 vlan_fail_q;
 };
 
 struct stmmac_rx_routing {
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c
index b1323d5c95b5..f61cb997a8f6 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c
@@ -11,6 +11,7 @@
 #include <linux/platform_device.h>
 #include <linux/stmmac.h>
 
+#include "dwmac4.h"
 #include "stmmac.h"
 #include "stmmac_platform.h"
 
@@ -146,6 +147,14 @@ static int intel_eth_plat_probe(struct platform_device *pdev)
 	}
 
 	plat_dat->bsp_priv = dwmac;
+	plat_dat->eee_usecs_rate = plat_dat->clk_ptp_rate;
+
+	if (plat_dat->eee_usecs_rate > 0) {
+		u32 tx_lpi_usec;
+
+		tx_lpi_usec = (plat_dat->eee_usecs_rate / 1000000) - 1;
+		writel(tx_lpi_usec, stmmac_res.addr + GMAC_1US_TIC_COUNTER);
+	}
 
 	ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
 	if (ret) {
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
index 2ac9dfb3462c..2af9458be95f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
@@ -6,6 +6,7 @@
 #include <linux/pci.h>
 #include <linux/dmi.h>
 #include "dwmac-intel.h"
+#include "dwmac4.h"
 #include "stmmac.h"
 
 struct intel_priv_data {
@@ -295,6 +296,7 @@ static int intel_mgbe_common_data(struct pci_dev *pdev,
 	plat->axi->axi_blen[2] = 16;
 
 	plat->ptp_max_adj = plat->clk_ptp_rate;
+	plat->eee_usecs_rate = plat->clk_ptp_rate;
 
 	/* Set system clock */
 	plat->stmmac_clk = clk_register_fixed_rate(&pdev->dev,
@@ -321,6 +323,11 @@ static int intel_mgbe_common_data(struct pci_dev *pdev,
 	/* Set the maxmtu to a default of JUMBO_LEN */
 	plat->maxmtu = JUMBO_LEN;
 
+	plat->vlan_fail_q_en = true;
+
+	/* Use the last Rx queue */
+	plat->vlan_fail_q = plat->rx_queues_to_use - 1;
+
 	return 0;
 }
 
@@ -618,6 +625,13 @@ static int intel_eth_pci_probe(struct pci_dev *pdev,
 	if (ret)
 		return ret;
 
+	if (plat->eee_usecs_rate > 0) {
+		u32 tx_lpi_usec;
+
+		tx_lpi_usec = (plat->eee_usecs_rate / 1000000) - 1;
+		writel(tx_lpi_usec, res.addr + GMAC_1US_TIC_COUNTER);
+	}
+
 	ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_ALL_TYPES);
 	if (ret < 0)
 		return ret;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
index 2d5573b3dee1..6ef30252bfe0 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /**
- * dwmac-rk.c - Rockchip RK3288 DWMAC specific glue layer
+ * DOC: dwmac-rk.c - Rockchip RK3288 DWMAC specific glue layer
  *
  * Copyright (C) 2014 Chen-Zhi (Roger Chen)
  *
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
index 61f3249bd724..592b043f9676 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
@@ -76,6 +76,7 @@
 #define GMAC_PACKET_FILTER_HPF		BIT(10)
 #define GMAC_PACKET_FILTER_VTFE		BIT(16)
 #define GMAC_PACKET_FILTER_IPFE		BIT(20)
+#define GMAC_PACKET_FILTER_RA		BIT(31)
 
 #define GMAC_MAX_PERFECT_ADDRESSES	128
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
index ecd834e0e121..002791b77356 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
@@ -618,7 +618,18 @@ static void dwmac4_set_filter(struct mac_device_info *hw,
 	value &= ~GMAC_PACKET_FILTER_PM;
 	value &= ~GMAC_PACKET_FILTER_PR;
 	if (dev->flags & IFF_PROMISC) {
-		value = GMAC_PACKET_FILTER_PR | GMAC_PACKET_FILTER_PCF;
+		/* VLAN Tag Filter Fail Packets Queuing */
+		if (hw->vlan_fail_q_en) {
+			value = readl(ioaddr + GMAC_RXQ_CTRL4);
+			value &= ~GMAC_RXQCTRL_VFFQ_MASK;
+			value |= GMAC_RXQCTRL_VFFQE |
+				 (hw->vlan_fail_q << GMAC_RXQCTRL_VFFQ_SHIFT);
+			writel(value, ioaddr + GMAC_RXQ_CTRL4);
+			value = GMAC_PACKET_FILTER_PR | GMAC_PACKET_FILTER_RA;
+		} else {
+			value = GMAC_PACKET_FILTER_PR | GMAC_PACKET_FILTER_PCF;
+		}
+
 	} else if ((dev->flags & IFF_ALLMULTI) ||
 		   (netdev_mc_count(dev) > hw->multicast_filter_bins)) {
 		/* Pass all multi */
@@ -680,7 +691,7 @@ static void dwmac4_set_filter(struct mac_device_info *hw,
 
 	writel(value, ioaddr + GMAC_PACKET_FILTER);
 
-	if (dev->flags & IFF_PROMISC) {
+	if (dev->flags & IFF_PROMISC && !hw->vlan_fail_q_en) {
 		if (!hw->promisc) {
 			hw->promisc = 1;
 			dwmac4_vlan_promisc_enable(dev, hw);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac5.h b/drivers/net/ethernet/stmicro/stmmac/dwmac5.h
index 3e8faa96b4d4..56b0762c1276 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac5.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac5.h
@@ -92,6 +92,12 @@
 #define TCEIE				BIT(0)
 #define DMA_ECC_INT_STATUS		0x00001088
 
+/* EQoS version 5.xx VLAN Tag Filter Fail Packets Queuing */
+#define GMAC_RXQ_CTRL4			0x00000094
+#define GMAC_RXQCTRL_VFFQ_MASK		GENMASK(19, 17)
+#define GMAC_RXQCTRL_VFFQ_SHIFT		17
+#define GMAC_RXQCTRL_VFFQE		BIT(16)
+
 int dwmac5_safety_feat_config(void __iomem *ioaddr, unsigned int asp);
 int dwmac5_safety_feat_irq_status(struct net_device *ndev,
 		void __iomem *ioaddr, unsigned int asp,
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index df2c74bbfcff..4779826b997d 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -334,7 +334,7 @@ void stmmac_disable_eee_mode(struct stmmac_priv *priv)
 
 /**
  * stmmac_eee_ctrl_timer - EEE TX SW timer.
- * @arg : data hook
+ * @t:  timer_list struct containing private info
  * Description:
  *  if there is no data transfer and if we are not in LPI state,
  *  then MAC Transmitter can be moved to LPI state.
@@ -709,7 +709,7 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
  *  a proprietary structure used to pass information to the driver.
  *  Description:
  *  This function obtain the current hardware timestamping settings
-    as requested.
+ *  as requested.
  */
 static int stmmac_hwtstamp_get(struct net_device *dev, struct ifreq *ifr)
 {
@@ -769,6 +769,7 @@ static void stmmac_release_ptp(struct stmmac_priv *priv)
 /**
  *  stmmac_mac_flow_ctrl - Configure flow control in all queues
  *  @priv: driver private structure
+ *  @duplex: duplex passed to the next function
  *  Description: It is used for configuring the flow control in all queues
  */
 static void stmmac_mac_flow_ctrl(struct stmmac_priv *priv, u32 duplex)
@@ -1942,6 +1943,7 @@ static void stmmac_dma_operation_mode(struct stmmac_priv *priv)
 /**
  * stmmac_tx_clean - to manage the transmission completion
  * @priv: driver private structure
+ * @budget: napi budget limiting this functions packet handling
  * @queue: TX queue index
  * Description: it reclaims the transmit resources after transmission completes.
  */
@@ -2335,7 +2337,7 @@ static void stmmac_tx_timer_arm(struct stmmac_priv *priv, u32 queue)
 
 /**
  * stmmac_tx_timer - mitigation sw timer for tx.
- * @data: data pointer
+ * @t: data pointer
  * Description:
  * This is the timer handler to directly invoke the stmmac_tx_clean.
  */
@@ -2598,6 +2600,7 @@ static void stmmac_safety_feat_configuration(struct stmmac_priv *priv)
 /**
  * stmmac_hw_setup - setup mac in a usable state.
  *  @dev : pointer to the device structure.
+ *  @init_ptp: initialize PTP if set
  *  Description:
  *  this is the main function to setup the HW in a usable state because the
  *  dma engine is reset, the core registers are configured (e.g. AXI,
@@ -2958,7 +2961,7 @@ static bool stmmac_vlan_insert(struct stmmac_priv *priv, struct sk_buff *skb,
  *  @priv: driver private structure
  *  @des: buffer start address
  *  @total_len: total length to fill in descriptors
- *  @last_segmant: condition for the last descriptor
+ *  @last_segment: condition for the last descriptor
  *  @queue: TX queue index
  *  Description:
  *  This function fills descriptor and request new descriptors according to
@@ -3927,6 +3930,7 @@ static int stmmac_napi_poll_tx(struct napi_struct *napi, int budget)
 /**
  *  stmmac_tx_timeout
  *  @dev : Pointer to net device structure
+ *  @txqueue: the index of the hanging transmit queue
  *  Description: this function is called when a packet transmission fails to
  *   complete within a reasonable time. The driver will mark the error in the
  *   netdev structure and arrange for the device to be reset to a sane state
@@ -4709,6 +4713,9 @@ static int stmmac_hw_init(struct stmmac_priv *priv)
 	if (priv->dma_cap.tsoen)
 		dev_info(priv->device, "TSO supported\n");
 
+	priv->hw->vlan_fail_q_en = priv->plat->vlan_fail_q_en;
+	priv->hw->vlan_fail_q = priv->plat->vlan_fail_q;
+
 	/* Run HW quirks, if any */
 	if (priv->hwif_quirks) {
 		ret = priv->hwif_quirks(priv);
@@ -5162,7 +5169,7 @@ EXPORT_SYMBOL_GPL(stmmac_suspend);
 
 /**
  * stmmac_reset_queues_param - reset queue parameters
- * @dev: device pointer
+ * @priv: device pointer
  */
 static void stmmac_reset_queues_param(struct stmmac_priv *priv)
 {
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index f32317fa75c8..af34a4cadbb0 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -125,6 +125,7 @@ static struct stmmac_axi *stmmac_axi_setup(struct platform_device *pdev)
 /**
  * stmmac_mtl_setup - parse DT parameters for multiple queues configuration
  * @pdev: platform device
+ * @plat: enet data
  */
 static int stmmac_mtl_setup(struct platform_device *pdev,
 			    struct plat_stmmacenet_data *plat)
@@ -360,7 +361,7 @@ static int stmmac_dt_phy(struct plat_stmmacenet_data *plat,
 
 /**
  * stmmac_of_get_mac_mode - retrieves the interface of the MAC
- * @np - device-tree node
+ * @np: - device-tree node
  * Description:
  * Similar to `of_get_phy_mode()`, this function will retrieve (from
  * the device-tree) the interface mode on the MAC side. This assumes
diff --git a/drivers/net/ethernet/sun/cassini.c b/drivers/net/ethernet/sun/cassini.c
index b624e177ec71..9ff894ba8d3e 100644
--- a/drivers/net/ethernet/sun/cassini.c
+++ b/drivers/net/ethernet/sun/cassini.c
@@ -454,8 +454,8 @@ static int cas_page_free(struct cas *cp, cas_page_t *page)
 #define RX_USED_ADD(x, y)       ((x)->used += (y))
 #define RX_USED_SET(x, y)       ((x)->used  = (y))
 #else
-#define RX_USED_ADD(x, y)
-#define RX_USED_SET(x, y)
+#define RX_USED_ADD(x, y) do { } while(0)
+#define RX_USED_SET(x, y) do { } while(0)
 #endif
 
 /* local page allocation routines for the receive buffers. jumbo pages
diff --git a/drivers/net/ethernet/sun/sunbmac.c b/drivers/net/ethernet/sun/sunbmac.c
index 34fdbc6d6031..c646575e79d5 100644
--- a/drivers/net/ethernet/sun/sunbmac.c
+++ b/drivers/net/ethernet/sun/sunbmac.c
@@ -209,13 +209,13 @@ static void bigmac_clean_rings(struct bigmac *bp)
 	}
 }
 
-static void bigmac_init_rings(struct bigmac *bp, int from_irq)
+static void bigmac_init_rings(struct bigmac *bp, bool non_blocking)
 {
 	struct bmac_init_block *bb = bp->bmac_block;
 	int i;
 	gfp_t gfp_flags = GFP_KERNEL;
 
-	if (from_irq || in_interrupt())
+	if (non_blocking)
 		gfp_flags = GFP_ATOMIC;
 
 	bp->rx_new = bp->rx_old = bp->tx_new = bp->tx_old = 0;
@@ -489,7 +489,7 @@ static void bigmac_tcvr_init(struct bigmac *bp)
 	}
 }
 
-static int bigmac_init_hw(struct bigmac *, int);
+static int bigmac_init_hw(struct bigmac *, bool);
 
 static int try_next_permutation(struct bigmac *bp, void __iomem *tregs)
 {
@@ -549,7 +549,7 @@ static void bigmac_timer(struct timer_list *t)
 				if (ret == -1) {
 					printk(KERN_ERR "%s: Link down, cable problem?\n",
 					       bp->dev->name);
-					ret = bigmac_init_hw(bp, 0);
+					ret = bigmac_init_hw(bp, true);
 					if (ret) {
 						printk(KERN_ERR "%s: Error, cannot re-init the "
 						       "BigMAC.\n", bp->dev->name);
@@ -617,7 +617,7 @@ static void bigmac_begin_auto_negotiation(struct bigmac *bp)
 	add_timer(&bp->bigmac_timer);
 }
 
-static int bigmac_init_hw(struct bigmac *bp, int from_irq)
+static int bigmac_init_hw(struct bigmac *bp, bool non_blocking)
 {
 	void __iomem *gregs        = bp->gregs;
 	void __iomem *cregs        = bp->creg;
@@ -635,7 +635,7 @@ static int bigmac_init_hw(struct bigmac *bp, int from_irq)
 	qec_init(bp);
 
 	/* Alloc and reset the tx/rx descriptor chains. */
-	bigmac_init_rings(bp, from_irq);
+	bigmac_init_rings(bp, non_blocking);
 
 	/* Initialize the PHY. */
 	bigmac_tcvr_init(bp);
@@ -749,7 +749,7 @@ static void bigmac_is_medium_rare(struct bigmac *bp, u32 qec_status, u32 bmac_st
 	}
 
 	printk(" RESET\n");
-	bigmac_init_hw(bp, 1);
+	bigmac_init_hw(bp, true);
 }
 
 /* BigMAC transmit complete service routines. */
@@ -921,7 +921,7 @@ static int bigmac_open(struct net_device *dev)
 		return ret;
 	}
 	timer_setup(&bp->bigmac_timer, bigmac_timer, 0);
-	ret = bigmac_init_hw(bp, 0);
+	ret = bigmac_init_hw(bp, false);
 	if (ret)
 		free_irq(dev->irq, bp);
 	return ret;
@@ -945,7 +945,7 @@ static void bigmac_tx_timeout(struct net_device *dev, unsigned int txqueue)
 {
 	struct bigmac *bp = netdev_priv(dev);
 
-	bigmac_init_hw(bp, 0);
+	bigmac_init_hw(bp, true);
 	netif_wake_queue(dev);
 }
 
diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-common.c b/drivers/net/ethernet/synopsys/dwc-xlgmac-common.c
index eb1c6b03c329..df26cea45904 100644
--- a/drivers/net/ethernet/synopsys/dwc-xlgmac-common.c
+++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-common.c
@@ -513,7 +513,7 @@ void xlgmac_get_all_hw_features(struct xlgmac_pdata *pdata)
 
 void xlgmac_print_all_hw_features(struct xlgmac_pdata *pdata)
 {
-	char *str = NULL;
+	char __maybe_unused *str = NULL;
 
 	XLGMAC_PR("\n");
 	XLGMAC_PR("=====================================================\n");
diff --git a/drivers/net/ethernet/tehuti/tehuti.c b/drivers/net/ethernet/tehuti/tehuti.c
index a142e4c9fc03..b8f4f419173f 100644
--- a/drivers/net/ethernet/tehuti/tehuti.c
+++ b/drivers/net/ethernet/tehuti/tehuti.c
@@ -138,7 +138,10 @@ static void print_eth_id(struct net_device *ndev)
  * @priv: NIC private structure
  * @f: fifo to initialize
  * @fsz_type: fifo size type: 0-4KB, 1-8KB, 2-16KB, 3-32KB
- * @reg_XXX: offsets of registers relative to base address
+ * @reg_CFG0: offsets of registers relative to base address
+ * @reg_CFG1: offsets of registers relative to base address
+ * @reg_RPTR: offsets of registers relative to base address
+ * @reg_WPTR: offsets of registers relative to base address
  *
  * 1K extra space is allocated at the end of the fifo to simplify
  * processing of descriptors that wraps around fifo's end
@@ -558,7 +561,7 @@ static int bdx_reset(struct bdx_priv *priv)
 
 /**
  * bdx_close - Disables a network interface
- * @netdev: network interface device structure
+ * @ndev: network interface device structure
  *
  * Returns 0, this is not allowed to fail
  *
@@ -585,7 +588,7 @@ static int bdx_close(struct net_device *ndev)
 
 /**
  * bdx_open - Called when a network interface is made active
- * @netdev: network interface device structure
+ * @ndev: network interface device structure
  *
  * Returns 0 on success, negative value on failure
  *
@@ -698,7 +701,7 @@ static int bdx_ioctl(struct net_device *ndev, struct ifreq *ifr, int cmd)
  * __bdx_vlan_rx_vid - private helper for adding/killing VLAN vid
  * @ndev: network device
  * @vid:  VLAN vid
- * @op:   add or kill operation
+ * @enable: enable or disable vlan
  *
  * Passes VLAN filter table to hardware
  */
@@ -729,6 +732,7 @@ static void __bdx_vlan_rx_vid(struct net_device *ndev, uint16_t vid, int enable)
 /**
  * bdx_vlan_rx_add_vid - kernel hook for adding VLAN vid to hw filtering table
  * @ndev: network device
+ * @proto: unused
  * @vid:  VLAN vid to add
  */
 static int bdx_vlan_rx_add_vid(struct net_device *ndev, __be16 proto, u16 vid)
@@ -740,6 +744,7 @@ static int bdx_vlan_rx_add_vid(struct net_device *ndev, __be16 proto, u16 vid)
 /**
  * bdx_vlan_rx_kill_vid - kernel hook for killing VLAN vid in hw filtering table
  * @ndev: network device
+ * @proto: unused
  * @vid:  VLAN vid to kill
  */
 static int bdx_vlan_rx_kill_vid(struct net_device *ndev, __be16 proto, u16 vid)
@@ -750,7 +755,7 @@ static int bdx_vlan_rx_kill_vid(struct net_device *ndev, __be16 proto, u16 vid)
 
 /**
  * bdx_change_mtu - Change the Maximum Transfer Unit
- * @netdev: network interface device structure
+ * @ndev: network interface device structure
  * @new_mtu: new value for maximum frame size
  *
  * Returns 0 on success, negative on failure
@@ -1753,6 +1758,8 @@ static void bdx_tx_cleanup(struct bdx_priv *priv)
 
 /**
  * bdx_tx_free_skbs - frees all skbs from TXD fifo.
+ * @priv: NIC private structure
+ *
  * It gets called when OS stops this dev, eg upon "ifconfig down" or rmmod
  */
 static void bdx_tx_free_skbs(struct bdx_priv *priv)
diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c
index a3528c5c823f..f779d2e1b5c5 100644
--- a/drivers/net/ethernet/ti/cpsw_new.c
+++ b/drivers/net/ethernet/ti/cpsw_new.c
@@ -17,6 +17,7 @@
 #include <linux/phy.h>
 #include <linux/phy/phy.h>
 #include <linux/delay.h>
+#include <linux/pinctrl/consumer.h>
 #include <linux/pm_runtime.h>
 #include <linux/gpio/consumer.h>
 #include <linux/of.h>
@@ -1659,12 +1660,10 @@ static int cpsw_dl_switch_mode_set(struct devlink *dl, u32 id,
 		for (i = 0; i < cpsw->data.slaves; i++) {
 			struct cpsw_slave *slave = &cpsw->slaves[i];
 			struct net_device *sl_ndev = slave->ndev;
-			struct cpsw_priv *priv;
 
 			if (!sl_ndev)
 				continue;
 
-			priv = netdev_priv(sl_ndev);
 			if (switch_en)
 				vlan = cpsw->data.default_vlan;
 			else
@@ -2069,9 +2068,61 @@ static int cpsw_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static int __maybe_unused cpsw_suspend(struct device *dev)
+{
+	struct cpsw_common *cpsw = dev_get_drvdata(dev);
+	int i;
+
+	rtnl_lock();
+
+	for (i = 0; i < cpsw->data.slaves; i++) {
+		struct net_device *ndev = cpsw->slaves[i].ndev;
+
+		if (!(ndev && netif_running(ndev)))
+			continue;
+
+		cpsw_ndo_stop(ndev);
+	}
+
+	rtnl_unlock();
+
+	/* Select sleep pin state */
+	pinctrl_pm_select_sleep_state(dev);
+
+	return 0;
+}
+
+static int __maybe_unused cpsw_resume(struct device *dev)
+{
+	struct cpsw_common *cpsw = dev_get_drvdata(dev);
+	int i;
+
+	/* Select default pin state */
+	pinctrl_pm_select_default_state(dev);
+
+	/* shut up ASSERT_RTNL() warning in netif_set_real_num_tx/rx_queues */
+	rtnl_lock();
+
+	for (i = 0; i < cpsw->data.slaves; i++) {
+		struct net_device *ndev = cpsw->slaves[i].ndev;
+
+		if (!(ndev && netif_running(ndev)))
+			continue;
+
+		cpsw_ndo_open(ndev);
+	}
+
+	rtnl_unlock();
+
+	return 0;
+}
+
+static SIMPLE_DEV_PM_OPS(cpsw_pm_ops, cpsw_suspend, cpsw_resume);
+
 static struct platform_driver cpsw_driver = {
 	.driver = {
 		.name	 = "cpsw-switch",
+		.pm	 = &cpsw_pm_ops,
 		.of_match_table = cpsw_of_mtable,
 	},
 	.probe = cpsw_probe,
diff --git a/drivers/net/ethernet/ti/davinci_cpdma.c b/drivers/net/ethernet/ti/davinci_cpdma.c
index 6614fa3089b2..d2eab5cd1e0c 100644
--- a/drivers/net/ethernet/ti/davinci_cpdma.c
+++ b/drivers/net/ethernet/ti/davinci_cpdma.c
@@ -718,7 +718,7 @@ static void cpdma_chan_set_descs(struct cpdma_ctlr *ctlr,
 		most_chan->desc_num += desc_cnt;
 }
 
-/**
+/*
  * cpdma_chan_split_pool - Splits ctrl pool between all channels.
  * Has to be called under ctlr lock
  */
diff --git a/drivers/net/ethernet/ti/davinci_emac.c b/drivers/net/ethernet/ti/davinci_emac.c
index de282531f68b..c7031e1960d4 100644
--- a/drivers/net/ethernet/ti/davinci_emac.c
+++ b/drivers/net/ethernet/ti/davinci_emac.c
@@ -671,7 +671,7 @@ static int emac_hash_del(struct emac_priv *priv, u8 *mac_addr)
  * emac_add_mcast - Set multicast address in the EMAC adapter (Internal)
  * @priv: The DaVinci EMAC private adapter structure
  * @action: multicast operation to perform
- * mac_addr: mac address to set
+ * @mac_addr: mac address to set
  *
  * Set multicast addresses in EMAC adapter - internal function
  *
@@ -977,6 +977,7 @@ fail_tx:
 /**
  * emac_dev_tx_timeout - EMAC Transmit timeout function
  * @ndev: The DaVinci EMAC network adapter
+ * @txqueue: the index of the hung transmit queue
  *
  * Called when system detects that a skb timeout period has expired
  * potentially due to a fault in the adapter in not being able to send
@@ -1209,7 +1210,7 @@ static int emac_hw_enable(struct emac_priv *priv)
 
 /**
  * emac_poll - EMAC NAPI Poll function
- * @ndev: The DaVinci EMAC network adapter
+ * @napi: pointer to the napi_struct containing The DaVinci EMAC network adapter
  * @budget: Number of receive packets to process (as told by NAPI layer)
  *
  * NAPI Poll function implemented to process packets as per budget. We check
@@ -1227,7 +1228,7 @@ static int emac_poll(struct napi_struct *napi, int budget)
 	struct net_device *ndev = priv->ndev;
 	struct device *emac_dev = &ndev->dev;
 	u32 status = 0;
-	u32 num_tx_pkts = 0, num_rx_pkts = 0;
+	u32 num_rx_pkts = 0;
 
 	/* Check interrupt vectors and call packet processing */
 	status = emac_read(EMAC_MACINVECTOR);
@@ -1238,8 +1239,7 @@ static int emac_poll(struct napi_struct *napi, int budget)
 		mask = EMAC_DM646X_MAC_IN_VECTOR_TX_INT_VEC;
 
 	if (status & mask) {
-		num_tx_pkts = cpdma_chan_process(priv->txchan,
-					      EMAC_DEF_TX_MAX_SERVICE);
+		cpdma_chan_process(priv->txchan, EMAC_DEF_TX_MAX_SERVICE);
 	} /* TX processing */
 
 	mask = EMAC_DM644X_MAC_IN_VECTOR_RX_INT_VEC;
diff --git a/drivers/net/ethernet/ti/tlan.c b/drivers/net/ethernet/ti/tlan.c
index 1203a3c0febb..317fad787d78 100644
--- a/drivers/net/ethernet/ti/tlan.c
+++ b/drivers/net/ethernet/ti/tlan.c
@@ -653,7 +653,6 @@ module_exit(tlan_exit);
 static void  __init tlan_eisa_probe(void)
 {
 	long	ioaddr;
-	int	rc = -ENODEV;
 	int	irq;
 	u16	device_id;
 
@@ -718,8 +717,7 @@ static void  __init tlan_eisa_probe(void)
 
 
 		/* Setup the newly found eisa adapter */
-		rc = tlan_probe1(NULL, ioaddr, irq,
-				 12, NULL);
+		tlan_probe1(NULL, ioaddr, irq, 12, NULL);
 		continue;
 
 out:
diff --git a/drivers/net/ethernet/via/via-rhine.c b/drivers/net/ethernet/via/via-rhine.c
index 803247d51fe9..26e6b087c0e4 100644
--- a/drivers/net/ethernet/via/via-rhine.c
+++ b/drivers/net/ethernet/via/via-rhine.c
@@ -1515,7 +1515,7 @@ static void rhine_init_cam_filter(struct net_device *dev)
 
 /**
  * rhine_update_vcam - update VLAN CAM filters
- * @rp: rhine_private data of this Rhine
+ * @dev: rhine_private data of this Rhine
  *
  * Update VLAN CAM filters to match configuration change.
  */
diff --git a/drivers/net/ethernet/via/via-velocity.c b/drivers/net/ethernet/via/via-velocity.c
index 6d2a31488a74..b65767f9e499 100644
--- a/drivers/net/ethernet/via/via-velocity.c
+++ b/drivers/net/ethernet/via/via-velocity.c
@@ -372,7 +372,7 @@ static const struct pci_device_id velocity_pci_id_table[] = {
 
 MODULE_DEVICE_TABLE(pci, velocity_pci_id_table);
 
-/**
+/*
  *	Describe the OF device identifiers that we support in this
  *	device driver. Used for devicetree nodes.
  */
@@ -384,7 +384,7 @@ MODULE_DEVICE_TABLE(of, velocity_of_ids);
 
 /**
  *	get_chip_name	- 	identifier to name
- *	@id: chip identifier
+ *	@chip_id: chip identifier
  *
  *	Given a chip identifier return a suitable description. Returns
  *	a pointer a static string valid while the driver is loaded.
@@ -748,7 +748,7 @@ static u32 mii_check_media_mode(struct mac_regs __iomem *regs)
 /**
  *	velocity_mii_write	-	write MII data
  *	@regs: velocity registers
- *	@index: MII register index
+ *	@mii_addr: MII register index
  *	@data: 16bit data for the MII register
  *
  *	Perform a single write to an MII 16bit register. Returns zero
@@ -869,6 +869,7 @@ static u32 check_connection_type(struct mac_regs __iomem *regs)
 
 /**
  *	velocity_set_media_mode		-	set media mode
+ *	@vptr: velocity adapter
  *	@mii_status: old MII link state
  *
  *	Check the media link state and configure the flow control
@@ -877,26 +878,13 @@ static u32 check_connection_type(struct mac_regs __iomem *regs)
  */
 static int velocity_set_media_mode(struct velocity_info *vptr, u32 mii_status)
 {
-	u32 curr_status;
 	struct mac_regs __iomem *regs = vptr->mac_regs;
 
 	vptr->mii_status = mii_check_media_mode(vptr->mac_regs);
-	curr_status = vptr->mii_status & (~VELOCITY_LINK_FAIL);
 
 	/* Set mii link status */
 	set_mii_flow_control(vptr);
 
-	/*
-	   Check if new status is consistent with current status
-	   if (((mii_status & curr_status) & VELOCITY_AUTONEG_ENABLE) ||
-	       (mii_status==curr_status)) {
-	   vptr->mii_status=mii_check_media_mode(vptr->mac_regs);
-	   vptr->mii_status=check_connection_type(vptr->mac_regs);
-	   netdev_info(vptr->netdev, "Velocity link no change\n");
-	   return 0;
-	   }
-	 */
-
 	if (PHYID_GET_PHY_ID(vptr->phy_id) == PHYID_CICADA_CS8201)
 		MII_REG_BITS_ON(AUXCR_MDPPS, MII_NCONFIG, vptr->mac_regs);
 
@@ -1269,6 +1257,7 @@ static void mii_init(struct velocity_info *vptr, u32 mii_status)
 
 /**
  * setup_queue_timers	-	Setup interrupt timers
+ * @vptr: velocity adapter
  *
  * Setup interrupt frequency during suppression (timeout if the frame
  * count isn't filled).
@@ -1293,8 +1282,7 @@ static void setup_queue_timers(struct velocity_info *vptr)
 
 /**
  * setup_adaptive_interrupts  -  Setup interrupt suppression
- *
- * @vptr velocity adapter
+ * @vptr: velocity adapter
  *
  * The velocity is able to suppress interrupt during high interrupt load.
  * This function turns on that feature.
@@ -1735,6 +1723,7 @@ err_free_dma_rings_0:
  *	velocity_free_tx_buf	-	free transmit buffer
  *	@vptr: velocity
  *	@tdinfo: buffer
+ *	@td: transmit descriptor to free
  *
  *	Release an transmit buffer. If the buffer was preallocated then
  *	recycle it, if not then unmap the buffer.
@@ -1909,7 +1898,7 @@ static void velocity_error(struct velocity_info *vptr, int status)
 
 /**
  *	tx_srv		-	transmit interrupt service
- *	@vptr; Velocity
+ *	@vptr: Velocity
  *
  *	Scan the queues looking for transmitted packets that
  *	we can complete and clean up. Update any statistics as
@@ -2003,8 +1992,7 @@ static inline void velocity_rx_csum(struct rx_desc *rd, struct sk_buff *skb)
  *	velocity_rx_copy	-	in place Rx copy for small packets
  *	@rx_skb: network layer packet buffer candidate
  *	@pkt_size: received data size
- *	@rd: receive packet descriptor
- *	@dev: network device
+ *	@vptr: velocity adapter
  *
  *	Replace the current skb that is scheduled for Rx processing by a
  *	shorter, immediately allocated skb, if the received packet is small
@@ -2110,6 +2098,7 @@ static int velocity_receive_frame(struct velocity_info *vptr, int idx)
 /**
  *	velocity_rx_srv		-	service RX interrupt
  *	@vptr: velocity
+ *	@budget_left: remaining budget
  *
  *	Walk the receive ring of the velocity adapter and remove
  *	any received packets from the receive queue. Hand the ring
@@ -2658,7 +2647,6 @@ static const struct net_device_ops velocity_netdev_ops = {
 
 /**
  *	velocity_init_info	-	init private data
- *	@pdev: PCI device
  *	@vptr: Velocity info
  *	@info: Board type
  *
@@ -2677,7 +2665,6 @@ static void velocity_init_info(struct velocity_info *vptr,
 /**
  *	velocity_get_pci_info	-	retrieve PCI info for device
  *	@vptr: velocity device
- *	@pdev: PCI device it matches
  *
  *	Retrieve the PCI configuration space data that interests us from
  *	the kernel PCI layer
@@ -2714,7 +2701,6 @@ static int velocity_get_pci_info(struct velocity_info *vptr)
 /**
  *	velocity_get_platform_info - retrieve platform info for device
  *	@vptr: velocity device
- *	@pdev: platform device it matches
  *
  *	Retrieve the Platform configuration data that interests us
  */
@@ -2764,8 +2750,9 @@ static u32 velocity_get_link(struct net_device *dev)
 
 /**
  *	velocity_probe - set up discovered velocity device
- *	@pdev: PCI device
- *	@ent: PCI device table entry that matched
+ *	@dev: PCI device
+ *	@info: table of match
+ *	@irq: interrupt info
  *	@bustype: bus that device is connected to
  *
  *	Configure a discovered adapter from scratch. Return a negative
@@ -2982,6 +2969,7 @@ static int velocity_platform_remove(struct platform_device *pdev)
 #ifdef CONFIG_PM_SLEEP
 /**
  *	wol_calc_crc		-	WOL CRC
+ *	@size: size of the wake mask
  *	@pattern: data pattern
  *	@mask_pattern: mask
  *
diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c
index 9a15f14daa47..60c199fcb91e 100644
--- a/drivers/net/ethernet/xilinx/ll_temac_main.c
+++ b/drivers/net/ethernet/xilinx/ll_temac_main.c
@@ -106,7 +106,7 @@ static bool hard_acs_rdy_or_timeout(struct temac_local *lp, ktime_t timeout)
  */
 #define HARD_ACS_RDY_POLL_NS (20 * NSEC_PER_MSEC)
 
-/**
+/*
  * temac_indirect_busywait - Wait for current indirect register access
  * to complete.
  */
@@ -121,7 +121,7 @@ int temac_indirect_busywait(struct temac_local *lp)
 		return 0;
 }
 
-/**
+/*
  * temac_indirect_in32 - Indirect register read access.  This function
  * must be called without lp->indirect_lock being held.
  */
@@ -136,7 +136,7 @@ u32 temac_indirect_in32(struct temac_local *lp, int reg)
 	return val;
 }
 
-/**
+/*
  * temac_indirect_in32_locked - Indirect register read access.  This
  * function must be called with lp->indirect_lock being held.  Use
  * this together with spin_lock_irqsave/spin_lock_irqrestore to avoid
@@ -164,7 +164,7 @@ u32 temac_indirect_in32_locked(struct temac_local *lp, int reg)
 	return temac_ior(lp, XTE_LSW0_OFFSET);
 }
 
-/**
+/*
  * temac_indirect_out32 - Indirect register write access.  This function
  * must be called without lp->indirect_lock being held.
  */
@@ -177,7 +177,7 @@ void temac_indirect_out32(struct temac_local *lp, int reg, u32 value)
 	spin_unlock_irqrestore(lp->indirect_lock, flags);
 }
 
-/**
+/*
  * temac_indirect_out32_locked - Indirect register write access.  This
  * function must be called with lp->indirect_lock being held.  Use
  * this together with spin_lock_irqsave/spin_lock_irqrestore to avoid
@@ -202,7 +202,7 @@ void temac_indirect_out32_locked(struct temac_local *lp, int reg, u32 value)
 	WARN_ON(temac_indirect_busywait(lp));
 }
 
-/**
+/*
  * temac_dma_in32_* - Memory mapped DMA read, these function expects a
  * register input that is based on DCR word addresses which are then
  * converted to memory mapped byte addresses.  To be assigned to
@@ -218,7 +218,7 @@ static u32 temac_dma_in32_le(struct temac_local *lp, int reg)
 	return ioread32(lp->sdma_regs + (reg << 2));
 }
 
-/**
+/*
  * temac_dma_out32_* - Memory mapped DMA read, these function expects
  * a register input that is based on DCR word addresses which are then
  * converted to memory mapped byte addresses.  To be assigned to
@@ -240,7 +240,7 @@ static void temac_dma_out32_le(struct temac_local *lp, int reg, u32 value)
  */
 #ifdef CONFIG_PPC_DCR
 
-/**
+/*
  * temac_dma_dcr_in32 - DCR based DMA read
  */
 static u32 temac_dma_dcr_in(struct temac_local *lp, int reg)
@@ -248,7 +248,7 @@ static u32 temac_dma_dcr_in(struct temac_local *lp, int reg)
 	return dcr_read(lp->sdma_dcrs, reg);
 }
 
-/**
+/*
  * temac_dma_dcr_out32 - DCR based DMA write
  */
 static void temac_dma_dcr_out(struct temac_local *lp, int reg, u32 value)
@@ -256,7 +256,7 @@ static void temac_dma_dcr_out(struct temac_local *lp, int reg, u32 value)
 	dcr_write(lp->sdma_dcrs, reg, value);
 }
 
-/**
+/*
  * temac_dcr_setup - If the DMA is DCR based, then setup the address and
  * I/O  functions
  */
@@ -293,7 +293,7 @@ static int temac_dcr_setup(struct temac_local *lp, struct platform_device *op,
 
 #endif
 
-/**
+/*
  * temac_dma_bd_release - Release buffer descriptor rings
  */
 static void temac_dma_bd_release(struct net_device *ndev)
@@ -323,7 +323,7 @@ static void temac_dma_bd_release(struct net_device *ndev)
 				  lp->tx_bd_v, lp->tx_bd_p);
 }
 
-/**
+/*
  * temac_dma_bd_init - Setup buffer descriptor rings
  */
 static int temac_dma_bd_init(struct net_device *ndev)
@@ -593,7 +593,7 @@ static struct temac_option {
 	{}
 };
 
-/**
+/*
  * temac_setoptions
  */
 static u32 temac_setoptions(struct net_device *ndev, u32 options)
diff --git a/drivers/net/fddi/skfp/h/smc.h b/drivers/net/fddi/skfp/h/smc.h
index 991857f6a83c..706fa619b703 100644
--- a/drivers/net/fddi/skfp/h/smc.h
+++ b/drivers/net/fddi/skfp/h/smc.h
@@ -122,7 +122,7 @@ struct s_rmt {
 	u_char timer1_exp ;		/* flag : timer 1 expired */
 	u_char timer2_exp ;		/* flag : timer 2 expired */
 
-	u_char rm_pad1[1] ;
+	u_char rm_pad1;
 } ;
 
 /*
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index c71f994fbc73..974a244f45ba 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -777,7 +777,8 @@ static struct rtable *geneve_get_v4_rt(struct sk_buff *skb,
 				       struct net_device *dev,
 				       struct geneve_sock *gs4,
 				       struct flowi4 *fl4,
-				       const struct ip_tunnel_info *info)
+				       const struct ip_tunnel_info *info,
+				       __be16 dport, __be16 sport)
 {
 	bool use_cache = ip_tunnel_dst_cache_usable(skb, info);
 	struct geneve_dev *geneve = netdev_priv(dev);
@@ -793,6 +794,8 @@ static struct rtable *geneve_get_v4_rt(struct sk_buff *skb,
 	fl4->flowi4_proto = IPPROTO_UDP;
 	fl4->daddr = info->key.u.ipv4.dst;
 	fl4->saddr = info->key.u.ipv4.src;
+	fl4->fl4_dport = dport;
+	fl4->fl4_sport = sport;
 
 	tos = info->key.tos;
 	if ((tos == 1) && !geneve->cfg.collect_md) {
@@ -827,7 +830,8 @@ static struct dst_entry *geneve_get_v6_dst(struct sk_buff *skb,
 					   struct net_device *dev,
 					   struct geneve_sock *gs6,
 					   struct flowi6 *fl6,
-					   const struct ip_tunnel_info *info)
+					   const struct ip_tunnel_info *info,
+					   __be16 dport, __be16 sport)
 {
 	bool use_cache = ip_tunnel_dst_cache_usable(skb, info);
 	struct geneve_dev *geneve = netdev_priv(dev);
@@ -843,6 +847,9 @@ static struct dst_entry *geneve_get_v6_dst(struct sk_buff *skb,
 	fl6->flowi6_proto = IPPROTO_UDP;
 	fl6->daddr = info->key.u.ipv6.dst;
 	fl6->saddr = info->key.u.ipv6.src;
+	fl6->fl6_dport = dport;
+	fl6->fl6_sport = sport;
+
 	prio = info->key.tos;
 	if ((prio == 1) && !geneve->cfg.collect_md) {
 		prio = ip_tunnel_get_dsfield(ip_hdr(skb), skb);
@@ -889,7 +896,9 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 	__be16 sport;
 	int err;
 
-	rt = geneve_get_v4_rt(skb, dev, gs4, &fl4, info);
+	sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true);
+	rt = geneve_get_v4_rt(skb, dev, gs4, &fl4, info,
+			      geneve->cfg.info.key.tp_dst, sport);
 	if (IS_ERR(rt))
 		return PTR_ERR(rt);
 
@@ -919,7 +928,6 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 		return -EMSGSIZE;
 	}
 
-	sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true);
 	if (geneve->cfg.collect_md) {
 		tos = ip_tunnel_ecn_encap(key->tos, ip_hdr(skb), skb);
 		ttl = key->ttl;
@@ -974,7 +982,9 @@ static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 	__be16 sport;
 	int err;
 
-	dst = geneve_get_v6_dst(skb, dev, gs6, &fl6, info);
+	sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true);
+	dst = geneve_get_v6_dst(skb, dev, gs6, &fl6, info,
+				geneve->cfg.info.key.tp_dst, sport);
 	if (IS_ERR(dst))
 		return PTR_ERR(dst);
 
@@ -1003,7 +1013,6 @@ static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 		return -EMSGSIZE;
 	}
 
-	sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true);
 	if (geneve->cfg.collect_md) {
 		prio = ip_tunnel_ecn_encap(key->tos, ip_hdr(skb), skb);
 		ttl = key->ttl;
@@ -1085,13 +1094,18 @@ static int geneve_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
 {
 	struct ip_tunnel_info *info = skb_tunnel_info(skb);
 	struct geneve_dev *geneve = netdev_priv(dev);
+	__be16 sport;
 
 	if (ip_tunnel_info_af(info) == AF_INET) {
 		struct rtable *rt;
 		struct flowi4 fl4;
+
 		struct geneve_sock *gs4 = rcu_dereference(geneve->sock4);
+		sport = udp_flow_src_port(geneve->net, skb,
+					  1, USHRT_MAX, true);
 
-		rt = geneve_get_v4_rt(skb, dev, gs4, &fl4, info);
+		rt = geneve_get_v4_rt(skb, dev, gs4, &fl4, info,
+				      geneve->cfg.info.key.tp_dst, sport);
 		if (IS_ERR(rt))
 			return PTR_ERR(rt);
 
@@ -1101,9 +1115,13 @@ static int geneve_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
 	} else if (ip_tunnel_info_af(info) == AF_INET6) {
 		struct dst_entry *dst;
 		struct flowi6 fl6;
+
 		struct geneve_sock *gs6 = rcu_dereference(geneve->sock6);
+		sport = udp_flow_src_port(geneve->net, skb,
+					  1, USHRT_MAX, true);
 
-		dst = geneve_get_v6_dst(skb, dev, gs6, &fl6, info);
+		dst = geneve_get_v6_dst(skb, dev, gs6, &fl6, info,
+					geneve->cfg.info.key.tp_dst, sport);
 		if (IS_ERR(dst))
 			return PTR_ERR(dst);
 
@@ -1114,8 +1132,7 @@ static int geneve_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
 		return -EINVAL;
 	}
 
-	info->key.tp_src = udp_flow_src_port(geneve->net, skb,
-					     1, USHRT_MAX, true);
+	info->key.tp_src = sport;
 	info->key.tp_dst = geneve->cfg.info.key.tp_dst;
 	return 0;
 }
diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index 611722eafed8..c09fe18c6c52 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -1339,7 +1339,7 @@ static const struct nla_policy gtp_genl_policy[GTPA_MAX + 1] = {
 	[GTPA_O_TEI]		= { .type = NLA_U32, },
 };
 
-static const struct genl_ops gtp_genl_ops[] = {
+static const struct genl_small_ops gtp_genl_ops[] = {
 	{
 		.cmd = GTP_CMD_NEWPDP,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
@@ -1369,8 +1369,8 @@ static struct genl_family gtp_genl_family __ro_after_init = {
 	.policy = gtp_genl_policy,
 	.netnsok	= true,
 	.module		= THIS_MODULE,
-	.ops		= gtp_genl_ops,
-	.n_ops		= ARRAY_SIZE(gtp_genl_ops),
+	.small_ops	= gtp_genl_ops,
+	.n_small_ops	= ARRAY_SIZE(gtp_genl_ops),
 	.mcgrps		= gtp_genl_mcgrps,
 	.n_mcgrps	= ARRAY_SIZE(gtp_genl_mcgrps),
 };
diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index 2181d4538ab7..a0f338cf1424 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -847,6 +847,10 @@ struct nvsp_message {
 
 #define NETVSC_XDP_HDRM 256
 
+#define NETVSC_XFER_HEADER_SIZE(rng_cnt) \
+		(offsetof(struct vmtransfer_page_packet_header, ranges) + \
+		(rng_cnt) * sizeof(struct vmtransfer_page_range))
+
 struct multi_send_data {
 	struct sk_buff *skb; /* skb containing the pkt */
 	struct hv_netvsc_packet *pkt; /* netvsc pkt pending */
@@ -974,6 +978,9 @@ struct net_device_context {
 	/* Serial number of the VF to team with */
 	u32 vf_serial;
 
+	/* Is the current data path through the VF NIC? */
+	bool  data_path_is_vf;
+
 	/* Used to temporarily save the config info across hibernation */
 	struct netvsc_device_info *saved_netvsc_dev_info;
 };
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index 41f5cf0bb997..5a57d1985bae 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -388,6 +388,15 @@ static int netvsc_init_buf(struct hv_device *device,
 	net_device->recv_section_size = resp->sections[0].sub_alloc_size;
 	net_device->recv_section_cnt = resp->sections[0].num_sub_allocs;
 
+	/* Ensure buffer will not overflow */
+	if (net_device->recv_section_size < NETVSC_MTU_MIN || (u64)net_device->recv_section_size *
+	    (u64)net_device->recv_section_cnt > (u64)buf_size) {
+		netdev_err(ndev, "invalid recv_section_size %u\n",
+			   net_device->recv_section_size);
+		ret = -EINVAL;
+		goto cleanup;
+	}
+
 	/* Setup receive completion ring.
 	 * Add 1 to the recv_section_cnt because at least one entry in a
 	 * ring buffer has to be empty.
@@ -460,6 +469,12 @@ static int netvsc_init_buf(struct hv_device *device,
 	/* Parse the response */
 	net_device->send_section_size = init_packet->msg.
 				v1_msg.send_send_buf_complete.section_size;
+	if (net_device->send_section_size < NETVSC_MTU_MIN) {
+		netdev_err(ndev, "invalid send_section_size %u\n",
+			   net_device->send_section_size);
+		ret = -EINVAL;
+		goto cleanup;
+	}
 
 	/* Section count is simply the size divided by the section size. */
 	net_device->send_section_cnt = buf_size / net_device->send_section_size;
@@ -731,12 +746,49 @@ static void netvsc_send_completion(struct net_device *ndev,
 				   int budget)
 {
 	const struct nvsp_message *nvsp_packet = hv_pkt_data(desc);
+	u32 msglen = hv_pkt_datalen(desc);
+
+	/* Ensure packet is big enough to read header fields */
+	if (msglen < sizeof(struct nvsp_message_header)) {
+		netdev_err(ndev, "nvsp_message length too small: %u\n", msglen);
+		return;
+	}
 
 	switch (nvsp_packet->hdr.msg_type) {
 	case NVSP_MSG_TYPE_INIT_COMPLETE:
+		if (msglen < sizeof(struct nvsp_message_header) +
+				sizeof(struct nvsp_message_init_complete)) {
+			netdev_err(ndev, "nvsp_msg length too small: %u\n",
+				   msglen);
+			return;
+		}
+		fallthrough;
+
 	case NVSP_MSG1_TYPE_SEND_RECV_BUF_COMPLETE:
+		if (msglen < sizeof(struct nvsp_message_header) +
+				sizeof(struct nvsp_1_message_send_receive_buffer_complete)) {
+			netdev_err(ndev, "nvsp_msg1 length too small: %u\n",
+				   msglen);
+			return;
+		}
+		fallthrough;
+
 	case NVSP_MSG1_TYPE_SEND_SEND_BUF_COMPLETE:
+		if (msglen < sizeof(struct nvsp_message_header) +
+				sizeof(struct nvsp_1_message_send_send_buffer_complete)) {
+			netdev_err(ndev, "nvsp_msg1 length too small: %u\n",
+				   msglen);
+			return;
+		}
+		fallthrough;
+
 	case NVSP_MSG5_TYPE_SUBCHANNEL:
+		if (msglen < sizeof(struct nvsp_message_header) +
+				sizeof(struct nvsp_5_subchannel_complete)) {
+			netdev_err(ndev, "nvsp_msg5 length too small: %u\n",
+				   msglen);
+			return;
+		}
 		/* Copy the response back */
 		memcpy(&net_device->channel_init_pkt, nvsp_packet,
 		       sizeof(struct nvsp_message));
@@ -1117,19 +1169,28 @@ static void enq_receive_complete(struct net_device *ndev,
 static int netvsc_receive(struct net_device *ndev,
 			  struct netvsc_device *net_device,
 			  struct netvsc_channel *nvchan,
-			  const struct vmpacket_descriptor *desc,
-			  const struct nvsp_message *nvsp)
+			  const struct vmpacket_descriptor *desc)
 {
 	struct net_device_context *net_device_ctx = netdev_priv(ndev);
 	struct vmbus_channel *channel = nvchan->channel;
 	const struct vmtransfer_page_packet_header *vmxferpage_packet
 		= container_of(desc, const struct vmtransfer_page_packet_header, d);
+	const struct nvsp_message *nvsp = hv_pkt_data(desc);
+	u32 msglen = hv_pkt_datalen(desc);
 	u16 q_idx = channel->offermsg.offer.sub_channel_index;
 	char *recv_buf = net_device->recv_buf;
 	u32 status = NVSP_STAT_SUCCESS;
 	int i;
 	int count = 0;
 
+	/* Ensure packet is big enough to read header fields */
+	if (msglen < sizeof(struct nvsp_message_header)) {
+		netif_err(net_device_ctx, rx_err, ndev,
+			  "invalid nvsp header, length too small: %u\n",
+			  msglen);
+		return 0;
+	}
+
 	/* Make sure this is a valid nvsp packet */
 	if (unlikely(nvsp->hdr.msg_type != NVSP_MSG1_TYPE_SEND_RNDIS_PKT)) {
 		netif_err(net_device_ctx, rx_err, ndev,
@@ -1138,6 +1199,14 @@ static int netvsc_receive(struct net_device *ndev,
 		return 0;
 	}
 
+	/* Validate xfer page pkt header */
+	if ((desc->offset8 << 3) < sizeof(struct vmtransfer_page_packet_header)) {
+		netif_err(net_device_ctx, rx_err, ndev,
+			  "Invalid xfer page pkt, offset too small: %u\n",
+			  desc->offset8 << 3);
+		return 0;
+	}
+
 	if (unlikely(vmxferpage_packet->xfer_pageset_id != NETVSC_RECEIVE_BUFFER_ID)) {
 		netif_err(net_device_ctx, rx_err, ndev,
 			  "Invalid xfer page set id - expecting %x got %x\n",
@@ -1148,6 +1217,14 @@ static int netvsc_receive(struct net_device *ndev,
 
 	count = vmxferpage_packet->range_cnt;
 
+	/* Check count for a valid value */
+	if (NETVSC_XFER_HEADER_SIZE(count) > desc->offset8 << 3) {
+		netif_err(net_device_ctx, rx_err, ndev,
+			  "Range count is not valid: %d\n",
+			  count);
+		return 0;
+	}
+
 	/* Each range represents 1 RNDIS pkt that contains 1 ethernet frame */
 	for (i = 0; i < count; i++) {
 		u32 offset = vmxferpage_packet->ranges[i].byte_offset;
@@ -1155,7 +1232,8 @@ static int netvsc_receive(struct net_device *ndev,
 		void *data;
 		int ret;
 
-		if (unlikely(offset + buflen > net_device->recv_buf_size)) {
+		if (unlikely(offset > net_device->recv_buf_size ||
+			     buflen > net_device->recv_buf_size - offset)) {
 			nvchan->rsc.cnt = 0;
 			status = NVSP_STAT_FAIL;
 			netif_err(net_device_ctx, rx_err, ndev,
@@ -1194,6 +1272,13 @@ static void netvsc_send_table(struct net_device *ndev,
 	u32 count, offset, *tab;
 	int i;
 
+	/* Ensure packet is big enough to read send_table fields */
+	if (msglen < sizeof(struct nvsp_message_header) +
+		     sizeof(struct nvsp_5_send_indirect_table)) {
+		netdev_err(ndev, "nvsp_v5_msg length too small: %u\n", msglen);
+		return;
+	}
+
 	count = nvmsg->msg.v5_msg.send_table.count;
 	offset = nvmsg->msg.v5_msg.send_table.offset;
 
@@ -1225,10 +1310,18 @@ static void netvsc_send_table(struct net_device *ndev,
 }
 
 static void netvsc_send_vf(struct net_device *ndev,
-			   const struct nvsp_message *nvmsg)
+			   const struct nvsp_message *nvmsg,
+			   u32 msglen)
 {
 	struct net_device_context *net_device_ctx = netdev_priv(ndev);
 
+	/* Ensure packet is big enough to read its fields */
+	if (msglen < sizeof(struct nvsp_message_header) +
+		     sizeof(struct nvsp_4_send_vf_association)) {
+		netdev_err(ndev, "nvsp_v4_msg length too small: %u\n", msglen);
+		return;
+	}
+
 	net_device_ctx->vf_alloc = nvmsg->msg.v4_msg.vf_assoc.allocated;
 	net_device_ctx->vf_serial = nvmsg->msg.v4_msg.vf_assoc.serial;
 	netdev_info(ndev, "VF slot %u %s\n",
@@ -1238,16 +1331,24 @@ static void netvsc_send_vf(struct net_device *ndev,
 
 static void netvsc_receive_inband(struct net_device *ndev,
 				  struct netvsc_device *nvscdev,
-				  const struct nvsp_message *nvmsg,
-				  u32 msglen)
+				  const struct vmpacket_descriptor *desc)
 {
+	const struct nvsp_message *nvmsg = hv_pkt_data(desc);
+	u32 msglen = hv_pkt_datalen(desc);
+
+	/* Ensure packet is big enough to read header fields */
+	if (msglen < sizeof(struct nvsp_message_header)) {
+		netdev_err(ndev, "inband nvsp_message length too small: %u\n", msglen);
+		return;
+	}
+
 	switch (nvmsg->hdr.msg_type) {
 	case NVSP_MSG5_TYPE_SEND_INDIRECTION_TABLE:
 		netvsc_send_table(ndev, nvscdev, nvmsg, msglen);
 		break;
 
 	case NVSP_MSG4_TYPE_SEND_VF_ASSOCIATION:
-		netvsc_send_vf(ndev, nvmsg);
+		netvsc_send_vf(ndev, nvmsg, msglen);
 		break;
 	}
 }
@@ -1261,23 +1362,20 @@ static int netvsc_process_raw_pkt(struct hv_device *device,
 {
 	struct vmbus_channel *channel = nvchan->channel;
 	const struct nvsp_message *nvmsg = hv_pkt_data(desc);
-	u32 msglen = hv_pkt_datalen(desc);
 
 	trace_nvsp_recv(ndev, channel, nvmsg);
 
 	switch (desc->type) {
 	case VM_PKT_COMP:
-		netvsc_send_completion(ndev, net_device, channel,
-				       desc, budget);
+		netvsc_send_completion(ndev, net_device, channel, desc, budget);
 		break;
 
 	case VM_PKT_DATA_USING_XFER_PAGES:
-		return netvsc_receive(ndev, net_device, nvchan,
-				      desc, nvmsg);
+		return netvsc_receive(ndev, net_device, nvchan, desc);
 		break;
 
 	case VM_PKT_DATA_INBAND:
-		netvsc_receive_inband(ndev, net_device, nvmsg, msglen);
+		netvsc_receive_inband(ndev, net_device, desc);
 		break;
 
 	default:
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 64b0a74c1523..9869e390875e 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -748,6 +748,13 @@ void netvsc_linkstatus_callback(struct net_device *net,
 	struct netvsc_reconfig *event;
 	unsigned long flags;
 
+	/* Ensure the packet is big enough to access its fields */
+	if (resp->msg_len - RNDIS_HEADER_SIZE < sizeof(struct rndis_indicate_status)) {
+		netdev_err(net, "invalid rndis_indicate_status packet, len: %u\n",
+			   resp->msg_len);
+		return;
+	}
+
 	/* Update the physical link speed when changing to another vSwitch */
 	if (indicate->status == RNDIS_STATUS_LINK_SPEED_CHANGE) {
 		u32 speed;
@@ -2366,7 +2373,16 @@ static int netvsc_register_vf(struct net_device *vf_netdev)
 	return NOTIFY_OK;
 }
 
-/* VF up/down change detected, schedule to change data path */
+/* Change the data path when VF UP/DOWN/CHANGE are detected.
+ *
+ * Typically a UP or DOWN event is followed by a CHANGE event, so
+ * net_device_ctx->data_path_is_vf is used to cache the current data path
+ * to avoid the duplicate call of netvsc_switch_datapath() and the duplicate
+ * message.
+ *
+ * During hibernation, if a VF NIC driver (e.g. mlx5) preserves the network
+ * interface, there is only the CHANGE event and no UP or DOWN event.
+ */
 static int netvsc_vf_changed(struct net_device *vf_netdev)
 {
 	struct net_device_context *net_device_ctx;
@@ -2383,6 +2399,10 @@ static int netvsc_vf_changed(struct net_device *vf_netdev)
 	if (!netvsc_dev)
 		return NOTIFY_DONE;
 
+	if (net_device_ctx->data_path_is_vf == vf_is_up)
+		return NOTIFY_OK;
+	net_device_ctx->data_path_is_vf = vf_is_up;
+
 	netvsc_switch_datapath(ndev, vf_is_up);
 	netdev_info(ndev, "Data path switched %s VF: %s\n",
 		    vf_is_up ? "to" : "from", vf_netdev->name);
@@ -2587,8 +2607,8 @@ static int netvsc_remove(struct hv_device *dev)
 static int netvsc_suspend(struct hv_device *dev)
 {
 	struct net_device_context *ndev_ctx;
-	struct net_device *vf_netdev, *net;
 	struct netvsc_device *nvdev;
+	struct net_device *net;
 	int ret;
 
 	net = hv_get_drvdata(dev);
@@ -2604,10 +2624,6 @@ static int netvsc_suspend(struct hv_device *dev)
 		goto out;
 	}
 
-	vf_netdev = rtnl_dereference(ndev_ctx->vf_netdev);
-	if (vf_netdev)
-		netvsc_unregister_vf(vf_netdev);
-
 	/* Save the current config info */
 	ndev_ctx->saved_netvsc_dev_info = netvsc_devinfo_get(nvdev);
 
@@ -2628,6 +2644,12 @@ static int netvsc_resume(struct hv_device *dev)
 	rtnl_lock();
 
 	net_device_ctx = netdev_priv(net);
+
+	/* Reset the data path to the netvsc NIC before re-opening the vmbus
+	 * channel. Later netvsc_netdev_event() will switch the data path to
+	 * the VF upon the UP or CHANGE event.
+	 */
+	net_device_ctx->data_path_is_vf = false;
 	device_info = net_device_ctx->saved_netvsc_dev_info;
 
 	ret = netvsc_attach(net, device_info);
@@ -2695,6 +2717,7 @@ static int netvsc_netdev_event(struct notifier_block *this,
 		return netvsc_unregister_vf(event_dev);
 	case NETDEV_UP:
 	case NETDEV_DOWN:
+	case NETDEV_CHANGE:
 		return netvsc_vf_changed(event_dev);
 	default:
 		return NOTIFY_DONE;
diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c
index b81ceba38218..12ad471ac5e1 100644
--- a/drivers/net/hyperv/rndis_filter.c
+++ b/drivers/net/hyperv/rndis_filter.c
@@ -275,6 +275,16 @@ static void rndis_filter_receive_response(struct net_device *ndev,
 		return;
 	}
 
+	/* Ensure the packet is big enough to read req_id. Req_id is the 1st
+	 * field in any request/response message, so the payload should have at
+	 * least sizeof(u32) bytes
+	 */
+	if (resp->msg_len - RNDIS_HEADER_SIZE < sizeof(u32)) {
+		netdev_err(ndev, "rndis msg_len too small: %u\n",
+			   resp->msg_len);
+		return;
+	}
+
 	spin_lock_irqsave(&dev->request_lock, flags);
 	list_for_each_entry(request, &dev->req_list, list_ent) {
 		/*
@@ -331,8 +341,9 @@ static void rndis_filter_receive_response(struct net_device *ndev,
  * Get the Per-Packet-Info with the specified type
  * return NULL if not found.
  */
-static inline void *rndis_get_ppi(struct rndis_packet *rpkt,
-				  u32 type, u8 internal)
+static inline void *rndis_get_ppi(struct net_device *ndev,
+				  struct rndis_packet *rpkt,
+				  u32 rpkt_len, u32 type, u8 internal)
 {
 	struct rndis_per_packet_info *ppi;
 	int len;
@@ -340,11 +351,36 @@ static inline void *rndis_get_ppi(struct rndis_packet *rpkt,
 	if (rpkt->per_pkt_info_offset == 0)
 		return NULL;
 
+	/* Validate info_offset and info_len */
+	if (rpkt->per_pkt_info_offset < sizeof(struct rndis_packet) ||
+	    rpkt->per_pkt_info_offset > rpkt_len) {
+		netdev_err(ndev, "Invalid per_pkt_info_offset: %u\n",
+			   rpkt->per_pkt_info_offset);
+		return NULL;
+	}
+
+	if (rpkt->per_pkt_info_len > rpkt_len - rpkt->per_pkt_info_offset) {
+		netdev_err(ndev, "Invalid per_pkt_info_len: %u\n",
+			   rpkt->per_pkt_info_len);
+		return NULL;
+	}
+
 	ppi = (struct rndis_per_packet_info *)((ulong)rpkt +
 		rpkt->per_pkt_info_offset);
 	len = rpkt->per_pkt_info_len;
 
 	while (len > 0) {
+		/* Validate ppi_offset and ppi_size */
+		if (ppi->size > len) {
+			netdev_err(ndev, "Invalid ppi size: %u\n", ppi->size);
+			continue;
+		}
+
+		if (ppi->ppi_offset >= ppi->size) {
+			netdev_err(ndev, "Invalid ppi_offset: %u\n", ppi->ppi_offset);
+			continue;
+		}
+
 		if (ppi->type == type && ppi->internal == internal)
 			return (void *)((ulong)ppi + ppi->ppi_offset);
 		len -= ppi->size;
@@ -388,14 +424,29 @@ static int rndis_filter_receive_data(struct net_device *ndev,
 	const struct ndis_pkt_8021q_info *vlan;
 	const struct rndis_pktinfo_id *pktinfo_id;
 	const u32 *hash_info;
-	u32 data_offset;
+	u32 data_offset, rpkt_len;
 	void *data;
 	bool rsc_more = false;
 	int ret;
 
+	/* Ensure data_buflen is big enough to read header fields */
+	if (data_buflen < RNDIS_HEADER_SIZE + sizeof(struct rndis_packet)) {
+		netdev_err(ndev, "invalid rndis pkt, data_buflen too small: %u\n",
+			   data_buflen);
+		return NVSP_STAT_FAIL;
+	}
+
+	/* Validate rndis_pkt offset */
+	if (rndis_pkt->data_offset >= data_buflen - RNDIS_HEADER_SIZE) {
+		netdev_err(ndev, "invalid rndis packet offset: %u\n",
+			   rndis_pkt->data_offset);
+		return NVSP_STAT_FAIL;
+	}
+
 	/* Remove the rndis header and pass it back up the stack */
 	data_offset = RNDIS_HEADER_SIZE + rndis_pkt->data_offset;
 
+	rpkt_len = data_buflen - RNDIS_HEADER_SIZE;
 	data_buflen -= data_offset;
 
 	/*
@@ -410,13 +461,13 @@ static int rndis_filter_receive_data(struct net_device *ndev,
 		return NVSP_STAT_FAIL;
 	}
 
-	vlan = rndis_get_ppi(rndis_pkt, IEEE_8021Q_INFO, 0);
+	vlan = rndis_get_ppi(ndev, rndis_pkt, rpkt_len, IEEE_8021Q_INFO, 0);
 
-	csum_info = rndis_get_ppi(rndis_pkt, TCPIP_CHKSUM_PKTINFO, 0);
+	csum_info = rndis_get_ppi(ndev, rndis_pkt, rpkt_len, TCPIP_CHKSUM_PKTINFO, 0);
 
-	hash_info = rndis_get_ppi(rndis_pkt, NBL_HASH_VALUE, 0);
+	hash_info = rndis_get_ppi(ndev, rndis_pkt, rpkt_len, NBL_HASH_VALUE, 0);
 
-	pktinfo_id = rndis_get_ppi(rndis_pkt, RNDIS_PKTINFO_ID, 1);
+	pktinfo_id = rndis_get_ppi(ndev, rndis_pkt, rpkt_len, RNDIS_PKTINFO_ID, 1);
 
 	data = (void *)msg + data_offset;
 
@@ -474,6 +525,14 @@ int rndis_filter_receive(struct net_device *ndev,
 	if (netif_msg_rx_status(net_device_ctx))
 		dump_rndis_message(ndev, rndis_msg);
 
+	/* Validate incoming rndis_message packet */
+	if (buflen < RNDIS_HEADER_SIZE || rndis_msg->msg_len < RNDIS_HEADER_SIZE ||
+	    buflen < rndis_msg->msg_len) {
+		netdev_err(ndev, "Invalid rndis_msg (buflen: %u, msg_len: %u)\n",
+			   buflen, rndis_msg->msg_len);
+		return NVSP_STAT_FAIL;
+	}
+
 	switch (rndis_msg->ndis_msg_type) {
 	case RNDIS_MSG_PACKET:
 		return rndis_filter_receive_data(ndev, net_dev, nvchan,
diff --git a/drivers/net/ieee802154/adf7242.c b/drivers/net/ieee802154/adf7242.c
index c11f32f644db..7db9cbd0f5de 100644
--- a/drivers/net/ieee802154/adf7242.c
+++ b/drivers/net/ieee802154/adf7242.c
@@ -882,7 +882,9 @@ static int adf7242_rx(struct adf7242_local *lp)
 	int ret;
 	u8 lqi, len_u8, *data;
 
-	adf7242_read_reg(lp, 0, &len_u8);
+	ret = adf7242_read_reg(lp, 0, &len_u8);
+	if (ret)
+		return ret;
 
 	len = len_u8;
 
diff --git a/drivers/net/ieee802154/ca8210.c b/drivers/net/ieee802154/ca8210.c
index e04c3b60cae7..4eb64709d44c 100644
--- a/drivers/net/ieee802154/ca8210.c
+++ b/drivers/net/ieee802154/ca8210.c
@@ -2925,6 +2925,7 @@ static int ca8210_dev_com_init(struct ca8210_priv *priv)
 	);
 	if (!priv->irq_workqueue) {
 		dev_crit(&priv->spi->dev, "alloc of irq_workqueue failed!\n");
+		destroy_workqueue(priv->mlme_workqueue);
 		return -ENOMEM;
 	}
 
diff --git a/drivers/net/ieee802154/mac802154_hwsim.c b/drivers/net/ieee802154/mac802154_hwsim.c
index c20e7ef18bc9..c0bf7d78276e 100644
--- a/drivers/net/ieee802154/mac802154_hwsim.c
+++ b/drivers/net/ieee802154/mac802154_hwsim.c
@@ -583,7 +583,7 @@ static const struct nla_policy hwsim_genl_policy[MAC802154_HWSIM_ATTR_MAX + 1] =
 };
 
 /* Generic Netlink operations array */
-static const struct genl_ops hwsim_nl_ops[] = {
+static const struct genl_small_ops hwsim_nl_ops[] = {
 	{
 		.cmd = MAC802154_HWSIM_CMD_NEW_RADIO,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
@@ -628,8 +628,8 @@ static struct genl_family hwsim_genl_family __ro_after_init = {
 	.maxattr = MAC802154_HWSIM_ATTR_MAX,
 	.policy = hwsim_genl_policy,
 	.module = THIS_MODULE,
-	.ops = hwsim_nl_ops,
-	.n_ops = ARRAY_SIZE(hwsim_nl_ops),
+	.small_ops = hwsim_nl_ops,
+	.n_small_ops = ARRAY_SIZE(hwsim_nl_ops),
 	.mcgrps = hwsim_mcgrps,
 	.n_mcgrps = ARRAY_SIZE(hwsim_mcgrps),
 };
diff --git a/drivers/net/ipa/gsi.c b/drivers/net/ipa/gsi.c
index cb75f7d54057..6bfac1efe037 100644
--- a/drivers/net/ipa/gsi.c
+++ b/drivers/net/ipa/gsi.c
@@ -254,8 +254,8 @@ static void gsi_irq_enable(struct gsi *gsi)
 
 	/* We don't use inter-EE channel or event interrupts */
 	val = GSI_CNTXT_TYPE_IRQ_MSK_ALL;
-	val &= ~MSK_INTER_EE_CH_CTRL_FMASK;
-	val &= ~MSK_INTER_EE_EV_CTRL_FMASK;
+	val &= ~INTER_EE_CH_CTRL_FMASK;
+	val &= ~INTER_EE_EV_CTRL_FMASK;
 	iowrite32(val, gsi->virt + GSI_CNTXT_TYPE_IRQ_MSK_OFFSET);
 
 	val = GENMASK(gsi->channel_count - 1, 0);
@@ -271,7 +271,7 @@ static void gsi_irq_enable(struct gsi *gsi)
 	iowrite32(val, gsi->virt + GSI_CNTXT_GLOB_IRQ_EN_OFFSET);
 
 	/* Never enable GSI_BREAK_POINT */
-	val = GSI_CNTXT_GSI_IRQ_ALL & ~EN_BREAK_POINT_FMASK;
+	val = GSI_CNTXT_GSI_IRQ_ALL & ~BREAK_POINT_FMASK;
 	iowrite32(val, gsi->virt + GSI_CNTXT_GSI_IRQ_EN_OFFSET);
 }
 
@@ -1074,8 +1074,8 @@ static void gsi_isr_glob_ee(struct gsi *gsi)
 
 	val &= ~ERROR_INT_FMASK;
 
-	if (val & EN_GP_INT1_FMASK) {
-		val ^= EN_GP_INT1_FMASK;
+	if (val & GP_INT1_FMASK) {
+		val ^= GP_INT1_FMASK;
 		gsi_isr_gp_int1(gsi);
 	}
 
@@ -1600,7 +1600,7 @@ err_unwind_modem:
 	/* Compute which modem channels need to be deallocated */
 	mask ^= gsi->modem_channel_bitmap;
 	while (mask) {
-		u32 channel_id = __fls(mask);
+		channel_id = __fls(mask);
 
 		mask ^= BIT(channel_id);
 
@@ -1628,7 +1628,7 @@ static void gsi_channel_teardown(struct gsi *gsi)
 	mutex_lock(&gsi->mutex);
 
 	while (mask) {
-		u32 channel_id = __fls(mask);
+		channel_id = __fls(mask);
 
 		mask ^= BIT(channel_id);
 
@@ -1972,7 +1972,6 @@ int gsi_init(struct gsi *gsi, struct platform_device *pdev, bool prefetch,
 	 */
 	init_dummy_netdev(&gsi->dummy_dev);
 
-	/* Get the GSI IRQ and request for it to wake the system */
 	ret = platform_get_irq_byname(pdev, "gsi");
 	if (ret <= 0) {
 		dev_err(dev, "DT error %d getting \"gsi\" IRQ property\n", ret);
diff --git a/drivers/net/ipa/gsi_reg.h b/drivers/net/ipa/gsi_reg.h
index acc9e744c67d..8e0e9350c383 100644
--- a/drivers/net/ipa/gsi_reg.h
+++ b/drivers/net/ipa/gsi_reg.h
@@ -258,6 +258,11 @@
 			GSI_EE_N_CNTXT_TYPE_IRQ_OFFSET(GSI_EE_AP)
 #define GSI_EE_N_CNTXT_TYPE_IRQ_OFFSET(ee) \
 			(0x0001f080 + 0x4000 * (ee))
+#define GSI_CNTXT_TYPE_IRQ_MSK_OFFSET \
+			GSI_EE_N_CNTXT_TYPE_IRQ_MSK_OFFSET(GSI_EE_AP)
+#define GSI_EE_N_CNTXT_TYPE_IRQ_MSK_OFFSET(ee) \
+			(0x0001f088 + 0x4000 * (ee))
+/* The masks below are used for the TYPE_IRQ and TYPE_IRQ_MASK registers */
 #define CH_CTRL_FMASK			GENMASK(0, 0)
 #define EV_CTRL_FMASK			GENMASK(1, 1)
 #define GLOB_EE_FMASK			GENMASK(2, 2)
@@ -265,18 +270,6 @@
 #define INTER_EE_CH_CTRL_FMASK		GENMASK(4, 4)
 #define INTER_EE_EV_CTRL_FMASK		GENMASK(5, 5)
 #define GENERAL_FMASK			GENMASK(6, 6)
-
-#define GSI_CNTXT_TYPE_IRQ_MSK_OFFSET \
-			GSI_EE_N_CNTXT_TYPE_IRQ_MSK_OFFSET(GSI_EE_AP)
-#define GSI_EE_N_CNTXT_TYPE_IRQ_MSK_OFFSET(ee) \
-			(0x0001f088 + 0x4000 * (ee))
-#define MSK_CH_CTRL_FMASK		GENMASK(0, 0)
-#define MSK_EV_CTRL_FMASK		GENMASK(1, 1)
-#define MSK_GLOB_EE_FMASK		GENMASK(2, 2)
-#define MSK_IEOB_FMASK			GENMASK(3, 3)
-#define MSK_INTER_EE_CH_CTRL_FMASK	GENMASK(4, 4)
-#define MSK_INTER_EE_EV_CTRL_FMASK	GENMASK(5, 5)
-#define MSK_GENERAL_FMASK		GENMASK(6, 6)
 #define GSI_CNTXT_TYPE_IRQ_MSK_ALL	GENMASK(6, 0)
 
 #define GSI_CNTXT_SRC_CH_IRQ_OFFSET \
@@ -328,57 +321,39 @@
 			GSI_EE_N_CNTXT_GLOB_IRQ_STTS_OFFSET(GSI_EE_AP)
 #define GSI_EE_N_CNTXT_GLOB_IRQ_STTS_OFFSET(ee) \
 			(0x0001f100 + 0x4000 * (ee))
-#define ERROR_INT_FMASK			GENMASK(0, 0)
-#define GP_INT1_FMASK			GENMASK(1, 1)
-#define GP_INT2_FMASK			GENMASK(2, 2)
-#define GP_INT3_FMASK			GENMASK(3, 3)
-
 #define GSI_CNTXT_GLOB_IRQ_EN_OFFSET \
 			GSI_EE_N_CNTXT_GLOB_IRQ_EN_OFFSET(GSI_EE_AP)
 #define GSI_EE_N_CNTXT_GLOB_IRQ_EN_OFFSET(ee) \
 			(0x0001f108 + 0x4000 * (ee))
-#define EN_ERROR_INT_FMASK		GENMASK(0, 0)
-#define EN_GP_INT1_FMASK		GENMASK(1, 1)
-#define EN_GP_INT2_FMASK		GENMASK(2, 2)
-#define EN_GP_INT3_FMASK		GENMASK(3, 3)
-#define GSI_CNTXT_GLOB_IRQ_ALL		GENMASK(3, 0)
-
 #define GSI_CNTXT_GLOB_IRQ_CLR_OFFSET \
 			GSI_EE_N_CNTXT_GLOB_IRQ_CLR_OFFSET(GSI_EE_AP)
 #define GSI_EE_N_CNTXT_GLOB_IRQ_CLR_OFFSET(ee) \
 			(0x0001f110 + 0x4000 * (ee))
-#define CLR_ERROR_INT_FMASK		GENMASK(0, 0)
-#define CLR_GP_INT1_FMASK		GENMASK(1, 1)
-#define CLR_GP_INT2_FMASK		GENMASK(2, 2)
-#define CLR_GP_INT3_FMASK		GENMASK(3, 3)
+/* The masks below are used for the general IRQ STTS, EN, and CLR registers */
+#define ERROR_INT_FMASK			GENMASK(0, 0)
+#define GP_INT1_FMASK			GENMASK(1, 1)
+#define GP_INT2_FMASK			GENMASK(2, 2)
+#define GP_INT3_FMASK			GENMASK(3, 3)
+#define GSI_CNTXT_GLOB_IRQ_ALL		GENMASK(3, 0)
 
 #define GSI_CNTXT_GSI_IRQ_STTS_OFFSET \
 			GSI_EE_N_CNTXT_GSI_IRQ_STTS_OFFSET(GSI_EE_AP)
 #define GSI_EE_N_CNTXT_GSI_IRQ_STTS_OFFSET(ee) \
 			(0x0001f118 + 0x4000 * (ee))
-#define BREAK_POINT_FMASK		GENMASK(0, 0)
-#define BUS_ERROR_FMASK			GENMASK(1, 1)
-#define CMD_FIFO_OVRFLOW_FMASK		GENMASK(2, 2)
-#define MCS_STACK_OVRFLOW_FMASK		GENMASK(3, 3)
-
 #define GSI_CNTXT_GSI_IRQ_EN_OFFSET \
 			GSI_EE_N_CNTXT_GSI_IRQ_EN_OFFSET(GSI_EE_AP)
 #define GSI_EE_N_CNTXT_GSI_IRQ_EN_OFFSET(ee) \
 			(0x0001f120 + 0x4000 * (ee))
-#define EN_BREAK_POINT_FMASK		GENMASK(0, 0)
-#define EN_BUS_ERROR_FMASK		GENMASK(1, 1)
-#define EN_CMD_FIFO_OVRFLOW_FMASK	GENMASK(2, 2)
-#define EN_MCS_STACK_OVRFLOW_FMASK	GENMASK(3, 3)
-#define GSI_CNTXT_GSI_IRQ_ALL		GENMASK(3, 0)
-
 #define GSI_CNTXT_GSI_IRQ_CLR_OFFSET \
 			GSI_EE_N_CNTXT_GSI_IRQ_CLR_OFFSET(GSI_EE_AP)
 #define GSI_EE_N_CNTXT_GSI_IRQ_CLR_OFFSET(ee) \
 			(0x0001f128 + 0x4000 * (ee))
-#define CLR_BREAK_POINT_FMASK		GENMASK(0, 0)
-#define CLR_BUS_ERROR_FMASK		GENMASK(1, 1)
-#define CLR_CMD_FIFO_OVRFLOW_FMASK	GENMASK(2, 2)
-#define CLR_MCS_STACK_OVRFLOW_FMASK	GENMASK(3, 3)
+/* The masks below are used for the general IRQ STTS, EN, and CLR registers */
+#define BREAK_POINT_FMASK		GENMASK(0, 0)
+#define BUS_ERROR_FMASK			GENMASK(1, 1)
+#define CMD_FIFO_OVRFLOW_FMASK		GENMASK(2, 2)
+#define MCS_STACK_OVRFLOW_FMASK		GENMASK(3, 3)
+#define GSI_CNTXT_GSI_IRQ_ALL		GENMASK(3, 0)
 
 #define GSI_CNTXT_INTSET_OFFSET \
 			GSI_EE_N_CNTXT_INTSET_OFFSET(GSI_EE_AP)
diff --git a/drivers/net/ipa/gsi_trans.c b/drivers/net/ipa/gsi_trans.c
index bdbfeed359db..43f5f5d93cb0 100644
--- a/drivers/net/ipa/gsi_trans.c
+++ b/drivers/net/ipa/gsi_trans.c
@@ -81,7 +81,6 @@ struct gsi_tre {
 
 /* gsi_tre->flags mask values (in CPU byte order) */
 #define TRE_FLAGS_CHAIN_FMASK	GENMASK(0, 0)
-#define TRE_FLAGS_IEOB_FMASK	GENMASK(8, 8)
 #define TRE_FLAGS_IEOT_FMASK	GENMASK(9, 9)
 #define TRE_FLAGS_BEI_FMASK	GENMASK(10, 10)
 #define TRE_FLAGS_TYPE_FMASK	GENMASK(23, 16)
diff --git a/drivers/net/ipa/ipa_endpoint.c b/drivers/net/ipa/ipa_endpoint.c
index b7efd7c95e9c..24d688e3cd93 100644
--- a/drivers/net/ipa/ipa_endpoint.c
+++ b/drivers/net/ipa/ipa_endpoint.c
@@ -42,11 +42,8 @@
 /** enum ipa_status_opcode - status element opcode hardware values */
 enum ipa_status_opcode {
 	IPA_STATUS_OPCODE_PACKET		= 0x01,
-	IPA_STATUS_OPCODE_NEW_FRAG_RULE		= 0x02,
 	IPA_STATUS_OPCODE_DROPPED_PACKET	= 0x04,
 	IPA_STATUS_OPCODE_SUSPENDED_PACKET	= 0x08,
-	IPA_STATUS_OPCODE_LOG			= 0x10,
-	IPA_STATUS_OPCODE_DCMP			= 0x20,
 	IPA_STATUS_OPCODE_PACKET_2ND_PASS	= 0x40,
 };
 
@@ -54,13 +51,6 @@ enum ipa_status_opcode {
 enum ipa_status_exception {
 	/* 0 means no exception */
 	IPA_STATUS_EXCEPTION_DEAGGR		= 0x01,
-	IPA_STATUS_EXCEPTION_IPTYPE		= 0x04,
-	IPA_STATUS_EXCEPTION_PACKET_LENGTH	= 0x08,
-	IPA_STATUS_EXCEPTION_FRAG_RULE_MISS	= 0x10,
-	IPA_STATUS_EXCEPTION_SW_FILT		= 0x20,
-	/* The meaning of the next value depends on whether the IP version */
-	IPA_STATUS_EXCEPTION_NAT		= 0x40,		/* IPv4 */
-	IPA_STATUS_EXCEPTION_IPV6CT		= IPA_STATUS_EXCEPTION_NAT,
 };
 
 /* Status element provided by hardware */
@@ -79,36 +69,9 @@ struct ipa_status {
 };
 
 /* Field masks for struct ipa_status structure fields */
-
-#define IPA_STATUS_SRC_IDX_FMASK		GENMASK(4, 0)
-
 #define IPA_STATUS_DST_IDX_FMASK		GENMASK(4, 0)
-
-#define IPA_STATUS_FLAGS1_FLT_LOCAL_FMASK	GENMASK(0, 0)
-#define IPA_STATUS_FLAGS1_FLT_HASH_FMASK	GENMASK(1, 1)
-#define IPA_STATUS_FLAGS1_FLT_GLOBAL_FMASK	GENMASK(2, 2)
-#define IPA_STATUS_FLAGS1_FLT_RET_HDR_FMASK	GENMASK(3, 3)
-#define IPA_STATUS_FLAGS1_FLT_RULE_ID_FMASK	GENMASK(13, 4)
-#define IPA_STATUS_FLAGS1_RT_LOCAL_FMASK	GENMASK(14, 14)
-#define IPA_STATUS_FLAGS1_RT_HASH_FMASK		GENMASK(15, 15)
-#define IPA_STATUS_FLAGS1_UCP_FMASK		GENMASK(16, 16)
-#define IPA_STATUS_FLAGS1_RT_TBL_IDX_FMASK	GENMASK(21, 17)
 #define IPA_STATUS_FLAGS1_RT_RULE_ID_FMASK	GENMASK(31, 22)
 
-#define IPA_STATUS_FLAGS2_NAT_HIT_FMASK		GENMASK_ULL(0, 0)
-#define IPA_STATUS_FLAGS2_NAT_ENTRY_IDX_FMASK	GENMASK_ULL(13, 1)
-#define IPA_STATUS_FLAGS2_NAT_TYPE_FMASK	GENMASK_ULL(15, 14)
-#define IPA_STATUS_FLAGS2_TAG_INFO_FMASK	GENMASK_ULL(63, 16)
-
-#define IPA_STATUS_FLAGS3_SEQ_NUM_FMASK		GENMASK(7, 0)
-#define IPA_STATUS_FLAGS3_TOD_CTR_FMASK		GENMASK(31, 8)
-
-#define IPA_STATUS_FLAGS4_HDR_LOCAL_FMASK	GENMASK(0, 0)
-#define IPA_STATUS_FLAGS4_HDR_OFFSET_FMASK	GENMASK(10, 1)
-#define IPA_STATUS_FLAGS4_FRAG_HIT_FMASK	GENMASK(11, 11)
-#define IPA_STATUS_FLAGS4_FRAG_RULE_FMASK	GENMASK(15, 12)
-#define IPA_STATUS_FLAGS4_HW_SPECIFIC_FMASK	GENMASK(31, 16)
-
 #ifdef IPA_VALIDATE
 
 static void ipa_endpoint_validate_build(void)
@@ -1048,8 +1011,7 @@ static bool ipa_endpoint_skb_build(struct ipa_endpoint *endpoint,
 }
 
 /* The format of a packet status element is the same for several status
- * types (opcodes).  The NEW_FRAG_RULE, LOG, DCMP (decompression) types
- * aren't currently supported
+ * types (opcodes).  Other types aren't currently supported.
  */
 static bool ipa_status_format_packet(enum ipa_status_opcode opcode)
 {
@@ -1086,7 +1048,7 @@ static bool ipa_status_drop_packet(const struct ipa_status *status)
 {
 	u32 val;
 
-	/* Deaggregation exceptions we drop; others we consume */
+	/* Deaggregation exceptions we drop; all other types we consume */
 	if (status->exception)
 		return status->exception == IPA_STATUS_EXCEPTION_DEAGGR;
 
@@ -1432,11 +1394,10 @@ void ipa_endpoint_suspend_one(struct ipa_endpoint *endpoint)
 	if (!(endpoint->ipa->enabled & BIT(endpoint->endpoint_id)))
 		return;
 
-	if (!endpoint->toward_ipa)
+	if (!endpoint->toward_ipa) {
 		ipa_endpoint_replenish_disable(endpoint);
-
-	if (!endpoint->toward_ipa)
 		(void)ipa_endpoint_program_suspend(endpoint, true);
+	}
 
 	/* IPA v3.5.1 doesn't use channel stop for suspend */
 	stop_channel = endpoint->ipa->version != IPA_VERSION_3_5_1;
diff --git a/drivers/net/ipa/ipa_main.c b/drivers/net/ipa/ipa_main.c
index 1044758b501d..cd4d993b0bbb 100644
--- a/drivers/net/ipa/ipa_main.c
+++ b/drivers/net/ipa/ipa_main.c
@@ -723,8 +723,8 @@ static int ipa_probe(struct platform_device *pdev)
 	bool modem_alloc;
 	bool modem_init;
 	struct ipa *ipa;
-	phandle phandle;
 	bool prefetch;
+	phandle ph;
 	int ret;
 
 	ipa_validate_build();
@@ -736,13 +736,13 @@ static int ipa_probe(struct platform_device *pdev)
 			return -EPROBE_DEFER;
 
 	/* We rely on remoteproc to tell us about modem state changes */
-	phandle = of_property_read_phandle(dev->of_node, "modem-remoteproc");
-	if (!phandle) {
+	ph = of_property_read_phandle(dev->of_node, "modem-remoteproc");
+	if (!ph) {
 		dev_err(dev, "DT missing \"modem-remoteproc\" property\n");
 		return -EINVAL;
 	}
 
-	rproc = rproc_get_by_phandle(phandle);
+	rproc = rproc_get_by_phandle(ph);
 	if (!rproc)
 		return -EPROBE_DEFER;
 
diff --git a/drivers/net/ipa/ipa_reg.h b/drivers/net/ipa/ipa_reg.h
index eb4e39fa7d4b..e542598fd775 100644
--- a/drivers/net/ipa/ipa_reg.h
+++ b/drivers/net/ipa/ipa_reg.h
@@ -426,7 +426,7 @@ enum ipa_cs_offload_en {
 	IPA_CS_RSVD
 };
 
-/** enum ipa_aggr_en - aggregation type field in ENDP_INIT_AGGR_N */
+/** enum ipa_aggr_en - aggregation enable field in ENDP_INIT_AGGR_N */
 enum ipa_aggr_en {
 	IPA_BYPASS_AGGR		= 0,
 	IPA_ENABLE_AGGR		= 1,
diff --git a/drivers/net/ipa/ipa_table.c b/drivers/net/ipa/ipa_table.c
index 2098ca2f2c90..b3790aa952a1 100644
--- a/drivers/net/ipa/ipa_table.c
+++ b/drivers/net/ipa/ipa_table.c
@@ -521,7 +521,7 @@ static void ipa_filter_tuple_zero(struct ipa_endpoint *endpoint)
 	val = ioread32(endpoint->ipa->reg_virt + offset);
 
 	/* Zero all filter-related fields, preserving the rest */
-	u32_replace_bits(val, 0, IPA_REG_ENDP_FILTER_HASH_MSK_ALL);
+	u32p_replace_bits(&val, 0, IPA_REG_ENDP_FILTER_HASH_MSK_ALL);
 
 	iowrite32(val, endpoint->ipa->reg_virt + offset);
 }
@@ -573,7 +573,7 @@ static void ipa_route_tuple_zero(struct ipa *ipa, u32 route_id)
 	val = ioread32(ipa->reg_virt + offset);
 
 	/* Zero all route-related fields, preserving the rest */
-	u32_replace_bits(val, 0, IPA_REG_ENDP_ROUTER_HASH_MSK_ALL);
+	u32p_replace_bits(&val, 0, IPA_REG_ENDP_ROUTER_HASH_MSK_ALL);
 
 	iowrite32(val, ipa->reg_virt + offset);
 }
diff --git a/drivers/net/ipa/ipa_uc.c b/drivers/net/ipa/ipa_uc.c
index 1a0b04e0ab74..b382d47bc70d 100644
--- a/drivers/net/ipa/ipa_uc.c
+++ b/drivers/net/ipa/ipa_uc.c
@@ -144,7 +144,7 @@ static void ipa_uc_response_hdlr(struct ipa *ipa, enum ipa_irq_id irq_id)
 	 * should only receive responses from the microcontroller when it has
 	 * sent it a request message.
 	 *
-	 * We can drop the clock reference taken in ipa_uc_init() once we
+	 * We can drop the clock reference taken in ipa_uc_setup() once we
 	 * know the microcontroller has finished its initialization.
 	 */
 	switch (shared->response) {
diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 124045cbcda3..3f4d8c6625de 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -3285,7 +3285,7 @@ done:
 	return skb->len;
 }
 
-static const struct genl_ops macsec_genl_ops[] = {
+static const struct genl_small_ops macsec_genl_ops[] = {
 	{
 		.cmd = MACSEC_CMD_GET_TXSC,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
@@ -3361,8 +3361,8 @@ static struct genl_family macsec_fam __ro_after_init = {
 	.policy = macsec_genl_policy,
 	.netnsok	= true,
 	.module		= THIS_MODULE,
-	.ops		= macsec_genl_ops,
-	.n_ops		= ARRAY_SIZE(macsec_genl_ops),
+	.small_ops	= macsec_genl_ops,
+	.n_small_ops	= ARRAY_SIZE(macsec_genl_ops),
 };
 
 static netdev_tx_t macsec_start_xmit(struct sk_buff *skb,
diff --git a/drivers/net/mdio/mdio-ipq4019.c b/drivers/net/mdio/mdio-ipq4019.c
index 1ce81ff2f41d..25c25ea6da66 100644
--- a/drivers/net/mdio/mdio-ipq4019.c
+++ b/drivers/net/mdio/mdio-ipq4019.c
@@ -12,6 +12,7 @@
 #include <linux/phy.h>
 #include <linux/platform_device.h>
 
+#define MDIO_MODE_REG				0x40
 #define MDIO_ADDR_REG				0x44
 #define MDIO_DATA_WRITE_REG			0x48
 #define MDIO_DATA_READ_REG			0x4c
@@ -20,9 +21,15 @@
 #define MDIO_CMD_ACCESS_START		BIT(8)
 #define MDIO_CMD_ACCESS_CODE_READ	0
 #define MDIO_CMD_ACCESS_CODE_WRITE	1
+#define MDIO_CMD_ACCESS_CODE_C45_ADDR	0
+#define MDIO_CMD_ACCESS_CODE_C45_WRITE	1
+#define MDIO_CMD_ACCESS_CODE_C45_READ	2
 
-#define ipq4019_MDIO_TIMEOUT	10000
-#define ipq4019_MDIO_SLEEP		10
+/* 0 = Clause 22, 1 = Clause 45 */
+#define MDIO_MODE_C45				BIT(8)
+
+#define IPQ4019_MDIO_TIMEOUT	10000
+#define IPQ4019_MDIO_SLEEP		10
 
 struct ipq4019_mdio_data {
 	void __iomem	*membase;
@@ -35,25 +42,50 @@ static int ipq4019_mdio_wait_busy(struct mii_bus *bus)
 
 	return readl_poll_timeout(priv->membase + MDIO_CMD_REG, busy,
 				  (busy & MDIO_CMD_ACCESS_BUSY) == 0,
-				  ipq4019_MDIO_SLEEP, ipq4019_MDIO_TIMEOUT);
+				  IPQ4019_MDIO_SLEEP, IPQ4019_MDIO_TIMEOUT);
 }
 
 static int ipq4019_mdio_read(struct mii_bus *bus, int mii_id, int regnum)
 {
 	struct ipq4019_mdio_data *priv = bus->priv;
+	unsigned int data;
 	unsigned int cmd;
 
-	/* Reject clause 45 */
-	if (regnum & MII_ADDR_C45)
-		return -EOPNOTSUPP;
-
 	if (ipq4019_mdio_wait_busy(bus))
 		return -ETIMEDOUT;
 
-	/* issue the phy address and reg */
-	writel((mii_id << 8) | regnum, priv->membase + MDIO_ADDR_REG);
+	/* Clause 45 support */
+	if (regnum & MII_ADDR_C45) {
+		unsigned int mmd = (regnum >> 16) & 0x1F;
+		unsigned int reg = regnum & 0xFFFF;
+
+		/* Enter Clause 45 mode */
+		data = readl(priv->membase + MDIO_MODE_REG);
+
+		data |= MDIO_MODE_C45;
+
+		writel(data, priv->membase + MDIO_MODE_REG);
+
+		/* issue the phy address and mmd */
+		writel((mii_id << 8) | mmd, priv->membase + MDIO_ADDR_REG);
+
+		/* issue reg */
+		writel(reg, priv->membase + MDIO_DATA_WRITE_REG);
+
+		cmd = MDIO_CMD_ACCESS_START | MDIO_CMD_ACCESS_CODE_C45_ADDR;
+	} else {
+		/* Enter Clause 22 mode */
+		data = readl(priv->membase + MDIO_MODE_REG);
 
-	cmd = MDIO_CMD_ACCESS_START | MDIO_CMD_ACCESS_CODE_READ;
+		data &= ~MDIO_MODE_C45;
+
+		writel(data, priv->membase + MDIO_MODE_REG);
+
+		/* issue the phy address and reg */
+		writel((mii_id << 8) | regnum, priv->membase + MDIO_ADDR_REG);
+
+		cmd = MDIO_CMD_ACCESS_START | MDIO_CMD_ACCESS_CODE_READ;
+	}
 
 	/* issue read command */
 	writel(cmd, priv->membase + MDIO_CMD_REG);
@@ -62,6 +94,15 @@ static int ipq4019_mdio_read(struct mii_bus *bus, int mii_id, int regnum)
 	if (ipq4019_mdio_wait_busy(bus))
 		return -ETIMEDOUT;
 
+	if (regnum & MII_ADDR_C45) {
+		cmd = MDIO_CMD_ACCESS_START | MDIO_CMD_ACCESS_CODE_C45_READ;
+
+		writel(cmd, priv->membase + MDIO_CMD_REG);
+
+		if (ipq4019_mdio_wait_busy(bus))
+			return -ETIMEDOUT;
+	}
+
 	/* Read and return data */
 	return readl(priv->membase + MDIO_DATA_READ_REG);
 }
@@ -70,23 +111,57 @@ static int ipq4019_mdio_write(struct mii_bus *bus, int mii_id, int regnum,
 							 u16 value)
 {
 	struct ipq4019_mdio_data *priv = bus->priv;
+	unsigned int data;
 	unsigned int cmd;
 
-	/* Reject clause 45 */
-	if (regnum & MII_ADDR_C45)
-		return -EOPNOTSUPP;
-
 	if (ipq4019_mdio_wait_busy(bus))
 		return -ETIMEDOUT;
 
-	/* issue the phy address and reg */
-	writel((mii_id << 8) | regnum, priv->membase + MDIO_ADDR_REG);
+	/* Clause 45 support */
+	if (regnum & MII_ADDR_C45) {
+		unsigned int mmd = (regnum >> 16) & 0x1F;
+		unsigned int reg = regnum & 0xFFFF;
+
+		/* Enter Clause 45 mode */
+		data = readl(priv->membase + MDIO_MODE_REG);
+
+		data |= MDIO_MODE_C45;
+
+		writel(data, priv->membase + MDIO_MODE_REG);
+
+		/* issue the phy address and mmd */
+		writel((mii_id << 8) | mmd, priv->membase + MDIO_ADDR_REG);
+
+		/* issue reg */
+		writel(reg, priv->membase + MDIO_DATA_WRITE_REG);
+
+		cmd = MDIO_CMD_ACCESS_START | MDIO_CMD_ACCESS_CODE_C45_ADDR;
+
+		writel(cmd, priv->membase + MDIO_CMD_REG);
+
+		if (ipq4019_mdio_wait_busy(bus))
+			return -ETIMEDOUT;
+	} else {
+		/* Enter Clause 22 mode */
+		data = readl(priv->membase + MDIO_MODE_REG);
+
+		data &= ~MDIO_MODE_C45;
+
+		writel(data, priv->membase + MDIO_MODE_REG);
+
+		/* issue the phy address and reg */
+		writel((mii_id << 8) | regnum, priv->membase + MDIO_ADDR_REG);
+	}
 
 	/* issue write data */
 	writel(value, priv->membase + MDIO_DATA_WRITE_REG);
 
-	cmd = MDIO_CMD_ACCESS_START | MDIO_CMD_ACCESS_CODE_WRITE;
 	/* issue write command */
+	if (regnum & MII_ADDR_C45)
+		cmd = MDIO_CMD_ACCESS_START | MDIO_CMD_ACCESS_CODE_C45_WRITE;
+	else
+		cmd = MDIO_CMD_ACCESS_START | MDIO_CMD_ACCESS_CODE_WRITE;
+
 	writel(cmd, priv->membase + MDIO_CMD_REG);
 
 	/* Wait write complete */
diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c
index e665efd760f8..56213ba151f6 100644
--- a/drivers/net/netdevsim/dev.c
+++ b/drivers/net/netdevsim/dev.c
@@ -203,6 +203,8 @@ static int nsim_dev_debugfs_init(struct nsim_dev *nsim_dev)
 		return PTR_ERR(nsim_dev->ports_ddir);
 	debugfs_create_bool("fw_update_status", 0600, nsim_dev->ddir,
 			    &nsim_dev->fw_update_status);
+	debugfs_create_u32("fw_update_overwrite_mask", 0600, nsim_dev->ddir,
+			    &nsim_dev->fw_update_overwrite_mask);
 	debugfs_create_u32("max_macs", 0600, nsim_dev->ddir,
 			   &nsim_dev->max_macs);
 	debugfs_create_bool("test1", 0600, nsim_dev->ddir,
@@ -742,24 +744,27 @@ static int nsim_dev_info_get(struct devlink *devlink,
 #define NSIM_DEV_FLASH_CHUNK_SIZE 1000
 #define NSIM_DEV_FLASH_CHUNK_TIME_MS 10
 
-static int nsim_dev_flash_update(struct devlink *devlink, const char *file_name,
-				 const char *component,
+static int nsim_dev_flash_update(struct devlink *devlink,
+				 struct devlink_flash_update_params *params,
 				 struct netlink_ext_ack *extack)
 {
 	struct nsim_dev *nsim_dev = devlink_priv(devlink);
 	int i;
 
+	if ((params->overwrite_mask & ~nsim_dev->fw_update_overwrite_mask) != 0)
+		return -EOPNOTSUPP;
+
 	if (nsim_dev->fw_update_status) {
 		devlink_flash_update_begin_notify(devlink);
 		devlink_flash_update_status_notify(devlink,
 						   "Preparing to flash",
-						   component, 0, 0);
+						   params->component, 0, 0);
 	}
 
 	for (i = 0; i < NSIM_DEV_FLASH_SIZE / NSIM_DEV_FLASH_CHUNK_SIZE; i++) {
 		if (nsim_dev->fw_update_status)
 			devlink_flash_update_status_notify(devlink, "Flashing",
-							   component,
+							   params->component,
 							   i * NSIM_DEV_FLASH_CHUNK_SIZE,
 							   NSIM_DEV_FLASH_SIZE);
 		msleep(NSIM_DEV_FLASH_CHUNK_TIME_MS);
@@ -767,13 +772,13 @@ static int nsim_dev_flash_update(struct devlink *devlink, const char *file_name,
 
 	if (nsim_dev->fw_update_status) {
 		devlink_flash_update_status_notify(devlink, "Flashing",
-						   component,
+						   params->component,
 						   NSIM_DEV_FLASH_SIZE,
 						   NSIM_DEV_FLASH_SIZE);
 		devlink_flash_update_timeout_notify(devlink, "Flash select",
-						    component, 81);
+						    params->component, 81);
 		devlink_flash_update_status_notify(devlink, "Flashing done",
-						   component, 0, 0);
+						   params->component, 0, 0);
 		devlink_flash_update_end_notify(devlink);
 	}
 
@@ -879,6 +884,8 @@ nsim_dev_devlink_trap_policer_counter_get(struct devlink *devlink,
 }
 
 static const struct devlink_ops nsim_dev_devlink_ops = {
+	.supported_flash_update_params = DEVLINK_SUPPORT_FLASH_UPDATE_COMPONENT |
+					 DEVLINK_SUPPORT_FLASH_UPDATE_OVERWRITE_MASK,
 	.reload_down = nsim_dev_reload_down,
 	.reload_up = nsim_dev_reload_up,
 	.info_get = nsim_dev_info_get,
@@ -993,6 +1000,7 @@ static int nsim_dev_reload_create(struct nsim_dev *nsim_dev,
 	INIT_LIST_HEAD(&nsim_dev->port_list);
 	mutex_init(&nsim_dev->port_list_lock);
 	nsim_dev->fw_update_status = true;
+	nsim_dev->fw_update_overwrite_mask = 0;
 
 	nsim_dev->fib_data = nsim_fib_create(devlink, extack);
 	if (IS_ERR(nsim_dev->fib_data))
@@ -1051,6 +1059,7 @@ int nsim_dev_probe(struct nsim_bus_dev *nsim_bus_dev)
 	INIT_LIST_HEAD(&nsim_dev->port_list);
 	mutex_init(&nsim_dev->port_list_lock);
 	nsim_dev->fw_update_status = true;
+	nsim_dev->fw_update_overwrite_mask = 0;
 	nsim_dev->max_macs = NSIM_DEV_MAX_MACS_DEFAULT;
 	nsim_dev->test1 = NSIM_DEV_TEST1_DEFAULT;
 	spin_lock_init(&nsim_dev->fa_cookie_lock);
diff --git a/drivers/net/netdevsim/ethtool.c b/drivers/net/netdevsim/ethtool.c
index 7a4c779b4c89..f1884d90a876 100644
--- a/drivers/net/netdevsim/ethtool.c
+++ b/drivers/net/netdevsim/ethtool.c
@@ -54,7 +54,7 @@ void nsim_ethtool_init(struct netdevsim *ns)
 
 	ns->netdev->ethtool_ops = &nsim_ethtool_ops;
 
-	ethtool = debugfs_create_dir("ethtool", ns->nsim_dev->ddir);
+	ethtool = debugfs_create_dir("ethtool", ns->nsim_dev_port->ddir);
 
 	dir = debugfs_create_dir("pause", ethtool);
 	debugfs_create_bool("report_stats_rx", 0600, dir,
diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h
index 0c86561e6d8d..827fc80f50a0 100644
--- a/drivers/net/netdevsim/netdevsim.h
+++ b/drivers/net/netdevsim/netdevsim.h
@@ -20,6 +20,7 @@
 #include <linux/netdevice.h>
 #include <linux/u64_stats_sync.h>
 #include <net/devlink.h>
+#include <net/udp_tunnel.h>
 #include <net/xdp.h>
 
 #define DRV_NAME	"netdevsim"
@@ -84,7 +85,8 @@ struct netdevsim {
 	struct {
 		u32 inject_error;
 		u32 sleep;
-		u32 ports[2][NSIM_UDP_TUNNEL_N_PORTS];
+		u32 __ports[2][NSIM_UDP_TUNNEL_N_PORTS];
+		u32 (*ports)[NSIM_UDP_TUNNEL_N_PORTS];
 		struct debugfs_u32_array dfs_ports[2];
 	} udp_ports;
 
@@ -196,6 +198,7 @@ struct nsim_dev {
 	struct list_head port_list;
 	struct mutex port_list_lock; /* protects port list */
 	bool fw_update_status;
+	u32 fw_update_overwrite_mask;
 	u32 max_macs;
 	bool test1;
 	bool dont_allow_reload;
@@ -208,9 +211,13 @@ struct nsim_dev {
 	bool fail_trap_policer_set;
 	bool fail_trap_policer_counter_get;
 	struct {
+		struct udp_tunnel_nic_shared utn_shared;
+		u32 __ports[2][NSIM_UDP_TUNNEL_N_PORTS];
 		bool sync_all;
 		bool open_only;
 		bool ipv4_only;
+		bool shared;
+		bool static_iana_vxlan;
 		u32 sleep;
 	} udp_ports;
 };
diff --git a/drivers/net/netdevsim/udp_tunnels.c b/drivers/net/netdevsim/udp_tunnels.c
index 22c06a76033c..6ab023acefd6 100644
--- a/drivers/net/netdevsim/udp_tunnels.c
+++ b/drivers/net/netdevsim/udp_tunnels.c
@@ -22,11 +22,13 @@ nsim_udp_tunnel_set_port(struct net_device *dev, unsigned int table,
 		msleep(ns->udp_ports.sleep);
 
 	if (!ret) {
-		if (ns->udp_ports.ports[table][entry])
+		if (ns->udp_ports.ports[table][entry]) {
+			WARN(1, "entry already in use\n");
 			ret = -EBUSY;
-		else
+		} else {
 			ns->udp_ports.ports[table][entry] =
 				be16_to_cpu(ti->port) << 16 | ti->type;
+		}
 	}
 
 	netdev_info(dev, "set [%d, %d] type %d family %d port %d - %d\n",
@@ -50,10 +52,13 @@ nsim_udp_tunnel_unset_port(struct net_device *dev, unsigned int table,
 	if (!ret) {
 		u32 val = be16_to_cpu(ti->port) << 16 | ti->type;
 
-		if (val == ns->udp_ports.ports[table][entry])
+		if (val == ns->udp_ports.ports[table][entry]) {
 			ns->udp_ports.ports[table][entry] = 0;
-		else
+		} else {
+			WARN(1, "entry not installed %x vs %x\n",
+			     val, ns->udp_ports.ports[table][entry]);
 			ret = -ENOENT;
+		}
 	}
 
 	netdev_info(dev, "unset [%d, %d] type %d family %d port %d - %d\n",
@@ -107,7 +112,7 @@ nsim_udp_tunnels_info_reset_write(struct file *file, const char __user *data,
 	struct net_device *dev = file->private_data;
 	struct netdevsim *ns = netdev_priv(dev);
 
-	memset(&ns->udp_ports.ports, 0, sizeof(ns->udp_ports.ports));
+	memset(ns->udp_ports.ports, 0, sizeof(ns->udp_ports.__ports));
 	rtnl_lock();
 	udp_tunnel_nic_reset_ntf(dev);
 	rtnl_unlock();
@@ -127,6 +132,17 @@ int nsim_udp_tunnels_info_create(struct nsim_dev *nsim_dev,
 	struct netdevsim *ns = netdev_priv(dev);
 	struct udp_tunnel_nic_info *info;
 
+	if (nsim_dev->udp_ports.shared && nsim_dev->udp_ports.open_only) {
+		dev_err(&nsim_dev->nsim_bus_dev->dev,
+			"shared can't be used in conjunction with open_only\n");
+		return -EINVAL;
+	}
+
+	if (!nsim_dev->udp_ports.shared)
+		ns->udp_ports.ports = ns->udp_ports.__ports;
+	else
+		ns->udp_ports.ports = nsim_dev->udp_ports.__ports;
+
 	debugfs_create_u32("udp_ports_inject_error", 0600,
 			   ns->nsim_dev_port->ddir,
 			   &ns->udp_ports.inject_error);
@@ -168,6 +184,10 @@ int nsim_udp_tunnels_info_create(struct nsim_dev *nsim_dev,
 		info->flags |= UDP_TUNNEL_NIC_INFO_OPEN_ONLY;
 	if (nsim_dev->udp_ports.ipv4_only)
 		info->flags |= UDP_TUNNEL_NIC_INFO_IPV4_ONLY;
+	if (nsim_dev->udp_ports.shared)
+		info->shared = &nsim_dev->udp_ports.utn_shared;
+	if (nsim_dev->udp_ports.static_iana_vxlan)
+		info->flags |= UDP_TUNNEL_NIC_INFO_STATIC_IANA_VXLAN;
 
 	dev->udp_tunnel_nic_info = info;
 	return 0;
@@ -187,6 +207,10 @@ void nsim_udp_tunnels_debugfs_create(struct nsim_dev *nsim_dev)
 			    &nsim_dev->udp_ports.open_only);
 	debugfs_create_bool("udp_ports_ipv4_only", 0600, nsim_dev->ddir,
 			    &nsim_dev->udp_ports.ipv4_only);
+	debugfs_create_bool("udp_ports_shared", 0600, nsim_dev->ddir,
+			    &nsim_dev->udp_ports.shared);
+	debugfs_create_bool("udp_ports_static_iana_vxlan", 0600, nsim_dev->ddir,
+			    &nsim_dev->udp_ports.static_iana_vxlan);
 	debugfs_create_u32("udp_ports_sleep", 0600, nsim_dev->ddir,
 			   &nsim_dev->udp_ports.sleep);
 }
diff --git a/drivers/net/pcs/pcs-lynx.c b/drivers/net/pcs/pcs-lynx.c
index c43d97682083..62bb9272dcb2 100644
--- a/drivers/net/pcs/pcs-lynx.c
+++ b/drivers/net/pcs/pcs-lynx.c
@@ -93,6 +93,9 @@ static void lynx_pcs_get_state(struct phylink_pcs *pcs,
 	case PHY_INTERFACE_MODE_USXGMII:
 		lynx_pcs_get_state_usxgmii(lynx->mdio, state);
 		break;
+	case PHY_INTERFACE_MODE_10GBASER:
+		phylink_mii_c45_pcs_get_state(lynx->mdio, state);
+		break;
 	default:
 		break;
 	}
@@ -172,6 +175,9 @@ static int lynx_pcs_config(struct phylink_pcs *pcs, unsigned int mode,
 		break;
 	case PHY_INTERFACE_MODE_USXGMII:
 		return lynx_pcs_config_usxgmii(lynx->mdio, mode, advertising);
+	case PHY_INTERFACE_MODE_10GBASER:
+		/* Nothing to do here for 10GBASER */
+		break;
 	default:
 		return -EOPNOTSUPP;
 	}
diff --git a/drivers/net/phy/bcm7xxx.c b/drivers/net/phy/bcm7xxx.c
index 744c24491d63..15812001b3ff 100644
--- a/drivers/net/phy/bcm7xxx.c
+++ b/drivers/net/phy/bcm7xxx.c
@@ -611,6 +611,7 @@ static void bcm7xxx_28nm_remove(struct phy_device *phydev)
 }
 
 static struct phy_driver bcm7xxx_driver[] = {
+	BCM7XXX_28NM_EPHY(PHY_ID_BCM72113, "Broadcom BCM72113"),
 	BCM7XXX_28NM_GPHY(PHY_ID_BCM7250, "Broadcom BCM7250"),
 	BCM7XXX_28NM_EPHY(PHY_ID_BCM7255, "Broadcom BCM7255"),
 	BCM7XXX_28NM_EPHY(PHY_ID_BCM7260, "Broadcom BCM7260"),
@@ -631,6 +632,7 @@ static struct phy_driver bcm7xxx_driver[] = {
 };
 
 static struct mdio_device_id __maybe_unused bcm7xxx_tbl[] = {
+	{ PHY_ID_BCM72113, 0xfffffff0 },
 	{ PHY_ID_BCM7250, 0xfffffff0, },
 	{ PHY_ID_BCM7255, 0xfffffff0, },
 	{ PHY_ID_BCM7260, 0xfffffff0, },
diff --git a/drivers/net/phy/dp83869.c b/drivers/net/phy/dp83869.c
index 81899bc99add..cf6dec7b7d8e 100644
--- a/drivers/net/phy/dp83869.c
+++ b/drivers/net/phy/dp83869.c
@@ -4,12 +4,14 @@
  */
 
 #include <linux/ethtool.h>
+#include <linux/etherdevice.h>
 #include <linux/kernel.h>
 #include <linux/mii.h>
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/phy.h>
 #include <linux/delay.h>
+#include <linux/bitfield.h>
 
 #include <dt-bindings/net/ti-dp83869.h>
 
@@ -19,6 +21,7 @@
 #define MII_DP83869_PHYCTRL	0x10
 #define MII_DP83869_MICR	0x12
 #define MII_DP83869_ISR		0x13
+#define DP83869_CFG2		0x14
 #define DP83869_CTRL		0x1f
 #define DP83869_CFG4		0x1e
 
@@ -27,6 +30,13 @@
 #define DP83869_RGMIICTL	0x0032
 #define DP83869_STRAP_STS1	0x006e
 #define DP83869_RGMIIDCTL	0x0086
+#define DP83869_RXFCFG		0x0134
+#define DP83869_RXFPMD1		0x0136
+#define DP83869_RXFPMD2		0x0137
+#define DP83869_RXFPMD3		0x0138
+#define DP83869_RXFSOP1		0x0139
+#define DP83869_RXFSOP2		0x013A
+#define DP83869_RXFSOP3		0x013B
 #define DP83869_IO_MUX_CFG	0x0170
 #define DP83869_OP_MODE		0x01df
 #define DP83869_FX_CTRL		0x0c00
@@ -104,6 +114,26 @@
 #define DP83869_OP_MODE_MII			BIT(5)
 #define DP83869_SGMII_RGMII_BRIDGE		BIT(6)
 
+/* RXFCFG bits*/
+#define DP83869_WOL_MAGIC_EN		BIT(0)
+#define DP83869_WOL_PATTERN_EN		BIT(1)
+#define DP83869_WOL_BCAST_EN		BIT(2)
+#define DP83869_WOL_UCAST_EN		BIT(4)
+#define DP83869_WOL_SEC_EN		BIT(5)
+#define DP83869_WOL_ENH_MAC		BIT(7)
+
+/* CFG2 bits */
+#define DP83869_DOWNSHIFT_EN		(BIT(8) | BIT(9))
+#define DP83869_DOWNSHIFT_ATTEMPT_MASK	(BIT(10) | BIT(11))
+#define DP83869_DOWNSHIFT_1_COUNT_VAL	0
+#define DP83869_DOWNSHIFT_2_COUNT_VAL	1
+#define DP83869_DOWNSHIFT_4_COUNT_VAL	2
+#define DP83869_DOWNSHIFT_8_COUNT_VAL	3
+#define DP83869_DOWNSHIFT_1_COUNT	1
+#define DP83869_DOWNSHIFT_2_COUNT	2
+#define DP83869_DOWNSHIFT_4_COUNT	4
+#define DP83869_DOWNSHIFT_8_COUNT	8
+
 enum {
 	DP83869_PORT_MIRRORING_KEEP,
 	DP83869_PORT_MIRRORING_EN,
@@ -177,6 +207,256 @@ static int dp83869_config_intr(struct phy_device *phydev)
 	return phy_write(phydev, MII_DP83869_MICR, micr_status);
 }
 
+static int dp83869_set_wol(struct phy_device *phydev,
+			   struct ethtool_wolinfo *wol)
+{
+	struct net_device *ndev = phydev->attached_dev;
+	int val_rxcfg, val_micr;
+	u8 *mac;
+	int ret;
+
+	val_rxcfg = phy_read_mmd(phydev, DP83869_DEVADDR, DP83869_RXFCFG);
+	if (val_rxcfg < 0)
+		return val_rxcfg;
+
+	val_micr = phy_read(phydev, MII_DP83869_MICR);
+	if (val_micr < 0)
+		return val_micr;
+
+	if (wol->wolopts & (WAKE_MAGIC | WAKE_MAGICSECURE | WAKE_UCAST |
+			    WAKE_BCAST)) {
+		val_rxcfg |= DP83869_WOL_ENH_MAC;
+		val_micr |= MII_DP83869_MICR_WOL_INT_EN;
+
+		if (wol->wolopts & WAKE_MAGIC ||
+		    wol->wolopts & WAKE_MAGICSECURE) {
+			mac = (u8 *)ndev->dev_addr;
+
+			if (!is_valid_ether_addr(mac))
+				return -EINVAL;
+
+			ret = phy_write_mmd(phydev, DP83869_DEVADDR,
+					    DP83869_RXFPMD1,
+					    mac[1] << 8 | mac[0]);
+			if (ret)
+				return ret;
+
+			ret = phy_write_mmd(phydev, DP83869_DEVADDR,
+					    DP83869_RXFPMD2,
+					    mac[3] << 8 | mac[2]);
+			if (ret)
+				return ret;
+
+			ret = phy_write_mmd(phydev, DP83869_DEVADDR,
+					    DP83869_RXFPMD3,
+					    mac[5] << 8 | mac[4]);
+			if (ret)
+				return ret;
+
+			val_rxcfg |= DP83869_WOL_MAGIC_EN;
+		} else {
+			val_rxcfg &= ~DP83869_WOL_MAGIC_EN;
+		}
+
+		if (wol->wolopts & WAKE_MAGICSECURE) {
+			ret = phy_write_mmd(phydev, DP83869_DEVADDR,
+					    DP83869_RXFSOP1,
+					    (wol->sopass[1] << 8) | wol->sopass[0]);
+			if (ret)
+				return ret;
+
+			ret = phy_write_mmd(phydev, DP83869_DEVADDR,
+					    DP83869_RXFSOP2,
+					    (wol->sopass[3] << 8) | wol->sopass[2]);
+			if (ret)
+				return ret;
+			ret = phy_write_mmd(phydev, DP83869_DEVADDR,
+					    DP83869_RXFSOP3,
+					    (wol->sopass[5] << 8) | wol->sopass[4]);
+			if (ret)
+				return ret;
+
+			val_rxcfg |= DP83869_WOL_SEC_EN;
+		} else {
+			val_rxcfg &= ~DP83869_WOL_SEC_EN;
+		}
+
+		if (wol->wolopts & WAKE_UCAST)
+			val_rxcfg |= DP83869_WOL_UCAST_EN;
+		else
+			val_rxcfg &= ~DP83869_WOL_UCAST_EN;
+
+		if (wol->wolopts & WAKE_BCAST)
+			val_rxcfg |= DP83869_WOL_BCAST_EN;
+		else
+			val_rxcfg &= ~DP83869_WOL_BCAST_EN;
+	} else {
+		val_rxcfg &= ~DP83869_WOL_ENH_MAC;
+		val_micr &= ~MII_DP83869_MICR_WOL_INT_EN;
+	}
+
+	ret = phy_write_mmd(phydev, DP83869_DEVADDR, DP83869_RXFCFG, val_rxcfg);
+	if (ret)
+		return ret;
+
+	return phy_write(phydev, MII_DP83869_MICR, val_micr);
+}
+
+static void dp83869_get_wol(struct phy_device *phydev,
+			    struct ethtool_wolinfo *wol)
+{
+	int value, sopass_val;
+
+	wol->supported = (WAKE_UCAST | WAKE_BCAST | WAKE_MAGIC |
+			WAKE_MAGICSECURE);
+	wol->wolopts = 0;
+
+	value = phy_read_mmd(phydev, DP83869_DEVADDR, DP83869_RXFCFG);
+	if (value < 0) {
+		phydev_err(phydev, "Failed to read RX CFG\n");
+		return;
+	}
+
+	if (value & DP83869_WOL_UCAST_EN)
+		wol->wolopts |= WAKE_UCAST;
+
+	if (value & DP83869_WOL_BCAST_EN)
+		wol->wolopts |= WAKE_BCAST;
+
+	if (value & DP83869_WOL_MAGIC_EN)
+		wol->wolopts |= WAKE_MAGIC;
+
+	if (value & DP83869_WOL_SEC_EN) {
+		sopass_val = phy_read_mmd(phydev, DP83869_DEVADDR,
+					  DP83869_RXFSOP1);
+		if (sopass_val < 0) {
+			phydev_err(phydev, "Failed to read RX SOP 1\n");
+			return;
+		}
+
+		wol->sopass[0] = (sopass_val & 0xff);
+		wol->sopass[1] = (sopass_val >> 8);
+
+		sopass_val = phy_read_mmd(phydev, DP83869_DEVADDR,
+					  DP83869_RXFSOP2);
+		if (sopass_val < 0) {
+			phydev_err(phydev, "Failed to read RX SOP 2\n");
+			return;
+		}
+
+		wol->sopass[2] = (sopass_val & 0xff);
+		wol->sopass[3] = (sopass_val >> 8);
+
+		sopass_val = phy_read_mmd(phydev, DP83869_DEVADDR,
+					  DP83869_RXFSOP3);
+		if (sopass_val < 0) {
+			phydev_err(phydev, "Failed to read RX SOP 3\n");
+			return;
+		}
+
+		wol->sopass[4] = (sopass_val & 0xff);
+		wol->sopass[5] = (sopass_val >> 8);
+
+		wol->wolopts |= WAKE_MAGICSECURE;
+	}
+
+	if (!(value & DP83869_WOL_ENH_MAC))
+		wol->wolopts = 0;
+}
+
+static int dp83869_get_downshift(struct phy_device *phydev, u8 *data)
+{
+	int val, cnt, enable, count;
+
+	val = phy_read(phydev, DP83869_CFG2);
+	if (val < 0)
+		return val;
+
+	enable = FIELD_GET(DP83869_DOWNSHIFT_EN, val);
+	cnt = FIELD_GET(DP83869_DOWNSHIFT_ATTEMPT_MASK, val);
+
+	switch (cnt) {
+	case DP83869_DOWNSHIFT_1_COUNT_VAL:
+		count = DP83869_DOWNSHIFT_1_COUNT;
+		break;
+	case DP83869_DOWNSHIFT_2_COUNT_VAL:
+		count = DP83869_DOWNSHIFT_2_COUNT;
+		break;
+	case DP83869_DOWNSHIFT_4_COUNT_VAL:
+		count = DP83869_DOWNSHIFT_4_COUNT;
+		break;
+	case DP83869_DOWNSHIFT_8_COUNT_VAL:
+		count = DP83869_DOWNSHIFT_8_COUNT;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	*data = enable ? count : DOWNSHIFT_DEV_DISABLE;
+
+	return 0;
+}
+
+static int dp83869_set_downshift(struct phy_device *phydev, u8 cnt)
+{
+	int val, count;
+
+	if (cnt > DP83869_DOWNSHIFT_8_COUNT)
+		return -EINVAL;
+
+	if (!cnt)
+		return phy_clear_bits(phydev, DP83869_CFG2,
+				      DP83869_DOWNSHIFT_EN);
+
+	switch (cnt) {
+	case DP83869_DOWNSHIFT_1_COUNT:
+		count = DP83869_DOWNSHIFT_1_COUNT_VAL;
+		break;
+	case DP83869_DOWNSHIFT_2_COUNT:
+		count = DP83869_DOWNSHIFT_2_COUNT_VAL;
+		break;
+	case DP83869_DOWNSHIFT_4_COUNT:
+		count = DP83869_DOWNSHIFT_4_COUNT_VAL;
+		break;
+	case DP83869_DOWNSHIFT_8_COUNT:
+		count = DP83869_DOWNSHIFT_8_COUNT_VAL;
+		break;
+	default:
+		phydev_err(phydev,
+			   "Downshift count must be 1, 2, 4 or 8\n");
+		return -EINVAL;
+	}
+
+	val = DP83869_DOWNSHIFT_EN;
+	val |= FIELD_PREP(DP83869_DOWNSHIFT_ATTEMPT_MASK, count);
+
+	return phy_modify(phydev, DP83869_CFG2,
+			  DP83869_DOWNSHIFT_EN | DP83869_DOWNSHIFT_ATTEMPT_MASK,
+			  val);
+}
+
+static int dp83869_get_tunable(struct phy_device *phydev,
+			       struct ethtool_tunable *tuna, void *data)
+{
+	switch (tuna->id) {
+	case ETHTOOL_PHY_DOWNSHIFT:
+		return dp83869_get_downshift(phydev, data);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int dp83869_set_tunable(struct phy_device *phydev,
+			       struct ethtool_tunable *tuna, const void *data)
+{
+	switch (tuna->id) {
+	case ETHTOOL_PHY_DOWNSHIFT:
+		return dp83869_set_downshift(phydev, *(const u8 *)data);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
 static int dp83869_config_port_mirroring(struct phy_device *phydev)
 {
 	struct dp83869_private *dp83869 = phydev->priv;
@@ -469,6 +749,12 @@ static int dp83869_config_init(struct phy_device *phydev)
 	struct dp83869_private *dp83869 = phydev->priv;
 	int ret, val;
 
+	/* Force speed optimization for the PHY even if it strapped */
+	ret = phy_modify(phydev, DP83869_CFG2, DP83869_DOWNSHIFT_EN,
+			 DP83869_DOWNSHIFT_EN);
+	if (ret)
+		return ret;
+
 	ret = dp83869_configure_mode(phydev, dp83869);
 	if (ret)
 		return ret;
@@ -568,6 +854,12 @@ static struct phy_driver dp83869_driver[] = {
 		.config_intr	= dp83869_config_intr,
 		.read_status	= dp83869_read_status,
 
+		.get_tunable	= dp83869_get_tunable,
+		.set_tunable	= dp83869_set_tunable,
+
+		.get_wol	= dp83869_get_wol,
+		.set_wol	= dp83869_set_wol,
+
 		.suspend	= genphy_suspend,
 		.resume		= genphy_resume,
 	},
diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c
index 0af20faad69d..757e950fb745 100644
--- a/drivers/net/phy/mdio_bus.c
+++ b/drivers/net/phy/mdio_bus.c
@@ -825,9 +825,6 @@ int mdiobus_read_nested(struct mii_bus *bus, int addr, u32 regnum)
 {
 	int retval;
 
-	if (WARN_ON_ONCE(in_interrupt()))
-		return -EINVAL;
-
 	mutex_lock_nested(&bus->mdio_lock, MDIO_MUTEX_NESTED);
 	retval = __mdiobus_read(bus, addr, regnum);
 	mutex_unlock(&bus->mdio_lock);
@@ -850,9 +847,6 @@ int mdiobus_read(struct mii_bus *bus, int addr, u32 regnum)
 {
 	int retval;
 
-	if (WARN_ON_ONCE(in_interrupt()))
-		return -EINVAL;
-
 	mutex_lock(&bus->mdio_lock);
 	retval = __mdiobus_read(bus, addr, regnum);
 	mutex_unlock(&bus->mdio_lock);
@@ -879,9 +873,6 @@ int mdiobus_write_nested(struct mii_bus *bus, int addr, u32 regnum, u16 val)
 {
 	int err;
 
-	if (WARN_ON_ONCE(in_interrupt()))
-		return -EINVAL;
-
 	mutex_lock_nested(&bus->mdio_lock, MDIO_MUTEX_NESTED);
 	err = __mdiobus_write(bus, addr, regnum, val);
 	mutex_unlock(&bus->mdio_lock);
@@ -905,9 +896,6 @@ int mdiobus_write(struct mii_bus *bus, int addr, u32 regnum, u16 val)
 {
 	int err;
 
-	if (WARN_ON_ONCE(in_interrupt()))
-		return -EINVAL;
-
 	mutex_lock(&bus->mdio_lock);
 	err = __mdiobus_write(bus, addr, regnum, val);
 	mutex_unlock(&bus->mdio_lock);
@@ -929,9 +917,6 @@ int mdiobus_modify(struct mii_bus *bus, int addr, u32 regnum, u16 mask, u16 set)
 {
 	int err;
 
-	if (WARN_ON_ONCE(in_interrupt()))
-		return -EINVAL;
-
 	mutex_lock(&bus->mdio_lock);
 	err = __mdiobus_modify_changed(bus, addr, regnum, mask, set);
 	mutex_unlock(&bus->mdio_lock);
diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c
index de5b869139d7..8d333d3084ed 100644
--- a/drivers/net/phy/phy-core.c
+++ b/drivers/net/phy/phy-core.c
@@ -6,6 +6,11 @@
 #include <linux/phy.h>
 #include <linux/of.h>
 
+/**
+ * phy_speed_to_str - Return a string representing the PHY link speed
+ *
+ * @speed: Speed of the link
+ */
 const char *phy_speed_to_str(int speed)
 {
 	BUILD_BUG_ON_MSG(__ETHTOOL_LINK_MODE_MASK_NBITS != 92,
@@ -52,6 +57,11 @@ const char *phy_speed_to_str(int speed)
 }
 EXPORT_SYMBOL_GPL(phy_speed_to_str);
 
+/**
+ * phy_duplex_to_str - Return string describing the duplex
+ *
+ * @duplex: Duplex setting to describe
+ */
 const char *phy_duplex_to_str(unsigned int duplex)
 {
 	if (duplex == DUPLEX_HALF)
@@ -252,6 +262,16 @@ static int __set_phy_supported(struct phy_device *phydev, u32 max_speed)
 	return __set_linkmode_max_speed(max_speed, phydev->supported);
 }
 
+/**
+ * phy_set_max_speed - Set the maximum speed the PHY should support
+ *
+ * @phydev: The phy_device struct
+ * @max_speed: Maximum speed
+ *
+ * The PHY might be more capable than the MAC. For example a Fast Ethernet
+ * is connected to a 1G PHY. This function allows the MAC to indicate its
+ * maximum speed, and so limit what the PHY will advertise.
+ */
 int phy_set_max_speed(struct phy_device *phydev, u32 max_speed)
 {
 	int err;
@@ -308,6 +328,16 @@ void of_set_phy_eee_broken(struct phy_device *phydev)
 	phydev->eee_broken_modes = broken;
 }
 
+/**
+ * phy_resolve_aneg_pause - Determine pause autoneg results
+ *
+ * @phydev: The phy_device struct
+ *
+ * Once autoneg has completed the local pause settings can be
+ * resolved.  Determine if pause and asymmetric pause should be used
+ * by the MAC.
+ */
+
 void phy_resolve_aneg_pause(struct phy_device *phydev)
 {
 	if (phydev->duplex == DUPLEX_FULL) {
@@ -321,7 +351,7 @@ void phy_resolve_aneg_pause(struct phy_device *phydev)
 EXPORT_SYMBOL_GPL(phy_resolve_aneg_pause);
 
 /**
- * phy_resolve_aneg_linkmode - resolve the advertisements into phy settings
+ * phy_resolve_aneg_linkmode - resolve the advertisements into PHY settings
  * @phydev: The phy_device struct
  *
  * Resolve our and the link partner advertisements into their corresponding
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 735a806045ac..35525a671400 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -456,7 +456,16 @@ int phy_do_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 }
 EXPORT_SYMBOL(phy_do_ioctl);
 
-/* same as phy_do_ioctl, but ensures that net_device is running */
+/**
+ * phy_do_ioctl_running - generic ndo_do_ioctl implementation but test first
+ *
+ * @dev: the net_device struct
+ * @ifr: &struct ifreq for socket ioctl's
+ * @cmd: ioctl cmd to execute
+ *
+ * Same as phy_do_ioctl, but ensures that net_device is running before
+ * handling the ioctl.
+ */
 int phy_do_ioctl_running(struct net_device *dev, struct ifreq *ifr, int cmd)
 {
 	if (!netif_running(dev))
@@ -466,6 +475,12 @@ int phy_do_ioctl_running(struct net_device *dev, struct ifreq *ifr, int cmd)
 }
 EXPORT_SYMBOL(phy_do_ioctl_running);
 
+/**
+ * phy_queue_state_machine - Trigger the state machine to run soon
+ *
+ * @phydev: the phy_device struct
+ * @jiffies: Run the state machine after these jiffies
+ */
 void phy_queue_state_machine(struct phy_device *phydev, unsigned long jiffies)
 {
 	mod_delayed_work(system_power_efficient_wq, &phydev->state_queue,
@@ -473,6 +488,11 @@ void phy_queue_state_machine(struct phy_device *phydev, unsigned long jiffies)
 }
 EXPORT_SYMBOL(phy_queue_state_machine);
 
+/**
+ * phy_queue_state_machine - Trigger the state machine to run now
+ *
+ * @phydev: the phy_device struct
+ */
 static void phy_trigger_machine(struct phy_device *phydev)
 {
 	phy_queue_state_machine(phydev, 0);
@@ -489,6 +509,12 @@ static void phy_abort_cable_test(struct phy_device *phydev)
 		phydev_err(phydev, "Error while aborting cable test");
 }
 
+/**
+ * phy_ethtool_get_strings - Get the statistic counter names
+ *
+ * @phydev: the phy_device struct
+ * @data: Where to put the strings
+ */
 int phy_ethtool_get_strings(struct phy_device *phydev, u8 *data)
 {
 	if (!phydev->drv)
@@ -502,6 +528,11 @@ int phy_ethtool_get_strings(struct phy_device *phydev, u8 *data)
 }
 EXPORT_SYMBOL(phy_ethtool_get_strings);
 
+/**
+ * phy_ethtool_get_sset_count - Get the number of statistic counters
+ *
+ * @phydev: the phy_device struct
+ */
 int phy_ethtool_get_sset_count(struct phy_device *phydev)
 {
 	int ret;
@@ -523,6 +554,13 @@ int phy_ethtool_get_sset_count(struct phy_device *phydev)
 }
 EXPORT_SYMBOL(phy_ethtool_get_sset_count);
 
+/**
+ * phy_ethtool_get_stats - Get the statistic counters
+ *
+ * @phydev: the phy_device struct
+ * @stats: What counters to get
+ * @data: Where to store the counters
+ */
 int phy_ethtool_get_stats(struct phy_device *phydev,
 			  struct ethtool_stats *stats, u64 *data)
 {
@@ -537,6 +575,12 @@ int phy_ethtool_get_stats(struct phy_device *phydev,
 }
 EXPORT_SYMBOL(phy_ethtool_get_stats);
 
+/**
+ * phy_start_cable_test - Start a cable test
+ *
+ * @phydev: the phy_device struct
+ * @extack: extack for reporting useful error messages
+ */
 int phy_start_cable_test(struct phy_device *phydev,
 			 struct netlink_ext_ack *extack)
 {
@@ -600,6 +644,13 @@ out:
 }
 EXPORT_SYMBOL(phy_start_cable_test);
 
+/**
+ * phy_start_cable_test_tdr - Start a raw TDR cable test
+ *
+ * @phydev: the phy_device struct
+ * @extack: extack for reporting useful error messages
+ * @config: Configuration of the test to run
+ */
 int phy_start_cable_test_tdr(struct phy_device *phydev,
 			     struct netlink_ext_ack *extack,
 			     const struct phy_tdr_config *config)
@@ -996,7 +1047,7 @@ void phy_stop(struct phy_device *phydev)
 {
 	struct net_device *dev = phydev->attached_dev;
 
-	if (!phy_is_started(phydev)) {
+	if (!phy_is_started(phydev) && phydev->state != PHY_DOWN) {
 		WARN(1, "called from state %s\n",
 		     phy_state_to_str(phydev->state));
 		return;
@@ -1363,6 +1414,12 @@ int phy_ethtool_set_eee(struct phy_device *phydev, struct ethtool_eee *data)
 }
 EXPORT_SYMBOL(phy_ethtool_set_eee);
 
+/**
+ * phy_ethtool_set_wol - Configure Wake On LAN
+ *
+ * @phydev: target phy_device struct
+ * @wol: Configuration requested
+ */
 int phy_ethtool_set_wol(struct phy_device *phydev, struct ethtool_wolinfo *wol)
 {
 	if (phydev->drv && phydev->drv->set_wol)
@@ -1372,6 +1429,12 @@ int phy_ethtool_set_wol(struct phy_device *phydev, struct ethtool_wolinfo *wol)
 }
 EXPORT_SYMBOL(phy_ethtool_set_wol);
 
+/**
+ * phy_ethtool_get_wol - Get the current Wake On LAN configuration
+ *
+ * @phydev: target phy_device struct
+ * @wol: Store the current configuration here
+ */
 void phy_ethtool_get_wol(struct phy_device *phydev, struct ethtool_wolinfo *wol)
 {
 	if (phydev->drv && phydev->drv->get_wol)
@@ -1405,6 +1468,10 @@ int phy_ethtool_set_link_ksettings(struct net_device *ndev,
 }
 EXPORT_SYMBOL(phy_ethtool_set_link_ksettings);
 
+/**
+ * phy_ethtool_nway_reset - Restart auto negotiation
+ * @ndev: Network device to restart autoneg for
+ */
 int phy_ethtool_nway_reset(struct net_device *ndev)
 {
 	struct phy_device *phydev = ndev->phydev;
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 8adfbad0a1e8..5dab6be6fc38 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1143,10 +1143,6 @@ int phy_init_hw(struct phy_device *phydev)
 	if (ret < 0)
 		return ret;
 
-	ret = phy_disable_interrupts(phydev);
-	if (ret)
-		return ret;
-
 	if (phydev->drv->config_init)
 		ret = phydev->drv->config_init(phydev);
 
@@ -1423,6 +1419,10 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev,
 	if (err)
 		goto error;
 
+	err = phy_disable_interrupts(phydev);
+	if (err)
+		return err;
+
 	phy_resume(phydev);
 	phy_led_triggers_register(phydev);
 
@@ -1682,7 +1682,8 @@ void phy_detach(struct phy_device *phydev)
 
 	phy_led_triggers_unregister(phydev);
 
-	module_put(phydev->mdio.dev.driver->owner);
+	if (phydev->mdio.dev.driver)
+		module_put(phydev->mdio.dev.driver->owner);
 
 	/* If the device had no specific driver before (i.e. - it
 	 * was using the generic driver), we unbind the device
diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c
index 4bf54cded48a..1af874d36ced 100644
--- a/drivers/net/phy/realtek.c
+++ b/drivers/net/phy/realtek.c
@@ -409,7 +409,7 @@ static int rtlgen_write_mmd(struct phy_device *phydev, int devnum, u16 regnum,
 	return ret;
 }
 
-static int rtl8125_read_mmd(struct phy_device *phydev, int devnum, u16 regnum)
+static int rtl822x_read_mmd(struct phy_device *phydev, int devnum, u16 regnum)
 {
 	int ret = rtlgen_read_mmd(phydev, devnum, regnum);
 
@@ -433,7 +433,7 @@ static int rtl8125_read_mmd(struct phy_device *phydev, int devnum, u16 regnum)
 	return ret;
 }
 
-static int rtl8125_write_mmd(struct phy_device *phydev, int devnum, u16 regnum,
+static int rtl822x_write_mmd(struct phy_device *phydev, int devnum, u16 regnum,
 			     u16 val)
 {
 	int ret = rtlgen_write_mmd(phydev, devnum, regnum, val);
@@ -450,7 +450,7 @@ static int rtl8125_write_mmd(struct phy_device *phydev, int devnum, u16 regnum,
 	return ret;
 }
 
-static int rtl8125_get_features(struct phy_device *phydev)
+static int rtl822x_get_features(struct phy_device *phydev)
 {
 	int val;
 
@@ -468,7 +468,7 @@ static int rtl8125_get_features(struct phy_device *phydev)
 	return genphy_read_abilities(phydev);
 }
 
-static int rtl8125_config_aneg(struct phy_device *phydev)
+static int rtl822x_config_aneg(struct phy_device *phydev)
 {
 	int ret = 0;
 
@@ -488,7 +488,7 @@ static int rtl8125_config_aneg(struct phy_device *phydev)
 	return __genphy_config_aneg(phydev, ret);
 }
 
-static int rtl8125_read_status(struct phy_device *phydev)
+static int rtl822x_read_status(struct phy_device *phydev)
 {
 	int ret;
 
@@ -530,7 +530,7 @@ static int rtlgen_match_phy_device(struct phy_device *phydev)
 	       !rtlgen_supports_2_5gbps(phydev);
 }
 
-static int rtl8125_match_phy_device(struct phy_device *phydev)
+static int rtl8226_match_phy_device(struct phy_device *phydev)
 {
 	return phydev->phy_id == RTL_GENERIC_PHYID &&
 	       rtlgen_supports_2_5gbps(phydev);
@@ -635,29 +635,29 @@ static struct phy_driver realtek_drvs[] = {
 		.read_mmd	= rtlgen_read_mmd,
 		.write_mmd	= rtlgen_write_mmd,
 	}, {
-		.name		= "RTL8125 2.5Gbps internal",
-		.match_phy_device = rtl8125_match_phy_device,
-		.get_features	= rtl8125_get_features,
-		.config_aneg	= rtl8125_config_aneg,
-		.read_status	= rtl8125_read_status,
+		.name		= "RTL8226 2.5Gbps PHY",
+		.match_phy_device = rtl8226_match_phy_device,
+		.get_features	= rtl822x_get_features,
+		.config_aneg	= rtl822x_config_aneg,
+		.read_status	= rtl822x_read_status,
 		.suspend	= genphy_suspend,
 		.resume		= rtlgen_resume,
 		.read_page	= rtl821x_read_page,
 		.write_page	= rtl821x_write_page,
-		.read_mmd	= rtl8125_read_mmd,
-		.write_mmd	= rtl8125_write_mmd,
+		.read_mmd	= rtl822x_read_mmd,
+		.write_mmd	= rtl822x_write_mmd,
 	}, {
 		PHY_ID_MATCH_EXACT(0x001cc840),
-		.name		= "RTL8125B 2.5Gbps internal",
-		.get_features	= rtl8125_get_features,
-		.config_aneg	= rtl8125_config_aneg,
-		.read_status	= rtl8125_read_status,
+		.name		= "RTL8226B_RTL8221B 2.5Gbps PHY",
+		.get_features	= rtl822x_get_features,
+		.config_aneg	= rtl822x_config_aneg,
+		.read_status	= rtl822x_read_status,
 		.suspend	= genphy_suspend,
 		.resume		= rtlgen_resume,
 		.read_page	= rtl821x_read_page,
 		.write_page	= rtl821x_write_page,
-		.read_mmd	= rtl8125_read_mmd,
-		.write_mmd	= rtl8125_write_mmd,
+		.read_mmd	= rtl822x_read_mmd,
+		.write_mmd	= rtl822x_write_mmd,
 	}, {
 		PHY_ID_MATCH_EXACT(0x001cc961),
 		.name		= "RTL8366RB Gigabit Ethernet",
diff --git a/drivers/net/phy/spi_ks8995.c b/drivers/net/phy/spi_ks8995.c
index 7475cef17cf7..ca49c1ad3efc 100644
--- a/drivers/net/phy/spi_ks8995.c
+++ b/drivers/net/phy/spi_ks8995.c
@@ -300,7 +300,7 @@ static ssize_t ks8995_registers_read(struct file *filp, struct kobject *kobj,
 	struct device *dev;
 	struct ks8995_switch *ks8995;
 
-	dev = container_of(kobj, struct device, kobj);
+	dev = kobj_to_dev(kobj);
 	ks8995 = dev_get_drvdata(dev);
 
 	return ks8995_read(ks8995, buf, off, count);
@@ -312,7 +312,7 @@ static ssize_t ks8995_registers_write(struct file *filp, struct kobject *kobj,
 	struct device *dev;
 	struct ks8995_switch *ks8995;
 
-	dev = container_of(kobj, struct device, kobj);
+	dev = kobj_to_dev(kobj);
 	ks8995 = dev_get_drvdata(dev);
 
 	return ks8995_write(ks8995, buf, off, count);
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 8c1e02752ff6..a0c8c2fe6c3e 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -2795,7 +2795,7 @@ static int team_nl_cmd_port_list_get(struct sk_buff *skb,
 	return err;
 }
 
-static const struct genl_ops team_nl_ops[] = {
+static const struct genl_small_ops team_nl_ops[] = {
 	{
 		.cmd = TEAM_CMD_NOOP,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
@@ -2832,8 +2832,8 @@ static struct genl_family team_nl_family __ro_after_init = {
 	.policy = team_nl_policy,
 	.netnsok	= true,
 	.module		= THIS_MODULE,
-	.ops		= team_nl_ops,
-	.n_ops		= ARRAY_SIZE(team_nl_ops),
+	.small_ops	= team_nl_ops,
+	.n_small_ops	= ARRAY_SIZE(team_nl_ops),
 	.mcgrps		= team_nl_mcgrps,
 	.n_mcgrps	= ARRAY_SIZE(team_nl_mcgrps),
 };
diff --git a/drivers/net/usb/kaweth.c b/drivers/net/usb/kaweth.c
index ed01dc964c99..144c686b4333 100644
--- a/drivers/net/usb/kaweth.c
+++ b/drivers/net/usb/kaweth.c
@@ -103,10 +103,6 @@ static int kaweth_probe(
 		const struct usb_device_id *id	/* from id_table */
 	);
 static void kaweth_disconnect(struct usb_interface *intf);
-static int kaweth_internal_control_msg(struct usb_device *usb_dev,
-				       unsigned int pipe,
-				       struct usb_ctrlrequest *cmd, void *data,
-				       int len, int timeout);
 static int kaweth_suspend(struct usb_interface *intf, pm_message_t message);
 static int kaweth_resume(struct usb_interface *intf);
 
@@ -236,65 +232,17 @@ struct kaweth_device
 };
 
 /****************************************************************
- *     kaweth_control
- ****************************************************************/
-static int kaweth_control(struct kaweth_device *kaweth,
-			  unsigned int pipe,
-			  __u8 request,
-			  __u8 requesttype,
-			  __u16 value,
-			  __u16 index,
-			  void *data,
-			  __u16 size,
-			  int timeout)
-{
-	struct usb_ctrlrequest *dr;
-	int retval;
-
-	if(in_interrupt()) {
-		netdev_dbg(kaweth->net, "in_interrupt()\n");
-		return -EBUSY;
-	}
-
-	dr = kmalloc(sizeof(struct usb_ctrlrequest), GFP_ATOMIC);
-	if (!dr)
-		return -ENOMEM;
-
-	dr->bRequestType = requesttype;
-	dr->bRequest = request;
-	dr->wValue = cpu_to_le16(value);
-	dr->wIndex = cpu_to_le16(index);
-	dr->wLength = cpu_to_le16(size);
-
-	retval = kaweth_internal_control_msg(kaweth->dev,
-					     pipe,
-					     dr,
-					     data,
-					     size,
-					     timeout);
-
-	kfree(dr);
-	return retval;
-}
-
-/****************************************************************
  *     kaweth_read_configuration
  ****************************************************************/
 static int kaweth_read_configuration(struct kaweth_device *kaweth)
 {
-	int retval;
-
-	retval = kaweth_control(kaweth,
-				usb_rcvctrlpipe(kaweth->dev, 0),
+	return usb_control_msg(kaweth->dev, usb_rcvctrlpipe(kaweth->dev, 0),
 				KAWETH_COMMAND_GET_ETHERNET_DESC,
 				USB_TYPE_VENDOR | USB_DIR_IN | USB_RECIP_DEVICE,
-				0,
-				0,
-				(void *)&kaweth->configuration,
+				0, 0,
+				&kaweth->configuration,
 				sizeof(kaweth->configuration),
 				KAWETH_CONTROL_TIMEOUT);
-
-	return retval;
 }
 
 /****************************************************************
@@ -302,21 +250,14 @@ static int kaweth_read_configuration(struct kaweth_device *kaweth)
  ****************************************************************/
 static int kaweth_set_urb_size(struct kaweth_device *kaweth, __u16 urb_size)
 {
-	int retval;
-
 	netdev_dbg(kaweth->net, "Setting URB size to %d\n", (unsigned)urb_size);
 
-	retval = kaweth_control(kaweth,
-				usb_sndctrlpipe(kaweth->dev, 0),
-				KAWETH_COMMAND_SET_URB_SIZE,
-				USB_TYPE_VENDOR | USB_DIR_OUT | USB_RECIP_DEVICE,
-				urb_size,
-				0,
-				(void *)&kaweth->scratch,
-				0,
-				KAWETH_CONTROL_TIMEOUT);
-
-	return retval;
+	return usb_control_msg(kaweth->dev, usb_sndctrlpipe(kaweth->dev, 0),
+			       KAWETH_COMMAND_SET_URB_SIZE,
+			       USB_TYPE_VENDOR | USB_DIR_OUT | USB_RECIP_DEVICE,
+			       urb_size, 0,
+			       &kaweth->scratch, 0,
+			       KAWETH_CONTROL_TIMEOUT);
 }
 
 /****************************************************************
@@ -324,21 +265,14 @@ static int kaweth_set_urb_size(struct kaweth_device *kaweth, __u16 urb_size)
  ****************************************************************/
 static int kaweth_set_sofs_wait(struct kaweth_device *kaweth, __u16 sofs_wait)
 {
-	int retval;
-
 	netdev_dbg(kaweth->net, "Set SOFS wait to %d\n", (unsigned)sofs_wait);
 
-	retval = kaweth_control(kaweth,
-				usb_sndctrlpipe(kaweth->dev, 0),
-				KAWETH_COMMAND_SET_SOFS_WAIT,
-				USB_TYPE_VENDOR | USB_DIR_OUT | USB_RECIP_DEVICE,
-				sofs_wait,
-				0,
-				(void *)&kaweth->scratch,
-				0,
-				KAWETH_CONTROL_TIMEOUT);
-
-	return retval;
+	return usb_control_msg(kaweth->dev, usb_sndctrlpipe(kaweth->dev, 0),
+			       KAWETH_COMMAND_SET_SOFS_WAIT,
+			       USB_TYPE_VENDOR | USB_DIR_OUT | USB_RECIP_DEVICE,
+			       sofs_wait, 0,
+			       &kaweth->scratch, 0,
+			       KAWETH_CONTROL_TIMEOUT);
 }
 
 /****************************************************************
@@ -347,22 +281,15 @@ static int kaweth_set_sofs_wait(struct kaweth_device *kaweth, __u16 sofs_wait)
 static int kaweth_set_receive_filter(struct kaweth_device *kaweth,
 				     __u16 receive_filter)
 {
-	int retval;
-
 	netdev_dbg(kaweth->net, "Set receive filter to %d\n",
 		   (unsigned)receive_filter);
 
-	retval = kaweth_control(kaweth,
-				usb_sndctrlpipe(kaweth->dev, 0),
-				KAWETH_COMMAND_SET_PACKET_FILTER,
-				USB_TYPE_VENDOR | USB_DIR_OUT | USB_RECIP_DEVICE,
-				receive_filter,
-				0,
-				(void *)&kaweth->scratch,
-				0,
-				KAWETH_CONTROL_TIMEOUT);
-
-	return retval;
+	return usb_control_msg(kaweth->dev, usb_sndctrlpipe(kaweth->dev, 0),
+			       KAWETH_COMMAND_SET_PACKET_FILTER,
+			       USB_TYPE_VENDOR | USB_DIR_OUT | USB_RECIP_DEVICE,
+			       receive_filter, 0,
+			       &kaweth->scratch, 0,
+			       KAWETH_CONTROL_TIMEOUT);
 }
 
 /****************************************************************
@@ -407,14 +334,11 @@ static int kaweth_download_firmware(struct kaweth_device *kaweth,
 		   kaweth->firmware_buf, kaweth);
 	netdev_dbg(kaweth->net, "Firmware length: %d\n", data_len);
 
-	return kaweth_control(kaweth,
-		              usb_sndctrlpipe(kaweth->dev, 0),
+	return usb_control_msg(kaweth->dev, usb_sndctrlpipe(kaweth->dev, 0),
 			      KAWETH_COMMAND_SCAN,
 			      USB_TYPE_VENDOR | USB_DIR_OUT | USB_RECIP_DEVICE,
-			      0,
-			      0,
-			      (void *)kaweth->firmware_buf,
-			      data_len,
+			      0, 0,
+			      kaweth->firmware_buf, data_len,
 			      KAWETH_CONTROL_TIMEOUT);
 }
 
@@ -433,15 +357,12 @@ static int kaweth_trigger_firmware(struct kaweth_device *kaweth,
 	kaweth->firmware_buf[6] = 0x00;
 	kaweth->firmware_buf[7] = 0x00;
 
-	return kaweth_control(kaweth,
-			      usb_sndctrlpipe(kaweth->dev, 0),
-			      KAWETH_COMMAND_SCAN,
-			      USB_TYPE_VENDOR | USB_DIR_OUT | USB_RECIP_DEVICE,
-			      0,
-			      0,
-			      (void *)kaweth->firmware_buf,
-			      8,
-			      KAWETH_CONTROL_TIMEOUT);
+	return usb_control_msg(kaweth->dev, usb_sndctrlpipe(kaweth->dev, 0),
+			       KAWETH_COMMAND_SCAN,
+			       USB_TYPE_VENDOR | USB_DIR_OUT | USB_RECIP_DEVICE,
+			       0, 0,
+			       (void *)kaweth->firmware_buf, 8,
+			       KAWETH_CONTROL_TIMEOUT);
 }
 
 /****************************************************************
@@ -564,7 +485,8 @@ static int kaweth_resubmit_rx_urb(struct kaweth_device *kaweth,
 	return result;
 }
 
-static void kaweth_async_set_rx_mode(struct kaweth_device *kaweth);
+static void kaweth_async_set_rx_mode(struct kaweth_device *kaweth,
+				     bool may_sleep);
 
 /****************************************************************
  *     kaweth_usb_receive
@@ -694,7 +616,7 @@ static int kaweth_open(struct net_device *net)
 
 	netif_start_queue(net);
 
-	kaweth_async_set_rx_mode(kaweth);
+	kaweth_async_set_rx_mode(kaweth, true);
 	return 0;
 
 err_out:
@@ -782,7 +704,7 @@ static netdev_tx_t kaweth_start_xmit(struct sk_buff *skb,
 
 	spin_lock_irq(&kaweth->device_lock);
 
-	kaweth_async_set_rx_mode(kaweth);
+	kaweth_async_set_rx_mode(kaweth, false);
 	netif_stop_queue(net);
 	if (IS_BLOCKED(kaweth->status)) {
 		goto skip;
@@ -859,36 +781,31 @@ static void kaweth_set_rx_mode(struct net_device *net)
 /****************************************************************
  *     kaweth_async_set_rx_mode
  ****************************************************************/
-static void kaweth_async_set_rx_mode(struct kaweth_device *kaweth)
+static void kaweth_async_set_rx_mode(struct kaweth_device *kaweth,
+				     bool may_sleep)
 {
-	int result;
+	int ret;
 	__u16 packet_filter_bitmap = kaweth->packet_filter_bitmap;
 
 	kaweth->packet_filter_bitmap = 0;
 	if (packet_filter_bitmap == 0)
 		return;
 
-	if (in_interrupt())
+	if (!may_sleep)
 		return;
 
-	result = kaweth_control(kaweth,
-				usb_sndctrlpipe(kaweth->dev, 0),
-				KAWETH_COMMAND_SET_PACKET_FILTER,
-				USB_TYPE_VENDOR | USB_DIR_OUT | USB_RECIP_DEVICE,
-				packet_filter_bitmap,
-				0,
-				(void *)&kaweth->scratch,
-				0,
-				KAWETH_CONTROL_TIMEOUT);
-
-	if(result < 0) {
+	ret = usb_control_msg(kaweth->dev, usb_sndctrlpipe(kaweth->dev, 0),
+			      KAWETH_COMMAND_SET_PACKET_FILTER,
+			      USB_TYPE_VENDOR | USB_DIR_OUT | USB_RECIP_DEVICE,
+			      packet_filter_bitmap, 0,
+			      &kaweth->scratch, 0,
+			      KAWETH_CONTROL_TIMEOUT);
+	if (ret < 0)
 		dev_err(&kaweth->intf->dev, "Failed to set Rx mode: %d\n",
-			result);
-	}
-	else {
+			ret);
+	else
 		netdev_dbg(kaweth->net, "Set Rx mode to %d\n",
 			   packet_filter_bitmap);
-	}
 }
 
 /****************************************************************
@@ -1196,88 +1113,4 @@ static void kaweth_disconnect(struct usb_interface *intf)
 }
 
 
-// FIXME this completion stuff is a modified clone of
-// an OLD version of some stuff in usb.c ...
-struct usb_api_data {
-	wait_queue_head_t wqh;
-	int done;
-};
-
-/*-------------------------------------------------------------------*
- * completion handler for compatibility wrappers (sync control/bulk) *
- *-------------------------------------------------------------------*/
-static void usb_api_blocking_completion(struct urb *urb)
-{
-        struct usb_api_data *awd = (struct usb_api_data *)urb->context;
-
-	awd->done=1;
-	wake_up(&awd->wqh);
-}
-
-/*-------------------------------------------------------------------*
- *                         COMPATIBILITY STUFF                       *
- *-------------------------------------------------------------------*/
-
-// Starts urb and waits for completion or timeout
-static int usb_start_wait_urb(struct urb *urb, int timeout, int* actual_length)
-{
-	struct usb_api_data awd;
-        int status;
-
-        init_waitqueue_head(&awd.wqh);
-        awd.done = 0;
-
-        urb->context = &awd;
-        status = usb_submit_urb(urb, GFP_ATOMIC);
-        if (status) {
-                // something went wrong
-                usb_free_urb(urb);
-                return status;
-        }
-
-	if (!wait_event_timeout(awd.wqh, awd.done, timeout)) {
-                // timeout
-                dev_warn(&urb->dev->dev, "usb_control/bulk_msg: timeout\n");
-                usb_kill_urb(urb);  // remove urb safely
-                status = -ETIMEDOUT;
-        }
-	else {
-                status = urb->status;
-	}
-
-        if (actual_length) {
-                *actual_length = urb->actual_length;
-	}
-
-        usb_free_urb(urb);
-        return status;
-}
-
-/*-------------------------------------------------------------------*/
-// returns status (negative) or length (positive)
-static int kaweth_internal_control_msg(struct usb_device *usb_dev,
-				       unsigned int pipe,
-				       struct usb_ctrlrequest *cmd, void *data,
-				       int len, int timeout)
-{
-        struct urb *urb;
-        int retv;
-        int length = 0; /* shut up GCC */
-
-	urb = usb_alloc_urb(0, GFP_ATOMIC);
-        if (!urb)
-                return -ENOMEM;
-
-        usb_fill_control_urb(urb, usb_dev, pipe, (unsigned char*)cmd, data,
-			 len, usb_api_blocking_completion, NULL);
-
-        retv = usb_start_wait_urb(urb, timeout, &length);
-        if (retv < 0) {
-                return retv;
-	}
-        else {
-                return length;
-	}
-}
-
 module_usb_driver(kaweth_driver);
diff --git a/drivers/net/usb/net1080.c b/drivers/net/usb/net1080.c
index 1f04f1720426..b0c0c9dd6a02 100644
--- a/drivers/net/usb/net1080.c
+++ b/drivers/net/usb/net1080.c
@@ -113,7 +113,6 @@ nc_register_read(struct usbnet *dev, u8 regnum, u16 *retval_ptr)
 	return nc_vendor_read(dev, REQUEST_REGISTER, regnum, retval_ptr);
 }
 
-// no retval ... can become async, usable in_interrupt()
 static void
 nc_vendor_write(struct usbnet *dev, u8 req, u8 regnum, u16 value)
 {
diff --git a/drivers/net/usb/rndis_host.c b/drivers/net/usb/rndis_host.c
index bd9c07888ebb..6fa7a009a24a 100644
--- a/drivers/net/usb/rndis_host.c
+++ b/drivers/net/usb/rndis_host.c
@@ -201,7 +201,7 @@ int rndis_command(struct usbnet *dev, struct rndis_msg_hdr *buf, int buflen)
 			dev_dbg(&info->control->dev,
 				"rndis response error, code %d\n", retval);
 		}
-		msleep(20);
+		msleep(40);
 	}
 	dev_dbg(&info->control->dev, "rndis response timeout\n");
 	return -ETIMEDOUT;
diff --git a/drivers/net/usb/smsc75xx.c b/drivers/net/usb/smsc75xx.c
index 9556d431885f..8689835a5214 100644
--- a/drivers/net/usb/smsc75xx.c
+++ b/drivers/net/usb/smsc75xx.c
@@ -757,13 +757,14 @@ static int smsc75xx_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd)
 
 static void smsc75xx_init_mac_address(struct usbnet *dev)
 {
-	const u8 *mac_addr;
-
 	/* maybe the boot loader passed the MAC address in devicetree */
-	mac_addr = of_get_mac_address(dev->udev->dev.of_node);
-	if (!IS_ERR(mac_addr)) {
-		ether_addr_copy(dev->net->dev_addr, mac_addr);
-		return;
+	if (!eth_platform_get_mac_address(&dev->udev->dev,
+			dev->net->dev_addr)) {
+		if (is_valid_ether_addr(dev->net->dev_addr)) {
+			/* device tree values are valid so use them */
+			netif_dbg(dev, ifup, dev->net, "MAC address read from the device tree\n");
+			return;
+		}
 	}
 
 	/* try reading mac address from EEPROM */
diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c
index 601fb40a2a0a..ea0d5f04dc3a 100644
--- a/drivers/net/usb/smsc95xx.c
+++ b/drivers/net/usb/smsc95xx.c
@@ -755,13 +755,14 @@ static int smsc95xx_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd)
 
 static void smsc95xx_init_mac_address(struct usbnet *dev)
 {
-	const u8 *mac_addr;
-
 	/* maybe the boot loader passed the MAC address in devicetree */
-	mac_addr = of_get_mac_address(dev->udev->dev.of_node);
-	if (!IS_ERR(mac_addr)) {
-		ether_addr_copy(dev->net->dev_addr, mac_addr);
-		return;
+	if (!eth_platform_get_mac_address(&dev->udev->dev,
+			dev->net->dev_addr)) {
+		if (is_valid_ether_addr(dev->net->dev_addr)) {
+			/* device tree values are valid so use them */
+			netif_dbg(dev, ifup, dev->net, "MAC address read from the device tree\n");
+			return;
+		}
 	}
 
 	/* try reading mac address from EEPROM */
diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index 2b2a841cd938..bf6c58240bd4 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -597,7 +597,7 @@ static void rx_complete (struct urb *urb)
 	case -EPIPE:
 		dev->net->stats.rx_errors++;
 		usbnet_defer_kevent (dev, EVENT_RX_HALT);
-		// FALLTHROUGH
+		fallthrough;
 
 	/* software-driven interface shutdown */
 	case -ECONNRESET:		/* async unlink */
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index b9fefe27e3e8..be3bf233a809 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -190,8 +190,9 @@ static inline struct vxlan_rdst *first_remote_rtnl(struct vxlan_fdb *fdb)
 	return list_first_entry(&fdb->remotes, struct vxlan_rdst, list);
 }
 
-/* Find VXLAN socket based on network namespace, address family and UDP port
- * and enabled unshareable flags.
+/* Find VXLAN socket based on network namespace, address family, UDP port,
+ * enabled unshareable flags and socket device binding (see l3mdev with
+ * non-default VRF).
  */
 static struct vxlan_sock *vxlan_find_sock(struct net *net, sa_family_t family,
 					  __be16 port, u32 flags, int ifindex)
@@ -1875,6 +1876,10 @@ static int vxlan_rcv(struct sock *sk, struct sk_buff *skb)
 				   !net_eq(vxlan->net, dev_net(vxlan->dev))))
 		goto drop;
 
+	if (vs->flags & VXLAN_F_REMCSUM_RX)
+		if (unlikely(!vxlan_remcsum(&unparsed, skb, vs->flags)))
+			goto drop;
+
 	if (vxlan_collect_metadata(vs)) {
 		struct metadata_dst *tun_dst;
 
@@ -1891,9 +1896,6 @@ static int vxlan_rcv(struct sock *sk, struct sk_buff *skb)
 		memset(md, 0, sizeof(*md));
 	}
 
-	if (vs->flags & VXLAN_F_REMCSUM_RX)
-		if (!vxlan_remcsum(&unparsed, skb, vs->flags))
-			goto drop;
 	if (vs->flags & VXLAN_F_GBP)
 		vxlan_parse_gbp_hdr(&unparsed, skb, vs->flags, md);
 	/* Note that GBP and GPE can never be active together. This is
@@ -3890,7 +3892,7 @@ static int __vxlan_dev_create(struct net *net, struct net_device *dev,
 	}
 
 	err = rtnl_configure_link(dev, NULL);
-	if (err)
+	if (err < 0)
 		goto unlink;
 
 	if (f) {
diff --git a/drivers/net/wan/hdlc_cisco.c b/drivers/net/wan/hdlc_cisco.c
index 444130655d8e..cb5898f7d68c 100644
--- a/drivers/net/wan/hdlc_cisco.c
+++ b/drivers/net/wan/hdlc_cisco.c
@@ -118,6 +118,7 @@ static void cisco_keepalive_send(struct net_device *dev, u32 type,
 	skb_put(skb, sizeof(struct cisco_packet));
 	skb->priority = TC_PRIO_CONTROL;
 	skb->dev = dev;
+	skb->protocol = htons(ETH_P_HDLC);
 	skb_reset_network_header(skb);
 
 	dev_queue_xmit(skb);
diff --git a/drivers/net/wan/hdlc_fr.c b/drivers/net/wan/hdlc_fr.c
index 9acad651ea1f..3a44dad87602 100644
--- a/drivers/net/wan/hdlc_fr.c
+++ b/drivers/net/wan/hdlc_fr.c
@@ -273,63 +273,69 @@ static inline struct net_device **get_dev_p(struct pvc_device *pvc,
 
 static int fr_hard_header(struct sk_buff **skb_p, u16 dlci)
 {
-	u16 head_len;
 	struct sk_buff *skb = *skb_p;
 
-	switch (skb->protocol) {
-	case cpu_to_be16(NLPID_CCITT_ANSI_LMI):
-		head_len = 4;
-		skb_push(skb, head_len);
-		skb->data[3] = NLPID_CCITT_ANSI_LMI;
-		break;
-
-	case cpu_to_be16(NLPID_CISCO_LMI):
-		head_len = 4;
-		skb_push(skb, head_len);
-		skb->data[3] = NLPID_CISCO_LMI;
-		break;
-
-	case cpu_to_be16(ETH_P_IP):
-		head_len = 4;
-		skb_push(skb, head_len);
-		skb->data[3] = NLPID_IP;
-		break;
-
-	case cpu_to_be16(ETH_P_IPV6):
-		head_len = 4;
-		skb_push(skb, head_len);
-		skb->data[3] = NLPID_IPV6;
-		break;
-
-	case cpu_to_be16(ETH_P_802_3):
-		head_len = 10;
-		if (skb_headroom(skb) < head_len) {
-			struct sk_buff *skb2 = skb_realloc_headroom(skb,
-								    head_len);
+	if (!skb->dev) { /* Control packets */
+		switch (dlci) {
+		case LMI_CCITT_ANSI_DLCI:
+			skb_push(skb, 4);
+			skb->data[3] = NLPID_CCITT_ANSI_LMI;
+			break;
+
+		case LMI_CISCO_DLCI:
+			skb_push(skb, 4);
+			skb->data[3] = NLPID_CISCO_LMI;
+			break;
+
+		default:
+			return -EINVAL;
+		}
+
+	} else if (skb->dev->type == ARPHRD_DLCI) {
+		switch (skb->protocol) {
+		case htons(ETH_P_IP):
+			skb_push(skb, 4);
+			skb->data[3] = NLPID_IP;
+			break;
+
+		case htons(ETH_P_IPV6):
+			skb_push(skb, 4);
+			skb->data[3] = NLPID_IPV6;
+			break;
+
+		default:
+			skb_push(skb, 10);
+			skb->data[3] = FR_PAD;
+			skb->data[4] = NLPID_SNAP;
+			/* OUI 00-00-00 indicates an Ethertype follows */
+			skb->data[5] = 0x00;
+			skb->data[6] = 0x00;
+			skb->data[7] = 0x00;
+			/* This should be an Ethertype: */
+			*(__be16 *)(skb->data + 8) = skb->protocol;
+		}
+
+	} else if (skb->dev->type == ARPHRD_ETHER) {
+		if (skb_headroom(skb) < 10) {
+			struct sk_buff *skb2 = skb_realloc_headroom(skb, 10);
 			if (!skb2)
 				return -ENOBUFS;
 			dev_kfree_skb(skb);
 			skb = *skb_p = skb2;
 		}
-		skb_push(skb, head_len);
+		skb_push(skb, 10);
 		skb->data[3] = FR_PAD;
 		skb->data[4] = NLPID_SNAP;
-		skb->data[5] = FR_PAD;
+		/* OUI 00-80-C2 stands for the 802.1 organization */
+		skb->data[5] = 0x00;
 		skb->data[6] = 0x80;
 		skb->data[7] = 0xC2;
+		/* PID 00-07 stands for Ethernet frames without FCS */
 		skb->data[8] = 0x00;
-		skb->data[9] = 0x07; /* bridged Ethernet frame w/out FCS */
-		break;
+		skb->data[9] = 0x07;
 
-	default:
-		head_len = 10;
-		skb_push(skb, head_len);
-		skb->data[3] = FR_PAD;
-		skb->data[4] = NLPID_SNAP;
-		skb->data[5] = FR_PAD;
-		skb->data[6] = FR_PAD;
-		skb->data[7] = FR_PAD;
-		*(__be16*)(skb->data + 8) = skb->protocol;
+	} else {
+		return -EINVAL;
 	}
 
 	dlci_to_q922(skb->data, dlci);
@@ -425,14 +431,16 @@ static netdev_tx_t pvc_xmit(struct sk_buff *skb, struct net_device *dev)
 				skb_put(skb, pad);
 				memset(skb->data + len, 0, pad);
 			}
-			skb->protocol = cpu_to_be16(ETH_P_802_3);
 		}
+		skb->dev = dev;
 		if (!fr_hard_header(&skb, pvc->dlci)) {
 			dev->stats.tx_bytes += skb->len;
 			dev->stats.tx_packets++;
 			if (pvc->state.fecn) /* TX Congestion counter */
 				dev->stats.tx_compressed++;
 			skb->dev = pvc->frad;
+			skb->protocol = htons(ETH_P_HDLC);
+			skb_reset_network_header(skb);
 			dev_queue_xmit(skb);
 			return NETDEV_TX_OK;
 		}
@@ -492,10 +500,8 @@ static void fr_lmi_send(struct net_device *dev, int fullrep)
 	memset(skb->data, 0, len);
 	skb_reserve(skb, 4);
 	if (lmi == LMI_CISCO) {
-		skb->protocol = cpu_to_be16(NLPID_CISCO_LMI);
 		fr_hard_header(&skb, LMI_CISCO_DLCI);
 	} else {
-		skb->protocol = cpu_to_be16(NLPID_CCITT_ANSI_LMI);
 		fr_hard_header(&skb, LMI_CCITT_ANSI_DLCI);
 	}
 	data = skb_tail_pointer(skb);
@@ -555,6 +561,7 @@ static void fr_lmi_send(struct net_device *dev, int fullrep)
 	skb_put(skb, i);
 	skb->priority = TC_PRIO_CONTROL;
 	skb->dev = dev;
+	skb->protocol = htons(ETH_P_HDLC);
 	skb_reset_network_header(skb);
 
 	dev_queue_xmit(skb);
@@ -1041,7 +1048,7 @@ static void pvc_setup(struct net_device *dev)
 {
 	dev->type = ARPHRD_DLCI;
 	dev->flags = IFF_POINTOPOINT;
-	dev->hard_header_len = 10;
+	dev->hard_header_len = 0;
 	dev->addr_len = 2;
 	netif_keep_dst(dev);
 }
@@ -1093,6 +1100,7 @@ static int fr_add_pvc(struct net_device *frad, unsigned int dlci, int type)
 	dev->mtu = HDLC_MAX_MTU;
 	dev->min_mtu = 68;
 	dev->max_mtu = HDLC_MAX_MTU;
+	dev->needed_headroom = 10;
 	dev->priv_flags |= IFF_NO_QUEUE;
 	dev->ml_priv = pvc;
 
diff --git a/drivers/net/wan/hdlc_ppp.c b/drivers/net/wan/hdlc_ppp.c
index 48ced3912576..64f855651336 100644
--- a/drivers/net/wan/hdlc_ppp.c
+++ b/drivers/net/wan/hdlc_ppp.c
@@ -251,6 +251,7 @@ static void ppp_tx_cp(struct net_device *dev, u16 pid, u8 code,
 
 	skb->priority = TC_PRIO_CONTROL;
 	skb->dev = dev;
+	skb->protocol = htons(ETH_P_HDLC);
 	skb_reset_network_header(skb);
 	skb_queue_tail(&tx_queue, skb);
 }
@@ -383,11 +384,8 @@ static void ppp_cp_parse_cr(struct net_device *dev, u16 pid, u8 id,
 	}
 
 	for (opt = data; len; len -= opt[1], opt += opt[1]) {
-		if (len < 2 || len < opt[1]) {
-			dev->stats.rx_errors++;
-			kfree(out);
-			return; /* bad packet, drop silently */
-		}
+		if (len < 2 || opt[1] < 2 || len < opt[1])
+			goto err_out;
 
 		if (pid == PID_LCP)
 			switch (opt[0]) {
@@ -395,6 +393,8 @@ static void ppp_cp_parse_cr(struct net_device *dev, u16 pid, u8 id,
 				continue; /* MRU always OK and > 1500 bytes? */
 
 			case LCP_OPTION_ACCM: /* async control character map */
+				if (opt[1] < sizeof(valid_accm))
+					goto err_out;
 				if (!memcmp(opt, valid_accm,
 					    sizeof(valid_accm)))
 					continue;
@@ -406,6 +406,8 @@ static void ppp_cp_parse_cr(struct net_device *dev, u16 pid, u8 id,
 				}
 				break;
 			case LCP_OPTION_MAGIC:
+				if (len < 6)
+					goto err_out;
 				if (opt[1] != 6 || (!opt[2] && !opt[3] &&
 						    !opt[4] && !opt[5]))
 					break; /* reject invalid magic number */
@@ -424,6 +426,11 @@ static void ppp_cp_parse_cr(struct net_device *dev, u16 pid, u8 id,
 		ppp_cp_event(dev, pid, RCR_GOOD, CP_CONF_ACK, id, req_len, data);
 
 	kfree(out);
+	return;
+
+err_out:
+	dev->stats.rx_errors++;
+	kfree(out);
 }
 
 static int ppp_rx(struct sk_buff *skb)
diff --git a/drivers/net/wan/lapbether.c b/drivers/net/wan/lapbether.c
index 732a6c1851f5..b6be2454b8bd 100644
--- a/drivers/net/wan/lapbether.c
+++ b/drivers/net/wan/lapbether.c
@@ -198,8 +198,6 @@ static void lapbeth_data_transmit(struct net_device *ndev, struct sk_buff *skb)
 	struct net_device *dev;
 	int size = skb->len;
 
-	skb->protocol = htons(ETH_P_X25);
-
 	ptr = skb_push(skb, 2);
 
 	*ptr++ = size % 256;
@@ -210,6 +208,8 @@ static void lapbeth_data_transmit(struct net_device *ndev, struct sk_buff *skb)
 
 	skb->dev = dev = lapbeth->ethdev;
 
+	skb->protocol = htons(ETH_P_DEC);
+
 	skb_reset_network_header(skb);
 
 	dev_hard_header(skb, dev, ETH_P_DEC, bcast_addr, NULL, 0);
diff --git a/drivers/net/wan/lmc/lmc_debug.c b/drivers/net/wan/lmc/lmc_debug.c
index f999db788506..2b6051bda3fb 100644
--- a/drivers/net/wan/lmc/lmc_debug.c
+++ b/drivers/net/wan/lmc/lmc_debug.c
@@ -62,22 +62,4 @@ void lmcEventLog(u32 EventNum, u32 arg2, u32 arg3)
 }
 #endif  /*  DEBUG  */
 
-void lmc_trace(struct net_device *dev, char *msg){
-#ifdef LMC_TRACE
-    unsigned long j = jiffies + 3; /* Wait for 50 ms */
-
-    if(in_interrupt()){
-        printk("%s: * %s\n", dev->name, msg);
-//        while(time_before(jiffies, j+10))
-//            ;
-    }
-    else {
-        printk("%s: %s\n", dev->name, msg);
-        while(time_before(jiffies, j))
-            schedule();
-    }
-#endif
-}
-
-
 /* --------------------------- end if_lmc_linux.c ------------------------ */
diff --git a/drivers/net/wan/lmc/lmc_debug.h b/drivers/net/wan/lmc/lmc_debug.h
index 820adcae5d67..cfae9eddf003 100644
--- a/drivers/net/wan/lmc/lmc_debug.h
+++ b/drivers/net/wan/lmc/lmc_debug.h
@@ -48,6 +48,5 @@ extern u32 lmcEventLogBuf[LMC_EVENTLOGSIZE * LMC_EVENTLOGARGS];
 
 void lmcConsoleLog(char *type, unsigned char *ucData, int iLen);
 void lmcEventLog(u32 EventNum, u32 arg2, u32 arg3);
-void lmc_trace(struct net_device *dev, char *msg);
 
 #endif
diff --git a/drivers/net/wan/lmc/lmc_main.c b/drivers/net/wan/lmc/lmc_main.c
index 842def21e089..36600b0a0ab0 100644
--- a/drivers/net/wan/lmc/lmc_main.c
+++ b/drivers/net/wan/lmc/lmc_main.c
@@ -113,8 +113,6 @@ int lmc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) /*fold00*/
     u16 regVal;
     unsigned long flags;
 
-    lmc_trace(dev, "lmc_ioctl in");
-
     /*
      * Most functions mess with the structure
      * Disable interrupts while we do the polling
@@ -619,8 +617,6 @@ int lmc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) /*fold00*/
         break;
     }
 
-    lmc_trace(dev, "lmc_ioctl out");
-
     return ret;
 }
 
@@ -634,8 +630,6 @@ static void lmc_watchdog(struct timer_list *t) /*fold00*/
     u32 ticks;
     unsigned long flags;
 
-    lmc_trace(dev, "lmc_watchdog in");
-
     spin_lock_irqsave(&sc->lmc_lock, flags);
 
     if(sc->check != 0xBEAFCAFE){
@@ -782,9 +776,6 @@ kick_timer:
     add_timer (&sc->timer);
 
     spin_unlock_irqrestore(&sc->lmc_lock, flags);
-
-    lmc_trace(dev, "lmc_watchdog out");
-
 }
 
 static int lmc_attach(struct net_device *dev, unsigned short encoding,
@@ -813,8 +804,6 @@ static int lmc_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	int err;
 	static int cards_found;
 
-	/* lmc_trace(dev, "lmc_init_one in"); */
-
 	err = pcim_enable_device(pdev);
 	if (err) {
 		printk(KERN_ERR "lmc: pci enable failed: %d\n", err);
@@ -955,7 +944,6 @@ static int lmc_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
     sc->lmc_ok = 0;
     sc->last_link_status = 0;
 
-    lmc_trace(dev, "lmc_init_one out");
     return 0;
 }
 
@@ -981,8 +969,6 @@ static int lmc_open(struct net_device *dev)
     lmc_softc_t *sc = dev_to_sc(dev);
     int err;
 
-    lmc_trace(dev, "lmc_open in");
-
     lmc_led_on(sc, LMC_DS3_LED0);
 
     lmc_dec_reset(sc);
@@ -992,17 +978,14 @@ static int lmc_open(struct net_device *dev)
     LMC_EVENT_LOG(LMC_EVENT_RESET2, lmc_mii_readreg(sc, 0, 16),
 		  lmc_mii_readreg(sc, 0, 17));
 
-    if (sc->lmc_ok){
-        lmc_trace(dev, "lmc_open lmc_ok out");
+    if (sc->lmc_ok)
         return 0;
-    }
 
     lmc_softreset (sc);
 
     /* Since we have to use PCI bus, this should work on x86,alpha,ppc */
     if (request_irq (dev->irq, lmc_interrupt, IRQF_SHARED, dev->name, dev)){
         printk(KERN_WARNING "%s: could not get irq: %d\n", dev->name, dev->irq);
-        lmc_trace(dev, "lmc_open irq failed out");
         return -EAGAIN;
     }
     sc->got_irq = 1;
@@ -1078,8 +1061,6 @@ static int lmc_open(struct net_device *dev)
     sc->timer.expires = jiffies + HZ;
     add_timer (&sc->timer);
 
-    lmc_trace(dev, "lmc_open out");
-
     return 0;
 }
 
@@ -1091,8 +1072,6 @@ static void lmc_running_reset (struct net_device *dev) /*fold00*/
 {
     lmc_softc_t *sc = dev_to_sc(dev);
 
-    lmc_trace(dev, "lmc_running_reset in");
-
     /* stop interrupts */
     /* Clear the interrupt mask */
     LMC_CSR_WRITE (sc, csr_intr, 0x00000000);
@@ -1114,8 +1093,6 @@ static void lmc_running_reset (struct net_device *dev) /*fold00*/
 
     sc->lmc_cmdmode |= (TULIP_CMD_TXRUN | TULIP_CMD_RXRUN);
     LMC_CSR_WRITE (sc, csr_command, sc->lmc_cmdmode);
-
-    lmc_trace(dev, "lmc_running_reset_out");
 }
 
 
@@ -1128,16 +1105,12 @@ static int lmc_close(struct net_device *dev)
     /* not calling release_region() as we should */
     lmc_softc_t *sc = dev_to_sc(dev);
 
-    lmc_trace(dev, "lmc_close in");
-
     sc->lmc_ok = 0;
     sc->lmc_media->set_link_status (sc, 0);
     del_timer (&sc->timer);
     lmc_proto_close(sc);
     lmc_ifdown (dev);
 
-    lmc_trace(dev, "lmc_close out");
-
     return 0;
 }
 
@@ -1149,8 +1122,6 @@ static int lmc_ifdown (struct net_device *dev) /*fold00*/
     u32 csr6;
     int i;
 
-    lmc_trace(dev, "lmc_ifdown in");
-
     /* Don't let anything else go on right now */
     //    dev->start = 0;
     netif_stop_queue(dev);
@@ -1200,8 +1171,6 @@ static int lmc_ifdown (struct net_device *dev) /*fold00*/
     netif_wake_queue(dev);
     sc->extra_stats.tx_tbusy0++;
 
-    lmc_trace(dev, "lmc_ifdown out");
-
     return 0;
 }
 
@@ -1220,8 +1189,6 @@ static irqreturn_t lmc_interrupt (int irq, void *dev_instance) /*fold00*/
     int max_work = LMC_RXDESCS;
     int handled = 0;
 
-    lmc_trace(dev, "lmc_interrupt in");
-
     spin_lock(&sc->lmc_lock);
 
     /*
@@ -1264,12 +1231,10 @@ static irqreturn_t lmc_interrupt (int irq, void *dev_instance) /*fold00*/
             lmc_running_reset (dev);
             break;
         }
-        
-        if (csr & TULIP_STS_RXINTR){
-            lmc_trace(dev, "rx interrupt");
+
+        if (csr & TULIP_STS_RXINTR)
             lmc_rx (dev);
-            
-        }
+
         if (csr & (TULIP_STS_TXINTR | TULIP_STS_TXNOBUF | TULIP_STS_TXSTOPPED)) {
 
 	    int		n_compl = 0 ;
@@ -1389,7 +1354,6 @@ lmc_int_fail_out:
 
     spin_unlock(&sc->lmc_lock);
 
-    lmc_trace(dev, "lmc_interrupt out");
     return IRQ_RETVAL(handled);
 }
 
@@ -1401,8 +1365,6 @@ static netdev_tx_t lmc_start_xmit(struct sk_buff *skb,
     int entry;
     unsigned long flags;
 
-    lmc_trace(dev, "lmc_start_xmit in");
-
     spin_lock_irqsave(&sc->lmc_lock, flags);
 
     /* normal path, tbusy known to be zero */
@@ -1477,7 +1439,6 @@ static netdev_tx_t lmc_start_xmit(struct sk_buff *skb,
 
     spin_unlock_irqrestore(&sc->lmc_lock, flags);
 
-    lmc_trace(dev, "lmc_start_xmit_out");
     return NETDEV_TX_OK;
 }
 
@@ -1493,8 +1454,6 @@ static int lmc_rx(struct net_device *dev)
     struct sk_buff *skb, *nsb;
     u16 len;
 
-    lmc_trace(dev, "lmc_rx in");
-
     lmc_led_on(sc, LMC_DS3_LED3);
 
     rxIntLoopCnt = 0;		/* debug -baz */
@@ -1673,9 +1632,6 @@ static int lmc_rx(struct net_device *dev)
     lmc_led_off(sc, LMC_DS3_LED3);
 
 skip_out_of_mem:
-
-    lmc_trace(dev, "lmc_rx out");
-
     return 0;
 }
 
@@ -1684,16 +1640,12 @@ static struct net_device_stats *lmc_get_stats(struct net_device *dev)
     lmc_softc_t *sc = dev_to_sc(dev);
     unsigned long flags;
 
-    lmc_trace(dev, "lmc_get_stats in");
-
     spin_lock_irqsave(&sc->lmc_lock, flags);
 
     sc->lmc_device->stats.rx_missed_errors += LMC_CSR_READ(sc, csr_missed_frames) & 0xffff;
 
     spin_unlock_irqrestore(&sc->lmc_lock, flags);
 
-    lmc_trace(dev, "lmc_get_stats out");
-
     return &sc->lmc_device->stats;
 }
 
@@ -1712,12 +1664,8 @@ unsigned lmc_mii_readreg (lmc_softc_t * const sc, unsigned devaddr, unsigned reg
     int command = (0xf6 << 10) | (devaddr << 5) | regno;
     int retval = 0;
 
-    lmc_trace(sc->lmc_device, "lmc_mii_readreg in");
-
     LMC_MII_SYNC (sc);
 
-    lmc_trace(sc->lmc_device, "lmc_mii_readreg: done sync");
-
     for (i = 15; i >= 0; i--)
     {
         int dataval = (command & (1 << i)) ? 0x20000 : 0;
@@ -1730,8 +1678,6 @@ unsigned lmc_mii_readreg (lmc_softc_t * const sc, unsigned devaddr, unsigned reg
         /* __SLOW_DOWN_IO; */
     }
 
-    lmc_trace(sc->lmc_device, "lmc_mii_readreg: done1");
-
     for (i = 19; i > 0; i--)
     {
         LMC_CSR_WRITE (sc, csr_9, 0x40000);
@@ -1743,8 +1689,6 @@ unsigned lmc_mii_readreg (lmc_softc_t * const sc, unsigned devaddr, unsigned reg
         /* __SLOW_DOWN_IO; */
     }
 
-    lmc_trace(sc->lmc_device, "lmc_mii_readreg out");
-
     return (retval >> 1) & 0xffff;
 }
 
@@ -1753,8 +1697,6 @@ void lmc_mii_writereg (lmc_softc_t * const sc, unsigned devaddr, unsigned regno,
     int i = 32;
     int command = (0x5002 << 16) | (devaddr << 23) | (regno << 18) | data;
 
-    lmc_trace(sc->lmc_device, "lmc_mii_writereg in");
-
     LMC_MII_SYNC (sc);
 
     i = 31;
@@ -1787,16 +1729,12 @@ void lmc_mii_writereg (lmc_softc_t * const sc, unsigned devaddr, unsigned regno,
         /* __SLOW_DOWN_IO; */
         i--;
     }
-
-    lmc_trace(sc->lmc_device, "lmc_mii_writereg out");
 }
 
 static void lmc_softreset (lmc_softc_t * const sc) /*fold00*/
 {
     int i;
 
-    lmc_trace(sc->lmc_device, "lmc_softreset in");
-
     /* Initialize the receive rings and buffers. */
     sc->lmc_txfull = 0;
     sc->lmc_next_rx = 0;
@@ -1871,55 +1809,40 @@ static void lmc_softreset (lmc_softc_t * const sc) /*fold00*/
     }
     sc->lmc_txring[i - 1].buffer2 = virt_to_bus (&sc->lmc_txring[0]);
     LMC_CSR_WRITE (sc, csr_txlist, virt_to_bus (sc->lmc_txring));
-
-    lmc_trace(sc->lmc_device, "lmc_softreset out");
 }
 
 void lmc_gpio_mkinput(lmc_softc_t * const sc, u32 bits) /*fold00*/
 {
-    lmc_trace(sc->lmc_device, "lmc_gpio_mkinput in");
     sc->lmc_gpio_io &= ~bits;
     LMC_CSR_WRITE(sc, csr_gp, TULIP_GP_PINSET | (sc->lmc_gpio_io));
-    lmc_trace(sc->lmc_device, "lmc_gpio_mkinput out");
 }
 
 void lmc_gpio_mkoutput(lmc_softc_t * const sc, u32 bits) /*fold00*/
 {
-    lmc_trace(sc->lmc_device, "lmc_gpio_mkoutput in");
     sc->lmc_gpio_io |= bits;
     LMC_CSR_WRITE(sc, csr_gp, TULIP_GP_PINSET | (sc->lmc_gpio_io));
-    lmc_trace(sc->lmc_device, "lmc_gpio_mkoutput out");
 }
 
 void lmc_led_on(lmc_softc_t * const sc, u32 led) /*fold00*/
 {
-    lmc_trace(sc->lmc_device, "lmc_led_on in");
-    if((~sc->lmc_miireg16) & led){ /* Already on! */
-        lmc_trace(sc->lmc_device, "lmc_led_on aon out");
+    if ((~sc->lmc_miireg16) & led) /* Already on! */
         return;
-    }
-    
+
     sc->lmc_miireg16 &= ~led;
     lmc_mii_writereg(sc, 0, 16, sc->lmc_miireg16);
-    lmc_trace(sc->lmc_device, "lmc_led_on out");
 }
 
 void lmc_led_off(lmc_softc_t * const sc, u32 led) /*fold00*/
 {
-    lmc_trace(sc->lmc_device, "lmc_led_off in");
-    if(sc->lmc_miireg16 & led){ /* Already set don't do anything */
-        lmc_trace(sc->lmc_device, "lmc_led_off aoff out");
+    if (sc->lmc_miireg16 & led) /* Already set don't do anything */
         return;
-    }
-    
+
     sc->lmc_miireg16 |= led;
     lmc_mii_writereg(sc, 0, 16, sc->lmc_miireg16);
-    lmc_trace(sc->lmc_device, "lmc_led_off out");
 }
 
 static void lmc_reset(lmc_softc_t * const sc) /*fold00*/
 {
-    lmc_trace(sc->lmc_device, "lmc_reset in");
     sc->lmc_miireg16 |= LMC_MII16_FIFO_RESET;
     lmc_mii_writereg(sc, 0, 16, sc->lmc_miireg16);
 
@@ -1955,13 +1878,11 @@ static void lmc_reset(lmc_softc_t * const sc) /*fold00*/
     sc->lmc_media->init(sc);
 
     sc->extra_stats.resetCount++;
-    lmc_trace(sc->lmc_device, "lmc_reset out");
 }
 
 static void lmc_dec_reset(lmc_softc_t * const sc) /*fold00*/
 {
     u32 val;
-    lmc_trace(sc->lmc_device, "lmc_dec_reset in");
 
     /*
      * disable all interrupts
@@ -2017,14 +1938,11 @@ static void lmc_dec_reset(lmc_softc_t * const sc) /*fold00*/
     val = LMC_CSR_READ(sc, csr_sia_general);
     val |= (TULIP_WATCHDOG_TXDISABLE | TULIP_WATCHDOG_RXDISABLE);
     LMC_CSR_WRITE(sc, csr_sia_general, val);
-
-    lmc_trace(sc->lmc_device, "lmc_dec_reset out");
 }
 
 static void lmc_initcsrs(lmc_softc_t * const sc, lmc_csrptr_t csr_base, /*fold00*/
                          size_t csr_size)
 {
-    lmc_trace(sc->lmc_device, "lmc_initcsrs in");
     sc->lmc_csrs.csr_busmode	        = csr_base +  0 * csr_size;
     sc->lmc_csrs.csr_txpoll		= csr_base +  1 * csr_size;
     sc->lmc_csrs.csr_rxpoll		= csr_base +  2 * csr_size;
@@ -2041,7 +1959,6 @@ static void lmc_initcsrs(lmc_softc_t * const sc, lmc_csrptr_t csr_base, /*fold00
     sc->lmc_csrs.csr_13		        = csr_base + 13 * csr_size;
     sc->lmc_csrs.csr_14		        = csr_base + 14 * csr_size;
     sc->lmc_csrs.csr_15		        = csr_base + 15 * csr_size;
-    lmc_trace(sc->lmc_device, "lmc_initcsrs out");
 }
 
 static void lmc_driver_timeout(struct net_device *dev, unsigned int txqueue)
@@ -2050,8 +1967,6 @@ static void lmc_driver_timeout(struct net_device *dev, unsigned int txqueue)
     u32 csr6;
     unsigned long flags;
 
-    lmc_trace(dev, "lmc_driver_timeout in");
-
     spin_lock_irqsave(&sc->lmc_lock, flags);
 
     printk("%s: Xmitter busy|\n", dev->name);
@@ -2094,8 +2009,4 @@ static void lmc_driver_timeout(struct net_device *dev, unsigned int txqueue)
 bug_out:
 
     spin_unlock_irqrestore(&sc->lmc_lock, flags);
-
-    lmc_trace(dev, "lmc_driver_timeout out");
-
-
 }
diff --git a/drivers/net/wan/lmc/lmc_media.c b/drivers/net/wan/lmc/lmc_media.c
index 23ca4a62d6f5..ec1ac7b1f3fd 100644
--- a/drivers/net/wan/lmc/lmc_media.c
+++ b/drivers/net/wan/lmc/lmc_media.c
@@ -1026,7 +1026,6 @@ lmc_t1_get_link_status (lmc_softc_t * const sc)
    * led3 red    = Loss of Signal (LOS) or out of frame (OOF)
    *               conditions detected on T3 receive signal
    */
-    lmc_trace(sc->lmc_device, "lmc_t1_get_link_status in");
     lmc_led_on(sc, LMC_DS3_LED2);
 
     lmc_mii_writereg (sc, 0, 17, T1FRAMER_ALARM1_STATUS);
@@ -1120,9 +1119,6 @@ lmc_t1_get_link_status (lmc_softc_t * const sc)
     lmc_mii_writereg (sc, 0, 17, T1FRAMER_ALARM2_STATUS);
     sc->lmc_xinfo.t1_alarm2_status = lmc_mii_readreg (sc, 0, 18);
 
-    
-    lmc_trace(sc->lmc_device, "lmc_t1_get_link_status out");
-
     return ret;
 }
 
diff --git a/drivers/net/wan/lmc/lmc_proto.c b/drivers/net/wan/lmc/lmc_proto.c
index a58301dd0c1f..e8b0b902b424 100644
--- a/drivers/net/wan/lmc/lmc_proto.c
+++ b/drivers/net/wan/lmc/lmc_proto.c
@@ -47,7 +47,6 @@
 // attach
 void lmc_proto_attach(lmc_softc_t *sc) /*FOLD00*/
 {
-    lmc_trace(sc->lmc_device, "lmc_proto_attach in");
     if (sc->if_type == LMC_NET) {
             struct net_device *dev = sc->lmc_device;
             /*
@@ -57,12 +56,10 @@ void lmc_proto_attach(lmc_softc_t *sc) /*FOLD00*/
             dev->hard_header_len = 0;
             dev->addr_len = 0;
         }
-    lmc_trace(sc->lmc_device, "lmc_proto_attach out");
 }
 
 int lmc_proto_ioctl(lmc_softc_t *sc, struct ifreq *ifr, int cmd)
 {
-	lmc_trace(sc->lmc_device, "lmc_proto_ioctl");
 	if (sc->if_type == LMC_PPP)
 		return hdlc_ioctl(sc->lmc_device, ifr, cmd);
 	return -EOPNOTSUPP;
@@ -72,32 +69,23 @@ int lmc_proto_open(lmc_softc_t *sc)
 {
 	int ret = 0;
 
-	lmc_trace(sc->lmc_device, "lmc_proto_open in");
-
 	if (sc->if_type == LMC_PPP) {
 		ret = hdlc_open(sc->lmc_device);
 		if (ret < 0)
 			printk(KERN_WARNING "%s: HDLC open failed: %d\n",
 			       sc->name, ret);
 	}
-
-	lmc_trace(sc->lmc_device, "lmc_proto_open out");
 	return ret;
 }
 
 void lmc_proto_close(lmc_softc_t *sc)
 {
-	lmc_trace(sc->lmc_device, "lmc_proto_close in");
-
 	if (sc->if_type == LMC_PPP)
 		hdlc_close(sc->lmc_device);
-
-	lmc_trace(sc->lmc_device, "lmc_proto_close out");
 }
 
 __be16 lmc_proto_type(lmc_softc_t *sc, struct sk_buff *skb) /*FOLD00*/
 {
-    lmc_trace(sc->lmc_device, "lmc_proto_type in");
     switch(sc->if_type){
     case LMC_PPP:
 	    return hdlc_type_trans(skb, sc->lmc_device);
@@ -113,13 +101,10 @@ __be16 lmc_proto_type(lmc_softc_t *sc, struct sk_buff *skb) /*FOLD00*/
         return htons(ETH_P_802_2);
         break;
     }
-    lmc_trace(sc->lmc_device, "lmc_proto_tye out");
-
 }
 
 void lmc_proto_netif(lmc_softc_t *sc, struct sk_buff *skb) /*FOLD00*/
 {
-    lmc_trace(sc->lmc_device, "lmc_proto_netif in");
     switch(sc->if_type){
     case LMC_PPP:
     case LMC_NET:
@@ -129,5 +114,4 @@ void lmc_proto_netif(lmc_softc_t *sc, struct sk_buff *skb) /*FOLD00*/
     case LMC_RAW:
         break;
     }
-    lmc_trace(sc->lmc_device, "lmc_proto_netif out");
 }
diff --git a/drivers/net/wireguard/noise.c b/drivers/net/wireguard/noise.c
index 3dd3b76790d0..c0cfd9b36c0b 100644
--- a/drivers/net/wireguard/noise.c
+++ b/drivers/net/wireguard/noise.c
@@ -87,15 +87,12 @@ static void handshake_zero(struct noise_handshake *handshake)
 
 void wg_noise_handshake_clear(struct noise_handshake *handshake)
 {
+	down_write(&handshake->lock);
 	wg_index_hashtable_remove(
 			handshake->entry.peer->device->index_hashtable,
 			&handshake->entry);
-	down_write(&handshake->lock);
 	handshake_zero(handshake);
 	up_write(&handshake->lock);
-	wg_index_hashtable_remove(
-			handshake->entry.peer->device->index_hashtable,
-			&handshake->entry);
 }
 
 static struct noise_keypair *keypair_create(struct wg_peer *peer)
diff --git a/drivers/net/wireguard/peerlookup.c b/drivers/net/wireguard/peerlookup.c
index e4deb331476b..f2783aa7a88f 100644
--- a/drivers/net/wireguard/peerlookup.c
+++ b/drivers/net/wireguard/peerlookup.c
@@ -167,9 +167,13 @@ bool wg_index_hashtable_replace(struct index_hashtable *table,
 				struct index_hashtable_entry *old,
 				struct index_hashtable_entry *new)
 {
-	if (unlikely(hlist_unhashed(&old->index_hash)))
-		return false;
+	bool ret;
+
 	spin_lock_bh(&table->lock);
+	ret = !hlist_unhashed(&old->index_hash);
+	if (unlikely(!ret))
+		goto out;
+
 	new->index = old->index;
 	hlist_replace_rcu(&old->index_hash, &new->index_hash);
 
@@ -180,8 +184,9 @@ bool wg_index_hashtable_replace(struct index_hashtable *table,
 	 * simply gets dropped, which isn't terrible.
 	 */
 	INIT_HLIST_NODE(&old->index_hash);
+out:
 	spin_unlock_bh(&table->lock);
-	return true;
+	return ret;
 }
 
 void wg_index_hashtable_remove(struct index_hashtable *table,
diff --git a/drivers/net/wireless/ath/ath10k/core.c b/drivers/net/wireless/ath/ath10k/core.c
index 5f4e1219684b..d73ad60b571c 100644
--- a/drivers/net/wireless/ath/ath10k/core.c
+++ b/drivers/net/wireless/ath/ath10k/core.c
@@ -1022,7 +1022,7 @@ static int ath10k_core_check_smbios(struct ath10k *ar)
 	return 0;
 }
 
-static int ath10k_core_check_dt(struct ath10k *ar)
+int ath10k_core_check_dt(struct ath10k *ar)
 {
 	struct device_node *node;
 	const char *variant = NULL;
@@ -1043,6 +1043,7 @@ static int ath10k_core_check_dt(struct ath10k *ar)
 
 	return 0;
 }
+EXPORT_SYMBOL(ath10k_core_check_dt);
 
 static int ath10k_download_fw(struct ath10k *ar)
 {
@@ -1437,10 +1438,17 @@ static int ath10k_core_create_board_name(struct ath10k *ar, char *name,
 	}
 
 	if (ar->id.qmi_ids_valid) {
-		scnprintf(name, name_len,
-			  "bus=%s,qmi-board-id=%x",
-			  ath10k_bus_str(ar->hif.bus),
-			  ar->id.qmi_board_id);
+		if (with_variant && ar->id.bdf_ext[0] != '\0')
+			scnprintf(name, name_len,
+				  "bus=%s,qmi-board-id=%x,qmi-chip-id=%x%s",
+				  ath10k_bus_str(ar->hif.bus),
+				  ar->id.qmi_board_id, ar->id.qmi_chip_id,
+				  variant);
+		else
+			scnprintf(name, name_len,
+				  "bus=%s,qmi-board-id=%x",
+				  ath10k_bus_str(ar->hif.bus),
+				  ar->id.qmi_board_id);
 		goto out;
 	}
 
diff --git a/drivers/net/wireless/ath/ath10k/core.h b/drivers/net/wireless/ath/ath10k/core.h
index 4cf5bd4896bc..b50ab9e229dc 100644
--- a/drivers/net/wireless/ath/ath10k/core.h
+++ b/drivers/net/wireless/ath/ath10k/core.h
@@ -1076,6 +1076,7 @@ struct ath10k {
 		bool bmi_ids_valid;
 		bool qmi_ids_valid;
 		u32 qmi_board_id;
+		u32 qmi_chip_id;
 		u8 bmi_board_id;
 		u8 bmi_eboard_id;
 		u8 bmi_chip_id;
@@ -1315,6 +1316,7 @@ int ath10k_core_register(struct ath10k *ar,
 			 const struct ath10k_bus_params *bus_params);
 void ath10k_core_unregister(struct ath10k *ar);
 int ath10k_core_fetch_board_file(struct ath10k *ar, int bd_ie_type);
+int ath10k_core_check_dt(struct ath10k *ar);
 void ath10k_core_free_board_files(struct ath10k *ar);
 
 #endif /* _CORE_H_ */
diff --git a/drivers/net/wireless/ath/ath10k/qmi.c b/drivers/net/wireless/ath/ath10k/qmi.c
index 5468a41e928e..ae6b1f402adf 100644
--- a/drivers/net/wireless/ath/ath10k/qmi.c
+++ b/drivers/net/wireless/ath/ath10k/qmi.c
@@ -576,6 +576,8 @@ static int ath10k_qmi_cap_send_sync_msg(struct ath10k_qmi *qmi)
 	if (resp->chip_info_valid) {
 		qmi->chip_info.chip_id = resp->chip_info.chip_id;
 		qmi->chip_info.chip_family = resp->chip_info.chip_family;
+	} else {
+		qmi->chip_info.chip_id = 0xFF;
 	}
 
 	if (resp->board_info_valid)
@@ -817,12 +819,18 @@ err_setup_msa:
 static int ath10k_qmi_fetch_board_file(struct ath10k_qmi *qmi)
 {
 	struct ath10k *ar = qmi->ar;
+	int ret;
 
 	ar->hif.bus = ATH10K_BUS_SNOC;
 	ar->id.qmi_ids_valid = true;
 	ar->id.qmi_board_id = qmi->board_info.board_id;
+	ar->id.qmi_chip_id = qmi->chip_info.chip_id;
 	ar->hw_params.fw.dir = WCN3990_HW_1_0_FW_DIR;
 
+	ret = ath10k_core_check_dt(ar);
+	if (ret)
+		ath10k_dbg(ar, ATH10K_DBG_QMI, "DT bdf variant name not set.\n");
+
 	return ath10k_core_fetch_board_file(qmi->ar, ATH10K_BD_IE_BOARD);
 }
 
diff --git a/drivers/net/wireless/ath/ath11k/Makefile b/drivers/net/wireless/ath/ath11k/Makefile
index bc4911f0339d..c41d87bd025a 100644
--- a/drivers/net/wireless/ath/ath11k/Makefile
+++ b/drivers/net/wireless/ath/ath11k/Makefile
@@ -18,7 +18,7 @@ ath11k-y += core.o \
 	    dbring.o \
 	    hw.o
 
-ath11k-$(CONFIG_ATH11K_DEBUGFS) += debug_htt_stats.o debugfs_sta.o
+ath11k-$(CONFIG_ATH11K_DEBUGFS) += debugfs.o debugfs_htt_stats.o debugfs_sta.o
 ath11k-$(CONFIG_NL80211_TESTMODE) += testmode.o
 ath11k-$(CONFIG_ATH11K_TRACING) += trace.o
 ath11k-$(CONFIG_THERMAL) += thermal.o
diff --git a/drivers/net/wireless/ath/ath11k/ahb.c b/drivers/net/wireless/ath/ath11k/ahb.c
index f6e36e58e1fd..430723c64adc 100644
--- a/drivers/net/wireless/ath/ath11k/ahb.c
+++ b/drivers/net/wireless/ath/ath11k/ahb.c
@@ -323,9 +323,10 @@ static void ath11k_ahb_stop(struct ath11k_base *ab)
 
 static int ath11k_ahb_power_up(struct ath11k_base *ab)
 {
+	struct ath11k_ahb *ab_ahb = ath11k_ahb_priv(ab);
 	int ret;
 
-	ret = rproc_boot(ab->tgt_rproc);
+	ret = rproc_boot(ab_ahb->tgt_rproc);
 	if (ret)
 		ath11k_err(ab, "failed to boot the remote processor Q6\n");
 
@@ -334,7 +335,9 @@ static int ath11k_ahb_power_up(struct ath11k_base *ab)
 
 static void ath11k_ahb_power_down(struct ath11k_base *ab)
 {
-	rproc_shutdown(ab->tgt_rproc);
+	struct ath11k_ahb *ab_ahb = ath11k_ahb_priv(ab);
+
+	rproc_shutdown(ab_ahb->tgt_rproc);
 }
 
 static void ath11k_ahb_init_qmi_ce_config(struct ath11k_base *ab)
@@ -600,6 +603,28 @@ static const struct ath11k_hif_ops ath11k_ahb_hif_ops = {
 	.power_up = ath11k_ahb_power_up,
 };
 
+static int ath11k_core_get_rproc(struct ath11k_base *ab)
+{
+	struct ath11k_ahb *ab_ahb = ath11k_ahb_priv(ab);
+	struct device *dev = ab->dev;
+	struct rproc *prproc;
+	phandle rproc_phandle;
+
+	if (of_property_read_u32(dev->of_node, "qcom,rproc", &rproc_phandle)) {
+		ath11k_err(ab, "failed to get q6_rproc handle\n");
+		return -ENOENT;
+	}
+
+	prproc = rproc_get_by_phandle(rproc_phandle);
+	if (!prproc) {
+		ath11k_err(ab, "failed to get rproc\n");
+		return -EINVAL;
+	}
+	ab_ahb->tgt_rproc = prproc;
+
+	return 0;
+}
+
 static int ath11k_ahb_probe(struct platform_device *pdev)
 {
 	struct ath11k_base *ab;
@@ -626,7 +651,9 @@ static int ath11k_ahb_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	ab = ath11k_core_alloc(&pdev->dev, 0, ATH11K_BUS_AHB, &ath11k_ahb_bus_params);
+	ab = ath11k_core_alloc(&pdev->dev, sizeof(struct ath11k_ahb),
+			       ATH11K_BUS_AHB,
+			       &ath11k_ahb_bus_params);
 	if (!ab) {
 		dev_err(&pdev->dev, "failed to allocate ath11k base\n");
 		return -ENOMEM;
@@ -655,6 +682,12 @@ static int ath11k_ahb_probe(struct platform_device *pdev)
 
 	ath11k_ahb_init_qmi_ce_config(ab);
 
+	ret = ath11k_core_get_rproc(ab);
+	if (ret) {
+		ath11k_err(ab, "failed to get rproc: %d\n", ret);
+		goto err_ce_free;
+	}
+
 	ret = ath11k_core_init(ab);
 	if (ret) {
 		ath11k_err(ab, "failed to init core: %d\n", ret);
@@ -685,12 +718,16 @@ err_core_free:
 static int ath11k_ahb_remove(struct platform_device *pdev)
 {
 	struct ath11k_base *ab = platform_get_drvdata(pdev);
+	unsigned long left;
 
 	reinit_completion(&ab->driver_recovery);
 
-	if (test_bit(ATH11K_FLAG_RECOVERY, &ab->dev_flags))
-		wait_for_completion_timeout(&ab->driver_recovery,
-					    ATH11K_AHB_RECOVERY_TIMEOUT);
+	if (test_bit(ATH11K_FLAG_RECOVERY, &ab->dev_flags)) {
+		left = wait_for_completion_timeout(&ab->driver_recovery,
+						   ATH11K_AHB_RECOVERY_TIMEOUT);
+		if (!left)
+			ath11k_warn(ab, "failed to receive recovery response completion\n");
+	}
 
 	set_bit(ATH11K_FLAG_UNREGISTERING, &ab->dev_flags);
 	cancel_work_sync(&ab->restart_work);
diff --git a/drivers/net/wireless/ath/ath11k/ahb.h b/drivers/net/wireless/ath/ath11k/ahb.h
index 6c7b26ac6545..51e6e4a5f686 100644
--- a/drivers/net/wireless/ath/ath11k/ahb.h
+++ b/drivers/net/wireless/ath/ath11k/ahb.h
@@ -10,4 +10,12 @@
 #define ATH11K_AHB_RECOVERY_TIMEOUT (3 * HZ)
 struct ath11k_base;
 
+struct ath11k_ahb {
+	struct rproc *tgt_rproc;
+};
+
+static inline struct ath11k_ahb *ath11k_ahb_priv(struct ath11k_base *ab)
+{
+	return (struct ath11k_ahb *)ab->drv_priv;
+}
 #endif
diff --git a/drivers/net/wireless/ath/ath11k/ce.c b/drivers/net/wireless/ath/ath11k/ce.c
index b2da1f937478..9d730f8ac816 100644
--- a/drivers/net/wireless/ath/ath11k/ce.c
+++ b/drivers/net/wireless/ath/ath11k/ce.c
@@ -187,6 +187,26 @@ const struct ce_attr ath11k_host_ce_config_qca6390[] = {
 
 };
 
+static bool ath11k_ce_need_shadow_fix(int ce_id)
+{
+	/* only ce4 needs shadow workaroud*/
+	if (ce_id == 4)
+		return true;
+	return false;
+}
+
+static void ath11k_ce_stop_shadow_timers(struct ath11k_base *ab)
+{
+	int i;
+
+	if (!ab->hw_params.supports_shadow_regs)
+		return;
+
+	for (i = 0; i < ab->hw_params.ce_count; i++)
+		if (ath11k_ce_need_shadow_fix(i))
+			ath11k_dp_shadow_stop_timer(ab, &ab->ce.hp_timer[i]);
+}
+
 static int ath11k_ce_rx_buf_enqueue_pipe(struct ath11k_ce_pipe *pipe,
 					 struct sk_buff *skb, dma_addr_t paddr)
 {
@@ -505,6 +525,12 @@ static int ath11k_ce_init_ring(struct ath11k_base *ab,
 
 	ce_ring->hal_ring_id = ret;
 
+	if (ab->hw_params.supports_shadow_regs &&
+	    ath11k_ce_need_shadow_fix(ce_id))
+		ath11k_dp_shadow_init_timer(ab, &ab->ce.hp_timer[ce_id],
+					    ATH11K_SHADOW_CTRL_TIMER_INTERVAL,
+					    ce_ring->hal_ring_id);
+
 	return 0;
 }
 
@@ -677,6 +703,9 @@ int ath11k_ce_send(struct ath11k_base *ab, struct sk_buff *skb, u8 pipe_id,
 
 	ath11k_hal_srng_access_end(ab, srng);
 
+	if (ath11k_ce_need_shadow_fix(pipe_id))
+		ath11k_dp_shadow_start_timer(ab, srng, &ab->ce.hp_timer[pipe_id]);
+
 	spin_unlock_bh(&srng->lock);
 
 	spin_unlock_bh(&ab->ce.ce_lock);
@@ -713,11 +742,56 @@ static void ath11k_ce_rx_pipe_cleanup(struct ath11k_ce_pipe *pipe)
 	}
 }
 
+static void ath11k_ce_shadow_config(struct ath11k_base *ab)
+{
+	int i;
+
+	for (i = 0; i < ab->hw_params.ce_count; i++) {
+		if (ab->hw_params.host_ce_config[i].src_nentries)
+			ath11k_hal_srng_update_shadow_config(ab,
+							     HAL_CE_SRC, i);
+
+		if (ab->hw_params.host_ce_config[i].dest_nentries) {
+			ath11k_hal_srng_update_shadow_config(ab,
+							     HAL_CE_DST, i);
+
+			ath11k_hal_srng_update_shadow_config(ab,
+							     HAL_CE_DST_STATUS, i);
+		}
+	}
+}
+
+void ath11k_ce_get_shadow_config(struct ath11k_base *ab,
+				 u32 **shadow_cfg, u32 *shadow_cfg_len)
+{
+	if (!ab->hw_params.supports_shadow_regs)
+		return;
+
+	ath11k_hal_srng_get_shadow_config(ab, shadow_cfg, shadow_cfg_len);
+
+	/* shadow is already configured */
+	if (*shadow_cfg_len)
+		return;
+
+	/* shadow isn't configured yet, configure now.
+	 * non-CE srngs are configured firstly, then
+	 * all CE srngs.
+	 */
+	ath11k_hal_srng_shadow_config(ab);
+	ath11k_ce_shadow_config(ab);
+
+	/* get the shadow configuration */
+	ath11k_hal_srng_get_shadow_config(ab, shadow_cfg, shadow_cfg_len);
+}
+EXPORT_SYMBOL(ath11k_ce_get_shadow_config);
+
 void ath11k_ce_cleanup_pipes(struct ath11k_base *ab)
 {
 	struct ath11k_ce_pipe *pipe;
 	int pipe_num;
 
+	ath11k_ce_stop_shadow_timers(ab);
+
 	for (pipe_num = 0; pipe_num < ab->hw_params.ce_count; pipe_num++) {
 		pipe = &ab->ce.ce_pipe[pipe_num];
 		ath11k_ce_rx_pipe_cleanup(pipe);
@@ -767,6 +841,9 @@ int ath11k_ce_init_pipes(struct ath11k_base *ab)
 	int i;
 	int ret;
 
+	ath11k_ce_get_shadow_config(ab, &ab->qmi.ce_cfg.shadow_reg_v2,
+				    &ab->qmi.ce_cfg.shadow_reg_v2_len);
+
 	for (i = 0; i < ab->hw_params.ce_count; i++) {
 		pipe = &ab->ce.ce_pipe[i];
 
@@ -828,6 +905,9 @@ void ath11k_ce_free_pipes(struct ath11k_base *ab)
 	for (i = 0; i < ab->hw_params.ce_count; i++) {
 		pipe = &ab->ce.ce_pipe[i];
 
+		if (ath11k_ce_need_shadow_fix(i))
+			ath11k_dp_shadow_stop_timer(ab, &ab->ce.hp_timer[i]);
+
 		if (pipe->src_ring) {
 			desc_sz = ath11k_hal_ce_get_desc_size(HAL_CE_DESC_SRC);
 			dma_free_coherent(ab->dev,
diff --git a/drivers/net/wireless/ath/ath11k/ce.h b/drivers/net/wireless/ath/ath11k/ce.h
index cf704f18f3a1..269b599ac0b0 100644
--- a/drivers/net/wireless/ath/ath11k/ce.h
+++ b/drivers/net/wireless/ath/ath11k/ce.h
@@ -168,6 +168,7 @@ struct ath11k_ce {
 	struct ath11k_ce_pipe ce_pipe[CE_COUNT_MAX];
 	/* Protects rings of all ce pipes */
 	spinlock_t ce_lock;
+	struct ath11k_hp_update_timer hp_timer[CE_COUNT_MAX];
 };
 
 extern const struct ce_attr ath11k_host_ce_config_ipq8074[];
@@ -187,4 +188,6 @@ void ath11k_ce_poll_send_completed(struct ath11k_base *ab, u8 pipe_id);
 int ath11k_ce_map_service_to_pipe(struct ath11k_base *ab, u16 service_id,
 				  u8 *ul_pipe, u8 *dl_pipe);
 int ath11k_ce_attr_attach(struct ath11k_base *ab);
+void ath11k_ce_get_shadow_config(struct ath11k_base *ab,
+				 u32 **shadow_cfg, u32 *shadow_cfg_len);
 #endif
diff --git a/drivers/net/wireless/ath/ath11k/core.c b/drivers/net/wireless/ath/ath11k/core.c
index ce81702b27d2..ebd6886a8c18 100644
--- a/drivers/net/wireless/ath/ath11k/core.c
+++ b/drivers/net/wireless/ath/ath11k/core.c
@@ -57,6 +57,14 @@ static const struct ath11k_hw_params ath11k_hw_params[] = {
 		.vdev_start_delay = false,
 		.htt_peer_map_v2 = true,
 		.tcl_0_only = false,
+		.spectral_fft_sz = 2,
+
+		.interface_modes = BIT(NL80211_IFTYPE_STATION) |
+					BIT(NL80211_IFTYPE_AP) |
+					BIT(NL80211_IFTYPE_MESH_POINT),
+		.supports_monitor = true,
+		.supports_shadow_regs = false,
+		.idle_ps = false,
 	},
 	{
 		.hw_rev = ATH11K_HW_IPQ6018_HW10,
@@ -86,6 +94,14 @@ static const struct ath11k_hw_params ath11k_hw_params[] = {
 		.vdev_start_delay = false,
 		.htt_peer_map_v2 = true,
 		.tcl_0_only = false,
+		.spectral_fft_sz = 4,
+
+		.interface_modes = BIT(NL80211_IFTYPE_STATION) |
+					BIT(NL80211_IFTYPE_AP) |
+					BIT(NL80211_IFTYPE_MESH_POINT),
+		.supports_monitor = true,
+		.supports_shadow_regs = false,
+		.idle_ps = false,
 	},
 	{
 		.name = "qca6390 hw2.0",
@@ -115,6 +131,13 @@ static const struct ath11k_hw_params ath11k_hw_params[] = {
 		.vdev_start_delay = true,
 		.htt_peer_map_v2 = false,
 		.tcl_0_only = true,
+		.spectral_fft_sz = 0,
+
+		.interface_modes = BIT(NL80211_IFTYPE_STATION) |
+					BIT(NL80211_IFTYPE_AP),
+		.supports_monitor = false,
+		.supports_shadow_regs = true,
+		.idle_ps = true,
 	},
 };
 
@@ -395,6 +418,7 @@ static void ath11k_core_stop(struct ath11k_base *ab)
 {
 	if (!test_bit(ATH11K_FLAG_CRASH_FLUSH, &ab->dev_flags))
 		ath11k_qmi_firmware_stop(ab);
+
 	ath11k_hif_stop(ab);
 	ath11k_wmi_detach(ab);
 	ath11k_dp_pdev_reo_cleanup(ab);
@@ -412,7 +436,7 @@ static int ath11k_core_soc_create(struct ath11k_base *ab)
 		return ret;
 	}
 
-	ret = ath11k_debug_soc_create(ab);
+	ret = ath11k_debugfs_soc_create(ab);
 	if (ret) {
 		ath11k_err(ab, "failed to create ath11k debugfs\n");
 		goto err_qmi_deinit;
@@ -427,7 +451,7 @@ static int ath11k_core_soc_create(struct ath11k_base *ab)
 	return 0;
 
 err_debugfs_reg:
-	ath11k_debug_soc_destroy(ab);
+	ath11k_debugfs_soc_destroy(ab);
 err_qmi_deinit:
 	ath11k_qmi_deinit_service(ab);
 	return ret;
@@ -435,7 +459,7 @@ err_qmi_deinit:
 
 static void ath11k_core_soc_destroy(struct ath11k_base *ab)
 {
-	ath11k_debug_soc_destroy(ab);
+	ath11k_debugfs_soc_destroy(ab);
 	ath11k_dp_free(ab);
 	ath11k_reg_free(ab);
 	ath11k_qmi_deinit_service(ab);
@@ -445,7 +469,7 @@ static int ath11k_core_pdev_create(struct ath11k_base *ab)
 {
 	int ret;
 
-	ret = ath11k_debug_pdev_create(ab);
+	ret = ath11k_debugfs_pdev_create(ab);
 	if (ret) {
 		ath11k_err(ab, "failed to create core pdev debugfs: %d\n", ret);
 		return ret;
@@ -485,7 +509,7 @@ err_dp_pdev_free:
 err_mac_unregister:
 	ath11k_mac_unregister(ab);
 err_pdev_debug:
-	ath11k_debug_pdev_destroy(ab);
+	ath11k_debugfs_pdev_destroy(ab);
 
 	return ret;
 }
@@ -497,7 +521,7 @@ static void ath11k_core_pdev_destroy(struct ath11k_base *ab)
 	ath11k_mac_unregister(ab);
 	ath11k_hif_irq_disable(ab);
 	ath11k_dp_pdev_free(ab);
-	ath11k_debug_pdev_destroy(ab);
+	ath11k_debugfs_pdev_destroy(ab);
 }
 
 static int ath11k_core_start(struct ath11k_base *ab,
@@ -842,43 +866,10 @@ int ath11k_core_pre_init(struct ath11k_base *ab)
 }
 EXPORT_SYMBOL(ath11k_core_pre_init);
 
-static int ath11k_core_get_rproc(struct ath11k_base *ab)
-{
-	struct device *dev = ab->dev;
-	struct rproc *prproc;
-	phandle rproc_phandle;
-
-	if (!IS_ENABLED(CONFIG_REMOTEPROC))
-		return 0;
-
-	if (ab->bus_params.mhi_support)
-		return 0;
-
-	if (of_property_read_u32(dev->of_node, "qcom,rproc", &rproc_phandle)) {
-		ath11k_err(ab, "failed to get q6_rproc handle\n");
-		return -ENOENT;
-	}
-
-	prproc = rproc_get_by_phandle(rproc_phandle);
-	if (!prproc) {
-		ath11k_err(ab, "failed to get rproc\n");
-		return -EINVAL;
-	}
-	ab->tgt_rproc = prproc;
-
-	return 0;
-}
-
 int ath11k_core_init(struct ath11k_base *ab)
 {
 	int ret;
 
-	ret = ath11k_core_get_rproc(ab);
-	if (ret) {
-		ath11k_err(ab, "failed to get rproc: %d\n", ret);
-		return ret;
-	}
-
 	ret = ath11k_core_soc_create(ab);
 	if (ret) {
 		ath11k_err(ab, "failed to create soc core: %d\n", ret);
diff --git a/drivers/net/wireless/ath/ath11k/core.h b/drivers/net/wireless/ath/ath11k/core.h
index 807884687d39..18b97420f0d8 100644
--- a/drivers/net/wireless/ath/ath11k/core.h
+++ b/drivers/net/wireless/ath/ath11k/core.h
@@ -37,6 +37,8 @@
 
 extern unsigned int ath11k_frame_mode;
 
+#define ATH11K_MON_TIMER_INTERVAL  10
+
 enum ath11k_supported_bw {
 	ATH11K_BW_20	= 0,
 	ATH11K_BW_40	= 1,
@@ -648,7 +650,6 @@ struct ath11k_base {
 	struct ath11k_qmi qmi;
 	struct ath11k_wmi_base wmi_ab;
 	struct completion fw_ready;
-	struct rproc *tgt_rproc;
 	int num_radios;
 	/* HW channel counters frequency value in hertz common to all MACs */
 	u32 cc_freq_hz;
@@ -728,6 +729,7 @@ struct ath11k_base {
 	struct ath11k_dbring_cap *db_caps;
 	u32 num_db_cap;
 
+	struct timer_list mon_reap_timer;
 	/* must be last */
 	u8 drv_priv[0] __aligned(sizeof(void *));
 };
diff --git a/drivers/net/wireless/ath/ath11k/debug.c b/drivers/net/wireless/ath/ath11k/debug.c
index 0ba234ad99b2..c86de95fbdc5 100644
--- a/drivers/net/wireless/ath/ath11k/debug.c
+++ b/drivers/net/wireless/ath/ath11k/debug.c
@@ -6,48 +6,6 @@
 #include <linux/vmalloc.h>
 #include "core.h"
 #include "debug.h"
-#include "wmi.h"
-#include "hal_rx.h"
-#include "dp_tx.h"
-#include "debug_htt_stats.h"
-#include "peer.h"
-
-static const char *htt_bp_umac_ring[HTT_SW_UMAC_RING_IDX_MAX] = {
-	"REO2SW1_RING",
-	"REO2SW2_RING",
-	"REO2SW3_RING",
-	"REO2SW4_RING",
-	"WBM2REO_LINK_RING",
-	"REO2TCL_RING",
-	"REO2FW_RING",
-	"RELEASE_RING",
-	"PPE_RELEASE_RING",
-	"TCL2TQM_RING",
-	"TQM_RELEASE_RING",
-	"REO_RELEASE_RING",
-	"WBM2SW0_RELEASE_RING",
-	"WBM2SW1_RELEASE_RING",
-	"WBM2SW2_RELEASE_RING",
-	"WBM2SW3_RELEASE_RING",
-	"REO_CMD_RING",
-	"REO_STATUS_RING",
-};
-
-static const char *htt_bp_lmac_ring[HTT_SW_LMAC_RING_IDX_MAX] = {
-	"FW2RXDMA_BUF_RING",
-	"FW2RXDMA_STATUS_RING",
-	"FW2RXDMA_LINK_RING",
-	"SW2RXDMA_BUF_RING",
-	"WBM2RXDMA_LINK_RING",
-	"RXDMA2FW_RING",
-	"RXDMA2SW_RING",
-	"RXDMA2RELEASE_RING",
-	"RXDMA2REO_RING",
-	"MONITOR_STATUS_RING",
-	"MONITOR_BUF_RING",
-	"MONITOR_DESC_RING",
-	"MONITOR_DEST_RING",
-};
 
 void ath11k_info(struct ath11k_base *ab, const char *fmt, ...)
 {
@@ -95,6 +53,7 @@ void ath11k_warn(struct ath11k_base *ab, const char *fmt, ...)
 EXPORT_SYMBOL(ath11k_warn);
 
 #ifdef CONFIG_ATH11K_DEBUG
+
 void __ath11k_dbg(struct ath11k_base *ab, enum ath11k_debug_mask mask,
 		  const char *fmt, ...)
 {
@@ -144,1067 +103,4 @@ void ath11k_dbg_dump(struct ath11k_base *ab,
 }
 EXPORT_SYMBOL(ath11k_dbg_dump);
 
-#endif
-
-#ifdef CONFIG_ATH11K_DEBUGFS
-static void ath11k_fw_stats_pdevs_free(struct list_head *head)
-{
-	struct ath11k_fw_stats_pdev *i, *tmp;
-
-	list_for_each_entry_safe(i, tmp, head, list) {
-		list_del(&i->list);
-		kfree(i);
-	}
-}
-
-static void ath11k_fw_stats_vdevs_free(struct list_head *head)
-{
-	struct ath11k_fw_stats_vdev *i, *tmp;
-
-	list_for_each_entry_safe(i, tmp, head, list) {
-		list_del(&i->list);
-		kfree(i);
-	}
-}
-
-static void ath11k_fw_stats_bcn_free(struct list_head *head)
-{
-	struct ath11k_fw_stats_bcn *i, *tmp;
-
-	list_for_each_entry_safe(i, tmp, head, list) {
-		list_del(&i->list);
-		kfree(i);
-	}
-}
-
-static void ath11k_debug_fw_stats_reset(struct ath11k *ar)
-{
-	spin_lock_bh(&ar->data_lock);
-	ar->debug.fw_stats_done = false;
-	ath11k_fw_stats_pdevs_free(&ar->debug.fw_stats.pdevs);
-	ath11k_fw_stats_vdevs_free(&ar->debug.fw_stats.vdevs);
-	spin_unlock_bh(&ar->data_lock);
-}
-
-void ath11k_debug_fw_stats_process(struct ath11k_base *ab, struct sk_buff *skb)
-{
-	struct ath11k_fw_stats stats = {};
-	struct ath11k *ar;
-	struct ath11k_pdev *pdev;
-	bool is_end;
-	static unsigned int num_vdev, num_bcn;
-	size_t total_vdevs_started = 0;
-	int i, ret;
-
-	INIT_LIST_HEAD(&stats.pdevs);
-	INIT_LIST_HEAD(&stats.vdevs);
-	INIT_LIST_HEAD(&stats.bcn);
-
-	ret = ath11k_wmi_pull_fw_stats(ab, skb, &stats);
-	if (ret) {
-		ath11k_warn(ab, "failed to pull fw stats: %d\n", ret);
-		goto free;
-	}
-
-	rcu_read_lock();
-	ar = ath11k_mac_get_ar_by_pdev_id(ab, stats.pdev_id);
-	if (!ar) {
-		rcu_read_unlock();
-		ath11k_warn(ab, "failed to get ar for pdev_id %d: %d\n",
-			    stats.pdev_id, ret);
-		goto free;
-	}
-
-	spin_lock_bh(&ar->data_lock);
-
-	if (stats.stats_id == WMI_REQUEST_PDEV_STAT) {
-		list_splice_tail_init(&stats.pdevs, &ar->debug.fw_stats.pdevs);
-		ar->debug.fw_stats_done = true;
-		goto complete;
-	}
-
-	if (stats.stats_id == WMI_REQUEST_VDEV_STAT) {
-		if (list_empty(&stats.vdevs)) {
-			ath11k_warn(ab, "empty vdev stats");
-			goto complete;
-		}
-		/* FW sends all the active VDEV stats irrespective of PDEV,
-		 * hence limit until the count of all VDEVs started
-		 */
-		for (i = 0; i < ab->num_radios; i++) {
-			pdev = rcu_dereference(ab->pdevs_active[i]);
-			if (pdev && pdev->ar)
-				total_vdevs_started += ar->num_started_vdevs;
-		}
-
-		is_end = ((++num_vdev) == total_vdevs_started);
-
-		list_splice_tail_init(&stats.vdevs,
-				      &ar->debug.fw_stats.vdevs);
-
-		if (is_end) {
-			ar->debug.fw_stats_done = true;
-			num_vdev = 0;
-		}
-		goto complete;
-	}
-
-	if (stats.stats_id == WMI_REQUEST_BCN_STAT) {
-		if (list_empty(&stats.bcn)) {
-			ath11k_warn(ab, "empty bcn stats");
-			goto complete;
-		}
-		/* Mark end until we reached the count of all started VDEVs
-		 * within the PDEV
-		 */
-		is_end = ((++num_bcn) == ar->num_started_vdevs);
-
-		list_splice_tail_init(&stats.bcn,
-				      &ar->debug.fw_stats.bcn);
-
-		if (is_end) {
-			ar->debug.fw_stats_done = true;
-			num_bcn = 0;
-		}
-	}
-complete:
-	complete(&ar->debug.fw_stats_complete);
-	rcu_read_unlock();
-	spin_unlock_bh(&ar->data_lock);
-
-free:
-	ath11k_fw_stats_pdevs_free(&stats.pdevs);
-	ath11k_fw_stats_vdevs_free(&stats.vdevs);
-	ath11k_fw_stats_bcn_free(&stats.bcn);
-}
-
-static int ath11k_debug_fw_stats_request(struct ath11k *ar,
-					 struct stats_request_params *req_param)
-{
-	struct ath11k_base *ab = ar->ab;
-	unsigned long timeout, time_left;
-	int ret;
-
-	lockdep_assert_held(&ar->conf_mutex);
-
-	/* FW stats can get split when exceeding the stats data buffer limit.
-	 * In that case, since there is no end marking for the back-to-back
-	 * received 'update stats' event, we keep a 3 seconds timeout in case,
-	 * fw_stats_done is not marked yet
-	 */
-	timeout = jiffies + msecs_to_jiffies(3 * HZ);
-
-	ath11k_debug_fw_stats_reset(ar);
-
-	reinit_completion(&ar->debug.fw_stats_complete);
-
-	ret = ath11k_wmi_send_stats_request_cmd(ar, req_param);
-
-	if (ret) {
-		ath11k_warn(ab, "could not request fw stats (%d)\n",
-			    ret);
-		return ret;
-	}
-
-	time_left =
-	wait_for_completion_timeout(&ar->debug.fw_stats_complete,
-				    1 * HZ);
-	if (!time_left)
-		return -ETIMEDOUT;
-
-	for (;;) {
-		if (time_after(jiffies, timeout))
-			break;
-
-		spin_lock_bh(&ar->data_lock);
-		if (ar->debug.fw_stats_done) {
-			spin_unlock_bh(&ar->data_lock);
-			break;
-		}
-		spin_unlock_bh(&ar->data_lock);
-	}
-	return 0;
-}
-
-static int ath11k_open_pdev_stats(struct inode *inode, struct file *file)
-{
-	struct ath11k *ar = inode->i_private;
-	struct ath11k_base *ab = ar->ab;
-	struct stats_request_params req_param;
-	void *buf = NULL;
-	int ret;
-
-	mutex_lock(&ar->conf_mutex);
-
-	if (ar->state != ATH11K_STATE_ON) {
-		ret = -ENETDOWN;
-		goto err_unlock;
-	}
-
-	buf = vmalloc(ATH11K_FW_STATS_BUF_SIZE);
-	if (!buf) {
-		ret = -ENOMEM;
-		goto err_unlock;
-	}
-
-	req_param.pdev_id = ar->pdev->pdev_id;
-	req_param.vdev_id = 0;
-	req_param.stats_id = WMI_REQUEST_PDEV_STAT;
-
-	ret = ath11k_debug_fw_stats_request(ar, &req_param);
-	if (ret) {
-		ath11k_warn(ab, "failed to request fw pdev stats: %d\n", ret);
-		goto err_free;
-	}
-
-	ath11k_wmi_fw_stats_fill(ar, &ar->debug.fw_stats, req_param.stats_id,
-				 buf);
-
-	file->private_data = buf;
-
-	mutex_unlock(&ar->conf_mutex);
-	return 0;
-
-err_free:
-	vfree(buf);
-
-err_unlock:
-	mutex_unlock(&ar->conf_mutex);
-	return ret;
-}
-
-static int ath11k_release_pdev_stats(struct inode *inode, struct file *file)
-{
-	vfree(file->private_data);
-
-	return 0;
-}
-
-static ssize_t ath11k_read_pdev_stats(struct file *file,
-				      char __user *user_buf,
-				      size_t count, loff_t *ppos)
-{
-	const char *buf = file->private_data;
-	size_t len = strlen(buf);
-
-	return simple_read_from_buffer(user_buf, count, ppos, buf, len);
-}
-
-static const struct file_operations fops_pdev_stats = {
-	.open = ath11k_open_pdev_stats,
-	.release = ath11k_release_pdev_stats,
-	.read = ath11k_read_pdev_stats,
-	.owner = THIS_MODULE,
-	.llseek = default_llseek,
-};
-
-static int ath11k_open_vdev_stats(struct inode *inode, struct file *file)
-{
-	struct ath11k *ar = inode->i_private;
-	struct stats_request_params req_param;
-	void *buf = NULL;
-	int ret;
-
-	mutex_lock(&ar->conf_mutex);
-
-	if (ar->state != ATH11K_STATE_ON) {
-		ret = -ENETDOWN;
-		goto err_unlock;
-	}
-
-	buf = vmalloc(ATH11K_FW_STATS_BUF_SIZE);
-	if (!buf) {
-		ret = -ENOMEM;
-		goto err_unlock;
-	}
-
-	req_param.pdev_id = ar->pdev->pdev_id;
-	/* VDEV stats is always sent for all active VDEVs from FW */
-	req_param.vdev_id = 0;
-	req_param.stats_id = WMI_REQUEST_VDEV_STAT;
-
-	ret = ath11k_debug_fw_stats_request(ar, &req_param);
-	if (ret) {
-		ath11k_warn(ar->ab, "failed to request fw vdev stats: %d\n", ret);
-		goto err_free;
-	}
-
-	ath11k_wmi_fw_stats_fill(ar, &ar->debug.fw_stats, req_param.stats_id,
-				 buf);
-
-	file->private_data = buf;
-
-	mutex_unlock(&ar->conf_mutex);
-	return 0;
-
-err_free:
-	vfree(buf);
-
-err_unlock:
-	mutex_unlock(&ar->conf_mutex);
-	return ret;
-}
-
-static int ath11k_release_vdev_stats(struct inode *inode, struct file *file)
-{
-	vfree(file->private_data);
-
-	return 0;
-}
-
-static ssize_t ath11k_read_vdev_stats(struct file *file,
-				      char __user *user_buf,
-				      size_t count, loff_t *ppos)
-{
-	const char *buf = file->private_data;
-	size_t len = strlen(buf);
-
-	return simple_read_from_buffer(user_buf, count, ppos, buf, len);
-}
-
-static const struct file_operations fops_vdev_stats = {
-	.open = ath11k_open_vdev_stats,
-	.release = ath11k_release_vdev_stats,
-	.read = ath11k_read_vdev_stats,
-	.owner = THIS_MODULE,
-	.llseek = default_llseek,
-};
-
-static int ath11k_open_bcn_stats(struct inode *inode, struct file *file)
-{
-	struct ath11k *ar = inode->i_private;
-	struct ath11k_vif *arvif;
-	struct stats_request_params req_param;
-	void *buf = NULL;
-	int ret;
-
-	mutex_lock(&ar->conf_mutex);
-
-	if (ar->state != ATH11K_STATE_ON) {
-		ret = -ENETDOWN;
-		goto err_unlock;
-	}
-
-	buf = vmalloc(ATH11K_FW_STATS_BUF_SIZE);
-	if (!buf) {
-		ret = -ENOMEM;
-		goto err_unlock;
-	}
-
-	req_param.stats_id = WMI_REQUEST_BCN_STAT;
-	req_param.pdev_id = ar->pdev->pdev_id;
-
-	/* loop all active VDEVs for bcn stats */
-	list_for_each_entry(arvif, &ar->arvifs, list) {
-		if (!arvif->is_up)
-			continue;
-
-		req_param.vdev_id = arvif->vdev_id;
-		ret = ath11k_debug_fw_stats_request(ar, &req_param);
-		if (ret) {
-			ath11k_warn(ar->ab, "failed to request fw bcn stats: %d\n", ret);
-			goto err_free;
-		}
-	}
-
-	ath11k_wmi_fw_stats_fill(ar, &ar->debug.fw_stats, req_param.stats_id,
-				 buf);
-
-	/* since beacon stats request is looped for all active VDEVs, saved fw
-	 * stats is not freed for each request until done for all active VDEVs
-	 */
-	spin_lock_bh(&ar->data_lock);
-	ath11k_fw_stats_bcn_free(&ar->debug.fw_stats.bcn);
-	spin_unlock_bh(&ar->data_lock);
-
-	file->private_data = buf;
-
-	mutex_unlock(&ar->conf_mutex);
-	return 0;
-
-err_free:
-	vfree(buf);
-
-err_unlock:
-	mutex_unlock(&ar->conf_mutex);
-	return ret;
-}
-
-static int ath11k_release_bcn_stats(struct inode *inode, struct file *file)
-{
-	vfree(file->private_data);
-
-	return 0;
-}
-
-static ssize_t ath11k_read_bcn_stats(struct file *file,
-				     char __user *user_buf,
-				     size_t count, loff_t *ppos)
-{
-	const char *buf = file->private_data;
-	size_t len = strlen(buf);
-
-	return simple_read_from_buffer(user_buf, count, ppos, buf, len);
-}
-
-static const struct file_operations fops_bcn_stats = {
-	.open = ath11k_open_bcn_stats,
-	.release = ath11k_release_bcn_stats,
-	.read = ath11k_read_bcn_stats,
-	.owner = THIS_MODULE,
-	.llseek = default_llseek,
-};
-
-static ssize_t ath11k_read_simulate_fw_crash(struct file *file,
-					     char __user *user_buf,
-					     size_t count, loff_t *ppos)
-{
-	const char buf[] =
-		"To simulate firmware crash write one of the keywords to this file:\n"
-		"`assert` - this will send WMI_FORCE_FW_HANG_CMDID to firmware to cause assert.\n"
-		"`hw-restart` - this will simply queue hw restart without fw/hw actually crashing.\n";
-
-	return simple_read_from_buffer(user_buf, count, ppos, buf, strlen(buf));
-}
-
-/* Simulate firmware crash:
- * 'soft': Call wmi command causing firmware hang. This firmware hang is
- * recoverable by warm firmware reset.
- * 'hard': Force firmware crash by setting any vdev parameter for not allowed
- * vdev id. This is hard firmware crash because it is recoverable only by cold
- * firmware reset.
- */
-static ssize_t ath11k_write_simulate_fw_crash(struct file *file,
-					      const char __user *user_buf,
-					      size_t count, loff_t *ppos)
-{
-	struct ath11k_base *ab = file->private_data;
-	struct ath11k_pdev *pdev;
-	struct ath11k *ar = ab->pdevs[0].ar;
-	char buf[32] = {0};
-	ssize_t rc;
-	int i, ret, radioup = 0;
-
-	for (i = 0; i < ab->num_radios; i++) {
-		pdev = &ab->pdevs[i];
-		ar = pdev->ar;
-		if (ar && ar->state == ATH11K_STATE_ON) {
-			radioup = 1;
-			break;
-		}
-	}
-	/* filter partial writes and invalid commands */
-	if (*ppos != 0 || count >= sizeof(buf) || count == 0)
-		return -EINVAL;
-
-	rc = simple_write_to_buffer(buf, sizeof(buf) - 1, ppos, user_buf, count);
-	if (rc < 0)
-		return rc;
-
-	/* drop the possible '\n' from the end */
-	if (buf[*ppos - 1] == '\n')
-		buf[*ppos - 1] = '\0';
-
-	if (radioup == 0) {
-		ret = -ENETDOWN;
-		goto exit;
-	}
-
-	if (!strcmp(buf, "assert")) {
-		ath11k_info(ab, "simulating firmware assert crash\n");
-		ret = ath11k_wmi_force_fw_hang_cmd(ar,
-						   ATH11K_WMI_FW_HANG_ASSERT_TYPE,
-						   ATH11K_WMI_FW_HANG_DELAY);
-	} else {
-		ret = -EINVAL;
-		goto exit;
-	}
-
-	if (ret) {
-		ath11k_warn(ab, "failed to simulate firmware crash: %d\n", ret);
-		goto exit;
-	}
-
-	ret = count;
-
-exit:
-	return ret;
-}
-
-static const struct file_operations fops_simulate_fw_crash = {
-	.read = ath11k_read_simulate_fw_crash,
-	.write = ath11k_write_simulate_fw_crash,
-	.open = simple_open,
-	.owner = THIS_MODULE,
-	.llseek = default_llseek,
-};
-
-static ssize_t ath11k_write_enable_extd_tx_stats(struct file *file,
-						 const char __user *ubuf,
-						 size_t count, loff_t *ppos)
-{
-	struct ath11k *ar = file->private_data;
-	u32 filter;
-	int ret;
-
-	if (kstrtouint_from_user(ubuf, count, 0, &filter))
-		return -EINVAL;
-
-	mutex_lock(&ar->conf_mutex);
-
-	if (ar->state != ATH11K_STATE_ON) {
-		ret = -ENETDOWN;
-		goto out;
-	}
-
-	if (filter == ar->debug.extd_tx_stats) {
-		ret = count;
-		goto out;
-	}
-
-	ar->debug.extd_tx_stats = filter;
-	ret = count;
-
-out:
-	mutex_unlock(&ar->conf_mutex);
-	return ret;
-}
-
-static ssize_t ath11k_read_enable_extd_tx_stats(struct file *file,
-						char __user *ubuf,
-						size_t count, loff_t *ppos)
-
-{
-	char buf[32] = {0};
-	struct ath11k *ar = file->private_data;
-	int len = 0;
-
-	mutex_lock(&ar->conf_mutex);
-	len = scnprintf(buf, sizeof(buf) - len, "%08x\n",
-			ar->debug.extd_tx_stats);
-	mutex_unlock(&ar->conf_mutex);
-
-	return simple_read_from_buffer(ubuf, count, ppos, buf, len);
-}
-
-static const struct file_operations fops_extd_tx_stats = {
-	.read = ath11k_read_enable_extd_tx_stats,
-	.write = ath11k_write_enable_extd_tx_stats,
-	.open = simple_open
-};
-
-static ssize_t ath11k_write_extd_rx_stats(struct file *file,
-					  const char __user *ubuf,
-					  size_t count, loff_t *ppos)
-{
-	struct ath11k *ar = file->private_data;
-	struct ath11k_base *ab = ar->ab;
-	struct htt_rx_ring_tlv_filter tlv_filter = {0};
-	u32 enable, rx_filter = 0, ring_id;
-	int i;
-	int ret;
-
-	if (kstrtouint_from_user(ubuf, count, 0, &enable))
-		return -EINVAL;
-
-	mutex_lock(&ar->conf_mutex);
-
-	if (ar->state != ATH11K_STATE_ON) {
-		ret = -ENETDOWN;
-		goto exit;
-	}
-
-	if (enable > 1) {
-		ret = -EINVAL;
-		goto exit;
-	}
-
-	if (enable == ar->debug.extd_rx_stats) {
-		ret = count;
-		goto exit;
-	}
-
-	if (enable) {
-		rx_filter =  HTT_RX_FILTER_TLV_FLAGS_MPDU_START;
-		rx_filter |= HTT_RX_FILTER_TLV_FLAGS_PPDU_START;
-		rx_filter |= HTT_RX_FILTER_TLV_FLAGS_PPDU_END;
-		rx_filter |= HTT_RX_FILTER_TLV_FLAGS_PPDU_END_USER_STATS;
-		rx_filter |= HTT_RX_FILTER_TLV_FLAGS_PPDU_END_USER_STATS_EXT;
-		rx_filter |= HTT_RX_FILTER_TLV_FLAGS_PPDU_END_STATUS_DONE;
-
-		tlv_filter.rx_filter = rx_filter;
-		tlv_filter.pkt_filter_flags0 = HTT_RX_FP_MGMT_FILTER_FLAGS0;
-		tlv_filter.pkt_filter_flags1 = HTT_RX_FP_MGMT_FILTER_FLAGS1;
-		tlv_filter.pkt_filter_flags2 = HTT_RX_FP_CTRL_FILTER_FLASG2;
-		tlv_filter.pkt_filter_flags3 = HTT_RX_FP_CTRL_FILTER_FLASG3 |
-			HTT_RX_FP_DATA_FILTER_FLASG3;
-	} else {
-		tlv_filter = ath11k_mac_mon_status_filter_default;
-	}
-
-	ar->debug.rx_filter = tlv_filter.rx_filter;
-
-	for (i = 0; i < ab->hw_params.num_rxmda_per_pdev; i++) {
-		ring_id = ar->dp.rx_mon_status_refill_ring[i].refill_buf_ring.ring_id;
-		ret = ath11k_dp_tx_htt_rx_filter_setup(ar->ab, ring_id, ar->dp.mac_id,
-						       HAL_RXDMA_MONITOR_STATUS,
-						       DP_RX_BUFFER_SIZE, &tlv_filter);
-
-		if (ret) {
-			ath11k_warn(ar->ab, "failed to set rx filter for monitor status ring\n");
-			goto exit;
-		}
-	}
-
-	ar->debug.extd_rx_stats = enable;
-	ret = count;
-exit:
-	mutex_unlock(&ar->conf_mutex);
-	return ret;
-}
-
-static ssize_t ath11k_read_extd_rx_stats(struct file *file,
-					 char __user *ubuf,
-					 size_t count, loff_t *ppos)
-{
-	struct ath11k *ar = file->private_data;
-	char buf[32];
-	int len = 0;
-
-	mutex_lock(&ar->conf_mutex);
-	len = scnprintf(buf, sizeof(buf) - len, "%d\n",
-			ar->debug.extd_rx_stats);
-	mutex_unlock(&ar->conf_mutex);
-
-	return simple_read_from_buffer(ubuf, count, ppos, buf, len);
-}
-
-static const struct file_operations fops_extd_rx_stats = {
-	.read = ath11k_read_extd_rx_stats,
-	.write = ath11k_write_extd_rx_stats,
-	.open = simple_open,
-};
-
-static int ath11k_fill_bp_stats(struct ath11k_base *ab,
-				struct ath11k_bp_stats *bp_stats,
-				char *buf, int len, int size)
-{
-	lockdep_assert_held(&ab->base_lock);
-
-	len += scnprintf(buf + len, size - len, "count: %u\n",
-			 bp_stats->count);
-	len += scnprintf(buf + len, size - len, "hp: %u\n",
-			 bp_stats->hp);
-	len += scnprintf(buf + len, size - len, "tp: %u\n",
-			 bp_stats->tp);
-	len += scnprintf(buf + len, size - len, "seen before: %ums\n\n",
-			 jiffies_to_msecs(jiffies - bp_stats->jiffies));
-	return len;
-}
-
-static ssize_t ath11k_debug_dump_soc_ring_bp_stats(struct ath11k_base *ab,
-						   char *buf, int size)
-{
-	struct ath11k_bp_stats *bp_stats;
-	bool stats_rxd = false;
-	u8 i, pdev_idx;
-	int len = 0;
-
-	len += scnprintf(buf + len, size - len, "\nBackpressure Stats\n");
-	len += scnprintf(buf + len, size - len, "==================\n");
-
-	spin_lock_bh(&ab->base_lock);
-	for (i = 0; i < HTT_SW_UMAC_RING_IDX_MAX; i++) {
-		bp_stats = &ab->soc_stats.bp_stats.umac_ring_bp_stats[i];
-
-		if (!bp_stats->count)
-			continue;
-
-		len += scnprintf(buf + len, size - len, "Ring: %s\n",
-				 htt_bp_umac_ring[i]);
-		len = ath11k_fill_bp_stats(ab, bp_stats, buf, len, size);
-		stats_rxd = true;
-	}
-
-	for (i = 0; i < HTT_SW_LMAC_RING_IDX_MAX; i++) {
-		for (pdev_idx = 0; pdev_idx < MAX_RADIOS; pdev_idx++) {
-			bp_stats =
-				&ab->soc_stats.bp_stats.lmac_ring_bp_stats[i][pdev_idx];
-
-			if (!bp_stats->count)
-				continue;
-
-			len += scnprintf(buf + len, size - len, "Ring: %s\n",
-					 htt_bp_lmac_ring[i]);
-			len += scnprintf(buf + len, size - len, "pdev: %d\n",
-					 pdev_idx);
-			len = ath11k_fill_bp_stats(ab, bp_stats, buf, len, size);
-			stats_rxd = true;
-		}
-	}
-	spin_unlock_bh(&ab->base_lock);
-
-	if (!stats_rxd)
-		len += scnprintf(buf + len, size - len,
-				 "No Ring Backpressure stats received\n\n");
-
-	return len;
-}
-
-static ssize_t ath11k_debug_dump_soc_dp_stats(struct file *file,
-					      char __user *user_buf,
-					      size_t count, loff_t *ppos)
-{
-	struct ath11k_base *ab = file->private_data;
-	struct ath11k_soc_dp_stats *soc_stats = &ab->soc_stats;
-	int len = 0, i, retval;
-	const int size = 4096;
-	static const char *rxdma_err[HAL_REO_ENTR_RING_RXDMA_ECODE_MAX] = {
-			"Overflow", "MPDU len", "FCS", "Decrypt", "TKIP MIC",
-			"Unencrypt", "MSDU len", "MSDU limit", "WiFi parse",
-			"AMSDU parse", "SA timeout", "DA timeout",
-			"Flow timeout", "Flush req"};
-	static const char *reo_err[HAL_REO_DEST_RING_ERROR_CODE_MAX] = {
-			"Desc addr zero", "Desc inval", "AMPDU in non BA",
-			"Non BA dup", "BA dup", "Frame 2k jump", "BAR 2k jump",
-			"Frame OOR", "BAR OOR", "No BA session",
-			"Frame SN equal SSN", "PN check fail", "2k err",
-			"PN err", "Desc blocked"};
-
-	char *buf;
-
-	buf = kzalloc(size, GFP_KERNEL);
-	if (!buf)
-		return -ENOMEM;
-
-	len += scnprintf(buf + len, size - len, "SOC RX STATS:\n\n");
-	len += scnprintf(buf + len, size - len, "err ring pkts: %u\n",
-			 soc_stats->err_ring_pkts);
-	len += scnprintf(buf + len, size - len, "Invalid RBM: %u\n\n",
-			 soc_stats->invalid_rbm);
-	len += scnprintf(buf + len, size - len, "RXDMA errors:\n");
-	for (i = 0; i < HAL_REO_ENTR_RING_RXDMA_ECODE_MAX; i++)
-		len += scnprintf(buf + len, size - len, "%s: %u\n",
-				 rxdma_err[i], soc_stats->rxdma_error[i]);
-
-	len += scnprintf(buf + len, size - len, "\nREO errors:\n");
-	for (i = 0; i < HAL_REO_DEST_RING_ERROR_CODE_MAX; i++)
-		len += scnprintf(buf + len, size - len, "%s: %u\n",
-				 reo_err[i], soc_stats->reo_error[i]);
-
-	len += scnprintf(buf + len, size - len, "\nHAL REO errors:\n");
-	len += scnprintf(buf + len, size - len,
-			 "ring0: %u\nring1: %u\nring2: %u\nring3: %u\n",
-			 soc_stats->hal_reo_error[0],
-			 soc_stats->hal_reo_error[1],
-			 soc_stats->hal_reo_error[2],
-			 soc_stats->hal_reo_error[3]);
-
-	len += scnprintf(buf + len, size - len, "\nSOC TX STATS:\n");
-	len += scnprintf(buf + len, size - len, "\nTCL Ring Full Failures:\n");
-
-	for (i = 0; i < DP_TCL_NUM_RING_MAX; i++)
-		len += scnprintf(buf + len, size - len, "ring%d: %u\n",
-				 i, soc_stats->tx_err.desc_na[i]);
-
-	len += scnprintf(buf + len, size - len,
-			 "\nMisc Transmit Failures: %d\n",
-			 atomic_read(&soc_stats->tx_err.misc_fail));
-
-	len += ath11k_debug_dump_soc_ring_bp_stats(ab, buf + len, size - len);
-
-	if (len > size)
-		len = size;
-	retval = simple_read_from_buffer(user_buf, count, ppos, buf, len);
-	kfree(buf);
-
-	return retval;
-}
-
-static const struct file_operations fops_soc_dp_stats = {
-	.read = ath11k_debug_dump_soc_dp_stats,
-	.open = simple_open,
-	.owner = THIS_MODULE,
-	.llseek = default_llseek,
-};
-
-int ath11k_debug_pdev_create(struct ath11k_base *ab)
-{
-	if (test_bit(ATH11K_FLAG_REGISTERED, &ab->dev_flags))
-		return 0;
-
-	ab->debugfs_soc = debugfs_create_dir(ab->hw_params.name, ab->debugfs_ath11k);
-
-	if (IS_ERR_OR_NULL(ab->debugfs_soc)) {
-		if (IS_ERR(ab->debugfs_soc))
-			return PTR_ERR(ab->debugfs_soc);
-		return -ENOMEM;
-	}
-
-	debugfs_create_file("simulate_fw_crash", 0600, ab->debugfs_soc, ab,
-			    &fops_simulate_fw_crash);
-
-	debugfs_create_file("soc_dp_stats", 0600, ab->debugfs_soc, ab,
-			    &fops_soc_dp_stats);
-
-	return 0;
-}
-
-void ath11k_debug_pdev_destroy(struct ath11k_base *ab)
-{
-	debugfs_remove_recursive(ab->debugfs_ath11k);
-	ab->debugfs_ath11k = NULL;
-}
-
-int ath11k_debug_soc_create(struct ath11k_base *ab)
-{
-	ab->debugfs_ath11k = debugfs_create_dir("ath11k", NULL);
-
-	if (IS_ERR_OR_NULL(ab->debugfs_ath11k)) {
-		if (IS_ERR(ab->debugfs_ath11k))
-			return PTR_ERR(ab->debugfs_ath11k);
-		return -ENOMEM;
-	}
-
-	return 0;
-}
-
-void ath11k_debug_soc_destroy(struct ath11k_base *ab)
-{
-	debugfs_remove_recursive(ab->debugfs_soc);
-	ab->debugfs_soc = NULL;
-}
-
-void ath11k_debug_fw_stats_init(struct ath11k *ar)
-{
-	struct dentry *fwstats_dir = debugfs_create_dir("fw_stats",
-							ar->debug.debugfs_pdev);
-
-	ar->debug.fw_stats.debugfs_fwstats = fwstats_dir;
-
-	/* all stats debugfs files created are under "fw_stats" directory
-	 * created per PDEV
-	 */
-	debugfs_create_file("pdev_stats", 0600, fwstats_dir, ar,
-			    &fops_pdev_stats);
-	debugfs_create_file("vdev_stats", 0600, fwstats_dir, ar,
-			    &fops_vdev_stats);
-	debugfs_create_file("beacon_stats", 0600, fwstats_dir, ar,
-			    &fops_bcn_stats);
-
-	INIT_LIST_HEAD(&ar->debug.fw_stats.pdevs);
-	INIT_LIST_HEAD(&ar->debug.fw_stats.vdevs);
-	INIT_LIST_HEAD(&ar->debug.fw_stats.bcn);
-
-	init_completion(&ar->debug.fw_stats_complete);
-}
-
-static ssize_t ath11k_write_pktlog_filter(struct file *file,
-					  const char __user *ubuf,
-					  size_t count, loff_t *ppos)
-{
-	struct ath11k *ar = file->private_data;
-	struct ath11k_base *ab = ar->ab;
-	struct htt_rx_ring_tlv_filter tlv_filter = {0};
-	u32 rx_filter = 0, ring_id, filter, mode;
-	u8 buf[128] = {0};
-	int i, ret;
-	ssize_t rc;
-
-	mutex_lock(&ar->conf_mutex);
-	if (ar->state != ATH11K_STATE_ON) {
-		ret = -ENETDOWN;
-		goto out;
-	}
-
-	rc = simple_write_to_buffer(buf, sizeof(buf) - 1, ppos, ubuf, count);
-	if (rc < 0) {
-		ret = rc;
-		goto out;
-	}
-	buf[rc] = '\0';
-
-	ret = sscanf(buf, "0x%x %u", &filter, &mode);
-	if (ret != 2) {
-		ret = -EINVAL;
-		goto out;
-	}
-
-	if (filter) {
-		ret = ath11k_wmi_pdev_pktlog_enable(ar, filter);
-		if (ret) {
-			ath11k_warn(ar->ab,
-				    "failed to enable pktlog filter %x: %d\n",
-				    ar->debug.pktlog_filter, ret);
-			goto out;
-		}
-	} else {
-		ret = ath11k_wmi_pdev_pktlog_disable(ar);
-		if (ret) {
-			ath11k_warn(ar->ab, "failed to disable pktlog: %d\n", ret);
-			goto out;
-		}
-	}
-
-#define HTT_RX_FILTER_TLV_LITE_MODE \
-			(HTT_RX_FILTER_TLV_FLAGS_PPDU_START | \
-			HTT_RX_FILTER_TLV_FLAGS_PPDU_END | \
-			HTT_RX_FILTER_TLV_FLAGS_PPDU_END_USER_STATS | \
-			HTT_RX_FILTER_TLV_FLAGS_PPDU_END_USER_STATS_EXT | \
-			HTT_RX_FILTER_TLV_FLAGS_PPDU_END_STATUS_DONE | \
-			HTT_RX_FILTER_TLV_FLAGS_MPDU_START)
-
-	if (mode == ATH11K_PKTLOG_MODE_FULL) {
-		rx_filter = HTT_RX_FILTER_TLV_LITE_MODE |
-			    HTT_RX_FILTER_TLV_FLAGS_MSDU_START |
-			    HTT_RX_FILTER_TLV_FLAGS_MSDU_END |
-			    HTT_RX_FILTER_TLV_FLAGS_MPDU_END |
-			    HTT_RX_FILTER_TLV_FLAGS_PACKET_HEADER |
-			    HTT_RX_FILTER_TLV_FLAGS_ATTENTION;
-	} else if (mode == ATH11K_PKTLOG_MODE_LITE) {
-		ret = ath11k_dp_tx_htt_h2t_ppdu_stats_req(ar,
-							  HTT_PPDU_STATS_TAG_PKTLOG);
-		if (ret) {
-			ath11k_err(ar->ab, "failed to enable pktlog lite: %d\n", ret);
-			goto out;
-		}
-
-		rx_filter = HTT_RX_FILTER_TLV_LITE_MODE;
-	} else {
-		ret = ath11k_dp_tx_htt_h2t_ppdu_stats_req(ar,
-							  HTT_PPDU_STATS_TAG_DEFAULT);
-		if (ret) {
-			ath11k_err(ar->ab, "failed to send htt ppdu stats req: %d\n",
-				   ret);
-			goto out;
-		}
-	}
-
-	tlv_filter.rx_filter = rx_filter;
-	if (rx_filter) {
-		tlv_filter.pkt_filter_flags0 = HTT_RX_FP_MGMT_FILTER_FLAGS0;
-		tlv_filter.pkt_filter_flags1 = HTT_RX_FP_MGMT_FILTER_FLAGS1;
-		tlv_filter.pkt_filter_flags2 = HTT_RX_FP_CTRL_FILTER_FLASG2;
-		tlv_filter.pkt_filter_flags3 = HTT_RX_FP_CTRL_FILTER_FLASG3 |
-					       HTT_RX_FP_DATA_FILTER_FLASG3;
-	}
-
-	for (i = 0; i < ab->hw_params.num_rxmda_per_pdev; i++) {
-		ring_id = ar->dp.rx_mon_status_refill_ring[i].refill_buf_ring.ring_id;
-		ret = ath11k_dp_tx_htt_rx_filter_setup(ab, ring_id,
-						       ar->dp.mac_id + i,
-						       HAL_RXDMA_MONITOR_STATUS,
-						       DP_RX_BUFFER_SIZE, &tlv_filter);
-
-		if (ret) {
-			ath11k_warn(ab, "failed to set rx filter for monitor status ring\n");
-			goto out;
-		}
-	}
-
-	ath11k_dbg(ab, ATH11K_DBG_WMI, "pktlog filter %d mode %s\n",
-		   filter, ((mode == ATH11K_PKTLOG_MODE_FULL) ? "full" : "lite"));
-
-	ar->debug.pktlog_filter = filter;
-	ar->debug.pktlog_mode = mode;
-	ret = count;
-
-out:
-	mutex_unlock(&ar->conf_mutex);
-	return ret;
-}
-
-static ssize_t ath11k_read_pktlog_filter(struct file *file,
-					 char __user *ubuf,
-					 size_t count, loff_t *ppos)
-
-{
-	char buf[32] = {0};
-	struct ath11k *ar = file->private_data;
-	int len = 0;
-
-	mutex_lock(&ar->conf_mutex);
-	len = scnprintf(buf, sizeof(buf) - len, "%08x %08x\n",
-			ar->debug.pktlog_filter,
-			ar->debug.pktlog_mode);
-	mutex_unlock(&ar->conf_mutex);
-
-	return simple_read_from_buffer(ubuf, count, ppos, buf, len);
-}
-
-static const struct file_operations fops_pktlog_filter = {
-	.read = ath11k_read_pktlog_filter,
-	.write = ath11k_write_pktlog_filter,
-	.open = simple_open
-};
-
-static ssize_t ath11k_write_simulate_radar(struct file *file,
-					   const char __user *user_buf,
-					   size_t count, loff_t *ppos)
-{
-	struct ath11k *ar = file->private_data;
-	int ret;
-
-	ret = ath11k_wmi_simulate_radar(ar);
-	if (ret)
-		return ret;
-
-	return count;
-}
-
-static const struct file_operations fops_simulate_radar = {
-	.write = ath11k_write_simulate_radar,
-	.open = simple_open
-};
-
-int ath11k_debug_register(struct ath11k *ar)
-{
-	struct ath11k_base *ab = ar->ab;
-	char pdev_name[5];
-	char buf[100] = {0};
-
-	snprintf(pdev_name, sizeof(pdev_name), "%s%d", "mac", ar->pdev_idx);
-
-	ar->debug.debugfs_pdev = debugfs_create_dir(pdev_name, ab->debugfs_soc);
-
-	if (IS_ERR_OR_NULL(ar->debug.debugfs_pdev)) {
-		if (IS_ERR(ar->debug.debugfs_pdev))
-			return PTR_ERR(ar->debug.debugfs_pdev);
-
-		return -ENOMEM;
-	}
-
-	/* Create a symlink under ieee80211/phy* */
-	snprintf(buf, 100, "../../ath11k/%pd2", ar->debug.debugfs_pdev);
-	debugfs_create_symlink("ath11k", ar->hw->wiphy->debugfsdir, buf);
-
-	ath11k_debug_htt_stats_init(ar);
-
-	ath11k_debug_fw_stats_init(ar);
-
-	debugfs_create_file("ext_tx_stats", 0644,
-			    ar->debug.debugfs_pdev, ar,
-			    &fops_extd_tx_stats);
-	debugfs_create_file("ext_rx_stats", 0644,
-			    ar->debug.debugfs_pdev, ar,
-			    &fops_extd_rx_stats);
-	debugfs_create_file("pktlog_filter", 0644,
-			    ar->debug.debugfs_pdev, ar,
-			    &fops_pktlog_filter);
-
-	if (ar->hw->wiphy->bands[NL80211_BAND_5GHZ]) {
-		debugfs_create_file("dfs_simulate_radar", 0200,
-				    ar->debug.debugfs_pdev, ar,
-				    &fops_simulate_radar);
-		debugfs_create_bool("dfs_block_radar_events", 0200,
-				    ar->debug.debugfs_pdev,
-				    &ar->dfs_block_radar_events);
-	}
-
-	return 0;
-}
-
-void ath11k_debug_unregister(struct ath11k *ar)
-{
-}
-#endif /* CONFIG_ATH11K_DEBUGFS */
+#endif /* CONFIG_ATH11K_DEBUG */
diff --git a/drivers/net/wireless/ath/ath11k/debug.h b/drivers/net/wireless/ath/ath11k/debug.h
index 55717278ec3f..659a275e2eb3 100644
--- a/drivers/net/wireless/ath/ath11k/debug.h
+++ b/drivers/net/wireless/ath/ath11k/debug.h
@@ -6,11 +6,8 @@
 #ifndef _ATH11K_DEBUG_H_
 #define _ATH11K_DEBUG_H_
 
-#include "hal_tx.h"
 #include "trace.h"
-
-#define ATH11K_TX_POWER_MAX_VAL	70
-#define ATH11K_TX_POWER_MIN_VAL	0
+#include "debugfs.h"
 
 enum ath11k_debug_mask {
 	ATH11K_DBG_AHB		= 0x00000001,
@@ -31,98 +28,6 @@ enum ath11k_debug_mask {
 	ATH11K_DBG_ANY		= 0xffffffff,
 };
 
-/* htt_dbg_ext_stats_type */
-enum ath11k_dbg_htt_ext_stats_type {
-	ATH11K_DBG_HTT_EXT_STATS_RESET                      =  0,
-	ATH11K_DBG_HTT_EXT_STATS_PDEV_TX                    =  1,
-	ATH11K_DBG_HTT_EXT_STATS_PDEV_RX                    =  2,
-	ATH11K_DBG_HTT_EXT_STATS_PDEV_TX_HWQ                =  3,
-	ATH11K_DBG_HTT_EXT_STATS_PDEV_TX_SCHED              =  4,
-	ATH11K_DBG_HTT_EXT_STATS_PDEV_ERROR                 =  5,
-	ATH11K_DBG_HTT_EXT_STATS_PDEV_TQM                   =  6,
-	ATH11K_DBG_HTT_EXT_STATS_TQM_CMDQ                   =  7,
-	ATH11K_DBG_HTT_EXT_STATS_TX_DE_INFO                 =  8,
-	ATH11K_DBG_HTT_EXT_STATS_PDEV_TX_RATE               =  9,
-	ATH11K_DBG_HTT_EXT_STATS_PDEV_RX_RATE               =  10,
-	ATH11K_DBG_HTT_EXT_STATS_PEER_INFO                  =  11,
-	ATH11K_DBG_HTT_EXT_STATS_TX_SELFGEN_INFO            =  12,
-	ATH11K_DBG_HTT_EXT_STATS_TX_MU_HWQ                  =  13,
-	ATH11K_DBG_HTT_EXT_STATS_RING_IF_INFO               =  14,
-	ATH11K_DBG_HTT_EXT_STATS_SRNG_INFO                  =  15,
-	ATH11K_DBG_HTT_EXT_STATS_SFM_INFO                   =  16,
-	ATH11K_DBG_HTT_EXT_STATS_PDEV_TX_MU                 =  17,
-	ATH11K_DBG_HTT_EXT_STATS_ACTIVE_PEERS_LIST          =  18,
-	ATH11K_DBG_HTT_EXT_STATS_PDEV_CCA_STATS             =  19,
-	ATH11K_DBG_HTT_EXT_STATS_TWT_SESSIONS               =  20,
-	ATH11K_DBG_HTT_EXT_STATS_REO_RESOURCE_STATS         =  21,
-	ATH11K_DBG_HTT_EXT_STATS_TX_SOUNDING_INFO           =  22,
-	ATH11K_DBG_HTT_EXT_STATS_PDEV_OBSS_PD_STATS	    =  23,
-	ATH11K_DBG_HTT_EXT_STATS_RING_BACKPRESSURE_STATS    =  24,
-
-	/* keep this last */
-	ATH11K_DBG_HTT_NUM_EXT_STATS,
-};
-
-struct debug_htt_stats_req {
-	bool done;
-	u8 pdev_id;
-	u8 type;
-	u8 peer_addr[ETH_ALEN];
-	struct completion cmpln;
-	u32 buf_len;
-	u8 buf[];
-};
-
-struct ath_pktlog_hdr {
-	u16 flags;
-	u16 missed_cnt;
-	u16 log_type;
-	u16 size;
-	u32 timestamp;
-	u32 type_specific_data;
-	u8 payload[];
-};
-
-#define ATH11K_HTT_PEER_STATS_RESET BIT(16)
-
-#define ATH11K_HTT_STATS_BUF_SIZE (1024 * 512)
-#define ATH11K_FW_STATS_BUF_SIZE (1024 * 1024)
-
-enum ath11k_pktlog_filter {
-	ATH11K_PKTLOG_RX		= 0x000000001,
-	ATH11K_PKTLOG_TX		= 0x000000002,
-	ATH11K_PKTLOG_RCFIND		= 0x000000004,
-	ATH11K_PKTLOG_RCUPDATE		= 0x000000008,
-	ATH11K_PKTLOG_EVENT_SMART_ANT	= 0x000000020,
-	ATH11K_PKTLOG_EVENT_SW		= 0x000000040,
-	ATH11K_PKTLOG_ANY		= 0x00000006f,
-};
-
-enum ath11k_pktlog_mode {
-	ATH11K_PKTLOG_MODE_LITE = 1,
-	ATH11K_PKTLOG_MODE_FULL = 2,
-};
-
-enum ath11k_pktlog_enum {
-	ATH11K_PKTLOG_TYPE_TX_CTRL      = 1,
-	ATH11K_PKTLOG_TYPE_TX_STAT      = 2,
-	ATH11K_PKTLOG_TYPE_TX_MSDU_ID   = 3,
-	ATH11K_PKTLOG_TYPE_RX_STAT      = 5,
-	ATH11K_PKTLOG_TYPE_RC_FIND      = 6,
-	ATH11K_PKTLOG_TYPE_RC_UPDATE    = 7,
-	ATH11K_PKTLOG_TYPE_TX_VIRT_ADDR = 8,
-	ATH11K_PKTLOG_TYPE_RX_CBF       = 10,
-	ATH11K_PKTLOG_TYPE_RX_STATBUF   = 22,
-	ATH11K_PKTLOG_TYPE_PPDU_STATS   = 23,
-	ATH11K_PKTLOG_TYPE_LITE_RX      = 24,
-};
-
-enum ath11k_dbg_aggr_mode {
-	ATH11K_DBG_AGGR_MODE_AUTO,
-	ATH11K_DBG_AGGR_MODE_MANUAL,
-	ATH11K_DBG_AGGR_MODE_MAX,
-};
-
 __printf(2, 3) void ath11k_info(struct ath11k_base *ab, const char *fmt, ...);
 __printf(2, 3) void ath11k_err(struct ath11k_base *ab, const char *fmt, ...);
 __printf(2, 3) void ath11k_warn(struct ath11k_base *ab, const char *fmt, ...);
@@ -153,153 +58,6 @@ static inline void ath11k_dbg_dump(struct ath11k_base *ab,
 }
 #endif /* CONFIG_ATH11K_DEBUG */
 
-#ifdef CONFIG_ATH11K_DEBUGFS
-int ath11k_debug_soc_create(struct ath11k_base *ab);
-void ath11k_debug_soc_destroy(struct ath11k_base *ab);
-int ath11k_debug_pdev_create(struct ath11k_base *ab);
-void ath11k_debug_pdev_destroy(struct ath11k_base *ab);
-int ath11k_debug_register(struct ath11k *ar);
-void ath11k_debug_unregister(struct ath11k *ar);
-void ath11k_dbg_htt_ext_stats_handler(struct ath11k_base *ab,
-				      struct sk_buff *skb);
-void ath11k_debug_fw_stats_process(struct ath11k_base *ab, struct sk_buff *skb);
-
-void ath11k_debug_fw_stats_init(struct ath11k *ar);
-int ath11k_dbg_htt_stats_req(struct ath11k *ar);
-
-static inline bool ath11k_debug_is_pktlog_lite_mode_enabled(struct ath11k *ar)
-{
-	return (ar->debug.pktlog_mode == ATH11K_PKTLOG_MODE_LITE);
-}
-
-static inline bool ath11k_debug_is_pktlog_rx_stats_enabled(struct ath11k *ar)
-{
-	return (!ar->debug.pktlog_peer_valid && ar->debug.pktlog_mode);
-}
-
-static inline bool ath11k_debug_is_pktlog_peer_valid(struct ath11k *ar, u8 *addr)
-{
-	return (ar->debug.pktlog_peer_valid && ar->debug.pktlog_mode &&
-		ether_addr_equal(addr, ar->debug.pktlog_peer_addr));
-}
-
-static inline int ath11k_debug_is_extd_tx_stats_enabled(struct ath11k *ar)
-{
-	return ar->debug.extd_tx_stats;
-}
-
-static inline int ath11k_debug_is_extd_rx_stats_enabled(struct ath11k *ar)
-{
-	return ar->debug.extd_rx_stats;
-}
-
-static inline int ath11k_debug_rx_filter(struct ath11k *ar)
-{
-	return ar->debug.rx_filter;
-}
-
-void ath11k_sta_add_debugfs(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
-			    struct ieee80211_sta *sta, struct dentry *dir);
-void
-ath11k_accumulate_per_peer_tx_stats(struct ath11k_sta *arsta,
-				    struct ath11k_per_peer_tx_stats *peer_stats,
-				    u8 legacy_rate_idx);
-void ath11k_update_per_peer_stats_from_txcompl(struct ath11k *ar,
-					       struct sk_buff *msdu,
-					       struct hal_tx_status *ts);
-#else
-static inline int ath11k_debug_soc_create(struct ath11k_base *ab)
-{
-	return 0;
-}
-
-static inline void ath11k_debug_soc_destroy(struct ath11k_base *ab)
-{
-}
-
-static inline int ath11k_debug_pdev_create(struct ath11k_base *ab)
-{
-	return 0;
-}
-
-static inline void ath11k_debug_pdev_destroy(struct ath11k_base *ab)
-{
-}
-
-static inline int ath11k_debug_register(struct ath11k *ar)
-{
-	return 0;
-}
-
-static inline void ath11k_debug_unregister(struct ath11k *ar)
-{
-}
-
-static inline void ath11k_dbg_htt_ext_stats_handler(struct ath11k_base *ab,
-						    struct sk_buff *skb)
-{
-}
-
-static inline void ath11k_debug_fw_stats_process(struct ath11k_base *ab,
-						 struct sk_buff *skb)
-{
-}
-
-static inline void ath11k_debug_fw_stats_init(struct ath11k *ar)
-{
-}
-
-static inline int ath11k_debug_is_extd_tx_stats_enabled(struct ath11k *ar)
-{
-	return 0;
-}
-
-static inline int ath11k_debug_is_extd_rx_stats_enabled(struct ath11k *ar)
-{
-	return 0;
-}
-
-static inline int ath11k_dbg_htt_stats_req(struct ath11k *ar)
-{
-	return 0;
-}
-
-static inline bool ath11k_debug_is_pktlog_lite_mode_enabled(struct ath11k *ar)
-{
-	return false;
-}
-
-static inline bool ath11k_debug_is_pktlog_rx_stats_enabled(struct ath11k *ar)
-{
-	return false;
-}
-
-static inline bool ath11k_debug_is_pktlog_peer_valid(struct ath11k *ar, u8 *addr)
-{
-	return false;
-}
-
-static inline int ath11k_debug_rx_filter(struct ath11k *ar)
-{
-	return 0;
-}
-
-static inline void
-ath11k_accumulate_per_peer_tx_stats(struct ath11k_sta *arsta,
-				    struct ath11k_per_peer_tx_stats *peer_stats,
-				    u8 legacy_rate_idx)
-{
-}
-
-static inline void
-ath11k_update_per_peer_stats_from_txcompl(struct ath11k *ar,
-					  struct sk_buff *msdu,
-					  struct hal_tx_status *ts)
-{
-}
-
-#endif /* CONFIG_MAC80211_DEBUGFS*/
-
 #define ath11k_dbg(ar, dbg_mask, fmt, ...)			\
 do {								\
 	if (ath11k_debug_mask & dbg_mask)			\
diff --git a/drivers/net/wireless/ath/ath11k/debugfs.c b/drivers/net/wireless/ath/ath11k/debugfs.c
new file mode 100644
index 000000000000..1b914e67d314
--- /dev/null
+++ b/drivers/net/wireless/ath/ath11k/debugfs.c
@@ -0,0 +1,1097 @@
+// SPDX-License-Identifier: BSD-3-Clause-Clear
+/*
+ * Copyright (c) 2018-2020 The Linux Foundation. All rights reserved.
+ */
+
+#include "debugfs.h"
+
+#include "core.h"
+#include "debug.h"
+#include "wmi.h"
+#include "hal_rx.h"
+#include "dp_tx.h"
+#include "debugfs_htt_stats.h"
+#include "peer.h"
+
+static const char *htt_bp_umac_ring[HTT_SW_UMAC_RING_IDX_MAX] = {
+	"REO2SW1_RING",
+	"REO2SW2_RING",
+	"REO2SW3_RING",
+	"REO2SW4_RING",
+	"WBM2REO_LINK_RING",
+	"REO2TCL_RING",
+	"REO2FW_RING",
+	"RELEASE_RING",
+	"PPE_RELEASE_RING",
+	"TCL2TQM_RING",
+	"TQM_RELEASE_RING",
+	"REO_RELEASE_RING",
+	"WBM2SW0_RELEASE_RING",
+	"WBM2SW1_RELEASE_RING",
+	"WBM2SW2_RELEASE_RING",
+	"WBM2SW3_RELEASE_RING",
+	"REO_CMD_RING",
+	"REO_STATUS_RING",
+};
+
+static const char *htt_bp_lmac_ring[HTT_SW_LMAC_RING_IDX_MAX] = {
+	"FW2RXDMA_BUF_RING",
+	"FW2RXDMA_STATUS_RING",
+	"FW2RXDMA_LINK_RING",
+	"SW2RXDMA_BUF_RING",
+	"WBM2RXDMA_LINK_RING",
+	"RXDMA2FW_RING",
+	"RXDMA2SW_RING",
+	"RXDMA2RELEASE_RING",
+	"RXDMA2REO_RING",
+	"MONITOR_STATUS_RING",
+	"MONITOR_BUF_RING",
+	"MONITOR_DESC_RING",
+	"MONITOR_DEST_RING",
+};
+
+static void ath11k_fw_stats_pdevs_free(struct list_head *head)
+{
+	struct ath11k_fw_stats_pdev *i, *tmp;
+
+	list_for_each_entry_safe(i, tmp, head, list) {
+		list_del(&i->list);
+		kfree(i);
+	}
+}
+
+static void ath11k_fw_stats_vdevs_free(struct list_head *head)
+{
+	struct ath11k_fw_stats_vdev *i, *tmp;
+
+	list_for_each_entry_safe(i, tmp, head, list) {
+		list_del(&i->list);
+		kfree(i);
+	}
+}
+
+static void ath11k_fw_stats_bcn_free(struct list_head *head)
+{
+	struct ath11k_fw_stats_bcn *i, *tmp;
+
+	list_for_each_entry_safe(i, tmp, head, list) {
+		list_del(&i->list);
+		kfree(i);
+	}
+}
+
+static void ath11k_debugfs_fw_stats_reset(struct ath11k *ar)
+{
+	spin_lock_bh(&ar->data_lock);
+	ar->debug.fw_stats_done = false;
+	ath11k_fw_stats_pdevs_free(&ar->debug.fw_stats.pdevs);
+	ath11k_fw_stats_vdevs_free(&ar->debug.fw_stats.vdevs);
+	spin_unlock_bh(&ar->data_lock);
+}
+
+void ath11k_debugfs_fw_stats_process(struct ath11k_base *ab, struct sk_buff *skb)
+{
+	struct ath11k_fw_stats stats = {};
+	struct ath11k *ar;
+	struct ath11k_pdev *pdev;
+	bool is_end;
+	static unsigned int num_vdev, num_bcn;
+	size_t total_vdevs_started = 0;
+	int i, ret;
+
+	INIT_LIST_HEAD(&stats.pdevs);
+	INIT_LIST_HEAD(&stats.vdevs);
+	INIT_LIST_HEAD(&stats.bcn);
+
+	ret = ath11k_wmi_pull_fw_stats(ab, skb, &stats);
+	if (ret) {
+		ath11k_warn(ab, "failed to pull fw stats: %d\n", ret);
+		goto free;
+	}
+
+	rcu_read_lock();
+	ar = ath11k_mac_get_ar_by_pdev_id(ab, stats.pdev_id);
+	if (!ar) {
+		rcu_read_unlock();
+		ath11k_warn(ab, "failed to get ar for pdev_id %d: %d\n",
+			    stats.pdev_id, ret);
+		goto free;
+	}
+
+	spin_lock_bh(&ar->data_lock);
+
+	if (stats.stats_id == WMI_REQUEST_PDEV_STAT) {
+		list_splice_tail_init(&stats.pdevs, &ar->debug.fw_stats.pdevs);
+		ar->debug.fw_stats_done = true;
+		goto complete;
+	}
+
+	if (stats.stats_id == WMI_REQUEST_VDEV_STAT) {
+		if (list_empty(&stats.vdevs)) {
+			ath11k_warn(ab, "empty vdev stats");
+			goto complete;
+		}
+		/* FW sends all the active VDEV stats irrespective of PDEV,
+		 * hence limit until the count of all VDEVs started
+		 */
+		for (i = 0; i < ab->num_radios; i++) {
+			pdev = rcu_dereference(ab->pdevs_active[i]);
+			if (pdev && pdev->ar)
+				total_vdevs_started += ar->num_started_vdevs;
+		}
+
+		is_end = ((++num_vdev) == total_vdevs_started);
+
+		list_splice_tail_init(&stats.vdevs,
+				      &ar->debug.fw_stats.vdevs);
+
+		if (is_end) {
+			ar->debug.fw_stats_done = true;
+			num_vdev = 0;
+		}
+		goto complete;
+	}
+
+	if (stats.stats_id == WMI_REQUEST_BCN_STAT) {
+		if (list_empty(&stats.bcn)) {
+			ath11k_warn(ab, "empty bcn stats");
+			goto complete;
+		}
+		/* Mark end until we reached the count of all started VDEVs
+		 * within the PDEV
+		 */
+		is_end = ((++num_bcn) == ar->num_started_vdevs);
+
+		list_splice_tail_init(&stats.bcn,
+				      &ar->debug.fw_stats.bcn);
+
+		if (is_end) {
+			ar->debug.fw_stats_done = true;
+			num_bcn = 0;
+		}
+	}
+complete:
+	complete(&ar->debug.fw_stats_complete);
+	rcu_read_unlock();
+	spin_unlock_bh(&ar->data_lock);
+
+free:
+	ath11k_fw_stats_pdevs_free(&stats.pdevs);
+	ath11k_fw_stats_vdevs_free(&stats.vdevs);
+	ath11k_fw_stats_bcn_free(&stats.bcn);
+}
+
+static int ath11k_debugfs_fw_stats_request(struct ath11k *ar,
+					   struct stats_request_params *req_param)
+{
+	struct ath11k_base *ab = ar->ab;
+	unsigned long timeout, time_left;
+	int ret;
+
+	lockdep_assert_held(&ar->conf_mutex);
+
+	/* FW stats can get split when exceeding the stats data buffer limit.
+	 * In that case, since there is no end marking for the back-to-back
+	 * received 'update stats' event, we keep a 3 seconds timeout in case,
+	 * fw_stats_done is not marked yet
+	 */
+	timeout = jiffies + msecs_to_jiffies(3 * HZ);
+
+	ath11k_debugfs_fw_stats_reset(ar);
+
+	reinit_completion(&ar->debug.fw_stats_complete);
+
+	ret = ath11k_wmi_send_stats_request_cmd(ar, req_param);
+
+	if (ret) {
+		ath11k_warn(ab, "could not request fw stats (%d)\n",
+			    ret);
+		return ret;
+	}
+
+	time_left =
+	wait_for_completion_timeout(&ar->debug.fw_stats_complete,
+				    1 * HZ);
+	if (!time_left)
+		return -ETIMEDOUT;
+
+	for (;;) {
+		if (time_after(jiffies, timeout))
+			break;
+
+		spin_lock_bh(&ar->data_lock);
+		if (ar->debug.fw_stats_done) {
+			spin_unlock_bh(&ar->data_lock);
+			break;
+		}
+		spin_unlock_bh(&ar->data_lock);
+	}
+	return 0;
+}
+
+static int ath11k_open_pdev_stats(struct inode *inode, struct file *file)
+{
+	struct ath11k *ar = inode->i_private;
+	struct ath11k_base *ab = ar->ab;
+	struct stats_request_params req_param;
+	void *buf = NULL;
+	int ret;
+
+	mutex_lock(&ar->conf_mutex);
+
+	if (ar->state != ATH11K_STATE_ON) {
+		ret = -ENETDOWN;
+		goto err_unlock;
+	}
+
+	buf = vmalloc(ATH11K_FW_STATS_BUF_SIZE);
+	if (!buf) {
+		ret = -ENOMEM;
+		goto err_unlock;
+	}
+
+	req_param.pdev_id = ar->pdev->pdev_id;
+	req_param.vdev_id = 0;
+	req_param.stats_id = WMI_REQUEST_PDEV_STAT;
+
+	ret = ath11k_debugfs_fw_stats_request(ar, &req_param);
+	if (ret) {
+		ath11k_warn(ab, "failed to request fw pdev stats: %d\n", ret);
+		goto err_free;
+	}
+
+	ath11k_wmi_fw_stats_fill(ar, &ar->debug.fw_stats, req_param.stats_id,
+				 buf);
+
+	file->private_data = buf;
+
+	mutex_unlock(&ar->conf_mutex);
+	return 0;
+
+err_free:
+	vfree(buf);
+
+err_unlock:
+	mutex_unlock(&ar->conf_mutex);
+	return ret;
+}
+
+static int ath11k_release_pdev_stats(struct inode *inode, struct file *file)
+{
+	vfree(file->private_data);
+
+	return 0;
+}
+
+static ssize_t ath11k_read_pdev_stats(struct file *file,
+				      char __user *user_buf,
+				      size_t count, loff_t *ppos)
+{
+	const char *buf = file->private_data;
+	size_t len = strlen(buf);
+
+	return simple_read_from_buffer(user_buf, count, ppos, buf, len);
+}
+
+static const struct file_operations fops_pdev_stats = {
+	.open = ath11k_open_pdev_stats,
+	.release = ath11k_release_pdev_stats,
+	.read = ath11k_read_pdev_stats,
+	.owner = THIS_MODULE,
+	.llseek = default_llseek,
+};
+
+static int ath11k_open_vdev_stats(struct inode *inode, struct file *file)
+{
+	struct ath11k *ar = inode->i_private;
+	struct stats_request_params req_param;
+	void *buf = NULL;
+	int ret;
+
+	mutex_lock(&ar->conf_mutex);
+
+	if (ar->state != ATH11K_STATE_ON) {
+		ret = -ENETDOWN;
+		goto err_unlock;
+	}
+
+	buf = vmalloc(ATH11K_FW_STATS_BUF_SIZE);
+	if (!buf) {
+		ret = -ENOMEM;
+		goto err_unlock;
+	}
+
+	req_param.pdev_id = ar->pdev->pdev_id;
+	/* VDEV stats is always sent for all active VDEVs from FW */
+	req_param.vdev_id = 0;
+	req_param.stats_id = WMI_REQUEST_VDEV_STAT;
+
+	ret = ath11k_debugfs_fw_stats_request(ar, &req_param);
+	if (ret) {
+		ath11k_warn(ar->ab, "failed to request fw vdev stats: %d\n", ret);
+		goto err_free;
+	}
+
+	ath11k_wmi_fw_stats_fill(ar, &ar->debug.fw_stats, req_param.stats_id,
+				 buf);
+
+	file->private_data = buf;
+
+	mutex_unlock(&ar->conf_mutex);
+	return 0;
+
+err_free:
+	vfree(buf);
+
+err_unlock:
+	mutex_unlock(&ar->conf_mutex);
+	return ret;
+}
+
+static int ath11k_release_vdev_stats(struct inode *inode, struct file *file)
+{
+	vfree(file->private_data);
+
+	return 0;
+}
+
+static ssize_t ath11k_read_vdev_stats(struct file *file,
+				      char __user *user_buf,
+				      size_t count, loff_t *ppos)
+{
+	const char *buf = file->private_data;
+	size_t len = strlen(buf);
+
+	return simple_read_from_buffer(user_buf, count, ppos, buf, len);
+}
+
+static const struct file_operations fops_vdev_stats = {
+	.open = ath11k_open_vdev_stats,
+	.release = ath11k_release_vdev_stats,
+	.read = ath11k_read_vdev_stats,
+	.owner = THIS_MODULE,
+	.llseek = default_llseek,
+};
+
+static int ath11k_open_bcn_stats(struct inode *inode, struct file *file)
+{
+	struct ath11k *ar = inode->i_private;
+	struct ath11k_vif *arvif;
+	struct stats_request_params req_param;
+	void *buf = NULL;
+	int ret;
+
+	mutex_lock(&ar->conf_mutex);
+
+	if (ar->state != ATH11K_STATE_ON) {
+		ret = -ENETDOWN;
+		goto err_unlock;
+	}
+
+	buf = vmalloc(ATH11K_FW_STATS_BUF_SIZE);
+	if (!buf) {
+		ret = -ENOMEM;
+		goto err_unlock;
+	}
+
+	req_param.stats_id = WMI_REQUEST_BCN_STAT;
+	req_param.pdev_id = ar->pdev->pdev_id;
+
+	/* loop all active VDEVs for bcn stats */
+	list_for_each_entry(arvif, &ar->arvifs, list) {
+		if (!arvif->is_up)
+			continue;
+
+		req_param.vdev_id = arvif->vdev_id;
+		ret = ath11k_debugfs_fw_stats_request(ar, &req_param);
+		if (ret) {
+			ath11k_warn(ar->ab, "failed to request fw bcn stats: %d\n", ret);
+			goto err_free;
+		}
+	}
+
+	ath11k_wmi_fw_stats_fill(ar, &ar->debug.fw_stats, req_param.stats_id,
+				 buf);
+
+	/* since beacon stats request is looped for all active VDEVs, saved fw
+	 * stats is not freed for each request until done for all active VDEVs
+	 */
+	spin_lock_bh(&ar->data_lock);
+	ath11k_fw_stats_bcn_free(&ar->debug.fw_stats.bcn);
+	spin_unlock_bh(&ar->data_lock);
+
+	file->private_data = buf;
+
+	mutex_unlock(&ar->conf_mutex);
+	return 0;
+
+err_free:
+	vfree(buf);
+
+err_unlock:
+	mutex_unlock(&ar->conf_mutex);
+	return ret;
+}
+
+static int ath11k_release_bcn_stats(struct inode *inode, struct file *file)
+{
+	vfree(file->private_data);
+
+	return 0;
+}
+
+static ssize_t ath11k_read_bcn_stats(struct file *file,
+				     char __user *user_buf,
+				     size_t count, loff_t *ppos)
+{
+	const char *buf = file->private_data;
+	size_t len = strlen(buf);
+
+	return simple_read_from_buffer(user_buf, count, ppos, buf, len);
+}
+
+static const struct file_operations fops_bcn_stats = {
+	.open = ath11k_open_bcn_stats,
+	.release = ath11k_release_bcn_stats,
+	.read = ath11k_read_bcn_stats,
+	.owner = THIS_MODULE,
+	.llseek = default_llseek,
+};
+
+static ssize_t ath11k_read_simulate_fw_crash(struct file *file,
+					     char __user *user_buf,
+					     size_t count, loff_t *ppos)
+{
+	const char buf[] =
+		"To simulate firmware crash write one of the keywords to this file:\n"
+		"`assert` - this will send WMI_FORCE_FW_HANG_CMDID to firmware to cause assert.\n"
+		"`hw-restart` - this will simply queue hw restart without fw/hw actually crashing.\n";
+
+	return simple_read_from_buffer(user_buf, count, ppos, buf, strlen(buf));
+}
+
+/* Simulate firmware crash:
+ * 'soft': Call wmi command causing firmware hang. This firmware hang is
+ * recoverable by warm firmware reset.
+ * 'hard': Force firmware crash by setting any vdev parameter for not allowed
+ * vdev id. This is hard firmware crash because it is recoverable only by cold
+ * firmware reset.
+ */
+static ssize_t ath11k_write_simulate_fw_crash(struct file *file,
+					      const char __user *user_buf,
+					      size_t count, loff_t *ppos)
+{
+	struct ath11k_base *ab = file->private_data;
+	struct ath11k_pdev *pdev;
+	struct ath11k *ar = ab->pdevs[0].ar;
+	char buf[32] = {0};
+	ssize_t rc;
+	int i, ret, radioup = 0;
+
+	for (i = 0; i < ab->num_radios; i++) {
+		pdev = &ab->pdevs[i];
+		ar = pdev->ar;
+		if (ar && ar->state == ATH11K_STATE_ON) {
+			radioup = 1;
+			break;
+		}
+	}
+	/* filter partial writes and invalid commands */
+	if (*ppos != 0 || count >= sizeof(buf) || count == 0)
+		return -EINVAL;
+
+	rc = simple_write_to_buffer(buf, sizeof(buf) - 1, ppos, user_buf, count);
+	if (rc < 0)
+		return rc;
+
+	/* drop the possible '\n' from the end */
+	if (buf[*ppos - 1] == '\n')
+		buf[*ppos - 1] = '\0';
+
+	if (radioup == 0) {
+		ret = -ENETDOWN;
+		goto exit;
+	}
+
+	if (!strcmp(buf, "assert")) {
+		ath11k_info(ab, "simulating firmware assert crash\n");
+		ret = ath11k_wmi_force_fw_hang_cmd(ar,
+						   ATH11K_WMI_FW_HANG_ASSERT_TYPE,
+						   ATH11K_WMI_FW_HANG_DELAY);
+	} else {
+		ret = -EINVAL;
+		goto exit;
+	}
+
+	if (ret) {
+		ath11k_warn(ab, "failed to simulate firmware crash: %d\n", ret);
+		goto exit;
+	}
+
+	ret = count;
+
+exit:
+	return ret;
+}
+
+static const struct file_operations fops_simulate_fw_crash = {
+	.read = ath11k_read_simulate_fw_crash,
+	.write = ath11k_write_simulate_fw_crash,
+	.open = simple_open,
+	.owner = THIS_MODULE,
+	.llseek = default_llseek,
+};
+
+static ssize_t ath11k_write_enable_extd_tx_stats(struct file *file,
+						 const char __user *ubuf,
+						 size_t count, loff_t *ppos)
+{
+	struct ath11k *ar = file->private_data;
+	u32 filter;
+	int ret;
+
+	if (kstrtouint_from_user(ubuf, count, 0, &filter))
+		return -EINVAL;
+
+	mutex_lock(&ar->conf_mutex);
+
+	if (ar->state != ATH11K_STATE_ON) {
+		ret = -ENETDOWN;
+		goto out;
+	}
+
+	if (filter == ar->debug.extd_tx_stats) {
+		ret = count;
+		goto out;
+	}
+
+	ar->debug.extd_tx_stats = filter;
+	ret = count;
+
+out:
+	mutex_unlock(&ar->conf_mutex);
+	return ret;
+}
+
+static ssize_t ath11k_read_enable_extd_tx_stats(struct file *file,
+						char __user *ubuf,
+						size_t count, loff_t *ppos)
+
+{
+	char buf[32] = {0};
+	struct ath11k *ar = file->private_data;
+	int len = 0;
+
+	mutex_lock(&ar->conf_mutex);
+	len = scnprintf(buf, sizeof(buf) - len, "%08x\n",
+			ar->debug.extd_tx_stats);
+	mutex_unlock(&ar->conf_mutex);
+
+	return simple_read_from_buffer(ubuf, count, ppos, buf, len);
+}
+
+static const struct file_operations fops_extd_tx_stats = {
+	.read = ath11k_read_enable_extd_tx_stats,
+	.write = ath11k_write_enable_extd_tx_stats,
+	.open = simple_open
+};
+
+static ssize_t ath11k_write_extd_rx_stats(struct file *file,
+					  const char __user *ubuf,
+					  size_t count, loff_t *ppos)
+{
+	struct ath11k *ar = file->private_data;
+	struct ath11k_base *ab = ar->ab;
+	struct htt_rx_ring_tlv_filter tlv_filter = {0};
+	u32 enable, rx_filter = 0, ring_id;
+	int i;
+	int ret;
+
+	if (kstrtouint_from_user(ubuf, count, 0, &enable))
+		return -EINVAL;
+
+	mutex_lock(&ar->conf_mutex);
+
+	if (ar->state != ATH11K_STATE_ON) {
+		ret = -ENETDOWN;
+		goto exit;
+	}
+
+	if (enable > 1) {
+		ret = -EINVAL;
+		goto exit;
+	}
+
+	if (enable == ar->debug.extd_rx_stats) {
+		ret = count;
+		goto exit;
+	}
+
+	if (enable) {
+		rx_filter =  HTT_RX_FILTER_TLV_FLAGS_MPDU_START;
+		rx_filter |= HTT_RX_FILTER_TLV_FLAGS_PPDU_START;
+		rx_filter |= HTT_RX_FILTER_TLV_FLAGS_PPDU_END;
+		rx_filter |= HTT_RX_FILTER_TLV_FLAGS_PPDU_END_USER_STATS;
+		rx_filter |= HTT_RX_FILTER_TLV_FLAGS_PPDU_END_USER_STATS_EXT;
+		rx_filter |= HTT_RX_FILTER_TLV_FLAGS_PPDU_END_STATUS_DONE;
+
+		tlv_filter.rx_filter = rx_filter;
+		tlv_filter.pkt_filter_flags0 = HTT_RX_FP_MGMT_FILTER_FLAGS0;
+		tlv_filter.pkt_filter_flags1 = HTT_RX_FP_MGMT_FILTER_FLAGS1;
+		tlv_filter.pkt_filter_flags2 = HTT_RX_FP_CTRL_FILTER_FLASG2;
+		tlv_filter.pkt_filter_flags3 = HTT_RX_FP_CTRL_FILTER_FLASG3 |
+			HTT_RX_FP_DATA_FILTER_FLASG3;
+	} else {
+		tlv_filter = ath11k_mac_mon_status_filter_default;
+	}
+
+	ar->debug.rx_filter = tlv_filter.rx_filter;
+
+	for (i = 0; i < ab->hw_params.num_rxmda_per_pdev; i++) {
+		ring_id = ar->dp.rx_mon_status_refill_ring[i].refill_buf_ring.ring_id;
+		ret = ath11k_dp_tx_htt_rx_filter_setup(ar->ab, ring_id, ar->dp.mac_id,
+						       HAL_RXDMA_MONITOR_STATUS,
+						       DP_RX_BUFFER_SIZE, &tlv_filter);
+
+		if (ret) {
+			ath11k_warn(ar->ab, "failed to set rx filter for monitor status ring\n");
+			goto exit;
+		}
+	}
+
+	ar->debug.extd_rx_stats = enable;
+	ret = count;
+exit:
+	mutex_unlock(&ar->conf_mutex);
+	return ret;
+}
+
+static ssize_t ath11k_read_extd_rx_stats(struct file *file,
+					 char __user *ubuf,
+					 size_t count, loff_t *ppos)
+{
+	struct ath11k *ar = file->private_data;
+	char buf[32];
+	int len = 0;
+
+	mutex_lock(&ar->conf_mutex);
+	len = scnprintf(buf, sizeof(buf) - len, "%d\n",
+			ar->debug.extd_rx_stats);
+	mutex_unlock(&ar->conf_mutex);
+
+	return simple_read_from_buffer(ubuf, count, ppos, buf, len);
+}
+
+static const struct file_operations fops_extd_rx_stats = {
+	.read = ath11k_read_extd_rx_stats,
+	.write = ath11k_write_extd_rx_stats,
+	.open = simple_open,
+};
+
+static int ath11k_fill_bp_stats(struct ath11k_base *ab,
+				struct ath11k_bp_stats *bp_stats,
+				char *buf, int len, int size)
+{
+	lockdep_assert_held(&ab->base_lock);
+
+	len += scnprintf(buf + len, size - len, "count: %u\n",
+			 bp_stats->count);
+	len += scnprintf(buf + len, size - len, "hp: %u\n",
+			 bp_stats->hp);
+	len += scnprintf(buf + len, size - len, "tp: %u\n",
+			 bp_stats->tp);
+	len += scnprintf(buf + len, size - len, "seen before: %ums\n\n",
+			 jiffies_to_msecs(jiffies - bp_stats->jiffies));
+	return len;
+}
+
+static ssize_t ath11k_debugfs_dump_soc_ring_bp_stats(struct ath11k_base *ab,
+						     char *buf, int size)
+{
+	struct ath11k_bp_stats *bp_stats;
+	bool stats_rxd = false;
+	u8 i, pdev_idx;
+	int len = 0;
+
+	len += scnprintf(buf + len, size - len, "\nBackpressure Stats\n");
+	len += scnprintf(buf + len, size - len, "==================\n");
+
+	spin_lock_bh(&ab->base_lock);
+	for (i = 0; i < HTT_SW_UMAC_RING_IDX_MAX; i++) {
+		bp_stats = &ab->soc_stats.bp_stats.umac_ring_bp_stats[i];
+
+		if (!bp_stats->count)
+			continue;
+
+		len += scnprintf(buf + len, size - len, "Ring: %s\n",
+				 htt_bp_umac_ring[i]);
+		len = ath11k_fill_bp_stats(ab, bp_stats, buf, len, size);
+		stats_rxd = true;
+	}
+
+	for (i = 0; i < HTT_SW_LMAC_RING_IDX_MAX; i++) {
+		for (pdev_idx = 0; pdev_idx < MAX_RADIOS; pdev_idx++) {
+			bp_stats =
+				&ab->soc_stats.bp_stats.lmac_ring_bp_stats[i][pdev_idx];
+
+			if (!bp_stats->count)
+				continue;
+
+			len += scnprintf(buf + len, size - len, "Ring: %s\n",
+					 htt_bp_lmac_ring[i]);
+			len += scnprintf(buf + len, size - len, "pdev: %d\n",
+					 pdev_idx);
+			len = ath11k_fill_bp_stats(ab, bp_stats, buf, len, size);
+			stats_rxd = true;
+		}
+	}
+	spin_unlock_bh(&ab->base_lock);
+
+	if (!stats_rxd)
+		len += scnprintf(buf + len, size - len,
+				 "No Ring Backpressure stats received\n\n");
+
+	return len;
+}
+
+static ssize_t ath11k_debugfs_dump_soc_dp_stats(struct file *file,
+						char __user *user_buf,
+						size_t count, loff_t *ppos)
+{
+	struct ath11k_base *ab = file->private_data;
+	struct ath11k_soc_dp_stats *soc_stats = &ab->soc_stats;
+	int len = 0, i, retval;
+	const int size = 4096;
+	static const char *rxdma_err[HAL_REO_ENTR_RING_RXDMA_ECODE_MAX] = {
+			"Overflow", "MPDU len", "FCS", "Decrypt", "TKIP MIC",
+			"Unencrypt", "MSDU len", "MSDU limit", "WiFi parse",
+			"AMSDU parse", "SA timeout", "DA timeout",
+			"Flow timeout", "Flush req"};
+	static const char *reo_err[HAL_REO_DEST_RING_ERROR_CODE_MAX] = {
+			"Desc addr zero", "Desc inval", "AMPDU in non BA",
+			"Non BA dup", "BA dup", "Frame 2k jump", "BAR 2k jump",
+			"Frame OOR", "BAR OOR", "No BA session",
+			"Frame SN equal SSN", "PN check fail", "2k err",
+			"PN err", "Desc blocked"};
+
+	char *buf;
+
+	buf = kzalloc(size, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	len += scnprintf(buf + len, size - len, "SOC RX STATS:\n\n");
+	len += scnprintf(buf + len, size - len, "err ring pkts: %u\n",
+			 soc_stats->err_ring_pkts);
+	len += scnprintf(buf + len, size - len, "Invalid RBM: %u\n\n",
+			 soc_stats->invalid_rbm);
+	len += scnprintf(buf + len, size - len, "RXDMA errors:\n");
+	for (i = 0; i < HAL_REO_ENTR_RING_RXDMA_ECODE_MAX; i++)
+		len += scnprintf(buf + len, size - len, "%s: %u\n",
+				 rxdma_err[i], soc_stats->rxdma_error[i]);
+
+	len += scnprintf(buf + len, size - len, "\nREO errors:\n");
+	for (i = 0; i < HAL_REO_DEST_RING_ERROR_CODE_MAX; i++)
+		len += scnprintf(buf + len, size - len, "%s: %u\n",
+				 reo_err[i], soc_stats->reo_error[i]);
+
+	len += scnprintf(buf + len, size - len, "\nHAL REO errors:\n");
+	len += scnprintf(buf + len, size - len,
+			 "ring0: %u\nring1: %u\nring2: %u\nring3: %u\n",
+			 soc_stats->hal_reo_error[0],
+			 soc_stats->hal_reo_error[1],
+			 soc_stats->hal_reo_error[2],
+			 soc_stats->hal_reo_error[3]);
+
+	len += scnprintf(buf + len, size - len, "\nSOC TX STATS:\n");
+	len += scnprintf(buf + len, size - len, "\nTCL Ring Full Failures:\n");
+
+	for (i = 0; i < DP_TCL_NUM_RING_MAX; i++)
+		len += scnprintf(buf + len, size - len, "ring%d: %u\n",
+				 i, soc_stats->tx_err.desc_na[i]);
+
+	len += scnprintf(buf + len, size - len,
+			 "\nMisc Transmit Failures: %d\n",
+			 atomic_read(&soc_stats->tx_err.misc_fail));
+
+	len += ath11k_debugfs_dump_soc_ring_bp_stats(ab, buf + len, size - len);
+
+	if (len > size)
+		len = size;
+	retval = simple_read_from_buffer(user_buf, count, ppos, buf, len);
+	kfree(buf);
+
+	return retval;
+}
+
+static const struct file_operations fops_soc_dp_stats = {
+	.read = ath11k_debugfs_dump_soc_dp_stats,
+	.open = simple_open,
+	.owner = THIS_MODULE,
+	.llseek = default_llseek,
+};
+
+int ath11k_debugfs_pdev_create(struct ath11k_base *ab)
+{
+	if (test_bit(ATH11K_FLAG_REGISTERED, &ab->dev_flags))
+		return 0;
+
+	ab->debugfs_soc = debugfs_create_dir(ab->hw_params.name, ab->debugfs_ath11k);
+	if (IS_ERR(ab->debugfs_soc))
+		return PTR_ERR(ab->debugfs_soc);
+
+	debugfs_create_file("simulate_fw_crash", 0600, ab->debugfs_soc, ab,
+			    &fops_simulate_fw_crash);
+
+	debugfs_create_file("soc_dp_stats", 0600, ab->debugfs_soc, ab,
+			    &fops_soc_dp_stats);
+
+	return 0;
+}
+
+void ath11k_debugfs_pdev_destroy(struct ath11k_base *ab)
+{
+	debugfs_remove_recursive(ab->debugfs_soc);
+	ab->debugfs_soc = NULL;
+}
+
+int ath11k_debugfs_soc_create(struct ath11k_base *ab)
+{
+	ab->debugfs_ath11k = debugfs_create_dir("ath11k", NULL);
+
+	return PTR_ERR_OR_ZERO(ab->debugfs_ath11k);
+}
+
+void ath11k_debugfs_soc_destroy(struct ath11k_base *ab)
+{
+	debugfs_remove_recursive(ab->debugfs_ath11k);
+	ab->debugfs_ath11k = NULL;
+}
+
+void ath11k_debugfs_fw_stats_init(struct ath11k *ar)
+{
+	struct dentry *fwstats_dir = debugfs_create_dir("fw_stats",
+							ar->debug.debugfs_pdev);
+
+	ar->debug.fw_stats.debugfs_fwstats = fwstats_dir;
+
+	/* all stats debugfs files created are under "fw_stats" directory
+	 * created per PDEV
+	 */
+	debugfs_create_file("pdev_stats", 0600, fwstats_dir, ar,
+			    &fops_pdev_stats);
+	debugfs_create_file("vdev_stats", 0600, fwstats_dir, ar,
+			    &fops_vdev_stats);
+	debugfs_create_file("beacon_stats", 0600, fwstats_dir, ar,
+			    &fops_bcn_stats);
+
+	INIT_LIST_HEAD(&ar->debug.fw_stats.pdevs);
+	INIT_LIST_HEAD(&ar->debug.fw_stats.vdevs);
+	INIT_LIST_HEAD(&ar->debug.fw_stats.bcn);
+
+	init_completion(&ar->debug.fw_stats_complete);
+}
+
+static ssize_t ath11k_write_pktlog_filter(struct file *file,
+					  const char __user *ubuf,
+					  size_t count, loff_t *ppos)
+{
+	struct ath11k *ar = file->private_data;
+	struct ath11k_base *ab = ar->ab;
+	struct htt_rx_ring_tlv_filter tlv_filter = {0};
+	u32 rx_filter = 0, ring_id, filter, mode;
+	u8 buf[128] = {0};
+	int i, ret;
+	ssize_t rc;
+
+	mutex_lock(&ar->conf_mutex);
+	if (ar->state != ATH11K_STATE_ON) {
+		ret = -ENETDOWN;
+		goto out;
+	}
+
+	rc = simple_write_to_buffer(buf, sizeof(buf) - 1, ppos, ubuf, count);
+	if (rc < 0) {
+		ret = rc;
+		goto out;
+	}
+	buf[rc] = '\0';
+
+	ret = sscanf(buf, "0x%x %u", &filter, &mode);
+	if (ret != 2) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (filter) {
+		ret = ath11k_wmi_pdev_pktlog_enable(ar, filter);
+		if (ret) {
+			ath11k_warn(ar->ab,
+				    "failed to enable pktlog filter %x: %d\n",
+				    ar->debug.pktlog_filter, ret);
+			goto out;
+		}
+	} else {
+		ret = ath11k_wmi_pdev_pktlog_disable(ar);
+		if (ret) {
+			ath11k_warn(ar->ab, "failed to disable pktlog: %d\n", ret);
+			goto out;
+		}
+	}
+
+#define HTT_RX_FILTER_TLV_LITE_MODE \
+			(HTT_RX_FILTER_TLV_FLAGS_PPDU_START | \
+			HTT_RX_FILTER_TLV_FLAGS_PPDU_END | \
+			HTT_RX_FILTER_TLV_FLAGS_PPDU_END_USER_STATS | \
+			HTT_RX_FILTER_TLV_FLAGS_PPDU_END_USER_STATS_EXT | \
+			HTT_RX_FILTER_TLV_FLAGS_PPDU_END_STATUS_DONE | \
+			HTT_RX_FILTER_TLV_FLAGS_MPDU_START)
+
+	if (mode == ATH11K_PKTLOG_MODE_FULL) {
+		rx_filter = HTT_RX_FILTER_TLV_LITE_MODE |
+			    HTT_RX_FILTER_TLV_FLAGS_MSDU_START |
+			    HTT_RX_FILTER_TLV_FLAGS_MSDU_END |
+			    HTT_RX_FILTER_TLV_FLAGS_MPDU_END |
+			    HTT_RX_FILTER_TLV_FLAGS_PACKET_HEADER |
+			    HTT_RX_FILTER_TLV_FLAGS_ATTENTION;
+	} else if (mode == ATH11K_PKTLOG_MODE_LITE) {
+		ret = ath11k_dp_tx_htt_h2t_ppdu_stats_req(ar,
+							  HTT_PPDU_STATS_TAG_PKTLOG);
+		if (ret) {
+			ath11k_err(ar->ab, "failed to enable pktlog lite: %d\n", ret);
+			goto out;
+		}
+
+		rx_filter = HTT_RX_FILTER_TLV_LITE_MODE;
+	} else {
+		ret = ath11k_dp_tx_htt_h2t_ppdu_stats_req(ar,
+							  HTT_PPDU_STATS_TAG_DEFAULT);
+		if (ret) {
+			ath11k_err(ar->ab, "failed to send htt ppdu stats req: %d\n",
+				   ret);
+			goto out;
+		}
+	}
+
+	tlv_filter.rx_filter = rx_filter;
+	if (rx_filter) {
+		tlv_filter.pkt_filter_flags0 = HTT_RX_FP_MGMT_FILTER_FLAGS0;
+		tlv_filter.pkt_filter_flags1 = HTT_RX_FP_MGMT_FILTER_FLAGS1;
+		tlv_filter.pkt_filter_flags2 = HTT_RX_FP_CTRL_FILTER_FLASG2;
+		tlv_filter.pkt_filter_flags3 = HTT_RX_FP_CTRL_FILTER_FLASG3 |
+					       HTT_RX_FP_DATA_FILTER_FLASG3;
+	}
+
+	for (i = 0; i < ab->hw_params.num_rxmda_per_pdev; i++) {
+		ring_id = ar->dp.rx_mon_status_refill_ring[i].refill_buf_ring.ring_id;
+		ret = ath11k_dp_tx_htt_rx_filter_setup(ab, ring_id,
+						       ar->dp.mac_id + i,
+						       HAL_RXDMA_MONITOR_STATUS,
+						       DP_RX_BUFFER_SIZE, &tlv_filter);
+
+		if (ret) {
+			ath11k_warn(ab, "failed to set rx filter for monitor status ring\n");
+			goto out;
+		}
+	}
+
+	ath11k_dbg(ab, ATH11K_DBG_WMI, "pktlog filter %d mode %s\n",
+		   filter, ((mode == ATH11K_PKTLOG_MODE_FULL) ? "full" : "lite"));
+
+	ar->debug.pktlog_filter = filter;
+	ar->debug.pktlog_mode = mode;
+	ret = count;
+
+out:
+	mutex_unlock(&ar->conf_mutex);
+	return ret;
+}
+
+static ssize_t ath11k_read_pktlog_filter(struct file *file,
+					 char __user *ubuf,
+					 size_t count, loff_t *ppos)
+
+{
+	char buf[32] = {0};
+	struct ath11k *ar = file->private_data;
+	int len = 0;
+
+	mutex_lock(&ar->conf_mutex);
+	len = scnprintf(buf, sizeof(buf) - len, "%08x %08x\n",
+			ar->debug.pktlog_filter,
+			ar->debug.pktlog_mode);
+	mutex_unlock(&ar->conf_mutex);
+
+	return simple_read_from_buffer(ubuf, count, ppos, buf, len);
+}
+
+static const struct file_operations fops_pktlog_filter = {
+	.read = ath11k_read_pktlog_filter,
+	.write = ath11k_write_pktlog_filter,
+	.open = simple_open
+};
+
+static ssize_t ath11k_write_simulate_radar(struct file *file,
+					   const char __user *user_buf,
+					   size_t count, loff_t *ppos)
+{
+	struct ath11k *ar = file->private_data;
+	int ret;
+
+	ret = ath11k_wmi_simulate_radar(ar);
+	if (ret)
+		return ret;
+
+	return count;
+}
+
+static const struct file_operations fops_simulate_radar = {
+	.write = ath11k_write_simulate_radar,
+	.open = simple_open
+};
+
+int ath11k_debugfs_register(struct ath11k *ar)
+{
+	struct ath11k_base *ab = ar->ab;
+	char pdev_name[5];
+	char buf[100] = {0};
+
+	snprintf(pdev_name, sizeof(pdev_name), "%s%d", "mac", ar->pdev_idx);
+
+	ar->debug.debugfs_pdev = debugfs_create_dir(pdev_name, ab->debugfs_soc);
+	if (IS_ERR(ar->debug.debugfs_pdev))
+		return PTR_ERR(ar->debug.debugfs_pdev);
+
+	/* Create a symlink under ieee80211/phy* */
+	snprintf(buf, 100, "../../ath11k/%pd2", ar->debug.debugfs_pdev);
+	debugfs_create_symlink("ath11k", ar->hw->wiphy->debugfsdir, buf);
+
+	ath11k_debugfs_htt_stats_init(ar);
+
+	ath11k_debugfs_fw_stats_init(ar);
+
+	debugfs_create_file("ext_tx_stats", 0644,
+			    ar->debug.debugfs_pdev, ar,
+			    &fops_extd_tx_stats);
+	debugfs_create_file("ext_rx_stats", 0644,
+			    ar->debug.debugfs_pdev, ar,
+			    &fops_extd_rx_stats);
+	debugfs_create_file("pktlog_filter", 0644,
+			    ar->debug.debugfs_pdev, ar,
+			    &fops_pktlog_filter);
+
+	if (ar->hw->wiphy->bands[NL80211_BAND_5GHZ]) {
+		debugfs_create_file("dfs_simulate_radar", 0200,
+				    ar->debug.debugfs_pdev, ar,
+				    &fops_simulate_radar);
+		debugfs_create_bool("dfs_block_radar_events", 0200,
+				    ar->debug.debugfs_pdev,
+				    &ar->dfs_block_radar_events);
+	}
+
+	return 0;
+}
+
+void ath11k_debugfs_unregister(struct ath11k *ar)
+{
+}
diff --git a/drivers/net/wireless/ath/ath11k/debugfs.h b/drivers/net/wireless/ath/ath11k/debugfs.h
new file mode 100644
index 000000000000..e5346af71f24
--- /dev/null
+++ b/drivers/net/wireless/ath/ath11k/debugfs.h
@@ -0,0 +1,217 @@
+/* SPDX-License-Identifier: BSD-3-Clause-Clear */
+/*
+ * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
+ */
+
+#ifndef _ATH11K_DEBUGFS_H_
+#define _ATH11K_DEBUGFS_H_
+
+#include "hal_tx.h"
+
+#define ATH11K_TX_POWER_MAX_VAL	70
+#define ATH11K_TX_POWER_MIN_VAL	0
+
+/* htt_dbg_ext_stats_type */
+enum ath11k_dbg_htt_ext_stats_type {
+	ATH11K_DBG_HTT_EXT_STATS_RESET                      =  0,
+	ATH11K_DBG_HTT_EXT_STATS_PDEV_TX                    =  1,
+	ATH11K_DBG_HTT_EXT_STATS_PDEV_RX                    =  2,
+	ATH11K_DBG_HTT_EXT_STATS_PDEV_TX_HWQ                =  3,
+	ATH11K_DBG_HTT_EXT_STATS_PDEV_TX_SCHED              =  4,
+	ATH11K_DBG_HTT_EXT_STATS_PDEV_ERROR                 =  5,
+	ATH11K_DBG_HTT_EXT_STATS_PDEV_TQM                   =  6,
+	ATH11K_DBG_HTT_EXT_STATS_TQM_CMDQ                   =  7,
+	ATH11K_DBG_HTT_EXT_STATS_TX_DE_INFO                 =  8,
+	ATH11K_DBG_HTT_EXT_STATS_PDEV_TX_RATE               =  9,
+	ATH11K_DBG_HTT_EXT_STATS_PDEV_RX_RATE               =  10,
+	ATH11K_DBG_HTT_EXT_STATS_PEER_INFO                  =  11,
+	ATH11K_DBG_HTT_EXT_STATS_TX_SELFGEN_INFO            =  12,
+	ATH11K_DBG_HTT_EXT_STATS_TX_MU_HWQ                  =  13,
+	ATH11K_DBG_HTT_EXT_STATS_RING_IF_INFO               =  14,
+	ATH11K_DBG_HTT_EXT_STATS_SRNG_INFO                  =  15,
+	ATH11K_DBG_HTT_EXT_STATS_SFM_INFO                   =  16,
+	ATH11K_DBG_HTT_EXT_STATS_PDEV_TX_MU                 =  17,
+	ATH11K_DBG_HTT_EXT_STATS_ACTIVE_PEERS_LIST          =  18,
+	ATH11K_DBG_HTT_EXT_STATS_PDEV_CCA_STATS             =  19,
+	ATH11K_DBG_HTT_EXT_STATS_TWT_SESSIONS               =  20,
+	ATH11K_DBG_HTT_EXT_STATS_REO_RESOURCE_STATS         =  21,
+	ATH11K_DBG_HTT_EXT_STATS_TX_SOUNDING_INFO           =  22,
+	ATH11K_DBG_HTT_EXT_STATS_PDEV_OBSS_PD_STATS	    =  23,
+	ATH11K_DBG_HTT_EXT_STATS_RING_BACKPRESSURE_STATS    =  24,
+
+	/* keep this last */
+	ATH11K_DBG_HTT_NUM_EXT_STATS,
+};
+
+struct debug_htt_stats_req {
+	bool done;
+	u8 pdev_id;
+	u8 type;
+	u8 peer_addr[ETH_ALEN];
+	struct completion cmpln;
+	u32 buf_len;
+	u8 buf[];
+};
+
+struct ath_pktlog_hdr {
+	u16 flags;
+	u16 missed_cnt;
+	u16 log_type;
+	u16 size;
+	u32 timestamp;
+	u32 type_specific_data;
+	u8 payload[];
+};
+
+#define ATH11K_HTT_PEER_STATS_RESET BIT(16)
+
+#define ATH11K_HTT_STATS_BUF_SIZE (1024 * 512)
+#define ATH11K_FW_STATS_BUF_SIZE (1024 * 1024)
+
+enum ath11k_pktlog_filter {
+	ATH11K_PKTLOG_RX		= 0x000000001,
+	ATH11K_PKTLOG_TX		= 0x000000002,
+	ATH11K_PKTLOG_RCFIND		= 0x000000004,
+	ATH11K_PKTLOG_RCUPDATE		= 0x000000008,
+	ATH11K_PKTLOG_EVENT_SMART_ANT	= 0x000000020,
+	ATH11K_PKTLOG_EVENT_SW		= 0x000000040,
+	ATH11K_PKTLOG_ANY		= 0x00000006f,
+};
+
+enum ath11k_pktlog_mode {
+	ATH11K_PKTLOG_MODE_LITE = 1,
+	ATH11K_PKTLOG_MODE_FULL = 2,
+};
+
+enum ath11k_pktlog_enum {
+	ATH11K_PKTLOG_TYPE_TX_CTRL      = 1,
+	ATH11K_PKTLOG_TYPE_TX_STAT      = 2,
+	ATH11K_PKTLOG_TYPE_TX_MSDU_ID   = 3,
+	ATH11K_PKTLOG_TYPE_RX_STAT      = 5,
+	ATH11K_PKTLOG_TYPE_RC_FIND      = 6,
+	ATH11K_PKTLOG_TYPE_RC_UPDATE    = 7,
+	ATH11K_PKTLOG_TYPE_TX_VIRT_ADDR = 8,
+	ATH11K_PKTLOG_TYPE_RX_CBF       = 10,
+	ATH11K_PKTLOG_TYPE_RX_STATBUF   = 22,
+	ATH11K_PKTLOG_TYPE_PPDU_STATS   = 23,
+	ATH11K_PKTLOG_TYPE_LITE_RX      = 24,
+};
+
+enum ath11k_dbg_aggr_mode {
+	ATH11K_DBG_AGGR_MODE_AUTO,
+	ATH11K_DBG_AGGR_MODE_MANUAL,
+	ATH11K_DBG_AGGR_MODE_MAX,
+};
+
+#ifdef CONFIG_ATH11K_DEBUGFS
+int ath11k_debugfs_soc_create(struct ath11k_base *ab);
+void ath11k_debugfs_soc_destroy(struct ath11k_base *ab);
+int ath11k_debugfs_pdev_create(struct ath11k_base *ab);
+void ath11k_debugfs_pdev_destroy(struct ath11k_base *ab);
+int ath11k_debugfs_register(struct ath11k *ar);
+void ath11k_debugfs_unregister(struct ath11k *ar);
+void ath11k_debugfs_fw_stats_process(struct ath11k_base *ab, struct sk_buff *skb);
+
+void ath11k_debugfs_fw_stats_init(struct ath11k *ar);
+
+static inline bool ath11k_debugfs_is_pktlog_lite_mode_enabled(struct ath11k *ar)
+{
+	return (ar->debug.pktlog_mode == ATH11K_PKTLOG_MODE_LITE);
+}
+
+static inline bool ath11k_debugfs_is_pktlog_rx_stats_enabled(struct ath11k *ar)
+{
+	return (!ar->debug.pktlog_peer_valid && ar->debug.pktlog_mode);
+}
+
+static inline bool ath11k_debugfs_is_pktlog_peer_valid(struct ath11k *ar, u8 *addr)
+{
+	return (ar->debug.pktlog_peer_valid && ar->debug.pktlog_mode &&
+		ether_addr_equal(addr, ar->debug.pktlog_peer_addr));
+}
+
+static inline int ath11k_debugfs_is_extd_tx_stats_enabled(struct ath11k *ar)
+{
+	return ar->debug.extd_tx_stats;
+}
+
+static inline int ath11k_debugfs_is_extd_rx_stats_enabled(struct ath11k *ar)
+{
+	return ar->debug.extd_rx_stats;
+}
+
+static inline int ath11k_debugfs_rx_filter(struct ath11k *ar)
+{
+	return ar->debug.rx_filter;
+}
+
+#else
+static inline int ath11k_debugfs_soc_create(struct ath11k_base *ab)
+{
+	return 0;
+}
+
+static inline void ath11k_debugfs_soc_destroy(struct ath11k_base *ab)
+{
+}
+
+static inline int ath11k_debugfs_pdev_create(struct ath11k_base *ab)
+{
+	return 0;
+}
+
+static inline void ath11k_debugfs_pdev_destroy(struct ath11k_base *ab)
+{
+}
+
+static inline int ath11k_debugfs_register(struct ath11k *ar)
+{
+	return 0;
+}
+
+static inline void ath11k_debugfs_unregister(struct ath11k *ar)
+{
+}
+
+static inline void ath11k_debugfs_fw_stats_process(struct ath11k_base *ab,
+						   struct sk_buff *skb)
+{
+}
+
+static inline void ath11k_debugfs_fw_stats_init(struct ath11k *ar)
+{
+}
+
+static inline int ath11k_debugfs_is_extd_tx_stats_enabled(struct ath11k *ar)
+{
+	return 0;
+}
+
+static inline int ath11k_debugfs_is_extd_rx_stats_enabled(struct ath11k *ar)
+{
+	return 0;
+}
+
+static inline bool ath11k_debugfs_is_pktlog_lite_mode_enabled(struct ath11k *ar)
+{
+	return false;
+}
+
+static inline bool ath11k_debugfs_is_pktlog_rx_stats_enabled(struct ath11k *ar)
+{
+	return false;
+}
+
+static inline bool ath11k_debugfs_is_pktlog_peer_valid(struct ath11k *ar, u8 *addr)
+{
+	return false;
+}
+
+static inline int ath11k_debugfs_rx_filter(struct ath11k *ar)
+{
+	return 0;
+}
+
+#endif /* CONFIG_MAC80211_DEBUGFS*/
+
+#endif /* _ATH11K_DEBUGFS_H_ */
diff --git a/drivers/net/wireless/ath/ath11k/debug_htt_stats.c b/drivers/net/wireless/ath/ath11k/debugfs_htt_stats.c
index ad3f08a5b031..9191ffa081c2 100644
--- a/drivers/net/wireless/ath/ath11k/debug_htt_stats.c
+++ b/drivers/net/wireless/ath/ath11k/debugfs_htt_stats.c
@@ -8,7 +8,7 @@
 #include "dp_tx.h"
 #include "dp_rx.h"
 #include "debug.h"
-#include "debug_htt_stats.h"
+#include "debugfs_htt_stats.h"
 
 #define HTT_DBG_OUT(buf, len, fmt, ...) \
 			scnprintf(buf, len, fmt "\n", ##__VA_ARGS__)
@@ -4253,8 +4253,8 @@ static int ath11k_dbg_htt_ext_stats_parse(struct ath11k_base *ab,
 	return 0;
 }
 
-void ath11k_dbg_htt_ext_stats_handler(struct ath11k_base *ab,
-				      struct sk_buff *skb)
+void ath11k_debugfs_htt_ext_stats_handler(struct ath11k_base *ab,
+					  struct sk_buff *skb)
 {
 	struct ath11k_htt_extd_stats_msg *msg;
 	struct debug_htt_stats_req *stats_req;
@@ -4402,7 +4402,7 @@ static int ath11k_prep_htt_stats_cfg_params(struct ath11k *ar, u8 type,
 	return 0;
 }
 
-int ath11k_dbg_htt_stats_req(struct ath11k *ar)
+int ath11k_debugfs_htt_stats_req(struct ath11k *ar)
 {
 	struct debug_htt_stats_req *stats_req = ar->debug.htt_stats.stats_req;
 	u8 type = stats_req->type;
@@ -4476,7 +4476,7 @@ static int ath11k_open_htt_stats(struct inode *inode, struct file *file)
 	ar->debug.htt_stats.stats_req = stats_req;
 	stats_req->type = type;
 
-	ret = ath11k_dbg_htt_stats_req(ar);
+	ret = ath11k_debugfs_htt_stats_req(ar);
 	if (ret < 0)
 		goto out;
 
@@ -4586,7 +4586,7 @@ static const struct file_operations fops_htt_stats_reset = {
 	.llseek = default_llseek,
 };
 
-void ath11k_debug_htt_stats_init(struct ath11k *ar)
+void ath11k_debugfs_htt_stats_init(struct ath11k *ar)
 {
 	spin_lock_init(&ar->debug.htt_stats.lock);
 	debugfs_create_file("htt_stats_type", 0600, ar->debug.debugfs_pdev,
diff --git a/drivers/net/wireless/ath/ath11k/debug_htt_stats.h b/drivers/net/wireless/ath/ath11k/debugfs_htt_stats.h
index 682a6ff222bd..74b2086eed9d 100644
--- a/drivers/net/wireless/ath/ath11k/debug_htt_stats.h
+++ b/drivers/net/wireless/ath/ath11k/debugfs_htt_stats.h
@@ -1660,8 +1660,6 @@ struct htt_pdev_obss_pd_stats_tlv {
 	u32        num_obss_tx_ppdu_failure;
 };
 
-void ath11k_debug_htt_stats_init(struct ath11k *ar);
-
 struct htt_ring_backpressure_stats_tlv {
 	u32 pdev_id;
 	u32 current_head_idx;
@@ -1687,4 +1685,29 @@ struct htt_ring_backpressure_stats_tlv {
 	u32 backpressure_hist[5];
 };
 
+#ifdef CONFIG_ATH11K_DEBUGFS
+
+void ath11k_debugfs_htt_stats_init(struct ath11k *ar);
+void ath11k_debugfs_htt_ext_stats_handler(struct ath11k_base *ab,
+					  struct sk_buff *skb);
+int ath11k_debugfs_htt_stats_req(struct ath11k *ar);
+
+#else /* CONFIG_ATH11K_DEBUGFS */
+
+static inline void ath11k_debugfs_htt_stats_init(struct ath11k *ar)
+{
+}
+
+static inline void ath11k_debugfs_htt_ext_stats_handler(struct ath11k_base *ab,
+							struct sk_buff *skb)
+{
+}
+
+static inline int ath11k_debugfs_htt_stats_req(struct ath11k *ar)
+{
+	return 0;
+}
+
+#endif /* CONFIG_ATH11K_DEBUGFS */
+
 #endif
diff --git a/drivers/net/wireless/ath/ath11k/debugfs_sta.c b/drivers/net/wireless/ath/ath11k/debugfs_sta.c
index 7308ed254232..270c0edbb10f 100644
--- a/drivers/net/wireless/ath/ath11k/debugfs_sta.c
+++ b/drivers/net/wireless/ath/ath11k/debugfs_sta.c
@@ -5,16 +5,16 @@
 
 #include <linux/vmalloc.h>
 
+#include "debugfs_sta.h"
 #include "core.h"
 #include "peer.h"
 #include "debug.h"
 #include "dp_tx.h"
-#include "debug_htt_stats.h"
+#include "debugfs_htt_stats.h"
 
-void
-ath11k_accumulate_per_peer_tx_stats(struct ath11k_sta *arsta,
-				    struct ath11k_per_peer_tx_stats *peer_stats,
-				    u8 legacy_rate_idx)
+void ath11k_debugfs_sta_add_tx_stats(struct ath11k_sta *arsta,
+				     struct ath11k_per_peer_tx_stats *peer_stats,
+				     u8 legacy_rate_idx)
 {
 	struct rate_info *txrate = &arsta->txrate;
 	struct ath11k_htt_tx_stats *tx_stats;
@@ -125,9 +125,9 @@ ath11k_accumulate_per_peer_tx_stats(struct ath11k_sta *arsta,
 	tx_stats->tx_duration += peer_stats->duration;
 }
 
-void ath11k_update_per_peer_stats_from_txcompl(struct ath11k *ar,
-					       struct sk_buff *msdu,
-					       struct hal_tx_status *ts)
+void ath11k_debugfs_sta_update_txcompl(struct ath11k *ar,
+				       struct sk_buff *msdu,
+				       struct hal_tx_status *ts)
 {
 	struct ath11k_base *ab = ar->ab;
 	struct ath11k_per_peer_tx_stats *peer_stats = &ar->cached_stats;
@@ -200,7 +200,8 @@ void ath11k_update_per_peer_stats_from_txcompl(struct ath11k *ar,
 	arsta->txrate.nss = arsta->last_txrate.nss;
 	arsta->txrate.bw = ath11k_mac_bw_to_mac80211_bw(bw);
 
-	ath11k_accumulate_per_peer_tx_stats(arsta, peer_stats, rate_idx);
+	ath11k_debugfs_sta_add_tx_stats(arsta, peer_stats, rate_idx);
+
 err_out:
 	spin_unlock_bh(&ab->base_lock);
 	rcu_read_unlock();
@@ -428,7 +429,7 @@ ath11k_dbg_sta_open_htt_peer_stats(struct inode *inode, struct file *file)
 	ar->debug.htt_stats.stats_req = stats_req;
 	stats_req->type = ATH11K_DBG_HTT_EXT_STATS_PEER_INFO;
 	memcpy(stats_req->peer_addr, sta->addr, ETH_ALEN);
-	ret = ath11k_dbg_htt_stats_req(ar);
+	ret = ath11k_debugfs_htt_stats_req(ar);
 	mutex_unlock(&ar->conf_mutex);
 	if (ret < 0)
 		goto out;
@@ -820,15 +821,15 @@ static const struct file_operations fops_htt_peer_stats_reset = {
 	.llseek = default_llseek,
 };
 
-void ath11k_sta_add_debugfs(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
-			    struct ieee80211_sta *sta, struct dentry *dir)
+void ath11k_debugfs_sta_op_add(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+			       struct ieee80211_sta *sta, struct dentry *dir)
 {
 	struct ath11k *ar = hw->priv;
 
-	if (ath11k_debug_is_extd_tx_stats_enabled(ar))
+	if (ath11k_debugfs_is_extd_tx_stats_enabled(ar))
 		debugfs_create_file("tx_stats", 0400, dir, sta,
 				    &fops_tx_stats);
-	if (ath11k_debug_is_extd_rx_stats_enabled(ar))
+	if (ath11k_debugfs_is_extd_rx_stats_enabled(ar))
 		debugfs_create_file("rx_stats", 0400, dir, sta,
 				    &fops_rx_stats);
 
diff --git a/drivers/net/wireless/ath/ath11k/debugfs_sta.h b/drivers/net/wireless/ath/ath11k/debugfs_sta.h
new file mode 100644
index 000000000000..18dc65d9edcf
--- /dev/null
+++ b/drivers/net/wireless/ath/ath11k/debugfs_sta.h
@@ -0,0 +1,44 @@
+/* SPDX-License-Identifier: BSD-3-Clause-Clear */
+/*
+ * Copyright (c) 2018-2020 The Linux Foundation. All rights reserved.
+ */
+
+#ifndef _ATH11K_DEBUGFS_STA_H_
+#define _ATH11K_DEBUGFS_STA_H_
+
+#include <net/mac80211.h>
+
+#include "core.h"
+#include "hal_tx.h"
+
+#ifdef CONFIG_ATH11K_DEBUGFS
+
+void ath11k_debugfs_sta_op_add(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+			       struct ieee80211_sta *sta, struct dentry *dir);
+void ath11k_debugfs_sta_add_tx_stats(struct ath11k_sta *arsta,
+				     struct ath11k_per_peer_tx_stats *peer_stats,
+				     u8 legacy_rate_idx);
+void ath11k_debugfs_sta_update_txcompl(struct ath11k *ar,
+				       struct sk_buff *msdu,
+				       struct hal_tx_status *ts);
+
+#else /* CONFIG_ATH11K_DEBUGFS */
+
+#define ath11k_debugfs_sta_op_add NULL
+
+static inline void
+ath11k_debugfs_sta_add_tx_stats(struct ath11k_sta *arsta,
+				struct ath11k_per_peer_tx_stats *peer_stats,
+				u8 legacy_rate_idx)
+{
+}
+
+static inline void ath11k_debugfs_sta_update_txcompl(struct ath11k *ar,
+						     struct sk_buff *msdu,
+						     struct hal_tx_status *ts)
+{
+}
+
+#endif /* CONFIG_ATH11K_DEBUGFS */
+
+#endif /* _ATH11K_DEBUGFS_STA_H_ */
diff --git a/drivers/net/wireless/ath/ath11k/dp.c b/drivers/net/wireless/ath/ath11k/dp.c
index 2617ec221775..59dd185a0cfc 100644
--- a/drivers/net/wireless/ath/ath11k/dp.c
+++ b/drivers/net/wireless/ath/ath11k/dp.c
@@ -304,11 +304,25 @@ int ath11k_dp_srng_setup(struct ath11k_base *ab, struct dp_srng *ring,
 	return 0;
 }
 
+static void ath11k_dp_stop_shadow_timers(struct ath11k_base *ab)
+{
+	int i;
+
+	if (!ab->hw_params.supports_shadow_regs)
+		return;
+
+	for (i = 0; i < DP_TCL_NUM_RING_MAX; i++)
+		ath11k_dp_shadow_stop_timer(ab, &ab->dp.tx_ring_timer[i]);
+
+	ath11k_dp_shadow_stop_timer(ab, &ab->dp.reo_cmd_timer);
+}
+
 static void ath11k_dp_srng_common_cleanup(struct ath11k_base *ab)
 {
 	struct ath11k_dp *dp = &ab->dp;
 	int i;
 
+	ath11k_dp_stop_shadow_timers(ab);
 	ath11k_dp_srng_cleanup(ab, &dp->wbm_desc_rel_ring);
 	ath11k_dp_srng_cleanup(ab, &dp->tcl_cmd_ring);
 	ath11k_dp_srng_cleanup(ab, &dp->tcl_status_ring);
@@ -374,6 +388,10 @@ static int ath11k_dp_srng_common_setup(struct ath11k_base *ab)
 
 		srng = &ab->hal.srng_list[dp->tx_ring[i].tcl_data_ring.ring_id];
 		ath11k_hal_tx_init_data_ring(ab, srng);
+
+		ath11k_dp_shadow_init_timer(ab, &dp->tx_ring_timer[i],
+					    ATH11K_SHADOW_DP_TIMER_INTERVAL,
+					    dp->tx_ring[i].tcl_data_ring.ring_id);
 	}
 
 	ret = ath11k_dp_srng_setup(ab, &dp->reo_reinject_ring, HAL_REO_REINJECT,
@@ -409,6 +427,10 @@ static int ath11k_dp_srng_common_setup(struct ath11k_base *ab)
 	srng = &ab->hal.srng_list[dp->reo_cmd_ring.ring_id];
 	ath11k_hal_reo_init_cmd_ring(ab, srng);
 
+	ath11k_dp_shadow_init_timer(ab, &dp->reo_cmd_timer,
+				    ATH11K_SHADOW_CTRL_TIMER_INTERVAL,
+				    dp->reo_cmd_ring.ring_id);
+
 	ret = ath11k_dp_srng_setup(ab, &dp->reo_status_ring, HAL_REO_STATUS,
 				   0, 0, DP_REO_STATUS_RING_SIZE);
 	if (ret) {
@@ -812,8 +834,7 @@ int ath11k_dp_service_srng(struct ath11k_base *ab,
 				struct dp_rxdma_ring *rx_ring = &dp->rx_refill_buf_ring;
 
 				ath11k_dp_rxbufs_replenish(ab, id, rx_ring, 0,
-							   HAL_RX_BUF_RBM_SW3_BM,
-							   GFP_ATOMIC);
+							   HAL_RX_BUF_RBM_SW3_BM);
 			}
 		}
 	}
@@ -829,10 +850,12 @@ void ath11k_dp_pdev_free(struct ath11k_base *ab)
 	struct ath11k *ar;
 	int i;
 
+	del_timer_sync(&ab->mon_reap_timer);
+
 	for (i = 0; i < ab->num_radios; i++) {
 		ar = ab->pdevs[i].ar;
 		ath11k_dp_rx_pdev_free(ab, i);
-		ath11k_debug_unregister(ar);
+		ath11k_debugfs_unregister(ar);
 		ath11k_dp_rx_pdev_mon_detach(ar);
 	}
 }
@@ -1065,3 +1088,78 @@ fail_link_desc_cleanup:
 
 	return ret;
 }
+
+static void ath11k_dp_shadow_timer_handler(struct timer_list *t)
+{
+	struct ath11k_hp_update_timer *update_timer = from_timer(update_timer,
+								 t, timer);
+	struct ath11k_base *ab = update_timer->ab;
+	struct hal_srng	*srng = &ab->hal.srng_list[update_timer->ring_id];
+
+	spin_lock_bh(&srng->lock);
+
+	/* when the timer is fired, the handler checks whether there
+	 * are new TX happened. The handler updates HP only when there
+	 * are no TX operations during the timeout interval, and stop
+	 * the timer. Timer will be started again when TX happens again.
+	 */
+	if (update_timer->timer_tx_num != update_timer->tx_num) {
+		update_timer->timer_tx_num = update_timer->tx_num;
+		mod_timer(&update_timer->timer, jiffies +
+		  msecs_to_jiffies(update_timer->interval));
+	} else {
+		update_timer->started = false;
+		ath11k_hal_srng_shadow_update_hp_tp(ab, srng);
+	}
+
+	spin_unlock_bh(&srng->lock);
+}
+
+void ath11k_dp_shadow_start_timer(struct ath11k_base *ab,
+				  struct hal_srng *srng,
+				  struct ath11k_hp_update_timer *update_timer)
+{
+	lockdep_assert_held(&srng->lock);
+
+	if (!ab->hw_params.supports_shadow_regs)
+		return;
+
+	update_timer->tx_num++;
+
+	if (update_timer->started)
+		return;
+
+	update_timer->started = true;
+	update_timer->timer_tx_num = update_timer->tx_num;
+	mod_timer(&update_timer->timer, jiffies +
+		  msecs_to_jiffies(update_timer->interval));
+}
+
+void ath11k_dp_shadow_stop_timer(struct ath11k_base *ab,
+				 struct ath11k_hp_update_timer *update_timer)
+{
+	if (!ab->hw_params.supports_shadow_regs)
+		return;
+
+	if (!update_timer->init)
+		return;
+
+	del_timer_sync(&update_timer->timer);
+}
+
+void ath11k_dp_shadow_init_timer(struct ath11k_base *ab,
+				 struct ath11k_hp_update_timer *update_timer,
+				 u32 interval, u32 ring_id)
+{
+	if (!ab->hw_params.supports_shadow_regs)
+		return;
+
+	update_timer->tx_num = 0;
+	update_timer->timer_tx_num = 0;
+	update_timer->ab = ab;
+	update_timer->ring_id = ring_id;
+	update_timer->interval = interval;
+	update_timer->init = true;
+	timer_setup(&update_timer->timer,
+		    ath11k_dp_shadow_timer_handler, 0);
+}
diff --git a/drivers/net/wireless/ath/ath11k/dp.h b/drivers/net/wireless/ath/ath11k/dp.h
index 558f03fbec99..ee8db812589b 100644
--- a/drivers/net/wireless/ath/ath11k/dp.h
+++ b/drivers/net/wireless/ath/ath11k/dp.h
@@ -40,6 +40,7 @@ struct dp_rx_tid {
 
 #define DP_REO_DESC_FREE_THRESHOLD  64
 #define DP_REO_DESC_FREE_TIMEOUT_MS 1000
+#define DP_MON_SERVICE_BUDGET       128
 
 struct dp_reo_cache_flush_elem {
 	struct list_head list;
@@ -205,6 +206,20 @@ struct ath11k_pdev_dp {
 #define DP_TX_DESC_ID_MSDU_ID GENMASK(18, 2)
 #define DP_TX_DESC_ID_POOL_ID GENMASK(20, 19)
 
+#define ATH11K_SHADOW_DP_TIMER_INTERVAL 20
+#define ATH11K_SHADOW_CTRL_TIMER_INTERVAL 10
+
+struct ath11k_hp_update_timer {
+	struct timer_list timer;
+	bool started;
+	bool init;
+	u32 tx_num;
+	u32 timer_tx_num;
+	u32 ring_id;
+	u32 interval;
+	struct ath11k_base *ab;
+};
+
 struct ath11k_dp {
 	struct ath11k_base *ab;
 	enum ath11k_htc_ep_id eid;
@@ -234,6 +249,8 @@ struct ath11k_dp {
 	 * - reo_cmd_cache_flush_count
 	 */
 	spinlock_t reo_cmd_lock;
+	struct ath11k_hp_update_timer reo_cmd_timer;
+	struct ath11k_hp_update_timer tx_ring_timer[DP_TCL_NUM_RING_MAX];
 };
 
 /* HTT definitions */
@@ -497,7 +514,7 @@ struct htt_ppdu_stats_cfg_cmd {
 } __packed;
 
 #define HTT_PPDU_STATS_CFG_MSG_TYPE		GENMASK(7, 0)
-#define HTT_PPDU_STATS_CFG_PDEV_ID		GENMASK(16, 9)
+#define HTT_PPDU_STATS_CFG_PDEV_ID		GENMASK(15, 8)
 #define HTT_PPDU_STATS_CFG_TLV_TYPE_BITMASK	GENMASK(31, 16)
 
 enum htt_ppdu_stats_tag_type {
@@ -1615,5 +1632,13 @@ int ath11k_dp_link_desc_setup(struct ath11k_base *ab,
 			      struct dp_link_desc_bank *link_desc_banks,
 			      u32 ring_type, struct hal_srng *srng,
 			      u32 n_link_desc);
+void ath11k_dp_shadow_start_timer(struct ath11k_base *ab,
+				  struct hal_srng	*srng,
+				  struct ath11k_hp_update_timer *update_timer);
+void ath11k_dp_shadow_stop_timer(struct ath11k_base *ab,
+				 struct ath11k_hp_update_timer *update_timer);
+void ath11k_dp_shadow_init_timer(struct ath11k_base *ab,
+				 struct ath11k_hp_update_timer *update_timer,
+				 u32 interval, u32 ring_id);
 
 #endif
diff --git a/drivers/net/wireless/ath/ath11k/dp_rx.c b/drivers/net/wireless/ath/ath11k/dp_rx.c
index a507c1231a59..01625327eef7 100644
--- a/drivers/net/wireless/ath/ath11k/dp_rx.c
+++ b/drivers/net/wireless/ath/ath11k/dp_rx.c
@@ -9,6 +9,8 @@
 #include <crypto/hash.h>
 #include "core.h"
 #include "debug.h"
+#include "debugfs_htt_stats.h"
+#include "debugfs_sta.h"
 #include "hal_desc.h"
 #include "hw.h"
 #include "dp_rx.h"
@@ -260,12 +262,23 @@ static u32 ath11k_dp_rxdesc_get_ppduid(struct hal_rx_desc *rx_desc)
 	return __le16_to_cpu(rx_desc->mpdu_start.phy_ppdu_id);
 }
 
+static void ath11k_dp_service_mon_ring(struct timer_list *t)
+{
+	struct ath11k_base *ab = from_timer(ab, t, mon_reap_timer);
+	int i;
+
+	for (i = 0; i < ab->hw_params.num_rxmda_per_pdev; i++)
+		ath11k_dp_rx_process_mon_rings(ab, i, NULL, DP_MON_SERVICE_BUDGET);
+
+	mod_timer(&ab->mon_reap_timer, jiffies +
+		  msecs_to_jiffies(ATH11K_MON_TIMER_INTERVAL));
+}
+
 /* Returns number of Rx buffers replenished */
 int ath11k_dp_rxbufs_replenish(struct ath11k_base *ab, int mac_id,
 			       struct dp_rxdma_ring *rx_ring,
 			       int req_entries,
-			       enum hal_rx_buf_return_buf_manager mgr,
-			       gfp_t gfp)
+			       enum hal_rx_buf_return_buf_manager mgr)
 {
 	struct hal_srng *srng;
 	u32 *desc;
@@ -312,7 +325,7 @@ int ath11k_dp_rxbufs_replenish(struct ath11k_base *ab, int mac_id,
 
 		spin_lock_bh(&rx_ring->idr_lock);
 		buf_id = idr_alloc(&rx_ring->bufs_idr, skb, 0,
-				   rx_ring->bufs_max * 3, gfp);
+				   rx_ring->bufs_max * 3, GFP_ATOMIC);
 		spin_unlock_bh(&rx_ring->idr_lock);
 		if (buf_id < 0)
 			goto fail_dma_unmap;
@@ -432,7 +445,7 @@ static int ath11k_dp_rxdma_ring_buf_setup(struct ath11k *ar,
 
 	rx_ring->bufs_max = num_entries;
 	ath11k_dp_rxbufs_replenish(ar->ab, dp->mac_id, rx_ring, num_entries,
-				   HAL_RX_BUF_RBM_SW3_BM, GFP_KERNEL);
+				   HAL_RX_BUF_RBM_SW3_BM);
 	return 0;
 }
 
@@ -568,9 +581,14 @@ static int ath11k_dp_rx_pdev_srng_alloc(struct ath11k *ar)
 	/* if rxdma1_enable is false, then it doesn't need
 	 * to setup rxdam_mon_buf_ring, rxdma_mon_dst_ring
 	 * and rxdma_mon_desc_ring.
+	 * init reap timer for QCA6390.
 	 */
-	if (!ar->ab->hw_params.rxdma1_enable)
+	if (!ar->ab->hw_params.rxdma1_enable) {
+		//init mon status buffer reap timer
+		timer_setup(&ar->ab->mon_reap_timer,
+			    ath11k_dp_service_mon_ring, 0);
 		return 0;
+	}
 
 	ret = ath11k_dp_srng_setup(ar->ab,
 				   &dp->rxdma_mon_buf_ring.refill_buf_ring,
@@ -1433,9 +1451,8 @@ ath11k_update_per_peer_tx_stats(struct ath11k *ar,
 			HTT_USR_CMPLTN_LONG_RETRY(usr_stats->cmpltn_cmn.flags) +
 			HTT_USR_CMPLTN_SHORT_RETRY(usr_stats->cmpltn_cmn.flags);
 
-		if (ath11k_debug_is_extd_tx_stats_enabled(ar))
-			ath11k_accumulate_per_peer_tx_stats(arsta,
-							    peer_stats, rate_idx);
+		if (ath11k_debugfs_is_extd_tx_stats_enabled(ar))
+			ath11k_debugfs_sta_add_tx_stats(arsta, peer_stats, rate_idx);
 	}
 
 	spin_unlock_bh(&ab->base_lock);
@@ -1477,7 +1494,7 @@ struct htt_ppdu_stats_info *ath11k_dp_htt_get_ppdu_desc(struct ath11k *ar,
 	}
 	spin_unlock_bh(&ar->data_lock);
 
-	ppdu_info = kzalloc(sizeof(*ppdu_info), GFP_KERNEL);
+	ppdu_info = kzalloc(sizeof(*ppdu_info), GFP_ATOMIC);
 	if (!ppdu_info)
 		return NULL;
 
@@ -1511,7 +1528,7 @@ static int ath11k_htt_pull_ppdu_stats(struct ath11k_base *ab,
 		goto exit;
 	}
 
-	if (ath11k_debug_is_pktlog_lite_mode_enabled(ar))
+	if (ath11k_debugfs_is_pktlog_lite_mode_enabled(ar))
 		trace_ath11k_htt_ppdu_stats(ar, skb->data, len);
 
 	ppdu_info = ath11k_dp_htt_get_ppdu_desc(ar, ppdu_id);
@@ -1658,7 +1675,7 @@ void ath11k_dp_htt_htc_t2h_msg_handler(struct ath11k_base *ab,
 		ath11k_htt_pull_ppdu_stats(ab, skb);
 		break;
 	case HTT_T2H_MSG_TYPE_EXT_STATS_CONF:
-		ath11k_dbg_htt_ext_stats_handler(ab, skb);
+		ath11k_debugfs_htt_ext_stats_handler(ab, skb);
 		break;
 	case HTT_T2H_MSG_TYPE_PKTLOG:
 		ath11k_htt_pktlog(ab, skb);
@@ -2597,7 +2614,7 @@ try_again:
 		rx_ring = &ar->dp.rx_refill_buf_ring;
 
 		ath11k_dp_rxbufs_replenish(ab, i, rx_ring, num_buffs_reaped[i],
-					   HAL_RX_BUF_RBM_SW3_BM, GFP_ATOMIC);
+					   HAL_RX_BUF_RBM_SW3_BM);
 	}
 
 	ath11k_dp_rx_process_received_packets(ab, napi, &msdu_list,
@@ -2679,7 +2696,7 @@ static void ath11k_dp_rx_update_peer_stats(struct ath11k_sta *arsta,
 
 static struct sk_buff *ath11k_dp_rx_alloc_mon_status_buf(struct ath11k_base *ab,
 							 struct dp_rxdma_ring *rx_ring,
-							 int *buf_id, gfp_t gfp)
+							 int *buf_id)
 {
 	struct sk_buff *skb;
 	dma_addr_t paddr;
@@ -2704,7 +2721,7 @@ static struct sk_buff *ath11k_dp_rx_alloc_mon_status_buf(struct ath11k_base *ab,
 
 	spin_lock_bh(&rx_ring->idr_lock);
 	*buf_id = idr_alloc(&rx_ring->bufs_idr, skb, 0,
-			    rx_ring->bufs_max, gfp);
+			    rx_ring->bufs_max, GFP_ATOMIC);
 	spin_unlock_bh(&rx_ring->idr_lock);
 	if (*buf_id < 0)
 		goto fail_dma_unmap;
@@ -2724,8 +2741,7 @@ fail_alloc_skb:
 int ath11k_dp_rx_mon_status_bufs_replenish(struct ath11k_base *ab, int mac_id,
 					   struct dp_rxdma_ring *rx_ring,
 					   int req_entries,
-					   enum hal_rx_buf_return_buf_manager mgr,
-					   gfp_t gfp)
+					   enum hal_rx_buf_return_buf_manager mgr)
 {
 	struct hal_srng *srng;
 	u32 *desc;
@@ -2751,7 +2767,7 @@ int ath11k_dp_rx_mon_status_bufs_replenish(struct ath11k_base *ab, int mac_id,
 
 	while (num_remain > 0) {
 		skb = ath11k_dp_rx_alloc_mon_status_buf(ab, rx_ring,
-							&buf_id, gfp);
+							&buf_id);
 		if (!skb)
 			break;
 		paddr = ATH11K_SKB_RXCB(skb)->paddr;
@@ -2862,7 +2878,7 @@ static int ath11k_dp_rx_reap_mon_status_ring(struct ath11k_base *ab, int mac_id,
 		}
 move_next:
 		skb = ath11k_dp_rx_alloc_mon_status_buf(ab, rx_ring,
-							&buf_id, GFP_ATOMIC);
+							&buf_id);
 
 		if (!skb) {
 			ath11k_hal_rx_buf_addr_info_set(rx_mon_status_desc, 0, 0,
@@ -2909,7 +2925,7 @@ int ath11k_dp_rx_process_mon_status(struct ath11k_base *ab, int mac_id,
 		memset(&ppdu_info, 0, sizeof(ppdu_info));
 		ppdu_info.peer_id = HAL_INVALID_PEERID;
 
-		if (ath11k_debug_is_pktlog_rx_stats_enabled(ar))
+		if (ath11k_debugfs_is_pktlog_rx_stats_enabled(ar))
 			trace_ath11k_htt_rxdesc(ar, skb->data, DP_RX_BUFFER_SIZE);
 
 		hal_status = ath11k_hal_rx_parse_mon_status(ab, &ppdu_info, skb);
@@ -2937,7 +2953,7 @@ int ath11k_dp_rx_process_mon_status(struct ath11k_base *ab, int mac_id,
 		arsta = (struct ath11k_sta *)peer->sta->drv_priv;
 		ath11k_dp_rx_update_peer_stats(arsta, &ppdu_info);
 
-		if (ath11k_debug_is_pktlog_peer_valid(ar, peer->addr))
+		if (ath11k_debugfs_is_pktlog_peer_valid(ar, peer->addr))
 			trace_ath11k_htt_rxdesc(ar, skb->data, DP_RX_BUFFER_SIZE);
 
 		spin_unlock_bh(&ab->base_lock);
@@ -3675,7 +3691,7 @@ exit:
 		rx_ring = &ar->dp.rx_refill_buf_ring;
 
 		ath11k_dp_rxbufs_replenish(ab, i, rx_ring, n_bufs_reaped[i],
-					   HAL_RX_BUF_RBM_SW3_BM, GFP_ATOMIC);
+					   HAL_RX_BUF_RBM_SW3_BM);
 	}
 
 	return tot_n_bufs_reaped;
@@ -3971,7 +3987,7 @@ int ath11k_dp_rx_process_wbm_err(struct ath11k_base *ab,
 		rx_ring = &ar->dp.rx_refill_buf_ring;
 
 		ath11k_dp_rxbufs_replenish(ab, i, rx_ring, num_buffs_reaped[i],
-					   HAL_RX_BUF_RBM_SW3_BM, GFP_ATOMIC);
+					   HAL_RX_BUF_RBM_SW3_BM);
 	}
 
 	rcu_read_lock();
@@ -4080,7 +4096,7 @@ int ath11k_dp_process_rxdma_err(struct ath11k_base *ab, int mac_id, int budget)
 
 	if (num_buf_freed)
 		ath11k_dp_rxbufs_replenish(ab, mac_id, rx_ring, num_buf_freed,
-					   HAL_RX_BUF_RBM_SW3_BM, GFP_ATOMIC);
+					   HAL_RX_BUF_RBM_SW3_BM);
 
 	return budget - quota;
 }
@@ -4290,8 +4306,13 @@ int ath11k_dp_rx_monitor_link_desc_return(struct ath11k *ar,
 	void *src_srng_desc;
 	int ret = 0;
 
-	dp_srng = &dp->rxdma_mon_desc_ring;
-	hal_srng = &ar->ab->hal.srng_list[dp_srng->ring_id];
+	if (ar->ab->hw_params.rxdma1_enable) {
+		dp_srng = &dp->rxdma_mon_desc_ring;
+		hal_srng = &ar->ab->hal.srng_list[dp_srng->ring_id];
+	} else {
+		dp_srng = &ar->ab->dp.wbm_desc_rel_ring;
+		hal_srng = &ar->ab->hal.srng_list[dp_srng->ring_id];
+	}
 
 	ath11k_hal_srng_access_begin(ar->ab, hal_srng);
 
@@ -4315,16 +4336,16 @@ int ath11k_dp_rx_monitor_link_desc_return(struct ath11k *ar,
 static
 void ath11k_dp_rx_mon_next_link_desc_get(void *rx_msdu_link_desc,
 					 dma_addr_t *paddr, u32 *sw_cookie,
+					 u8 *rbm,
 					 void **pp_buf_addr_info)
 {
 	struct hal_rx_msdu_link *msdu_link =
 			(struct hal_rx_msdu_link *)rx_msdu_link_desc;
 	struct ath11k_buffer_addr *buf_addr_info;
-	u8 rbm = 0;
 
 	buf_addr_info = (struct ath11k_buffer_addr *)&msdu_link->buf_addr_info;
 
-	ath11k_hal_rx_buf_addr_info_get(buf_addr_info, paddr, sw_cookie, &rbm);
+	ath11k_hal_rx_buf_addr_info_get(buf_addr_info, paddr, sw_cookie, rbm);
 
 	*pp_buf_addr_info = (void *)buf_addr_info;
 }
@@ -4435,7 +4456,7 @@ static void ath11k_dp_mon_get_buf_len(struct hal_rx_msdu_desc_info *info,
 }
 
 static u32
-ath11k_dp_rx_mon_mpdu_pop(struct ath11k *ar,
+ath11k_dp_rx_mon_mpdu_pop(struct ath11k *ar, int mac_id,
 			  void *ring_entry, struct sk_buff **head_msdu,
 			  struct sk_buff **tail_msdu, u32 *npackets,
 			  u32 *ppdu_id)
@@ -4460,9 +4481,15 @@ ath11k_dp_rx_mon_mpdu_pop(struct ath11k *ar,
 	struct hal_reo_entrance_ring *ent_desc =
 			(struct hal_reo_entrance_ring *)ring_entry;
 	int buf_id;
+	u32 rx_link_buf_info[2];
+	u8 rbm;
+
+	if (!ar->ab->hw_params.rxdma1_enable)
+		rx_ring = &dp->rx_refill_buf_ring;
 
 	ath11k_hal_rx_reo_ent_buf_paddr_get(ring_entry, &paddr,
-					    &sw_cookie, &p_last_buf_addr_info,
+					    &sw_cookie,
+					    &p_last_buf_addr_info, &rbm,
 					    &msdu_cnt);
 
 	if (FIELD_GET(HAL_REO_ENTR_RING_INFO1_RXDMA_PUSH_REASON,
@@ -4488,9 +4515,14 @@ ath11k_dp_rx_mon_mpdu_pop(struct ath11k *ar,
 			return rx_bufs_used;
 		}
 
-		rx_msdu_link_desc =
-			(void *)pmon->link_desc_banks[sw_cookie].vaddr +
-			(paddr - pmon->link_desc_banks[sw_cookie].paddr);
+		if (ar->ab->hw_params.rxdma1_enable)
+			rx_msdu_link_desc =
+				(void *)pmon->link_desc_banks[sw_cookie].vaddr +
+				(paddr - pmon->link_desc_banks[sw_cookie].paddr);
+		else
+			rx_msdu_link_desc =
+				(void *)ar->ab->dp.link_desc_banks[sw_cookie].vaddr +
+				(paddr - ar->ab->dp.link_desc_banks[sw_cookie].paddr);
 
 		ath11k_hal_rx_msdu_list_get(ar, rx_msdu_link_desc, &msdu_list,
 					    &num_msdus);
@@ -4586,15 +4618,22 @@ next_msdu:
 			spin_unlock_bh(&rx_ring->idr_lock);
 		}
 
+		ath11k_hal_rx_buf_addr_info_set(rx_link_buf_info, paddr, sw_cookie, rbm);
+
 		ath11k_dp_rx_mon_next_link_desc_get(rx_msdu_link_desc, &paddr,
-						    &sw_cookie,
+						    &sw_cookie, &rbm,
 						    &p_buf_addr_info);
 
-		if (ath11k_dp_rx_monitor_link_desc_return(ar,
-							  p_last_buf_addr_info,
-							  dp->mac_id))
-			ath11k_dbg(ar->ab, ATH11K_DBG_DATA,
-				   "dp_rx_monitor_link_desc_return failed");
+		if (ar->ab->hw_params.rxdma1_enable) {
+			if (ath11k_dp_rx_monitor_link_desc_return(ar,
+								  p_last_buf_addr_info,
+								  dp->mac_id))
+				ath11k_dbg(ar->ab, ATH11K_DBG_DATA,
+					   "dp_rx_monitor_link_desc_return failed");
+		} else {
+			ath11k_dp_rx_link_desc_return(ar->ab, rx_link_buf_info,
+						      HAL_WBM_REL_BM_ACT_PUT_IN_IDLE);
+		}
 
 		p_last_buf_addr_info = p_buf_addr_info;
 
@@ -4778,8 +4817,8 @@ mon_deliver_fail:
 	return -EINVAL;
 }
 
-static void ath11k_dp_rx_mon_dest_process(struct ath11k *ar, u32 quota,
-					  struct napi_struct *napi)
+static void ath11k_dp_rx_mon_dest_process(struct ath11k *ar, int mac_id,
+					  u32 quota, struct napi_struct *napi)
 {
 	struct ath11k_pdev_dp *dp = &ar->dp;
 	struct ath11k_mon_data *pmon = (struct ath11k_mon_data *)&dp->mon_data;
@@ -4787,10 +4826,16 @@ static void ath11k_dp_rx_mon_dest_process(struct ath11k *ar, u32 quota,
 	void *mon_dst_srng;
 	u32 ppdu_id;
 	u32 rx_bufs_used;
+	u32 ring_id;
 	struct ath11k_pdev_mon_stats *rx_mon_stats;
 	u32	 npackets = 0;
 
-	mon_dst_srng = &ar->ab->hal.srng_list[dp->rxdma_mon_dst_ring.ring_id];
+	if (ar->ab->hw_params.rxdma1_enable)
+		ring_id = dp->rxdma_mon_dst_ring.ring_id;
+	else
+		ring_id = dp->rxdma_err_dst_ring[mac_id].ring_id;
+
+	mon_dst_srng = &ar->ab->hal.srng_list[ring_id];
 
 	if (!mon_dst_srng) {
 		ath11k_warn(ar->ab,
@@ -4813,7 +4858,7 @@ static void ath11k_dp_rx_mon_dest_process(struct ath11k *ar, u32 quota,
 		head_msdu = NULL;
 		tail_msdu = NULL;
 
-		rx_bufs_used += ath11k_dp_rx_mon_mpdu_pop(ar, ring_entry,
+		rx_bufs_used += ath11k_dp_rx_mon_mpdu_pop(ar, mac_id, ring_entry,
 							  &head_msdu,
 							  &tail_msdu,
 							  &npackets, &ppdu_id);
@@ -4840,15 +4885,21 @@ static void ath11k_dp_rx_mon_dest_process(struct ath11k *ar, u32 quota,
 
 	if (rx_bufs_used) {
 		rx_mon_stats->dest_ppdu_done++;
-		ath11k_dp_rxbufs_replenish(ar->ab, dp->mac_id,
-					   &dp->rxdma_mon_buf_ring,
-					   rx_bufs_used,
-					   HAL_RX_BUF_RBM_SW3_BM, GFP_ATOMIC);
+		if (ar->ab->hw_params.rxdma1_enable)
+			ath11k_dp_rxbufs_replenish(ar->ab, dp->mac_id,
+						   &dp->rxdma_mon_buf_ring,
+						   rx_bufs_used,
+						   HAL_RX_BUF_RBM_SW3_BM);
+		else
+			ath11k_dp_rxbufs_replenish(ar->ab, dp->mac_id,
+						   &dp->rx_refill_buf_ring,
+						   rx_bufs_used,
+						   HAL_RX_BUF_RBM_SW3_BM);
 	}
 }
 
 static void ath11k_dp_rx_mon_status_process_tlv(struct ath11k *ar,
-						u32 quota,
+						int mac_id, u32 quota,
 						struct napi_struct *napi)
 {
 	struct ath11k_pdev_dp *dp = &ar->dp;
@@ -4872,7 +4923,7 @@ static void ath11k_dp_rx_mon_status_process_tlv(struct ath11k *ar,
 		if (tlv_status == HAL_TLV_STATUS_PPDU_DONE) {
 			rx_mon_stats->status_ppdu_done++;
 			pmon->mon_ppdu_status = DP_PPDU_STATUS_DONE;
-			ath11k_dp_rx_mon_dest_process(ar, quota, napi);
+			ath11k_dp_rx_mon_dest_process(ar, mac_id, quota, napi);
 			pmon->mon_ppdu_status = DP_PPDU_STATUS_START;
 		}
 		dev_kfree_skb_any(status_skb);
@@ -4887,10 +4938,10 @@ static int ath11k_dp_mon_process_rx(struct ath11k_base *ab, int mac_id,
 	struct ath11k_mon_data *pmon = (struct ath11k_mon_data *)&dp->mon_data;
 	int num_buffs_reaped = 0;
 
-	num_buffs_reaped = ath11k_dp_rx_reap_mon_status_ring(ar->ab, dp->mac_id, &budget,
+	num_buffs_reaped = ath11k_dp_rx_reap_mon_status_ring(ar->ab, mac_id, &budget,
 							     &pmon->rx_status_q);
 	if (num_buffs_reaped)
-		ath11k_dp_rx_mon_status_process_tlv(ar, budget, napi);
+		ath11k_dp_rx_mon_status_process_tlv(ar, mac_id, budget, napi);
 
 	return num_buffs_reaped;
 }
diff --git a/drivers/net/wireless/ath/ath11k/dp_rx.h b/drivers/net/wireless/ath/ath11k/dp_rx.h
index 88bbcae14e34..fbea45f79c9b 100644
--- a/drivers/net/wireless/ath/ath11k/dp_rx.h
+++ b/drivers/net/wireless/ath/ath11k/dp_rx.h
@@ -74,8 +74,7 @@ int ath11k_dp_process_rx(struct ath11k_base *ab, int mac_id,
 int ath11k_dp_rxbufs_replenish(struct ath11k_base *ab, int mac_id,
 			       struct dp_rxdma_ring *rx_ring,
 			       int req_entries,
-			       enum hal_rx_buf_return_buf_manager mgr,
-			       gfp_t gfp);
+			       enum hal_rx_buf_return_buf_manager mgr);
 int ath11k_dp_htt_tlv_iter(struct ath11k_base *ab, const void *ptr, size_t len,
 			   int (*iter)(struct ath11k_base *ar, u16 tag, u16 len,
 				       const void *ptr, void *data),
@@ -87,8 +86,7 @@ int ath11k_dp_rx_process_mon_status(struct ath11k_base *ab, int mac_id,
 int ath11k_dp_rx_mon_status_bufs_replenish(struct ath11k_base *ab, int mac_id,
 					   struct dp_rxdma_ring *rx_ring,
 					   int req_entries,
-					   enum hal_rx_buf_return_buf_manager mgr,
-					   gfp_t gfp);
+					   enum hal_rx_buf_return_buf_manager mgr);
 int ath11k_dp_rx_pdev_mon_detach(struct ath11k *ar);
 int ath11k_dp_rx_pdev_mon_attach(struct ath11k *ar);
 int ath11k_peer_rx_frag_setup(struct ath11k *ar, const u8 *peer_mac, int vdev_id);
diff --git a/drivers/net/wireless/ath/ath11k/dp_tx.c b/drivers/net/wireless/ath/ath11k/dp_tx.c
index 5933800ccd64..3d962eee4d61 100644
--- a/drivers/net/wireless/ath/ath11k/dp_tx.c
+++ b/drivers/net/wireless/ath/ath11k/dp_tx.c
@@ -6,6 +6,7 @@
 #include "core.h"
 #include "dp_tx.h"
 #include "debug.h"
+#include "debugfs_sta.h"
 #include "hw.h"
 #include "peer.h"
 
@@ -253,6 +254,8 @@ tcl_ring_sel:
 
 	ath11k_hal_srng_access_end(ab, tcl_ring);
 
+	ath11k_dp_shadow_start_timer(ab, tcl_ring, &dp->tx_ring_timer[ti.ring_id]);
+
 	spin_unlock_bh(&tcl_ring->lock);
 
 	ath11k_dbg_dump(ab, ATH11K_DBG_DP_TX, NULL, "dp tx msdu: ",
@@ -457,7 +460,7 @@ static void ath11k_dp_tx_complete_msdu(struct ath11k *ar,
 	    (info->flags & IEEE80211_TX_CTL_NO_ACK))
 		info->flags |= IEEE80211_TX_STAT_NOACK_TRANSMITTED;
 
-	if (ath11k_debug_is_extd_tx_stats_enabled(ar)) {
+	if (ath11k_debugfs_is_extd_tx_stats_enabled(ar)) {
 		if (ts->flags & HAL_TX_STATUS_FLAGS_FIRST_MSDU) {
 			if (ar->last_ppdu_id == 0) {
 				ar->last_ppdu_id = ts->ppdu_id;
@@ -465,12 +468,12 @@ static void ath11k_dp_tx_complete_msdu(struct ath11k *ar,
 				   ar->cached_ppdu_id == ar->last_ppdu_id) {
 				ar->cached_ppdu_id = ar->last_ppdu_id;
 				ar->cached_stats.is_ampdu = true;
-				ath11k_update_per_peer_stats_from_txcompl(ar, msdu, ts);
+				ath11k_debugfs_sta_update_txcompl(ar, msdu, ts);
 				memset(&ar->cached_stats, 0,
 				       sizeof(struct ath11k_per_peer_tx_stats));
 			} else {
 				ar->cached_stats.is_ampdu = false;
-				ath11k_update_per_peer_stats_from_txcompl(ar, msdu, ts);
+				ath11k_debugfs_sta_update_txcompl(ar, msdu, ts);
 				memset(&ar->cached_stats, 0,
 				       sizeof(struct ath11k_per_peer_tx_stats));
 			}
@@ -535,6 +538,8 @@ void ath11k_dp_tx_completion_handler(struct ath11k_base *ab, int ring_id)
 	u32 msdu_id;
 	u8 mac_id;
 
+	spin_lock_bh(&status_ring->lock);
+
 	ath11k_hal_srng_access_begin(ab, status_ring);
 
 	while ((ATH11K_TX_COMPL_NEXT(tx_ring->tx_status_head) !=
@@ -554,6 +559,8 @@ void ath11k_dp_tx_completion_handler(struct ath11k_base *ab, int ring_id)
 
 	ath11k_hal_srng_access_end(ab, status_ring);
 
+	spin_unlock_bh(&status_ring->lock);
+
 	while (ATH11K_TX_COMPL_NEXT(tx_ring->tx_status_tail) != tx_ring->tx_status_head) {
 		struct hal_wbm_release_ring *tx_status;
 		u32 desc_id;
@@ -785,9 +792,9 @@ int ath11k_dp_tx_htt_srng_setup(struct ath11k_base *ab, u32 ring_id,
 	cmd->ring_tail_off32_remote_addr_hi = (u64)tp_addr >>
 					      HAL_ADDR_MSB_REG_SHIFT;
 
-	cmd->ring_msi_addr_lo = 0;
-	cmd->ring_msi_addr_hi = 0;
-	cmd->msi_data = 0;
+	cmd->ring_msi_addr_lo = params.msi_addr & 0xffffffff;
+	cmd->ring_msi_addr_hi = ((uint64_t)(params.msi_addr) >> 32) & 0xffffffff;
+	cmd->msi_data = params.msi_data;
 
 	cmd->intr_info = FIELD_PREP(
 			HTT_SRNG_SETUP_CMD_INTR_INFO_BATCH_COUNTER_THRESH,
@@ -803,6 +810,15 @@ int ath11k_dp_tx_htt_srng_setup(struct ath11k_base *ab, u32 ring_id,
 				params.low_threshold);
 	}
 
+	ath11k_dbg(ab, ATH11k_DBG_HAL,
+		   "%s msi_addr_lo:0x%x, msi_addr_hi:0x%x, msi_data:0x%x\n",
+		   __func__, cmd->ring_msi_addr_lo, cmd->ring_msi_addr_hi,
+		   cmd->msi_data);
+
+	ath11k_dbg(ab, ATH11k_DBG_HAL,
+		   "ring_id:%d, ring_type:%d, intr_info:0x%x, flags:0x%x\n",
+		   ring_id, ring_type, cmd->intr_info, cmd->info2);
+
 	ret = ath11k_htc_send(&ab->htc, ab->dp.eid, skb);
 	if (ret)
 		goto err_free;
@@ -867,24 +883,27 @@ int ath11k_dp_tx_htt_h2t_ppdu_stats_req(struct ath11k *ar, u32 mask)
 	int len = sizeof(*cmd);
 	u8 pdev_mask;
 	int ret;
+	int i;
 
-	skb = ath11k_htc_alloc_skb(ab, len);
-	if (!skb)
-		return -ENOMEM;
-
-	skb_put(skb, len);
-	cmd = (struct htt_ppdu_stats_cfg_cmd *)skb->data;
-	cmd->msg = FIELD_PREP(HTT_PPDU_STATS_CFG_MSG_TYPE,
-			      HTT_H2T_MSG_TYPE_PPDU_STATS_CFG);
-
-	pdev_mask = 1 << (ar->pdev_idx);
-	cmd->msg |= FIELD_PREP(HTT_PPDU_STATS_CFG_PDEV_ID, pdev_mask);
-	cmd->msg |= FIELD_PREP(HTT_PPDU_STATS_CFG_TLV_TYPE_BITMASK, mask);
-
-	ret = ath11k_htc_send(&ab->htc, dp->eid, skb);
-	if (ret) {
-		dev_kfree_skb_any(skb);
-		return ret;
+	for (i = 0; i < ab->hw_params.num_rxmda_per_pdev; i++) {
+		skb = ath11k_htc_alloc_skb(ab, len);
+		if (!skb)
+			return -ENOMEM;
+
+		skb_put(skb, len);
+		cmd = (struct htt_ppdu_stats_cfg_cmd *)skb->data;
+		cmd->msg = FIELD_PREP(HTT_PPDU_STATS_CFG_MSG_TYPE,
+				      HTT_H2T_MSG_TYPE_PPDU_STATS_CFG);
+
+		pdev_mask = 1 << (i + 1);
+		cmd->msg |= FIELD_PREP(HTT_PPDU_STATS_CFG_PDEV_ID, pdev_mask);
+		cmd->msg |= FIELD_PREP(HTT_PPDU_STATS_CFG_TLV_TYPE_BITMASK, mask);
+
+		ret = ath11k_htc_send(&ab->htc, dp->eid, skb);
+		if (ret) {
+			dev_kfree_skb_any(skb);
+			return ret;
+		}
 	}
 
 	return 0;
@@ -1027,10 +1046,23 @@ int ath11k_dp_tx_htt_monitor_mode_ring_config(struct ath11k *ar, bool reset)
 					HTT_RX_MON_MO_DATA_FILTER_FLASG3;
 	}
 
-	ret = ath11k_dp_tx_htt_rx_filter_setup(ar->ab, ring_id, dp->mac_id,
-					       HAL_RXDMA_MONITOR_BUF,
-					       DP_RXDMA_REFILL_RING_SIZE,
-					       &tlv_filter);
+	if (ab->hw_params.rxdma1_enable) {
+		ret = ath11k_dp_tx_htt_rx_filter_setup(ar->ab, ring_id, dp->mac_id,
+						       HAL_RXDMA_MONITOR_BUF,
+						       DP_RXDMA_REFILL_RING_SIZE,
+						       &tlv_filter);
+	} else if (!reset) {
+		/* set in monitor mode only */
+		for (i = 0; i < ab->hw_params.num_rxmda_per_pdev; i++) {
+			ring_id = dp->rx_mac_buf_ring[i].ring_id;
+			ret = ath11k_dp_tx_htt_rx_filter_setup(ar->ab, ring_id,
+							       dp->mac_id + i,
+							       HAL_RXDMA_BUF,
+							       1024,
+							       &tlv_filter);
+		}
+	}
+
 	if (ret)
 		return ret;
 
@@ -1049,5 +1081,9 @@ int ath11k_dp_tx_htt_monitor_mode_ring_config(struct ath11k *ar, bool reset)
 						       &tlv_filter);
 	}
 
+	if (!ar->ab->hw_params.rxdma1_enable)
+		mod_timer(&ar->ab->mon_reap_timer, jiffies +
+			  msecs_to_jiffies(ATH11K_MON_TIMER_INTERVAL));
+
 	return ret;
 }
diff --git a/drivers/net/wireless/ath/ath11k/hal.c b/drivers/net/wireless/ath/ath11k/hal.c
index 5cd948f55b95..9904c0eb7587 100644
--- a/drivers/net/wireless/ath/ath11k/hal.c
+++ b/drivers/net/wireless/ath/ath11k/hal.c
@@ -330,7 +330,7 @@ static void ath11k_hal_srng_dst_hw_init(struct ath11k_base *ab,
 	if (srng->flags & HAL_SRNG_FLAGS_MSI_INTR) {
 		ath11k_hif_write32(ab, reg_base +
 				   HAL_REO1_RING_MSI1_BASE_LSB_OFFSET(ab),
-				   (u32)srng->msi_addr);
+				   srng->msi_addr);
 
 		val = FIELD_PREP(HAL_REO1_RING_MSI1_BASE_MSB_ADDR,
 				 ((u64)srng->msi_addr >>
@@ -344,7 +344,7 @@ static void ath11k_hal_srng_dst_hw_init(struct ath11k_base *ab,
 				   srng->msi_data);
 	}
 
-	ath11k_hif_write32(ab, reg_base, (u32)srng->ring_base_paddr);
+	ath11k_hif_write32(ab, reg_base, srng->ring_base_paddr);
 
 	val = FIELD_PREP(HAL_REO1_RING_BASE_MSB_RING_BASE_ADDR_MSB,
 			 ((u64)srng->ring_base_paddr >>
@@ -409,7 +409,7 @@ static void ath11k_hal_srng_src_hw_init(struct ath11k_base *ab,
 	if (srng->flags & HAL_SRNG_FLAGS_MSI_INTR) {
 		ath11k_hif_write32(ab, reg_base +
 				   HAL_TCL1_RING_MSI1_BASE_LSB_OFFSET(ab),
-				   (u32)srng->msi_addr);
+				   srng->msi_addr);
 
 		val = FIELD_PREP(HAL_TCL1_RING_MSI1_BASE_MSB_ADDR,
 				 ((u64)srng->msi_addr >>
@@ -424,7 +424,7 @@ static void ath11k_hal_srng_src_hw_init(struct ath11k_base *ab,
 				   srng->msi_data);
 	}
 
-	ath11k_hif_write32(ab, reg_base, (u32)srng->ring_base_paddr);
+	ath11k_hif_write32(ab, reg_base, srng->ring_base_paddr);
 
 	val = FIELD_PREP(HAL_TCL1_RING_BASE_MSB_RING_BASE_ADDR_MSB,
 			 ((u64)srng->ring_base_paddr >>
@@ -560,6 +560,8 @@ void ath11k_hal_srng_get_params(struct ath11k_base *ab, struct hal_srng *srng,
 	params->intr_batch_cntr_thres_entries =
 		srng->intr_batch_cntr_thres_entries;
 	params->low_threshold = srng->u.src_ring.low_threshold;
+	params->msi_addr = srng->msi_addr;
+	params->msi_data = srng->msi_data;
 	params->flags = srng->flags;
 }
 
@@ -1018,8 +1020,16 @@ int ath11k_hal_srng_setup(struct ath11k_base *ab, enum hal_ring_type type,
 						   lmac_idx);
 			srng->flags |= HAL_SRNG_FLAGS_LMAC_RING;
 		} else {
-			srng->u.src_ring.hp_addr =
+			if (!ab->hw_params.supports_shadow_regs)
+				srng->u.src_ring.hp_addr =
 				(u32 *)((unsigned long)ab->mem + reg_base);
+			else
+				ath11k_dbg(ab, ATH11k_DBG_HAL,
+					   "hal type %d ring_num %d reg_base 0x%x shadow 0x%lx\n",
+					   type, ring_num,
+					   reg_base,
+					   (unsigned long)srng->u.src_ring.hp_addr -
+					   (unsigned long)ab->mem);
 		}
 	} else {
 		/* During initialization loop count in all the descriptors
@@ -1043,9 +1053,18 @@ int ath11k_hal_srng_setup(struct ath11k_base *ab, enum hal_ring_type type,
 						   lmac_idx);
 			srng->flags |= HAL_SRNG_FLAGS_LMAC_RING;
 		} else {
-			srng->u.dst_ring.tp_addr =
+			if (!ab->hw_params.supports_shadow_regs)
+				srng->u.dst_ring.tp_addr =
 				(u32 *)((unsigned long)ab->mem + reg_base +
 					(HAL_REO1_RING_TP(ab) - HAL_REO1_RING_HP(ab)));
+			else
+				ath11k_dbg(ab, ATH11k_DBG_HAL,
+					   "type %d ring_num %d target_reg 0x%x shadow 0x%lx\n",
+					   type, ring_num,
+					   reg_base + (HAL_REO1_RING_TP(ab) -
+						       HAL_REO1_RING_HP(ab)),
+					   (unsigned long)srng->u.dst_ring.tp_addr -
+					   (unsigned long)ab->mem);
 		}
 	}
 
@@ -1062,6 +1081,112 @@ int ath11k_hal_srng_setup(struct ath11k_base *ab, enum hal_ring_type type,
 	return ring_id;
 }
 
+static void ath11k_hal_srng_update_hp_tp_addr(struct ath11k_base *ab,
+					      int shadow_cfg_idx,
+					  enum hal_ring_type ring_type,
+					  int ring_num)
+{
+	struct hal_srng *srng;
+	struct ath11k_hal *hal = &ab->hal;
+	int ring_id;
+	struct hal_srng_config *srng_config = &hal->srng_config[ring_type];
+
+	ring_id = ath11k_hal_srng_get_ring_id(ab, ring_type, ring_num, 0);
+	if (ring_id < 0)
+		return;
+
+	srng = &hal->srng_list[ring_id];
+
+	if (srng_config->ring_dir == HAL_SRNG_DIR_DST)
+		srng->u.dst_ring.tp_addr = (u32 *)(HAL_SHADOW_REG(shadow_cfg_idx) +
+						   (unsigned long)ab->mem);
+	else
+		srng->u.src_ring.hp_addr = (u32 *)(HAL_SHADOW_REG(shadow_cfg_idx) +
+						   (unsigned long)ab->mem);
+}
+
+int ath11k_hal_srng_update_shadow_config(struct ath11k_base *ab,
+					 enum hal_ring_type ring_type,
+					 int ring_num)
+{
+	struct ath11k_hal *hal = &ab->hal;
+	struct hal_srng_config *srng_config = &hal->srng_config[ring_type];
+	int shadow_cfg_idx = hal->num_shadow_reg_configured;
+	u32 target_reg;
+
+	if (shadow_cfg_idx >= HAL_SHADOW_NUM_REGS)
+		return -EINVAL;
+
+	hal->num_shadow_reg_configured++;
+
+	target_reg = srng_config->reg_start[HAL_HP_OFFSET_IN_REG_START];
+	target_reg += srng_config->reg_size[HAL_HP_OFFSET_IN_REG_START] *
+		ring_num;
+
+	/* For destination ring, shadow the TP */
+	if (srng_config->ring_dir == HAL_SRNG_DIR_DST)
+		target_reg += HAL_OFFSET_FROM_HP_TO_TP;
+
+	hal->shadow_reg_addr[shadow_cfg_idx] = target_reg;
+
+	/* update hp/tp addr to hal structure*/
+	ath11k_hal_srng_update_hp_tp_addr(ab, shadow_cfg_idx, ring_type,
+					  ring_num);
+
+	ath11k_dbg(ab, ATH11k_DBG_HAL,
+		   "target_reg %x, shadow reg 0x%x shadow_idx 0x%x, ring_type %d, ring num %d",
+		  target_reg,
+		  HAL_SHADOW_REG(shadow_cfg_idx),
+		  shadow_cfg_idx,
+		  ring_type, ring_num);
+
+	return 0;
+}
+
+void ath11k_hal_srng_shadow_config(struct ath11k_base *ab)
+{
+	struct ath11k_hal *hal = &ab->hal;
+	int ring_type, ring_num;
+
+	/* update all the non-CE srngs. */
+	for (ring_type = 0; ring_type < HAL_MAX_RING_TYPES; ring_type++) {
+		struct hal_srng_config *srng_config = &hal->srng_config[ring_type];
+
+		if (ring_type == HAL_CE_SRC ||
+		    ring_type == HAL_CE_DST ||
+			ring_type == HAL_CE_DST_STATUS)
+			continue;
+
+		if (srng_config->lmac_ring)
+			continue;
+
+		for (ring_num = 0; ring_num < srng_config->max_rings; ring_num++)
+			ath11k_hal_srng_update_shadow_config(ab, ring_type, ring_num);
+	}
+}
+
+void ath11k_hal_srng_get_shadow_config(struct ath11k_base *ab,
+				       u32 **cfg, u32 *len)
+{
+	struct ath11k_hal *hal = &ab->hal;
+
+	*len = hal->num_shadow_reg_configured;
+	*cfg = hal->shadow_reg_addr;
+}
+
+void ath11k_hal_srng_shadow_update_hp_tp(struct ath11k_base *ab,
+					 struct hal_srng *srng)
+{
+	lockdep_assert_held(&srng->lock);
+
+	/* check whether the ring is emptry. Update the shadow
+	 * HP only when then ring isn't' empty.
+	 */
+	if (srng->ring_dir == HAL_SRNG_DIR_SRC &&
+	    *srng->u.src_ring.tp_addr != srng->u.src_ring.hp)
+		ath11k_hal_srng_access_end(ab, srng);
+}
+
 static int ath11k_hal_srng_create_config(struct ath11k_base *ab)
 {
 	struct ath11k_hal *hal = &ab->hal;
diff --git a/drivers/net/wireless/ath/ath11k/hal.h b/drivers/net/wireless/ath/ath11k/hal.h
index 85192d170b6b..1f1b29cd0aa3 100644
--- a/drivers/net/wireless/ath/ath11k/hal.h
+++ b/drivers/net/wireless/ath/ath11k/hal.h
@@ -31,8 +31,12 @@ struct ath11k_base;
 #define HAL_DSCP_TID_TBL_SIZE			24
 
 /* calculate the register address from bar0 of shadow register x */
-#define SHADOW_BASE_ADDRESS			0x00003024
-#define SHADOW_NUM_REGISTERS				36
+#define HAL_SHADOW_BASE_ADDR			0x000008fc
+#define HAL_SHADOW_NUM_REGS			36
+#define HAL_HP_OFFSET_IN_REG_START		1
+#define HAL_OFFSET_FROM_HP_TO_TP		4
+
+#define HAL_SHADOW_REG(x) (HAL_SHADOW_BASE_ADDR + (4 * (x)))
 
 /* WCSS Relative address */
 #define HAL_SEQ_WCSS_UMAC_REO_REG		0x00a38000
@@ -882,7 +886,7 @@ struct ath11k_hal {
 	u8 current_blk_index;
 
 	/* shadow register configuration */
-	u32 shadow_reg_addr[SHADOW_NUM_REGISTERS];
+	u32 shadow_reg_addr[HAL_SHADOW_NUM_REGS];
 	int num_shadow_reg_configured;
 };
 
@@ -935,5 +939,12 @@ int ath11k_hal_srng_setup(struct ath11k_base *ab, enum hal_ring_type type,
 int ath11k_hal_srng_init(struct ath11k_base *ath11k);
 void ath11k_hal_srng_deinit(struct ath11k_base *ath11k);
 void ath11k_hal_dump_srng_stats(struct ath11k_base *ab);
-
+void ath11k_hal_srng_get_shadow_config(struct ath11k_base *ab,
+				       u32 **cfg, u32 *len);
+int ath11k_hal_srng_update_shadow_config(struct ath11k_base *ab,
+					 enum hal_ring_type ring_type,
+					int ring_num);
+void ath11k_hal_srng_shadow_config(struct ath11k_base *ab);
+void ath11k_hal_srng_shadow_update_hp_tp(struct ath11k_base *ab,
+					 struct hal_srng *srng);
 #endif
diff --git a/drivers/net/wireless/ath/ath11k/hal_rx.c b/drivers/net/wireless/ath/ath11k/hal_rx.c
index 4bbad2e341ee..fac2396edf32 100644
--- a/drivers/net/wireless/ath/ath11k/hal_rx.c
+++ b/drivers/net/wireless/ath/ath11k/hal_rx.c
@@ -256,6 +256,8 @@ int ath11k_hal_reo_cmd_send(struct ath11k_base *ab, struct hal_srng *srng,
 		break;
 	}
 
+	ath11k_dp_shadow_start_timer(ab, srng, &ab->dp.reo_cmd_timer);
+
 out:
 	ath11k_hal_srng_access_end(ab, srng);
 	spin_unlock_bh(&srng->lock);
@@ -1195,7 +1197,7 @@ ath11k_hal_rx_parse_mon_status(struct ath11k_base *ab,
 
 void ath11k_hal_rx_reo_ent_buf_paddr_get(void *rx_desc, dma_addr_t *paddr,
 					 u32 *sw_cookie, void **pp_buf_addr,
-					 u32  *msdu_cnt)
+					 u8 *rbm, u32 *msdu_cnt)
 {
 	struct hal_reo_entrance_ring *reo_ent_ring =
 		(struct hal_reo_entrance_ring *)rx_desc;
@@ -1217,6 +1219,8 @@ void ath11k_hal_rx_reo_ent_buf_paddr_get(void *rx_desc, dma_addr_t *paddr,
 
 	*sw_cookie = FIELD_GET(BUFFER_ADDR_INFO1_SW_COOKIE,
 			       buf_addr_info->info1);
+	*rbm = FIELD_GET(BUFFER_ADDR_INFO1_RET_BUF_MGR,
+			 buf_addr_info->info1);
 
 	*pp_buf_addr = (void *)buf_addr_info;
 }
diff --git a/drivers/net/wireless/ath/ath11k/hal_rx.h b/drivers/net/wireless/ath/ath11k/hal_rx.h
index c436191ae1e8..d464a270c049 100644
--- a/drivers/net/wireless/ath/ath11k/hal_rx.h
+++ b/drivers/net/wireless/ath/ath11k/hal_rx.h
@@ -321,7 +321,7 @@ void ath11k_hal_rx_reo_ent_paddr_get(struct ath11k_base *ab, void *desc,
 				     dma_addr_t *paddr, u32 *desc_bank);
 void ath11k_hal_rx_reo_ent_buf_paddr_get(void *rx_desc,
 					 dma_addr_t *paddr, u32 *sw_cookie,
-					 void **pp_buf_addr_info,
+					 void **pp_buf_addr_info, u8 *rbm,
 					 u32 *msdu_cnt);
 enum hal_rx_mon_status
 ath11k_hal_rx_parse_mon_status(struct ath11k_base *ab,
diff --git a/drivers/net/wireless/ath/ath11k/htc.c b/drivers/net/wireless/ath/ath11k/htc.c
index e9e354fc11fa..6b57dc273e0b 100644
--- a/drivers/net/wireless/ath/ath11k/htc.c
+++ b/drivers/net/wireless/ath/ath11k/htc.c
@@ -50,15 +50,6 @@ static struct sk_buff *ath11k_htc_build_tx_ctrl_skb(void *ab)
 	return skb;
 }
 
-static inline void ath11k_htc_restore_tx_skb(struct ath11k_htc *htc,
-					     struct sk_buff *skb)
-{
-	struct ath11k_skb_cb *skb_cb = ATH11K_SKB_CB(skb);
-
-	dma_unmap_single(htc->ab->dev, skb_cb->paddr, skb->len, DMA_TO_DEVICE);
-	skb_pull(skb, sizeof(struct ath11k_htc_hdr));
-}
-
 static void ath11k_htc_prepare_tx_skb(struct ath11k_htc_ep *ep,
 				      struct sk_buff *skb)
 {
@@ -524,6 +515,12 @@ int ath11k_htc_wait_target(struct ath11k_htc *htc)
 		return -ECOMM;
 	}
 
+	/* For QCA6390, wmi endpoint uses 1 credit to avoid
+	 * back-to-back write.
+	 */
+	if (ab->hw_params.supports_shadow_regs)
+		htc->total_transmit_credits = 1;
+
 	ath11k_htc_setup_target_buffer_assignments(htc);
 
 	return 0;
diff --git a/drivers/net/wireless/ath/ath11k/hw.c b/drivers/net/wireless/ath/ath11k/hw.c
index 5f2eb2032118..11a411b76fe4 100644
--- a/drivers/net/wireless/ath/ath11k/hw.c
+++ b/drivers/net/wireless/ath/ath11k/hw.c
@@ -74,7 +74,6 @@ static void ath11k_init_wmi_config_qca6390(struct ath11k_base *ab,
 	config->beacon_tx_offload_max_vdev = 0x2;
 	config->num_multicast_filter_entries = 0x20;
 	config->num_wow_filters = 0x16;
-	config->num_keep_alive_pattern = 0x1;
 	config->num_keep_alive_pattern = 0;
 }
 
@@ -104,7 +103,12 @@ static void ath11k_init_wmi_config_ipq8074(struct ath11k_base *ab,
 	config->rx_timeout_pri[1] = TARGET_RX_TIMEOUT_LO_PRI;
 	config->rx_timeout_pri[2] = TARGET_RX_TIMEOUT_LO_PRI;
 	config->rx_timeout_pri[3] = TARGET_RX_TIMEOUT_HI_PRI;
-	config->rx_decap_mode = TARGET_DECAP_MODE_NATIVE_WIFI;
+
+	if (test_bit(ATH11K_FLAG_RAW_MODE, &ab->dev_flags))
+		config->rx_decap_mode = TARGET_DECAP_MODE_RAW;
+	else
+		config->rx_decap_mode = TARGET_DECAP_MODE_NATIVE_WIFI;
+
 	config->scan_max_pending_req = TARGET_SCAN_MAX_PENDING_REQS;
 	config->bmiss_offload_max_vdev = TARGET_BMISS_OFFLOAD_MAX_VDEV;
 	config->roam_offload_max_vdev = TARGET_ROAM_OFFLOAD_MAX_VDEV;
diff --git a/drivers/net/wireless/ath/ath11k/hw.h b/drivers/net/wireless/ath/ath11k/hw.h
index 57960a7c09a4..1dda4257e6d7 100644
--- a/drivers/net/wireless/ath/ath11k/hw.h
+++ b/drivers/net/wireless/ath/ath11k/hw.h
@@ -155,6 +155,12 @@ struct ath11k_hw_params {
 	bool vdev_start_delay;
 	bool htt_peer_map_v2;
 	bool tcl_0_only;
+	u8 spectral_fft_sz;
+
+	u16 interface_modes;
+	bool supports_monitor;
+	bool supports_shadow_regs;
+	bool idle_ps;
 };
 
 struct ath11k_hw_ops {
diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c
index 7d7b4d80c47f..3f63a7bd6b59 100644
--- a/drivers/net/wireless/ath/ath11k/mac.c
+++ b/drivers/net/wireless/ath/ath11k/mac.c
@@ -14,6 +14,7 @@
 #include "dp_rx.h"
 #include "testmode.h"
 #include "peer.h"
+#include "debugfs_sta.h"
 
 #define CHAN2G(_channel, _freq, _flags) { \
 	.band                   = NL80211_BAND_2GHZ, \
@@ -757,21 +758,12 @@ static int ath11k_monitor_vdev_up(struct ath11k *ar, int vdev_id)
 
 static int ath11k_mac_op_config(struct ieee80211_hw *hw, u32 changed)
 {
-	struct ath11k *ar = hw->priv;
-	int ret = 0;
-
 	/* mac80211 requires this op to be present and that's why
 	 * there's an empty function, this can be extended when
 	 * required.
 	 */
 
-	mutex_lock(&ar->conf_mutex);
-
-	/* TODO: Handle configuration changes as appropriate */
-
-	mutex_unlock(&ar->conf_mutex);
-
-	return ret;
+	return 0;
 }
 
 static int ath11k_mac_setup_bcn_tmpl(struct ath11k_vif *arvif)
@@ -2967,7 +2959,7 @@ static int ath11k_mac_station_add(struct ath11k *ar,
 	ath11k_dbg(ab, ATH11K_DBG_MAC, "Added peer: %pM for VDEV: %d\n",
 		   sta->addr, arvif->vdev_id);
 
-	if (ath11k_debug_is_extd_tx_stats_enabled(ar)) {
+	if (ath11k_debugfs_is_extd_tx_stats_enabled(ar)) {
 		arsta->tx_stats = kzalloc(sizeof(*arsta->tx_stats), GFP_KERNEL);
 		if (!arsta->tx_stats) {
 			ret = -ENOMEM;
@@ -2993,7 +2985,8 @@ static int ath11k_mac_station_add(struct ath11k *ar,
 		goto free_tx_stats;
 	}
 
-	if (ab->hw_params.vdev_start_delay) {
+	if (ab->hw_params.vdev_start_delay &&
+	    arvif->vdev_type != WMI_VDEV_TYPE_AP) {
 		ret = ath11k_start_vdev_delay(ar->hw, vif);
 		if (ret) {
 			ath11k_warn(ab, "failed to delay vdev start: %d\n", ret);
@@ -4101,7 +4094,7 @@ static int ath11k_mac_config_mon_status_default(struct ath11k *ar, bool enable)
 
 	if (enable) {
 		tlv_filter = ath11k_mac_mon_status_filter_default;
-		tlv_filter.rx_filter = ath11k_debug_rx_filter(ar);
+		tlv_filter.rx_filter = ath11k_debugfs_rx_filter(ar);
 	}
 
 	for (i = 0; i < ab->hw_params.num_rxmda_per_pdev; i++) {
@@ -4215,6 +4208,15 @@ static int ath11k_mac_op_start(struct ieee80211_hw *hw)
 	rcu_assign_pointer(ab->pdevs_active[ar->pdev_idx],
 			   &ab->pdevs[ar->pdev_idx]);
 
+	/* allow device to enter IMPS */
+	if (ab->hw_params.idle_ps) {
+		ret = ath11k_wmi_pdev_set_param(ar, WMI_PDEV_PARAM_IDLE_PS_CONFIG,
+						1, pdev->pdev_id);
+		if (ret) {
+			ath11k_err(ab, "failed to enable idle ps: %d\n", ret);
+			goto err;
+		}
+	}
 	return 0;
 
 err:
@@ -4350,7 +4352,7 @@ static int ath11k_set_he_mu_sounding_mode(struct ath11k *ar,
 }
 
 static void ath11k_mac_op_update_vif_offload(struct ieee80211_hw *hw,
-					    struct ieee80211_vif *vif)
+					     struct ieee80211_vif *vif)
 {
 	struct ath11k *ar = hw->priv;
 	struct ath11k_base *ab = ar->ab;
@@ -4701,6 +4703,10 @@ static void ath11k_mac_op_configure_filter(struct ieee80211_hw *hw,
 		ath11k_warn(ar->ab,
 			    "fail to set monitor filter: %d\n", ret);
 	}
+	ath11k_dbg(ar->ab, ATH11K_DBG_MAC,
+		   "changed_flags:0x%x, total_flags:0x%x, reset_flag:%d\n",
+		   changed_flags, *total_flags, reset_flag);
+
 	mutex_unlock(&ar->conf_mutex);
 }
 
@@ -5206,6 +5212,7 @@ ath11k_mac_op_assign_vif_chanctx(struct ieee80211_hw *hw,
 	struct ath11k_base *ab = ar->ab;
 	struct ath11k_vif *arvif = (void *)vif->drv_priv;
 	int ret;
+	struct peer_create_params param;
 
 	mutex_lock(&ar->conf_mutex);
 
@@ -5214,7 +5221,9 @@ ath11k_mac_op_assign_vif_chanctx(struct ieee80211_hw *hw,
 		   ctx, arvif->vdev_id);
 
 	/* for QCA6390 bss peer must be created before vdev_start */
-	if (ab->hw_params.vdev_start_delay) {
+	if (ab->hw_params.vdev_start_delay &&
+	    arvif->vdev_type != WMI_VDEV_TYPE_AP &&
+	    arvif->vdev_type != WMI_VDEV_TYPE_MONITOR) {
 		memcpy(&arvif->chanctx, ctx, sizeof(*ctx));
 		mutex_unlock(&ar->conf_mutex);
 		return 0;
@@ -5225,6 +5234,13 @@ ath11k_mac_op_assign_vif_chanctx(struct ieee80211_hw *hw,
 		return -EBUSY;
 	}
 
+	if (ab->hw_params.vdev_start_delay) {
+		param.vdev_id = arvif->vdev_id;
+		param.peer_type = WMI_PEER_TYPE_DEFAULT;
+		param.peer_addr = ar->mac_addr;
+		ret = ath11k_peer_create(ar, arvif, NULL, &param);
+	}
+
 	ret = ath11k_mac_vdev_start(arvif, &ctx->def);
 	if (ret) {
 		ath11k_warn(ab, "failed to start vdev %i addr %pM on freq %d: %d\n",
@@ -5270,6 +5286,11 @@ ath11k_mac_op_unassign_vif_chanctx(struct ieee80211_hw *hw,
 
 	WARN_ON(!arvif->is_started);
 
+	if (ab->hw_params.vdev_start_delay &&
+	    arvif->vdev_type == WMI_VDEV_TYPE_MONITOR &&
+	    ath11k_peer_find_by_addr(ab, ar->mac_addr))
+		ath11k_peer_delete(ar, arvif->vdev_id, ar->mac_addr);
+
 	ret = ath11k_mac_vdev_stop(arvif);
 	if (ret)
 		ath11k_warn(ab, "failed to stop vdev %i: %d\n",
@@ -5277,6 +5298,10 @@ ath11k_mac_op_unassign_vif_chanctx(struct ieee80211_hw *hw,
 
 	arvif->is_started = false;
 
+	if (ab->hw_params.vdev_start_delay &&
+	    arvif->vdev_type == WMI_VDEV_TYPE_MONITOR)
+		ath11k_wmi_vdev_down(ar, arvif->vdev_id);
+
 	mutex_unlock(&ar->conf_mutex);
 }
 
@@ -5873,37 +5898,8 @@ static const struct ieee80211_ops ath11k_ops = {
 	.sta_statistics			= ath11k_mac_op_sta_statistics,
 	CFG80211_TESTMODE_CMD(ath11k_tm_cmd)
 #ifdef CONFIG_ATH11K_DEBUGFS
-	.sta_add_debugfs		= ath11k_sta_add_debugfs,
-#endif
-};
-
-static const struct ieee80211_iface_limit ath11k_if_limits[] = {
-	{
-		.max = 1,
-		.types = BIT(NL80211_IFTYPE_STATION),
-	},
-	{
-		.max    = 16,
-		.types  = BIT(NL80211_IFTYPE_AP)
-#ifdef CONFIG_MAC80211_MESH
-			| BIT(NL80211_IFTYPE_MESH_POINT)
+	.sta_add_debugfs		= ath11k_debugfs_sta_op_add,
 #endif
-	},
-};
-
-static const struct ieee80211_iface_combination ath11k_if_comb[] = {
-	{
-		.limits = ath11k_if_limits,
-		.n_limits = ARRAY_SIZE(ath11k_if_limits),
-		.max_interfaces = 16,
-		.num_different_channels = 1,
-		.beacon_int_infra_match = true,
-		.beacon_int_min_gcd = 100,
-		.radar_detect_widths =	BIT(NL80211_CHAN_WIDTH_20_NOHT) |
-					BIT(NL80211_CHAN_WIDTH_20) |
-					BIT(NL80211_CHAN_WIDTH_40) |
-					BIT(NL80211_CHAN_WIDTH_80),
-	},
 };
 
 static void ath11k_mac_update_ch_list(struct ath11k *ar,
@@ -6031,6 +6027,50 @@ static int ath11k_mac_setup_channels_rates(struct ath11k *ar,
 	return 0;
 }
 
+static int ath11k_mac_setup_iface_combinations(struct ath11k *ar)
+{
+	struct ath11k_base *ab = ar->ab;
+	struct ieee80211_iface_combination *combinations;
+	struct ieee80211_iface_limit *limits;
+	int n_limits;
+
+	combinations = kzalloc(sizeof(*combinations), GFP_KERNEL);
+	if (!combinations)
+		return -ENOMEM;
+
+	n_limits = 2;
+
+	limits = kcalloc(n_limits, sizeof(*limits), GFP_KERNEL);
+	if (!limits)
+		return -ENOMEM;
+
+	limits[0].max = 1;
+	limits[0].types |= BIT(NL80211_IFTYPE_STATION);
+
+	limits[1].max = 16;
+	limits[1].types |= BIT(NL80211_IFTYPE_AP);
+
+	if (IS_ENABLED(CONFIG_MAC80211_MESH) &&
+	    ab->hw_params.interface_modes & BIT(NL80211_IFTYPE_MESH_POINT))
+		limits[1].types |= BIT(NL80211_IFTYPE_MESH_POINT);
+
+	combinations[0].limits = limits;
+	combinations[0].n_limits = n_limits;
+	combinations[0].max_interfaces = 16;
+	combinations[0].num_different_channels = 1;
+	combinations[0].beacon_int_infra_match = true;
+	combinations[0].beacon_int_min_gcd = 100;
+	combinations[0].radar_detect_widths = BIT(NL80211_CHAN_WIDTH_20_NOHT) |
+						BIT(NL80211_CHAN_WIDTH_20) |
+						BIT(NL80211_CHAN_WIDTH_40) |
+						BIT(NL80211_CHAN_WIDTH_80);
+
+	ar->hw->wiphy->iface_combinations = combinations;
+	ar->hw->wiphy->n_iface_combinations = 1;
+
+	return 0;
+}
+
 static const u8 ath11k_if_types_ext_capa[] = {
 	[0] = WLAN_EXT_CAPA1_EXT_CHANNEL_SWITCHING,
 	[7] = WLAN_EXT_CAPA8_OPMODE_NOTIF,
@@ -6081,6 +6121,9 @@ static void __ath11k_mac_unregister(struct ath11k *ar)
 	kfree(ar->mac.sbands[NL80211_BAND_5GHZ].channels);
 	kfree(ar->mac.sbands[NL80211_BAND_6GHZ].channels);
 
+	kfree(ar->hw->wiphy->iface_combinations[0].limits);
+	kfree(ar->hw->wiphy->iface_combinations);
+
 	SET_IEEE80211_DEV(ar->hw, NULL);
 }
 
@@ -6132,12 +6175,16 @@ static int __ath11k_mac_register(struct ath11k *ar)
 	ath11k_mac_setup_ht_vht_cap(ar, cap, &ht_cap);
 	ath11k_mac_setup_he_cap(ar, cap);
 
+	ret = ath11k_mac_setup_iface_combinations(ar);
+	if (ret) {
+		ath11k_err(ar->ab, "failed to setup interface combinations: %d\n", ret);
+		goto err_free_channels;
+	}
+
 	ar->hw->wiphy->available_antennas_rx = cap->rx_chain_mask;
 	ar->hw->wiphy->available_antennas_tx = cap->tx_chain_mask;
 
-	ar->hw->wiphy->interface_modes = BIT(NL80211_IFTYPE_STATION) |
-					 BIT(NL80211_IFTYPE_AP) |
-					 BIT(NL80211_IFTYPE_MESH_POINT);
+	ar->hw->wiphy->interface_modes = ab->hw_params.interface_modes;
 
 	ieee80211_hw_set(ar->hw, SIGNAL_DBM);
 	ieee80211_hw_set(ar->hw, SUPPORTS_PS);
@@ -6199,9 +6246,6 @@ static int __ath11k_mac_register(struct ath11k *ar)
 	ar->hw->vif_data_size = sizeof(struct ath11k_vif);
 	ar->hw->sta_data_size = sizeof(struct ath11k_sta);
 
-	ar->hw->wiphy->iface_combinations = ath11k_if_comb;
-	ar->hw->wiphy->n_iface_combinations = ARRAY_SIZE(ath11k_if_comb);
-
 	wiphy_ext_feature_set(ar->hw->wiphy, NL80211_EXT_FEATURE_CQM_RSSI_LIST);
 	wiphy_ext_feature_set(ar->hw->wiphy, NL80211_EXT_FEATURE_STA_TX_PWR);
 
@@ -6223,25 +6267,37 @@ static int __ath11k_mac_register(struct ath11k *ar)
 	ret = ieee80211_register_hw(ar->hw);
 	if (ret) {
 		ath11k_err(ar->ab, "ieee80211 registration failed: %d\n", ret);
-		goto err_free;
+		goto err_free_if_combs;
 	}
 
+	if (!ab->hw_params.supports_monitor)
+		/* There's a race between calling ieee80211_register_hw()
+		 * and here where the monitor mode is enabled for a little
+		 * while. But that time is so short and in practise it make
+		 * a difference in real life.
+		 */
+		ar->hw->wiphy->interface_modes &= ~BIT(NL80211_IFTYPE_MONITOR);
+
 	/* Apply the regd received during initialization */
 	ret = ath11k_regd_update(ar, true);
 	if (ret) {
 		ath11k_err(ar->ab, "ath11k regd update failed: %d\n", ret);
-		goto err_free;
+		goto err_free_if_combs;
 	}
 
-	ret = ath11k_debug_register(ar);
+	ret = ath11k_debugfs_register(ar);
 	if (ret) {
 		ath11k_err(ar->ab, "debugfs registration failed: %d\n", ret);
-		goto err_free;
+		goto err_free_if_combs;
 	}
 
 	return 0;
 
-err_free:
+err_free_if_combs:
+	kfree(ar->hw->wiphy->iface_combinations[0].limits);
+	kfree(ar->hw->wiphy->iface_combinations);
+
+err_free_channels:
 	kfree(ar->mac.sbands[NL80211_BAND_2GHZ].channels);
 	kfree(ar->mac.sbands[NL80211_BAND_5GHZ].channels);
 	kfree(ar->mac.sbands[NL80211_BAND_6GHZ].channels);
diff --git a/drivers/net/wireless/ath/ath11k/pci.c b/drivers/net/wireless/ath/ath11k/pci.c
index aec0b593c6a7..d7eb6b7160bb 100644
--- a/drivers/net/wireless/ath/ath11k/pci.c
+++ b/drivers/net/wireless/ath/ath11k/pci.c
@@ -24,6 +24,16 @@
 #define WINDOW_START			0x80000
 #define WINDOW_RANGE_MASK		GENMASK(18, 0)
 
+#define TCSR_SOC_HW_VERSION		0x0224
+#define TCSR_SOC_HW_VERSION_MAJOR_MASK	GENMASK(16, 8)
+#define TCSR_SOC_HW_VERSION_MINOR_MASK	GENMASK(7, 0)
+
+/* BAR0 + 4k is always accessible, and no
+ * need to force wakeup.
+ * 4K - 32 = 0xFE0
+ */
+#define ACCESS_ALWAYS_OFF 0xFE0
+
 #define QCA6390_DEVICE_ID		0x1101
 
 static const struct pci_device_id ath11k_pci_id_table[] = {
@@ -124,6 +134,13 @@ void ath11k_pci_write32(struct ath11k_base *ab, u32 offset, u32 value)
 {
 	struct ath11k_pci *ab_pci = ath11k_pci_priv(ab);
 
+	/* for offset beyond BAR + 4K - 32, may
+	 * need to wakeup MHI to access.
+	 */
+	if (test_bit(ATH11K_PCI_FLAG_INIT_DONE, &ab_pci->flags) &&
+	    offset >= ACCESS_ALWAYS_OFF)
+		mhi_device_get_sync(ab_pci->mhi_ctrl->mhi_dev);
+
 	if (offset < WINDOW_START) {
 		iowrite32(value, ab->mem  + offset);
 	} else {
@@ -132,6 +149,10 @@ void ath11k_pci_write32(struct ath11k_base *ab, u32 offset, u32 value)
 		iowrite32(value, ab->mem + WINDOW_START + (offset & WINDOW_RANGE_MASK));
 		spin_unlock_bh(&ab_pci->window_lock);
 	}
+
+	if (test_bit(ATH11K_PCI_FLAG_INIT_DONE, &ab_pci->flags) &&
+	    offset >= ACCESS_ALWAYS_OFF)
+		mhi_device_put(ab_pci->mhi_ctrl->mhi_dev);
 }
 
 u32 ath11k_pci_read32(struct ath11k_base *ab, u32 offset)
@@ -139,6 +160,13 @@ u32 ath11k_pci_read32(struct ath11k_base *ab, u32 offset)
 	struct ath11k_pci *ab_pci = ath11k_pci_priv(ab);
 	u32 val;
 
+	/* for offset beyond BAR + 4K - 32, may
+	 * need to wakeup MHI to access.
+	 */
+	if (test_bit(ATH11K_PCI_FLAG_INIT_DONE, &ab_pci->flags) &&
+	    offset >= ACCESS_ALWAYS_OFF)
+		mhi_device_get_sync(ab_pci->mhi_ctrl->mhi_dev);
+
 	if (offset < WINDOW_START) {
 		val = ioread32(ab->mem + offset);
 	} else {
@@ -148,6 +176,10 @@ u32 ath11k_pci_read32(struct ath11k_base *ab, u32 offset)
 		spin_unlock_bh(&ab_pci->window_lock);
 	}
 
+	if (test_bit(ATH11K_PCI_FLAG_INIT_DONE, &ab_pci->flags) &&
+	    offset >= ACCESS_ALWAYS_OFF)
+		mhi_device_put(ab_pci->mhi_ctrl->mhi_dev);
+
 	return val;
 }
 
@@ -582,6 +614,9 @@ static void ath11k_pci_init_qmi_ce_config(struct ath11k_base *ab)
 	cfg->svc_to_ce_map = ab->hw_params.svc_to_ce_map;
 	cfg->svc_to_ce_map_len = ab->hw_params.svc_to_ce_map_len;
 	ab->qmi.service_ins_id = ATH11K_QMI_WLFW_SERVICE_INS_ID_V01_QCA6390;
+
+	ath11k_ce_get_shadow_config(ab, &cfg->shadow_reg_v2,
+				    &cfg->shadow_reg_v2_len);
 }
 
 static void ath11k_pci_ce_irqs_enable(struct ath11k_base *ab)
@@ -727,6 +762,8 @@ static int ath11k_pci_power_up(struct ath11k_base *ab)
 	struct ath11k_pci *ab_pci = ath11k_pci_priv(ab);
 	int ret;
 
+	ab_pci->register_window = 0;
+	clear_bit(ATH11K_PCI_FLAG_INIT_DONE, &ab_pci->flags);
 	ath11k_pci_sw_reset(ab_pci->ab);
 
 	ret = ath11k_mhi_start(ab_pci);
@@ -743,6 +780,7 @@ static void ath11k_pci_power_down(struct ath11k_base *ab)
 	struct ath11k_pci *ab_pci = ath11k_pci_priv(ab);
 
 	ath11k_mhi_stop(ab_pci);
+	clear_bit(ATH11K_PCI_FLAG_INIT_DONE, &ab_pci->flags);
 	ath11k_pci_force_wake(ab_pci->ab);
 	ath11k_pci_sw_reset(ab_pci->ab);
 }
@@ -771,6 +809,10 @@ static void ath11k_pci_stop(struct ath11k_base *ab)
 
 static int ath11k_pci_start(struct ath11k_base *ab)
 {
+	struct ath11k_pci *ab_pci = ath11k_pci_priv(ab);
+
+	set_bit(ATH11K_PCI_FLAG_INIT_DONE, &ab_pci->flags);
+
 	ath11k_pci_ce_irqs_enable(ab);
 	ath11k_ce_rx_post_buf(ab);
 
@@ -839,21 +881,11 @@ static int ath11k_pci_probe(struct pci_dev *pdev,
 {
 	struct ath11k_base *ab;
 	struct ath11k_pci *ab_pci;
-	enum ath11k_hw_rev hw_rev;
+	u32 soc_hw_version, soc_hw_version_major, soc_hw_version_minor;
 	int ret;
 
 	dev_warn(&pdev->dev, "WARNING: ath11k PCI support is experimental!\n");
 
-	switch (pci_dev->device) {
-	case QCA6390_DEVICE_ID:
-		hw_rev = ATH11K_HW_QCA6390_HW20;
-		break;
-	default:
-		dev_err(&pdev->dev, "Unknown PCI device found: 0x%x\n",
-			pci_dev->device);
-		return -ENOTSUPP;
-	}
-
 	ab = ath11k_core_alloc(&pdev->dev, sizeof(*ab_pci), ATH11K_BUS_PCI,
 			       &ath11k_pci_bus_params);
 	if (!ab) {
@@ -862,7 +894,6 @@ static int ath11k_pci_probe(struct pci_dev *pdev,
 	}
 
 	ab->dev = &pdev->dev;
-	ab->hw_rev = hw_rev;
 	pci_set_drvdata(pdev, ab);
 	ab_pci = ath11k_pci_priv(ab);
 	ab_pci->dev_id = pci_dev->device;
@@ -878,6 +909,35 @@ static int ath11k_pci_probe(struct pci_dev *pdev,
 		goto err_free_core;
 	}
 
+	switch (pci_dev->device) {
+	case QCA6390_DEVICE_ID:
+		soc_hw_version = ath11k_pci_read32(ab, TCSR_SOC_HW_VERSION);
+		soc_hw_version_major = FIELD_GET(TCSR_SOC_HW_VERSION_MAJOR_MASK,
+						 soc_hw_version);
+		soc_hw_version_minor = FIELD_GET(TCSR_SOC_HW_VERSION_MINOR_MASK,
+						 soc_hw_version);
+
+		ath11k_dbg(ab, ATH11K_DBG_PCI, "pci tcsr_soc_hw_version major %d minor %d\n",
+			   soc_hw_version_major, soc_hw_version_minor);
+
+		switch (soc_hw_version_major) {
+		case 2:
+			ab->hw_rev = ATH11K_HW_QCA6390_HW20;
+			break;
+		default:
+			dev_err(&pdev->dev, "Unsupported QCA6390 SOC hardware version: %d %d\n",
+				soc_hw_version_major, soc_hw_version_minor);
+			ret = -EOPNOTSUPP;
+			goto err_pci_free_region;
+		}
+		break;
+	default:
+		dev_err(&pdev->dev, "Unknown PCI device found: 0x%x\n",
+			pci_dev->device);
+		ret = -EOPNOTSUPP;
+		goto err_pci_free_region;
+	}
+
 	ret = ath11k_pci_enable_msi(ab_pci);
 	if (ret) {
 		ath11k_err(ab, "failed to enable msi: %d\n", ret);
@@ -949,10 +1009,17 @@ static void ath11k_pci_remove(struct pci_dev *pdev)
 	struct ath11k_pci *ab_pci = ath11k_pci_priv(ab);
 
 	set_bit(ATH11K_FLAG_UNREGISTERING, &ab->dev_flags);
+
+	ath11k_core_deinit(ab);
+
 	ath11k_mhi_unregister(ab_pci);
+
+	ath11k_pci_free_irq(ab);
 	ath11k_pci_disable_msi(ab_pci);
 	ath11k_pci_free_region(ab_pci);
-	ath11k_pci_free_irq(ab);
+
+	ath11k_hal_srng_deinit(ab);
+	ath11k_ce_free_pipes(ab);
 	ath11k_core_free(ab);
 }
 
diff --git a/drivers/net/wireless/ath/ath11k/pci.h b/drivers/net/wireless/ath/ath11k/pci.h
index f2f280eb8b55..43562f774a37 100644
--- a/drivers/net/wireless/ath/ath11k/pci.h
+++ b/drivers/net/wireless/ath/ath11k/pci.h
@@ -36,6 +36,10 @@ struct ath11k_msi_config {
 	struct ath11k_msi_user *users;
 };
 
+enum ath11k_pci_flags {
+	ATH11K_PCI_FLAG_INIT_DONE,
+};
+
 struct ath11k_pci {
 	struct pci_dev *pdev;
 	struct ath11k_base *ab;
@@ -48,6 +52,9 @@ struct ath11k_pci {
 
 	/* protects register_window above */
 	spinlock_t window_lock;
+
+	/* enum ath11k_pci_flags */
+	unsigned long flags;
 };
 
 static inline struct ath11k_pci *ath11k_pci_priv(struct ath11k_base *ab)
diff --git a/drivers/net/wireless/ath/ath11k/qmi.c b/drivers/net/wireless/ath/ath11k/qmi.c
index b906b50ee57e..c2b165158225 100644
--- a/drivers/net/wireless/ath/ath11k/qmi.c
+++ b/drivers/net/wireless/ath/ath11k/qmi.c
@@ -3,6 +3,8 @@
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
  */
 
+#include <linux/elf.h>
+
 #include "qmi.h"
 #include "core.h"
 #include "debug.h"
@@ -1990,6 +1992,7 @@ static int ath11k_qmi_load_bdf_qmi(struct ath11k_base *ab)
 	struct qmi_txn txn = {};
 	int ret;
 	const u8 *temp;
+	int bdf_type;
 
 	req = kzalloc(sizeof(*req), GFP_KERNEL);
 	if (!req)
@@ -2006,6 +2009,13 @@ static int ath11k_qmi_load_bdf_qmi(struct ath11k_base *ab)
 	temp = bd.data;
 	remaining = bd.len;
 
+	if (bd.len >= SELFMAG && memcmp(bd.data, ELFMAG, SELFMAG) == 0)
+		bdf_type = ATH11K_QMI_BDF_TYPE_ELF;
+	else
+		bdf_type = ATH11K_QMI_BDF_TYPE_BIN;
+
+	ath11k_dbg(ab, ATH11K_DBG_QMI, "qmi bdf_type %d\n", bdf_type);
+
 	while (remaining) {
 		req->valid = 1;
 		req->file_id_valid = 1;
@@ -2015,7 +2025,7 @@ static int ath11k_qmi_load_bdf_qmi(struct ath11k_base *ab)
 		req->seg_id_valid = 1;
 		req->data_valid = 1;
 		req->data_len = ATH11K_QMI_MAX_BDF_FILE_NAME_SIZE;
-		req->bdf_type = ATH11K_QMI_BDF_TYPE_BIN;
+		req->bdf_type = bdf_type;
 		req->bdf_type_valid = 1;
 		req->end_valid = 1;
 		req->end = 0;
@@ -2265,7 +2275,18 @@ static int ath11k_qmi_wlanfw_wlan_cfg_send(struct ath11k_base *ab)
 		req->svc_cfg[pipe_num].pipe_num = svc_cfg[pipe_num].pipenum;
 	}
 	req->shadow_reg_valid = 0;
-	req->shadow_reg_v2_valid = 0;
+
+	/* set shadow v2 configuration */
+	if (ab->hw_params.supports_shadow_regs) {
+		req->shadow_reg_v2_valid = 1;
+		req->shadow_reg_v2_len = min_t(u32,
+					       ab->qmi.ce_cfg.shadow_reg_v2_len,
+					       QMI_WLANFW_MAX_NUM_SHADOW_REG_V2_V01);
+		memcpy(&req->shadow_reg_v2, ab->qmi.ce_cfg.shadow_reg_v2,
+		       sizeof(u32) * req->shadow_reg_v2_len);
+	} else {
+		req->shadow_reg_v2_valid = 0;
+	}
 
 	ret = qmi_txn_init(&ab->qmi.handle, &txn,
 			   qmi_wlanfw_wlan_cfg_resp_msg_v01_ei, &resp);
diff --git a/drivers/net/wireless/ath/ath11k/qmi.h b/drivers/net/wireless/ath/ath11k/qmi.h
index 60e904683165..b0a818f0401b 100644
--- a/drivers/net/wireless/ath/ath11k/qmi.h
+++ b/drivers/net/wireless/ath/ath11k/qmi.h
@@ -77,7 +77,7 @@ struct ath11k_qmi_ce_cfg {
 	int svc_to_ce_map_len;
 	const u8 *shadow_reg;
 	int shadow_reg_len;
-	u8 *shadow_reg_v2;
+	u32 *shadow_reg_v2;
 	int shadow_reg_v2_len;
 };
 
diff --git a/drivers/net/wireless/ath/ath11k/reg.c b/drivers/net/wireless/ath/ath11k/reg.c
index 0ba80e6f3979..f6a1f0352989 100644
--- a/drivers/net/wireless/ath/ath11k/reg.c
+++ b/drivers/net/wireless/ath/ath11k/reg.c
@@ -206,7 +206,7 @@ int ath11k_regd_update(struct ath11k *ar, bool init)
 	ab = ar->ab;
 	pdev_id = ar->pdev_idx;
 
-	spin_lock(&ab->base_lock);
+	spin_lock_bh(&ab->base_lock);
 
 	if (init) {
 		/* Apply the regd received during init through
@@ -227,7 +227,7 @@ int ath11k_regd_update(struct ath11k *ar, bool init)
 
 	if (!regd) {
 		ret = -EINVAL;
-		spin_unlock(&ab->base_lock);
+		spin_unlock_bh(&ab->base_lock);
 		goto err;
 	}
 
@@ -238,7 +238,7 @@ int ath11k_regd_update(struct ath11k *ar, bool init)
 	if (regd_copy)
 		ath11k_copy_regd(regd, regd_copy);
 
-	spin_unlock(&ab->base_lock);
+	spin_unlock_bh(&ab->base_lock);
 
 	if (!regd_copy) {
 		ret = -ENOMEM;
diff --git a/drivers/net/wireless/ath/ath11k/spectral.c b/drivers/net/wireless/ath/ath11k/spectral.c
index 92fd8a4df1f2..ac2a8cfdc1c0 100644
--- a/drivers/net/wireless/ath/ath11k/spectral.c
+++ b/drivers/net/wireless/ath/ath11k/spectral.c
@@ -17,8 +17,6 @@
 #define ATH11K_SPECTRAL_ATH11K_MIN_IB_BINS	32
 #define ATH11K_SPECTRAL_ATH11K_MAX_IB_BINS	256
 
-#define ATH11K_SPECTRAL_SAMPLE_FFT_BIN_MASK	0xFF
-
 #define ATH11K_SPECTRAL_SCAN_COUNT_MAX		4095
 
 /* Max channel computed by sum of 2g and 5g band channels */
@@ -557,16 +555,16 @@ static u8 ath11k_spectral_get_max_exp(s8 max_index, u8 max_magnitude,
 	return max_exp;
 }
 
-static void ath11k_spectral_parse_16bit_fft(u8 *outbins, u8 *inbins, int num_bins)
+static void ath11k_spectral_parse_fft(u8 *outbins, u8 *inbins, int num_bins, u8 fft_sz)
 {
-	int i;
-	__le16 *data = (__le16 *)inbins;
+	int i, j;
 
 	i = 0;
+	j = 0;
 	while (i < num_bins) {
-		outbins[i] = (__le16_to_cpu(data[i])) &
-			     ATH11K_SPECTRAL_SAMPLE_FFT_BIN_MASK;
+		outbins[i] = inbins[j];
 		i++;
+		j += fft_sz;
 	}
 }
 
@@ -588,6 +586,12 @@ int ath11k_spectral_process_fft(struct ath11k *ar,
 
 	lockdep_assert_held(&ar->spectral.lock);
 
+	if (!ab->hw_params.spectral_fft_sz) {
+		ath11k_warn(ab, "invalid bin size type for hw rev %d\n",
+			    ab->hw_rev);
+		return -EINVAL;
+	}
+
 	tlv = (struct spectral_tlv *)data;
 	tlv_len = FIELD_GET(SPECTRAL_TLV_HDR_LEN, __le32_to_cpu(tlv->header));
 	/* convert Dword into bytes */
@@ -649,9 +653,8 @@ int ath11k_spectral_process_fft(struct ath11k *ar,
 	freq = summary->meta.freq2;
 	fft_sample->freq2 = __cpu_to_be16(freq);
 
-	ath11k_spectral_parse_16bit_fft(fft_sample->data,
-					fft_report->bins,
-					num_bins);
+	ath11k_spectral_parse_fft(fft_sample->data, fft_report->bins, num_bins,
+				  ab->hw_params.spectral_fft_sz);
 
 	fft_sample->max_exp = ath11k_spectral_get_max_exp(fft_sample->max_index,
 							  search.peak_mag,
@@ -959,6 +962,9 @@ int ath11k_spectral_init(struct ath11k_base *ab)
 		      ab->wmi_ab.svc_map))
 		return 0;
 
+	if (!ab->hw_params.spectral_fft_sz)
+		return 0;
+
 	for (i = 0; i < ab->num_radios; i++) {
 		ar = ab->pdevs[i].ar;
 		sp = &ar->spectral;
diff --git a/drivers/net/wireless/ath/ath11k/wmi.c b/drivers/net/wireless/ath/ath11k/wmi.c
index adde14a390ec..8eca92520837 100644
--- a/drivers/net/wireless/ath/ath11k/wmi.c
+++ b/drivers/net/wireless/ath/ath11k/wmi.c
@@ -3342,55 +3342,6 @@ int ath11k_wmi_cmd_init(struct ath11k_base *ab)
 	memset(&init_param, 0, sizeof(init_param));
 	memset(&config, 0, sizeof(config));
 
-	config.num_vdevs = ab->num_radios * TARGET_NUM_VDEVS;
-
-	if (ab->num_radios == 2) {
-		config.num_peers = TARGET_NUM_PEERS(DBS);
-		config.num_tids = TARGET_NUM_TIDS(DBS);
-	} else if (ab->num_radios == 3) {
-		config.num_peers = TARGET_NUM_PEERS(DBS_SBS);
-		config.num_tids = TARGET_NUM_TIDS(DBS_SBS);
-	} else {
-		/* Control should not reach here */
-		config.num_peers = TARGET_NUM_PEERS(SINGLE);
-		config.num_tids = TARGET_NUM_TIDS(SINGLE);
-	}
-	config.num_offload_peers = TARGET_NUM_OFFLD_PEERS;
-	config.num_offload_reorder_buffs = TARGET_NUM_OFFLD_REORDER_BUFFS;
-	config.num_peer_keys = TARGET_NUM_PEER_KEYS;
-	config.ast_skid_limit = TARGET_AST_SKID_LIMIT;
-	config.tx_chain_mask = (1 << ab->target_caps.num_rf_chains) - 1;
-	config.rx_chain_mask = (1 << ab->target_caps.num_rf_chains) - 1;
-	config.rx_timeout_pri[0] = TARGET_RX_TIMEOUT_LO_PRI;
-	config.rx_timeout_pri[1] = TARGET_RX_TIMEOUT_LO_PRI;
-	config.rx_timeout_pri[2] = TARGET_RX_TIMEOUT_LO_PRI;
-	config.rx_timeout_pri[3] = TARGET_RX_TIMEOUT_HI_PRI;
-	config.rx_decap_mode = TARGET_DECAP_MODE_NATIVE_WIFI;
-
-	if (test_bit(ATH11K_FLAG_RAW_MODE, &ab->dev_flags))
-		config.rx_decap_mode = TARGET_DECAP_MODE_RAW;
-
-	config.scan_max_pending_req = TARGET_SCAN_MAX_PENDING_REQS;
-	config.bmiss_offload_max_vdev = TARGET_BMISS_OFFLOAD_MAX_VDEV;
-	config.roam_offload_max_vdev = TARGET_ROAM_OFFLOAD_MAX_VDEV;
-	config.roam_offload_max_ap_profiles = TARGET_ROAM_OFFLOAD_MAX_AP_PROFILES;
-	config.num_mcast_groups = TARGET_NUM_MCAST_GROUPS;
-	config.num_mcast_table_elems = TARGET_NUM_MCAST_TABLE_ELEMS;
-	config.mcast2ucast_mode = TARGET_MCAST2UCAST_MODE;
-	config.tx_dbg_log_size = TARGET_TX_DBG_LOG_SIZE;
-	config.num_wds_entries = TARGET_NUM_WDS_ENTRIES;
-	config.dma_burst_size = TARGET_DMA_BURST_SIZE;
-	config.rx_skip_defrag_timeout_dup_detection_check =
-		TARGET_RX_SKIP_DEFRAG_TIMEOUT_DUP_DETECTION_CHECK;
-	config.vow_config = TARGET_VOW_CONFIG;
-	config.gtk_offload_max_vdev = TARGET_GTK_OFFLOAD_MAX_VDEV;
-	config.num_msdu_desc = TARGET_NUM_MSDU_DESC;
-	config.beacon_tx_offload_max_vdev = ab->num_radios * TARGET_MAX_BCN_OFFLD;
-	config.rx_batchmode = TARGET_RX_BATCHMODE;
-	config.peer_map_unmap_v2_support = 1;
-	config.twt_ap_pdev_count = ab->num_radios;
-	config.twt_ap_sta_count = 1000;
-
 	ab->hw_params.hw_ops->wmi_init_config(ab, &config);
 
 	memcpy(&wmi_sc->wlan_resource_config, &config, sizeof(config));
@@ -6301,7 +6252,7 @@ static void ath11k_peer_assoc_conf_event(struct ath11k_base *ab, struct sk_buff
 
 static void ath11k_update_stats_event(struct ath11k_base *ab, struct sk_buff *skb)
 {
-	ath11k_debug_fw_stats_process(ab, skb);
+	ath11k_debugfs_fw_stats_process(ab, skb);
 }
 
 /* PDEV_CTL_FAILSAFE_CHECK_EVENT is received from FW when the frequency scanned
@@ -6579,7 +6530,7 @@ static void ath11k_wmi_tlv_op_rx(struct ath11k_base *ab, struct sk_buff *skb)
 		break;
 	/* TODO: Add remaining events */
 	default:
-		ath11k_warn(ab, "Unknown eventid: 0x%x\n", id);
+		ath11k_dbg(ab, ATH11K_DBG_WMI, "Unknown eventid: 0x%x\n", id);
 		break;
 	}
 
diff --git a/drivers/net/wireless/ath/ath5k/debug.c b/drivers/net/wireless/ath/ath5k/debug.c
index 2eaba1ccab20..4b41160e5d38 100644
--- a/drivers/net/wireless/ath/ath5k/debug.c
+++ b/drivers/net/wireless/ath/ath5k/debug.c
@@ -161,33 +161,14 @@ static int reg_show(struct seq_file *seq, void *p)
 	return 0;
 }
 
-static const struct seq_operations register_seq_ops = {
+static const struct seq_operations registers_sops = {
 	.start = reg_start,
 	.next  = reg_next,
 	.stop  = reg_stop,
 	.show  = reg_show
 };
 
-static int open_file_registers(struct inode *inode, struct file *file)
-{
-	struct seq_file *s;
-	int res;
-	res = seq_open(file, &register_seq_ops);
-	if (res == 0) {
-		s = file->private_data;
-		s->private = inode->i_private;
-	}
-	return res;
-}
-
-static const struct file_operations fops_registers = {
-	.open = open_file_registers,
-	.read    = seq_read,
-	.llseek  = seq_lseek,
-	.release = seq_release,
-	.owner = THIS_MODULE,
-};
-
+DEFINE_SEQ_ATTRIBUTE(registers);
 
 /* debugfs: beacons */
 
@@ -1005,7 +986,7 @@ ath5k_debug_init_device(struct ath5k_hw *ah)
 		return;
 
 	debugfs_create_file("debug", 0600, phydir, ah, &fops_debug);
-	debugfs_create_file("registers", 0400, phydir, ah, &fops_registers);
+	debugfs_create_file("registers", 0400, phydir, ah, &registers_fops);
 	debugfs_create_file("beacon", 0600, phydir, ah, &fops_beacon);
 	debugfs_create_file("reset", 0200, phydir, ah, &fops_reset);
 	debugfs_create_file("antenna", 0600, phydir, ah, &fops_antenna);
diff --git a/drivers/net/wireless/ath/ath6kl/wmi.c b/drivers/net/wireless/ath/ath6kl/wmi.c
index a4339cca661f..dbc47702a268 100644
--- a/drivers/net/wireless/ath/ath6kl/wmi.c
+++ b/drivers/net/wireless/ath/ath6kl/wmi.c
@@ -2639,6 +2639,11 @@ int ath6kl_wmi_delete_pstream_cmd(struct wmi *wmi, u8 if_idx, u8 traffic_class,
 		return -EINVAL;
 	}
 
+	if (tsid >= 16) {
+		ath6kl_err("invalid tsid: %d\n", tsid);
+		return -EINVAL;
+	}
+
 	skb = ath6kl_wmi_get_new_buf(sizeof(*cmd));
 	if (!skb)
 		return -ENOMEM;
diff --git a/drivers/net/wireless/ath/ath9k/ar9580_1p0_initvals.h b/drivers/net/wireless/ath/ath9k/ar9580_1p0_initvals.h
index f4c9befb3949..fab14e0a87b9 100644
--- a/drivers/net/wireless/ath/ath9k/ar9580_1p0_initvals.h
+++ b/drivers/net/wireless/ath/ath9k/ar9580_1p0_initvals.h
@@ -1328,27 +1328,6 @@ static const u32 ar9580_1p0_baseband_postamble[][5] = {
 	{0x0000c284, 0x00000000, 0x00000000, 0x00000150, 0x00000150},
 };
 
-static const u32 ar9580_1p0_pcie_phy_clkreq_enable_L1[][2] = {
-	/* Addr      allmodes  */
-	{0x00004040, 0x0835365e},
-	{0x00004040, 0x0008003b},
-	{0x00004044, 0x00000000},
-};
-
-static const u32 ar9580_1p0_pcie_phy_clkreq_disable_L1[][2] = {
-	/* Addr      allmodes  */
-	{0x00004040, 0x0831365e},
-	{0x00004040, 0x0008003b},
-	{0x00004044, 0x00000000},
-};
-
-static const u32 ar9580_1p0_pcie_phy_pll_on_clkreq[][2] = {
-	/* Addr      allmodes  */
-	{0x00004040, 0x0831265e},
-	{0x00004040, 0x0008003b},
-	{0x00004044, 0x00000000},
-};
-
 static const u32 ar9580_1p0_baseband_postamble_dfs_channel[][3] = {
 	/* Addr      5G          2G        */
 	{0x00009814, 0x3400c00f, 0x3400c00f},
diff --git a/drivers/net/wireless/ath/ath9k/hif_usb.c b/drivers/net/wireless/ath/ath9k/hif_usb.c
index 38f07420f4f9..860da13bfb6a 100644
--- a/drivers/net/wireless/ath/ath9k/hif_usb.c
+++ b/drivers/net/wireless/ath/ath9k/hif_usb.c
@@ -449,10 +449,19 @@ static void hif_usb_stop(void *hif_handle)
 	spin_unlock_irqrestore(&hif_dev->tx.tx_lock, flags);
 
 	/* The pending URBs have to be canceled. */
+	spin_lock_irqsave(&hif_dev->tx.tx_lock, flags);
 	list_for_each_entry_safe(tx_buf, tx_buf_tmp,
 				 &hif_dev->tx.tx_pending, list) {
+		usb_get_urb(tx_buf->urb);
+		spin_unlock_irqrestore(&hif_dev->tx.tx_lock, flags);
 		usb_kill_urb(tx_buf->urb);
+		list_del(&tx_buf->list);
+		usb_free_urb(tx_buf->urb);
+		kfree(tx_buf->buf);
+		kfree(tx_buf);
+		spin_lock_irqsave(&hif_dev->tx.tx_lock, flags);
 	}
+	spin_unlock_irqrestore(&hif_dev->tx.tx_lock, flags);
 
 	usb_kill_anchored_urbs(&hif_dev->mgmt_submitted);
 }
@@ -762,27 +771,37 @@ static void ath9k_hif_usb_dealloc_tx_urbs(struct hif_device_usb *hif_dev)
 	struct tx_buf *tx_buf = NULL, *tx_buf_tmp = NULL;
 	unsigned long flags;
 
+	spin_lock_irqsave(&hif_dev->tx.tx_lock, flags);
 	list_for_each_entry_safe(tx_buf, tx_buf_tmp,
 				 &hif_dev->tx.tx_buf, list) {
+		usb_get_urb(tx_buf->urb);
+		spin_unlock_irqrestore(&hif_dev->tx.tx_lock, flags);
 		usb_kill_urb(tx_buf->urb);
 		list_del(&tx_buf->list);
 		usb_free_urb(tx_buf->urb);
 		kfree(tx_buf->buf);
 		kfree(tx_buf);
+		spin_lock_irqsave(&hif_dev->tx.tx_lock, flags);
 	}
+	spin_unlock_irqrestore(&hif_dev->tx.tx_lock, flags);
 
 	spin_lock_irqsave(&hif_dev->tx.tx_lock, flags);
 	hif_dev->tx.flags |= HIF_USB_TX_FLUSH;
 	spin_unlock_irqrestore(&hif_dev->tx.tx_lock, flags);
 
+	spin_lock_irqsave(&hif_dev->tx.tx_lock, flags);
 	list_for_each_entry_safe(tx_buf, tx_buf_tmp,
 				 &hif_dev->tx.tx_pending, list) {
+		usb_get_urb(tx_buf->urb);
+		spin_unlock_irqrestore(&hif_dev->tx.tx_lock, flags);
 		usb_kill_urb(tx_buf->urb);
 		list_del(&tx_buf->list);
 		usb_free_urb(tx_buf->urb);
 		kfree(tx_buf->buf);
 		kfree(tx_buf);
+		spin_lock_irqsave(&hif_dev->tx.tx_lock, flags);
 	}
+	spin_unlock_irqrestore(&hif_dev->tx.tx_lock, flags);
 
 	usb_kill_anchored_urbs(&hif_dev->mgmt_submitted);
 }
diff --git a/drivers/net/wireless/ath/wcn36xx/hal.h b/drivers/net/wireless/ath/wcn36xx/hal.h
index 573799274a02..65ef893f2736 100644
--- a/drivers/net/wireless/ath/wcn36xx/hal.h
+++ b/drivers/net/wireless/ath/wcn36xx/hal.h
@@ -726,7 +726,129 @@ enum pe_stats_mask {
 #define WCN36XX_HAL_CFG_AP_LINK_MONITOR_TIMEOUT		102
 #define WCN36XX_HAL_CFG_BTC_DWELL_TIME_MULTIPLIER	103
 #define WCN36XX_HAL_CFG_ENABLE_TDLS_OXYGEN_MODE		104
-#define WCN36XX_HAL_CFG_MAX_PARAMS			105
+#define WCN36XX_HAL_CFG_ENABLE_NAT_KEEP_ALIVE_FILTER	105
+#define WCN36XX_HAL_CFG_ENABLE_SAP_OBSS_PROT		106
+#define WCN36XX_HAL_CFG_PSPOLL_DATA_RECEP_TIMEOUT	107
+#define WCN36XX_HAL_CFG_TDLS_PUAPSD_BUFFER_STA_CAPABLE	108
+#define WCN36XX_HAL_CFG_TDLS_PUAPSD_MASK		109
+#define WCN36XX_HAL_CFG_TDLS_PUAPSD_INACTIVITY_TIME	110
+#define WCN36XX_HAL_CFG_TDLS_PUAPSD_RX_FRAME_THRESHOLD	111
+#define WCN36XX_HAL_CFG_ANTENNA_DIVERSITY		112
+#define WCN36XX_HAL_CFG_ATH_DISABLE			113
+#define WCN36XX_HAL_CFG_FLEXCONNECT_POWER_FACTOR	114
+#define WCN36XX_HAL_CFG_ENABLE_ADAPTIVE_RX_DRAIN	115
+#define WCN36XX_HAL_CFG_TDLS_OFF_CHANNEL_CAPABLE	116
+#define WCN36XX_HAL_CFG_MWS_COEX_V1_WAN_FREQ		117
+#define WCN36XX_HAL_CFG_MWS_COEX_V1_WLAN_FREQ		118
+#define WCN36XX_HAL_CFG_MWS_COEX_V1_CONFIG		119
+#define WCN36XX_HAL_CFG_MWS_COEX_V1_CONFIG2		120
+#define WCN36XX_HAL_CFG_MWS_COEX_V2_WAN_FREQ		121
+#define WCN36XX_HAL_CFG_MWS_COEX_V2_WLAN_FREQ		122
+#define WCN36XX_HAL_CFG_MWS_COEX_V2_CONFIG		123
+#define WCN36XX_HAL_CFG_MWS_COEX_V2_CONFIG2		124
+#define WCN36XX_HAL_CFG_MWS_COEX_V3_WAN_FREQ		125
+#define WCN36XX_HAL_CFG_MWS_COEX_V3_WLAN_FREQ		126
+#define WCN36XX_HAL_CFG_MWS_COEX_V3_CONFIG		127
+#define WCN36XX_HAL_CFG_MWS_COEX_V3_CONFIG2		128
+#define WCN36XX_HAL_CFG_MWS_COEX_V4_WAN_FREQ		129
+#define WCN36XX_HAL_CFG_MWS_COEX_V4_WLAN_FREQ		130
+#define WCN36XX_HAL_CFG_MWS_COEX_V4_CONFIG		131
+#define WCN36XX_HAL_CFG_MWS_COEX_V4_CONFIG2		132
+#define WCN36XX_HAL_CFG_MWS_COEX_V5_WAN_FREQ		133
+#define WCN36XX_HAL_CFG_MWS_COEX_V5_WLAN_FREQ		134
+#define WCN36XX_HAL_CFG_MWS_COEX_V5_CONFIG		135
+#define WCN36XX_HAL_CFG_MWS_COEX_V5_CONFIG2		136
+#define WCN36XX_HAL_CFG_MWS_COEX_V6_WAN_FREQ		137
+#define WCN36XX_HAL_CFG_MWS_COEX_V6_WLAN_FREQ		138
+#define WCN36XX_HAL_CFG_MWS_COEX_V6_CONFIG		139
+#define WCN36XX_HAL_CFG_MWS_COEX_V6_CONFIG2		140
+#define WCN36XX_HAL_CFG_MWS_COEX_V7_WAN_FREQ		141
+#define WCN36XX_HAL_CFG_MWS_COEX_V7_WLAN_FREQ		142
+#define WCN36XX_HAL_CFG_MWS_COEX_V7_CONFIG		143
+#define WCN36XX_HAL_CFG_MWS_COEX_V7_CONFIG2		144
+#define WCN36XX_HAL_CFG_MWS_COEX_V8_WAN_FREQ		145
+#define WCN36XX_HAL_CFG_MWS_COEX_V8_WLAN_FREQ		146
+#define WCN36XX_HAL_CFG_MWS_COEX_V8_CONFIG		147
+#define WCN36XX_HAL_CFG_MWS_COEX_V8_CONFIG2		148
+#define WCN36XX_HAL_CFG_MWS_COEX_V9_WAN_FREQ		149
+#define WCN36XX_HAL_CFG_MWS_COEX_V9_WLAN_FREQ		150
+#define WCN36XX_HAL_CFG_MWS_COEX_V9_CONFIG		151
+#define WCN36XX_HAL_CFG_MWS_COEX_V9_CONFIG2		152
+#define WCN36XX_HAL_CFG_MWS_COEX_V10_WAN_FREQ		153
+#define WCN36XX_HAL_CFG_MWS_COEX_V10_WLAN_FREQ		154
+#define WCN36XX_HAL_CFG_MWS_COEX_V10_CONFIG		155
+#define WCN36XX_HAL_CFG_MWS_COEX_V10_CONFIG2		156
+#define WCN36XX_HAL_CFG_MWS_COEX_MODEM_BACKOFF		157
+#define WCN36XX_HAL_CFG_MWS_COEX_CONFIG1		158
+#define WCN36XX_HAL_CFG_MWS_COEX_CONFIG2		159
+#define WCN36XX_HAL_CFG_MWS_COEX_CONFIG3		160
+#define WCN36XX_HAL_CFG_MWS_COEX_CONFIG4		161
+#define WCN36XX_HAL_CFG_MWS_COEX_CONFIG5		162
+#define WCN36XX_HAL_CFG_MWS_COEX_CONFIG6		163
+#define WCN36XX_HAL_CFG_SAR_POWER_BACKOFF		164
+#define WCN36XX_HAL_CFG_GO_LINK_MONITOR_TIMEOUT		165
+#define WCN36XX_HAL_CFG_BTC_STATIC_OPP_WLAN_ACTIVE_WLAN_LEN	166
+#define WCN36XX_HAL_CFG_BTC_STATIC_OPP_WLAN_ACTIVE_BT_LEN	167
+#define WCN36XX_HAL_CFG_BTC_SAP_STATIC_OPP_ACTIVE_WLAN_LEN	168
+#define WCN36XX_HAL_CFG_BTC_SAP_STATIC_OPP_ACTIVE_BT_LEN	169
+#define WCN36XX_HAL_CFG_RMC_FIXED_RATE			170
+#define WCN36XX_HAL_CFG_ASD_PROBE_INTERVAL		171
+#define WCN36XX_HAL_CFG_ASD_TRIGGER_THRESHOLD		172
+#define WCN36XX_HAL_CFG_ASD_RTT_RSSI_HYST_THRESHOLD	173
+#define WCN36XX_HAL_CFG_BTC_CTS2S_ON_STA_DURING_SCO	174
+#define WCN36XX_HAL_CFG_SHORT_PREAMBLE			175
+#define WCN36XX_HAL_CFG_SHORT_SLOT_TIME			176
+#define WCN36XX_HAL_CFG_DELAYED_BA			177
+#define WCN36XX_HAL_CFG_IMMEDIATE_BA			178
+#define WCN36XX_HAL_CFG_DOT11_MODE			179
+#define WCN36XX_HAL_CFG_HT_CAPS				180
+#define WCN36XX_HAL_CFG_AMPDU_PARAMS			181
+#define WCN36XX_HAL_CFG_TX_BF_INFO			182
+#define WCN36XX_HAL_CFG_ASC_CAP_INFO			183
+#define WCN36XX_HAL_CFG_EXT_HT_CAPS			184
+#define WCN36XX_HAL_CFG_QOS_ENABLED			185
+#define WCN36XX_HAL_CFG_WME_ENABLED			186
+#define WCN36XX_HAL_CFG_WSM_ENABLED			187
+#define WCN36XX_HAL_CFG_WMM_ENABLED			188
+#define WCN36XX_HAL_CFG_UAPSD_PER_AC_BITMASK		189
+#define WCN36XX_HAL_CFG_MCS_RATES			190
+#define WCN36XX_HAL_CFG_VHT_CAPS			191
+#define WCN36XX_HAL_CFG_VHT_RX_SUPP_MCS			192
+#define WCN36XX_HAL_CFG_VHT_TX_SUPP_MCS			193
+#define WCN36XX_HAL_CFG_RA_FILTER_ENABLE		194
+#define WCN36XX_HAL_CFG_RA_RATE_LIMIT_INTERVAL		195
+#define WCN36XX_HAL_CFG_BTC_FATAL_HID_NSNIFF_BLK	196
+#define WCN36XX_HAL_CFG_BTC_CRITICAL_HID_NSNIFF_BLK	197
+#define WCN36XX_HAL_CFG_BTC_DYN_A2DP_TX_QUEUE_THOLD	198
+#define WCN36XX_HAL_CFG_BTC_DYN_OPP_TX_QUEUE_THOLD	199
+#define WCN36XX_HAL_CFG_LINK_FAIL_TIMEOUT		200
+#define WCN36XX_HAL_CFG_MAX_UAPSD_CONSEC_SP		201
+#define WCN36XX_HAL_CFG_MAX_UAPSD_CONSEC_RX_CNT		202
+#define WCN36XX_HAL_CFG_MAX_UAPSD_CONSEC_TX_CNT		203
+#define WCN36XX_HAL_CFG_MAX_UAPSD_CONSEC_RX_CNT_MEAS_WINDOW	204
+#define WCN36XX_HAL_CFG_MAX_UAPSD_CONSEC_TX_CNT_MEAS_WINDOW	205
+#define WCN36XX_HAL_CFG_MAX_PSPOLL_IN_WMM_UAPSD_PS_MODE	206
+#define WCN36XX_HAL_CFG_MAX_UAPSD_INACTIVITY_INTERVALS	207
+#define WCN36XX_HAL_CFG_ENABLE_DYNAMIC_WMMPS		208
+#define WCN36XX_HAL_CFG_BURST_MODE_BE_TXOP_VALUE	209
+#define WCN36XX_HAL_CFG_ENABLE_DYNAMIC_RA_START_RATE	210
+#define WCN36XX_HAL_CFG_BTC_FAST_WLAN_CONN_PREF		211
+#define WCN36XX_HAL_CFG_ENABLE_RTSCTS_HTVHT		212
+#define WCN36XX_HAL_CFG_BTC_STATIC_OPP_WLAN_IDLE_WLAN_LEN	213
+#define WCN36XX_HAL_CFG_BTC_STATIC_OPP_WLAN_IDLE_BT_LEN	214
+#define WCN36XX_HAL_CFG_LINK_FAIL_TX_CNT		215
+#define WCN36XX_HAL_CFG_TOGGLE_ARP_BDRATES		216
+#define WCN36XX_HAL_CFG_OPTIMIZE_CA_EVENT		217
+#define WCN36XX_HAL_CFG_EXT_SCAN_CONC_MODE		218
+#define WCN36XX_HAL_CFG_BAR_WAKEUP_HOST_DISABLE		219
+#define WCN36XX_HAL_CFG_SAR_BOFFSET_CORRECTION_ENABLE	220
+#define WCN36XX_HAL_CFG_UNITS_OF_BCN_WAIT_TIME		221
+#define WCN36XX_HAL_CFG_CONS_BCNMISS_COUNT		222
+#define WCN36XX_HAL_CFG_BTC_DISABLE_WLAN_LINK_CRITICAL	223
+#define WCN36XX_HAL_CFG_DISABLE_SCAN_DURING_SCO		224
+#define WCN36XX_HAL_CFG_TRIGGER_NULLFRAME_BEFORE_HB	225
+#define WCN36XX_HAL_CFG_ENABLE_POWERSAVE_OFFLOAD	226
+#define WCN36XX_HAL_CFG_MAX_PARAMS			227
 
 /* Specify the starting bitrate, 11B and 11A/G rates can be specified in
  * multiples of 0.5 So for 5.5 mbps => 11. for MCS 0 - 7 rates, Bit 7 should
@@ -1592,9 +1714,15 @@ struct wcn36xx_hal_config_sta_params_v1 {
 	u8 reserved:4;
 
 	/* These rates are the intersection of peer and self capabilities. */
-	struct wcn36xx_hal_supported_rates supported_rates;
+	struct wcn36xx_hal_supported_rates_v1 supported_rates;
+
+	u8 vht_capable;
+	u8 vht_tx_channel_width_set;
+
 } __packed;
 
+#define WCN36XX_DIFF_STA_PARAMS_V1_NOVHT 10
+
 struct wcn36xx_hal_config_sta_req_msg_v1 {
 	struct wcn36xx_hal_msg_header header;
 	struct wcn36xx_hal_config_sta_params_v1 sta_params;
@@ -2015,8 +2143,14 @@ struct wcn36xx_hal_config_bss_params_v1 {
 	 *  "STA context"
 	 */
 	struct wcn36xx_hal_config_sta_params_v1 sta;
+
+	u8 vht_capable;
+	u8 vht_tx_channel_width_set;
+
 } __packed;
 
+#define WCN36XX_DIFF_BSS_PARAMS_V1_NOVHT (WCN36XX_DIFF_STA_PARAMS_V1_NOVHT + 2)
+
 struct wcn36xx_hal_config_bss_req_msg_v1 {
 	struct wcn36xx_hal_msg_header header;
 	struct wcn36xx_hal_config_bss_params_v1 bss_params;
diff --git a/drivers/net/wireless/ath/wcn36xx/main.c b/drivers/net/wireless/ath/wcn36xx/main.c
index c5e94ba8f941..706728fba72d 100644
--- a/drivers/net/wireless/ath/wcn36xx/main.c
+++ b/drivers/net/wireless/ath/wcn36xx/main.c
@@ -39,10 +39,10 @@ MODULE_PARM_DESC(debug_mask, "Debugging mask");
 	.max_power = 25, \
 }
 
-#define CHAN5G(_freq, _idx) { \
+#define CHAN5G(_freq, _idx, _phy_val) { \
 	.band = NL80211_BAND_5GHZ, \
 	.center_freq = (_freq), \
-	.hw_value = (_idx), \
+	.hw_value = (_phy_val) << HW_VALUE_PHY_SHIFT | HW_VALUE_CHANNEL(_idx), \
 	.max_power = 25, \
 }
 
@@ -67,29 +67,29 @@ static struct ieee80211_channel wcn_2ghz_channels[] = {
 };
 
 static struct ieee80211_channel wcn_5ghz_channels[] = {
-	CHAN5G(5180, 36),
-	CHAN5G(5200, 40),
-	CHAN5G(5220, 44),
-	CHAN5G(5240, 48),
-	CHAN5G(5260, 52),
-	CHAN5G(5280, 56),
-	CHAN5G(5300, 60),
-	CHAN5G(5320, 64),
-	CHAN5G(5500, 100),
-	CHAN5G(5520, 104),
-	CHAN5G(5540, 108),
-	CHAN5G(5560, 112),
-	CHAN5G(5580, 116),
-	CHAN5G(5600, 120),
-	CHAN5G(5620, 124),
-	CHAN5G(5640, 128),
-	CHAN5G(5660, 132),
-	CHAN5G(5700, 140),
-	CHAN5G(5745, 149),
-	CHAN5G(5765, 153),
-	CHAN5G(5785, 157),
-	CHAN5G(5805, 161),
-	CHAN5G(5825, 165)
+	CHAN5G(5180, 36, PHY_QUADRUPLE_CHANNEL_20MHZ_LOW_40MHZ_LOW),
+	CHAN5G(5200, 40, PHY_QUADRUPLE_CHANNEL_20MHZ_HIGH_40MHZ_LOW),
+	CHAN5G(5220, 44, PHY_QUADRUPLE_CHANNEL_20MHZ_LOW_40MHZ_HIGH),
+	CHAN5G(5240, 48, PHY_QUADRUPLE_CHANNEL_20MHZ_HIGH_40MHZ_HIGH),
+	CHAN5G(5260, 52, PHY_QUADRUPLE_CHANNEL_20MHZ_LOW_40MHZ_LOW),
+	CHAN5G(5280, 56, PHY_QUADRUPLE_CHANNEL_20MHZ_HIGH_40MHZ_LOW),
+	CHAN5G(5300, 60, PHY_QUADRUPLE_CHANNEL_20MHZ_LOW_40MHZ_HIGH),
+	CHAN5G(5320, 64, PHY_QUADRUPLE_CHANNEL_20MHZ_HIGH_40MHZ_HIGH),
+	CHAN5G(5500, 100, PHY_QUADRUPLE_CHANNEL_20MHZ_LOW_40MHZ_LOW),
+	CHAN5G(5520, 104, PHY_QUADRUPLE_CHANNEL_20MHZ_HIGH_40MHZ_LOW),
+	CHAN5G(5540, 108, PHY_QUADRUPLE_CHANNEL_20MHZ_LOW_40MHZ_HIGH),
+	CHAN5G(5560, 112, PHY_QUADRUPLE_CHANNEL_20MHZ_HIGH_40MHZ_HIGH),
+	CHAN5G(5580, 116, PHY_QUADRUPLE_CHANNEL_20MHZ_LOW_40MHZ_LOW),
+	CHAN5G(5600, 120, PHY_QUADRUPLE_CHANNEL_20MHZ_HIGH_40MHZ_LOW),
+	CHAN5G(5620, 124, PHY_QUADRUPLE_CHANNEL_20MHZ_LOW_40MHZ_HIGH),
+	CHAN5G(5640, 128, PHY_QUADRUPLE_CHANNEL_20MHZ_HIGH_40MHZ_HIGH),
+	CHAN5G(5660, 132, PHY_QUADRUPLE_CHANNEL_20MHZ_LOW_40MHZ_LOW),
+	CHAN5G(5700, 140, PHY_QUADRUPLE_CHANNEL_20MHZ_LOW_40MHZ_HIGH),
+	CHAN5G(5745, 149, PHY_QUADRUPLE_CHANNEL_20MHZ_LOW_40MHZ_LOW),
+	CHAN5G(5765, 153, PHY_QUADRUPLE_CHANNEL_20MHZ_HIGH_40MHZ_LOW),
+	CHAN5G(5785, 157, PHY_QUADRUPLE_CHANNEL_20MHZ_LOW_40MHZ_HIGH),
+	CHAN5G(5805, 161, PHY_QUADRUPLE_CHANNEL_20MHZ_HIGH_40MHZ_HIGH),
+	CHAN5G(5825, 165, 0)
 };
 
 #define RATE(_bitrate, _hw_rate, _flags) { \
@@ -766,7 +766,16 @@ static void wcn36xx_update_allowed_rates(struct ieee80211_sta *sta,
 		       sta->ht_cap.mcs.rx_mask,
 		       sizeof(sta->ht_cap.mcs.rx_mask));
 	}
+
+	if (sta->vht_cap.vht_supported) {
+		sta_priv->supported_rates.op_rate_mode = STA_11ac;
+		sta_priv->supported_rates.vht_rx_mcs_map =
+				sta->vht_cap.vht_mcs.rx_mcs_map;
+		sta_priv->supported_rates.vht_tx_mcs_map =
+				sta->vht_cap.vht_mcs.tx_mcs_map;
+	}
 }
+
 void wcn36xx_set_default_rates(struct wcn36xx_hal_supported_rates *rates)
 {
 	u16 ofdm_rates[WCN36XX_HAL_NUM_OFDM_RATES] = {
@@ -793,6 +802,14 @@ void wcn36xx_set_default_rates(struct wcn36xx_hal_supported_rates *rates)
 		sizeof(*ofdm_rates) * WCN36XX_HAL_NUM_OFDM_RATES);
 	rates->supported_mcs_set[0] = 0xFF;
 }
+
+void wcn36xx_set_default_rates_v1(struct wcn36xx_hal_supported_rates_v1 *rates)
+{
+	rates->op_rate_mode = STA_11ac;
+	rates->vht_rx_mcs_map = IEEE80211_VHT_MCS_SUPPORT_0_9;
+	rates->vht_tx_mcs_map = IEEE80211_VHT_MCS_SUPPORT_0_9;
+}
+
 static void wcn36xx_bss_info_changed(struct ieee80211_hw *hw,
 				     struct ieee80211_vif *vif,
 				     struct ieee80211_bss_conf *bss_conf,
@@ -1184,6 +1201,35 @@ static const struct ieee80211_ops wcn36xx_ops = {
 	CFG80211_TESTMODE_CMD(wcn36xx_tm_cmd)
 };
 
+static void
+wcn36xx_set_ieee80211_vht_caps(struct ieee80211_sta_vht_cap *vht_cap)
+{
+	vht_cap->vht_supported = true;
+
+	vht_cap->cap = (IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_3895 |
+			IEEE80211_VHT_CAP_SHORT_GI_80 |
+			IEEE80211_VHT_CAP_RXSTBC_1 |
+			IEEE80211_VHT_CAP_SU_BEAMFORMEE_CAPABLE |
+			IEEE80211_VHT_CAP_MU_BEAMFORMEE_CAPABLE |
+			3 << IEEE80211_VHT_CAP_BEAMFORMEE_STS_SHIFT |
+			7 << IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_SHIFT);
+
+	vht_cap->vht_mcs.rx_mcs_map =
+		cpu_to_le16(IEEE80211_VHT_MCS_SUPPORT_0_9 |
+			    IEEE80211_VHT_MCS_NOT_SUPPORTED << 2 |
+			    IEEE80211_VHT_MCS_NOT_SUPPORTED << 4 |
+			    IEEE80211_VHT_MCS_NOT_SUPPORTED << 6 |
+			    IEEE80211_VHT_MCS_NOT_SUPPORTED << 8 |
+			    IEEE80211_VHT_MCS_NOT_SUPPORTED << 10 |
+			    IEEE80211_VHT_MCS_NOT_SUPPORTED << 12 |
+			    IEEE80211_VHT_MCS_NOT_SUPPORTED << 14);
+
+	vht_cap->vht_mcs.rx_highest = cpu_to_le16(433);
+	vht_cap->vht_mcs.tx_highest = vht_cap->vht_mcs.rx_highest;
+
+	vht_cap->vht_mcs.tx_mcs_map = vht_cap->vht_mcs.rx_mcs_map;
+}
+
 static int wcn36xx_init_ieee80211(struct wcn36xx *wcn)
 {
 	static const u32 cipher_suites[] = {
@@ -1210,6 +1256,9 @@ static int wcn36xx_init_ieee80211(struct wcn36xx *wcn)
 	if (wcn->rf_id != RF_IRIS_WCN3620)
 		wcn->hw->wiphy->bands[NL80211_BAND_5GHZ] = &wcn_band_5ghz;
 
+	if (wcn->rf_id == RF_IRIS_WCN3680)
+		wcn36xx_set_ieee80211_vht_caps(&wcn_band_5ghz.vht_cap);
+
 	wcn->hw->wiphy->max_scan_ssids = WCN36XX_MAX_SCAN_SSIDS;
 	wcn->hw->wiphy->max_scan_ie_len = WCN36XX_MAX_SCAN_IE_LEN;
 
diff --git a/drivers/net/wireless/ath/wcn36xx/pmc.c b/drivers/net/wireless/ath/wcn36xx/pmc.c
index 8441031b667c..2d0780fefd47 100644
--- a/drivers/net/wireless/ath/wcn36xx/pmc.c
+++ b/drivers/net/wireless/ath/wcn36xx/pmc.c
@@ -31,6 +31,7 @@ int wcn36xx_pmc_enter_bmps_state(struct wcn36xx *wcn,
 	if (!ret) {
 		wcn36xx_dbg(WCN36XX_DBG_PMC, "Entered BMPS\n");
 		vif_priv->pw_state = WCN36XX_BMPS;
+		vif->driver_flags |= IEEE80211_VIF_BEACON_FILTER;
 	} else {
 		/*
 		 * One of the reasons why HW will not enter BMPS is because
@@ -55,6 +56,7 @@ int wcn36xx_pmc_exit_bmps_state(struct wcn36xx *wcn,
 	}
 	wcn36xx_smd_exit_bmps(wcn, vif);
 	vif_priv->pw_state = WCN36XX_FULL_POWER;
+	vif->driver_flags &= ~IEEE80211_VIF_BEACON_FILTER;
 	return 0;
 }
 
diff --git a/drivers/net/wireless/ath/wcn36xx/smd.c b/drivers/net/wireless/ath/wcn36xx/smd.c
index 4c30036e2e56..766400f7b61c 100644
--- a/drivers/net/wireless/ath/wcn36xx/smd.c
+++ b/drivers/net/wireless/ath/wcn36xx/smd.c
@@ -80,6 +80,102 @@ static struct wcn36xx_cfg_val wcn36xx_cfg_vals[] = {
 	WCN36XX_CFG_VAL(ENABLE_DYNAMIC_RA_START_RATE, 133), /* MCS 5 */
 };
 
+static struct wcn36xx_cfg_val wcn3680_cfg_vals[] = {
+	WCN36XX_CFG_VAL(CURRENT_TX_ANTENNA, 1),
+	WCN36XX_CFG_VAL(CURRENT_RX_ANTENNA, 1),
+	WCN36XX_CFG_VAL(LOW_GAIN_OVERRIDE, 0),
+	WCN36XX_CFG_VAL(POWER_STATE_PER_CHAIN, 785),
+	WCN36XX_CFG_VAL(CAL_PERIOD, 5),
+	WCN36XX_CFG_VAL(CAL_CONTROL, 1),
+	WCN36XX_CFG_VAL(PROXIMITY, 0),
+	WCN36XX_CFG_VAL(NETWORK_DENSITY, 3),
+	WCN36XX_CFG_VAL(MAX_MEDIUM_TIME, 4096),
+	WCN36XX_CFG_VAL(MAX_MPDUS_IN_AMPDU, 64),
+	WCN36XX_CFG_VAL(RTS_THRESHOLD, 2347),
+	WCN36XX_CFG_VAL(SHORT_RETRY_LIMIT, 15),
+	WCN36XX_CFG_VAL(LONG_RETRY_LIMIT, 15),
+	WCN36XX_CFG_VAL(FRAGMENTATION_THRESHOLD, 8000),
+	WCN36XX_CFG_VAL(DYNAMIC_THRESHOLD_ZERO, 5),
+	WCN36XX_CFG_VAL(DYNAMIC_THRESHOLD_ONE, 10),
+	WCN36XX_CFG_VAL(DYNAMIC_THRESHOLD_TWO, 15),
+	WCN36XX_CFG_VAL(FIXED_RATE, 0),
+	WCN36XX_CFG_VAL(RETRYRATE_POLICY, 4),
+	WCN36XX_CFG_VAL(RETRYRATE_SECONDARY, 0),
+	WCN36XX_CFG_VAL(RETRYRATE_TERTIARY, 0),
+	WCN36XX_CFG_VAL(FORCE_POLICY_PROTECTION, 5),
+	WCN36XX_CFG_VAL(FIXED_RATE_MULTICAST_24GHZ, 1),
+	WCN36XX_CFG_VAL(FIXED_RATE_MULTICAST_5GHZ, 5),
+	WCN36XX_CFG_VAL(DEFAULT_RATE_INDEX_24GHZ, 1),
+	WCN36XX_CFG_VAL(DEFAULT_RATE_INDEX_5GHZ, 5),
+	WCN36XX_CFG_VAL(MAX_BA_SESSIONS, 40),
+	WCN36XX_CFG_VAL(PS_DATA_INACTIVITY_TIMEOUT, 200),
+	WCN36XX_CFG_VAL(PS_ENABLE_BCN_FILTER, 1),
+	WCN36XX_CFG_VAL(PS_ENABLE_RSSI_MONITOR, 1),
+	WCN36XX_CFG_VAL(NUM_BEACON_PER_RSSI_AVERAGE, 20),
+	WCN36XX_CFG_VAL(STATS_PERIOD, 10),
+	WCN36XX_CFG_VAL(CFP_MAX_DURATION, 30000),
+	WCN36XX_CFG_VAL(FRAME_TRANS_ENABLED, 0),
+	WCN36XX_CFG_VAL(BA_THRESHOLD_HIGH, 128),
+	WCN36XX_CFG_VAL(MAX_BA_BUFFERS, 2560),
+	WCN36XX_CFG_VAL(DYNAMIC_PS_POLL_VALUE, 0),
+	WCN36XX_CFG_VAL(TX_PWR_CTRL_ENABLE, 1),
+	WCN36XX_CFG_VAL(ENABLE_CLOSE_LOOP, 1),
+	WCN36XX_CFG_VAL(ENABLE_LPWR_IMG_TRANSITION, 0),
+	WCN36XX_CFG_VAL(BTC_STATIC_LEN_LE_BT, 120000),
+	WCN36XX_CFG_VAL(BTC_STATIC_LEN_LE_WLAN, 30000),
+	WCN36XX_CFG_VAL(MAX_ASSOC_LIMIT, 10),
+	WCN36XX_CFG_VAL(ENABLE_MCC_ADAPTIVE_SCHEDULER, 0),
+	WCN36XX_CFG_VAL(TDLS_PUAPSD_MASK, 0),
+	WCN36XX_CFG_VAL(TDLS_PUAPSD_BUFFER_STA_CAPABLE, 1),
+	WCN36XX_CFG_VAL(TDLS_PUAPSD_INACTIVITY_TIME, 0),
+	WCN36XX_CFG_VAL(TDLS_PUAPSD_RX_FRAME_THRESHOLD, 10),
+	WCN36XX_CFG_VAL(TDLS_OFF_CHANNEL_CAPABLE, 1),
+	WCN36XX_CFG_VAL(ENABLE_ADAPTIVE_RX_DRAIN, 1),
+	WCN36XX_CFG_VAL(FLEXCONNECT_POWER_FACTOR, 0),
+	WCN36XX_CFG_VAL(ANTENNA_DIVERSITY, 3),
+	WCN36XX_CFG_VAL(ATH_DISABLE, 0),
+	WCN36XX_CFG_VAL(BTC_STATIC_OPP_WLAN_ACTIVE_WLAN_LEN, 60000),
+	WCN36XX_CFG_VAL(BTC_STATIC_OPP_WLAN_ACTIVE_BT_LEN, 90000),
+	WCN36XX_CFG_VAL(BTC_SAP_STATIC_OPP_ACTIVE_WLAN_LEN, 30000),
+	WCN36XX_CFG_VAL(BTC_SAP_STATIC_OPP_ACTIVE_BT_LEN, 30000),
+	WCN36XX_CFG_VAL(ASD_PROBE_INTERVAL, 50),
+	WCN36XX_CFG_VAL(ASD_TRIGGER_THRESHOLD, -60),
+	WCN36XX_CFG_VAL(ASD_RTT_RSSI_HYST_THRESHOLD, 3),
+	WCN36XX_CFG_VAL(BTC_CTS2S_ON_STA_DURING_SCO, 0),
+	WCN36XX_CFG_VAL(RA_FILTER_ENABLE, 0),
+	WCN36XX_CFG_VAL(RA_RATE_LIMIT_INTERVAL, 60),
+	WCN36XX_CFG_VAL(BTC_FATAL_HID_NSNIFF_BLK, 2),
+	WCN36XX_CFG_VAL(BTC_CRITICAL_HID_NSNIFF_BLK, 1),
+	WCN36XX_CFG_VAL(BTC_DYN_A2DP_TX_QUEUE_THOLD, 0),
+	WCN36XX_CFG_VAL(BTC_DYN_OPP_TX_QUEUE_THOLD, 1),
+	WCN36XX_CFG_VAL(MAX_UAPSD_CONSEC_SP, 10),
+	WCN36XX_CFG_VAL(MAX_UAPSD_CONSEC_RX_CNT, 50),
+	WCN36XX_CFG_VAL(MAX_UAPSD_CONSEC_TX_CNT, 50),
+	WCN36XX_CFG_VAL(MAX_UAPSD_CONSEC_TX_CNT_MEAS_WINDOW, 500),
+	WCN36XX_CFG_VAL(MAX_UAPSD_CONSEC_RX_CNT_MEAS_WINDOW, 500),
+	WCN36XX_CFG_VAL(MAX_PSPOLL_IN_WMM_UAPSD_PS_MODE, 0),
+	WCN36XX_CFG_VAL(MAX_UAPSD_INACTIVITY_INTERVALS, 10),
+	WCN36XX_CFG_VAL(ENABLE_DYNAMIC_WMMPS, 1),
+	WCN36XX_CFG_VAL(BURST_MODE_BE_TXOP_VALUE, 0),
+	WCN36XX_CFG_VAL(ENABLE_DYNAMIC_RA_START_RATE, 136),
+	WCN36XX_CFG_VAL(BTC_FAST_WLAN_CONN_PREF, 1),
+	WCN36XX_CFG_VAL(ENABLE_RTSCTS_HTVHT, 0),
+	WCN36XX_CFG_VAL(BTC_STATIC_OPP_WLAN_IDLE_WLAN_LEN, 30000),
+	WCN36XX_CFG_VAL(BTC_STATIC_OPP_WLAN_IDLE_BT_LEN, 120000),
+	WCN36XX_CFG_VAL(LINK_FAIL_TX_CNT, 200),
+	WCN36XX_CFG_VAL(TOGGLE_ARP_BDRATES, 0),
+	WCN36XX_CFG_VAL(OPTIMIZE_CA_EVENT, 0),
+	WCN36XX_CFG_VAL(EXT_SCAN_CONC_MODE, 0),
+	WCN36XX_CFG_VAL(BAR_WAKEUP_HOST_DISABLE, 0),
+	WCN36XX_CFG_VAL(SAR_BOFFSET_CORRECTION_ENABLE, 0),
+	WCN36XX_CFG_VAL(BTC_DISABLE_WLAN_LINK_CRITICAL, 5),
+	WCN36XX_CFG_VAL(DISABLE_SCAN_DURING_SCO, 2),
+	WCN36XX_CFG_VAL(CONS_BCNMISS_COUNT, 0),
+	WCN36XX_CFG_VAL(UNITS_OF_BCN_WAIT_TIME, 0),
+	WCN36XX_CFG_VAL(TRIGGER_NULLFRAME_BEFORE_HB, 0),
+	WCN36XX_CFG_VAL(ENABLE_POWERSAVE_OFFLOAD, 0),
+};
+
 static int put_cfg_tlv_u32(struct wcn36xx *wcn, size_t *len, u32 id, u32 value)
 {
 	struct wcn36xx_hal_cfg *entry;
@@ -122,6 +218,7 @@ static inline u8 is_cap_supported(unsigned long caps, unsigned long flag)
 {
 	return caps & flag ? 1 : 0;
 }
+
 static void wcn36xx_smd_set_bss_ht_params(struct ieee80211_vif *vif,
 		struct ieee80211_sta *sta,
 		struct wcn36xx_hal_config_bss_params *bss_params)
@@ -146,6 +243,15 @@ static void wcn36xx_smd_set_bss_ht_params(struct ieee80211_vif *vif,
 	}
 }
 
+static void
+wcn36xx_smd_set_bss_vht_params(struct ieee80211_vif *vif,
+			       struct ieee80211_sta *sta,
+			       struct wcn36xx_hal_config_bss_params_v1 *bss)
+{
+	if (sta && sta->vht_cap.vht_supported)
+		bss->vht_capable = 1;
+}
+
 static void wcn36xx_smd_set_sta_ht_params(struct ieee80211_sta *sta,
 		struct wcn36xx_hal_config_sta_params *sta_params)
 {
@@ -174,6 +280,37 @@ static void wcn36xx_smd_set_sta_ht_params(struct ieee80211_sta *sta,
 	}
 }
 
+static void wcn36xx_smd_set_sta_vht_params(struct wcn36xx *wcn,
+		struct ieee80211_sta *sta,
+		struct wcn36xx_hal_config_sta_params_v1 *sta_params)
+{
+	if (sta->vht_cap.vht_supported) {
+		unsigned long caps = sta->vht_cap.cap;
+
+		sta_params->vht_capable = sta->vht_cap.vht_supported;
+		sta_params->vht_ldpc_enabled =
+			is_cap_supported(caps, IEEE80211_VHT_CAP_RXLDPC);
+		if (get_feat_caps(wcn->fw_feat_caps, MU_MIMO)) {
+			sta_params->vht_tx_mu_beamformee_capable =
+				is_cap_supported(caps, IEEE80211_VHT_CAP_MU_BEAMFORMER_CAPABLE);
+			if (sta_params->vht_tx_mu_beamformee_capable)
+			       sta_params->vht_tx_bf_enabled = 1;
+		} else {
+			sta_params->vht_tx_mu_beamformee_capable = 0;
+		}
+		sta_params->vht_tx_channel_width_set = 0;
+	}
+}
+
+static void wcn36xx_smd_set_sta_ht_ldpc_params(struct ieee80211_sta *sta,
+		struct wcn36xx_hal_config_sta_params_v1 *sta_params)
+{
+	if (sta->ht_cap.ht_supported) {
+		sta_params->ht_ldpc_enabled =
+			is_cap_supported(sta->ht_cap.cap, IEEE80211_HT_CAP_LDPC_CODING);
+	}
+}
+
 static void wcn36xx_smd_set_sta_default_ht_params(
 		struct wcn36xx_hal_config_sta_params *sta_params)
 {
@@ -190,6 +327,31 @@ static void wcn36xx_smd_set_sta_default_ht_params(
 	sta_params->dsss_cck_mode_40mhz = 1;
 }
 
+static void wcn36xx_smd_set_sta_default_vht_params(struct wcn36xx *wcn,
+		struct wcn36xx_hal_config_sta_params_v1 *sta_params)
+{
+	if (wcn->rf_id == RF_IRIS_WCN3680) {
+		sta_params->vht_capable = 1;
+		sta_params->vht_tx_mu_beamformee_capable = 1;
+	} else {
+		sta_params->vht_capable = 0;
+		sta_params->vht_tx_mu_beamformee_capable = 0;
+	}
+
+	sta_params->vht_ldpc_enabled = 0;
+	sta_params->vht_tx_channel_width_set = 0;
+	sta_params->vht_tx_bf_enabled = 0;
+}
+
+static void wcn36xx_smd_set_sta_default_ht_ldpc_params(struct wcn36xx *wcn,
+		struct wcn36xx_hal_config_sta_params_v1 *sta_params)
+{
+	if (wcn->rf_id == RF_IRIS_WCN3680)
+		sta_params->ht_ldpc_enabled = 1;
+	else
+		sta_params->ht_ldpc_enabled = 0;
+}
+
 static void wcn36xx_smd_set_sta_params(struct wcn36xx *wcn,
 		struct ieee80211_vif *vif,
 		struct ieee80211_sta *sta,
@@ -242,9 +404,10 @@ static void wcn36xx_smd_set_sta_params(struct wcn36xx *wcn,
 		sta_params->aid = sta_priv->aid;
 		wcn36xx_smd_set_sta_ht_params(sta, sta_params);
 		memcpy(&sta_params->supported_rates, &sta_priv->supported_rates,
-			sizeof(sta_priv->supported_rates));
+			sizeof(struct wcn36xx_hal_supported_rates));
 	} else {
-		wcn36xx_set_default_rates(&sta_params->supported_rates);
+		wcn36xx_set_default_rates((struct wcn36xx_hal_supported_rates *)
+					  &sta_params->supported_rates);
 		wcn36xx_smd_set_sta_default_ht_params(sta_params);
 	}
 }
@@ -291,14 +454,20 @@ static void init_hal_msg(struct wcn36xx_hal_msg_header *hdr,
 	hdr->len = msg_size + sizeof(*hdr);
 }
 
-#define INIT_HAL_MSG(msg_body, type) \
+#define __INIT_HAL_MSG(msg_body, type, version) \
 	do {								\
 		memset(&msg_body, 0, sizeof(msg_body));			\
 		msg_body.header.msg_type = type;			\
-		msg_body.header.msg_version = WCN36XX_HAL_MSG_VERSION0; \
+		msg_body.header.msg_version = version;			\
 		msg_body.header.len = sizeof(msg_body);			\
 	} while (0)							\
 
+#define INIT_HAL_MSG(msg_body, type)	\
+	__INIT_HAL_MSG(msg_body, type, WCN36XX_HAL_MSG_VERSION0)
+
+#define INIT_HAL_MSG_V1(msg_body, type) \
+	__INIT_HAL_MSG(msg_body, type, WCN36XX_HAL_MSG_VERSION1)
+
 #define INIT_HAL_PTT_MSG(p_msg_body, ppt_msg_len) \
 	do { \
 		memset(p_msg_body, 0, sizeof(*p_msg_body) + ppt_msg_len); \
@@ -450,6 +619,8 @@ int wcn36xx_smd_start(struct wcn36xx *wcn)
 	int ret;
 	int i;
 	size_t len;
+	int cfg_elements;
+	static struct wcn36xx_cfg_val *cfg_vals;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg_body, WCN36XX_HAL_START_REQ);
@@ -462,9 +633,17 @@ int wcn36xx_smd_start(struct wcn36xx *wcn)
 	body = (struct wcn36xx_hal_mac_start_req_msg *)wcn->hal_buf;
 	len = body->header.len;
 
-	for (i = 0; i < ARRAY_SIZE(wcn36xx_cfg_vals); i++) {
-		ret = put_cfg_tlv_u32(wcn, &len, wcn36xx_cfg_vals[i].cfg_id,
-				      wcn36xx_cfg_vals[i].value);
+	if (wcn->rf_id == RF_IRIS_WCN3680) {
+		cfg_vals = wcn3680_cfg_vals;
+		cfg_elements = ARRAY_SIZE(wcn3680_cfg_vals);
+	} else {
+		cfg_vals = wcn36xx_cfg_vals;
+		cfg_elements = ARRAY_SIZE(wcn36xx_cfg_vals);
+	}
+
+	for (i = 0; i < cfg_elements; i++) {
+		ret = put_cfg_tlv_u32(wcn, &len, cfg_vals[i].cfg_id,
+				      cfg_vals[i].value);
 		if (ret)
 			goto out;
 	}
@@ -694,8 +873,10 @@ int wcn36xx_smd_start_hw_scan(struct wcn36xx *wcn, struct ieee80211_vif *vif,
 
 	msg_body->num_channel = min_t(u8, req->n_channels,
 				     sizeof(msg_body->channels));
-	for (i = 0; i < msg_body->num_channel; i++)
-		msg_body->channels[i] = req->channels[i]->hw_value;
+	for (i = 0; i < msg_body->num_channel; i++) {
+		msg_body->channels[i] =
+			HW_VALUE_CHANNEL(req->channels[i]->hw_value);
+	}
 
 	msg_body->header.len -= WCN36XX_MAX_SCAN_IE_LEN;
 
@@ -1183,6 +1364,31 @@ static void wcn36xx_smd_convert_sta_to_v1(struct wcn36xx *wcn,
 	v1->p2p = orig->p2p;
 }
 
+static void
+wcn36xx_smd_set_sta_params_v1(struct wcn36xx *wcn,
+			      struct ieee80211_vif *vif,
+			      struct ieee80211_sta *sta,
+			      struct wcn36xx_hal_config_sta_params_v1 *sta_par)
+{
+	struct wcn36xx_sta *sta_priv = NULL;
+	struct wcn36xx_hal_config_sta_params sta_par_v0;
+
+	wcn36xx_smd_set_sta_params(wcn, vif, sta, &sta_par_v0);
+	wcn36xx_smd_convert_sta_to_v1(wcn, &sta_par_v0, sta_par);
+
+	if (sta) {
+		sta_priv = wcn36xx_sta_to_priv(sta);
+		wcn36xx_smd_set_sta_vht_params(wcn, sta, sta_par);
+		wcn36xx_smd_set_sta_ht_ldpc_params(sta, sta_par);
+		memcpy(&sta_par->supported_rates, &sta_priv->supported_rates,
+		       sizeof(sta_par->supported_rates));
+	} else {
+		wcn36xx_set_default_rates_v1(&sta_par->supported_rates);
+		wcn36xx_smd_set_sta_default_vht_params(wcn, sta_par);
+		wcn36xx_smd_set_sta_default_ht_ldpc_params(wcn, sta_par);
+	}
+}
+
 static int wcn36xx_smd_config_sta_rsp(struct wcn36xx *wcn,
 				      struct ieee80211_sta *sta,
 				      void *buf,
@@ -1217,53 +1423,69 @@ static int wcn36xx_smd_config_sta_rsp(struct wcn36xx *wcn,
 }
 
 static int wcn36xx_smd_config_sta_v1(struct wcn36xx *wcn,
-		     const struct wcn36xx_hal_config_sta_req_msg *orig)
+				     struct ieee80211_vif *vif,
+				     struct ieee80211_sta *sta)
 {
 	struct wcn36xx_hal_config_sta_req_msg_v1 msg_body;
-	struct wcn36xx_hal_config_sta_params_v1 *sta = &msg_body.sta_params;
+	struct wcn36xx_hal_config_sta_params_v1 *sta_params;
 
-	INIT_HAL_MSG(msg_body, WCN36XX_HAL_CONFIG_STA_REQ);
+	if (wcn->rf_id == RF_IRIS_WCN3680) {
+		INIT_HAL_MSG_V1(msg_body, WCN36XX_HAL_CONFIG_STA_REQ);
+	} else {
+		INIT_HAL_MSG(msg_body, WCN36XX_HAL_CONFIG_STA_REQ);
+		msg_body.header.len -= WCN36XX_DIFF_STA_PARAMS_V1_NOVHT;
+	}
+
+	sta_params = &msg_body.sta_params;
 
-	wcn36xx_smd_convert_sta_to_v1(wcn, &orig->sta_params,
-				      &msg_body.sta_params);
+	wcn36xx_smd_set_sta_params_v1(wcn, vif, sta, sta_params);
 
 	PREPARE_HAL_BUF(wcn->hal_buf, msg_body);
 
 	wcn36xx_dbg(WCN36XX_DBG_HAL,
 		    "hal config sta v1 action %d sta_index %d bssid_index %d bssid %pM type %d mac %pM aid %d\n",
-		    sta->action, sta->sta_index, sta->bssid_index,
-		    sta->bssid, sta->type, sta->mac, sta->aid);
+		    sta_params->action, sta_params->sta_index, sta_params->bssid_index,
+		    sta_params->bssid, sta_params->type, sta_params->mac, sta_params->aid);
 
 	return wcn36xx_smd_send_and_wait(wcn, msg_body.header.len);
 }
 
-int wcn36xx_smd_config_sta(struct wcn36xx *wcn, struct ieee80211_vif *vif,
-			   struct ieee80211_sta *sta)
+static int wcn36xx_smd_config_sta_v0(struct wcn36xx *wcn,
+				     struct ieee80211_vif *vif,
+				     struct ieee80211_sta *sta)
 {
 	struct wcn36xx_hal_config_sta_req_msg msg;
 	struct wcn36xx_hal_config_sta_params *sta_params;
-	int ret;
 
-	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg, WCN36XX_HAL_CONFIG_STA_REQ);
 
 	sta_params = &msg.sta_params;
 
 	wcn36xx_smd_set_sta_params(wcn, vif, sta, sta_params);
 
-	if (!wcn36xx_is_fw_version(wcn, 1, 2, 2, 24)) {
-		ret = wcn36xx_smd_config_sta_v1(wcn, &msg);
-	} else {
-		PREPARE_HAL_BUF(wcn->hal_buf, msg);
+	PREPARE_HAL_BUF(wcn->hal_buf, msg);
 
-		wcn36xx_dbg(WCN36XX_DBG_HAL,
-			    "hal config sta action %d sta_index %d bssid_index %d bssid %pM type %d mac %pM aid %d\n",
-			    sta_params->action, sta_params->sta_index,
-			    sta_params->bssid_index, sta_params->bssid,
-			    sta_params->type, sta_params->mac, sta_params->aid);
+	wcn36xx_dbg(WCN36XX_DBG_HAL,
+		    "hal config sta action %d sta_index %d bssid_index %d bssid %pM type %d mac %pM aid %d\n",
+		    sta_params->action, sta_params->sta_index,
+		    sta_params->bssid_index, sta_params->bssid,
+		    sta_params->type, sta_params->mac, sta_params->aid);
+
+	return wcn36xx_smd_send_and_wait(wcn, msg.header.len);
+}
+
+int wcn36xx_smd_config_sta(struct wcn36xx *wcn, struct ieee80211_vif *vif,
+			   struct ieee80211_sta *sta)
+{
+	int ret;
+
+	mutex_lock(&wcn->hal_mutex);
+
+	if (!wcn36xx_is_fw_version(wcn, 1, 2, 2, 24))
+		ret = wcn36xx_smd_config_sta_v1(wcn, vif, sta);
+	else
+		ret = wcn36xx_smd_config_sta_v0(wcn, vif, sta);
 
-		ret = wcn36xx_smd_send_and_wait(wcn, msg.header.len);
-	}
 	if (ret) {
 		wcn36xx_err("Sending hal_config_sta failed\n");
 		goto out;
@@ -1281,89 +1503,197 @@ out:
 	return ret;
 }
 
+static void wcn36xx_smd_set_bss_params(struct wcn36xx *wcn,
+				       struct ieee80211_vif *vif,
+				       struct ieee80211_sta *sta,
+				       const u8 *bssid,
+				       bool update,
+				       struct wcn36xx_hal_config_bss_params *bss)
+{
+	struct wcn36xx_vif *vif_priv = wcn36xx_vif_to_priv(vif);
+
+	WARN_ON(is_zero_ether_addr(bssid));
+
+	memcpy(&bss->bssid, bssid, ETH_ALEN);
+
+	memcpy(bss->self_mac_addr, vif->addr, ETH_ALEN);
+
+	if (vif->type == NL80211_IFTYPE_STATION) {
+		bss->bss_type = WCN36XX_HAL_INFRASTRUCTURE_MODE;
+
+		/* STA */
+		bss->oper_mode = 1;
+		bss->wcn36xx_hal_persona = WCN36XX_HAL_STA_MODE;
+	} else if (vif->type == NL80211_IFTYPE_AP ||
+		   vif->type == NL80211_IFTYPE_MESH_POINT) {
+		bss->bss_type = WCN36XX_HAL_INFRA_AP_MODE;
+
+		/* AP */
+		bss->oper_mode = 0;
+		bss->wcn36xx_hal_persona = WCN36XX_HAL_STA_SAP_MODE;
+	} else if (vif->type == NL80211_IFTYPE_ADHOC) {
+		bss->bss_type = WCN36XX_HAL_IBSS_MODE;
+
+		/* STA */
+		bss->oper_mode = 1;
+	} else {
+		wcn36xx_warn("Unknown type for bss config: %d\n", vif->type);
+	}
+
+	if (vif->type == NL80211_IFTYPE_STATION)
+		wcn36xx_smd_set_bss_nw_type(wcn, sta, bss);
+	else
+		bss->nw_type = WCN36XX_HAL_11N_NW_TYPE;
+
+	bss->short_slot_time_supported = vif->bss_conf.use_short_slot;
+	bss->lla_coexist = 0;
+	bss->llb_coexist = 0;
+	bss->llg_coexist = 0;
+	bss->rifs_mode = 0;
+	bss->beacon_interval = vif->bss_conf.beacon_int;
+	bss->dtim_period = vif_priv->dtim_period;
+
+	wcn36xx_smd_set_bss_ht_params(vif, sta, bss);
+
+	bss->oper_channel = WCN36XX_HW_CHANNEL(wcn);
+
+	if (conf_is_ht40_minus(&wcn->hw->conf))
+		bss->ext_channel = IEEE80211_HT_PARAM_CHA_SEC_BELOW;
+	else if (conf_is_ht40_plus(&wcn->hw->conf))
+		bss->ext_channel = IEEE80211_HT_PARAM_CHA_SEC_ABOVE;
+	else
+		bss->ext_channel = IEEE80211_HT_PARAM_CHA_SEC_NONE;
+
+	bss->reserved = 0;
+
+	/* wcn->ssid is only valid in AP and IBSS mode */
+	bss->ssid.length = vif_priv->ssid.length;
+	memcpy(bss->ssid.ssid, vif_priv->ssid.ssid, vif_priv->ssid.length);
+
+	bss->obss_prot_enabled = 0;
+	bss->rmf = 0;
+	bss->max_probe_resp_retry_limit = 0;
+	bss->hidden_ssid = vif->bss_conf.hidden_ssid;
+	bss->proxy_probe_resp = 0;
+	bss->edca_params_valid = 0;
+
+	/* FIXME: set acbe, acbk, acvi and acvo */
+
+	bss->ext_set_sta_key_param_valid = 0;
+
+	/* FIXME: set ext_set_sta_key_param */
+
+	bss->spectrum_mgt_enable = 0;
+	bss->tx_mgmt_power = 0;
+	bss->max_tx_power = WCN36XX_MAX_POWER(wcn);
+	bss->action = update;
+
+	vif_priv->bss_type = bss->bss_type;
+}
+
 static int wcn36xx_smd_config_bss_v1(struct wcn36xx *wcn,
-			const struct wcn36xx_hal_config_bss_req_msg *orig)
+				     struct ieee80211_vif *vif,
+				     struct ieee80211_sta *sta_80211,
+				     const u8 *bssid,
+				     bool update)
 {
 	struct wcn36xx_hal_config_bss_req_msg_v1 *msg_body;
 	struct wcn36xx_hal_config_bss_params_v1 *bss;
+	struct wcn36xx_hal_config_bss_params bss_v0;
 	struct wcn36xx_hal_config_sta_params_v1 *sta;
+	struct cfg80211_chan_def *chandef;
 	int ret;
 
 	msg_body = kzalloc(sizeof(*msg_body), GFP_KERNEL);
 	if (!msg_body)
 		return -ENOMEM;
 
-	INIT_HAL_MSG((*msg_body), WCN36XX_HAL_CONFIG_BSS_REQ);
+	if (wcn->rf_id == RF_IRIS_WCN3680) {
+		INIT_HAL_MSG_V1((*msg_body), WCN36XX_HAL_CONFIG_BSS_REQ);
+	} else {
+		INIT_HAL_MSG((*msg_body), WCN36XX_HAL_CONFIG_BSS_REQ);
+		msg_body->header.len -= WCN36XX_DIFF_BSS_PARAMS_V1_NOVHT;
+	}
 
 	bss = &msg_body->bss_params;
 	sta = &bss->sta;
 
+	memset(&bss_v0, 0x00, sizeof(bss_v0));
+	wcn36xx_smd_set_bss_params(wcn, vif, sta_80211, bssid, update, &bss_v0);
+	wcn36xx_smd_set_sta_params_v1(wcn, vif, sta_80211, sta);
+
 	/* convert orig to v1 */
-	memcpy(bss->bssid, &orig->bss_params.bssid, ETH_ALEN);
-	memcpy(bss->self_mac_addr, &orig->bss_params.self_mac_addr, ETH_ALEN);
+	memcpy(bss->bssid, &bss_v0.bssid, ETH_ALEN);
+	memcpy(bss->self_mac_addr, &bss_v0.self_mac_addr, ETH_ALEN);
 
-	bss->bss_type = orig->bss_params.bss_type;
-	bss->oper_mode = orig->bss_params.oper_mode;
-	bss->nw_type = orig->bss_params.nw_type;
+	bss->bss_type = bss_v0.bss_type;
+	bss->oper_mode = bss_v0.oper_mode;
+	bss->nw_type = bss_v0.nw_type;
 
 	bss->short_slot_time_supported =
-		orig->bss_params.short_slot_time_supported;
-	bss->lla_coexist = orig->bss_params.lla_coexist;
-	bss->llb_coexist = orig->bss_params.llb_coexist;
-	bss->llg_coexist = orig->bss_params.llg_coexist;
-	bss->ht20_coexist = orig->bss_params.ht20_coexist;
-	bss->lln_non_gf_coexist = orig->bss_params.lln_non_gf_coexist;
+		bss_v0.short_slot_time_supported;
+	bss->lla_coexist = bss_v0.lla_coexist;
+	bss->llb_coexist = bss_v0.llb_coexist;
+	bss->llg_coexist = bss_v0.llg_coexist;
+	bss->ht20_coexist = bss_v0.ht20_coexist;
+	bss->lln_non_gf_coexist = bss_v0.lln_non_gf_coexist;
 
 	bss->lsig_tx_op_protection_full_support =
-		orig->bss_params.lsig_tx_op_protection_full_support;
-	bss->rifs_mode = orig->bss_params.rifs_mode;
-	bss->beacon_interval = orig->bss_params.beacon_interval;
-	bss->dtim_period = orig->bss_params.dtim_period;
-	bss->tx_channel_width_set = orig->bss_params.tx_channel_width_set;
-	bss->oper_channel = orig->bss_params.oper_channel;
-	bss->ext_channel = orig->bss_params.ext_channel;
-
-	bss->reserved = orig->bss_params.reserved;
-
-	memcpy(&bss->ssid, &orig->bss_params.ssid,
-	       sizeof(orig->bss_params.ssid));
-
-	bss->action = orig->bss_params.action;
-	bss->rateset = orig->bss_params.rateset;
-	bss->ht = orig->bss_params.ht;
-	bss->obss_prot_enabled = orig->bss_params.obss_prot_enabled;
-	bss->rmf = orig->bss_params.rmf;
-	bss->ht_oper_mode = orig->bss_params.ht_oper_mode;
-	bss->dual_cts_protection = orig->bss_params.dual_cts_protection;
+		bss_v0.lsig_tx_op_protection_full_support;
+	bss->rifs_mode = bss_v0.rifs_mode;
+	bss->beacon_interval = bss_v0.beacon_interval;
+	bss->dtim_period = bss_v0.dtim_period;
+	bss->tx_channel_width_set = bss_v0.tx_channel_width_set;
+	bss->oper_channel = bss_v0.oper_channel;
+
+	if (wcn->hw->conf.chandef.width == NL80211_CHAN_WIDTH_80) {
+		chandef = &wcn->hw->conf.chandef;
+		bss->ext_channel = HW_VALUE_PHY(chandef->chan->hw_value);
+	} else {
+		bss->ext_channel = bss_v0.ext_channel;
+	}
+
+	bss->reserved = bss_v0.reserved;
+
+	memcpy(&bss->ssid, &bss_v0.ssid,
+	       sizeof(bss_v0.ssid));
+
+	bss->action = bss_v0.action;
+	bss->rateset = bss_v0.rateset;
+	bss->ht = bss_v0.ht;
+	bss->obss_prot_enabled = bss_v0.obss_prot_enabled;
+	bss->rmf = bss_v0.rmf;
+	bss->ht_oper_mode = bss_v0.ht_oper_mode;
+	bss->dual_cts_protection = bss_v0.dual_cts_protection;
 
 	bss->max_probe_resp_retry_limit =
-		orig->bss_params.max_probe_resp_retry_limit;
-	bss->hidden_ssid = orig->bss_params.hidden_ssid;
-	bss->proxy_probe_resp =	orig->bss_params.proxy_probe_resp;
-	bss->edca_params_valid = orig->bss_params.edca_params_valid;
-
-	memcpy(&bss->acbe, &orig->bss_params.acbe,
-	       sizeof(orig->bss_params.acbe));
-	memcpy(&bss->acbk, &orig->bss_params.acbk,
-	       sizeof(orig->bss_params.acbk));
-	memcpy(&bss->acvi, &orig->bss_params.acvi,
-	       sizeof(orig->bss_params.acvi));
-	memcpy(&bss->acvo, &orig->bss_params.acvo,
-	       sizeof(orig->bss_params.acvo));
+		bss_v0.max_probe_resp_retry_limit;
+	bss->hidden_ssid = bss_v0.hidden_ssid;
+	bss->proxy_probe_resp =	bss_v0.proxy_probe_resp;
+	bss->edca_params_valid = bss_v0.edca_params_valid;
+
+	memcpy(&bss->acbe, &bss_v0.acbe,
+	       sizeof(bss_v0.acbe));
+	memcpy(&bss->acbk, &bss_v0.acbk,
+	       sizeof(bss_v0.acbk));
+	memcpy(&bss->acvi, &bss_v0.acvi,
+	       sizeof(bss_v0.acvi));
+	memcpy(&bss->acvo, &bss_v0.acvo,
+	       sizeof(bss_v0.acvo));
 
 	bss->ext_set_sta_key_param_valid =
-		orig->bss_params.ext_set_sta_key_param_valid;
+		bss_v0.ext_set_sta_key_param_valid;
 
 	memcpy(&bss->ext_set_sta_key_param,
-	       &orig->bss_params.ext_set_sta_key_param,
-	       sizeof(orig->bss_params.acvo));
+	       &bss_v0.ext_set_sta_key_param,
+	       sizeof(bss_v0.acvo));
 
-	bss->wcn36xx_hal_persona = orig->bss_params.wcn36xx_hal_persona;
-	bss->spectrum_mgt_enable = orig->bss_params.spectrum_mgt_enable;
-	bss->tx_mgmt_power = orig->bss_params.tx_mgmt_power;
-	bss->max_tx_power = orig->bss_params.max_tx_power;
+	bss->wcn36xx_hal_persona = bss_v0.wcn36xx_hal_persona;
+	bss->spectrum_mgt_enable = bss_v0.spectrum_mgt_enable;
+	bss->tx_mgmt_power = bss_v0.tx_mgmt_power;
+	bss->max_tx_power = bss_v0.max_tx_power;
 
-	wcn36xx_smd_convert_sta_to_v1(wcn, &orig->bss_params.sta, sta);
+	wcn36xx_smd_set_bss_vht_params(vif, sta_80211, bss);
 
 	PREPARE_HAL_BUF(wcn->hal_buf, (*msg_body));
 
@@ -1383,6 +1713,48 @@ static int wcn36xx_smd_config_bss_v1(struct wcn36xx *wcn,
 	return ret;
 }
 
+static int wcn36xx_smd_config_bss_v0(struct wcn36xx *wcn,
+				     struct ieee80211_vif *vif,
+				     struct ieee80211_sta *sta,
+				     const u8 *bssid,
+				     bool update)
+{
+	struct wcn36xx_hal_config_bss_req_msg *msg;
+	struct wcn36xx_hal_config_bss_params *bss;
+	struct wcn36xx_hal_config_sta_params *sta_params;
+	int ret;
+
+	msg = kzalloc(sizeof(*msg), GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	INIT_HAL_MSG((*msg), WCN36XX_HAL_CONFIG_BSS_REQ);
+
+	bss = &msg->bss_params;
+	sta_params = &bss->sta;
+
+	wcn36xx_smd_set_bss_params(wcn, vif, sta, bssid, update, bss);
+	wcn36xx_smd_set_sta_params(wcn, vif, sta, sta_params);
+
+	PREPARE_HAL_BUF(wcn->hal_buf, (*msg));
+
+	wcn36xx_dbg(WCN36XX_DBG_HAL,
+		    "hal config bss bssid %pM self_mac_addr %pM bss_type %d oper_mode %d nw_type %d\n",
+		    bss->bssid, bss->self_mac_addr, bss->bss_type,
+		    bss->oper_mode, bss->nw_type);
+
+	wcn36xx_dbg(WCN36XX_DBG_HAL,
+		    "- sta bssid %pM action %d sta_index %d bssid_index %d aid %d type %d mac %pM\n",
+		    sta_params->bssid, sta_params->action,
+		    sta_params->sta_index, sta_params->bssid_index,
+		    sta_params->aid, sta_params->type,
+		    sta_params->mac);
+
+	ret = wcn36xx_smd_send_and_wait(wcn, msg->header.len);
+	kfree(msg);
+
+	return ret;
+}
 
 static int wcn36xx_smd_config_bss_rsp(struct wcn36xx *wcn,
 				      struct ieee80211_vif *vif,
@@ -1432,121 +1804,15 @@ int wcn36xx_smd_config_bss(struct wcn36xx *wcn, struct ieee80211_vif *vif,
 			   struct ieee80211_sta *sta, const u8 *bssid,
 			   bool update)
 {
-	struct wcn36xx_hal_config_bss_req_msg *msg;
-	struct wcn36xx_hal_config_bss_params *bss;
-	struct wcn36xx_hal_config_sta_params *sta_params;
-	struct wcn36xx_vif *vif_priv = wcn36xx_vif_to_priv(vif);
 	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
-	msg = kzalloc(sizeof(*msg), GFP_KERNEL);
-	if (!msg) {
-		ret = -ENOMEM;
-		goto out;
-	}
-	INIT_HAL_MSG((*msg), WCN36XX_HAL_CONFIG_BSS_REQ);
-
-	bss = &msg->bss_params;
-	sta_params = &bss->sta;
-
-	WARN_ON(is_zero_ether_addr(bssid));
-
-	memcpy(&bss->bssid, bssid, ETH_ALEN);
-
-	memcpy(bss->self_mac_addr, vif->addr, ETH_ALEN);
-
-	if (vif->type == NL80211_IFTYPE_STATION) {
-		bss->bss_type = WCN36XX_HAL_INFRASTRUCTURE_MODE;
-
-		/* STA */
-		bss->oper_mode = 1;
-		bss->wcn36xx_hal_persona = WCN36XX_HAL_STA_MODE;
-	} else if (vif->type == NL80211_IFTYPE_AP ||
-		   vif->type == NL80211_IFTYPE_MESH_POINT) {
-		bss->bss_type = WCN36XX_HAL_INFRA_AP_MODE;
-
-		/* AP */
-		bss->oper_mode = 0;
-		bss->wcn36xx_hal_persona = WCN36XX_HAL_STA_SAP_MODE;
-	} else if (vif->type == NL80211_IFTYPE_ADHOC) {
-		bss->bss_type = WCN36XX_HAL_IBSS_MODE;
-
-		/* STA */
-		bss->oper_mode = 1;
-	} else {
-		wcn36xx_warn("Unknown type for bss config: %d\n", vif->type);
-	}
 
-	if (vif->type == NL80211_IFTYPE_STATION)
-		wcn36xx_smd_set_bss_nw_type(wcn, sta, bss);
+	if (!wcn36xx_is_fw_version(wcn, 1, 2, 2, 24))
+		ret = wcn36xx_smd_config_bss_v1(wcn, vif, sta, bssid, update);
 	else
-		bss->nw_type = WCN36XX_HAL_11N_NW_TYPE;
-
-	bss->short_slot_time_supported = vif->bss_conf.use_short_slot;
-	bss->lla_coexist = 0;
-	bss->llb_coexist = 0;
-	bss->llg_coexist = 0;
-	bss->rifs_mode = 0;
-	bss->beacon_interval = vif->bss_conf.beacon_int;
-	bss->dtim_period = vif_priv->dtim_period;
-
-	wcn36xx_smd_set_bss_ht_params(vif, sta, bss);
-
-	bss->oper_channel = WCN36XX_HW_CHANNEL(wcn);
-
-	if (conf_is_ht40_minus(&wcn->hw->conf))
-		bss->ext_channel = IEEE80211_HT_PARAM_CHA_SEC_BELOW;
-	else if (conf_is_ht40_plus(&wcn->hw->conf))
-		bss->ext_channel = IEEE80211_HT_PARAM_CHA_SEC_ABOVE;
-	else
-		bss->ext_channel = IEEE80211_HT_PARAM_CHA_SEC_NONE;
-
-	bss->reserved = 0;
-	wcn36xx_smd_set_sta_params(wcn, vif, sta, sta_params);
-
-	/* wcn->ssid is only valid in AP and IBSS mode */
-	bss->ssid.length = vif_priv->ssid.length;
-	memcpy(bss->ssid.ssid, vif_priv->ssid.ssid, vif_priv->ssid.length);
-
-	bss->obss_prot_enabled = 0;
-	bss->rmf = 0;
-	bss->max_probe_resp_retry_limit = 0;
-	bss->hidden_ssid = vif->bss_conf.hidden_ssid;
-	bss->proxy_probe_resp = 0;
-	bss->edca_params_valid = 0;
-
-	/* FIXME: set acbe, acbk, acvi and acvo */
-
-	bss->ext_set_sta_key_param_valid = 0;
-
-	/* FIXME: set ext_set_sta_key_param */
-
-	bss->spectrum_mgt_enable = 0;
-	bss->tx_mgmt_power = 0;
-	bss->max_tx_power = WCN36XX_MAX_POWER(wcn);
-	bss->action = update;
+		ret = wcn36xx_smd_config_bss_v0(wcn, vif, sta, bssid, update);
 
-	vif_priv->bss_type = bss->bss_type;
-
-	wcn36xx_dbg(WCN36XX_DBG_HAL,
-		    "hal config bss bssid %pM self_mac_addr %pM bss_type %d oper_mode %d nw_type %d\n",
-		    bss->bssid, bss->self_mac_addr, bss->bss_type,
-		    bss->oper_mode, bss->nw_type);
-
-	wcn36xx_dbg(WCN36XX_DBG_HAL,
-		    "- sta bssid %pM action %d sta_index %d bssid_index %d aid %d type %d mac %pM\n",
-		    sta_params->bssid, sta_params->action,
-		    sta_params->sta_index, sta_params->bssid_index,
-		    sta_params->aid, sta_params->type,
-		    sta_params->mac);
-
-	if (!wcn36xx_is_fw_version(wcn, 1, 2, 2, 24)) {
-		ret = wcn36xx_smd_config_bss_v1(wcn, msg);
-	} else {
-		PREPARE_HAL_BUF(wcn->hal_buf, (*msg));
-
-		ret = wcn36xx_smd_send_and_wait(wcn, msg->header.len);
-	}
 	if (ret) {
 		wcn36xx_err("Sending hal_config_bss failed\n");
 		goto out;
@@ -1556,12 +1822,10 @@ int wcn36xx_smd_config_bss(struct wcn36xx *wcn, struct ieee80211_vif *vif,
 					 sta,
 					 wcn->hal_buf,
 					 wcn->hal_rsp_len);
-	if (ret) {
+	if (ret)
 		wcn36xx_err("hal_config_bss response failed err=%d\n", ret);
-		goto out;
-	}
+
 out:
-	kfree(msg);
 	mutex_unlock(&wcn->hal_mutex);
 	return ret;
 }
@@ -1928,6 +2192,7 @@ out:
 	mutex_unlock(&wcn->hal_mutex);
 	return ret;
 }
+
 int wcn36xx_smd_set_power_params(struct wcn36xx *wcn, bool ignore_dtim)
 {
 	struct wcn36xx_hal_set_power_params_req_msg msg_body;
@@ -1957,6 +2222,7 @@ out:
 	mutex_unlock(&wcn->hal_mutex);
 	return ret;
 }
+
 /* Notice: This function should be called after associated, or else it
  * will be invalid
  */
@@ -2636,6 +2902,7 @@ static void wcn36xx_ind_smd_work(struct work_struct *work)
 		kfree(hal_ind_msg);
 	}
 }
+
 int wcn36xx_smd_open(struct wcn36xx *wcn)
 {
 	wcn->hal_ind_wq = create_freezable_workqueue("wcn36xx_smd_ind");
diff --git a/drivers/net/wireless/ath/wcn36xx/wcn36xx.h b/drivers/net/wireless/ath/wcn36xx/wcn36xx.h
index 342ca0ae7e28..71fa9992b118 100644
--- a/drivers/net/wireless/ath/wcn36xx/wcn36xx.h
+++ b/drivers/net/wireless/ath/wcn36xx/wcn36xx.h
@@ -83,7 +83,11 @@ enum wcn36xx_ampdu_state {
 	WCN36XX_AMPDU_OPERATIONAL,
 };
 
-#define WCN36XX_HW_CHANNEL(__wcn) (__wcn->hw->conf.chandef.chan->hw_value)
+#define HW_VALUE_PHY_SHIFT 8
+#define HW_VALUE_PHY(hw_value) ((hw_value) >> HW_VALUE_PHY_SHIFT)
+#define HW_VALUE_CHANNEL(hw_value) ((hw_value) & 0xFF)
+#define WCN36XX_HW_CHANNEL(__wcn)\
+	HW_VALUE_CHANNEL(__wcn->hw->conf.chandef.chan->hw_value)
 #define WCN36XX_BAND(__wcn) (__wcn->hw->conf.chandef.chan->band)
 #define WCN36XX_CENTER_FREQ(__wcn) (__wcn->hw->conf.chandef.chan->center_freq)
 #define WCN36XX_LISTEN_INTERVAL(__wcn) (__wcn->hw->conf.listen_interval)
@@ -169,7 +173,7 @@ struct wcn36xx_sta {
 	u8 bss_dpu_desc_index;
 	bool is_data_encrypted;
 	/* Rates */
-	struct wcn36xx_hal_supported_rates supported_rates;
+	struct wcn36xx_hal_supported_rates_v1 supported_rates;
 
 	spinlock_t ampdu_lock;		/* protects next two fields */
 	enum wcn36xx_ampdu_state ampdu_state[16];
@@ -271,6 +275,7 @@ static inline bool wcn36xx_is_fw_version(struct wcn36xx *wcn,
 		wcn->fw_revision == revision);
 }
 void wcn36xx_set_default_rates(struct wcn36xx_hal_supported_rates *rates);
+void wcn36xx_set_default_rates_v1(struct wcn36xx_hal_supported_rates_v1 *rates);
 
 static inline
 struct ieee80211_sta *wcn36xx_priv_to_sta(struct wcn36xx_sta *sta_priv)
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcdc.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcdc.c
index 2c95a08a5871..3984fd7d918e 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcdc.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcdc.c
@@ -397,9 +397,9 @@ brcmf_proto_bcdc_add_tdls_peer(struct brcmf_pub *drvr, int ifidx,
 }
 
 static void brcmf_proto_bcdc_rxreorder(struct brcmf_if *ifp,
-				       struct sk_buff *skb)
+				       struct sk_buff *skb, bool inirq)
 {
-	brcmf_fws_rxreorder(ifp, skb);
+	brcmf_fws_rxreorder(ifp, skb, inirq);
 }
 
 static void
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c
index 318bd00bf94f..f9ebb98b0e3c 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c
@@ -74,7 +74,7 @@ static irqreturn_t brcmf_sdiod_oob_irqhandler(int irq, void *dev_id)
 		sdiodev->irq_en = false;
 	}
 
-	brcmf_sdio_isr(sdiodev->bus);
+	brcmf_sdio_isr(sdiodev->bus, true);
 
 	return IRQ_HANDLED;
 }
@@ -86,7 +86,7 @@ static void brcmf_sdiod_ib_irqhandler(struct sdio_func *func)
 
 	brcmf_dbg(INTR, "IB intr triggered\n");
 
-	brcmf_sdio_isr(sdiodev->bus);
+	brcmf_sdio_isr(sdiodev->bus, false);
 }
 
 /* dummy handler for SDIO function 2 interrupt */
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bus.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bus.h
index 623c0168da79..08f9d47f2e5c 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bus.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bus.h
@@ -249,7 +249,8 @@ int brcmf_bus_reset(struct brcmf_bus *bus)
  */
 
 /* Receive frame for delivery to OS.  Callee disposes of rxp. */
-void brcmf_rx_frame(struct device *dev, struct sk_buff *rxp, bool handle_event);
+void brcmf_rx_frame(struct device *dev, struct sk_buff *rxp, bool handle_event,
+		    bool inirq);
 /* Receive async event packet from firmware. Callee disposes of rxp. */
 void brcmf_rx_event(struct device *dev, struct sk_buff *rxp);
 
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
index 8b5fda9bb853..a2dbbb977d0c 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
@@ -56,6 +56,7 @@
 #define RSN_AKM_PSK			2	/* Pre-shared Key */
 #define RSN_AKM_SHA256_1X		5	/* SHA256, 802.1X */
 #define RSN_AKM_SHA256_PSK		6	/* SHA256, Pre-shared Key */
+#define RSN_AKM_SAE			8	/* SAE */
 #define RSN_CAP_LEN			2	/* Length of RSN capabilities */
 #define RSN_CAP_PTK_REPLAY_CNTR_MASK	(BIT(2) | BIT(3))
 #define RSN_CAP_MFPR_MASK		BIT(6)
@@ -4242,6 +4243,10 @@ brcmf_configure_wpaie(struct brcmf_if *ifp,
 			brcmf_dbg(TRACE, "RSN_AKM_MFP_1X\n");
 			wpa_auth |= WPA2_AUTH_1X_SHA256;
 			break;
+		case RSN_AKM_SAE:
+			brcmf_dbg(TRACE, "RSN_AKM_SAE\n");
+			wpa_auth |= WPA3_AUTH_SAE_PSK;
+			break;
 		default:
 			bphy_err(drvr, "Invalid key mgmt info\n");
 		}
@@ -4259,11 +4264,12 @@ brcmf_configure_wpaie(struct brcmf_if *ifp,
 				brcmf_dbg(TRACE, "MFP Required\n");
 				mfp = BRCMF_MFP_REQUIRED;
 				/* Firmware only supports mfp required in
-				 * combination with WPA2_AUTH_PSK_SHA256 or
-				 * WPA2_AUTH_1X_SHA256.
+				 * combination with WPA2_AUTH_PSK_SHA256,
+				 * WPA2_AUTH_1X_SHA256, or WPA3_AUTH_SAE_PSK.
 				 */
 				if (!(wpa_auth & (WPA2_AUTH_PSK_SHA256 |
-						  WPA2_AUTH_1X_SHA256))) {
+						  WPA2_AUTH_1X_SHA256 |
+						  WPA3_AUTH_SAE_PSK))) {
 					err = -EINVAL;
 					goto exit;
 				}
@@ -4679,6 +4685,8 @@ brcmf_cfg80211_start_ap(struct wiphy *wiphy, struct net_device *ndev,
 	struct brcmf_cfg80211_info *cfg = wiphy_to_cfg(wiphy);
 	struct brcmf_if *ifp = netdev_priv(ndev);
 	struct brcmf_pub *drvr = cfg->pub;
+	struct brcmf_cfg80211_profile *profile = &ifp->vif->profile;
+	struct cfg80211_crypto_settings *crypto = &settings->crypto;
 	const struct brcmf_tlv *ssid_ie;
 	const struct brcmf_tlv *country_ie;
 	struct brcmf_ssid_le ssid_le;
@@ -4818,6 +4826,25 @@ brcmf_cfg80211_start_ap(struct wiphy *wiphy, struct net_device *ndev,
 			goto exit;
 		}
 
+		if (crypto->psk) {
+			brcmf_dbg(INFO, "using PSK offload\n");
+			profile->use_fwauth |= BIT(BRCMF_PROFILE_FWAUTH_PSK);
+			err = brcmf_set_pmk(ifp, crypto->psk,
+					    BRCMF_WSEC_MAX_PSK_LEN);
+			if (err < 0)
+				goto exit;
+		}
+		if (crypto->sae_pwd) {
+			brcmf_dbg(INFO, "using SAE offload\n");
+			profile->use_fwauth |= BIT(BRCMF_PROFILE_FWAUTH_SAE);
+			err = brcmf_set_sae_password(ifp, crypto->sae_pwd,
+						     crypto->sae_pwd_len);
+			if (err < 0)
+				goto exit;
+		}
+		if (profile->use_fwauth == 0)
+			profile->use_fwauth = BIT(BRCMF_PROFILE_FWAUTH_NONE);
+
 		err = brcmf_parse_configure_security(ifp, settings,
 						     NL80211_IFTYPE_AP);
 		if (err < 0) {
@@ -4904,6 +4931,7 @@ static int brcmf_cfg80211_stop_ap(struct wiphy *wiphy, struct net_device *ndev)
 	struct brcmf_cfg80211_info *cfg = wiphy_to_cfg(wiphy);
 	struct brcmf_if *ifp = netdev_priv(ndev);
 	struct brcmf_pub *drvr = cfg->pub;
+	struct brcmf_cfg80211_profile *profile = &ifp->vif->profile;
 	s32 err;
 	struct brcmf_fil_bss_enable_le bss_enable;
 	struct brcmf_join_params join_params;
@@ -4915,6 +4943,14 @@ static int brcmf_cfg80211_stop_ap(struct wiphy *wiphy, struct net_device *ndev)
 		/* first to make sure they get processed by fw. */
 		msleep(400);
 
+		if (profile->use_fwauth != BIT(BRCMF_PROFILE_FWAUTH_NONE)) {
+			if (profile->use_fwauth & BIT(BRCMF_PROFILE_FWAUTH_PSK))
+				brcmf_set_pmk(ifp, NULL, 0);
+			if (profile->use_fwauth & BIT(BRCMF_PROFILE_FWAUTH_SAE))
+				brcmf_set_sae_password(ifp, NULL, 0);
+			profile->use_fwauth = BIT(BRCMF_PROFILE_FWAUTH_NONE);
+		}
+
 		if (ifp->vif->mbss) {
 			err = brcmf_fil_cmd_int_set(ifp, BRCMF_C_DOWN, 1);
 			return err;
@@ -7063,6 +7099,13 @@ static int brcmf_setup_wiphy(struct wiphy *wiphy, struct brcmf_if *ifp)
 			wiphy_ext_feature_set(wiphy,
 					      NL80211_EXT_FEATURE_SAE_OFFLOAD);
 	}
+	if (brcmf_feat_is_enabled(ifp, BRCMF_FEAT_FWAUTH)) {
+		wiphy_ext_feature_set(wiphy,
+				      NL80211_EXT_FEATURE_4WAY_HANDSHAKE_AP_PSK);
+		if (brcmf_feat_is_enabled(ifp, BRCMF_FEAT_SAE))
+			wiphy_ext_feature_set(wiphy,
+					      NL80211_EXT_FEATURE_SAE_OFFLOAD_AP);
+	}
 	wiphy->mgmt_stypes = brcmf_txrx_stypes;
 	wiphy->max_remain_on_channel_duration = 5000;
 	if (brcmf_feat_is_enabled(ifp, BRCMF_FEAT_PNO)) {
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.h
index 333fdf394f95..17817cdb5de2 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.h
@@ -129,6 +129,19 @@ enum brcmf_profile_fwsup {
 };
 
 /**
+ * enum brcmf_profile_fwauth - firmware authenticator profile
+ *
+ * @BRCMF_PROFILE_FWAUTH_NONE: no firmware authenticator
+ * @BRCMF_PROFILE_FWAUTH_PSK: authenticator for WPA/WPA2-PSK
+ * @BRCMF_PROFILE_FWAUTH_SAE: authenticator for SAE
+ */
+enum brcmf_profile_fwauth {
+	BRCMF_PROFILE_FWAUTH_NONE,
+	BRCMF_PROFILE_FWAUTH_PSK,
+	BRCMF_PROFILE_FWAUTH_SAE
+};
+
+/**
  * struct brcmf_cfg80211_profile - profile information.
  *
  * @bssid: bssid of joined/joining ibss.
@@ -140,6 +153,7 @@ struct brcmf_cfg80211_profile {
 	struct brcmf_cfg80211_security sec;
 	struct brcmf_wsec_key key[BRCMF_MAX_DEFAULT_KEYS];
 	enum brcmf_profile_fwsup use_fwsup;
+	u16 use_fwauth;
 	bool is_ft;
 };
 
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c
index aa9ced3c86fb..3dd28f5fef19 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c
@@ -395,7 +395,7 @@ void brcmf_txflowblock_if(struct brcmf_if *ifp,
 	spin_unlock_irqrestore(&ifp->netif_stop_lock, flags);
 }
 
-void brcmf_netif_rx(struct brcmf_if *ifp, struct sk_buff *skb)
+void brcmf_netif_rx(struct brcmf_if *ifp, struct sk_buff *skb, bool inirq)
 {
 	/* Most of Broadcom's firmwares send 802.11f ADD frame every time a new
 	 * STA connects to the AP interface. This is an obsoleted standard most
@@ -418,14 +418,15 @@ void brcmf_netif_rx(struct brcmf_if *ifp, struct sk_buff *skb)
 	ifp->ndev->stats.rx_packets++;
 
 	brcmf_dbg(DATA, "rx proto=0x%X\n", ntohs(skb->protocol));
-	if (in_interrupt())
+	if (inirq) {
 		netif_rx(skb);
-	else
+	} else {
 		/* If the receive is not processed inside an ISR,
 		 * the softirqd must be woken explicitly to service
 		 * the NET_RX_SOFTIRQ.  This is handled by netif_rx_ni().
 		 */
 		netif_rx_ni(skb);
+	}
 }
 
 void brcmf_netif_mon_rx(struct brcmf_if *ifp, struct sk_buff *skb)
@@ -474,7 +475,7 @@ void brcmf_netif_mon_rx(struct brcmf_if *ifp, struct sk_buff *skb)
 	skb->pkt_type = PACKET_OTHERHOST;
 	skb->protocol = htons(ETH_P_802_2);
 
-	brcmf_netif_rx(ifp, skb);
+	brcmf_netif_rx(ifp, skb, false);
 }
 
 static int brcmf_rx_hdrpull(struct brcmf_pub *drvr, struct sk_buff *skb,
@@ -496,7 +497,8 @@ static int brcmf_rx_hdrpull(struct brcmf_pub *drvr, struct sk_buff *skb,
 	return 0;
 }
 
-void brcmf_rx_frame(struct device *dev, struct sk_buff *skb, bool handle_event)
+void brcmf_rx_frame(struct device *dev, struct sk_buff *skb, bool handle_event,
+		    bool inirq)
 {
 	struct brcmf_if *ifp;
 	struct brcmf_bus *bus_if = dev_get_drvdata(dev);
@@ -508,14 +510,16 @@ void brcmf_rx_frame(struct device *dev, struct sk_buff *skb, bool handle_event)
 		return;
 
 	if (brcmf_proto_is_reorder_skb(skb)) {
-		brcmf_proto_rxreorder(ifp, skb);
+		brcmf_proto_rxreorder(ifp, skb, inirq);
 	} else {
 		/* Process special event packets */
-		if (handle_event)
-			brcmf_fweh_process_skb(ifp->drvr, skb,
-					       BCMILCP_SUBTYPE_VENDOR_LONG);
+		if (handle_event) {
+			gfp_t gfp = inirq ? GFP_ATOMIC : GFP_KERNEL;
 
-		brcmf_netif_rx(ifp, skb);
+			brcmf_fweh_process_skb(ifp->drvr, skb,
+					       BCMILCP_SUBTYPE_VENDOR_LONG, gfp);
+		}
+		brcmf_netif_rx(ifp, skb, inirq);
 	}
 }
 
@@ -530,7 +534,7 @@ void brcmf_rx_event(struct device *dev, struct sk_buff *skb)
 	if (brcmf_rx_hdrpull(drvr, skb, &ifp))
 		return;
 
-	brcmf_fweh_process_skb(ifp->drvr, skb, 0);
+	brcmf_fweh_process_skb(ifp->drvr, skb, 0, GFP_KERNEL);
 	brcmu_pkt_buf_free_skb(skb);
 }
 
@@ -1422,6 +1426,11 @@ void brcmf_detach(struct device *dev)
 #endif
 
 	brcmf_bus_change_state(bus_if, BRCMF_BUS_DOWN);
+	/* make sure primary interface removed last */
+	for (i = BRCMF_MAX_IFS - 1; i > -1; i--) {
+		if (drvr->iflist[i])
+			brcmf_remove_interface(drvr->iflist[i], false);
+	}
 	brcmf_bus_stop(drvr->bus_if);
 
 	brcmf_fweh_detach(drvr);
@@ -1432,12 +1441,6 @@ void brcmf_detach(struct device *dev)
 		drvr->mon_if = NULL;
 	}
 
-	/* make sure primary interface removed last */
-	for (i = BRCMF_MAX_IFS - 1; i > -1; i--) {
-		if (drvr->iflist[i])
-			brcmf_del_if(drvr, drvr->iflist[i]->bsscfgidx, false);
-	}
-
 	if (drvr->config) {
 		brcmf_p2p_detach(&drvr->config->p2p);
 		brcmf_cfg80211_detach(drvr->config);
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.h
index 33b2ab3b54b0..5767d665cee5 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.h
@@ -208,7 +208,7 @@ void brcmf_remove_interface(struct brcmf_if *ifp, bool rtnl_locked);
 void brcmf_txflowblock_if(struct brcmf_if *ifp,
 			  enum brcmf_netif_stop_reason reason, bool state);
 void brcmf_txfinalize(struct brcmf_if *ifp, struct sk_buff *txp, bool success);
-void brcmf_netif_rx(struct brcmf_if *ifp, struct sk_buff *skb);
+void brcmf_netif_rx(struct brcmf_if *ifp, struct sk_buff *skb, bool inirq);
 void brcmf_netif_mon_rx(struct brcmf_if *ifp, struct sk_buff *skb);
 void brcmf_net_detach(struct net_device *ndev, bool rtnl_locked);
 int brcmf_net_mon_attach(struct brcmf_if *ifp);
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c
index 0dcefbd0c000..7c68d9849324 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c
@@ -42,6 +42,7 @@ static const struct brcmf_feat_fwcap brcmf_fwcap_map[] = {
 	{ BRCMF_FEAT_MONITOR_FMT_RADIOTAP, "rtap" },
 	{ BRCMF_FEAT_DOT11H, "802.11h" },
 	{ BRCMF_FEAT_SAE, "sae" },
+	{ BRCMF_FEAT_FWAUTH, "idauth" },
 };
 
 #ifdef DEBUG
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.h
index cda3fc1bab7f..d1f4257af696 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.h
@@ -28,6 +28,7 @@
  * MONITOR_FMT_HW_RX_HDR: firmware provides monitor packets with hw/ucode header
  * DOT11H: firmware supports 802.11h
  * SAE: simultaneous authentication of equals
+ * FWAUTH: Firmware authenticator
  */
 #define BRCMF_FEAT_LIST \
 	BRCMF_FEAT_DEF(MBSS) \
@@ -49,7 +50,8 @@
 	BRCMF_FEAT_DEF(MONITOR_FMT_RADIOTAP) \
 	BRCMF_FEAT_DEF(MONITOR_FMT_HW_RX_HDR) \
 	BRCMF_FEAT_DEF(DOT11H) \
-	BRCMF_FEAT_DEF(SAE)
+	BRCMF_FEAT_DEF(SAE) \
+	BRCMF_FEAT_DEF(FWAUTH)
 
 /*
  * Quirks:
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.c
index 3bdbb285b3aa..430d2cca98b3 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.c
@@ -304,10 +304,12 @@ void brcmf_fweh_detach(struct brcmf_pub *drvr)
 {
 	struct brcmf_fweh_info *fweh = &drvr->fweh;
 
-	/* cancel the worker */
-	cancel_work_sync(&fweh->event_work);
-	WARN_ON(!list_empty(&fweh->event_q));
-	memset(fweh->evt_handler, 0, sizeof(fweh->evt_handler));
+	/* cancel the worker if initialized */
+	if (fweh->event_work.func) {
+		cancel_work_sync(&fweh->event_work);
+		WARN_ON(!list_empty(&fweh->event_q));
+		memset(fweh->evt_handler, 0, sizeof(fweh->evt_handler));
+	}
 }
 
 /**
@@ -388,12 +390,11 @@ int brcmf_fweh_activate_events(struct brcmf_if *ifp)
  */
 void brcmf_fweh_process_event(struct brcmf_pub *drvr,
 			      struct brcmf_event *event_packet,
-			      u32 packet_len)
+			      u32 packet_len, gfp_t gfp)
 {
 	enum brcmf_fweh_event_code code;
 	struct brcmf_fweh_info *fweh = &drvr->fweh;
 	struct brcmf_fweh_queue_item *event;
-	gfp_t alloc_flag = GFP_KERNEL;
 	void *data;
 	u32 datalen;
 
@@ -412,10 +413,7 @@ void brcmf_fweh_process_event(struct brcmf_pub *drvr,
 	    datalen + sizeof(*event_packet) > packet_len)
 		return;
 
-	if (in_interrupt())
-		alloc_flag = GFP_ATOMIC;
-
-	event = kzalloc(sizeof(*event) + datalen, alloc_flag);
+	event = kzalloc(sizeof(*event) + datalen, gfp);
 	if (!event)
 		return;
 
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.h
index a82f51bc1e69..48414e8b9389 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.h
@@ -319,11 +319,12 @@ void brcmf_fweh_unregister(struct brcmf_pub *drvr,
 int brcmf_fweh_activate_events(struct brcmf_if *ifp);
 void brcmf_fweh_process_event(struct brcmf_pub *drvr,
 			      struct brcmf_event *event_packet,
-			      u32 packet_len);
+			      u32 packet_len, gfp_t gfp);
 void brcmf_fweh_p2pdev_setup(struct brcmf_if *ifp, bool ongoing);
 
 static inline void brcmf_fweh_process_skb(struct brcmf_pub *drvr,
-					  struct sk_buff *skb, u16 stype)
+					  struct sk_buff *skb, u16 stype,
+					  gfp_t gfp)
 {
 	struct brcmf_event *event_packet;
 	u16 subtype, usr_stype;
@@ -354,7 +355,7 @@ static inline void brcmf_fweh_process_skb(struct brcmf_pub *drvr,
 	if (usr_stype != BCMILCP_BCM_SUBTYPE_EVENT)
 		return;
 
-	brcmf_fweh_process_event(drvr, event_packet, skb->len + ETH_HLEN);
+	brcmf_fweh_process_event(drvr, event_packet, skb->len + ETH_HLEN, gfp);
 }
 
 #endif /* FWEH_H_ */
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c
index 775e0612fa17..437e83ea8902 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c
@@ -1664,7 +1664,7 @@ static void brcmf_rxreorder_get_skb_list(struct brcmf_ampdu_rx_reorder *rfi,
 	rfi->pend_pkts -= skb_queue_len(skb_list);
 }
 
-void brcmf_fws_rxreorder(struct brcmf_if *ifp, struct sk_buff *pkt)
+void brcmf_fws_rxreorder(struct brcmf_if *ifp, struct sk_buff *pkt, bool inirq)
 {
 	struct brcmf_pub *drvr = ifp->drvr;
 	u8 *reorder_data;
@@ -1682,7 +1682,7 @@ void brcmf_fws_rxreorder(struct brcmf_if *ifp, struct sk_buff *pkt)
 	/* validate flags and flow id */
 	if (flags == 0xFF) {
 		bphy_err(drvr, "invalid flags...so ignore this packet\n");
-		brcmf_netif_rx(ifp, pkt);
+		brcmf_netif_rx(ifp, pkt, inirq);
 		return;
 	}
 
@@ -1694,7 +1694,7 @@ void brcmf_fws_rxreorder(struct brcmf_if *ifp, struct sk_buff *pkt)
 		if (rfi == NULL) {
 			brcmf_dbg(INFO, "received flags to cleanup, but no flow (%d) yet\n",
 				  flow_id);
-			brcmf_netif_rx(ifp, pkt);
+			brcmf_netif_rx(ifp, pkt, inirq);
 			return;
 		}
 
@@ -1719,7 +1719,7 @@ void brcmf_fws_rxreorder(struct brcmf_if *ifp, struct sk_buff *pkt)
 		rfi = kzalloc(buf_size, GFP_ATOMIC);
 		if (rfi == NULL) {
 			bphy_err(drvr, "failed to alloc buffer\n");
-			brcmf_netif_rx(ifp, pkt);
+			brcmf_netif_rx(ifp, pkt, inirq);
 			return;
 		}
 
@@ -1833,7 +1833,7 @@ void brcmf_fws_rxreorder(struct brcmf_if *ifp, struct sk_buff *pkt)
 netif_rx:
 	skb_queue_walk_safe(&reorder_list, pkt, pnext) {
 		__skb_unlink(pkt, &reorder_list);
-		brcmf_netif_rx(ifp, pkt);
+		brcmf_netif_rx(ifp, pkt, inirq);
 	}
 }
 
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.h
index b16a9d1c0508..50e424b5880d 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.h
@@ -42,6 +42,6 @@ void brcmf_fws_add_interface(struct brcmf_if *ifp);
 void brcmf_fws_del_interface(struct brcmf_if *ifp);
 void brcmf_fws_bustxfail(struct brcmf_fws_info *fws, struct sk_buff *skb);
 void brcmf_fws_bus_blocked(struct brcmf_pub *drvr, bool flow_blocked);
-void brcmf_fws_rxreorder(struct brcmf_if *ifp, struct sk_buff *skb);
+void brcmf_fws_rxreorder(struct brcmf_if *ifp, struct sk_buff *skb, bool inirq);
 
 #endif /* FWSIGNAL_H_ */
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/msgbuf.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/msgbuf.c
index bfddb851e386..7c8e08ee8f0f 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/msgbuf.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/msgbuf.c
@@ -536,7 +536,8 @@ static int brcmf_msgbuf_hdrpull(struct brcmf_pub *drvr, bool do_fws,
 	return -ENODEV;
 }
 
-static void brcmf_msgbuf_rxreorder(struct brcmf_if *ifp, struct sk_buff *skb)
+static void brcmf_msgbuf_rxreorder(struct brcmf_if *ifp, struct sk_buff *skb,
+				   bool inirq)
 {
 }
 
@@ -1128,7 +1129,7 @@ static void brcmf_msgbuf_process_event(struct brcmf_msgbuf *msgbuf, void *buf)
 
 	skb->protocol = eth_type_trans(skb, ifp->ndev);
 
-	brcmf_fweh_process_skb(ifp->drvr, skb, 0);
+	brcmf_fweh_process_skb(ifp->drvr, skb, 0, GFP_KERNEL);
 
 exit:
 	brcmu_pkt_buf_free_skb(skb);
@@ -1190,7 +1191,7 @@ brcmf_msgbuf_process_rx_complete(struct brcmf_msgbuf *msgbuf, void *buf)
 	}
 
 	skb->protocol = eth_type_trans(skb, ifp->ndev);
-	brcmf_netif_rx(ifp, skb);
+	brcmf_netif_rx(ifp, skb, false);
 }
 
 static void brcmf_msgbuf_process_gen_status(struct brcmf_msgbuf *msgbuf,
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/proto.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/proto.h
index bd08d3aaa8f4..f4a79e217da5 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/proto.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/proto.h
@@ -32,7 +32,7 @@ struct brcmf_proto {
 			    u8 peer[ETH_ALEN]);
 	void (*add_tdls_peer)(struct brcmf_pub *drvr, int ifidx,
 			      u8 peer[ETH_ALEN]);
-	void (*rxreorder)(struct brcmf_if *ifp, struct sk_buff *skb);
+	void (*rxreorder)(struct brcmf_if *ifp, struct sk_buff *skb, bool inirq);
 	void (*add_if)(struct brcmf_if *ifp);
 	void (*del_if)(struct brcmf_if *ifp);
 	void (*reset_if)(struct brcmf_if *ifp);
@@ -109,9 +109,9 @@ static inline bool brcmf_proto_is_reorder_skb(struct sk_buff *skb)
 }
 
 static inline void
-brcmf_proto_rxreorder(struct brcmf_if *ifp, struct sk_buff *skb)
+brcmf_proto_rxreorder(struct brcmf_if *ifp, struct sk_buff *skb, bool inirq)
 {
-	ifp->drvr->proto->rxreorder(ifp, skb);
+	ifp->drvr->proto->rxreorder(ifp, skb, inirq);
 }
 
 static inline void
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
index 991ca9e32be3..99987a789e7e 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
@@ -664,9 +664,15 @@ static void pkt_align(struct sk_buff *p, int len, int align)
 /* To check if there's window offered */
 static bool data_ok(struct brcmf_sdio *bus)
 {
-	/* Reserve TXCTL_CREDITS credits for txctl */
-	return (bus->tx_max - bus->tx_seq) > TXCTL_CREDITS &&
-	       ((bus->tx_max - bus->tx_seq) & 0x80) == 0;
+	u8 tx_rsv = 0;
+
+	/* Reserve TXCTL_CREDITS credits for txctl when it is ready to send */
+	if (bus->ctrl_frame_stat)
+		tx_rsv = TXCTL_CREDITS;
+
+	return (bus->tx_max - bus->tx_seq - tx_rsv) != 0 &&
+	       ((bus->tx_max - bus->tx_seq - tx_rsv) & 0x80) == 0;
+
 }
 
 /* To check if there's window offered */
@@ -1698,7 +1704,7 @@ static u8 brcmf_sdio_rxglom(struct brcmf_sdio *bus, u8 rxseq)
 				brcmf_rx_event(bus->sdiodev->dev, pfirst);
 			else
 				brcmf_rx_frame(bus->sdiodev->dev, pfirst,
-					       false);
+					       false, false);
 			bus->sdcnt.rxglompkts++;
 		}
 
@@ -2032,7 +2038,7 @@ static uint brcmf_sdio_readframes(struct brcmf_sdio *bus, uint maxframes)
 			brcmf_rx_event(bus->sdiodev->dev, pkt);
 		else
 			brcmf_rx_frame(bus->sdiodev->dev, pkt,
-				       false);
+				       false, false);
 
 		/* prepare the descriptor for the next read */
 		rd->len = rd->len_nxtfrm << 4;
@@ -3619,7 +3625,7 @@ void brcmf_sdio_trigger_dpc(struct brcmf_sdio *bus)
 	}
 }
 
-void brcmf_sdio_isr(struct brcmf_sdio *bus)
+void brcmf_sdio_isr(struct brcmf_sdio *bus, bool in_isr)
 {
 	brcmf_dbg(TRACE, "Enter\n");
 
@@ -3630,7 +3636,7 @@ void brcmf_sdio_isr(struct brcmf_sdio *bus)
 
 	/* Count the interrupt call */
 	bus->sdcnt.intrcount++;
-	if (in_interrupt())
+	if (in_isr)
 		atomic_set(&bus->ipend, 1);
 	else
 		if (brcmf_sdio_intr_rstatus(bus)) {
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h
index 12108927fb50..15d2c02fa3ec 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h
@@ -372,7 +372,7 @@ int brcmf_sdiod_remove(struct brcmf_sdio_dev *sdiodev);
 
 struct brcmf_sdio *brcmf_sdio_probe(struct brcmf_sdio_dev *sdiodev);
 void brcmf_sdio_remove(struct brcmf_sdio *bus);
-void brcmf_sdio_isr(struct brcmf_sdio *bus);
+void brcmf_sdio_isr(struct brcmf_sdio *bus, bool in_isr);
 
 void brcmf_sdio_wd_timer(struct brcmf_sdio *bus, bool active);
 void brcmf_sdio_wowl_config(struct device *dev, bool enabled);
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c
index ac5463838fcf..586f4dfc638b 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c
@@ -532,7 +532,7 @@ static void brcmf_usb_rx_complete(struct urb *urb)
 	if (devinfo->bus_pub.state == BRCMFMAC_USB_STATE_UP ||
 	    devinfo->bus_pub.state == BRCMFMAC_USB_STATE_SLEEP) {
 		skb_put(skb, urb->actual_length);
-		brcmf_rx_frame(devinfo->dev, skb, true);
+		brcmf_rx_frame(devinfo->dev, skb, true, true);
 		brcmf_usb_rx_refill(devinfo, req);
 		usb_mark_last_busy(urb->dev);
 	} else {
@@ -1578,6 +1578,9 @@ void brcmf_usb_exit(void)
 	brcmf_dbg(USB, "Enter\n");
 	ret = driver_for_each_device(drv, NULL, NULL,
 				     brcmf_usb_reset_device);
+	if (ret)
+		brcmf_err("failed to reset all usb devices %d\n", ret);
+
 	usb_deregister(&brcmf_usbdrvr);
 }
 
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/main.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/main.c
index 21691581b532..763e0ec583d7 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/main.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/main.c
@@ -5085,13 +5085,6 @@ int brcms_c_up(struct brcms_c_info *wlc)
 	return 0;
 }
 
-static uint brcms_c_down_del_timer(struct brcms_c_info *wlc)
-{
-	uint callbacks = 0;
-
-	return callbacks;
-}
-
 static int brcms_b_bmac_down_prep(struct brcms_hardware *wlc_hw)
 {
 	bool dev_gone;
@@ -5201,8 +5194,6 @@ uint brcms_c_down(struct brcms_c_info *wlc)
 			callbacks++;
 		wlc->WDarmed = false;
 	}
-	/* cancel all other timers */
-	callbacks += brcms_c_down_del_timer(wlc);
 
 	wlc->pub->up = false;
 
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_lcn.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_lcn.c
index 322bbd71388b..7717eb85a1db 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_lcn.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_lcn.c
@@ -357,61 +357,6 @@ u16 rxiq_cal_rf_reg[11] = {
 	RADIO_2064_REG12A,
 };
 
-static const
-struct lcnphy_rx_iqcomp lcnphy_rx_iqcomp_table_rev0[] = {
-	{1, 0, 0},
-	{2, 0, 0},
-	{3, 0, 0},
-	{4, 0, 0},
-	{5, 0, 0},
-	{6, 0, 0},
-	{7, 0, 0},
-	{8, 0, 0},
-	{9, 0, 0},
-	{10, 0, 0},
-	{11, 0, 0},
-	{12, 0, 0},
-	{13, 0, 0},
-	{14, 0, 0},
-	{34, 0, 0},
-	{38, 0, 0},
-	{42, 0, 0},
-	{46, 0, 0},
-	{36, 0, 0},
-	{40, 0, 0},
-	{44, 0, 0},
-	{48, 0, 0},
-	{52, 0, 0},
-	{56, 0, 0},
-	{60, 0, 0},
-	{64, 0, 0},
-	{100, 0, 0},
-	{104, 0, 0},
-	{108, 0, 0},
-	{112, 0, 0},
-	{116, 0, 0},
-	{120, 0, 0},
-	{124, 0, 0},
-	{128, 0, 0},
-	{132, 0, 0},
-	{136, 0, 0},
-	{140, 0, 0},
-	{149, 0, 0},
-	{153, 0, 0},
-	{157, 0, 0},
-	{161, 0, 0},
-	{165, 0, 0},
-	{184, 0, 0},
-	{188, 0, 0},
-	{192, 0, 0},
-	{196, 0, 0},
-	{200, 0, 0},
-	{204, 0, 0},
-	{208, 0, 0},
-	{212, 0, 0},
-	{216, 0, 0},
-};
-
 static const u32 lcnphy_23bitgaincode_table[] = {
 	0x200100,
 	0x200200,
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phytbl_lcn.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phytbl_lcn.c
index 7526aa441de1..5331b5468e14 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phytbl_lcn.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phytbl_lcn.c
@@ -105,105 +105,6 @@ static const u32 dot11lcn_gain_tbl_rev0[] = {
 	0x00000000,
 };
 
-static const u32 dot11lcn_gain_tbl_rev1[] = {
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000008,
-	0x00000004,
-	0x00000008,
-	0x00000001,
-	0x00000005,
-	0x00000009,
-	0x0000000D,
-	0x00000011,
-	0x00000051,
-	0x00000091,
-	0x00000011,
-	0x00000051,
-	0x00000091,
-	0x000000d1,
-	0x00000053,
-	0x00000093,
-	0x000000d3,
-	0x000000d7,
-	0x00000117,
-	0x00000517,
-	0x00000917,
-	0x00000957,
-	0x00000d57,
-	0x00001157,
-	0x00001197,
-	0x00005197,
-	0x00009197,
-	0x0000d197,
-	0x00011197,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000008,
-	0x00000004,
-	0x00000008,
-	0x00000001,
-	0x00000005,
-	0x00000009,
-	0x0000000D,
-	0x00000011,
-	0x00000051,
-	0x00000091,
-	0x00000011,
-	0x00000051,
-	0x00000091,
-	0x000000d1,
-	0x00000053,
-	0x00000093,
-	0x000000d3,
-	0x000000d7,
-	0x00000117,
-	0x00000517,
-	0x00000917,
-	0x00000957,
-	0x00000d57,
-	0x00001157,
-	0x00005157,
-	0x00009157,
-	0x0000d157,
-	0x00011157,
-	0x00015157,
-	0x00019157,
-	0x0001d157,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-};
-
 static const u16 dot11lcn_aux_gain_idx_tbl_rev0[] = {
 	0x0401,
 	0x0402,
diff --git a/drivers/net/wireless/cisco/airo.c b/drivers/net/wireless/cisco/airo.c
index dd78c415d6e7..87b9398b03fd 100644
--- a/drivers/net/wireless/cisco/airo.c
+++ b/drivers/net/wireless/cisco/airo.c
@@ -2430,8 +2430,8 @@ void stop_airo_card(struct net_device *dev, int freeres)
 				iounmap(ai->pcimem);
 			if (ai->pciaux)
 				iounmap(ai->pciaux);
-			pci_free_consistent(ai->pci, PCI_SHARED_LEN,
-				ai->shared, ai->shared_dma);
+			dma_free_coherent(&ai->pci->dev, PCI_SHARED_LEN,
+					  ai->shared, ai->shared_dma);
 		}
         }
 	crypto_free_sync_skcipher(ai->tfm);
@@ -2581,9 +2581,10 @@ static int mpi_map_card(struct airo_info *ai, struct pci_dev *pci)
 	}
 
 	/* Reserve PKTSIZE for each fid and 2K for the Rids */
-	ai->shared = pci_alloc_consistent(pci, PCI_SHARED_LEN, &ai->shared_dma);
+	ai->shared = dma_alloc_coherent(&pci->dev, PCI_SHARED_LEN,
+					&ai->shared_dma, GFP_KERNEL);
 	if (!ai->shared) {
-		airo_print_err("", "Couldn't alloc_consistent %d",
+		airo_print_err("", "Couldn't alloc_coherent %d",
 			PCI_SHARED_LEN);
 		goto free_auxmap;
 	}
@@ -2643,7 +2644,8 @@ static int mpi_map_card(struct airo_info *ai, struct pci_dev *pci)
 
 	return 0;
  free_shared:
-	pci_free_consistent(pci, PCI_SHARED_LEN, ai->shared, ai->shared_dma);
+	dma_free_coherent(&pci->dev, PCI_SHARED_LEN, ai->shared,
+			  ai->shared_dma);
  free_auxmap:
 	iounmap(ai->pciaux);
  free_memmap:
@@ -2930,7 +2932,8 @@ err_out_reg:
 	unregister_netdev(dev);
 err_out_map:
 	if (test_bit(FLAG_MPI,&ai->flags) && pci) {
-		pci_free_consistent(pci, PCI_SHARED_LEN, ai->shared, ai->shared_dma);
+		dma_free_coherent(&pci->dev, PCI_SHARED_LEN, ai->shared,
+				  ai->shared_dma);
 		iounmap(ai->pciaux);
 		iounmap(ai->pcimem);
 		mpi_unmap_card(ai->pci);
diff --git a/drivers/net/wireless/intel/ipw2x00/ipw2100.c b/drivers/net/wireless/intel/ipw2x00/ipw2100.c
index b7fbfc77b612..23fbddd0c1f8 100644
--- a/drivers/net/wireless/intel/ipw2x00/ipw2100.c
+++ b/drivers/net/wireless/intel/ipw2x00/ipw2100.c
@@ -201,8 +201,7 @@ static u32 ipw2100_debug_level = IPW_DL_NONE;
 #define IPW_DEBUG(level, message...) \
 do { \
 	if (ipw2100_debug_level & (level)) { \
-		printk(KERN_DEBUG "ipw2100: %c %s ", \
-                       in_interrupt() ? 'I' : 'U',  __func__); \
+		printk(KERN_DEBUG "ipw2100: %s ", __func__); \
 		printk(message); \
 	} \
 } while (0)
diff --git a/drivers/net/wireless/intel/ipw2x00/ipw2200.h b/drivers/net/wireless/intel/ipw2x00/ipw2200.h
index e1ec1c96dcd8..98fe62737888 100644
--- a/drivers/net/wireless/intel/ipw2x00/ipw2200.h
+++ b/drivers/net/wireless/intel/ipw2x00/ipw2200.h
@@ -1382,14 +1382,12 @@ BIT_ARG16(x)
 
 #define IPW_DEBUG(level, fmt, args...) \
 do { if (ipw_debug_level & (level)) \
-  printk(KERN_DEBUG DRV_NAME": %c %s " fmt, \
-         in_interrupt() ? 'I' : 'U', __func__ , ## args); } while (0)
+  printk(KERN_DEBUG DRV_NAME": %s " fmt, __func__ , ## args); } while (0)
 
 #ifdef CONFIG_IPW2200_DEBUG
 #define IPW_LL_DEBUG(level, fmt, args...) \
 do { if (ipw_debug_level & (level)) \
-  printk(KERN_DEBUG DRV_NAME": %c %s " fmt, \
-         in_interrupt() ? 'I' : 'U', __func__ , ## args); } while (0)
+  printk(KERN_DEBUG DRV_NAME": %s " fmt, __func__ , ## args); } while (0)
 #else
 #define IPW_LL_DEBUG(level, fmt, args...) do {} while (0)
 #endif				/* CONFIG_IPW2200_DEBUG */
diff --git a/drivers/net/wireless/intel/ipw2x00/libipw.h b/drivers/net/wireless/intel/ipw2x00/libipw.h
index e87538a8b88b..7964ef7d15f0 100644
--- a/drivers/net/wireless/intel/ipw2x00/libipw.h
+++ b/drivers/net/wireless/intel/ipw2x00/libipw.h
@@ -60,8 +60,7 @@
 extern u32 libipw_debug_level;
 #define LIBIPW_DEBUG(level, fmt, args...) \
 do { if (libipw_debug_level & (level)) \
-  printk(KERN_DEBUG "libipw: %c %s " fmt, \
-         in_interrupt() ? 'I' : 'U', __func__ , ## args); } while (0)
+  printk(KERN_DEBUG "libipw: %s " fmt, __func__ , ## args); } while (0)
 #else
 #define LIBIPW_DEBUG(level, fmt, args...) do {} while (0)
 #endif				/* CONFIG_LIBIPW_DEBUG */
diff --git a/drivers/net/wireless/intel/iwlegacy/common.h b/drivers/net/wireless/intel/iwlegacy/common.h
index bc9cd7e5ccb8..ea1b1bb7ddcb 100644
--- a/drivers/net/wireless/intel/iwlegacy/common.h
+++ b/drivers/net/wireless/intel/iwlegacy/common.h
@@ -2925,8 +2925,8 @@ do {									\
 #define IL_DBG(level, fmt, args...)					\
 do {									\
 	if (il_get_debug_level(il) & level)				\
-		dev_err(&il->hw->wiphy->dev, "%c %s " fmt,		\
-			in_interrupt() ? 'I' : 'U', __func__ , ##args); \
+		dev_err(&il->hw->wiphy->dev, "%s " fmt, __func__,	\
+			 ##args);					\
 } while (0)
 
 #define il_print_hex_dump(il, level, p, len)				\
diff --git a/drivers/net/wireless/intel/iwlwifi/Makefile b/drivers/net/wireless/intel/iwlwifi/Makefile
index fbcd1405aeea..85c6fed28f8e 100644
--- a/drivers/net/wireless/intel/iwlwifi/Makefile
+++ b/drivers/net/wireless/intel/iwlwifi/Makefile
@@ -13,6 +13,7 @@ iwlwifi-$(CONFIG_IWLDVM) += cfg/1000.o cfg/2000.o cfg/5000.o cfg/6000.o
 iwlwifi-$(CONFIG_IWLMVM) += cfg/7000.o cfg/8000.o cfg/9000.o cfg/22000.o
 iwlwifi-objs		+= iwl-dbg-tlv.o
 iwlwifi-objs		+= iwl-trans.o
+iwlwifi-objs		+= queue/tx.o
 
 iwlwifi-objs		+= fw/img.o fw/notif-wait.o
 iwlwifi-objs		+= fw/dbg.o
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
index efe427049a6e..60e0640d07dc 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
@@ -57,7 +57,7 @@
 #include "iwl-prph.h"
 
 /* Highest firmware API version supported */
-#define IWL_22000_UCODE_API_MAX	56
+#define IWL_22000_UCODE_API_MAX	57
 
 /* Lowest firmware API version supported */
 #define IWL_22000_UCODE_API_MIN	39
@@ -89,6 +89,9 @@
 #define IWL_SO_A_GF4_A_FW_PRE		"iwlwifi-so-a0-gf4-a0-"
 #define IWL_SNJ_A_GF4_A_FW_PRE		"iwlwifi-SoSnj-a0-gf4-a0-"
 #define IWL_SNJ_A_GF_A_FW_PRE		"iwlwifi-SoSnj-a0-gf-a0-"
+#define IWL_SNJ_A_HR_B_FW_PRE		"iwlwifi-SoSnj-a0-hr-b0-"
+#define IWL_MA_A_GF_A_FW_PRE		"iwlwifi-ma-a0-gf-a0-"
+#define IWL_MA_A_MR_A_FW_PRE		"iwlwifi-ma-a0-mr-a0-"
 
 #define IWL_QU_B_HR_B_MODULE_FIRMWARE(api) \
 	IWL_QU_B_HR_B_FW_PRE __stringify(api) ".ucode"
@@ -118,6 +121,12 @@
 	IWL_SNJ_A_GF4_A_FW_PRE __stringify(api) ".ucode"
 #define IWL_SNJ_A_GF_A_MODULE_FIRMWARE(api) \
 	IWL_SNJ_A_GF_A_FW_PRE __stringify(api) ".ucode"
+#define IWL_SNJ_A_HR_B_MODULE_FIRMWARE(api) \
+	IWL_SNJ_A_HR_B_FW_PRE __stringify(api) ".ucode"
+#define IWL_MA_A_GF_A_FW_MODULE_FIRMWARE(api) \
+	IWL_MA_A_GF_A_FW_PRE __stringify(api) ".ucode"
+#define IWL_MA_A_MR_A_FW_MODULE_FIRMWARE(api) \
+	IWL_MA_A_MR_A_FW_PRE __stringify(api) ".ucode"
 
 static const struct iwl_base_params iwl_22000_base_params = {
 	.eeprom_size = OTP_LOW_IMAGE_SIZE_32K,
@@ -335,14 +344,32 @@ const struct iwl_cfg_trans_params iwl_ax200_trans_cfg = {
 	.bisr_workaround = 1,
 };
 
+const struct iwl_cfg_trans_params iwl_ma_trans_cfg = {
+	.device_family = IWL_DEVICE_FAMILY_AX210,
+	.base_params = &iwl_ax210_base_params,
+	.mq_rx_supported = true,
+	.use_tfh = true,
+	.rf_id = true,
+	.gen2 = true,
+	.integrated = true,
+	.umac_prph_offset = 0x300000
+};
+
+const char iwl_ax101_name[] = "Intel(R) Wi-Fi 6 AX101";
 const char iwl_ax200_name[] = "Intel(R) Wi-Fi 6 AX200 160MHz";
 const char iwl_ax201_name[] = "Intel(R) Wi-Fi 6 AX201 160MHz";
-const char iwl_ax101_name[] = "Intel(R) Wi-Fi 6 AX101";
+const char iwl_ax211_name[] = "Intel(R) Wi-Fi 6 AX211 160MHz";
+const char iwl_ax411_name[] = "Intel(R) Wi-Fi 6 AX411 160MHz";
+const char iwl_ma_name[] = "Intel(R) Wi-Fi 6";
 
 const char iwl_ax200_killer_1650w_name[] =
 	"Killer(R) Wi-Fi 6 AX1650w 160MHz Wireless Network Adapter (200D2W)";
 const char iwl_ax200_killer_1650x_name[] =
 	"Killer(R) Wi-Fi 6 AX1650x 160MHz Wireless Network Adapter (200NGW)";
+const char iwl_ax201_killer_1650s_name[] =
+	"Killer(R) Wi-Fi 6 AX1650s 160MHz Wireless Network Adapter (201D2W)";
+const char iwl_ax201_killer_1650i_name[] =
+	"Killer(R) Wi-Fi 6 AX1650i 160MHz Wireless Network Adapter (201NGW)";
 
 const struct iwl_cfg iwl_qu_b0_hr1_b0 = {
 	.fw_name_pre = IWL_QU_B_HR_B_FW_PRE,
@@ -539,7 +566,7 @@ const struct iwl_cfg iwlax210_2ax_cfg_so_hr_a0 = {
 };
 
 const struct iwl_cfg iwlax211_2ax_cfg_so_gf_a0 = {
-	.name = "Intel(R) Wi-Fi 6 AX211 160MHz",
+	.name = iwl_ax211_name,
 	.fw_name_pre = IWL_SO_A_GF_A_FW_PRE,
 	.uhb_supported = true,
 	IWL_DEVICE_AX210,
@@ -547,7 +574,7 @@ const struct iwl_cfg iwlax211_2ax_cfg_so_gf_a0 = {
 };
 
 const struct iwl_cfg iwlax211_2ax_cfg_so_gf_a0_long = {
-	.name = "Intel(R) Wi-Fi 6 AX211 160MHz",
+	.name = iwl_ax211_name,
 	.fw_name_pre = IWL_SO_A_GF_A_FW_PRE,
 	.uhb_supported = true,
 	IWL_DEVICE_AX210,
@@ -565,7 +592,7 @@ const struct iwl_cfg iwlax210_2ax_cfg_ty_gf_a0 = {
 };
 
 const struct iwl_cfg iwlax411_2ax_cfg_so_gf4_a0 = {
-	.name = "Intel(R) Wi-Fi 6 AX411 160MHz",
+	.name = iwl_ax411_name,
 	.fw_name_pre = IWL_SO_A_GF4_A_FW_PRE,
 	.uhb_supported = true,
 	IWL_DEVICE_AX210,
@@ -573,7 +600,7 @@ const struct iwl_cfg iwlax411_2ax_cfg_so_gf4_a0 = {
 };
 
 const struct iwl_cfg iwlax411_2ax_cfg_so_gf4_a0_long = {
-	.name = "Intel(R) Wi-Fi 6 AX411 160MHz",
+	.name = iwl_ax411_name,
 	.fw_name_pre = IWL_SO_A_GF4_A_FW_PRE,
 	.uhb_supported = true,
 	IWL_DEVICE_AX210,
@@ -583,7 +610,7 @@ const struct iwl_cfg iwlax411_2ax_cfg_so_gf4_a0_long = {
 };
 
 const struct iwl_cfg iwlax411_2ax_cfg_sosnj_gf4_a0 = {
-	.name = "Intel(R) Wi-Fi 6 AX411 160MHz",
+	.name = iwl_ax411_name,
 	.fw_name_pre = IWL_SNJ_A_GF4_A_FW_PRE,
 	.uhb_supported = true,
 	IWL_DEVICE_AX210,
@@ -591,13 +618,35 @@ const struct iwl_cfg iwlax411_2ax_cfg_sosnj_gf4_a0 = {
 };
 
 const struct iwl_cfg iwlax211_cfg_snj_gf_a0 = {
-	.name = "Intel(R) Wi-Fi 6 AX211 160MHz",
+	.name = iwl_ax211_name,
 	.fw_name_pre = IWL_SNJ_A_GF_A_FW_PRE,
 	.uhb_supported = true,
 	IWL_DEVICE_AX210,
 	.num_rbds = IWL_NUM_RBDS_AX210_HE,
 };
 
+const struct iwl_cfg iwlax201_cfg_snj_hr_b0 = {
+	.name = iwl_ax201_name,
+	.fw_name_pre = IWL_QU_B_HR_B_FW_PRE,
+	.uhb_supported = true,
+	IWL_DEVICE_AX210,
+	.num_rbds = IWL_NUM_RBDS_AX210_HE,
+};
+
+const struct iwl_cfg iwl_cfg_ma_a0_gf_a0 = {
+	.fw_name_pre = IWL_MA_A_GF_A_FW_PRE,
+	.uhb_supported = true,
+	IWL_DEVICE_AX210,
+	.num_rbds = IWL_NUM_RBDS_AX210_HE,
+};
+
+const struct iwl_cfg iwl_cfg_ma_a0_mr_a0 = {
+	.fw_name_pre = IWL_MA_A_MR_A_FW_PRE,
+	.uhb_supported = true,
+	IWL_DEVICE_AX210,
+	.num_rbds = IWL_NUM_RBDS_AX210_HE,
+};
+
 MODULE_FIRMWARE(IWL_QU_B_HR_B_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
 MODULE_FIRMWARE(IWL_QNJ_B_HR_B_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
 MODULE_FIRMWARE(IWL_QU_C_HR_B_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
@@ -612,3 +661,6 @@ MODULE_FIRMWARE(IWL_SO_A_GF_A_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
 MODULE_FIRMWARE(IWL_TY_A_GF_A_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
 MODULE_FIRMWARE(IWL_SNJ_A_GF4_A_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
 MODULE_FIRMWARE(IWL_SNJ_A_GF_A_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
+MODULE_FIRMWARE(IWL_SNJ_A_HR_B_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
+MODULE_FIRMWARE(IWL_MA_A_GF_A_FW_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
+MODULE_FIRMWARE(IWL_MA_A_MR_A_FW_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
index dc769b580431..e93656e461ea 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
@@ -118,8 +118,8 @@ IWL_EXPORT_SYMBOL(iwl_acpi_get_object);
 * method (DSM) interface. The returned acpi object must be freed by calling
 * function.
 */
-void *iwl_acpi_get_dsm_object(struct device *dev, int rev, int func,
-			      union acpi_object *args)
+static void *iwl_acpi_get_dsm_object(struct device *dev, int rev, int func,
+				     union acpi_object *args)
 {
 	union acpi_object *obj;
 
@@ -400,9 +400,9 @@ out_free:
 }
 IWL_EXPORT_SYMBOL(iwl_acpi_get_eckv);
 
-int iwl_sar_set_profile(union acpi_object *table,
-			struct iwl_sar_profile *profile,
-			bool enabled)
+static int iwl_sar_set_profile(union acpi_object *table,
+			       struct iwl_sar_profile *profile,
+			       bool enabled)
 {
 	int i;
 
@@ -418,18 +418,13 @@ int iwl_sar_set_profile(union acpi_object *table,
 
 	return 0;
 }
-IWL_EXPORT_SYMBOL(iwl_sar_set_profile);
 
-int iwl_sar_select_profile(struct iwl_fw_runtime *fwrt,
-			   __le16 per_chain_restriction[][IWL_NUM_SUB_BANDS],
-			   int prof_a, int prof_b)
+static int iwl_sar_fill_table(struct iwl_fw_runtime *fwrt,
+			      __le16 *per_chain, u32 n_subbands,
+			      int prof_a, int prof_b)
 {
-	int i, j, idx;
 	int profs[ACPI_SAR_NUM_CHAIN_LIMITS] = { prof_a, prof_b };
-
-	BUILD_BUG_ON(ACPI_SAR_NUM_CHAIN_LIMITS < 2);
-	BUILD_BUG_ON(ACPI_SAR_NUM_CHAIN_LIMITS * ACPI_SAR_NUM_SUB_BANDS !=
-		     ACPI_SAR_TABLE_SIZE);
+	int i, j, idx;
 
 	for (i = 0; i < ACPI_SAR_NUM_CHAIN_LIMITS; i++) {
 		struct iwl_sar_profile *prof;
@@ -461,9 +456,9 @@ int iwl_sar_select_profile(struct iwl_fw_runtime *fwrt,
 			       "SAR EWRD: chain %d profile index %d\n",
 			       i, profs[i]);
 		IWL_DEBUG_RADIO(fwrt, "  Chain[%d]:\n", i);
-		for (j = 0; j < ACPI_SAR_NUM_SUB_BANDS; j++) {
-			idx = (i * ACPI_SAR_NUM_SUB_BANDS) + j;
-			per_chain_restriction[i][j] =
+		for (j = 0; j < n_subbands; j++) {
+			idx = i * ACPI_SAR_NUM_SUB_BANDS + j;
+			per_chain[i * n_subbands + j] =
 				cpu_to_le16(prof->table[idx]);
 			IWL_DEBUG_RADIO(fwrt, "    Band[%d] = %d * .125dBm\n",
 					j, prof->table[idx]);
@@ -472,6 +467,23 @@ int iwl_sar_select_profile(struct iwl_fw_runtime *fwrt,
 
 	return 0;
 }
+
+int iwl_sar_select_profile(struct iwl_fw_runtime *fwrt,
+			   __le16 *per_chain, u32 n_tables, u32 n_subbands,
+			   int prof_a, int prof_b)
+{
+	int i, ret = 0;
+
+	for (i = 0; i < n_tables; i++) {
+		ret = iwl_sar_fill_table(fwrt,
+			 &per_chain[i * n_subbands * ACPI_SAR_NUM_CHAIN_LIMITS],
+			 n_subbands, prof_a, prof_b);
+		if (ret)
+			break;
+	}
+
+	return ret;
+}
 IWL_EXPORT_SYMBOL(iwl_sar_select_profile);
 
 int iwl_sar_get_wrds_table(struct iwl_fw_runtime *fwrt)
@@ -632,25 +644,8 @@ bool iwl_sar_geo_support(struct iwl_fw_runtime *fwrt)
 }
 IWL_EXPORT_SYMBOL(iwl_sar_geo_support);
 
-int iwl_validate_sar_geo_profile(struct iwl_fw_runtime *fwrt,
-				 struct iwl_host_cmd *cmd)
-{
-	struct iwl_geo_tx_power_profiles_resp *resp;
-	int ret;
-
-	resp = (void *)cmd->resp_pkt->data;
-	ret = le32_to_cpu(resp->profile_idx);
-	if (WARN_ON(ret > ACPI_NUM_GEO_PROFILES)) {
-		ret = -EIO;
-		IWL_WARN(fwrt, "Invalid geographic profile idx (%d)\n", ret);
-	}
-
-	return ret;
-}
-IWL_EXPORT_SYMBOL(iwl_validate_sar_geo_profile);
-
 int iwl_sar_geo_init(struct iwl_fw_runtime *fwrt,
-		     struct iwl_per_chain_offset_group *table)
+		     struct iwl_per_chain_offset *table, u32 n_bands)
 {
 	int ret, i, j;
 
@@ -666,16 +661,11 @@ int iwl_sar_geo_init(struct iwl_fw_runtime *fwrt,
 		return -ENOENT;
 	}
 
-	BUILD_BUG_ON(ACPI_NUM_GEO_PROFILES * ACPI_WGDS_NUM_BANDS *
-		     ACPI_WGDS_TABLE_SIZE + 1 !=  ACPI_WGDS_WIFI_DATA_SIZE);
-
-	BUILD_BUG_ON(ACPI_NUM_GEO_PROFILES > IWL_NUM_GEO_PROFILES);
-
 	for (i = 0; i < ACPI_NUM_GEO_PROFILES; i++) {
 		struct iwl_per_chain_offset *chain =
 			(struct iwl_per_chain_offset *)&table[i];
 
-		for (j = 0; j < ACPI_WGDS_NUM_BANDS; j++) {
+		for (j = 0; j < n_bands; j++) {
 			u8 *value;
 
 			value = &fwrt->geo_profiles[i].values[j *
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/acpi.h b/drivers/net/wireless/intel/iwlwifi/fw/acpi.h
index 0ada9eddb8b1..71ef8647d7b5 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/acpi.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/acpi.h
@@ -89,6 +89,7 @@
 
 #define ACPI_SAR_NUM_CHAIN_LIMITS	2
 #define ACPI_SAR_NUM_SUB_BANDS		5
+#define ACPI_SAR_NUM_TABLES		1
 
 #define ACPI_WRDS_WIFI_DATA_SIZE	(ACPI_SAR_TABLE_SIZE + 2)
 #define ACPI_EWRD_WIFI_DATA_SIZE	((ACPI_SAR_PROFILE_NUM - 1) * \
@@ -107,10 +108,10 @@
 #define ACPI_WGDS_NUM_BANDS		2
 #define ACPI_WGDS_TABLE_SIZE		3
 
-#define ACPI_PPAG_NUM_CHAINS		2
-#define ACPI_PPAG_NUM_SUB_BANDS		5
-#define ACPI_PPAG_WIFI_DATA_SIZE	((ACPI_PPAG_NUM_CHAINS * \
-					ACPI_PPAG_NUM_SUB_BANDS) + 3)
+#define ACPI_PPAG_WIFI_DATA_SIZE	((IWL_NUM_CHAIN_LIMITS * \
+					IWL_NUM_SUB_BANDS) + 3)
+#define ACPI_PPAG_WIFI_DATA_SIZE_V2	((IWL_NUM_CHAIN_LIMITS * \
+					IWL_NUM_SUB_BANDS_V2) + 3)
 
 /* PPAG gain value bounds in 1/8 dBm */
 #define ACPI_PPAG_MIN_LB -16
@@ -133,15 +134,26 @@ enum iwl_dsm_funcs_rev_0 {
 	DSM_FUNC_ENABLE_INDONESIA_5G2 = 2,
 };
 
+enum iwl_dsm_values_srd {
+	DSM_VALUE_SRD_ACTIVE,
+	DSM_VALUE_SRD_PASSIVE,
+	DSM_VALUE_SRD_DISABLE,
+	DSM_VALUE_SRD_MAX
+};
+
+enum iwl_dsm_values_indonesia {
+	DSM_VALUE_INDONESIA_DISABLE,
+	DSM_VALUE_INDONESIA_ENABLE,
+	DSM_VALUE_INDONESIA_RESERVED,
+	DSM_VALUE_INDONESIA_MAX
+};
+
 #ifdef CONFIG_ACPI
 
 struct iwl_fw_runtime;
 
 void *iwl_acpi_get_object(struct device *dev, acpi_string method);
 
-void *iwl_acpi_get_dsm_object(struct device *dev, int rev, int func,
-			      union acpi_object *args);
-
 int iwl_acpi_get_dsm_u8(struct device *dev, int rev, int func);
 
 union acpi_object *iwl_acpi_get_wifi_pkg(struct device *dev,
@@ -171,12 +183,8 @@ u64 iwl_acpi_get_pwr_limit(struct device *dev);
  */
 int iwl_acpi_get_eckv(struct device *dev, u32 *extl_clk);
 
-int iwl_sar_set_profile(union acpi_object *table,
-			struct iwl_sar_profile *profile,
-			bool enabled);
-
 int iwl_sar_select_profile(struct iwl_fw_runtime *fwrt,
-			   __le16 per_chain_restriction[][IWL_NUM_SUB_BANDS],
+			   __le16 *per_chain, u32 n_tables, u32 n_subbands,
 			   int prof_a, int prof_b);
 
 int iwl_sar_get_wrds_table(struct iwl_fw_runtime *fwrt);
@@ -187,11 +195,8 @@ int iwl_sar_get_wgds_table(struct iwl_fw_runtime *fwrt);
 
 bool iwl_sar_geo_support(struct iwl_fw_runtime *fwrt);
 
-int iwl_validate_sar_geo_profile(struct iwl_fw_runtime *fwrt,
-				 struct iwl_host_cmd *cmd);
-
 int iwl_sar_geo_init(struct iwl_fw_runtime *fwrt,
-		     struct iwl_per_chain_offset_group *table);
+		     struct iwl_per_chain_offset *table, u32 n_bands);
 
 int iwl_acpi_get_tas(struct iwl_fw_runtime *fwrt, __le32 *black_list_array,
 		     int *black_list_size);
@@ -237,15 +242,8 @@ static inline int iwl_acpi_get_eckv(struct device *dev, u32 *extl_clk)
 	return -ENOENT;
 }
 
-static inline int iwl_sar_set_profile(union acpi_object *table,
-				      struct iwl_sar_profile *profile,
-				      bool enabled)
-{
-	return -ENOENT;
-}
-
 static inline int iwl_sar_select_profile(struct iwl_fw_runtime *fwrt,
-			   __le16 per_chain_restriction[][IWL_NUM_SUB_BANDS],
+			   __le16 *per_chain, u32 n_tables, u32 n_subbands,
 			   int prof_a, int prof_b)
 {
 	return -ENOENT;
@@ -271,18 +269,6 @@ static inline bool iwl_sar_geo_support(struct iwl_fw_runtime *fwrt)
 	return false;
 }
 
-static inline int iwl_validate_sar_geo_profile(struct iwl_fw_runtime *fwrt,
-					       struct iwl_host_cmd *cmd)
-{
-	return -ENOENT;
-}
-
-static inline int iwl_sar_geo_init(struct iwl_fw_runtime *fwrt,
-				   struct iwl_per_chain_offset_group *table)
-{
-	return -ENOENT;
-}
-
 static inline int iwl_acpi_get_tas(struct iwl_fw_runtime *fwrt,
 				   __le32 *black_list_array,
 				   int *black_list_size)
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/alive.h b/drivers/net/wireless/intel/iwlwifi/fw/api/alive.h
index df1bd0d2450e..a1cac47395bc 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/alive.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/alive.h
@@ -5,10 +5,9 @@
  *
  * GPL LICENSE SUMMARY
  *
- * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
- * Copyright (C) 2018 Intel Corporation
+ * Copyright(c) 2012 - 2014, 2018, 2020 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -31,7 +30,7 @@
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
- * Copyright (C) 2018 Intel Corporation
+ * Copyright(c) 2012 - 2014, 2018, 2020 Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -129,19 +128,31 @@ struct iwl_umac_alive {
 	struct iwl_umac_debug_addrs dbg_ptrs;
 } __packed; /* UMAC_ALIVE_DATA_API_S_VER_2 */
 
-struct mvm_alive_resp_v3 {
+struct iwl_sku_id {
+	__le32 data[3];
+} __packed; /* SKU_ID_API_S_VER_1 */
+
+struct iwl_alive_ntf_v3 {
 	__le16 status;
 	__le16 flags;
 	struct iwl_lmac_alive lmac_data;
 	struct iwl_umac_alive umac_data;
-} __packed; /* ALIVE_RES_API_S_VER_3 */
+} __packed; /* UCODE_ALIVE_NTFY_API_S_VER_3 */
+
+struct iwl_alive_ntf_v4 {
+	__le16 status;
+	__le16 flags;
+	struct iwl_lmac_alive lmac_data[2];
+	struct iwl_umac_alive umac_data;
+} __packed; /* UCODE_ALIVE_NTFY_API_S_VER_4 */
 
-struct mvm_alive_resp {
+struct iwl_alive_ntf_v5 {
 	__le16 status;
 	__le16 flags;
 	struct iwl_lmac_alive lmac_data[2];
 	struct iwl_umac_alive umac_data;
-} __packed; /* ALIVE_RES_API_S_VER_4 */
+	struct iwl_sku_id sku_id;
+} __packed; /* UCODE_ALIVE_NTFY_API_S_VER_5 */
 
 /**
  * enum iwl_extended_cfg_flag - commands driver may send before
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h b/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h
index 4f46f3ed8794..14975a7e7203 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h
@@ -104,11 +104,12 @@ enum iwl_mvm_command_groups {
  */
 enum iwl_legacy_cmds {
 	/**
-	 * @MVM_ALIVE:
+	 * @UCODE_ALIVE_NTFY:
 	 * Alive data from the firmware, as described in
-	 * &struct mvm_alive_resp_v3 or &struct mvm_alive_resp.
+	 * &struct iwl_alive_ntf_v3 or &struct iwl_alive_ntf_v4 or
+	 * &struct iwl_alive_ntf_v5.
 	 */
-	MVM_ALIVE = 0x1,
+	UCODE_ALIVE_NTFY = 0x1,
 
 	/**
 	 * @REPLY_ERROR: Cause an error in the firmware, for testing purposes.
@@ -431,8 +432,7 @@ enum iwl_legacy_cmds {
 
 	/**
 	 * @REDUCE_TX_POWER_CMD:
-	 * &struct iwl_dev_tx_power_cmd_v3 or &struct iwl_dev_tx_power_cmd_v4
-	 * or &struct iwl_dev_tx_power_cmd
+	 * &struct iwl_dev_tx_power_cmd
 	 */
 	REDUCE_TX_POWER_CMD = 0x9f,
 
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/d3.h b/drivers/net/wireless/intel/iwlwifi/fw/api/d3.h
index c4562e1f8d18..5db301a6a312 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/d3.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/d3.h
@@ -8,7 +8,7 @@
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH
  * Copyright(c) 2015 - 2017 Intel Deutschland GmbH
- * Copyright(c) 2018 - 2019 Intel Corporation
+ * Copyright(c) 2018 - 2020 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -31,7 +31,7 @@
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH
  * Copyright(c) 2015 - 2017 Intel Deutschland GmbH
- * Copyright(c) 2018 - 2019 Intel Corporation
+ * Copyright(c) 2018 - 2020 Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -451,10 +451,15 @@ union iwl_all_tsc_rsc {
 	struct iwl_aes_rsc_tsc aes;
 }; /* ALL_TSC_RSC_API_S_VER_2 */
 
-struct iwl_wowlan_rsc_tsc_params_cmd {
+struct iwl_wowlan_rsc_tsc_params_cmd_ver_2 {
 	union iwl_all_tsc_rsc all_tsc_rsc;
 } __packed; /* ALL_TSC_RSC_API_S_VER_2 */
 
+struct iwl_wowlan_rsc_tsc_params_cmd {
+	struct iwl_wowlan_rsc_tsc_params_cmd_ver_2 params;
+	__le32 sta_id;
+} __packed; /* ALL_TSC_RSC_API_S_VER_4 */
+
 #define IWL_MIC_KEY_SIZE	8
 struct iwl_mic_keys {
 	u8 tx[IWL_MIC_KEY_SIZE];
@@ -469,17 +474,26 @@ struct iwl_p1k_cache {
 
 #define IWL_NUM_RX_P1K_CACHE	2
 
-struct iwl_wowlan_tkip_params_cmd {
+struct iwl_wowlan_tkip_params_cmd_ver_1 {
 	struct iwl_mic_keys mic_keys;
 	struct iwl_p1k_cache tx;
 	struct iwl_p1k_cache rx_uni[IWL_NUM_RX_P1K_CACHE];
 	struct iwl_p1k_cache rx_multi[IWL_NUM_RX_P1K_CACHE];
 } __packed; /* WOWLAN_TKIP_SETTING_API_S_VER_1 */
 
+struct iwl_wowlan_tkip_params_cmd {
+	struct iwl_mic_keys mic_keys;
+	struct iwl_p1k_cache tx;
+	struct iwl_p1k_cache rx_uni[IWL_NUM_RX_P1K_CACHE];
+	struct iwl_p1k_cache rx_multi[IWL_NUM_RX_P1K_CACHE];
+	u8     reversed[2];
+	__le32 sta_id;
+} __packed; /* WOWLAN_TKIP_SETTING_API_S_VER_2 */
+
 #define IWL_KCK_MAX_SIZE	32
 #define IWL_KEK_MAX_SIZE	32
 
-struct iwl_wowlan_kek_kck_material_cmd {
+struct iwl_wowlan_kek_kck_material_cmd_v2 {
 	u8	kck[IWL_KCK_MAX_SIZE];
 	u8	kek[IWL_KEK_MAX_SIZE];
 	__le16	kck_len;
@@ -487,6 +501,18 @@ struct iwl_wowlan_kek_kck_material_cmd {
 	__le64	replay_ctr;
 } __packed; /* KEK_KCK_MATERIAL_API_S_VER_2 */
 
+struct iwl_wowlan_kek_kck_material_cmd_v3 {
+	u8	kck[IWL_KCK_MAX_SIZE];
+	u8	kek[IWL_KEK_MAX_SIZE];
+	__le16	kck_len;
+	__le16	kek_len;
+	__le64	replay_ctr;
+	__le32  akm;
+	__le32  gtk_cipher;
+	__le32  igtk_cipher;
+	__le32  bigtk_cipher;
+} __packed; /* KEK_KCK_MATERIAL_API_S_VER_3 */
+
 #define RF_KILL_INDICATOR_FOR_WOWLAN	0x87
 
 enum iwl_wowlan_rekey_status {
@@ -525,7 +551,7 @@ struct iwl_wowlan_gtk_status_v1 {
 	u8 reserved[3];
 	u8 decrypt_key[16];
 	u8 tkip_mic_key[8];
-	struct iwl_wowlan_rsc_tsc_params_cmd rsc;
+	struct iwl_wowlan_rsc_tsc_params_cmd_ver_2 rsc;
 } __packed; /* WOWLAN_GTK_MATERIAL_VER_1 */
 
 #define WOWLAN_KEY_MAX_SIZE	32
@@ -550,7 +576,7 @@ struct iwl_wowlan_gtk_status {
 	u8 key_flags;
 	u8 reserved[2];
 	u8 tkip_mic_key[8];
-	struct iwl_wowlan_rsc_tsc_params_cmd rsc;
+	struct iwl_wowlan_rsc_tsc_params_cmd_ver_2 rsc;
 } __packed; /* WOWLAN_GTK_MATERIAL_VER_2 */
 
 #define IWL_WOWLAN_GTK_IDX_MASK		(BIT(0) | BIT(1))
@@ -635,7 +661,7 @@ struct iwl_wowlan_status_v7 {
 } __packed; /* WOWLAN_STATUSES_API_S_VER_7 */
 
 /**
- * struct iwl_wowlan_status - WoWLAN status
+ * struct iwl_wowlan_status_v9 - WoWLAN status (version 9)
  * @gtk: GTK data
  * @igtk: IGTK data
  * @replay_ctr: GTK rekey replay counter
@@ -653,7 +679,7 @@ struct iwl_wowlan_status_v7 {
  * @reserved: unused
  * @wake_packet: wakeup packet
  */
-struct iwl_wowlan_status {
+struct iwl_wowlan_status_v9 {
 	struct iwl_wowlan_gtk_status gtk[WOWLAN_GTK_KEYS_NUM];
 	struct iwl_wowlan_igtk_status igtk[WOWLAN_IGTK_KEYS_NUM];
 	__le64 replay_ctr;
@@ -671,6 +697,44 @@ struct iwl_wowlan_status {
 	u8 wake_packet[]; /* can be truncated from _length to _bufsize */
 } __packed; /* WOWLAN_STATUSES_API_S_VER_9 */
 
+/**
+ * struct iwl_wowlan_status - WoWLAN status
+ * @gtk: GTK data
+ * @igtk: IGTK data
+ * @bigtk: BIGTK data
+ * @replay_ctr: GTK rekey replay counter
+ * @pattern_number: number of the matched pattern
+ * @non_qos_seq_ctr: non-QoS sequence counter to use next
+ * @qos_seq_ctr: QoS sequence counters to use next
+ * @wakeup_reasons: wakeup reasons, see &enum iwl_wowlan_wakeup_reason
+ * @num_of_gtk_rekeys: number of GTK rekeys
+ * @tid_tear_down: bitmap of TIDs torn down
+ * @reserved: reserved
+ * @received_beacons: number of received beacons
+ * @wake_packet_length: wakeup packet length
+ * @wake_packet_bufsize: wakeup packet buffer size
+ * @tid_tear_down: bit mask of tids whose BA sessions were closed
+ *		   in suspend state
+ * @wake_packet: wakeup packet
+ */
+struct iwl_wowlan_status {
+	struct iwl_wowlan_gtk_status gtk[1];
+	struct iwl_wowlan_igtk_status igtk[1];
+	struct iwl_wowlan_igtk_status bigtk[WOWLAN_IGTK_KEYS_NUM];
+	__le64 replay_ctr;
+	__le16 pattern_number;
+	__le16 non_qos_seq_ctr;
+	__le16 qos_seq_ctr[8];
+	__le32 wakeup_reasons;
+	__le32 num_of_gtk_rekeys;
+	u8 tid_tear_down;
+	u8 reserved[3];
+	__le32 received_beacons;
+	__le32 wake_packet_length;
+	__le32 wake_packet_bufsize;
+	u8 wake_packet[]; /* can be truncated from _length to _bufsize */
+} __packed; /* WOWLAN_STATUSES_API_S_VER_11 */
+
 static inline u8 iwlmvm_wowlan_gtk_idx(struct iwl_wowlan_gtk_status *gtk)
 {
 	return gtk->key_flags & IWL_WOWLAN_GTK_IDX_MASK;
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/dbg-tlv.h b/drivers/net/wireless/intel/iwlwifi/fw/api/dbg-tlv.h
index 74ac65bd545a..95ada51d3f9e 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/dbg-tlv.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/dbg-tlv.h
@@ -135,6 +135,25 @@ struct iwl_fw_ini_region_err_table {
 } __packed; /* FW_TLV_DEBUG_REGION_ERROR_TABLE_API_S_VER_1 */
 
 /**
+ * struct iwl_fw_ini_region_special_device_memory - special device memory
+ *
+ * Configuration to read a special memory
+ *
+ * @type: type of the special memory
+ * @version: version of the special memory
+ * @base_addr: base address of the error table
+ * @size: size of the error table
+ * @offset: offset to add to &base_addr
+ */
+struct iwl_fw_ini_region_special_device_memory {
+	__le16 type;
+	__le16 version;
+	__le32 base_addr;
+	__le32 size;
+	__le32 offset;
+} __packed; /* FW_TLV_DEBUG_REGION_SPECIAL_DEVICE_ADDR_API_S_VER_1 */
+
+/**
  * struct iwl_fw_ini_region_internal_buffer - internal buffer region data
  *
  * Configuration to read internal monitor buffer
@@ -185,6 +204,7 @@ struct iwl_fw_ini_region_tlv {
 		struct iwl_fw_ini_region_fifos fifos;
 		struct iwl_fw_ini_region_err_table err_table;
 		struct iwl_fw_ini_region_internal_buffer internal_buffer;
+		struct iwl_fw_ini_region_special_device_memory special_mem;
 		__le32 dram_alloc_id;
 		__le32 tlv_mask;
 	}; /* FW_TLV_DEBUG_REGION_CONF_PARAMS_API_U_VER_1 */
@@ -281,6 +301,7 @@ struct iwl_fw_ini_hcmd_tlv {
  * @IWL_FW_INI_ALLOCATION_ID_DBGC1: allocation meant for DBGC1 configuration
  * @IWL_FW_INI_ALLOCATION_ID_DBGC2: allocation meant for DBGC2 configuration
  * @IWL_FW_INI_ALLOCATION_ID_DBGC3: allocation meant for DBGC3 configuration
+ * @IWL_FW_INI_ALLOCATION_ID_INTERNAL: allocation meant for Intreanl SMEM in D3
  * @IWL_FW_INI_ALLOCATION_NUM: number of allocation ids
 */
 enum iwl_fw_ini_allocation_id {
@@ -288,6 +309,7 @@ enum iwl_fw_ini_allocation_id {
 	IWL_FW_INI_ALLOCATION_ID_DBGC1,
 	IWL_FW_INI_ALLOCATION_ID_DBGC2,
 	IWL_FW_INI_ALLOCATION_ID_DBGC3,
+	IWL_FW_INI_ALLOCATION_ID_INTERNAL,
 	IWL_FW_INI_ALLOCATION_NUM,
 }; /* FW_DEBUG_TLV_ALLOCATION_ID_E_VER_1 */
 
@@ -327,6 +349,7 @@ enum iwl_fw_ini_buffer_location {
  * @IWL_FW_INI_REGION_CSR: CSR registers
  * @IWL_FW_INI_REGION_DRAM_IMR: IMR memory
  * @IWL_FW_INI_REGION_PCI_IOSF_CONFIG: PCI/IOSF config
+ * @IWL_FW_INI_REGION_SPECIAL_DEVICE_MEMORY: special device memory
  * @IWL_FW_INI_REGION_NUM: number of region types
  */
 enum iwl_fw_ini_region_type {
@@ -347,6 +370,7 @@ enum iwl_fw_ini_region_type {
 	IWL_FW_INI_REGION_CSR,
 	IWL_FW_INI_REGION_DRAM_IMR,
 	IWL_FW_INI_REGION_PCI_IOSF_CONFIG,
+	IWL_FW_INI_REGION_SPECIAL_DEVICE_MEMORY,
 	IWL_FW_INI_REGION_NUM
 }; /* FW_TLV_DEBUG_REGION_TYPE_API_E */
 
@@ -362,13 +386,13 @@ enum iwl_fw_ini_region_type {
  * @IWL_FW_INI_TIME_POINT_FW_ASSERT: FW assert
  * @IWL_FW_INI_TIME_POINT_FW_HW_ERROR: FW HW error
  * @IWL_FW_INI_TIME_POINT_FW_TFD_Q_HANG: TFD queue hang
- * @IWL_FW_INI_TIME_POINT_FW_DHC_NOTIFOCATION: DHC cmd response and notif
+ * @IWL_FW_INI_TIME_POINT_FW_DHC_NOTIFICATION: DHC cmd response and notif
  * @IWL_FW_INI_TIME_POINT_FW_RSP_OR_NOTIF: FW response or notification.
  *	data field holds id and group
  * @IWL_FW_INI_TIME_POINT_USER_TRIGGER: user trigger time point
  * @IWL_FW_INI_TIME_POINT_PERIODIC: periodic timepoint that fires in constant
  *	intervals. data field holds the interval time in msec
- * @IWL_FW_INI_TIME_POINT_WDG_TIMEOUT: watchdog timeout
+ * @IWL_FW_INI_TIME_POINT_RESERVED: reserved
  * @IWL_FW_INI_TIME_POINT_HOST_ASSERT: Unused
  * @IWL_FW_INI_TIME_POINT_HOST_ALIVE_TIMEOUT: alive timeout
  * @IWL_FW_INI_TIME_POINT_HOST_DEVICE_ENABLE: device enable
@@ -395,11 +419,11 @@ enum iwl_fw_ini_time_point {
 	IWL_FW_INI_TIME_POINT_FW_ASSERT,
 	IWL_FW_INI_TIME_POINT_FW_HW_ERROR,
 	IWL_FW_INI_TIME_POINT_FW_TFD_Q_HANG,
-	IWL_FW_INI_TIME_POINT_FW_DHC_NOTIFOCATION,
+	IWL_FW_INI_TIME_POINT_FW_DHC_NOTIFICATION,
 	IWL_FW_INI_TIME_POINT_FW_RSP_OR_NOTIF,
 	IWL_FW_INI_TIME_POINT_USER_TRIGGER,
 	IWL_FW_INI_TIME_POINT_PERIODIC,
-	IWL_FW_INI_TIME_POINT_WDG_TIMEOUT,
+	IWL_FW_INI_TIME_POINT_RESERVED,
 	IWL_FW_INI_TIME_POINT_HOST_ASSERT,
 	IWL_FW_INI_TIME_POINT_HOST_ALIVE_TIMEOUT,
 	IWL_FW_INI_TIME_POINT_HOST_DEVICE_ENABLE,
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/location.h b/drivers/net/wireless/intel/iwlwifi/fw/api/location.h
index 1df2e497fabf..465a8e3974e8 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/location.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/location.h
@@ -321,12 +321,54 @@ struct iwl_tof_responder_config_cmd {
  *	data (if exists) follows, and then 0-padding again to complete a
  *	4-multiple long buffer.
  */
-struct iwl_tof_responder_dyn_config_cmd {
+struct iwl_tof_responder_dyn_config_cmd_v2 {
 	__le32 lci_len;
 	__le32 civic_len;
 	u8 lci_civic[];
 } __packed; /* TOF_RESPONDER_DYN_CONFIG_CMD_API_S_VER_2 */
 
+#define IWL_LCI_MAX_SIZE	160
+#define IWL_CIVIC_MAX_SIZE	160
+#define HLTK_11AZ_LEN	32
+
+/**
+ * enum iwl_responder_dyn_cfg_valid_flags - valid flags for dyn_config_cmd
+ * @IWL_RESPONDER_DYN_CFG_VALID_LCI: LCI data is valid
+ * @IWL_RESPONDER_DYN_CFG_VALID_CIVIC: Civic data is valid
+ * @IWL_RESPONDER_DYN_CFG_VALID_PASN_STA: the pasn_addr, HLTK and cipher fields
+ *	are valid.
+ */
+enum iwl_responder_dyn_cfg_valid_flags {
+	IWL_RESPONDER_DYN_CFG_VALID_LCI = BIT(0),
+	IWL_RESPONDER_DYN_CFG_VALID_CIVIC = BIT(1),
+	IWL_RESPONDER_DYN_CFG_VALID_PASN_STA = BIT(2),
+};
+
+/**
+ * struct iwl_tof_responder_dyn_config_cmd - Dynamic responder settings
+ * @cipher: The negotiated cipher. see &enum iwl_location_cipher.
+ * @valid_flags: flags indicating which fields in the command are valid. see
+ *	&enum iwl_responder_dyn_cfg_valid_flags.
+ * @lci_len: length of the LCI data in bytes
+ * @civic_len: length of the Civic data in bytes
+ * @lci_buf: the LCI buffer
+ * @civic_buf: the Civic buffer
+ * @hltk_buf: HLTK for secure LTF bits generation for the specified station
+ * @addr: mac address of the station for which to use the HLTK
+ * @reserved: for alignment
+ */
+struct iwl_tof_responder_dyn_config_cmd {
+	u8 cipher;
+	u8 valid_flags;
+	u8 lci_len;
+	u8 civic_len;
+	u8 lci_buf[IWL_LCI_MAX_SIZE];
+	u8 civic_buf[IWL_LCI_MAX_SIZE];
+	u8 hltk_buf[HLTK_11AZ_LEN];
+	u8 addr[ETH_ALEN];
+	u8 reserved[2];
+} __packed; /* TOF_RESPONDER_DYN_CONFIG_CMD_API_S_VER_3 */
+
 /**
  * struct iwl_tof_range_req_ext_cmd - extended range req for WLS
  * @tsf_timer_offset_msec: the recommended time offset (mSec) from the AP's TSF
@@ -507,7 +549,6 @@ enum iwl_location_bw {
 	IWL_LOCATION_BW_80MHZ,
 };
 
-#define HLTK_11AZ_LEN	32
 #define TK_11AZ_LEN	32
 
 #define LOCATION_BW_POS	4
@@ -552,15 +593,19 @@ struct iwl_tof_range_req_ap_entry_v4 {
  * @IWL_LOCATION_CIPHER_CCMP_128: CCMP 128
  * @IWL_LOCATION_CIPHER_GCMP_128: GCMP 128
  * @IWL_LOCATION_CIPHER_GCMP_256: GCMP 256
+ * @IWL_LOCATION_CIPHER_INVALID: security is not used.
+ * @IWL_LOCATION_CIPHER_MAX: maximum value for this enum.
  */
 enum iwl_location_cipher {
 	IWL_LOCATION_CIPHER_CCMP_128,
 	IWL_LOCATION_CIPHER_GCMP_128,
 	IWL_LOCATION_CIPHER_GCMP_256,
+	IWL_LOCATION_CIPHER_INVALID,
+	IWL_LOCATION_CIPHER_MAX,
 };
 
 /**
- * struct iwl_tof_range_req_ap_entry - AP configuration parameters
+ * struct iwl_tof_range_req_ap_entry_v6 - AP configuration parameters
  * @initiator_ap_flags: see &enum iwl_initiator_ap_flags.
  * @channel_num: AP Channel number
  * @format_bw: bits 0 - 3: &enum iwl_location_frame_format.
@@ -588,7 +633,7 @@ enum iwl_location_cipher {
  * @beacon_interval: beacon interval of the AP in TUs. Only required if
  *	&IWL_INITIATOR_AP_FLAGS_TB is set.
  */
-struct iwl_tof_range_req_ap_entry {
+struct iwl_tof_range_req_ap_entry_v6 {
 	__le32 initiator_ap_flags;
 	u8 channel_num;
 	u8 format_bw;
@@ -607,6 +652,61 @@ struct iwl_tof_range_req_ap_entry {
 } __packed; /* LOCATION_RANGE_REQ_AP_ENTRY_CMD_API_S_VER_6 */
 
 /**
+ * struct iwl_tof_range_req_ap_entry_v7 - AP configuration parameters
+ * @initiator_ap_flags: see &enum iwl_initiator_ap_flags.
+ * @channel_num: AP Channel number
+ * @format_bw: bits 0 - 3: &enum iwl_location_frame_format.
+ *             bits 4 - 7: &enum iwl_location_bw.
+ * @ctrl_ch_position: Coding of the control channel position relative to the
+ *	center frequency, see iwl_mvm_get_ctrl_pos().
+ * @ftmr_max_retries: Max number of retries to send the FTMR in case of no
+ *	reply from the AP.
+ * @bssid: AP's BSSID
+ * @burst_period: Recommended value to be sent to the AP. Measurement
+ *	periodicity In units of 100ms. ignored if num_of_bursts_exp = 0
+ * @samples_per_burst: the number of FTMs pairs in single Burst (1-31);
+ * @num_of_bursts: Recommended value to be sent to the AP. 2s Exponent of
+ *	the number of measurement iterations (min 2^0 = 1, max 2^14)
+ * @sta_id: the station id of the AP. Only relevant when associated to the AP,
+ *	otherwise should be set to &IWL_MVM_INVALID_STA.
+ * @cipher: pairwise cipher suite for secured measurement.
+ *          &enum iwl_location_cipher.
+ * @hltk: HLTK to be used for secured 11az measurement
+ * @tk: TK to be used for secured 11az measurement
+ * @calib: An array of calibration values per FTM rx bandwidth.
+ *         If &IWL_INITIATOR_AP_FLAGS_USE_CALIB is set, the fw will use the
+ *         calibration value that corresponds to the rx bandwidth of the FTM
+ *         frame.
+ * @beacon_interval: beacon interval of the AP in TUs. Only required if
+ *	&IWL_INITIATOR_AP_FLAGS_TB is set.
+ * @rx_pn: the next expected PN for protected management frames Rx. LE byte
+ *	order. Only valid if &IWL_INITIATOR_AP_FLAGS_SECURED is set and sta_id
+ *	is set to &IWL_MVM_INVALID_STA.
+ * @tx_pn: the next PN to use for protected management frames Tx. LE byte
+ *	order. Only valid if &IWL_INITIATOR_AP_FLAGS_SECURED is set and sta_id
+ *	is set to &IWL_MVM_INVALID_STA.
+ */
+struct iwl_tof_range_req_ap_entry_v7 {
+	__le32 initiator_ap_flags;
+	u8 channel_num;
+	u8 format_bw;
+	u8 ctrl_ch_position;
+	u8 ftmr_max_retries;
+	u8 bssid[ETH_ALEN];
+	__le16 burst_period;
+	u8 samples_per_burst;
+	u8 num_of_bursts;
+	u8 sta_id;
+	u8 cipher;
+	u8 hltk[HLTK_11AZ_LEN];
+	u8 tk[TK_11AZ_LEN];
+	__le16 calib[IWL_TOF_BW_NUM];
+	__le16 beacon_interval;
+	u8 rx_pn[IEEE80211_CCMP_PN_LEN];
+	u8 tx_pn[IEEE80211_CCMP_PN_LEN];
+} __packed; /* LOCATION_RANGE_REQ_AP_ENTRY_CMD_API_S_VER_7 */
+
+/**
  * enum iwl_tof_response_mode
  * @IWL_MVM_TOF_RESPONSE_ASAP: report each AP measurement separately as soon as
  *			       possible (not supported for this release)
@@ -772,7 +872,7 @@ struct iwl_tof_range_req_cmd_v8 {
 } __packed; /* LOCATION_RANGE_REQ_CMD_API_S_VER_8 */
 
 /**
- * struct iwl_tof_range_req_cmd - start measurement cmd
+ * struct iwl_tof_range_req_cmd_v9 - start measurement cmd
  * @initiator_flags: see flags @ iwl_tof_initiator_flags
  * @request_id: A Token incremented per request. The same Token will be
  *		sent back in the range response
@@ -787,7 +887,7 @@ struct iwl_tof_range_req_cmd_v8 {
  *	TSF of this mac id. 0xff to disable TSF reporting.
  * @ap: per-AP request data, see &struct iwl_tof_range_req_ap_entry_v2.
  */
-struct iwl_tof_range_req_cmd {
+struct iwl_tof_range_req_cmd_v9 {
 	__le32 initiator_flags;
 	u8 request_id;
 	u8 num_of_ap;
@@ -796,9 +896,37 @@ struct iwl_tof_range_req_cmd {
 	u8 macaddr_template[ETH_ALEN];
 	__le32 req_timeout_ms;
 	__le32 tsf_mac_id;
-	struct iwl_tof_range_req_ap_entry ap[IWL_MVM_TOF_MAX_APS];
+	struct iwl_tof_range_req_ap_entry_v6 ap[IWL_MVM_TOF_MAX_APS];
 } __packed; /* LOCATION_RANGE_REQ_CMD_API_S_VER_9 */
 
+/**
+ * struct iwl_tof_range_req_cmd_v11 - start measurement cmd
+ * @initiator_flags: see flags @ iwl_tof_initiator_flags
+ * @request_id: A Token incremented per request. The same Token will be
+ *		sent back in the range response
+ * @num_of_ap: Number of APs to measure (error if > IWL_MVM_TOF_MAX_APS)
+ * @range_req_bssid: ranging request BSSID
+ * @macaddr_mask: Bits set to 0 shall be copied from the MAC address template.
+ *		  Bits set to 1 shall be randomized by the UMAC
+ * @macaddr_template: MAC address template to use for non-randomized bits
+ * @req_timeout_ms: Requested timeout of the response in units of milliseconds.
+ *	This is the session time for completing the measurement.
+ * @tsf_mac_id: report the measurement start time for each ap in terms of the
+ *	TSF of this mac id. 0xff to disable TSF reporting.
+ * @ap: per-AP request data, see &struct iwl_tof_range_req_ap_entry_v2.
+ */
+struct iwl_tof_range_req_cmd_v11 {
+	__le32 initiator_flags;
+	u8 request_id;
+	u8 num_of_ap;
+	u8 range_req_bssid[ETH_ALEN];
+	u8 macaddr_mask[ETH_ALEN];
+	u8 macaddr_template[ETH_ALEN];
+	__le32 req_timeout_ms;
+	__le32 tsf_mac_id;
+	struct iwl_tof_range_req_ap_entry_v7 ap[IWL_MVM_TOF_MAX_APS];
+} __packed; /* LOCATION_RANGE_REQ_CMD_API_S_VER_11 */
+
 /*
  * enum iwl_tof_range_request_status - status of the sent request
  * @IWL_TOF_RANGE_REQUEST_STATUS_SUCCESSFUL - FW successfully received the
@@ -960,7 +1088,7 @@ struct iwl_tof_range_rsp_ap_entry_ntfy_v4 {
 } __packed; /* LOCATION_RANGE_RSP_AP_ETRY_NTFY_API_S_VER_4 */
 
 /**
- * struct iwl_tof_range_rsp_ap_entry_ntfy - AP parameters (response)
+ * struct iwl_tof_range_rsp_ap_entry_ntfy_v5 - AP parameters (response)
  * @bssid: BSSID of the AP
  * @measure_status: current APs measurement status, one of
  *	&enum iwl_tof_entry_status.
@@ -992,7 +1120,7 @@ struct iwl_tof_range_rsp_ap_entry_ntfy_v4 {
  * @rttConfidence: a value between 0 - 31 that represents the rtt accuracy.
  * @reserved: for alignment
  */
-struct iwl_tof_range_rsp_ap_entry_ntfy {
+struct iwl_tof_range_rsp_ap_entry_ntfy_v5 {
 	u8 bssid[ETH_ALEN];
 	u8 measure_status;
 	u8 measure_bw;
@@ -1017,6 +1145,69 @@ struct iwl_tof_range_rsp_ap_entry_ntfy {
 } __packed; /* LOCATION_RANGE_RSP_AP_ETRY_NTFY_API_S_VER_5 */
 
 /**
+ * struct iwl_tof_range_rsp_ap_entry_ntfy_v6 - AP parameters (response)
+ * @bssid: BSSID of the AP
+ * @measure_status: current APs measurement status, one of
+ *	&enum iwl_tof_entry_status.
+ * @measure_bw: Current AP Bandwidth: 0  20MHz, 1  40MHz, 2  80MHz
+ * @rtt: The Round Trip Time that took for the last measurement for
+ *	current AP [pSec]
+ * @rtt_variance: The Variance of the RTT values measured for current AP
+ * @rtt_spread: The Difference between the maximum and the minimum RTT
+ *	values measured for current AP in the current session [pSec]
+ * @rssi: RSSI as uploaded in the Channel Estimation notification
+ * @rssi_spread: The Difference between the maximum and the minimum RSSI values
+ *	measured for current AP in the current session
+ * @last_burst: 1 if no more FTM sessions are scheduled for this responder
+ * @refusal_period: refusal period in case of
+ *	@IWL_TOF_ENTRY_RESPONDER_CANNOT_COLABORATE [sec]
+ * @timestamp: The GP2 Clock [usec] where Channel Estimation notification was
+ *	uploaded by the LMAC
+ * @start_tsf: measurement start time in TSF of the mac specified in the range
+ *	request
+ * @rx_rate_n_flags: rate and flags of the last FTM frame received from this
+ *	responder
+ * @tx_rate_n_flags: rate and flags of the last ack sent to this responder
+ * @t2t3_initiator: as calculated from the algo in the initiator
+ * @t1t4_responder: as calculated from the algo in the responder
+ * @common_calib: Calib val that was used in for this AP measurement
+ * @specific_calib: val that was used in for this AP measurement
+ * @papd_calib_output: The result of the tof papd calibration that was injected
+ *	into the algorithm.
+ * @rttConfidence: a value between 0 - 31 that represents the rtt accuracy.
+ * @reserved: for alignment
+ * @rx_pn: the last PN used for this responder Rx in case PMF is configured in
+ *	LE byte order.
+ * @tx_pn: the last PN used for this responder Tx in case PMF is configured in
+ *	LE byte order.
+ */
+struct iwl_tof_range_rsp_ap_entry_ntfy_v6 {
+	u8 bssid[ETH_ALEN];
+	u8 measure_status;
+	u8 measure_bw;
+	__le32 rtt;
+	__le32 rtt_variance;
+	__le32 rtt_spread;
+	s8 rssi;
+	u8 rssi_spread;
+	u8 last_burst;
+	u8 refusal_period;
+	__le32 timestamp;
+	__le32 start_tsf;
+	__le32 rx_rate_n_flags;
+	__le32 tx_rate_n_flags;
+	__le32 t2t3_initiator;
+	__le32 t1t4_responder;
+	__le16 common_calib;
+	__le16 specific_calib;
+	__le32 papd_calib_output;
+	u8 rttConfidence;
+	u8 reserved[3];
+	u8 rx_pn[IEEE80211_CCMP_PN_LEN];
+	u8 tx_pn[IEEE80211_CCMP_PN_LEN];
+} __packed; /* LOCATION_RANGE_RSP_AP_ETRY_NTFY_API_S_VER_6 */
+
+/**
  * enum iwl_tof_response_status - tof response status
  *
  * @IWL_TOF_RESPONSE_SUCCESS: successful range.
@@ -1066,21 +1257,37 @@ struct iwl_tof_range_rsp_ntfy_v6 {
 } __packed; /* LOCATION_RANGE_RSP_NTFY_API_S_VER_6 */
 
 /**
- * struct iwl_tof_range_rsp_ntfy - ranging response notification
+ * struct iwl_tof_range_rsp_ntfy_v7 - ranging response notification
  * @request_id: A Token ID of the corresponding Range request
  * @num_of_aps: Number of APs results
  * @last_report: 1 if no more FTM sessions are scheduled, 0 otherwise.
  * @reserved: reserved
  * @ap: per-AP data
  */
-struct iwl_tof_range_rsp_ntfy {
+struct iwl_tof_range_rsp_ntfy_v7 {
 	u8 request_id;
 	u8 num_of_aps;
 	u8 last_report;
 	u8 reserved;
-	struct iwl_tof_range_rsp_ap_entry_ntfy ap[IWL_MVM_TOF_MAX_APS];
+	struct iwl_tof_range_rsp_ap_entry_ntfy_v5 ap[IWL_MVM_TOF_MAX_APS];
 } __packed; /* LOCATION_RANGE_RSP_NTFY_API_S_VER_7 */
 
+/**
+ * struct iwl_tof_range_rsp_ntfy_v8 - ranging response notification
+ * @request_id: A Token ID of the corresponding Range request
+ * @num_of_aps: Number of APs results
+ * @last_report: 1 if no more FTM sessions are scheduled, 0 otherwise.
+ * @reserved: reserved
+ * @ap: per-AP data
+ */
+struct iwl_tof_range_rsp_ntfy_v8 {
+	u8 request_id;
+	u8 num_of_aps;
+	u8 last_report;
+	u8 reserved;
+	struct iwl_tof_range_rsp_ap_entry_ntfy_v6 ap[IWL_MVM_TOF_MAX_APS];
+} __packed; /* LOCATION_RANGE_RSP_NTFY_API_S_VER_8 */
+
 #define IWL_MVM_TOF_MCSI_BUF_SIZE  (245)
 /**
  * struct iwl_tof_mcsi_notif - used for debug
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/mac.h b/drivers/net/wireless/intel/iwlwifi/fw/api/mac.h
index 73fb0030c496..afc3eccfa718 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/mac.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/mac.h
@@ -5,9 +5,8 @@
  *
  * GPL LICENSE SUMMARY
  *
- * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2017        Intel Deutschland GmbH
- * Copyright(c) 2018 - 2019 Intel Corporation
+ * Copyright(c) 2012 - 2014, 2018 - 2020 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -27,9 +26,8 @@
  *
  * BSD LICENSE
  *
- * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2017        Intel Deutschland GmbH
- * Copyright(c) 2018 - 2019 Intel Corporation
+ * Copyright(c) 2012 - 2014, 2018 - 2020 Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -188,9 +186,17 @@ struct iwl_mac_data_ibss {
 /**
  * enum iwl_mac_data_policy - policy of the data path for this MAC
  * @TWT_SUPPORTED: twt is supported
+ * @MORE_DATA_ACK_SUPPORTED: AP supports More Data Ack according to
+ *	paragraph 9.4.1.17 in P802.11ax_D4 specification. Used for TWT
+ *	early termination detection.
+ * @FLEXIBLE_TWT_SUPPORTED: AP supports flexible TWT schedule
+ * @PROTECTED_TWT_SUPPORTED: AP supports protected TWT frames (with 11w)
  */
 enum iwl_mac_data_policy {
-	TWT_SUPPORTED	= BIT(0),
+	TWT_SUPPORTED = BIT(0),
+	MORE_DATA_ACK_SUPPORTED = BIT(1),
+	FLEXIBLE_TWT_SUPPORTED = BIT(2),
+	PROTECTED_TWT_SUPPORTED = BIT(3),
 };
 
 /**
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/phy-ctxt.h b/drivers/net/wireless/intel/iwlwifi/fw/api/phy-ctxt.h
index b833b80ea3d6..e6a069683462 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/phy-ctxt.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/phy-ctxt.h
@@ -5,10 +5,9 @@
  *
  * GPL LICENSE SUMMARY
  *
- * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
- * Copyright(c) 2018        Intel Corporation
+ * Copyright(c) 2012 - 2014, 2018, 2020 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -28,10 +27,9 @@
  *
  * BSD LICENSE
  *
- * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
- * Copyright(c) 2018        Intel Corporation
+ * Copyright(c) 2012 - 2014, 2018, 2020 Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -181,15 +179,37 @@ struct iwl_phy_context_cmd_tail {
  * @ci: channel info
  * @tail: command tail
  */
-struct iwl_phy_context_cmd {
+struct iwl_phy_context_cmd_v1 {
 	/* COMMON_INDEX_HDR_API_S_VER_1 */
 	__le32 id_and_color;
 	__le32 action;
-	/* PHY_CONTEXT_DATA_API_S_VER_1 */
+	/* PHY_CONTEXT_DATA_API_S_VER_3 */
 	__le32 apply_time;
 	__le32 tx_param_color;
 	struct iwl_fw_channel_info ci;
 	struct iwl_phy_context_cmd_tail tail;
 } __packed; /* PHY_CONTEXT_CMD_API_VER_1 */
 
+/**
+ * struct iwl_phy_context_cmd - config of the PHY context
+ * ( PHY_CONTEXT_CMD = 0x8 )
+ * @id_and_color: ID and color of the relevant Binding
+ * @action: action to perform, one of FW_CTXT_ACTION_*
+ * @lmac_id: the lmac id the phy context belongs to
+ * @ci: channel info
+ * @rxchain_info: ???
+ * @dsp_cfg_flags: set to 0
+ * @reserved: reserved to align to 64 bit
+ */
+struct iwl_phy_context_cmd {
+	/* COMMON_INDEX_HDR_API_S_VER_1 */
+	__le32 id_and_color;
+	__le32 action;
+	/* PHY_CONTEXT_DATA_API_S_VER_3 */
+	struct iwl_fw_channel_info ci;
+	__le32 lmac_id;
+	__le32 rxchain_info;
+	__le32 dsp_cfg_flags;
+	__le32 reserved;
+} __packed; /* PHY_CONTEXT_CMD_API_VER_3 */
 #endif /* __iwl_fw_api_phy_ctxt_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/phy.h b/drivers/net/wireless/intel/iwlwifi/fw/api/phy.h
index 8991ddffbf5e..0debca6dd037 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/phy.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/phy.h
@@ -8,7 +8,7 @@
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
- * Copyright(c) 2019 Intel Corporation
+ * Copyright(c) 2019 - 2020 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -31,7 +31,7 @@
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
- * Copyright(c) 2019 Intel Corporation
+ * Copyright(c) 2019 - 2020 Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -214,6 +214,15 @@ struct iwl_dts_measurement_notif_v2 {
 } __packed; /* TEMPERATURE_MEASUREMENT_TRIGGER_NTFY_S_VER_2 */
 
 /**
+ * struct iwl_dts_measurement_resp - measurements response
+ *
+ * @temp: the measured temperature
+ */
+struct iwl_dts_measurement_resp {
+	__le32 temp;
+} __packed; /* CMD_DTS_MEASUREMENT_RSP_API_S_VER_1 */
+
+/**
  * struct ct_kill_notif - CT-kill entry notification
  *
  * @temperature: the current temperature in celsius
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/power.h b/drivers/net/wireless/intel/iwlwifi/fw/api/power.h
index 6e1b9b21904e..4e6ad1793d0a 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/power.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/power.h
@@ -8,7 +8,7 @@
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH
  * Copyright(c) 2015 - 2017 Intel Deutschland GmbH
- * Copyright (C) 2018 - 2019 Intel Corporation
+ * Copyright (C) 2018 - 2020 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -31,7 +31,7 @@
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH
  * Copyright(c) 2015 - 2017 Intel Deutschland GmbH
- * Copyright (C) 2018 - 2019 Intel Corporation
+ * Copyright (C) 2018 - 2020 Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -329,48 +329,56 @@ enum iwl_dev_tx_power_cmd_mode {
 	IWL_TX_POWER_MODE_SET_SAR_TIMER_DEFAULT_TABLE = 5,
 }; /* TX_POWER_REDUCED_FLAGS_TYPE_API_E_VER_5 */;
 
+#define IWL_NUM_CHAIN_TABLES	1
+#define IWL_NUM_CHAIN_TABLES_V2	2
 #define IWL_NUM_CHAIN_LIMITS	2
 #define IWL_NUM_SUB_BANDS	5
+#define IWL_NUM_SUB_BANDS_V2	11
 
 /**
- * struct iwl_dev_tx_power_cmd - TX power reduction command
+ * struct iwl_dev_tx_power_common - Common part of the TX power reduction cmd
  * @set_mode: see &enum iwl_dev_tx_power_cmd_mode
  * @mac_context_id: id of the mac ctx for which we are reducing TX power.
  * @pwr_restriction: TX power restriction in 1/8 dBms.
  * @dev_24: device TX power restriction in 1/8 dBms
  * @dev_52_low: device TX power restriction upper band - low
  * @dev_52_high: device TX power restriction upper band - high
- * @per_chain_restriction: per chain restrictions
  */
-struct iwl_dev_tx_power_cmd_v3 {
+struct iwl_dev_tx_power_common {
 	__le32 set_mode;
 	__le32 mac_context_id;
 	__le16 pwr_restriction;
 	__le16 dev_24;
 	__le16 dev_52_low;
 	__le16 dev_52_high;
-	__le16 per_chain_restriction[IWL_NUM_CHAIN_LIMITS][IWL_NUM_SUB_BANDS];
+};
+
+/**
+ * struct iwl_dev_tx_power_cmd_v3 - TX power reduction command version 3
+ * @per_chain: per chain restrictions
+ */
+struct iwl_dev_tx_power_cmd_v3 {
+	__le16 per_chain[IWL_NUM_CHAIN_TABLES][IWL_NUM_CHAIN_LIMITS][IWL_NUM_SUB_BANDS];
 } __packed; /* TX_REDUCED_POWER_API_S_VER_3 */
 
 #define IWL_DEV_MAX_TX_POWER 0x7FFF
 
 /**
- * struct iwl_dev_tx_power_cmd - TX power reduction command
- * @v3: version 3 of the command, embedded here for easier software handling
+ * struct iwl_dev_tx_power_cmd_v4 - TX power reduction command version 4
+ * @per_chain: per chain restrictions
  * @enable_ack_reduction: enable or disable close range ack TX power
  *	reduction.
  * @reserved: reserved (padding)
  */
 struct iwl_dev_tx_power_cmd_v4 {
-	/* v4 is just an extension of v3 - keep this here */
-	struct iwl_dev_tx_power_cmd_v3 v3;
+	__le16 per_chain[IWL_NUM_CHAIN_TABLES][IWL_NUM_CHAIN_LIMITS][IWL_NUM_SUB_BANDS];
 	u8 enable_ack_reduction;
 	u8 reserved[3];
 } __packed; /* TX_REDUCED_POWER_API_S_VER_4 */
 
 /**
- * struct iwl_dev_tx_power_cmd - TX power reduction command
- * @v3: version 3 of the command, embedded here for easier software handling
+ * struct iwl_dev_tx_power_cmd_v5 - TX power reduction command version 5
+ * @per_chain: per chain restrictions
  * @enable_ack_reduction: enable or disable close range ack TX power
  *	reduction.
  * @per_chain_restriction_changed: is per_chain_restriction has changed
@@ -381,16 +389,56 @@ struct iwl_dev_tx_power_cmd_v4 {
  * @timer_period: timer in milliseconds. if expires FW will change to default
  *	BIOS values. relevant if setMode is IWL_TX_POWER_MODE_SET_SAR_TIMER
  */
-struct iwl_dev_tx_power_cmd {
-	/* v5 is just an extension of v3 - keep this here */
-	struct iwl_dev_tx_power_cmd_v3 v3;
+struct iwl_dev_tx_power_cmd_v5 {
+	__le16 per_chain[IWL_NUM_CHAIN_TABLES][IWL_NUM_CHAIN_LIMITS][IWL_NUM_SUB_BANDS];
 	u8 enable_ack_reduction;
 	u8 per_chain_restriction_changed;
 	u8 reserved[2];
 	__le32 timer_period;
 } __packed; /* TX_REDUCED_POWER_API_S_VER_5 */
 
+/**
+ * struct iwl_dev_tx_power_cmd_v5 - TX power reduction command version 5
+ * @per_chain: per chain restrictions
+ * @enable_ack_reduction: enable or disable close range ack TX power
+ *	reduction.
+ * @per_chain_restriction_changed: is per_chain_restriction has changed
+ *	from last command. used if set_mode is
+ *	IWL_TX_POWER_MODE_SET_SAR_TIMER.
+ *	note: if not changed, the command is used for keep alive only.
+ * @reserved: reserved (padding)
+ * @timer_period: timer in milliseconds. if expires FW will change to default
+ *	BIOS values. relevant if setMode is IWL_TX_POWER_MODE_SET_SAR_TIMER
+ */
+struct iwl_dev_tx_power_cmd_v6 {
+	__le16 per_chain[IWL_NUM_CHAIN_TABLES_V2][IWL_NUM_CHAIN_LIMITS][IWL_NUM_SUB_BANDS_V2];
+	u8 enable_ack_reduction;
+	u8 per_chain_restriction_changed;
+	u8 reserved[2];
+	__le32 timer_period;
+} __packed; /* TX_REDUCED_POWER_API_S_VER_6 */
+
+/**
+ * struct iwl_dev_tx_power_cmd - TX power reduction command (multiversion)
+ * @common: common part of the command
+ * @v3: version 3 part of the command
+ * @v4: version 4 part of the command
+ * @v5: version 5 part of the command
+ * @v6: version 6 part of the command
+ */
+struct iwl_dev_tx_power_cmd {
+	struct iwl_dev_tx_power_common common;
+	union {
+		struct iwl_dev_tx_power_cmd_v3 v3;
+		struct iwl_dev_tx_power_cmd_v4 v4;
+		struct iwl_dev_tx_power_cmd_v5 v5;
+		struct iwl_dev_tx_power_cmd_v6 v6;
+	};
+};
+
 #define IWL_NUM_GEO_PROFILES   3
+#define IWL_NUM_BANDS_PER_CHAIN_V1 2
+#define IWL_NUM_BANDS_PER_CHAIN_V2 3
 
 /**
  * enum iwl_geo_per_chain_offset_operation - type of operation
@@ -414,11 +462,6 @@ struct iwl_per_chain_offset {
 	u8 chain_b;
 } __packed; /* PER_CHAIN_LIMIT_OFFSET_PER_CHAIN_S_VER_1 */
 
-struct iwl_per_chain_offset_group {
-	struct iwl_per_chain_offset lb;
-	struct iwl_per_chain_offset hb;
-} __packed; /* PER_CHAIN_LIMIT_OFFSET_GROUP_S_VER_1 */
-
 /**
  * struct iwl_geo_tx_power_profile_cmd_v1 - struct for GEO_TX_POWER_LIMIT cmd.
  * @ops: operations, value from &enum iwl_geo_per_chain_offset_operation
@@ -426,20 +469,38 @@ struct iwl_per_chain_offset_group {
  */
 struct iwl_geo_tx_power_profiles_cmd_v1 {
 	__le32 ops;
-	struct iwl_per_chain_offset_group table[IWL_NUM_GEO_PROFILES];
+	struct iwl_per_chain_offset table[IWL_NUM_GEO_PROFILES][IWL_NUM_BANDS_PER_CHAIN_V1];
 } __packed; /* GEO_TX_POWER_LIMIT_VER_1 */
 
 /**
- * struct iwl_geo_tx_power_profile_cmd - struct for GEO_TX_POWER_LIMIT cmd.
+ * struct iwl_geo_tx_power_profile_cmd_v2 - struct for GEO_TX_POWER_LIMIT cmd.
+ * @ops: operations, value from &enum iwl_geo_per_chain_offset_operation
+ * @table: offset profile per band.
+ * @table_revision: BIOS table revision.
+ */
+struct iwl_geo_tx_power_profiles_cmd_v2 {
+	__le32 ops;
+	struct iwl_per_chain_offset table[IWL_NUM_GEO_PROFILES][IWL_NUM_BANDS_PER_CHAIN_V1];
+	__le32 table_revision;
+} __packed; /* GEO_TX_POWER_LIMIT_VER_2 */
+
+/**
+ * struct iwl_geo_tx_power_profile_cmd_v3 - struct for GEO_TX_POWER_LIMIT cmd.
  * @ops: operations, value from &enum iwl_geo_per_chain_offset_operation
  * @table: offset profile per band.
  * @table_revision: BIOS table revision.
  */
-struct iwl_geo_tx_power_profiles_cmd {
+struct iwl_geo_tx_power_profiles_cmd_v3 {
 	__le32 ops;
-	struct iwl_per_chain_offset_group table[IWL_NUM_GEO_PROFILES];
+	struct iwl_per_chain_offset table[IWL_NUM_GEO_PROFILES][IWL_NUM_BANDS_PER_CHAIN_V2];
 	__le32 table_revision;
-} __packed; /* GEO_TX_POWER_LIMIT */
+} __packed; /* GEO_TX_POWER_LIMIT_VER_3 */
+
+union iwl_geo_tx_power_profiles_cmd {
+	struct iwl_geo_tx_power_profiles_cmd_v1 v1;
+	struct iwl_geo_tx_power_profiles_cmd_v2 v2;
+	struct iwl_geo_tx_power_profiles_cmd_v3 v3;
+};
 
 /**
  * struct iwl_geo_tx_power_profiles_resp -  response to GEO_TX_POWER_LIMIT cmd
@@ -450,16 +511,26 @@ struct iwl_geo_tx_power_profiles_resp {
 } __packed; /* GEO_TX_POWER_LIMIT_RESP */
 
 /**
- * struct iwl_ppag_table_cmd - struct for PER_PLATFORM_ANT_GAIN_CMD cmd.
+ * union iwl_ppag_table_cmd - union for all versions of PPAG command
+ * @v1: version 1, table revision = 0
+ * @v2: version 2, table revision = 1
+ *
  * @enabled: 1 if PPAG is enabled, 0 otherwise
  * @gain: table of antenna gain values per chain and sub-band
  * @reserved: reserved
  */
-struct iwl_ppag_table_cmd {
-	__le32 enabled;
-	s8 gain[IWL_NUM_CHAIN_LIMITS][IWL_NUM_SUB_BANDS];
-	s8 reserved[2];
-} __packed; /* PER_PLATFORM_ANT_GAIN_CMD */
+union iwl_ppag_table_cmd {
+	struct {
+		__le32 enabled;
+		s8 gain[IWL_NUM_CHAIN_LIMITS][IWL_NUM_SUB_BANDS];
+		s8 reserved[2];
+	} v1;
+	struct {
+		__le32 enabled;
+		s8 gain[IWL_NUM_CHAIN_LIMITS][IWL_NUM_SUB_BANDS_V2];
+		s8 reserved[2];
+	} v2;
+} __packed;
 
 /**
  * struct iwl_beacon_filter_cmd
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/rs.h b/drivers/net/wireless/intel/iwlwifi/fw/api/rs.h
index 4347be6491e9..73b839c3cac1 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/rs.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/rs.h
@@ -7,7 +7,7 @@
  *
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2017 Intel Deutschland GmbH
- * Copyright(c) 2018 - 2019 Intel Corporation
+ * Copyright(c) 2018 - 2020 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -29,7 +29,7 @@
  *
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2017 Intel Deutschland GmbH
- * Copyright(c) 2018 - 2019 Intel Corporation
+ * Copyright(c) 2018 - 2020 Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -486,6 +486,13 @@ enum {
 #define RATE_MCS_HE_106T_POS		28
 #define RATE_MCS_HE_106T_MSK		(1 << RATE_MCS_HE_106T_POS)
 
+/* Bit 30-31: (1) RTS, (2) CTS */
+#define RATE_MCS_RTS_REQUIRED_POS  (30)
+#define RATE_MCS_RTS_REQUIRED_MSK  (0x1 << RATE_MCS_RTS_REQUIRED_POS)
+
+#define RATE_MCS_CTS_REQUIRED_POS  (31)
+#define RATE_MCS_CTS_REQUIRED_MSK  (0x1 << RATE_MCS_CTS_REQUIRED_POS)
+
 /* Link Quality definitions */
 
 /* # entries in rate scale table to support Tx retries */
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/rx.h b/drivers/net/wireless/intel/iwlwifi/fw/api/rx.h
index b8b36a4f9eb9..8a8a204bfe26 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/rx.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/rx.h
@@ -308,17 +308,11 @@ enum iwl_rx_mpdu_status {
 	IWL_RX_MPDU_STATUS_EXT_IV_MATCH		= BIT(13),
 	IWL_RX_MPDU_STATUS_KEY_ID_MATCH		= BIT(14),
 	IWL_RX_MPDU_STATUS_ROBUST_MNG_FRAME	= BIT(15),
-};
 
-enum iwl_rx_mpdu_hash_filter {
-	IWL_RX_MPDU_HF_A1_HASH_MASK		= 0x3f,
-	IWL_RX_MPDU_HF_FILTER_STATUS_MASK	= 0xc0,
-};
+	IWL_RX_MPDU_STATUS_KEY			= 0x3f0000,
+	IWL_RX_MPDU_STATUS_DUPLICATE		= BIT(22),
 
-enum iwl_rx_mpdu_sta_id_flags {
-	IWL_RX_MPDU_SIF_STA_ID_MASK		= 0x1f,
-	IWL_RX_MPDU_SIF_RRF_ABORT		= 0x20,
-	IWL_RX_MPDU_SIF_FILTER_STATUS_MASK	= 0xc0,
+	IWL_RX_MPDU_STATUS_STA_ID		= 0x1f000000,
 };
 
 #define IWL_RX_REORDER_DATA_INVALID_BAID 0x7f
@@ -560,7 +554,11 @@ struct iwl_rx_mpdu_desc_v3 {
 	/**
 	 * @raw_xsum: raw xsum value
 	 */
-	__le32 raw_xsum;
+	__be16 raw_xsum;
+	/**
+	 * @reserved_xsum: reserved high bits in the raw checksum
+	 */
+	__le16 reserved_xsum;
 	/* DW11 */
 	/**
 	 * @rate_n_flags: RX rate/flags encoding
@@ -668,15 +666,8 @@ struct iwl_rx_mpdu_desc {
 	/**
 	 * @status: &enum iwl_rx_mpdu_status
 	 */
-	__le16 status;
-	/**
-	 * @hash_filter: hash filter value
-	 */
-	u8 hash_filter;
-	/**
-	 * @sta_id_flags: &enum iwl_rx_mpdu_sta_id_flags
-	 */
-	u8 sta_id_flags;
+	__le32 status;
+
 	/* DW6 */
 	/**
 	 * @reorder_data: &enum iwl_rx_mpdu_reorder_data
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/tx.h b/drivers/net/wireless/intel/iwlwifi/fw/api/tx.h
index 82d59b5a5f8c..de2e2ca7a3ea 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/tx.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/tx.h
@@ -5,9 +5,8 @@
  *
  * GPL LICENSE SUMMARY
  *
- * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
- * Copyright(c) 2018 - 2019 Intel Corporation
+ * Copyright(c) 2012 - 2014, 2018 - 2020 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -27,9 +26,8 @@
  *
  * BSD LICENSE
  *
- * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
- * Copyright(c) 2018 - 2019 Intel Corporation
+ * Copyright(c) 2012 - 2014, 2018 - 2020 Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -61,6 +59,7 @@
 
 #ifndef __iwl_fw_api_tx_h__
 #define __iwl_fw_api_tx_h__
+#include <linux/ieee80211.h>
 
 /**
  * enum iwl_tx_flags - bitmasks for tx_flags in TX command
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
index 7ea55cfdd8a8..ab4a8b942c81 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
@@ -1507,6 +1507,27 @@ iwl_dump_ini_err_table_iter(struct iwl_fw_runtime *fwrt,
 	return sizeof(*range) + le32_to_cpu(range->range_data_size);
 }
 
+static int
+iwl_dump_ini_special_mem_iter(struct iwl_fw_runtime *fwrt,
+			      struct iwl_dump_ini_region_data *reg_data,
+			      void *range_ptr, int idx)
+{
+	struct iwl_fw_ini_region_tlv *reg = (void *)reg_data->reg_tlv->data;
+	struct iwl_fw_ini_region_special_device_memory *special_mem =
+		&reg->special_mem;
+
+	struct iwl_fw_ini_error_dump_range *range = range_ptr;
+	u32 addr = le32_to_cpu(special_mem->base_addr) +
+		   le32_to_cpu(special_mem->offset);
+
+	range->internal_base_addr = cpu_to_le32(addr);
+	range->range_data_size = special_mem->size;
+	iwl_trans_read_mem_bytes(fwrt->trans, addr, range->data,
+				 le32_to_cpu(special_mem->size));
+
+	return sizeof(*range) + le32_to_cpu(range->range_data_size);
+}
+
 static int iwl_dump_ini_fw_pkt_iter(struct iwl_fw_runtime *fwrt,
 				    struct iwl_dump_ini_region_data *reg_data,
 				    void *range_ptr, int idx)
@@ -1636,6 +1657,21 @@ iwl_dump_ini_err_table_fill_header(struct iwl_fw_runtime *fwrt,
 	return dump->ranges;
 }
 
+static void *
+iwl_dump_ini_special_mem_fill_header(struct iwl_fw_runtime *fwrt,
+				     struct iwl_dump_ini_region_data *reg_data,
+				     void *data)
+{
+	struct iwl_fw_ini_region_tlv *reg = (void *)reg_data->reg_tlv->data;
+	struct iwl_fw_ini_special_device_memory *dump = data;
+
+	dump->header.version = cpu_to_le32(IWL_INI_DUMP_VER);
+	dump->type = reg->special_mem.type;
+	dump->version = reg->special_mem.version;
+
+	return dump->ranges;
+}
+
 static u32 iwl_dump_ini_mem_ranges(struct iwl_fw_runtime *fwrt,
 				   struct iwl_dump_ini_region_data *reg_data)
 {
@@ -1827,6 +1863,20 @@ iwl_dump_ini_err_table_get_size(struct iwl_fw_runtime *fwrt,
 }
 
 static u32
+iwl_dump_ini_special_mem_get_size(struct iwl_fw_runtime *fwrt,
+				  struct iwl_dump_ini_region_data *reg_data)
+{
+	struct iwl_fw_ini_region_tlv *reg = (void *)reg_data->reg_tlv->data;
+	u32 size = le32_to_cpu(reg->special_mem.size);
+
+	if (size)
+		size += sizeof(struct iwl_fw_ini_special_device_memory) +
+			sizeof(struct iwl_fw_ini_error_dump_range);
+
+	return size;
+}
+
+static u32
 iwl_dump_ini_fw_pkt_get_size(struct iwl_fw_runtime *fwrt,
 			     struct iwl_dump_ini_region_data *reg_data)
 {
@@ -2125,6 +2175,12 @@ static const struct iwl_dump_ini_mem_ops iwl_dump_ini_region_ops[] = {
 		.fill_mem_hdr = iwl_dump_ini_mem_fill_header,
 		.fill_range = iwl_dump_ini_config_iter,
 	},
+	[IWL_FW_INI_REGION_SPECIAL_DEVICE_MEMORY] = {
+		.get_num_of_ranges = iwl_dump_ini_single_range,
+		.get_size = iwl_dump_ini_special_mem_get_size,
+		.fill_mem_hdr = iwl_dump_ini_special_mem_fill_header,
+		.fill_range = iwl_dump_ini_special_mem_iter,
+	},
 };
 
 static u32 iwl_dump_ini_trigger(struct iwl_fw_runtime *fwrt,
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/error-dump.h b/drivers/net/wireless/intel/iwlwifi/fw/error-dump.h
index 72bfc64580ab..cb40f509ab61 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/error-dump.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/error-dump.h
@@ -495,6 +495,20 @@ struct iwl_fw_ini_monitor_dump {
 } __packed;
 
 /**
+ * struct iwl_fw_ini_special_device_memory - special device memory
+ * @header: header of the region
+ * @type: type of special memory
+ * @version: struct special memory version
+ * @ranges: the memory ranges of this this region
+ */
+struct iwl_fw_ini_special_device_memory {
+	struct iwl_fw_ini_error_dump_header header;
+	__le16 type;
+	__le16 version;
+	struct iwl_fw_ini_error_dump_range ranges[];
+} __packed;
+
+/**
  * struct iwl_fw_error_dump_paging - content of the UMAC's image page
  *	block on DRAM
  * @index: the index of the page block
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/file.h b/drivers/net/wireless/intel/iwlwifi/fw/file.h
index 1fb45fd30ffa..044b9d4ca4d1 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/file.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/file.h
@@ -405,8 +405,8 @@ typedef unsigned int __bitwise iwl_ucode_tlv_capa_t;
  *	to report the CSI information with (certain) RX frames
  * @IWL_UCODE_TLV_CAPA_FTM_CALIBRATED: has FTM calibrated and thus supports both
  *	initiator and responder
- *
  * @IWL_UCODE_TLV_CAPA_MLME_OFFLOAD: supports MLME offload
+ * @IWL_UCODE_TLV_CAPA_PROTECTED_TWT: Supports protection of TWT action frames
  *
  * @NUM_IWL_UCODE_TLV_CAPA: number of bits used
  */
@@ -451,6 +451,7 @@ enum iwl_ucode_tlv_capa {
 	IWL_UCODE_TLV_CAPA_SET_PPAG			= (__force iwl_ucode_tlv_capa_t)52,
 	IWL_UCODE_TLV_CAPA_TAS_CFG			= (__force iwl_ucode_tlv_capa_t)53,
 	IWL_UCODE_TLV_CAPA_SESSION_PROT_CMD		= (__force iwl_ucode_tlv_capa_t)54,
+	IWL_UCODE_TLV_CAPA_PROTECTED_TWT		= (__force iwl_ucode_tlv_capa_t)56,
 
 	/* set 2 */
 	IWL_UCODE_TLV_CAPA_EXTENDED_DTS_MEASURE		= (__force iwl_ucode_tlv_capa_t)64,
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/img.c b/drivers/net/wireless/intel/iwlwifi/fw/img.c
index de8cff463dbe..c2a4e60518bc 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/img.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/img.c
@@ -5,7 +5,7 @@
  *
  * GPL LICENSE SUMMARY
  *
- * Copyright(c) 2019 Intel Corporation
+ * Copyright(c) 2019 - 2020 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -25,7 +25,7 @@
  *
  * BSD LICENSE
  *
- * Copyright(c) 2019 Intel Corporation
+ * Copyright(c) 2019 - 2020 Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -57,22 +57,25 @@
 
 #include "img.h"
 
-u8 iwl_fw_lookup_cmd_ver(const struct iwl_fw *fw, u8 grp, u8 cmd)
+u8 iwl_fw_lookup_cmd_ver(const struct iwl_fw *fw, u8 grp, u8 cmd, u8 def)
 {
 	const struct iwl_fw_cmd_version *entry;
 	unsigned int i;
 
 	if (!fw->ucode_capa.cmd_versions ||
 	    !fw->ucode_capa.n_cmd_versions)
-		return IWL_FW_CMD_VER_UNKNOWN;
+		return def;
 
 	entry = fw->ucode_capa.cmd_versions;
 	for (i = 0; i < fw->ucode_capa.n_cmd_versions; i++, entry++) {
-		if (entry->group == grp && entry->cmd == cmd)
+		if (entry->group == grp && entry->cmd == cmd) {
+			if (entry->cmd_ver == IWL_FW_CMD_VER_UNKNOWN)
+				return def;
 			return entry->cmd_ver;
+		}
 	}
 
-	return IWL_FW_CMD_VER_UNKNOWN;
+	return def;
 }
 EXPORT_SYMBOL_GPL(iwl_fw_lookup_cmd_ver);
 
@@ -97,3 +100,43 @@ u8 iwl_fw_lookup_notif_ver(const struct iwl_fw *fw, u8 grp, u8 cmd, u8 def)
 	return def;
 }
 EXPORT_SYMBOL_GPL(iwl_fw_lookup_notif_ver);
+
+#define FW_SYSASSERT_CPU_MASK 0xf0000000
+static const struct {
+	const char *name;
+	u8 num;
+} advanced_lookup[] = {
+	{ "NMI_INTERRUPT_WDG", 0x34 },
+	{ "SYSASSERT", 0x35 },
+	{ "UCODE_VERSION_MISMATCH", 0x37 },
+	{ "BAD_COMMAND", 0x38 },
+	{ "BAD_COMMAND", 0x39 },
+	{ "NMI_INTERRUPT_DATA_ACTION_PT", 0x3C },
+	{ "FATAL_ERROR", 0x3D },
+	{ "NMI_TRM_HW_ERR", 0x46 },
+	{ "NMI_INTERRUPT_TRM", 0x4C },
+	{ "NMI_INTERRUPT_BREAK_POINT", 0x54 },
+	{ "NMI_INTERRUPT_WDG_RXF_FULL", 0x5C },
+	{ "NMI_INTERRUPT_WDG_NO_RBD_RXF_FULL", 0x64 },
+	{ "NMI_INTERRUPT_HOST", 0x66 },
+	{ "NMI_INTERRUPT_LMAC_FATAL", 0x70 },
+	{ "NMI_INTERRUPT_UMAC_FATAL", 0x71 },
+	{ "NMI_INTERRUPT_OTHER_LMAC_FATAL", 0x73 },
+	{ "NMI_INTERRUPT_ACTION_PT", 0x7C },
+	{ "NMI_INTERRUPT_UNKNOWN", 0x84 },
+	{ "NMI_INTERRUPT_INST_ACTION_PT", 0x86 },
+	{ "ADVANCED_SYSASSERT", 0 },
+};
+
+const char *iwl_fw_lookup_assert_desc(u32 num)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(advanced_lookup) - 1; i++)
+		if (advanced_lookup[i].num == (num & ~FW_SYSASSERT_CPU_MASK))
+			return advanced_lookup[i].name;
+
+	/* No entry matches 'num', so it is the last: ADVANCED_SYSASSERT */
+	return advanced_lookup[i].name;
+}
+EXPORT_SYMBOL_GPL(iwl_fw_lookup_assert_desc);
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/img.h b/drivers/net/wireless/intel/iwlwifi/fw/img.h
index a8630bf90b63..07d72bcf9c46 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/img.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/img.h
@@ -5,10 +5,9 @@
  *
  * GPL LICENSE SUMMARY
  *
- * Copyright(c) 2008 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2016        Intel Deutschland GmbH
- * Copyright(c) 2018 - 2019 Intel Corporation
+ * Copyright(c) 2008 - 2014, 2018 - 2020 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -31,7 +30,7 @@
  * Copyright(c) 2005 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2016        Intel Deutschland GmbH
- * Copyright(c) 2018 - 2019 Intel Corporation
+ * Copyright(c) 2008 - 2014, 2018 - 2020 Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -313,7 +312,8 @@ iwl_get_ucode_image(const struct iwl_fw *fw, enum iwl_ucode_type ucode_type)
 	return &fw->img[ucode_type];
 }
 
-u8 iwl_fw_lookup_cmd_ver(const struct iwl_fw *fw, u8 grp, u8 cmd);
+u8 iwl_fw_lookup_cmd_ver(const struct iwl_fw *fw, u8 grp, u8 cmd, u8 def);
 
 u8 iwl_fw_lookup_notif_ver(const struct iwl_fw *fw, u8 grp, u8 cmd, u8 def);
+const char *iwl_fw_lookup_assert_desc(u32 num);
 #endif  /* __iwl_fw_img_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/init.c b/drivers/net/wireless/intel/iwlwifi/fw/init.c
index b373606e1241..f8516c7ca767 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/init.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/init.c
@@ -134,7 +134,8 @@ int iwl_set_soc_latency(struct iwl_fw_runtime *fwrt)
 					      SOC_FLAGS_LTR_APPLY_DELAY_MASK);
 
 	if (iwl_fw_lookup_cmd_ver(fwrt->fw, IWL_ALWAYS_LONG_GROUP,
-				  SCAN_REQ_UMAC) >= 2 &&
+				  SCAN_REQ_UMAC,
+				  IWL_FW_CMD_VER_UNKNOWN) >= 2 &&
 	    fwrt->trans->trans_cfg->low_latency_xtal)
 		cmd.flags |= cpu_to_le32(SOC_CONFIG_CMD_FLAGS_LOW_LATENCY);
 
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/runtime.h b/drivers/net/wireless/intel/iwlwifi/fw/runtime.h
index b5e5e32b6152..cddcb4d9a264 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/runtime.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/runtime.h
@@ -207,7 +207,8 @@ struct iwl_fw_runtime {
 	u8 sar_chain_b_profile;
 	struct iwl_geo_profile geo_profiles[ACPI_NUM_GEO_PROFILES];
 	u32 geo_rev;
-	struct iwl_ppag_table_cmd ppag_table;
+	union iwl_ppag_table_cmd ppag_table;
+	u32 ppag_ver;
 #endif
 };
 
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-config.h b/drivers/net/wireless/intel/iwlwifi/iwl-config.h
index e27c13263a23..d03f51bf7dfd 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-config.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-config.h
@@ -472,6 +472,7 @@ struct iwl_cfg {
 #define IWL_CFG_MAC_TYPE_QU		0x33
 #define IWL_CFG_MAC_TYPE_QUZ		0x35
 #define IWL_CFG_MAC_TYPE_QNJ		0x36
+#define IWL_CFG_MAC_TYPE_MA		0x44
 
 #define IWL_CFG_RF_TYPE_TH		0x105
 #define IWL_CFG_RF_TYPE_TH1		0x108
@@ -479,6 +480,8 @@ struct iwl_cfg {
 #define IWL_CFG_RF_TYPE_JF1		0x108
 #define IWL_CFG_RF_TYPE_HR2		0x10A
 #define IWL_CFG_RF_TYPE_HR1		0x10C
+#define IWL_CFG_RF_TYPE_GF		0x10D
+#define IWL_CFG_RF_TYPE_MR		0x110
 
 #define IWL_CFG_RF_ID_TH		0x1
 #define IWL_CFG_RF_ID_TH1		0x1
@@ -522,6 +525,7 @@ extern const struct iwl_cfg_trans_params iwl_qu_trans_cfg;
 extern const struct iwl_cfg_trans_params iwl_qu_medium_latency_trans_cfg;
 extern const struct iwl_cfg_trans_params iwl_qu_long_latency_trans_cfg;
 extern const struct iwl_cfg_trans_params iwl_ax200_trans_cfg;
+extern const struct iwl_cfg_trans_params iwl_ma_trans_cfg;
 extern const char iwl9162_name[];
 extern const char iwl9260_name[];
 extern const char iwl9260_1_name[];
@@ -543,7 +547,11 @@ extern const char iwl_ax201_name[];
 extern const char iwl_ax101_name[];
 extern const char iwl_ax200_killer_1650w_name[];
 extern const char iwl_ax200_killer_1650x_name[];
-
+extern const char iwl_ax201_killer_1650s_name[];
+extern const char iwl_ax201_killer_1650i_name[];
+extern const char iwl_ma_name[];
+extern const char iwl_ax211_name[];
+extern const char iwl_ax411_name[];
 #if IS_ENABLED(CONFIG_IWLDVM)
 extern const struct iwl_cfg iwl5300_agn_cfg;
 extern const struct iwl_cfg iwl5100_agn_cfg;
@@ -641,6 +649,9 @@ extern const struct iwl_cfg iwlax411_2ax_cfg_so_gf4_a0;
 extern const struct iwl_cfg iwlax411_2ax_cfg_so_gf4_a0_long;
 extern const struct iwl_cfg iwlax411_2ax_cfg_sosnj_gf4_a0;
 extern const struct iwl_cfg iwlax211_cfg_snj_gf_a0;
+extern const struct iwl_cfg iwlax201_cfg_snj_hr_b0;
+extern const struct iwl_cfg iwl_cfg_ma_a0_gf_a0;
+extern const struct iwl_cfg iwl_cfg_ma_a0_mr_a0;
 #endif /* CONFIG_IWLMVM */
 
 #endif /* __IWL_CONFIG_H__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c
index 9ce7207d9ec5..51ce93d21ffe 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c
@@ -182,9 +182,13 @@ static int iwl_dbg_tlv_alloc_buf_alloc(struct iwl_trans *trans,
 	    alloc_id >= IWL_FW_INI_ALLOCATION_NUM)
 		goto err;
 
-	if ((buf_location == IWL_FW_INI_LOCATION_SRAM_PATH ||
-	     buf_location == IWL_FW_INI_LOCATION_NPK_PATH) &&
-	     alloc_id != IWL_FW_INI_ALLOCATION_ID_DBGC1)
+	if (buf_location == IWL_FW_INI_LOCATION_NPK_PATH &&
+	    alloc_id != IWL_FW_INI_ALLOCATION_ID_DBGC1)
+		goto err;
+
+	if (buf_location == IWL_FW_INI_LOCATION_SRAM_PATH &&
+	    alloc_id != IWL_FW_INI_ALLOCATION_ID_DBGC1 &&
+	    alloc_id != IWL_FW_INI_ALLOCATION_ID_INTERNAL)
 		goto err;
 
 	trans->dbg.fw_mon_cfg[alloc_id] = *alloc;
@@ -233,6 +237,13 @@ static int iwl_dbg_tlv_alloc_region(struct iwl_trans *trans,
 	if (le32_to_cpu(tlv->length) < sizeof(*reg))
 		return -EINVAL;
 
+	/* For safe using a string from FW make sure we have a
+	 * null terminator
+	 */
+	reg->name[IWL_FW_INI_MAX_NAME - 1] = 0;
+
+	IWL_DEBUG_FW(trans, "WRT: parsing region: %s\n", reg->name);
+
 	if (id >= IWL_FW_INI_MAX_REGION_ID) {
 		IWL_ERR(trans, "WRT: Invalid region id %u\n", id);
 		return -EINVAL;
@@ -947,9 +958,8 @@ static bool iwl_dbg_tlv_check_fw_pkt(struct iwl_fw_runtime *fwrt,
 	struct iwl_rx_packet *pkt = tp_data->fw_pkt;
 	struct iwl_cmd_header *wanted_hdr = (void *)&trig_data;
 
-	if (pkt && ((wanted_hdr->cmd == 0 && wanted_hdr->group_id == 0) ||
-		    (pkt->hdr.cmd == wanted_hdr->cmd &&
-		     pkt->hdr.group_id == wanted_hdr->group_id))) {
+	if (pkt && (pkt->hdr.cmd == wanted_hdr->cmd &&
+		    pkt->hdr.group_id == wanted_hdr->group_id)) {
 		struct iwl_rx_packet *fw_pkt =
 			kmemdup(pkt,
 				sizeof(*pkt) + iwl_rx_packet_payload_len(pkt),
@@ -1012,6 +1022,9 @@ static void iwl_dbg_tlv_init_cfg(struct iwl_fw_runtime *fwrt)
 	enum iwl_fw_ini_buffer_location *ini_dest = &fwrt->trans->dbg.ini_dest;
 	int ret, i;
 
+	if (*ini_dest != IWL_FW_INI_LOCATION_INVALID)
+		return;
+
 	IWL_DEBUG_FW(fwrt,
 		     "WRT: Generating active triggers list, domain 0x%x\n",
 		     fwrt->trans->dbg.domains_bitmap);
@@ -1076,6 +1089,7 @@ void iwl_dbg_tlv_time_point(struct iwl_fw_runtime *fwrt,
 		break;
 	case IWL_FW_INI_TIME_POINT_FW_RSP_OR_NOTIF:
 	case IWL_FW_INI_TIME_POINT_MISSED_BEACONS:
+	case IWL_FW_INI_TIME_POINT_FW_DHC_NOTIFICATION:
 		iwl_dbg_tlv_send_hcmds(fwrt, hcmd_list);
 		iwl_dbg_tlv_tp_trigger(fwrt, trig_list, tp_data,
 				       iwl_dbg_tlv_check_fw_pkt);
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-debug.c b/drivers/net/wireless/intel/iwlwifi/iwl-debug.c
index e1a41fd503a8..7df173cc9ddc 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-debug.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-debug.c
@@ -121,10 +121,9 @@ void __iwl_dbg(struct device *dev,
 #ifdef CONFIG_IWLWIFI_DEBUG
 	if (iwl_have_debug_level(level) &&
 	    (!limit || net_ratelimit()))
-		dev_printk(KERN_DEBUG, dev, "%c %s %pV",
-			   in_interrupt() ? 'I' : 'U', function, &vaf);
+		dev_printk(KERN_DEBUG, dev, "%s %pV", function, &vaf);
 #endif
-	trace_iwlwifi_dbg(level, in_interrupt(), function, &vaf);
+	trace_iwlwifi_dbg(level, function, &vaf);
 	va_end(args);
 }
 IWL_EXPORT_SYMBOL(__iwl_dbg);
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-debug.h b/drivers/net/wireless/intel/iwlwifi/iwl-debug.h
index 063d8add147f..528eba441926 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-debug.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-debug.h
@@ -2,7 +2,7 @@
 /******************************************************************************
  *
  * Copyright(c) 2003 - 2014 Intel Corporation. All rights reserved.
- * Copyright (C) 2018 Intel Corporation
+ * Copyright(c) 2018 - 2020 Intel Corporation
  *
  * Portions of this file are derived from the ipw3945 project.
  *
@@ -139,7 +139,7 @@ do {                                            			\
 /* 0x00000F00 - 0x00000100 */
 #define IWL_DL_POWER		0x00000100
 #define IWL_DL_TEMP		0x00000200
-#define IWL_DL_RPM		0x00000400
+#define IWL_DL_WOWLAN		0x00000400
 #define IWL_DL_SCAN		0x00000800
 /* 0x0000F000 - 0x00001000 */
 #define IWL_DL_ASSOC		0x00001000
@@ -205,7 +205,7 @@ do {                                            			\
 #define IWL_DEBUG_POWER(p, f, a...)	IWL_DEBUG(p, IWL_DL_POWER, f, ## a)
 #define IWL_DEBUG_11H(p, f, a...)	IWL_DEBUG(p, IWL_DL_11H, f, ## a)
 #define IWL_DEBUG_TPT(p, f, a...)	IWL_DEBUG(p, IWL_DL_TPT, f, ## a)
-#define IWL_DEBUG_RPM(p, f, a...)	IWL_DEBUG(p, IWL_DL_RPM, f, ## a)
+#define IWL_DEBUG_WOWLAN(p, f, a...)	IWL_DEBUG(p, IWL_DL_WOWLAN, f, ## a)
 #define IWL_DEBUG_LAR(p, f, a...)	IWL_DEBUG(p, IWL_DL_LAR, f, ## a)
 #define IWL_DEBUG_FW_INFO(p, f, a...)		\
 		IWL_DEBUG(p, IWL_DL_INFO | IWL_DL_FW, f, ## a)
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-devtrace-msg.h b/drivers/net/wireless/intel/iwlwifi/iwl-devtrace-msg.h
index 9ad93ef60890..d0467da5af03 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-devtrace-msg.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-devtrace-msg.h
@@ -54,18 +54,16 @@ DEFINE_EVENT(iwlwifi_msg_event, iwlwifi_crit,
 );
 
 TRACE_EVENT(iwlwifi_dbg,
-	TP_PROTO(u32 level, bool in_interrupt, const char *function,
+	TP_PROTO(u32 level, const char *function,
 		 struct va_format *vaf),
-	TP_ARGS(level, in_interrupt, function, vaf),
+	TP_ARGS(level, function, vaf),
 	TP_STRUCT__entry(
 		__field(u32, level)
-		__field(u8, in_interrupt)
 		__string(function, function)
 		__dynamic_array(char, msg, MAX_MSG_LEN)
 	),
 	TP_fast_assign(
 		__entry->level = level;
-		__entry->in_interrupt = in_interrupt;
 		__assign_str(function, function);
 		WARN_ON_ONCE(vsnprintf(__get_dynamic_array(msg),
 				       MAX_MSG_LEN, vaf->fmt,
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
index ee410417761d..6d19de3058d2 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
@@ -254,6 +254,65 @@ enum iwl_reg_capa_flags {
 	REG_CAPA_11AX_DISABLED		= BIT(10),
 };
 
+/**
+ * enum iwl_reg_capa_flags_v2 - global flags applied for the whole regulatory
+ * domain (version 2).
+ * @REG_CAPA_V2_STRADDLE_DISABLED: Straddle channels (144, 142, 138) are
+ *	disabled.
+ * @REG_CAPA_V2_BF_CCD_LOW_BAND: Beam-forming or Cyclic Delay Diversity in the
+ *	2.4Ghz band is allowed.
+ * @REG_CAPA_V2_BF_CCD_HIGH_BAND: Beam-forming or Cyclic Delay Diversity in the
+ *	5Ghz band is allowed.
+ * @REG_CAPA_V2_160MHZ_ALLOWED: 11ac channel with a width of 160Mhz is allowed
+ *	for this regulatory domain (valid only in 5Ghz).
+ * @REG_CAPA_V2_80MHZ_ALLOWED: 11ac channel with a width of 80Mhz is allowed
+ *	for this regulatory domain (valid only in 5Ghz).
+ * @REG_CAPA_V2_MCS_8_ALLOWED: 11ac with MCS 8 is allowed.
+ * @REG_CAPA_V2_MCS_9_ALLOWED: 11ac with MCS 9 is allowed.
+ * @REG_CAPA_V2_WEATHER_DISABLED: Weather radar channels (120, 124, 128, 118,
+ *	126, 122) are disabled.
+ * @REG_CAPA_V2_40MHZ_ALLOWED: 11n channel with a width of 40Mhz is allowed
+ *	for this regulatory domain (uvalid only in 5Ghz).
+ * @REG_CAPA_V2_11AX_DISABLED: 11ax is forbidden for this regulatory domain.
+ */
+enum iwl_reg_capa_flags_v2 {
+	REG_CAPA_V2_STRADDLE_DISABLED	= BIT(0),
+	REG_CAPA_V2_BF_CCD_LOW_BAND	= BIT(1),
+	REG_CAPA_V2_BF_CCD_HIGH_BAND	= BIT(2),
+	REG_CAPA_V2_160MHZ_ALLOWED	= BIT(3),
+	REG_CAPA_V2_80MHZ_ALLOWED	= BIT(4),
+	REG_CAPA_V2_MCS_8_ALLOWED	= BIT(5),
+	REG_CAPA_V2_MCS_9_ALLOWED	= BIT(6),
+	REG_CAPA_V2_WEATHER_DISABLED	= BIT(7),
+	REG_CAPA_V2_40MHZ_ALLOWED	= BIT(8),
+	REG_CAPA_V2_11AX_DISABLED	= BIT(13),
+};
+
+/*
+* API v2 for reg_capa_flags is relevant from version 6 and onwards of the
+* MCC update command response.
+*/
+#define REG_CAPA_V2_RESP_VER	6
+
+/**
+ * struct iwl_reg_capa - struct for global regulatory capabilities, Used for
+ * handling the different APIs of reg_capa_flags.
+ *
+ * @allow_40mhz: 11n channel with a width of 40Mhz is allowed
+ *	for this regulatory domain (valid only in 5Ghz).
+ * @allow_80mhz: 11ac channel with a width of 80Mhz is allowed
+ *	for this regulatory domain (valid only in 5Ghz).
+ * @allow_160mhz: 11ac channel with a width of 160Mhz is allowed
+ *	for this regulatory domain (valid only in 5Ghz).
+ * @disable_11ax: 11ax is forbidden for this regulatory domain.
+ */
+struct iwl_reg_capa {
+	u16 allow_40mhz;
+	u16 allow_80mhz;
+	u16 allow_160mhz;
+	u16 disable_11ax;
+};
+
 static inline void iwl_nvm_print_channel_flags(struct device *dev, u32 level,
 					       int chan, u32 flags)
 {
@@ -1064,7 +1123,7 @@ IWL_EXPORT_SYMBOL(iwl_parse_nvm_data);
 
 static u32 iwl_nvm_get_regdom_bw_flags(const u16 *nvm_chan,
 				       int ch_idx, u16 nvm_flags,
-				       u16 cap_flags,
+				       struct iwl_reg_capa reg_capa,
 				       const struct iwl_cfg *cfg)
 {
 	u32 flags = NL80211_RRF_NO_HT40;
@@ -1104,29 +1163,46 @@ static u32 iwl_nvm_get_regdom_bw_flags(const u16 *nvm_chan,
 		flags |= NL80211_RRF_GO_CONCURRENT;
 
 	/*
-	 * cap_flags is per regulatory domain so apply it for every channel
+	 * reg_capa is per regulatory domain so apply it for every channel
 	 */
 	if (ch_idx >= NUM_2GHZ_CHANNELS) {
-		if (cap_flags & REG_CAPA_40MHZ_FORBIDDEN)
+		if (!reg_capa.allow_40mhz)
 			flags |= NL80211_RRF_NO_HT40;
 
-		if (!(cap_flags & REG_CAPA_80MHZ_ALLOWED))
+		if (!reg_capa.allow_80mhz)
 			flags |= NL80211_RRF_NO_80MHZ;
 
-		if (!(cap_flags & REG_CAPA_160MHZ_ALLOWED))
+		if (!reg_capa.allow_160mhz)
 			flags |= NL80211_RRF_NO_160MHZ;
 	}
-
-	if (cap_flags & REG_CAPA_11AX_DISABLED)
+	if (reg_capa.disable_11ax)
 		flags |= NL80211_RRF_NO_HE;
 
 	return flags;
 }
 
+static struct iwl_reg_capa iwl_get_reg_capa(u16 flags, u8 resp_ver)
+{
+	struct iwl_reg_capa reg_capa;
+
+	if (resp_ver >= REG_CAPA_V2_RESP_VER) {
+		reg_capa.allow_40mhz = flags & REG_CAPA_V2_40MHZ_ALLOWED;
+		reg_capa.allow_80mhz = flags & REG_CAPA_V2_80MHZ_ALLOWED;
+		reg_capa.allow_160mhz = flags & REG_CAPA_V2_160MHZ_ALLOWED;
+		reg_capa.disable_11ax = flags & REG_CAPA_V2_11AX_DISABLED;
+	} else {
+		reg_capa.allow_40mhz = !(flags & REG_CAPA_40MHZ_FORBIDDEN);
+		reg_capa.allow_80mhz = flags & REG_CAPA_80MHZ_ALLOWED;
+		reg_capa.allow_160mhz = flags & REG_CAPA_160MHZ_ALLOWED;
+		reg_capa.disable_11ax = flags & REG_CAPA_11AX_DISABLED;
+	}
+	return reg_capa;
+}
+
 struct ieee80211_regdomain *
 iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg,
 		       int num_of_ch, __le32 *channels, u16 fw_mcc,
-		       u16 geo_info, u16 cap)
+		       u16 geo_info, u16 cap, u8 resp_ver)
 {
 	int ch_idx;
 	u16 ch_flags;
@@ -1139,6 +1215,7 @@ iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg,
 	int valid_rules = 0;
 	bool new_rule;
 	int max_num_ch;
+	struct iwl_reg_capa reg_capa;
 
 	if (cfg->uhb_supported) {
 		max_num_ch = IWL_NVM_NUM_CHANNELS_UHB;
@@ -1169,6 +1246,9 @@ iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg,
 	regd->alpha2[0] = fw_mcc >> 8;
 	regd->alpha2[1] = fw_mcc & 0xff;
 
+	/* parse regulatory capability flags */
+	reg_capa = iwl_get_reg_capa(cap, resp_ver);
+
 	for (ch_idx = 0; ch_idx < num_of_ch; ch_idx++) {
 		ch_flags = (u16)__le32_to_cpup(channels + ch_idx);
 		band = iwl_nl80211_band_from_channel_idx(ch_idx);
@@ -1183,7 +1263,7 @@ iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg,
 		}
 
 		reg_rule_flags = iwl_nvm_get_regdom_bw_flags(nvm_chan, ch_idx,
-							     ch_flags, cap,
+							     ch_flags, reg_capa,
 							     cfg);
 
 		/* we can't continue the same rule */
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h
index fb0b385d10fd..50bd7fdcf852 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h
@@ -104,7 +104,7 @@ iwl_parse_nvm_data(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 struct ieee80211_regdomain *
 iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg,
 		       int num_of_ch, __le32 *channels, u16 fw_mcc,
-		       u16 geo_info, u16 cap);
+		       u16 geo_info, u16 cap, u8 resp_ver);
 
 /**
  * struct iwl_nvm_section - describes an NVM section in memory.
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.c b/drivers/net/wireless/intel/iwlwifi/iwl-trans.c
index f91197e4ae40..a26da96763dd 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.c
@@ -7,6 +7,7 @@
  *
  * Copyright(c) 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
+ * Copyright(c) 2019 - 2020 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -28,6 +29,7 @@
  *
  * Copyright(c) 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
+ * Copyright(c) 2019 - 2020 Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -60,17 +62,20 @@
 #include <linux/kernel.h>
 #include <linux/bsearch.h>
 
+#include "fw/api/tx.h"
 #include "iwl-trans.h"
 #include "iwl-drv.h"
 #include "iwl-fh.h"
+#include "queue/tx.h"
+#include <linux/dmapool.h>
 
 struct iwl_trans *iwl_trans_alloc(unsigned int priv_size,
 				  struct device *dev,
 				  const struct iwl_trans_ops *ops,
-				  unsigned int cmd_pool_size,
-				  unsigned int cmd_pool_align)
+				  const struct iwl_cfg_trans_params *cfg_trans)
 {
 	struct iwl_trans *trans;
+	int txcmd_size, txcmd_align;
 #ifdef CONFIG_LOCKDEP
 	static struct lock_class_key __key;
 #endif
@@ -79,6 +84,25 @@ struct iwl_trans *iwl_trans_alloc(unsigned int priv_size,
 	if (!trans)
 		return NULL;
 
+	trans->trans_cfg = cfg_trans;
+	if (!cfg_trans->gen2) {
+		txcmd_size = sizeof(struct iwl_tx_cmd);
+		txcmd_align = sizeof(void *);
+	} else if (cfg_trans->device_family < IWL_DEVICE_FAMILY_AX210) {
+		txcmd_size = sizeof(struct iwl_tx_cmd_gen2);
+		txcmd_align = 64;
+	} else {
+		txcmd_size = sizeof(struct iwl_tx_cmd_gen3);
+		txcmd_align = 128;
+	}
+
+	txcmd_size += sizeof(struct iwl_cmd_header);
+	txcmd_size += 36; /* biggest possible 802.11 header */
+
+	/* Ensure device TX cmd cannot reach/cross a page boundary in gen2 */
+	if (WARN_ON(cfg_trans->gen2 && txcmd_size >= txcmd_align))
+		return ERR_PTR(-EINVAL);
+
 #ifdef CONFIG_LOCKDEP
 	lockdep_init_map(&trans->sync_cmd_lockdep_map, "sync_cmd_lockdep_map",
 			 &__key, 0);
@@ -88,22 +112,68 @@ struct iwl_trans *iwl_trans_alloc(unsigned int priv_size,
 	trans->ops = ops;
 	trans->num_rx_queues = 1;
 
+	if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210)
+		trans->txqs.bc_tbl_size = sizeof(struct iwl_gen3_bc_tbl);
+	else
+		trans->txqs.bc_tbl_size = sizeof(struct iwlagn_scd_bc_tbl);
+	/*
+	 * For gen2 devices, we use a single allocation for each byte-count
+	 * table, but they're pretty small (1k) so use a DMA pool that we
+	 * allocate here.
+	 */
+	if (trans->trans_cfg->gen2) {
+		trans->txqs.bc_pool = dmam_pool_create("iwlwifi:bc", dev,
+						       trans->txqs.bc_tbl_size,
+						       256, 0);
+		if (!trans->txqs.bc_pool)
+			return NULL;
+	}
+
+	if (trans->trans_cfg->use_tfh) {
+		trans->txqs.tfd.addr_size = 64;
+		trans->txqs.tfd.max_tbs = IWL_TFH_NUM_TBS;
+		trans->txqs.tfd.size = sizeof(struct iwl_tfh_tfd);
+	} else {
+		trans->txqs.tfd.addr_size = 36;
+		trans->txqs.tfd.max_tbs = IWL_NUM_OF_TBS;
+		trans->txqs.tfd.size = sizeof(struct iwl_tfd);
+	}
+	trans->max_skb_frags = IWL_TRANS_MAX_FRAGS(trans);
+
 	snprintf(trans->dev_cmd_pool_name, sizeof(trans->dev_cmd_pool_name),
 		 "iwl_cmd_pool:%s", dev_name(trans->dev));
 	trans->dev_cmd_pool =
 		kmem_cache_create(trans->dev_cmd_pool_name,
-				  cmd_pool_size, cmd_pool_align,
+				  txcmd_size, txcmd_align,
 				  SLAB_HWCACHE_ALIGN, NULL);
 	if (!trans->dev_cmd_pool)
 		return NULL;
 
 	WARN_ON(!ops->wait_txq_empty && !ops->wait_tx_queues_empty);
 
+	trans->txqs.tso_hdr_page = alloc_percpu(struct iwl_tso_hdr_page);
+	if (!trans->txqs.tso_hdr_page) {
+		kmem_cache_destroy(trans->dev_cmd_pool);
+		return NULL;
+	}
+
 	return trans;
 }
 
 void iwl_trans_free(struct iwl_trans *trans)
 {
+	int i;
+
+	for_each_possible_cpu(i) {
+		struct iwl_tso_hdr_page *p =
+			per_cpu_ptr(trans->txqs.tso_hdr_page, i);
+
+		if (p->page)
+			__free_page(p->page);
+	}
+
+	free_percpu(trans->txqs.tso_hdr_page);
+
 	kmem_cache_destroy(trans->dev_cmd_pool);
 }
 
@@ -130,7 +200,7 @@ int iwl_trans_send_cmd(struct iwl_trans *trans, struct iwl_host_cmd *cmd)
 	if (!(cmd->flags & CMD_ASYNC))
 		lock_map_acquire_read(&trans->sync_cmd_lockdep_map);
 
-	if (trans->wide_cmd_header && !iwl_cmd_groupid(cmd->id))
+	if (!iwl_cmd_groupid(cmd->id))
 		cmd->id = DEF_ID(cmd->id);
 
 	ret = trans->ops->send_cmd(trans, cmd);
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
index 34788e7afc7b..45a9df0d42ed 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
@@ -215,6 +215,12 @@ struct iwl_device_tx_cmd {
  */
 #define IWL_MAX_CMD_TBS_PER_TFD	2
 
+/* We need 2 entries for the TX command and header, and another one might
+ * be needed for potential data in the SKB's head. The remaining ones can
+ * be used for frags.
+ */
+#define IWL_TRANS_MAX_FRAGS(trans) ((trans)->txqs.tfd.max_tbs - 3)
+
 /**
  * enum iwl_hcmd_dataflag - flag for each one of the chunks of the command
  *
@@ -316,6 +322,7 @@ static inline void iwl_free_rxb(struct iwl_rx_cmd_buffer *r)
 #define IWL_MGMT_TID		15
 #define IWL_FRAME_LIMIT	64
 #define IWL_MAX_RX_HW_QUEUES	16
+#define IWL_9000_MAX_RX_HW_QUEUES	6
 
 /**
  * enum iwl_wowlan_status - WoWLAN image/device status
@@ -906,19 +913,37 @@ struct iwl_txq {
 /**
  * struct iwl_trans_txqs - transport tx queues data
  *
+ * @bc_table_dword: true if the BC table expects DWORD (as opposed to bytes)
+ * @page_offs: offset from skb->cb to mac header page pointer
+ * @dev_cmd_offs: offset from skb->cb to iwl_device_tx_cmd pointer
  * @queue_used - bit mask of used queues
  * @queue_stopped - bit mask of stopped queues
+ * @scd_bc_tbls: gen1 pointer to the byte count table of the scheduler
  */
 struct iwl_trans_txqs {
 	unsigned long queue_used[BITS_TO_LONGS(IWL_MAX_TVQM_QUEUES)];
 	unsigned long queue_stopped[BITS_TO_LONGS(IWL_MAX_TVQM_QUEUES)];
 	struct iwl_txq *txq[IWL_MAX_TVQM_QUEUES];
+	struct dma_pool *bc_pool;
+	size_t bc_tbl_size;
+	bool bc_table_dword;
+	u8 page_offs;
+	u8 dev_cmd_offs;
+	struct __percpu iwl_tso_hdr_page * tso_hdr_page;
+
 	struct {
 		u8 fifo;
 		u8 q_id;
 		unsigned int wdg_timeout;
 	} cmd;
 
+	struct {
+		u8 max_tbs;
+		u16 size;
+		u8 addr_size;
+	} tfd;
+
+	struct iwl_dma_ptr scd_bc_tbls;
 };
 
 /**
@@ -939,7 +964,6 @@ struct iwl_trans_txqs {
  * @hw_id_str: a string with info about HW ID. Set during transport allocation.
  * @pm_support: set to true in start_hw if link pm is supported
  * @ltr_enabled: set to true if the LTR is enabled
- * @wide_cmd_header: true when ucode supports wide command header format
  * @num_rx_queues: number of RX queues allocated by the transport;
  *	the transport must set this before calling iwl_drv_start()
  * @iml_len: the length of the image loader
@@ -979,7 +1003,6 @@ struct iwl_trans {
 
 	const struct iwl_hcmd_arr *command_groups;
 	int command_groups_size;
-	bool wide_cmd_header;
 
 	u8 num_rx_queues;
 
@@ -1435,10 +1458,9 @@ static inline bool iwl_trans_dbg_ini_valid(struct iwl_trans *trans)
  * transport helper functions
  *****************************************************/
 struct iwl_trans *iwl_trans_alloc(unsigned int priv_size,
-				  struct device *dev,
-				  const struct iwl_trans_ops *ops,
-				  unsigned int cmd_pool_size,
-				  unsigned int cmd_pool_align);
+			  struct device *dev,
+			  const struct iwl_trans_ops *ops,
+			  const struct iwl_cfg_trans_params *cfg_trans);
 void iwl_trans_free(struct iwl_trans *trans);
 
 /*****************************************************
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/constants.h b/drivers/net/wireless/intel/iwlwifi/mvm/constants.h
index b0268f44b2ea..2487871eac73 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/constants.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/constants.h
@@ -152,12 +152,18 @@
 #define IWL_MVM_FTM_INITIATOR_ALGO		IWL_TOF_ALGO_TYPE_MAX_LIKE
 #define IWL_MVM_FTM_INITIATOR_DYNACK		true
 #define IWL_MVM_D3_DEBUG			false
-#define IWL_MVM_USE_TWT				false
+#define IWL_MVM_USE_TWT				true
 #define IWL_MVM_AMPDU_CONSEC_DROPS_DELBA	10
 #define IWL_MVM_USE_NSSN_SYNC			0
 #define IWL_MVM_PHY_FILTER_CHAIN_A		0
 #define IWL_MVM_PHY_FILTER_CHAIN_B		0
 #define IWL_MVM_PHY_FILTER_CHAIN_C		0
 #define IWL_MVM_PHY_FILTER_CHAIN_D		0
+#define IWL_MVM_FTM_INITIATOR_ENABLE_SMOOTH     false
+#define IWL_MVM_FTM_INITIATOR_SMOOTH_ALPHA      40
+/*  20016 pSec is 6 meter RTT, meaning 3 meter range */
+#define IWL_MVM_FTM_INITIATOR_SMOOTH_UNDERSHOOT 20016
+#define IWL_MVM_FTM_INITIATOR_SMOOTH_OVERSHOOT  20016
+#define IWL_MVM_FTM_INITIATOR_SMOOTH_AGE_SEC    2
 
 #endif /* __MVM_CONSTANTS_H */
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
index 2a94545d737f..e47c0be28656 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
@@ -70,6 +70,7 @@
 #include "iwl-modparams.h"
 #include "fw-api.h"
 #include "mvm.h"
+#include "fw/img.h"
 
 void iwl_mvm_set_rekey_data(struct ieee80211_hw *hw,
 			    struct ieee80211_vif *vif,
@@ -80,8 +81,11 @@ void iwl_mvm_set_rekey_data(struct ieee80211_hw *hw,
 
 	mutex_lock(&mvm->mutex);
 
-	memcpy(mvmvif->rekey_data.kek, data->kek, NL80211_KEK_LEN);
-	memcpy(mvmvif->rekey_data.kck, data->kck, NL80211_KCK_LEN);
+	mvmvif->rekey_data.kek_len = data->kek_len;
+	mvmvif->rekey_data.kck_len = data->kck_len;
+	memcpy(mvmvif->rekey_data.kek, data->kek, data->kek_len);
+	memcpy(mvmvif->rekey_data.kck, data->kck, data->kck_len);
+	mvmvif->rekey_data.akm = data->akm & 0xFF;
 	mvmvif->rekey_data.replay_ctr =
 		cpu_to_le64(be64_to_cpup((__be64 *)data->replay_ctr));
 	mvmvif->rekey_data.valid = true;
@@ -156,6 +160,7 @@ static const u8 *iwl_mvm_find_max_pn(struct ieee80211_key_conf *key,
 struct wowlan_key_data {
 	struct iwl_wowlan_rsc_tsc_params_cmd *rsc_tsc;
 	struct iwl_wowlan_tkip_params_cmd *tkip;
+	struct iwl_wowlan_kek_kck_material_cmd_v3 *kek_kck_cmd;
 	bool error, use_rsc_tsc, use_tkip, configure_keys;
 	int wep_key_idx;
 };
@@ -232,7 +237,12 @@ static void iwl_mvm_wowlan_program_keys(struct ieee80211_hw *hw,
 	default:
 		data->error = true;
 		return;
+	case WLAN_CIPHER_SUITE_BIP_GMAC_256:
+	case WLAN_CIPHER_SUITE_BIP_GMAC_128:
+		data->kek_kck_cmd->igtk_cipher = cpu_to_le32(STA_KEY_FLG_GCMP);
+		return;
 	case WLAN_CIPHER_SUITE_AES_CMAC:
+		data->kek_kck_cmd->igtk_cipher = cpu_to_le32(STA_KEY_FLG_CCM);
 		/*
 		 * Ignore CMAC keys -- the WoWLAN firmware doesn't support them
 		 * but we also shouldn't abort suspend due to that. It does have
@@ -245,8 +255,10 @@ static void iwl_mvm_wowlan_program_keys(struct ieee80211_hw *hw,
 		if (sta) {
 			u64 pn64;
 
-			tkip_sc = data->rsc_tsc->all_tsc_rsc.tkip.unicast_rsc;
-			tkip_tx_sc = &data->rsc_tsc->all_tsc_rsc.tkip.tsc;
+			tkip_sc =
+			   data->rsc_tsc->params.all_tsc_rsc.tkip.unicast_rsc;
+			tkip_tx_sc =
+				&data->rsc_tsc->params.all_tsc_rsc.tkip.tsc;
 
 			rx_p1ks = data->tkip->rx_uni;
 
@@ -265,9 +277,11 @@ static void iwl_mvm_wowlan_program_keys(struct ieee80211_hw *hw,
 			rx_mic_key = data->tkip->mic_keys.rx_unicast;
 		} else {
 			tkip_sc =
-				data->rsc_tsc->all_tsc_rsc.tkip.multicast_rsc;
+			  data->rsc_tsc->params.all_tsc_rsc.tkip.multicast_rsc;
 			rx_p1ks = data->tkip->rx_multi;
 			rx_mic_key = data->tkip->mic_keys.rx_mcast;
+			data->kek_kck_cmd->gtk_cipher =
+				cpu_to_le32(STA_KEY_FLG_TKIP);
 		}
 
 		/*
@@ -299,16 +313,25 @@ static void iwl_mvm_wowlan_program_keys(struct ieee80211_hw *hw,
 		data->use_rsc_tsc = true;
 		break;
 	case WLAN_CIPHER_SUITE_CCMP:
+	case WLAN_CIPHER_SUITE_GCMP:
+	case WLAN_CIPHER_SUITE_GCMP_256:
 		if (sta) {
 			u64 pn64;
 
-			aes_sc = data->rsc_tsc->all_tsc_rsc.aes.unicast_rsc;
-			aes_tx_sc = &data->rsc_tsc->all_tsc_rsc.aes.tsc;
+			aes_sc =
+			   data->rsc_tsc->params.all_tsc_rsc.aes.unicast_rsc;
+			aes_tx_sc =
+				&data->rsc_tsc->params.all_tsc_rsc.aes.tsc;
 
 			pn64 = atomic64_read(&key->tx_pn);
 			aes_tx_sc->pn = cpu_to_le64(pn64);
 		} else {
-			aes_sc = data->rsc_tsc->all_tsc_rsc.aes.multicast_rsc;
+			aes_sc =
+			   data->rsc_tsc->params.all_tsc_rsc.aes.multicast_rsc;
+			data->kek_kck_cmd->gtk_cipher =
+				key->cipher == WLAN_CIPHER_SUITE_CCMP ?
+				cpu_to_le32(STA_KEY_FLG_CCM) :
+				cpu_to_le32(STA_KEY_FLG_GCMP);
 		}
 
 		/*
@@ -354,6 +377,8 @@ static void iwl_mvm_wowlan_program_keys(struct ieee80211_hw *hw,
 		break;
 	}
 
+	IWL_DEBUG_WOWLAN(mvm, "GTK cipher %d\n", data->kek_kck_cmd->gtk_cipher);
+
 	if (data->configure_keys) {
 		mutex_lock(&mvm->mutex);
 		/*
@@ -734,7 +759,7 @@ static int iwl_mvm_wowlan_config_key_params(struct iwl_mvm *mvm,
 					    struct ieee80211_vif *vif,
 					    u32 cmd_flags)
 {
-	struct iwl_wowlan_kek_kck_material_cmd kek_kck_cmd = {};
+	struct iwl_wowlan_kek_kck_material_cmd_v3 kek_kck_cmd = {};
 	struct iwl_wowlan_tkip_params_cmd tkip_cmd = {};
 	bool unified = fw_has_capa(&mvm->fw->ucode_capa,
 				   IWL_UCODE_TLV_CAPA_CNSLDTD_D3_D0_IMG);
@@ -743,9 +768,12 @@ static int iwl_mvm_wowlan_config_key_params(struct iwl_mvm *mvm,
 		.use_rsc_tsc = false,
 		.tkip = &tkip_cmd,
 		.use_tkip = false,
+		.kek_kck_cmd = &kek_kck_cmd,
 	};
 	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
 	int ret;
+	u8 cmd_ver;
+	size_t cmd_size;
 
 	key_data.rsc_tsc = kzalloc(sizeof(*key_data.rsc_tsc), GFP_KERNEL);
 	if (!key_data.rsc_tsc)
@@ -772,10 +800,29 @@ static int iwl_mvm_wowlan_config_key_params(struct iwl_mvm *mvm,
 	}
 
 	if (key_data.use_rsc_tsc) {
-		ret = iwl_mvm_send_cmd_pdu(mvm,
-					   WOWLAN_TSC_RSC_PARAM, cmd_flags,
-					   sizeof(*key_data.rsc_tsc),
+		int ver = iwl_fw_lookup_cmd_ver(mvm->fw, LONG_GROUP,
+						WOWLAN_TSC_RSC_PARAM,
+						IWL_FW_CMD_VER_UNKNOWN);
+		int size;
+
+		if (ver == 4) {
+			size = sizeof(*key_data.rsc_tsc);
+			key_data.rsc_tsc->sta_id =
+				cpu_to_le32(mvmvif->ap_sta_id);
+
+		} else if (ver == 2 || ver == IWL_FW_CMD_VER_UNKNOWN) {
+			size = sizeof(key_data.rsc_tsc->params);
+		} else {
+			ret = 0;
+			WARN_ON_ONCE(1);
+			goto out;
+		}
+
+		ret = iwl_mvm_send_cmd_pdu(mvm, WOWLAN_TSC_RSC_PARAM,
+					   cmd_flags,
+					   size,
 					   key_data.rsc_tsc);
+
 		if (ret)
 			goto out;
 	}
@@ -783,9 +830,27 @@ static int iwl_mvm_wowlan_config_key_params(struct iwl_mvm *mvm,
 	if (key_data.use_tkip &&
 	    !fw_has_api(&mvm->fw->ucode_capa,
 			IWL_UCODE_TLV_API_TKIP_MIC_KEYS)) {
+		int ver = iwl_fw_lookup_cmd_ver(mvm->fw, LONG_GROUP,
+						WOWLAN_TKIP_PARAM,
+						IWL_FW_CMD_VER_UNKNOWN);
+		int size;
+
+		if (ver == 2) {
+			size = sizeof(tkip_cmd);
+			key_data.tkip->sta_id =
+				cpu_to_le32(mvmvif->ap_sta_id);
+		} else if (ver == 1 || ver == IWL_FW_CMD_VER_UNKNOWN) {
+			size = sizeof(struct iwl_wowlan_tkip_params_cmd_ver_1);
+		} else {
+			ret =  -EINVAL;
+			WARN_ON_ONCE(1);
+			goto out;
+		}
+
+		/* send relevant data according to CMD version */
 		ret = iwl_mvm_send_cmd_pdu(mvm,
 					   WOWLAN_TKIP_PARAM,
-					   cmd_flags, sizeof(tkip_cmd),
+					   cmd_flags, size,
 					   &tkip_cmd);
 		if (ret)
 			goto out;
@@ -793,18 +858,34 @@ static int iwl_mvm_wowlan_config_key_params(struct iwl_mvm *mvm,
 
 	/* configure rekey data only if offloaded rekey is supported (d3) */
 	if (mvmvif->rekey_data.valid) {
+		cmd_ver = iwl_fw_lookup_cmd_ver(mvm->fw,
+						IWL_ALWAYS_LONG_GROUP,
+						WOWLAN_KEK_KCK_MATERIAL,
+						IWL_FW_CMD_VER_UNKNOWN);
+		if (WARN_ON(cmd_ver != 2 && cmd_ver != 3 &&
+			    cmd_ver != IWL_FW_CMD_VER_UNKNOWN))
+			return -EINVAL;
+		if (cmd_ver == 3)
+			cmd_size = sizeof(struct iwl_wowlan_kek_kck_material_cmd_v3);
+		else
+			cmd_size = sizeof(struct iwl_wowlan_kek_kck_material_cmd_v2);
+
 		memset(&kek_kck_cmd, 0, sizeof(kek_kck_cmd));
 		memcpy(kek_kck_cmd.kck, mvmvif->rekey_data.kck,
-		       NL80211_KCK_LEN);
-		kek_kck_cmd.kck_len = cpu_to_le16(NL80211_KCK_LEN);
+		       mvmvif->rekey_data.kck_len);
+		kek_kck_cmd.kck_len = cpu_to_le16(mvmvif->rekey_data.kck_len);
 		memcpy(kek_kck_cmd.kek, mvmvif->rekey_data.kek,
-		       NL80211_KEK_LEN);
-		kek_kck_cmd.kek_len = cpu_to_le16(NL80211_KEK_LEN);
+		       mvmvif->rekey_data.kek_len);
+		kek_kck_cmd.kek_len = cpu_to_le16(mvmvif->rekey_data.kek_len);
 		kek_kck_cmd.replay_ctr = mvmvif->rekey_data.replay_ctr;
+		kek_kck_cmd.akm = cpu_to_le32(mvmvif->rekey_data.akm);
+
+		IWL_DEBUG_WOWLAN(mvm, "setting akm %d\n",
+				 mvmvif->rekey_data.akm);
 
 		ret = iwl_mvm_send_cmd_pdu(mvm,
 					   WOWLAN_KEK_KCK_MATERIAL, cmd_flags,
-					   sizeof(kek_kck_cmd),
+					   cmd_size,
 					   &kek_kck_cmd);
 		if (ret)
 			goto out;
@@ -1331,6 +1412,8 @@ static void iwl_mvm_set_key_rx_seq(struct iwl_mvm *mvm,
 
 	switch (key->cipher) {
 	case WLAN_CIPHER_SUITE_CCMP:
+	case WLAN_CIPHER_SUITE_GCMP:
+	case WLAN_CIPHER_SUITE_GCMP_256:
 		iwl_mvm_set_aes_rx_seq(mvm, rsc->aes.multicast_rsc, NULL, key);
 		break;
 	case WLAN_CIPHER_SUITE_TKIP:
@@ -1367,6 +1450,8 @@ static void iwl_mvm_d3_update_keys(struct ieee80211_hw *hw,
 		/* ignore WEP completely, nothing to do */
 		return;
 	case WLAN_CIPHER_SUITE_CCMP:
+	case WLAN_CIPHER_SUITE_GCMP:
+	case WLAN_CIPHER_SUITE_GCMP_256:
 	case WLAN_CIPHER_SUITE_TKIP:
 		/* we support these */
 		break;
@@ -1392,6 +1477,8 @@ static void iwl_mvm_d3_update_keys(struct ieee80211_hw *hw,
 
 		switch (key->cipher) {
 		case WLAN_CIPHER_SUITE_CCMP:
+		case WLAN_CIPHER_SUITE_GCMP:
+		case WLAN_CIPHER_SUITE_GCMP_256:
 			iwl_mvm_set_aes_rx_seq(data->mvm, sc->aes.unicast_rsc,
 					       sta, key);
 			atomic64_set(&key->tx_pn, le64_to_cpu(sc->aes.tsc.pn));
@@ -1460,6 +1547,8 @@ static bool iwl_mvm_setup_connection_keep(struct iwl_mvm *mvm,
 	ieee80211_iter_keys(mvm->hw, vif,
 			    iwl_mvm_d3_update_keys, &gtkdata);
 
+	IWL_DEBUG_WOWLAN(mvm, "num of GTK rekeying %d\n",
+			 le32_to_cpu(status->num_of_gtk_rekeys));
 	if (status->num_of_gtk_rekeys) {
 		struct ieee80211_key_conf *key;
 		struct {
@@ -1472,13 +1561,26 @@ static bool iwl_mvm_setup_connection_keep(struct iwl_mvm *mvm,
 		};
 		__be64 replay_ctr;
 
+		IWL_DEBUG_WOWLAN(mvm,
+				 "Received from FW GTK cipher %d, key index %d\n",
+				 conf.conf.cipher, conf.conf.keyidx);
 		switch (gtkdata.cipher) {
 		case WLAN_CIPHER_SUITE_CCMP:
+		case WLAN_CIPHER_SUITE_GCMP:
+			BUILD_BUG_ON(WLAN_KEY_LEN_CCMP != WLAN_KEY_LEN_GCMP);
+			BUILD_BUG_ON(sizeof(conf.key) < WLAN_KEY_LEN_CCMP);
 			conf.conf.keylen = WLAN_KEY_LEN_CCMP;
 			memcpy(conf.conf.key, status->gtk[0].key,
 			       WLAN_KEY_LEN_CCMP);
 			break;
+		case WLAN_CIPHER_SUITE_GCMP_256:
+			BUILD_BUG_ON(sizeof(conf.key) < WLAN_KEY_LEN_GCMP_256);
+			conf.conf.keylen = WLAN_KEY_LEN_GCMP_256;
+			memcpy(conf.conf.key, status->gtk[0].key,
+			       WLAN_KEY_LEN_GCMP_256);
+			break;
 		case WLAN_CIPHER_SUITE_TKIP:
+			BUILD_BUG_ON(sizeof(conf.key) < WLAN_KEY_LEN_TKIP);
 			conf.conf.keylen = WLAN_KEY_LEN_TKIP;
 			memcpy(conf.conf.key, status->gtk[0].key, 16);
 			/* leave TX MIC key zeroed, we don't use it anyway */
@@ -1508,15 +1610,60 @@ out:
 	return true;
 }
 
+/* Occasionally, templates would be nice. This is one of those times ... */
+#define iwl_mvm_parse_wowlan_status_common(_ver)			\
+static struct iwl_wowlan_status *					\
+iwl_mvm_parse_wowlan_status_common_ ## _ver(struct iwl_mvm *mvm,	\
+					    void *_data, int len)	\
+{									\
+	struct iwl_wowlan_status *status;				\
+	struct iwl_wowlan_status_ ##_ver *data = _data;			\
+	int data_size;							\
+									\
+	if (len < sizeof(*data)) {					\
+		IWL_ERR(mvm, "Invalid WoWLAN status response!\n");	\
+		return ERR_PTR(-EIO);					\
+	}								\
+									\
+	data_size = ALIGN(le32_to_cpu(data->wake_packet_bufsize), 4);	\
+	if (len != sizeof(*data) + data_size) {				\
+		IWL_ERR(mvm, "Invalid WoWLAN status response!\n");	\
+		return ERR_PTR(-EIO);					\
+	}								\
+									\
+	status = kzalloc(sizeof(*status) + data_size, GFP_KERNEL);	\
+	if (!status)							\
+		return ERR_PTR(-ENOMEM);				\
+									\
+	/* copy all the common fields */				\
+	status->replay_ctr = data->replay_ctr;				\
+	status->pattern_number = data->pattern_number;			\
+	status->non_qos_seq_ctr = data->non_qos_seq_ctr;		\
+	memcpy(status->qos_seq_ctr, data->qos_seq_ctr,			\
+	       sizeof(status->qos_seq_ctr));				\
+	status->wakeup_reasons = data->wakeup_reasons;			\
+	status->num_of_gtk_rekeys = data->num_of_gtk_rekeys;		\
+	status->received_beacons = data->received_beacons;		\
+	status->wake_packet_length = data->wake_packet_length;		\
+	status->wake_packet_bufsize = data->wake_packet_bufsize;	\
+	memcpy(status->wake_packet, data->wake_packet,			\
+	       le32_to_cpu(status->wake_packet_bufsize));		\
+									\
+	return status;							\
+}
+
+iwl_mvm_parse_wowlan_status_common(v6)
+iwl_mvm_parse_wowlan_status_common(v7)
+iwl_mvm_parse_wowlan_status_common(v9)
+
 struct iwl_wowlan_status *iwl_mvm_send_wowlan_get_status(struct iwl_mvm *mvm)
 {
-	struct iwl_wowlan_status_v7 *v7;
 	struct iwl_wowlan_status *status;
 	struct iwl_host_cmd cmd = {
 		.id = WOWLAN_GET_STATUSES,
 		.flags = CMD_WANT_SKB,
 	};
-	int ret, len, status_size, data_size;
+	int ret, len;
 	u8 notif_ver;
 
 	lockdep_assert_held(&mvm->mutex);
@@ -1528,28 +1675,19 @@ struct iwl_wowlan_status *iwl_mvm_send_wowlan_get_status(struct iwl_mvm *mvm)
 	}
 
 	len = iwl_rx_packet_payload_len(cmd.resp_pkt);
+
+	/* default to 7 (when we have IWL_UCODE_TLV_API_WOWLAN_KEY_MATERIAL) */
+	notif_ver = iwl_fw_lookup_notif_ver(mvm->fw, LEGACY_GROUP,
+					    WOWLAN_GET_STATUSES, 7);
+
 	if (!fw_has_api(&mvm->fw->ucode_capa,
 			IWL_UCODE_TLV_API_WOWLAN_KEY_MATERIAL)) {
 		struct iwl_wowlan_status_v6 *v6 = (void *)cmd.resp_pkt->data;
 
-		status_size = sizeof(*v6);
-
-		if (len < status_size) {
-			IWL_ERR(mvm, "Invalid WoWLAN status response!\n");
-			status = ERR_PTR(-EIO);
-			goto out_free_resp;
-		}
-
-		data_size = ALIGN(le32_to_cpu(v6->wake_packet_bufsize), 4);
-
-		if (len != (status_size + data_size)) {
-			IWL_ERR(mvm, "Invalid WoWLAN status response!\n");
-			status = ERR_PTR(-EIO);
-			goto out_free_resp;
-		}
-
-		status = kzalloc(sizeof(*status) + data_size, GFP_KERNEL);
-		if (!status)
+		status = iwl_mvm_parse_wowlan_status_common_v6(mvm,
+							       cmd.resp_pkt->data,
+							       len);
+		if (IS_ERR(status))
 			goto out_free_resp;
 
 		BUILD_BUG_ON(sizeof(v6->gtk.decrypt_key) >
@@ -1574,47 +1712,37 @@ struct iwl_wowlan_status *iwl_mvm_send_wowlan_get_status(struct iwl_mvm *mvm)
 		 * currently used key.
 		 */
 		status->gtk[0].key_flags = v6->gtk.key_index | BIT(7);
+	} else if (notif_ver == 7) {
+		struct iwl_wowlan_status_v7 *v7 = (void *)cmd.resp_pkt->data;
 
-		status->replay_ctr = v6->replay_ctr;
-
-		/* everything starting from pattern_number is identical */
-		memcpy(&status->pattern_number, &v6->pattern_number,
-		       offsetof(struct iwl_wowlan_status, wake_packet) -
-		       offsetof(struct iwl_wowlan_status, pattern_number) +
-		       data_size);
-
-		goto out_free_resp;
-	}
-
-	v7 = (void *)cmd.resp_pkt->data;
-	notif_ver = iwl_fw_lookup_notif_ver(mvm->fw, LEGACY_GROUP,
-					    WOWLAN_GET_STATUSES, 0);
+		status = iwl_mvm_parse_wowlan_status_common_v7(mvm,
+							       cmd.resp_pkt->data,
+							       len);
+		if (IS_ERR(status))
+			goto out_free_resp;
 
-	status_size = sizeof(*status);
+		status->gtk[0] = v7->gtk[0];
+		status->igtk[0] = v7->igtk[0];
+	} else if (notif_ver == 9) {
+		struct iwl_wowlan_status_v9 *v9 = (void *)cmd.resp_pkt->data;
 
-	if (notif_ver == IWL_FW_CMD_VER_UNKNOWN || notif_ver < 9)
-		status_size = sizeof(*v7);
+		status = iwl_mvm_parse_wowlan_status_common_v9(mvm,
+							       cmd.resp_pkt->data,
+							       len);
+		if (IS_ERR(status))
+			goto out_free_resp;
 
-	if (len < status_size) {
-		IWL_ERR(mvm, "Invalid WoWLAN status response!\n");
-		status = ERR_PTR(-EIO);
-		goto out_free_resp;
-	}
-	data_size = ALIGN(le32_to_cpu(v7->wake_packet_bufsize), 4);
+		status->gtk[0] = v9->gtk[0];
+		status->igtk[0] = v9->igtk[0];
 
-	if (len != (status_size + data_size)) {
-		IWL_ERR(mvm, "Invalid WoWLAN status response!\n");
+		status->tid_tear_down = v9->tid_tear_down;
+	} else {
+		IWL_ERR(mvm,
+			"Firmware advertises unknown WoWLAN status response %d!\n",
+			notif_ver);
 		status = ERR_PTR(-EIO);
-		goto out_free_resp;
 	}
 
-	status = kzalloc(sizeof(*status) + data_size, GFP_KERNEL);
-	if (!status)
-		goto out_free_resp;
-
-	memcpy(status, v7, status_size);
-	memcpy(status->wake_packet, (u8 *)v7 + status_size, data_size);
-
 out_free_resp:
 	iwl_free_resp(&cmd);
 	return status;
@@ -1647,6 +1775,9 @@ static bool iwl_mvm_query_wakeup_reasons(struct iwl_mvm *mvm,
 	if (IS_ERR_OR_NULL(fw_status))
 		goto out_unlock;
 
+	IWL_DEBUG_WOWLAN(mvm, "wakeup reason 0x%x\n",
+			 le32_to_cpu(fw_status->wakeup_reasons));
+
 	status.pattern_number = le16_to_cpu(fw_status->pattern_number);
 	for (i = 0; i < 8; i++)
 		status.qos_seq_ctr[i] =
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c
index 5ca45915cf7c..a0ce761d0c59 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c
@@ -76,6 +76,103 @@ struct iwl_mvm_loc_entry {
 	u8 buf[];
 };
 
+struct iwl_mvm_smooth_entry {
+	struct list_head list;
+	u8 addr[ETH_ALEN];
+	s64 rtt_avg;
+	u64 host_time;
+};
+
+struct iwl_mvm_ftm_pasn_entry {
+	struct list_head list;
+	u8 addr[ETH_ALEN];
+	u8 hltk[HLTK_11AZ_LEN];
+	u8 tk[TK_11AZ_LEN];
+	u8 cipher;
+	u8 tx_pn[IEEE80211_CCMP_PN_LEN];
+	u8 rx_pn[IEEE80211_CCMP_PN_LEN];
+};
+
+int iwl_mvm_ftm_add_pasn_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
+			     u8 *addr, u32 cipher, u8 *tk, u32 tk_len,
+			     u8 *hltk, u32 hltk_len)
+{
+	struct iwl_mvm_ftm_pasn_entry *pasn = kzalloc(sizeof(*pasn),
+						      GFP_KERNEL);
+	u32 expected_tk_len;
+
+	lockdep_assert_held(&mvm->mutex);
+
+	if (!pasn)
+		return -ENOBUFS;
+
+	pasn->cipher = iwl_mvm_cipher_to_location_cipher(cipher);
+
+	switch (pasn->cipher) {
+	case IWL_LOCATION_CIPHER_CCMP_128:
+	case IWL_LOCATION_CIPHER_GCMP_128:
+		expected_tk_len = WLAN_KEY_LEN_CCMP;
+		break;
+	case IWL_LOCATION_CIPHER_GCMP_256:
+		expected_tk_len = WLAN_KEY_LEN_GCMP_256;
+		break;
+	default:
+		goto out;
+	}
+
+	/*
+	 * If associated to this AP and already have security context,
+	 * the TK is already configured for this station, so it
+	 * shouldn't be set again here.
+	 */
+	if (vif->bss_conf.assoc &&
+	    !memcmp(addr, vif->bss_conf.bssid, ETH_ALEN)) {
+		struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
+		struct ieee80211_sta *sta;
+
+		rcu_read_lock();
+		sta = rcu_dereference(mvm->fw_id_to_mac_id[mvmvif->ap_sta_id]);
+		if (!IS_ERR_OR_NULL(sta) && sta->mfp)
+			expected_tk_len = 0;
+		rcu_read_unlock();
+	}
+
+	if (tk_len != expected_tk_len || hltk_len != sizeof(pasn->hltk)) {
+		IWL_ERR(mvm, "Invalid key length: tk_len=%u hltk_len=%u\n",
+			tk_len, hltk_len);
+		goto out;
+	}
+
+	memcpy(pasn->addr, addr, sizeof(pasn->addr));
+	memcpy(pasn->hltk, hltk, sizeof(pasn->hltk));
+
+	if (tk && tk_len)
+		memcpy(pasn->tk, tk, sizeof(pasn->tk));
+
+	list_add_tail(&pasn->list, &mvm->ftm_initiator.pasn_list);
+	return 0;
+out:
+	kfree(pasn);
+	return -EINVAL;
+}
+
+void iwl_mvm_ftm_remove_pasn_sta(struct iwl_mvm *mvm, u8 *addr)
+{
+	struct iwl_mvm_ftm_pasn_entry *entry, *prev;
+
+	lockdep_assert_held(&mvm->mutex);
+
+	list_for_each_entry_safe(entry, prev, &mvm->ftm_initiator.pasn_list,
+				 list) {
+		if (memcmp(entry->addr, addr, sizeof(entry->addr)))
+			continue;
+
+		list_del(&entry->list);
+		kfree(entry);
+		return;
+	}
+}
+
 static void iwl_mvm_ftm_reset(struct iwl_mvm *mvm)
 {
 	struct iwl_mvm_loc_entry *e, *t;
@@ -84,6 +181,7 @@ static void iwl_mvm_ftm_reset(struct iwl_mvm *mvm)
 	mvm->ftm_initiator.req_wdev = NULL;
 	memset(mvm->ftm_initiator.responses, 0,
 	       sizeof(mvm->ftm_initiator.responses));
+
 	list_for_each_entry_safe(e, t, &mvm->ftm_initiator.loc_list, list) {
 		list_del(&e->list);
 		kfree(e);
@@ -120,6 +218,30 @@ void iwl_mvm_ftm_restart(struct iwl_mvm *mvm)
 	iwl_mvm_ftm_reset(mvm);
 }
 
+void iwl_mvm_ftm_initiator_smooth_config(struct iwl_mvm *mvm)
+{
+	INIT_LIST_HEAD(&mvm->ftm_initiator.smooth.resp);
+
+	IWL_DEBUG_INFO(mvm,
+		       "enable=%u, alpha=%u, age_jiffies=%u, thresh=(%u:%u)\n",
+			IWL_MVM_FTM_INITIATOR_ENABLE_SMOOTH,
+			IWL_MVM_FTM_INITIATOR_SMOOTH_ALPHA,
+			IWL_MVM_FTM_INITIATOR_SMOOTH_AGE_SEC * HZ,
+			IWL_MVM_FTM_INITIATOR_SMOOTH_OVERSHOOT,
+			IWL_MVM_FTM_INITIATOR_SMOOTH_UNDERSHOOT);
+}
+
+void iwl_mvm_ftm_initiator_smooth_stop(struct iwl_mvm *mvm)
+{
+	struct iwl_mvm_smooth_entry *se, *st;
+
+	list_for_each_entry_safe(se, st, &mvm->ftm_initiator.smooth.resp,
+				 list) {
+		list_del(&se->list);
+		kfree(se);
+	}
+}
+
 static int
 iwl_ftm_range_request_status_to_err(enum iwl_tof_range_request_status s)
 {
@@ -166,7 +288,7 @@ static void iwl_mvm_ftm_cmd_v5(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 
 static void iwl_mvm_ftm_cmd_common(struct iwl_mvm *mvm,
 				   struct ieee80211_vif *vif,
-				   struct iwl_tof_range_req_cmd *cmd,
+				   struct iwl_tof_range_req_cmd_v9 *cmd,
 				   struct cfg80211_pmsr_request *req)
 {
 	int i;
@@ -335,7 +457,7 @@ iwl_mvm_ftm_put_target_v2(struct iwl_mvm *mvm,
 static void
 iwl_mvm_ftm_put_target_common(struct iwl_mvm *mvm,
 			      struct cfg80211_pmsr_request_peer *peer,
-			      struct iwl_tof_range_req_ap_entry *target)
+			      struct iwl_tof_range_req_ap_entry_v6 *target)
 {
 	memcpy(target->bssid, peer->addr, ETH_ALEN);
 	target->burst_period =
@@ -411,7 +533,7 @@ iwl_mvm_ftm_put_target_v4(struct iwl_mvm *mvm,
 static int
 iwl_mvm_ftm_put_target(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 		       struct cfg80211_pmsr_request_peer *peer,
-		       struct iwl_tof_range_req_ap_entry *target)
+		       struct iwl_tof_range_req_ap_entry_v6 *target)
 {
 	int ret;
 
@@ -421,7 +543,7 @@ iwl_mvm_ftm_put_target(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 	if (ret)
 		return ret;
 
-	iwl_mvm_ftm_put_target_common(mvm, peer, (void *)target);
+	iwl_mvm_ftm_put_target_common(mvm, peer, target);
 
 	if (vif->bss_conf.assoc &&
 	    !memcmp(peer->addr, vif->bss_conf.bssid, ETH_ALEN)) {
@@ -539,7 +661,7 @@ static int iwl_mvm_ftm_start_v8(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 static int iwl_mvm_ftm_start_v9(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 				struct cfg80211_pmsr_request *req)
 {
-	struct iwl_tof_range_req_cmd cmd;
+	struct iwl_tof_range_req_cmd_v9 cmd;
 	struct iwl_host_cmd hcmd = {
 		.id = iwl_cmd_id(TOF_RANGE_REQ_CMD, LOCATION_GROUP, 0),
 		.dataflags[0] = IWL_HCMD_DFL_DUP,
@@ -553,7 +675,7 @@ static int iwl_mvm_ftm_start_v9(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 
 	for (i = 0; i < cmd.num_of_ap; i++) {
 		struct cfg80211_pmsr_request_peer *peer = &req->peers[i];
-		struct iwl_tof_range_req_ap_entry *target = &cmd.ap[i];
+		struct iwl_tof_range_req_ap_entry_v6 *target = &cmd.ap[i];
 
 		err = iwl_mvm_ftm_put_target(mvm, vif, peer, target);
 		if (err)
@@ -563,6 +685,93 @@ static int iwl_mvm_ftm_start_v9(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 	return iwl_mvm_ftm_send_cmd(mvm, &hcmd);
 }
 
+static void iter(struct ieee80211_hw *hw,
+		 struct ieee80211_vif *vif,
+		 struct ieee80211_sta *sta,
+		 struct ieee80211_key_conf *key,
+		 void *data)
+{
+	struct iwl_tof_range_req_ap_entry_v6 *target = data;
+
+	if (!sta || memcmp(sta->addr, target->bssid, ETH_ALEN))
+		return;
+
+	WARN_ON(!sta->mfp);
+
+	if (WARN_ON(key->keylen > sizeof(target->tk)))
+		return;
+
+	memcpy(target->tk, key->key, key->keylen);
+	target->cipher = iwl_mvm_cipher_to_location_cipher(key->cipher);
+	WARN_ON(target->cipher == IWL_LOCATION_CIPHER_INVALID);
+}
+
+static void
+iwl_mvm_ftm_set_secured_ranging(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
+				struct iwl_tof_range_req_ap_entry_v7 *target)
+{
+	struct iwl_mvm_ftm_pasn_entry *entry;
+	u32 flags = le32_to_cpu(target->initiator_ap_flags);
+
+	if (!(flags & (IWL_INITIATOR_AP_FLAGS_NON_TB |
+		       IWL_INITIATOR_AP_FLAGS_TB)))
+		return;
+
+	lockdep_assert_held(&mvm->mutex);
+
+	list_for_each_entry(entry, &mvm->ftm_initiator.pasn_list, list) {
+		if (memcmp(entry->addr, target->bssid, sizeof(entry->addr)))
+			continue;
+
+		target->cipher = entry->cipher;
+		memcpy(target->hltk, entry->hltk, sizeof(target->hltk));
+
+		if (vif->bss_conf.assoc &&
+		    !memcmp(vif->bss_conf.bssid, target->bssid,
+			    sizeof(target->bssid)))
+			ieee80211_iter_keys(mvm->hw, vif, iter, target);
+		else
+			memcpy(target->tk, entry->tk, sizeof(target->tk));
+
+		memcpy(target->rx_pn, entry->rx_pn, sizeof(target->rx_pn));
+		memcpy(target->tx_pn, entry->tx_pn, sizeof(target->tx_pn));
+
+		target->initiator_ap_flags |=
+			cpu_to_le32(IWL_INITIATOR_AP_FLAGS_SECURED);
+		return;
+	}
+}
+
+static int iwl_mvm_ftm_start_v11(struct iwl_mvm *mvm,
+				 struct ieee80211_vif *vif,
+				 struct cfg80211_pmsr_request *req)
+{
+	struct iwl_tof_range_req_cmd_v11 cmd;
+	struct iwl_host_cmd hcmd = {
+		.id = iwl_cmd_id(TOF_RANGE_REQ_CMD, LOCATION_GROUP, 0),
+		.dataflags[0] = IWL_HCMD_DFL_DUP,
+		.data[0] = &cmd,
+		.len[0] = sizeof(cmd),
+	};
+	u8 i;
+	int err;
+
+	iwl_mvm_ftm_cmd_common(mvm, vif, (void *)&cmd, req);
+
+	for (i = 0; i < cmd.num_of_ap; i++) {
+		struct cfg80211_pmsr_request_peer *peer = &req->peers[i];
+		struct iwl_tof_range_req_ap_entry_v7 *target = &cmd.ap[i];
+
+		err = iwl_mvm_ftm_put_target(mvm, vif, peer, (void *)target);
+		if (err)
+			return err;
+
+		iwl_mvm_ftm_set_secured_ranging(mvm, vif, target);
+	}
+
+	return iwl_mvm_ftm_send_cmd(mvm, &hcmd);
+}
+
 int iwl_mvm_ftm_start(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 		      struct cfg80211_pmsr_request *req)
 {
@@ -577,9 +786,13 @@ int iwl_mvm_ftm_start(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 
 	if (new_api) {
 		u8 cmd_ver = iwl_fw_lookup_cmd_ver(mvm->fw, LOCATION_GROUP,
-						   TOF_RANGE_REQ_CMD);
+						   TOF_RANGE_REQ_CMD,
+						   IWL_FW_CMD_VER_UNKNOWN);
 
 		switch (cmd_ver) {
+		case 11:
+			err = iwl_mvm_ftm_start_v11(mvm, vif, req);
+			break;
 		case 9:
 		case 10:
 			err = iwl_mvm_ftm_start_v9(mvm, vif, req);
@@ -696,6 +909,95 @@ static int iwl_mvm_ftm_range_resp_valid(struct iwl_mvm *mvm, u8 request_id,
 	return 0;
 }
 
+static void iwl_mvm_ftm_rtt_smoothing(struct iwl_mvm *mvm,
+				      struct cfg80211_pmsr_result *res)
+{
+	struct iwl_mvm_smooth_entry *resp;
+	s64 rtt_avg, rtt = res->ftm.rtt_avg;
+	u32 undershoot, overshoot;
+	u8 alpha;
+	bool found;
+
+	if (!IWL_MVM_FTM_INITIATOR_ENABLE_SMOOTH)
+		return;
+
+	WARN_ON(rtt < 0);
+
+	if (res->status != NL80211_PMSR_STATUS_SUCCESS) {
+		IWL_DEBUG_INFO(mvm,
+			       ": %pM: ignore failed measurement. Status=%u\n",
+			       res->addr, res->status);
+		return;
+	}
+
+	found = false;
+	list_for_each_entry(resp, &mvm->ftm_initiator.smooth.resp, list) {
+		if (!memcmp(res->addr, resp->addr, ETH_ALEN)) {
+			found = true;
+			break;
+		}
+	}
+
+	if (!found) {
+		resp = kzalloc(sizeof(*resp), GFP_KERNEL);
+		if (!resp)
+			return;
+
+		memcpy(resp->addr, res->addr, ETH_ALEN);
+		list_add_tail(&resp->list, &mvm->ftm_initiator.smooth.resp);
+
+		resp->rtt_avg = rtt;
+
+		IWL_DEBUG_INFO(mvm, "new: %pM: rtt_avg=%lld\n",
+			       resp->addr, resp->rtt_avg);
+		goto update_time;
+	}
+
+	if (res->host_time - resp->host_time >
+	    IWL_MVM_FTM_INITIATOR_SMOOTH_AGE_SEC * 1000000000) {
+		resp->rtt_avg = rtt;
+
+		IWL_DEBUG_INFO(mvm, "expired: %pM: rtt_avg=%lld\n",
+			       resp->addr, resp->rtt_avg);
+		goto update_time;
+	}
+
+	/* Smooth the results based on the tracked RTT average */
+	undershoot = IWL_MVM_FTM_INITIATOR_SMOOTH_UNDERSHOOT;
+	overshoot = IWL_MVM_FTM_INITIATOR_SMOOTH_OVERSHOOT;
+	alpha = IWL_MVM_FTM_INITIATOR_SMOOTH_ALPHA;
+
+	rtt_avg = (alpha * rtt + (100 - alpha) * resp->rtt_avg) / 100;
+
+	IWL_DEBUG_INFO(mvm,
+		       "%pM: prev rtt_avg=%lld, new rtt_avg=%lld, rtt=%lld\n",
+		       resp->addr, resp->rtt_avg, rtt_avg, rtt);
+
+	/*
+	 * update the responder's average RTT results regardless of
+	 * the under/over shoot logic below
+	 */
+	resp->rtt_avg = rtt_avg;
+
+	/* smooth the results */
+	if (rtt_avg > rtt && (rtt_avg - rtt) > undershoot) {
+		res->ftm.rtt_avg = rtt_avg;
+
+		IWL_DEBUG_INFO(mvm,
+			       "undershoot: val=%lld\n",
+			       (rtt_avg - rtt));
+	} else if (rtt_avg < rtt && (rtt - rtt_avg) >
+		   overshoot) {
+		res->ftm.rtt_avg = rtt_avg;
+		IWL_DEBUG_INFO(mvm,
+			       "overshoot: val=%lld\n",
+			       (rtt - rtt_avg));
+	}
+
+update_time:
+	resp->host_time = res->host_time;
+}
+
 static void iwl_mvm_debug_range_resp(struct iwl_mvm *mvm, u8 index,
 				     struct cfg80211_pmsr_result *res)
 {
@@ -715,12 +1017,31 @@ static void iwl_mvm_debug_range_resp(struct iwl_mvm *mvm, u8 index,
 	IWL_DEBUG_INFO(mvm, "\tdistance: %lld\n", rtt_avg);
 }
 
+static void
+iwl_mvm_ftm_pasn_update_pn(struct iwl_mvm *mvm,
+			   struct iwl_tof_range_rsp_ap_entry_ntfy_v6 *fw_ap)
+{
+	struct iwl_mvm_ftm_pasn_entry *entry;
+
+	lockdep_assert_held(&mvm->mutex);
+
+	list_for_each_entry(entry, &mvm->ftm_initiator.pasn_list, list) {
+		if (memcmp(fw_ap->bssid, entry->addr, sizeof(entry->addr)))
+			continue;
+
+		memcpy(entry->rx_pn, fw_ap->rx_pn, sizeof(entry->rx_pn));
+		memcpy(entry->tx_pn, fw_ap->tx_pn, sizeof(entry->tx_pn));
+		return;
+	}
+}
+
 void iwl_mvm_ftm_range_resp(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb)
 {
 	struct iwl_rx_packet *pkt = rxb_addr(rxb);
 	struct iwl_tof_range_rsp_ntfy_v5 *fw_resp_v5 = (void *)pkt->data;
 	struct iwl_tof_range_rsp_ntfy_v6 *fw_resp_v6 = (void *)pkt->data;
-	struct iwl_tof_range_rsp_ntfy *fw_resp = (void *)pkt->data;
+	struct iwl_tof_range_rsp_ntfy_v7 *fw_resp_v7 = (void *)pkt->data;
+	struct iwl_tof_range_rsp_ntfy_v8 *fw_resp_v8 = (void *)pkt->data;
 	int i;
 	bool new_api = fw_has_api(&mvm->fw->ucode_capa,
 				  IWL_UCODE_TLV_API_FTM_NEW_RANGE_REQ);
@@ -733,12 +1054,12 @@ void iwl_mvm_ftm_range_resp(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb)
 	}
 
 	if (new_api) {
-		if (iwl_mvm_ftm_range_resp_valid(mvm, fw_resp->request_id,
-						 fw_resp->num_of_aps))
+		if (iwl_mvm_ftm_range_resp_valid(mvm, fw_resp_v8->request_id,
+						 fw_resp_v8->num_of_aps))
 			return;
 
-		num_of_aps = fw_resp->num_of_aps;
-		last_in_batch = fw_resp->last_report;
+		num_of_aps = fw_resp_v8->num_of_aps;
+		last_in_batch = fw_resp_v8->last_report;
 	} else {
 		if (iwl_mvm_ftm_range_resp_valid(mvm, fw_resp_v5->request_id,
 						 fw_resp_v5->num_of_aps))
@@ -754,17 +1075,21 @@ void iwl_mvm_ftm_range_resp(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb)
 
 	for (i = 0; i < num_of_aps && i < IWL_MVM_TOF_MAX_APS; i++) {
 		struct cfg80211_pmsr_result result = {};
-		struct iwl_tof_range_rsp_ap_entry_ntfy *fw_ap;
+		struct iwl_tof_range_rsp_ap_entry_ntfy_v6 *fw_ap;
 		int peer_idx;
 
 		if (new_api) {
-			if (fw_has_api(&mvm->fw->ucode_capa,
-				       IWL_UCODE_TLV_API_FTM_RTT_ACCURACY))
-				fw_ap = &fw_resp->ap[i];
-			else
+			if (mvm->cmd_ver.range_resp == 8) {
+				fw_ap = &fw_resp_v8->ap[i];
+				iwl_mvm_ftm_pasn_update_pn(mvm, fw_ap);
+			} else if (fw_has_api(&mvm->fw->ucode_capa,
+					      IWL_UCODE_TLV_API_FTM_RTT_ACCURACY)) {
+				fw_ap = (void *)&fw_resp_v7->ap[i];
+			} else {
 				fw_ap = (void *)&fw_resp_v6->ap[i];
+			}
 
-			result.final = fw_resp->ap[i].last_burst;
+			result.final = fw_ap->last_burst;
 			result.ap_tsf = le32_to_cpu(fw_ap->start_tsf);
 			result.ap_tsf_valid = 1;
 		} else {
@@ -830,6 +1155,8 @@ void iwl_mvm_ftm_range_resp(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb)
 
 		iwl_mvm_ftm_get_lci_civic(mvm, &result);
 
+		iwl_mvm_ftm_rtt_smoothing(mvm, &result);
+
 		cfg80211_pmsr_report(mvm->ftm_initiator.req_wdev,
 				     mvm->ftm_initiator.req,
 				     &result, GFP_KERNEL);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-responder.c b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-responder.c
index 0b6c32098b5a..c794612c41d5 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-responder.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-responder.c
@@ -6,7 +6,7 @@
  * GPL LICENSE SUMMARY
  *
  * Copyright(c) 2015 - 2017 Intel Deutschland GmbH
- * Copyright (C) 2018 - 2019 Intel Corporation
+ * Copyright (C) 2018 - 2020 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -27,7 +27,7 @@
  * BSD LICENSE
  *
  * Copyright(c) 2015 - 2017 Intel Deutschland GmbH
- * Copyright (C) 2018 - 2019 Intel Corporation
+ * Copyright (C) 2018 - 2020 Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -62,6 +62,18 @@
 #include "mvm.h"
 #include "constants.h"
 
+struct iwl_mvm_pasn_sta {
+	struct list_head list;
+	struct iwl_mvm_int_sta int_sta;
+	u8 addr[ETH_ALEN];
+};
+
+struct iwl_mvm_pasn_hltk_data {
+	u8 *addr;
+	u8 cipher;
+	u8 *hltk;
+};
+
 static int iwl_mvm_ftm_responder_set_bw_v1(struct cfg80211_chan_def *chandef,
 					   u8 *bw, u8 *ctrl_ch_position)
 {
@@ -137,7 +149,7 @@ iwl_mvm_ftm_responder_cmd(struct iwl_mvm *mvm,
 		.sta_id = mvmvif->bcast_sta.sta_id,
 	};
 	u8 cmd_ver = iwl_fw_lookup_cmd_ver(mvm->fw, LOCATION_GROUP,
-					   TOF_RESPONDER_CONFIG_CMD);
+					   TOF_RESPONDER_CONFIG_CMD, 6);
 	int err;
 
 	lockdep_assert_held(&mvm->mutex);
@@ -162,11 +174,11 @@ iwl_mvm_ftm_responder_cmd(struct iwl_mvm *mvm,
 }
 
 static int
-iwl_mvm_ftm_responder_dyn_cfg_cmd(struct iwl_mvm *mvm,
-				  struct ieee80211_vif *vif,
-				  struct ieee80211_ftm_responder_params *params)
+iwl_mvm_ftm_responder_dyn_cfg_v2(struct iwl_mvm *mvm,
+				 struct ieee80211_vif *vif,
+				 struct ieee80211_ftm_responder_params *params)
 {
-	struct iwl_tof_responder_dyn_config_cmd cmd = {
+	struct iwl_tof_responder_dyn_config_cmd_v2 cmd = {
 		.lci_len = cpu_to_le32(params->lci_len + 2),
 		.civic_len = cpu_to_le32(params->civicloc_len + 2),
 	};
@@ -207,6 +219,173 @@ iwl_mvm_ftm_responder_dyn_cfg_cmd(struct iwl_mvm *mvm,
 	return iwl_mvm_send_cmd(mvm, &hcmd);
 }
 
+static int
+iwl_mvm_ftm_responder_dyn_cfg_v3(struct iwl_mvm *mvm,
+				 struct ieee80211_vif *vif,
+				 struct ieee80211_ftm_responder_params *params,
+				 struct iwl_mvm_pasn_hltk_data *hltk_data)
+{
+	struct iwl_tof_responder_dyn_config_cmd cmd;
+	struct iwl_host_cmd hcmd = {
+		.id = iwl_cmd_id(TOF_RESPONDER_DYN_CONFIG_CMD,
+				 LOCATION_GROUP, 0),
+		.data[0] = &cmd,
+		.len[0] = sizeof(cmd),
+		/* may not be able to DMA from stack */
+		.dataflags[0] = IWL_HCMD_DFL_DUP,
+	};
+
+	lockdep_assert_held(&mvm->mutex);
+
+	cmd.valid_flags = 0;
+
+	if (params) {
+		if (params->lci_len + 2 > sizeof(cmd.lci_buf) ||
+		    params->civicloc_len + 2 > sizeof(cmd.civic_buf)) {
+			IWL_ERR(mvm,
+				"LCI/civic data too big (lci=%zd, civic=%zd)\n",
+				params->lci_len, params->civicloc_len);
+			return -ENOBUFS;
+		}
+
+		cmd.lci_buf[0] = WLAN_EID_MEASURE_REPORT;
+		cmd.lci_buf[1] = params->lci_len;
+		memcpy(cmd.lci_buf + 2, params->lci, params->lci_len);
+		cmd.lci_len = params->lci_len + 2;
+
+		cmd.civic_buf[0] = WLAN_EID_MEASURE_REPORT;
+		cmd.civic_buf[1] = params->civicloc_len;
+		memcpy(cmd.civic_buf + 2, params->civicloc,
+		       params->civicloc_len);
+		cmd.civic_len = params->civicloc_len + 2;
+
+		cmd.valid_flags |= IWL_RESPONDER_DYN_CFG_VALID_LCI |
+			IWL_RESPONDER_DYN_CFG_VALID_CIVIC;
+	}
+
+	if (hltk_data) {
+		if (hltk_data->cipher > IWL_LOCATION_CIPHER_GCMP_256) {
+			IWL_ERR(mvm, "invalid cipher: %u\n",
+				hltk_data->cipher);
+			return -EINVAL;
+		}
+
+		cmd.cipher = hltk_data->cipher;
+		memcpy(cmd.addr, hltk_data->addr, sizeof(cmd.addr));
+		memcpy(cmd.hltk_buf, hltk_data->hltk, sizeof(cmd.hltk_buf));
+		cmd.valid_flags |= IWL_RESPONDER_DYN_CFG_VALID_PASN_STA;
+	}
+
+	return iwl_mvm_send_cmd(mvm, &hcmd);
+}
+
+static int
+iwl_mvm_ftm_responder_dyn_cfg_cmd(struct iwl_mvm *mvm,
+				  struct ieee80211_vif *vif,
+				  struct ieee80211_ftm_responder_params *params)
+{
+	int ret;
+	u8 cmd_ver = iwl_fw_lookup_cmd_ver(mvm->fw, LOCATION_GROUP,
+					   TOF_RESPONDER_DYN_CONFIG_CMD, 2);
+
+	switch (cmd_ver) {
+	case 2:
+		ret = iwl_mvm_ftm_responder_dyn_cfg_v2(mvm, vif,
+						       params);
+		break;
+	case 3:
+		ret = iwl_mvm_ftm_responder_dyn_cfg_v3(mvm, vif,
+						       params, NULL);
+		break;
+	default:
+		IWL_ERR(mvm, "Unsupported DYN_CONFIG_CMD version %u\n",
+			cmd_ver);
+		ret = -ENOTSUPP;
+	}
+
+	return ret;
+}
+
+static void iwl_mvm_resp_del_pasn_sta(struct iwl_mvm *mvm,
+				      struct ieee80211_vif *vif,
+				      struct iwl_mvm_pasn_sta *sta)
+{
+	list_del(&sta->list);
+	iwl_mvm_rm_sta_id(mvm, vif, sta->int_sta.sta_id);
+	iwl_mvm_dealloc_int_sta(mvm, &sta->int_sta);
+	kfree(sta);
+}
+
+int iwl_mvm_ftm_respoder_add_pasn_sta(struct iwl_mvm *mvm,
+				      struct ieee80211_vif *vif,
+				      u8 *addr, u32 cipher, u8 *tk, u32 tk_len,
+				      u8 *hltk, u32 hltk_len)
+{
+	int ret;
+	struct iwl_mvm_pasn_sta *sta = NULL;
+	struct iwl_mvm_pasn_hltk_data hltk_data = {
+		.addr = addr,
+		.hltk = hltk,
+	};
+	u8 cmd_ver = iwl_fw_lookup_cmd_ver(mvm->fw, LOCATION_GROUP,
+					   TOF_RESPONDER_DYN_CONFIG_CMD, 2);
+
+	lockdep_assert_held(&mvm->mutex);
+
+	if (cmd_ver < 3) {
+		IWL_ERR(mvm, "Adding PASN station not supported by FW\n");
+		return -ENOTSUPP;
+	}
+
+	hltk_data.cipher = iwl_mvm_cipher_to_location_cipher(cipher);
+	if (hltk_data.cipher == IWL_LOCATION_CIPHER_INVALID) {
+		IWL_ERR(mvm, "invalid cipher: %u\n", cipher);
+		return -EINVAL;
+	}
+
+	if (tk && tk_len) {
+		sta = kzalloc(sizeof(*sta), GFP_KERNEL);
+		if (!sta)
+			return -ENOBUFS;
+
+		ret = iwl_mvm_add_pasn_sta(mvm, vif, &sta->int_sta, addr,
+					   cipher, tk, tk_len);
+		if (ret) {
+			kfree(sta);
+			return ret;
+		}
+	}
+
+	ret = iwl_mvm_ftm_responder_dyn_cfg_v3(mvm, vif, NULL, &hltk_data);
+	if (ret) {
+		if (sta)
+			iwl_mvm_resp_del_pasn_sta(mvm, vif, sta);
+		return ret;
+	}
+
+	memcpy(sta->addr, addr, ETH_ALEN);
+	list_add_tail(&sta->list, &mvm->resp_pasn_list);
+	return 0;
+}
+
+int iwl_mvm_ftm_resp_remove_pasn_sta(struct iwl_mvm *mvm,
+				     struct ieee80211_vif *vif, u8 *addr)
+{
+	struct iwl_mvm_pasn_sta *sta, *prev;
+
+	lockdep_assert_held(&mvm->mutex);
+
+	list_for_each_entry_safe(sta, prev, &mvm->resp_pasn_list, list) {
+		if (!memcmp(sta->addr, addr, ETH_ALEN)) {
+			iwl_mvm_resp_del_pasn_sta(mvm, vif, sta);
+			return 0;
+		}
+	}
+
+	IWL_ERR(mvm, "FTM: PASN station %pM not found\n", addr);
+	return -EINVAL;
+}
+
 int iwl_mvm_ftm_start_responder(struct iwl_mvm *mvm, struct ieee80211_vif *vif)
 {
 	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
@@ -255,12 +434,24 @@ int iwl_mvm_ftm_start_responder(struct iwl_mvm *mvm, struct ieee80211_vif *vif)
 	return ret;
 }
 
+void iwl_mvm_ftm_responder_clear(struct iwl_mvm *mvm,
+				 struct ieee80211_vif *vif)
+{
+	struct iwl_mvm_pasn_sta *sta, *prev;
+
+	lockdep_assert_held(&mvm->mutex);
+
+	list_for_each_entry_safe(sta, prev, &mvm->resp_pasn_list, list)
+		iwl_mvm_resp_del_pasn_sta(mvm, vif, sta);
+}
+
 void iwl_mvm_ftm_restart_responder(struct iwl_mvm *mvm,
 				   struct ieee80211_vif *vif)
 {
 	if (!vif->bss_conf.ftm_responder)
 		return;
 
+	iwl_mvm_ftm_responder_clear(mvm, vif);
 	iwl_mvm_ftm_start_responder(mvm, vif);
 }
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
index 95a613537047..4ea1032d8263 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
@@ -210,25 +210,36 @@ static bool iwl_alive_fn(struct iwl_notif_wait_data *notif_wait,
 	struct iwl_mvm *mvm =
 		container_of(notif_wait, struct iwl_mvm, notif_wait);
 	struct iwl_mvm_alive_data *alive_data = data;
-	struct mvm_alive_resp_v3 *palive3;
-	struct mvm_alive_resp *palive;
 	struct iwl_umac_alive *umac;
 	struct iwl_lmac_alive *lmac1;
 	struct iwl_lmac_alive *lmac2 = NULL;
 	u16 status;
-	u32 lmac_error_event_table, umac_error_event_table;
+	u32 lmac_error_event_table, umac_error_table;
+
+	/* we don't use the SKU ID from v5 yet, so handle it as v4 */
+	if (iwl_fw_lookup_notif_ver(mvm->fw, LEGACY_GROUP,
+				    UCODE_ALIVE_NTFY, 0) == 5 ||
+	    iwl_rx_packet_payload_len(pkt) == sizeof(struct iwl_alive_ntf_v4)) {
+		struct iwl_alive_ntf_v4 *palive;
 
-	if (iwl_rx_packet_payload_len(pkt) == sizeof(*palive)) {
 		palive = (void *)pkt->data;
 		umac = &palive->umac_data;
 		lmac1 = &palive->lmac_data[0];
 		lmac2 = &palive->lmac_data[1];
 		status = le16_to_cpu(palive->status);
-	} else {
+	} else if (iwl_rx_packet_payload_len(pkt) ==
+		   sizeof(struct iwl_alive_ntf_v3)) {
+		struct iwl_alive_ntf_v3 *palive3;
+
 		palive3 = (void *)pkt->data;
 		umac = &palive3->umac_data;
 		lmac1 = &palive3->lmac_data;
 		status = le16_to_cpu(palive3->status);
+	} else {
+		WARN(1, "unsupported alive notification (size %d)\n",
+		     iwl_rx_packet_payload_len(pkt));
+		/* get timeout later */
+		return false;
 	}
 
 	lmac_error_event_table =
@@ -239,26 +250,22 @@ static bool iwl_alive_fn(struct iwl_notif_wait_data *notif_wait,
 		mvm->trans->dbg.lmac_error_event_table[1] =
 			le32_to_cpu(lmac2->dbg_ptrs.error_event_table_ptr);
 
-	umac_error_event_table = le32_to_cpu(umac->dbg_ptrs.error_info_addr);
+	umac_error_table = le32_to_cpu(umac->dbg_ptrs.error_info_addr);
 
-	if (!umac_error_event_table) {
-		mvm->support_umac_log = false;
-	} else if (umac_error_event_table >=
-		   mvm->trans->cfg->min_umac_error_event_table) {
-		mvm->support_umac_log = true;
-	} else {
-		IWL_ERR(mvm,
-			"Not valid error log pointer 0x%08X for %s uCode\n",
-			umac_error_event_table,
-			(mvm->fwrt.cur_fw_img == IWL_UCODE_INIT) ?
-			"Init" : "RT");
-		mvm->support_umac_log = false;
+	if (umac_error_table) {
+		if (umac_error_table >=
+		    mvm->trans->cfg->min_umac_error_event_table) {
+			iwl_fw_umac_set_alive_err_table(mvm->trans,
+							umac_error_table);
+		} else {
+			IWL_ERR(mvm,
+				"Not valid error log pointer 0x%08X for %s uCode\n",
+				umac_error_table,
+				(mvm->fwrt.cur_fw_img == IWL_UCODE_INIT) ?
+				"Init" : "RT");
+		}
 	}
 
-	if (mvm->support_umac_log)
-		iwl_fw_umac_set_alive_err_table(mvm->trans,
-						umac_error_event_table);
-
 	alive_data->scd_base_addr = le32_to_cpu(lmac1->dbg_ptrs.scd_base_ptr);
 	alive_data->valid = status == IWL_ALIVE_STATUS_OK;
 
@@ -310,7 +317,7 @@ static int iwl_mvm_load_ucode_wait_alive(struct iwl_mvm *mvm,
 	const struct fw_img *fw;
 	int ret;
 	enum iwl_ucode_type old_type = mvm->fwrt.cur_fw_img;
-	static const u16 alive_cmd[] = { MVM_ALIVE };
+	static const u16 alive_cmd[] = { UCODE_ALIVE_NTFY };
 	bool run_in_rfkill =
 		ucode_type == IWL_UCODE_INIT || iwl_mvm_has_unified_ucode(mvm);
 
@@ -590,7 +597,8 @@ static int iwl_send_phy_cfg_cmd(struct iwl_mvm *mvm)
 		mvm->fw->default_calib[ucode_type].flow_trigger;
 
 	cmd_ver = iwl_fw_lookup_cmd_ver(mvm->fw, IWL_ALWAYS_LONG_GROUP,
-					PHY_CONFIGURATION_CMD);
+					PHY_CONFIGURATION_CMD,
+					IWL_FW_CMD_VER_UNKNOWN);
 	if (cmd_ver == 3) {
 		iwl_mvm_phy_filter_init(mvm, &phy_filters);
 		memcpy(&phy_cfg_cmd.phy_specific_cfg, &phy_filters,
@@ -740,28 +748,42 @@ static int iwl_mvm_config_ltr(struct iwl_mvm *mvm)
 #ifdef CONFIG_ACPI
 int iwl_mvm_sar_select_profile(struct iwl_mvm *mvm, int prof_a, int prof_b)
 {
-	union {
-		struct iwl_dev_tx_power_cmd v5;
-		struct iwl_dev_tx_power_cmd_v4 v4;
-	} cmd = {
-		.v5.v3.set_mode = cpu_to_le32(IWL_TX_POWER_MODE_SET_CHAINS),
+	struct iwl_dev_tx_power_cmd cmd = {
+		.common.set_mode = cpu_to_le32(IWL_TX_POWER_MODE_SET_CHAINS),
 	};
+	__le16 *per_chain;
 	int ret;
 	u16 len = 0;
-
-	if (fw_has_api(&mvm->fw->ucode_capa,
-		       IWL_UCODE_TLV_API_REDUCE_TX_POWER))
+	u32 n_subbands;
+	u8 cmd_ver = iwl_fw_lookup_cmd_ver(mvm->fw, LONG_GROUP,
+					   REDUCE_TX_POWER_CMD,
+					   IWL_FW_CMD_VER_UNKNOWN);
+
+	if (cmd_ver == 6) {
+		len = sizeof(cmd.v6);
+		n_subbands = IWL_NUM_SUB_BANDS_V2;
+		per_chain = cmd.v6.per_chain[0][0];
+	} else if (fw_has_api(&mvm->fw->ucode_capa,
+			      IWL_UCODE_TLV_API_REDUCE_TX_POWER)) {
 		len = sizeof(cmd.v5);
-	else if (fw_has_capa(&mvm->fw->ucode_capa,
-			     IWL_UCODE_TLV_CAPA_TX_POWER_ACK))
-		len = sizeof(struct iwl_dev_tx_power_cmd_v4);
-	else
-		len = sizeof(cmd.v4.v3);
+		n_subbands = IWL_NUM_SUB_BANDS;
+		per_chain = cmd.v5.per_chain[0][0];
+	} else if (fw_has_capa(&mvm->fw->ucode_capa,
+			       IWL_UCODE_TLV_CAPA_TX_POWER_ACK)) {
+		len = sizeof(cmd.v4);
+		n_subbands = IWL_NUM_SUB_BANDS;
+		per_chain = cmd.v4.per_chain[0][0];
+	} else {
+		len = sizeof(cmd.v3);
+		n_subbands = IWL_NUM_SUB_BANDS;
+		per_chain = cmd.v3.per_chain[0][0];
+	}
 
+	/* all structs have the same common part, add it */
+	len += sizeof(cmd.common);
 
-	ret = iwl_sar_select_profile(&mvm->fwrt,
-				     cmd.v5.v3.per_chain_restriction,
-				     prof_a, prof_b);
+	ret = iwl_sar_select_profile(&mvm->fwrt, per_chain, ACPI_SAR_NUM_TABLES,
+				     n_subbands, prof_a, prof_b);
 
 	/* return on error or if the profile is disabled (positive number) */
 	if (ret)
@@ -773,21 +795,26 @@ int iwl_mvm_sar_select_profile(struct iwl_mvm *mvm, int prof_a, int prof_b)
 
 int iwl_mvm_get_sar_geo_profile(struct iwl_mvm *mvm)
 {
-	union geo_tx_power_profiles_cmd geo_tx_cmd;
+	union iwl_geo_tx_power_profiles_cmd geo_tx_cmd;
+	struct iwl_geo_tx_power_profiles_resp *resp;
 	u16 len;
 	int ret;
 	struct iwl_host_cmd cmd;
-
-	if (fw_has_api(&mvm->fwrt.fw->ucode_capa,
-		       IWL_UCODE_TLV_API_SAR_TABLE_VER)) {
-		geo_tx_cmd.geo_cmd.ops =
-			cpu_to_le32(IWL_PER_CHAIN_OFFSET_GET_CURRENT_TABLE);
-		len = sizeof(geo_tx_cmd.geo_cmd);
-	} else {
-		geo_tx_cmd.geo_cmd_v1.ops =
-			cpu_to_le32(IWL_PER_CHAIN_OFFSET_GET_CURRENT_TABLE);
-		len = sizeof(geo_tx_cmd.geo_cmd_v1);
-	}
+	u8 cmd_ver = iwl_fw_lookup_cmd_ver(mvm->fw, PHY_OPS_GROUP,
+					   GEO_TX_POWER_LIMIT,
+					   IWL_FW_CMD_VER_UNKNOWN);
+
+	/* the ops field is at the same spot for all versions, so set in v1 */
+	geo_tx_cmd.v1.ops =
+		cpu_to_le32(IWL_PER_CHAIN_OFFSET_GET_CURRENT_TABLE);
+
+	if (cmd_ver == 3)
+		len = sizeof(geo_tx_cmd.v3);
+	else if (fw_has_api(&mvm->fwrt.fw->ucode_capa,
+			    IWL_UCODE_TLV_API_SAR_TABLE_VER))
+		len = sizeof(geo_tx_cmd.v2);
+	else
+		len = sizeof(geo_tx_cmd.v1);
 
 	if (!iwl_sar_geo_support(&mvm->fwrt))
 		return -EOPNOTSUPP;
@@ -804,21 +831,30 @@ int iwl_mvm_get_sar_geo_profile(struct iwl_mvm *mvm)
 		IWL_ERR(mvm, "Failed to get geographic profile info %d\n", ret);
 		return ret;
 	}
-	ret = iwl_validate_sar_geo_profile(&mvm->fwrt, &cmd);
+
+	resp = (void *)cmd.resp_pkt->data;
+	ret = le32_to_cpu(resp->profile_idx);
+
+	if (WARN_ON(ret > ACPI_NUM_GEO_PROFILES))
+		ret = -EIO;
+
 	iwl_free_resp(&cmd);
 	return ret;
 }
 
 static int iwl_mvm_sar_geo_init(struct iwl_mvm *mvm)
 {
-	u16 cmd_wide_id =  WIDE_ID(PHY_OPS_GROUP, GEO_TX_POWER_LIMIT);
-	union geo_tx_power_profiles_cmd cmd;
+	union iwl_geo_tx_power_profiles_cmd cmd;
 	u16 len;
 	int ret;
+	u8 cmd_ver = iwl_fw_lookup_cmd_ver(mvm->fw, PHY_OPS_GROUP,
+					   GEO_TX_POWER_LIMIT,
+					   IWL_FW_CMD_VER_UNKNOWN);
 
-	cmd.geo_cmd.ops = cpu_to_le32(IWL_PER_CHAIN_OFFSET_SET_TABLES);
+	/* the table is also at the same position both in v1 and v2 */
+	ret = iwl_sar_geo_init(&mvm->fwrt, &cmd.v1.table[0][0],
+			       ACPI_WGDS_NUM_BANDS);
 
-	ret = iwl_sar_geo_init(&mvm->fwrt, cmd.geo_cmd.table);
 	/*
 	 * It is a valid scenario to not support SAR, or miss wgds table,
 	 * but in that case there is no need to send the command.
@@ -826,42 +862,75 @@ static int iwl_mvm_sar_geo_init(struct iwl_mvm *mvm)
 	if (ret)
 		return 0;
 
-	cmd.geo_cmd.table_revision = cpu_to_le32(mvm->fwrt.geo_rev);
+	/* the ops field is at the same spot for all versions, so set in v1 */
+	cmd.v1.ops = cpu_to_le32(IWL_PER_CHAIN_OFFSET_SET_TABLES);
 
-	if (!fw_has_api(&mvm->fwrt.fw->ucode_capa,
-			IWL_UCODE_TLV_API_SAR_TABLE_VER)) {
-		len = sizeof(struct iwl_geo_tx_power_profiles_cmd_v1);
+	if (cmd_ver == 3) {
+		len = sizeof(cmd.v3);
+		cmd.v3.table_revision = cpu_to_le32(mvm->fwrt.geo_rev);
+	} else if (fw_has_api(&mvm->fwrt.fw->ucode_capa,
+			      IWL_UCODE_TLV_API_SAR_TABLE_VER)) {
+		len = sizeof(cmd.v2);
+		cmd.v2.table_revision = cpu_to_le32(mvm->fwrt.geo_rev);
 	} else {
-		len =  sizeof(cmd.geo_cmd);
+		len = sizeof(cmd.v1);
 	}
 
-	return iwl_mvm_send_cmd_pdu(mvm, cmd_wide_id, 0, len, &cmd);
+	return iwl_mvm_send_cmd_pdu(mvm,
+				    WIDE_ID(PHY_OPS_GROUP, GEO_TX_POWER_LIMIT),
+				    0, len, &cmd);
 }
 
 static int iwl_mvm_get_ppag_table(struct iwl_mvm *mvm)
 {
 	union acpi_object *wifi_pkg, *data, *enabled;
-	int i, j, ret, tbl_rev;
+	union iwl_ppag_table_cmd ppag_table;
+	int i, j, ret, tbl_rev, num_sub_bands;
 	int idx = 2;
+	s8 *gain;
 
-	mvm->fwrt.ppag_table.enabled = cpu_to_le32(0);
+	/*
+	 * The 'enabled' field is the same in v1 and v2 so we can just
+	 * use v1 to access it.
+	 */
+	mvm->fwrt.ppag_table.v1.enabled = cpu_to_le32(0);
 	data = iwl_acpi_get_object(mvm->dev, ACPI_PPAG_METHOD);
 	if (IS_ERR(data))
 		return PTR_ERR(data);
 
+	/* try to read ppag table revision 1 */
 	wifi_pkg = iwl_acpi_get_wifi_pkg(mvm->dev, data,
-					 ACPI_PPAG_WIFI_DATA_SIZE, &tbl_rev);
-
-	if (IS_ERR(wifi_pkg)) {
-		ret = PTR_ERR(wifi_pkg);
-		goto out_free;
+					 ACPI_PPAG_WIFI_DATA_SIZE_V2, &tbl_rev);
+	if (!IS_ERR(wifi_pkg)) {
+		if (tbl_rev != 1) {
+			ret = -EINVAL;
+			goto out_free;
+		}
+		num_sub_bands = IWL_NUM_SUB_BANDS_V2;
+		gain = mvm->fwrt.ppag_table.v2.gain[0];
+		mvm->fwrt.ppag_ver = 2;
+		IWL_DEBUG_RADIO(mvm, "Reading PPAG table v2 (tbl_rev=1)\n");
+		goto read_table;
 	}
 
-	if (tbl_rev != 0) {
-		ret = -EINVAL;
-		goto out_free;
+	/* try to read ppag table revision 0 */
+	wifi_pkg = iwl_acpi_get_wifi_pkg(mvm->dev, data,
+					 ACPI_PPAG_WIFI_DATA_SIZE, &tbl_rev);
+	if (!IS_ERR(wifi_pkg)) {
+		if (tbl_rev != 0) {
+			ret = -EINVAL;
+			goto out_free;
+		}
+		num_sub_bands = IWL_NUM_SUB_BANDS;
+		gain = mvm->fwrt.ppag_table.v1.gain[0];
+		mvm->fwrt.ppag_ver = 1;
+		IWL_DEBUG_RADIO(mvm, "Reading PPAG table v1 (tbl_rev=0)\n");
+		goto read_table;
 	}
+	ret = PTR_ERR(wifi_pkg);
+	goto out_free;
 
+read_table:
 	enabled = &wifi_pkg->package.elements[1];
 	if (enabled->type != ACPI_TYPE_INTEGER ||
 	    (enabled->integer.value != 0 && enabled->integer.value != 1)) {
@@ -869,8 +938,8 @@ static int iwl_mvm_get_ppag_table(struct iwl_mvm *mvm)
 		goto out_free;
 	}
 
-	mvm->fwrt.ppag_table.enabled = cpu_to_le32(enabled->integer.value);
-	if (!mvm->fwrt.ppag_table.enabled) {
+	ppag_table.v1.enabled = cpu_to_le32(enabled->integer.value);
+	if (!ppag_table.v1.enabled) {
 		ret = 0;
 		goto out_free;
 	}
@@ -880,8 +949,8 @@ static int iwl_mvm_get_ppag_table(struct iwl_mvm *mvm)
 	 * first sub-band (j=0) corresponds to Low-Band (2.4GHz), and the
 	 * following sub-bands to High-Band (5GHz).
 	 */
-	for (i = 0; i < ACPI_PPAG_NUM_CHAINS; i++) {
-		for (j = 0; j < ACPI_PPAG_NUM_SUB_BANDS; j++) {
+	for (i = 0; i < IWL_NUM_CHAIN_LIMITS; i++) {
+		for (j = 0; j < num_sub_bands; j++) {
 			union acpi_object *ent;
 
 			ent = &wifi_pkg->package.elements[idx++];
@@ -890,11 +959,11 @@ static int iwl_mvm_get_ppag_table(struct iwl_mvm *mvm)
 			    (j == 0 && ent->integer.value < ACPI_PPAG_MIN_LB) ||
 			    (j != 0 && ent->integer.value > ACPI_PPAG_MAX_HB) ||
 			    (j != 0 && ent->integer.value < ACPI_PPAG_MIN_HB)) {
-				mvm->fwrt.ppag_table.enabled = cpu_to_le32(0);
+				ppag_table.v1.enabled = cpu_to_le32(0);
 				ret = -EINVAL;
 				goto out_free;
 			}
-			mvm->fwrt.ppag_table.gain[i][j] = ent->integer.value;
+			gain[i * num_sub_bands + j] = ent->integer.value;
 		}
 	}
 	ret = 0;
@@ -905,34 +974,56 @@ out_free:
 
 int iwl_mvm_ppag_send_cmd(struct iwl_mvm *mvm)
 {
-	int i, j, ret;
+	u8 cmd_ver;
+	int i, j, ret, num_sub_bands, cmd_size;
+	union iwl_ppag_table_cmd ppag_table;
+	s8 *gain;
 
 	if (!fw_has_capa(&mvm->fw->ucode_capa, IWL_UCODE_TLV_CAPA_SET_PPAG)) {
 		IWL_DEBUG_RADIO(mvm,
 				"PPAG capability not supported by FW, command not sent.\n");
 		return 0;
 	}
-
-	if (!mvm->fwrt.ppag_table.enabled) {
-		IWL_DEBUG_RADIO(mvm,
-				"PPAG not enabled, command not sent.\n");
+	if (!mvm->fwrt.ppag_table.v1.enabled) {
+		IWL_DEBUG_RADIO(mvm, "PPAG not enabled, command not sent.\n");
 		return 0;
 	}
 
-	IWL_DEBUG_RADIO(mvm, "Sending PER_PLATFORM_ANT_GAIN_CMD\n");
+	cmd_ver = iwl_fw_lookup_cmd_ver(mvm->fw, PHY_OPS_GROUP,
+					PER_PLATFORM_ANT_GAIN_CMD,
+					IWL_FW_CMD_VER_UNKNOWN);
+	if (cmd_ver == 1) {
+		num_sub_bands = IWL_NUM_SUB_BANDS;
+		gain = mvm->fwrt.ppag_table.v1.gain[0];
+		cmd_size = sizeof(ppag_table.v1);
+		if (mvm->fwrt.ppag_ver == 2) {
+			IWL_DEBUG_RADIO(mvm,
+					"PPAG table is v2 but FW supports v1, sending truncated table\n");
+		}
+	} else if (cmd_ver == 2) {
+		num_sub_bands = IWL_NUM_SUB_BANDS_V2;
+		gain = mvm->fwrt.ppag_table.v2.gain[0];
+		cmd_size = sizeof(ppag_table.v2);
+		if (mvm->fwrt.ppag_ver == 1) {
+			IWL_DEBUG_RADIO(mvm,
+					"PPAG table is v1 but FW supports v2, sending padded table\n");
+		}
+	} else {
+		IWL_DEBUG_RADIO(mvm, "Unsupported PPAG command version\n");
+		return 0;
+	}
 
-	for (i = 0; i < ACPI_PPAG_NUM_CHAINS; i++) {
-		for (j = 0; j < ACPI_PPAG_NUM_SUB_BANDS; j++) {
+	for (i = 0; i < IWL_NUM_CHAIN_LIMITS; i++) {
+		for (j = 0; j < num_sub_bands; j++) {
 			IWL_DEBUG_RADIO(mvm,
 					"PPAG table: chain[%d] band[%d]: gain = %d\n",
-					i, j, mvm->fwrt.ppag_table.gain[i][j]);
+					i, j, gain[i * num_sub_bands + j]);
 		}
 	}
-
+	IWL_DEBUG_RADIO(mvm, "Sending PER_PLATFORM_ANT_GAIN_CMD\n");
 	ret = iwl_mvm_send_cmd_pdu(mvm, WIDE_ID(PHY_OPS_GROUP,
 						PER_PLATFORM_ANT_GAIN_CMD),
-				   0, sizeof(mvm->fwrt.ppag_table),
-				   &mvm->fwrt.ppag_table);
+				   0, cmd_size, &ppag_table);
 	if (ret < 0)
 		IWL_ERR(mvm, "failed to send PER_PLATFORM_ANT_GAIN_CMD (%d)\n",
 			ret);
@@ -989,41 +1080,90 @@ static void iwl_mvm_tas_init(struct iwl_mvm *mvm)
 		IWL_DEBUG_RADIO(mvm, "failed to send TAS_CONFIG (%d)\n", ret);
 }
 
-static bool iwl_mvm_eval_dsm_indonesia_5g2(struct iwl_mvm *mvm)
+static u8 iwl_mvm_eval_dsm_indonesia_5g2(struct iwl_mvm *mvm)
 {
 	int ret = iwl_acpi_get_dsm_u8((&mvm->fwrt)->dev, 0,
 				      DSM_FUNC_ENABLE_INDONESIA_5G2);
 
-	IWL_DEBUG_RADIO(mvm,
-			"Evaluated DSM function ENABLE_INDONESIA_5G2, ret=%d\n",
-			ret);
+	if (ret < 0)
+		IWL_DEBUG_RADIO(mvm,
+				"Failed to evaluate DSM function ENABLE_INDONESIA_5G2, ret=%d\n",
+				ret);
+
+	else if (ret >= DSM_VALUE_INDONESIA_MAX)
+		IWL_DEBUG_RADIO(mvm,
+				"DSM function ENABLE_INDONESIA_5G2 return invalid value, ret=%d\n",
+				ret);
+
+	else if (ret == DSM_VALUE_INDONESIA_ENABLE) {
+		IWL_DEBUG_RADIO(mvm,
+				"Evaluated DSM function ENABLE_INDONESIA_5G2: Enabling 5g2\n");
+		return DSM_VALUE_INDONESIA_ENABLE;
+	}
+	/* default behaviour is disabled */
+	return DSM_VALUE_INDONESIA_DISABLE;
+}
+
+static u8 iwl_mvm_eval_dsm_disable_srd(struct iwl_mvm *mvm)
+{
+	int ret = iwl_acpi_get_dsm_u8((&mvm->fwrt)->dev, 0,
+				      DSM_FUNC_DISABLE_SRD);
+
+	if (ret < 0)
+		IWL_DEBUG_RADIO(mvm,
+				"Failed to evaluate DSM function DISABLE_SRD, ret=%d\n",
+				ret);
+
+	else if (ret >= DSM_VALUE_SRD_MAX)
+		IWL_DEBUG_RADIO(mvm,
+				"DSM function DISABLE_SRD return invalid value, ret=%d\n",
+				ret);
+
+	else if (ret == DSM_VALUE_SRD_PASSIVE) {
+		IWL_DEBUG_RADIO(mvm,
+				"Evaluated DSM function DISABLE_SRD: setting SRD to passive\n");
+		return DSM_VALUE_SRD_PASSIVE;
 
-	return ret == 1;
+	} else if (ret == DSM_VALUE_SRD_DISABLE) {
+		IWL_DEBUG_RADIO(mvm,
+				"Evaluated DSM function DISABLE_SRD: disabling SRD\n");
+		return DSM_VALUE_SRD_DISABLE;
+	}
+	/* default behaviour is active */
+	return DSM_VALUE_SRD_ACTIVE;
 }
 
 static void iwl_mvm_lari_cfg(struct iwl_mvm *mvm)
 {
-	int ret;
+	u8 ret;
+	int cmd_ret;
 	struct iwl_lari_config_change_cmd cmd = {};
 
-	if (iwl_mvm_eval_dsm_indonesia_5g2(mvm))
+	if (iwl_mvm_eval_dsm_indonesia_5g2(mvm) == DSM_VALUE_INDONESIA_ENABLE)
 		cmd.config_bitmap |=
 			cpu_to_le32(LARI_CONFIG_ENABLE_5G2_IN_INDONESIA_MSK);
 
+	ret = iwl_mvm_eval_dsm_disable_srd(mvm);
+	if (ret == DSM_VALUE_SRD_PASSIVE)
+		cmd.config_bitmap |=
+			cpu_to_le32(LARI_CONFIG_CHANGE_ETSI_TO_PASSIVE_MSK);
+
+	else if (ret == DSM_VALUE_SRD_DISABLE)
+		cmd.config_bitmap |=
+			cpu_to_le32(LARI_CONFIG_CHANGE_ETSI_TO_DISABLED_MSK);
+
 	/* apply more config masks here */
 
 	if (cmd.config_bitmap) {
-		IWL_DEBUG_RADIO(mvm,
-				"sending LARI_CONFIG_CHANGE, config_bitmap=0x%x\n",
-				le32_to_cpu(cmd.config_bitmap));
-		ret = iwl_mvm_send_cmd_pdu(mvm,
-					   WIDE_ID(REGULATORY_AND_NVM_GROUP,
-						   LARI_CONFIG_CHANGE),
-					   0, sizeof(cmd), &cmd);
-		if (ret < 0)
+		IWL_DEBUG_RADIO(mvm, "sending LARI_CONFIG_CHANGE\n");
+		cmd_ret = iwl_mvm_send_cmd_pdu(mvm,
+					       WIDE_ID(REGULATORY_AND_NVM_GROUP,
+						       LARI_CONFIG_CHANGE),
+					       0, sizeof(cmd), &cmd);
+		if (cmd_ret < 0)
 			IWL_DEBUG_RADIO(mvm,
 					"Failed to send LARI_CONFIG_CHANGE (%d)\n",
-					ret);
+					cmd_ret);
 	}
 }
 #else /* CONFIG_ACPI */
@@ -1383,6 +1523,8 @@ int iwl_mvm_up(struct iwl_mvm *mvm)
 	iwl_mvm_tas_init(mvm);
 	iwl_mvm_leds_sync(mvm);
 
+	iwl_mvm_ftm_initiator_smooth_config(mvm);
+
 	IWL_DEBUG_INFO(mvm, "RT uCode started.\n");
 	return 0;
  error:
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
index 81bc05d70267..8c98def8b7f7 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
@@ -5,10 +5,9 @@
  *
  * GPL LICENSE SUMMARY
  *
- * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH
  * Copyright(c) 2015 - 2017 Intel Deutschland GmbH
- * Copyright(c) 2018 - 2019 Intel Corporation
+ * Copyright(c) 2012 - 2014, 2018 - 2020 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -28,10 +27,9 @@
  *
  * BSD LICENSE
  *
- * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH
  * Copyright(c) 2015 - 2017 Intel Deutschland GmbH
- * Copyright(c) 2018 - 2019 Intel Corporation
+ * Copyright(c) 2012 - 2014, 2018 - 2020 Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -704,8 +702,12 @@ static int iwl_mvm_mac_ctxt_cmd_sta(struct iwl_mvm *mvm,
 
 	if (vif->bss_conf.he_support && !iwlwifi_mod_params.disable_11ax) {
 		cmd.filter_flags |= cpu_to_le32(MAC_FILTER_IN_11AX);
-		if (vif->bss_conf.twt_requester && IWL_MVM_USE_TWT)
+		if (vif->bss_conf.twt_requester && IWL_MVM_USE_TWT) {
 			ctxt_sta->data_policy |= cpu_to_le32(TWT_SUPPORTED);
+			if (vif->bss_conf.twt_protected)
+				ctxt_sta->data_policy |=
+					cpu_to_le32(PROTECTED_TWT_SUPPORTED);
+		}
 	}
 
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index 9374c85c5caf..5c9bde99ce19 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -234,6 +234,7 @@ struct ieee80211_regdomain *iwl_mvm_get_regdomain(struct wiphy *wiphy,
 	struct ieee80211_hw *hw = wiphy_to_ieee80211_hw(wiphy);
 	struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
 	struct iwl_mcc_update_resp *resp;
+	u8 resp_ver;
 
 	IWL_DEBUG_LAR(mvm, "Getting regdomain data for %s from FW\n", alpha2);
 
@@ -252,13 +253,16 @@ struct ieee80211_regdomain *iwl_mvm_get_regdomain(struct wiphy *wiphy,
 		*changed = (status == MCC_RESP_NEW_CHAN_PROFILE ||
 			    status == MCC_RESP_ILLEGAL);
 	}
+	resp_ver = iwl_fw_lookup_notif_ver(mvm->fw, IWL_ALWAYS_LONG_GROUP,
+					   MCC_UPDATE_CMD, 0);
+	IWL_DEBUG_LAR(mvm, "MCC update response version: %d\n", resp_ver);
 
 	regd = iwl_parse_nvm_mcc_info(mvm->trans->dev, mvm->cfg,
 				      __le32_to_cpu(resp->n_channels),
 				      resp->channels,
 				      __le16_to_cpu(resp->mcc),
 				      __le16_to_cpu(resp->geo_info),
-				      __le16_to_cpu(resp->cap));
+				      __le16_to_cpu(resp->cap), resp_ver);
 	/* Store the return source id */
 	src_id = resp->source_id;
 	kfree(resp);
@@ -662,6 +666,11 @@ int iwl_mvm_mac_setup_register(struct iwl_mvm *mvm)
 			IWL_UCODE_TLV_CAPA_WFA_TPC_REP_IE_SUPPORT))
 		hw->wiphy->features |= NL80211_FEATURE_WFA_TPC_IE_IN_PROBES;
 
+	if (iwl_fw_lookup_cmd_ver(mvm->fw, IWL_ALWAYS_LONG_GROUP,
+				  WOWLAN_KEK_KCK_MATERIAL,
+				  IWL_FW_CMD_VER_UNKNOWN) == 3)
+		hw->wiphy->flags |= WIPHY_FLAG_SUPPORTS_EXT_KEK_KCK;
+
 	if (fw_has_api(&mvm->fw->ucode_capa,
 		       IWL_UCODE_TLV_API_SCAN_TSF_REPORT)) {
 		wiphy_ext_feature_set(hw->wiphy,
@@ -753,6 +762,10 @@ int iwl_mvm_mac_setup_register(struct iwl_mvm *mvm)
 		wiphy_ext_feature_set(hw->wiphy,
 				      NL80211_EXT_FEATURE_MU_MIMO_AIR_SNIFFER);
 
+	if (fw_has_capa(&mvm->fw->ucode_capa, IWL_UCODE_TLV_CAPA_PROTECTED_TWT))
+		wiphy_ext_feature_set(hw->wiphy,
+				      NL80211_EXT_FEATURE_PROTECTED_TWT);
+
 	hw->wiphy->available_antennas_tx = iwl_mvm_get_valid_tx_ant(mvm);
 	hw->wiphy->available_antennas_rx = iwl_mvm_get_valid_rx_ant(mvm);
 
@@ -1203,6 +1216,8 @@ void __iwl_mvm_mac_stop(struct iwl_mvm *mvm)
 {
 	lockdep_assert_held(&mvm->mutex);
 
+	iwl_mvm_ftm_initiator_smooth_stop(mvm);
+
 	/* firmware counters are obviously reset now, but we shouldn't
 	 * partially track so also clear the fw_reset_accu counters.
 	 */
@@ -1300,27 +1315,32 @@ static int iwl_mvm_set_tx_power(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 				s16 tx_power)
 {
 	int len;
-	union {
-		struct iwl_dev_tx_power_cmd v5;
-		struct iwl_dev_tx_power_cmd_v4 v4;
-	} cmd = {
-		.v5.v3.set_mode = cpu_to_le32(IWL_TX_POWER_MODE_SET_MAC),
-		.v5.v3.mac_context_id =
+	struct iwl_dev_tx_power_cmd cmd = {
+		.common.set_mode = cpu_to_le32(IWL_TX_POWER_MODE_SET_MAC),
+		.common.mac_context_id =
 			cpu_to_le32(iwl_mvm_vif_from_mac80211(vif)->id),
-		.v5.v3.pwr_restriction = cpu_to_le16(8 * tx_power),
+		.common.pwr_restriction = cpu_to_le16(8 * tx_power),
 	};
+	u8 cmd_ver = iwl_fw_lookup_cmd_ver(mvm->fw, LONG_GROUP,
+					   REDUCE_TX_POWER_CMD,
+					   IWL_FW_CMD_VER_UNKNOWN);
 
 	if (tx_power == IWL_DEFAULT_MAX_TX_POWER)
-		cmd.v5.v3.pwr_restriction = cpu_to_le16(IWL_DEV_MAX_TX_POWER);
+		cmd.common.pwr_restriction = cpu_to_le16(IWL_DEV_MAX_TX_POWER);
 
-	if (fw_has_api(&mvm->fw->ucode_capa,
-		       IWL_UCODE_TLV_API_REDUCE_TX_POWER))
+	if (cmd_ver == 6)
+		len = sizeof(cmd.v6);
+	else if (fw_has_api(&mvm->fw->ucode_capa,
+			    IWL_UCODE_TLV_API_REDUCE_TX_POWER))
 		len = sizeof(cmd.v5);
 	else if (fw_has_capa(&mvm->fw->ucode_capa,
 			     IWL_UCODE_TLV_CAPA_TX_POWER_ACK))
 		len = sizeof(cmd.v4);
 	else
-		len = sizeof(cmd.v4.v3);
+		len = sizeof(cmd.v3);
+
+	/* all structs have the same common part, add it */
+	len += sizeof(cmd.common);
 
 	return iwl_mvm_send_cmd_pdu(mvm, REDUCE_TX_POWER_CMD, 0, len, &cmd);
 }
@@ -2629,6 +2649,8 @@ static void iwl_mvm_stop_ap_ibss(struct ieee80211_hw *hw,
 
 	iwl_mvm_update_quotas(mvm, false, NULL);
 
+	iwl_mvm_ftm_responder_clear(mvm, vif);
+
 	/*
 	 * This is not very nice, but the simplest:
 	 * For older FWs removing the mcast sta before the bcast station may
@@ -3428,15 +3450,16 @@ static int __iwl_mvm_mac_set_key(struct ieee80211_hw *hw,
 			 */
 			if (key->cipher == WLAN_CIPHER_SUITE_AES_CMAC ||
 			    key->cipher == WLAN_CIPHER_SUITE_BIP_GMAC_128 ||
-			    key->cipher == WLAN_CIPHER_SUITE_BIP_GMAC_256)
+			    key->cipher == WLAN_CIPHER_SUITE_BIP_GMAC_256) {
 				ret = -EOPNOTSUPP;
-			else
-				ret = 0;
+				break;
+			}
 
 			if (key->cipher != WLAN_CIPHER_SUITE_GCMP &&
 			    key->cipher != WLAN_CIPHER_SUITE_GCMP_256 &&
 			    !iwl_mvm_has_new_tx_api(mvm)) {
 				key->hw_key_idx = STA_KEY_IDX_INVALID;
+				ret = 0;
 				break;
 			}
 
@@ -3452,6 +3475,8 @@ static int __iwl_mvm_mac_set_key(struct ieee80211_hw *hw,
 
 				if (i >= ARRAY_SIZE(mvmvif->ap_early_keys))
 					ret = -ENOSPC;
+				else
+					ret = 0;
 
 				break;
 			}
@@ -3693,9 +3718,12 @@ static int iwl_mvm_send_aux_roc_cmd(struct iwl_mvm *mvm,
 	tail->apply_time_max_delay = cpu_to_le32(delay);
 
 	IWL_DEBUG_TE(mvm,
-		     "ROC: Requesting to remain on channel %u for %ums (requested = %ums, max_delay = %ums, dtim_interval = %ums)\n",
-		     channel->hw_value, req_dur, duration, delay,
-		     dtim_interval);
+		     "ROC: Requesting to remain on channel %u for %ums\n",
+		     channel->hw_value, req_dur);
+	IWL_DEBUG_TE(mvm,
+		     "\t(requested = %ums, max_delay = %ums, dtim_interval = %ums)\n",
+		     duration, delay, dtim_interval);
+
 	/* Set the node address */
 	memcpy(tail->node_addr, vif->addr, ETH_ALEN);
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
index e2f7f6ec711e..9187f8a1126d 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
@@ -184,11 +184,6 @@ enum iwl_power_scheme {
 	IWL_POWER_SCHEME_LP
 };
 
-union geo_tx_power_profiles_cmd {
-	struct iwl_geo_tx_power_profiles_cmd geo_cmd;
-	struct iwl_geo_tx_power_profiles_cmd_v1 geo_cmd_v1;
-};
-
 #define IWL_CONN_MAX_LISTEN_INTERVAL	10
 #define IWL_UAPSD_MAX_SP		IEEE80211_WMM_IE_STA_QOSINFO_SP_ALL
 
@@ -421,7 +416,11 @@ struct iwl_mvm_vif {
 #ifdef CONFIG_PM
 	/* WoWLAN GTK rekey data */
 	struct {
-		u8 kck[NL80211_KCK_LEN], kek[NL80211_KEK_LEN];
+		u8 kck[NL80211_KCK_EXT_LEN];
+		u8 kek[NL80211_KEK_EXT_LEN];
+		size_t kek_len;
+		size_t kck_len;
+		u32 akm;
 		__le64 replay_ctr;
 		bool valid;
 	} rekey_data;
@@ -852,7 +851,6 @@ struct iwl_mvm {
 
 	bool hw_registered;
 	bool rfkill_safe_init_done;
-	bool support_umac_log;
 
 	u32 ampdu_ref;
 	bool ampdu_toggle;
@@ -1113,10 +1111,17 @@ struct iwl_mvm {
 		struct wireless_dev *req_wdev;
 		struct list_head loc_list;
 		int responses[IWL_MVM_TOF_MAX_APS];
+		struct {
+			struct list_head resp;
+		} smooth;
+		struct list_head pasn_list;
 	} ftm_initiator;
 
+	struct list_head resp_pasn_list;
+
 	struct {
 		u8 d0i3_resp;
+		u8 range_resp;
 	} cmd_ver;
 
 	struct ieee80211_vif *nan_vif;
@@ -1996,6 +2001,14 @@ void iwl_mvm_ftm_restart_responder(struct iwl_mvm *mvm,
 				   struct ieee80211_vif *vif);
 void iwl_mvm_ftm_responder_stats(struct iwl_mvm *mvm,
 				 struct iwl_rx_cmd_buffer *rxb);
+int iwl_mvm_ftm_resp_remove_pasn_sta(struct iwl_mvm *mvm,
+				     struct ieee80211_vif *vif, u8 *addr);
+int iwl_mvm_ftm_respoder_add_pasn_sta(struct iwl_mvm *mvm,
+				      struct ieee80211_vif *vif,
+				      u8 *addr, u32 cipher, u8 *tk, u32 tk_len,
+				      u8 *hltk, u32 hltk_len);
+void iwl_mvm_ftm_responder_clear(struct iwl_mvm *mvm,
+				 struct ieee80211_vif *vif);
 
 /* FTM initiator */
 void iwl_mvm_ftm_restart(struct iwl_mvm *mvm);
@@ -2006,6 +2019,12 @@ void iwl_mvm_ftm_lc_notif(struct iwl_mvm *mvm,
 int iwl_mvm_ftm_start(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 		      struct cfg80211_pmsr_request *request);
 void iwl_mvm_ftm_abort(struct iwl_mvm *mvm, struct cfg80211_pmsr_request *req);
+void iwl_mvm_ftm_initiator_smooth_config(struct iwl_mvm *mvm);
+void iwl_mvm_ftm_initiator_smooth_stop(struct iwl_mvm *mvm);
+int iwl_mvm_ftm_add_pasn_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
+			     u8 *addr, u32 cipher, u8 *tk, u32 tk_len,
+			     u8 *hltk, u32 hltk_len);
+void iwl_mvm_ftm_remove_pasn_sta(struct iwl_mvm *mvm, u8 *addr);
 
 /* TDLS */
 
@@ -2146,8 +2165,24 @@ iwl_mvm_set_chan_info_chandef(struct iwl_mvm *mvm,
 static inline int iwl_umac_scan_get_max_profiles(const struct iwl_fw *fw)
 {
 	u8 ver = iwl_fw_lookup_cmd_ver(fw, IWL_ALWAYS_LONG_GROUP,
-				       SCAN_OFFLOAD_UPDATE_PROFILES_CMD);
+				       SCAN_OFFLOAD_UPDATE_PROFILES_CMD,
+				       IWL_FW_CMD_VER_UNKNOWN);
 	return (ver == IWL_FW_CMD_VER_UNKNOWN || ver < 3) ?
 		IWL_SCAN_MAX_PROFILES : IWL_SCAN_MAX_PROFILES_V2;
 }
+
+static inline
+enum iwl_location_cipher iwl_mvm_cipher_to_location_cipher(u32 cipher)
+{
+	switch (cipher) {
+	case WLAN_CIPHER_SUITE_CCMP:
+		return IWL_LOCATION_CIPHER_CCMP_128;
+	case WLAN_CIPHER_SUITE_GCMP:
+		return IWL_LOCATION_CIPHER_GCMP_128;
+	case WLAN_CIPHER_SUITE_GCMP_256:
+		return IWL_LOCATION_CIPHER_GCMP_256;
+	default:
+		return IWL_LOCATION_CIPHER_INVALID;
+	}
+}
 #endif /* __IWL_MVM_H__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
index d095ff847be9..b86d62eff284 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
@@ -133,6 +133,7 @@ module_exit(iwl_mvm_exit);
 static void iwl_mvm_nic_config(struct iwl_op_mode *op_mode)
 {
 	struct iwl_mvm *mvm = IWL_OP_MODE_GET_MVM(op_mode);
+	struct iwl_trans_debug *dbg = &mvm->trans->dbg;
 	u8 radio_cfg_type, radio_cfg_step, radio_cfg_dash;
 	u32 reg_val = 0;
 	u32 phy_config = iwl_mvm_get_phy_config(mvm);
@@ -169,7 +170,10 @@ static void iwl_mvm_nic_config(struct iwl_op_mode *op_mode)
 	if (mvm->trans->trans_cfg->device_family < IWL_DEVICE_FAMILY_8000)
 		reg_val |= CSR_HW_IF_CONFIG_REG_BIT_RADIO_SI;
 
-	if (iwl_fw_dbg_is_d3_debug_enabled(&mvm->fwrt))
+	if (iwl_fw_dbg_is_d3_debug_enabled(&mvm->fwrt) ||
+	    (iwl_trans_dbg_ini_valid(mvm->trans) &&
+	     dbg->fw_mon_cfg[IWL_FW_INI_ALLOCATION_ID_INTERNAL].buf_location)
+	    )
 		reg_val |= CSR_HW_IF_CONFIG_REG_D3_DEBUG;
 
 	iwl_trans_set_bits_mask(mvm->trans, CSR_HW_IF_CONFIG_REG,
@@ -319,7 +323,7 @@ static const struct iwl_rx_handlers iwl_mvm_rx_handlers[] = {
  * Access is done through binary search
  */
 static const struct iwl_hcmd_names iwl_mvm_legacy_names[] = {
-	HCMD_NAME(MVM_ALIVE),
+	HCMD_NAME(UCODE_ALIVE_NTFY),
 	HCMD_NAME(REPLY_ERROR),
 	HCMD_NAME(ECHO_CMD),
 	HCMD_NAME(INIT_COMPLETE_NOTIF),
@@ -695,6 +699,8 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 	INIT_LIST_HEAD(&mvm->async_handlers_list);
 	spin_lock_init(&mvm->time_event_lock);
 	INIT_LIST_HEAD(&mvm->ftm_initiator.loc_list);
+	INIT_LIST_HEAD(&mvm->ftm_initiator.pasn_list);
+	INIT_LIST_HEAD(&mvm->resp_pasn_list);
 
 	INIT_WORK(&mvm->async_handlers_wk, iwl_mvm_async_handlers_wk);
 	INIT_WORK(&mvm->roc_done_wk, iwl_mvm_roc_done_wk);
@@ -724,6 +730,13 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 	if (WARN_ON_ONCE(mvm->cmd_ver.d0i3_resp > 1))
 		goto out_free;
 
+	mvm->cmd_ver.range_resp =
+		iwl_fw_lookup_notif_ver(mvm->fw, LOCATION_GROUP,
+					TOF_RANGE_RESPONSE_NOTIF, 5);
+	/* we only support up to version 8 */
+	if (WARN_ON_ONCE(mvm->cmd_ver.range_resp > 8))
+		goto out_free;
+
 	/*
 	 * Populate the state variables that the transport layer needs
 	 * to know about.
@@ -756,7 +769,6 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 		trans_cfg.rx_buf_size = rb_size_default;
 	}
 
-	trans->wide_cmd_header = true;
 	trans_cfg.bc_table_dword =
 		mvm->trans->trans_cfg->device_family < IWL_DEVICE_FAMILY_AX210;
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/phy-ctxt.c b/drivers/net/wireless/intel/iwlwifi/mvm/phy-ctxt.c
index 0243dbe8ac49..a5da4106ba5a 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/phy-ctxt.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/phy-ctxt.c
@@ -7,8 +7,8 @@
  *
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH
- * Copyright(c) 2017           Intel Deutschland GmbH
- * Copyright(c) 2018           Intel Corporation
+ * Copyright(c) 2017        Intel Deutschland GmbH
+ * Copyright(c) 2018 - 2020 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -30,7 +30,7 @@
  *
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH
- * Copyright(c) 2018           Intel Corporation
+ * Copyright(c) 2018 - 2020 Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -125,30 +125,19 @@ u8 iwl_mvm_get_ctrl_pos(struct cfg80211_chan_def *chandef)
  */
 static void iwl_mvm_phy_ctxt_cmd_hdr(struct iwl_mvm_phy_ctxt *ctxt,
 				     struct iwl_phy_context_cmd *cmd,
-				     u32 action, u32 apply_time)
+				     u32 action)
 {
-	memset(cmd, 0, sizeof(struct iwl_phy_context_cmd));
-
 	cmd->id_and_color = cpu_to_le32(FW_CMD_ID_AND_COLOR(ctxt->id,
 							    ctxt->color));
 	cmd->action = cpu_to_le32(action);
-	cmd->apply_time = cpu_to_le32(apply_time);
 }
 
-/*
- * Add the phy configuration to the PHY context command
- */
-static void iwl_mvm_phy_ctxt_cmd_data(struct iwl_mvm *mvm,
-				      struct iwl_phy_context_cmd *cmd,
-				      struct cfg80211_chan_def *chandef,
-				      u8 chains_static, u8 chains_dynamic)
+static void iwl_mvm_phy_ctxt_set_rxchain(struct iwl_mvm *mvm,
+					 __le32 *rxchain_info,
+					 u8 chains_static,
+					 u8 chains_dynamic)
 {
 	u8 active_cnt, idle_cnt;
-	struct iwl_phy_context_cmd_tail *tail =
-		iwl_mvm_chan_info_cmd_tail(mvm, &cmd->ci);
-
-	/* Set the channel info data */
-	iwl_mvm_set_chan_info_chandef(mvm, &cmd->ci, chandef);
 
 	/* Set rx the chains */
 	idle_cnt = chains_static;
@@ -166,20 +155,59 @@ static void iwl_mvm_phy_ctxt_cmd_data(struct iwl_mvm *mvm,
 		active_cnt = 2;
 	}
 
-	tail->rxchain_info = cpu_to_le32(iwl_mvm_get_valid_rx_ant(mvm) <<
+	*rxchain_info = cpu_to_le32(iwl_mvm_get_valid_rx_ant(mvm) <<
 					PHY_RX_CHAIN_VALID_POS);
-	tail->rxchain_info |= cpu_to_le32(idle_cnt << PHY_RX_CHAIN_CNT_POS);
-	tail->rxchain_info |= cpu_to_le32(active_cnt <<
+	*rxchain_info |= cpu_to_le32(idle_cnt << PHY_RX_CHAIN_CNT_POS);
+	*rxchain_info |= cpu_to_le32(active_cnt <<
 					 PHY_RX_CHAIN_MIMO_CNT_POS);
 #ifdef CONFIG_IWLWIFI_DEBUGFS
 	if (unlikely(mvm->dbgfs_rx_phyinfo))
-		tail->rxchain_info = cpu_to_le32(mvm->dbgfs_rx_phyinfo);
+		*rxchain_info = cpu_to_le32(mvm->dbgfs_rx_phyinfo);
 #endif
+}
+
+/*
+ * Add the phy configuration to the PHY context command
+ */
+static void iwl_mvm_phy_ctxt_cmd_data_v1(struct iwl_mvm *mvm,
+					 struct iwl_phy_context_cmd_v1 *cmd,
+					 struct cfg80211_chan_def *chandef,
+					 u8 chains_static, u8 chains_dynamic)
+{
+	struct iwl_phy_context_cmd_tail *tail =
+		iwl_mvm_chan_info_cmd_tail(mvm, &cmd->ci);
+
+	/* Set the channel info data */
+	iwl_mvm_set_chan_info_chandef(mvm, &cmd->ci, chandef);
+
+	iwl_mvm_phy_ctxt_set_rxchain(mvm, &tail->rxchain_info,
+				     chains_static, chains_dynamic);
 
 	tail->txchain_info = cpu_to_le32(iwl_mvm_get_valid_tx_ant(mvm));
 }
 
 /*
+ * Add the phy configuration to the PHY context command
+ */
+static void iwl_mvm_phy_ctxt_cmd_data(struct iwl_mvm *mvm,
+				      struct iwl_phy_context_cmd *cmd,
+				      struct cfg80211_chan_def *chandef,
+				      u8 chains_static, u8 chains_dynamic)
+{
+	if (chandef->chan->band == NL80211_BAND_2GHZ ||
+	    !iwl_mvm_is_cdb_supported(mvm))
+		cmd->lmac_id = cpu_to_le32(IWL_LMAC_24G_INDEX);
+	else
+		cmd->lmac_id = cpu_to_le32(IWL_LMAC_5G_INDEX);
+
+	/* Set the channel info data */
+	iwl_mvm_set_chan_info_chandef(mvm, &cmd->ci, chandef);
+
+	iwl_mvm_phy_ctxt_set_rxchain(mvm, &cmd->rxchain_info,
+				     chains_static, chains_dynamic);
+}
+
+/*
  * Send a command to apply the current phy configuration. The command is send
  * only if something in the configuration changed: in case that this is the
  * first time that the phy configuration is applied or in case that the phy
@@ -189,20 +217,46 @@ static int iwl_mvm_phy_ctxt_apply(struct iwl_mvm *mvm,
 				  struct iwl_mvm_phy_ctxt *ctxt,
 				  struct cfg80211_chan_def *chandef,
 				  u8 chains_static, u8 chains_dynamic,
-				  u32 action, u32 apply_time)
+				  u32 action)
 {
-	struct iwl_phy_context_cmd cmd;
 	int ret;
-	u16 len = sizeof(cmd) - iwl_mvm_chan_info_padding(mvm);
-
-	/* Set the command header fields */
-	iwl_mvm_phy_ctxt_cmd_hdr(ctxt, &cmd, action, apply_time);
+	int ver = iwl_fw_lookup_cmd_ver(mvm->fw, IWL_ALWAYS_LONG_GROUP,
+					PHY_CONTEXT_CMD, 1);
+
+	if (ver == 3) {
+		struct iwl_phy_context_cmd cmd = {};
+
+		/* Set the command header fields */
+		iwl_mvm_phy_ctxt_cmd_hdr(ctxt, &cmd, action);
+
+		/* Set the command data */
+		iwl_mvm_phy_ctxt_cmd_data(mvm, &cmd, chandef,
+					  chains_static,
+					  chains_dynamic);
+
+		ret = iwl_mvm_send_cmd_pdu(mvm, PHY_CONTEXT_CMD,
+					   0, sizeof(cmd), &cmd);
+	} else if (ver < 3) {
+		struct iwl_phy_context_cmd_v1 cmd = {};
+		u16 len = sizeof(cmd) - iwl_mvm_chan_info_padding(mvm);
+
+		/* Set the command header fields */
+		iwl_mvm_phy_ctxt_cmd_hdr(ctxt,
+					 (struct iwl_phy_context_cmd *)&cmd,
+					 action);
+
+		/* Set the command data */
+		iwl_mvm_phy_ctxt_cmd_data_v1(mvm, &cmd, chandef,
+					     chains_static,
+					     chains_dynamic);
+		ret = iwl_mvm_send_cmd_pdu(mvm, PHY_CONTEXT_CMD,
+					   0, len, &cmd);
+	} else {
+		IWL_ERR(mvm, "PHY ctxt cmd error ver %d not supported\n", ver);
+		return -EOPNOTSUPP;
+	}
 
-	/* Set the command data */
-	iwl_mvm_phy_ctxt_cmd_data(mvm, &cmd, chandef,
-				  chains_static, chains_dynamic);
 
-	ret = iwl_mvm_send_cmd_pdu(mvm, PHY_CONTEXT_CMD, 0, len, &cmd);
 	if (ret)
 		IWL_ERR(mvm, "PHY ctxt cmd error. ret=%d\n", ret);
 	return ret;
@@ -223,7 +277,7 @@ int iwl_mvm_phy_ctxt_add(struct iwl_mvm *mvm, struct iwl_mvm_phy_ctxt *ctxt,
 
 	return iwl_mvm_phy_ctxt_apply(mvm, ctxt, chandef,
 				      chains_static, chains_dynamic,
-				      FW_CTXT_ACTION_ADD, 0);
+				      FW_CTXT_ACTION_ADD);
 }
 
 /*
@@ -257,7 +311,7 @@ int iwl_mvm_phy_ctxt_changed(struct iwl_mvm *mvm, struct iwl_mvm_phy_ctxt *ctxt,
 		/* ... remove it here ...*/
 		ret = iwl_mvm_phy_ctxt_apply(mvm, ctxt, chandef,
 					     chains_static, chains_dynamic,
-					     FW_CTXT_ACTION_REMOVE, 0);
+					     FW_CTXT_ACTION_REMOVE);
 		if (ret)
 			return ret;
 
@@ -269,7 +323,7 @@ int iwl_mvm_phy_ctxt_changed(struct iwl_mvm *mvm, struct iwl_mvm_phy_ctxt *ctxt,
 	ctxt->width = chandef->width;
 	return iwl_mvm_phy_ctxt_apply(mvm, ctxt, chandef,
 				      chains_static, chains_dynamic,
-				      action, 0);
+				      action);
 }
 
 void iwl_mvm_phy_ctxt_unref(struct iwl_mvm *mvm, struct iwl_mvm_phy_ctxt *ctxt)
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rs-fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/rs-fw.c
index 6f4d241d47e9..012123268ba9 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rs-fw.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rs-fw.c
@@ -195,14 +195,20 @@ rs_fw_vht_set_enabled_rates(const struct ieee80211_sta *sta,
 {
 	u16 supp;
 	int i, highest_mcs;
-	u8 nss = sta->rx_nss;
+	u8 max_nss = sta->rx_nss;
+	struct ieee80211_vht_cap ieee_vht_cap = {
+		.vht_cap_info = cpu_to_le32(vht_cap->cap),
+		.supp_mcs = vht_cap->vht_mcs,
+	};
 
 	/* the station support only a single receive chain */
 	if (sta->smps_mode == IEEE80211_SMPS_STATIC)
-		nss = 1;
+		max_nss = 1;
 
-	for (i = 0; i < nss && i < IWL_TLC_NSS_MAX; i++) {
-		highest_mcs = rs_fw_vht_highest_rx_mcs_index(vht_cap, i + 1);
+	for (i = 0; i < max_nss && i < IWL_TLC_NSS_MAX; i++) {
+		int nss = i + 1;
+
+		highest_mcs = rs_fw_vht_highest_rx_mcs_index(vht_cap, nss);
 		if (!highest_mcs)
 			continue;
 
@@ -211,7 +217,15 @@ rs_fw_vht_set_enabled_rates(const struct ieee80211_sta *sta,
 			supp &= ~BIT(IWL_TLC_MNG_HT_RATE_MCS9);
 
 		cmd->ht_rates[i][IWL_TLC_HT_BW_NONE_160] = cpu_to_le16(supp);
-		if (sta->bandwidth == IEEE80211_STA_RX_BW_160)
+		/*
+		 * Check if VHT extended NSS indicates that the bandwidth/NSS
+		 * configuration is supported - only for MCS 0 since we already
+		 * decoded the MCS bits anyway ourselves.
+		 */
+		if (sta->bandwidth == IEEE80211_STA_RX_BW_160 &&
+		    ieee80211_get_vht_max_nss(&ieee_vht_cap,
+					      IEEE80211_VHT_CHANWIDTH_160MHZ,
+					      0, true, nss) >= nss)
 			cmd->ht_rates[i][IWL_TLC_HT_BW_160] =
 				cmd->ht_rates[i][IWL_TLC_HT_BW_NONE_160];
 	}
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c
index 86b2ebb5d5fb..ed7382e7ea17 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c
@@ -830,6 +830,12 @@ static u32 ucode_rate_from_rs_rate(struct iwl_mvm *mvm,
 		return ucode_rate;
 	}
 
+	/* set RTS protection for all non legacy rates
+	 * This helps with congested environments reducing the conflict cost to
+	 * RTS retries only, instead of the entire BA packet.
+	 */
+	ucode_rate |= RATE_MCS_RTS_REQUIRED_MSK;
+
 	if (is_ht(rate)) {
 		if (index < IWL_FIRST_HT_RATE || index > IWL_LAST_HT_RATE) {
 			IWL_ERR(mvm, "Invalid HT rate index %d\n", index);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
index c15f7dbc9516..ea29aeb86eef 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
@@ -8,7 +8,7 @@
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2015 - 2017 Intel Deutschland GmbH
- * Copyright(c) 2018 - 2019 Intel Corporation
+ * Copyright(c) 2018 - 2020 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -31,7 +31,7 @@
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2015 - 2017 Intel Deutschland GmbH
- * Copyright(c) 2018 - 2019 Intel Corporation
+ * Copyright(c) 2018 - 2020 Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -221,6 +221,31 @@ static int iwl_mvm_create_skb(struct iwl_mvm *mvm, struct sk_buff *skb,
 	skb_put_data(skb, hdr, hdrlen);
 	skb_put_data(skb, (u8 *)hdr + hdrlen + pad_len, headlen - hdrlen);
 
+	/*
+	 * If we did CHECKSUM_COMPLETE, the hardware only does it right for
+	 * certain cases and starts the checksum after the SNAP. Check if
+	 * this is the case - it's easier to just bail out to CHECKSUM_NONE
+	 * in the cases the hardware didn't handle, since it's rare to see
+	 * such packets, even though the hardware did calculate the checksum
+	 * in this case, just starting after the MAC header instead.
+	 */
+	if (skb->ip_summed == CHECKSUM_COMPLETE) {
+		struct {
+			u8 hdr[6];
+			__be16 type;
+		} __packed *shdr = (void *)((u8 *)hdr + hdrlen + pad_len);
+
+		if (unlikely(headlen - hdrlen < sizeof(*shdr) ||
+			     !ether_addr_equal(shdr->hdr, rfc1042_header) ||
+			     (shdr->type != htons(ETH_P_IP) &&
+			      shdr->type != htons(ETH_P_ARP) &&
+			      shdr->type != htons(ETH_P_IPV6) &&
+			      shdr->type != htons(ETH_P_8021Q) &&
+			      shdr->type != htons(ETH_P_PAE) &&
+			      shdr->type != htons(ETH_P_TDLS))))
+			skb->ip_summed = CHECKSUM_NONE;
+	}
+
 	fraglen = len - headlen;
 
 	if (fraglen) {
@@ -308,7 +333,7 @@ static int iwl_mvm_rx_crypto(struct iwl_mvm *mvm, struct ieee80211_hdr *hdr,
 			     struct iwl_rx_mpdu_desc *desc,
 			     u32 pkt_flags, int queue, u8 *crypt_len)
 {
-	u16 status = le16_to_cpu(desc->status);
+	u32 status = le32_to_cpu(desc->status);
 
 	/*
 	 * Drop UNKNOWN frames in aggregation, unless in monitor mode
@@ -393,22 +418,36 @@ static int iwl_mvm_rx_crypto(struct iwl_mvm *mvm, struct ieee80211_hdr *hdr,
 	return 0;
 }
 
-static void iwl_mvm_rx_csum(struct ieee80211_sta *sta,
+static void iwl_mvm_rx_csum(struct iwl_mvm *mvm,
+			    struct ieee80211_sta *sta,
 			    struct sk_buff *skb,
-			    struct iwl_rx_mpdu_desc *desc)
+			    struct iwl_rx_packet *pkt)
 {
-	struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta);
-	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(mvmsta->vif);
-	u16 flags = le16_to_cpu(desc->l3l4_flags);
-	u8 l3_prot = (u8)((flags & IWL_RX_L3L4_L3_PROTO_MASK) >>
-			  IWL_RX_L3_PROTO_POS);
-
-	if (mvmvif->features & NETIF_F_RXCSUM &&
-	    flags & IWL_RX_L3L4_TCP_UDP_CSUM_OK &&
-	    (flags & IWL_RX_L3L4_IP_HDR_CSUM_OK ||
-	     l3_prot == IWL_RX_L3_TYPE_IPV6 ||
-	     l3_prot == IWL_RX_L3_TYPE_IPV6_FRAG))
-		skb->ip_summed = CHECKSUM_UNNECESSARY;
+	struct iwl_rx_mpdu_desc *desc = (void *)pkt->data;
+
+	if (mvm->trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210) {
+		if (pkt->len_n_flags & cpu_to_le32(FH_RSCSR_RPA_EN)) {
+			u16 hwsum = be16_to_cpu(desc->v3.raw_xsum);
+
+			skb->ip_summed = CHECKSUM_COMPLETE;
+			skb->csum = csum_unfold(~(__force __sum16)hwsum);
+		}
+	} else {
+		struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta);
+		struct iwl_mvm_vif *mvmvif;
+		u16 flags = le16_to_cpu(desc->l3l4_flags);
+		u8 l3_prot = (u8)((flags & IWL_RX_L3L4_L3_PROTO_MASK) >>
+				  IWL_RX_L3_PROTO_POS);
+
+		mvmvif = iwl_mvm_vif_from_mac80211(mvmsta->vif);
+
+		if (mvmvif->features & NETIF_F_RXCSUM &&
+		    flags & IWL_RX_L3L4_TCP_UDP_CSUM_OK &&
+		    (flags & IWL_RX_L3L4_IP_HDR_CSUM_OK ||
+		     l3_prot == IWL_RX_L3_TYPE_IPV6 ||
+		     l3_prot == IWL_RX_L3_TYPE_IPV6_FRAG))
+			skb->ip_summed = CHECKSUM_UNNECESSARY;
+	}
 }
 
 /*
@@ -1668,10 +1707,10 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 	 * Keep packets with CRC errors (and with overrun) for monitor mode
 	 * (otherwise the firmware discards them) but mark them as bad.
 	 */
-	if (!(desc->status & cpu_to_le16(IWL_RX_MPDU_STATUS_CRC_OK)) ||
-	    !(desc->status & cpu_to_le16(IWL_RX_MPDU_STATUS_OVERRUN_OK))) {
+	if (!(desc->status & cpu_to_le32(IWL_RX_MPDU_STATUS_CRC_OK)) ||
+	    !(desc->status & cpu_to_le32(IWL_RX_MPDU_STATUS_OVERRUN_OK))) {
 		IWL_DEBUG_RX(mvm, "Bad CRC or FIFO: 0x%08X.\n",
-			     le16_to_cpu(desc->status));
+			     le32_to_cpu(desc->status));
 		rx_status->flag |= RX_FLAG_FAILED_FCS_CRC;
 	}
 	/* set the preamble flag if appropriate */
@@ -1731,8 +1770,8 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 
 	rcu_read_lock();
 
-	if (desc->status & cpu_to_le16(IWL_RX_MPDU_STATUS_SRC_STA_FOUND)) {
-		u8 id = desc->sta_id_flags & IWL_RX_MPDU_SIF_STA_ID_MASK;
+	if (desc->status & cpu_to_le32(IWL_RX_MPDU_STATUS_SRC_STA_FOUND)) {
+		u8 id = le32_get_bits(desc->status, IWL_RX_MPDU_STATUS_STA_ID);
 
 		if (!WARN_ON_ONCE(id >= ARRAY_SIZE(mvm->fw_id_to_mac_id))) {
 			sta = rcu_dereference(mvm->fw_id_to_mac_id[id]);
@@ -1796,7 +1835,7 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 		}
 
 		if (ieee80211_is_data(hdr->frame_control))
-			iwl_mvm_rx_csum(sta, skb, desc);
+			iwl_mvm_rx_csum(mvm, sta, skb, pkt);
 
 		if (iwl_mvm_is_dup(sta, queue, rx_status, hdr, desc)) {
 			kfree_skb(skb);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
index 51a061b138ba..1fbb52713493 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
@@ -147,7 +147,7 @@ struct iwl_mvm_scan_params {
 	struct cfg80211_match_set *match_sets;
 	int n_scan_plans;
 	struct cfg80211_sched_scan_plan *scan_plans;
-	u32 measurement_dwell;
+	bool iter_notif;
 };
 
 static inline void *iwl_mvm_get_scan_req_umac_data(struct iwl_mvm *mvm)
@@ -337,33 +337,6 @@ iwl_mvm_scan_type iwl_mvm_get_scan_type_band(struct iwl_mvm *mvm,
 	return _iwl_mvm_get_scan_type(mvm, vif, load, low_latency);
 }
 
-static int
-iwl_mvm_get_measurement_dwell(struct iwl_mvm *mvm,
-			      struct cfg80211_scan_request *req,
-			      struct iwl_mvm_scan_params *params)
-{
-	u32 duration = scan_timing[params->type].max_out_time;
-
-	if (!req->duration)
-		return 0;
-
-	if (iwl_mvm_is_cdb_supported(mvm)) {
-		u32 hb_time = scan_timing[params->hb_type].max_out_time;
-
-		duration = min_t(u32, duration, hb_time);
-	}
-
-	if (req->duration_mandatory && req->duration > duration) {
-		IWL_DEBUG_SCAN(mvm,
-			       "Measurement scan - too long dwell %hu (max out time %u)\n",
-			       req->duration,
-			       duration);
-		return -EOPNOTSUPP;
-	}
-
-	return min_t(u32, (u32)req->duration, duration);
-}
-
 static inline bool iwl_mvm_rrm_scan_needed(struct iwl_mvm *mvm)
 {
 	/* require rrm scan whenever the fw supports it */
@@ -1333,10 +1306,8 @@ static void iwl_mvm_scan_umac_dwell(struct iwl_mvm *mvm,
 	u8 active_dwell, passive_dwell;
 
 	timing = &scan_timing[params->type];
-	active_dwell = params->measurement_dwell ?
-		params->measurement_dwell : IWL_SCAN_DWELL_ACTIVE;
-	passive_dwell = params->measurement_dwell ?
-		params->measurement_dwell : IWL_SCAN_DWELL_PASSIVE;
+	active_dwell = IWL_SCAN_DWELL_ACTIVE;
+	passive_dwell = IWL_SCAN_DWELL_PASSIVE;
 
 	if (iwl_mvm_is_adaptive_dwell_supported(mvm)) {
 		cmd->v7.adwell_default_n_aps_social =
@@ -1389,8 +1360,7 @@ static void iwl_mvm_scan_umac_dwell(struct iwl_mvm *mvm,
 			}
 		}
 	} else {
-		cmd->v1.extended_dwell = params->measurement_dwell ?
-			params->measurement_dwell : IWL_SCAN_DWELL_EXTENDED;
+		cmd->v1.extended_dwell = IWL_SCAN_DWELL_EXTENDED;
 		cmd->v1.active_dwell = active_dwell;
 		cmd->v1.passive_dwell = passive_dwell;
 		cmd->v1.fragmented_dwell = IWL_SCAN_DWELL_FRAGMENTED;
@@ -1443,10 +1413,8 @@ iwl_mvm_scan_umac_dwell_v10(struct iwl_mvm *mvm,
 	u8 active_dwell, passive_dwell;
 
 	timing = &scan_timing[params->type];
-	active_dwell = params->measurement_dwell ?
-		params->measurement_dwell : IWL_SCAN_DWELL_ACTIVE;
-	passive_dwell = params->measurement_dwell ?
-		params->measurement_dwell : IWL_SCAN_DWELL_PASSIVE;
+	active_dwell = IWL_SCAN_DWELL_ACTIVE;
+	passive_dwell = IWL_SCAN_DWELL_PASSIVE;
 
 	general_params->adwell_default_social_chn =
 		IWL_SCAN_ADWELL_DEFAULT_N_APS_SOCIAL;
@@ -1737,7 +1705,7 @@ static u16 iwl_mvm_scan_umac_flags_v2(struct iwl_mvm *mvm,
 	if (!iwl_mvm_is_regular_scan(params))
 		flags |= IWL_UMAC_SCAN_GEN_FLAGS_V2_PERIODIC;
 
-	if (params->measurement_dwell ||
+	if (params->iter_notif ||
 	    mvm->sched_scan_pass_all == SCHED_SCAN_PASS_ALL_ENABLED)
 		flags |= IWL_UMAC_SCAN_GEN_FLAGS_V2_NTFY_ITER_COMPLETE;
 
@@ -1782,7 +1750,7 @@ static u16 iwl_mvm_scan_umac_flags(struct iwl_mvm *mvm,
 	if (!iwl_mvm_is_regular_scan(params))
 		flags |= IWL_UMAC_SCAN_GEN_FLAGS_PERIODIC;
 
-	if (params->measurement_dwell)
+	if (params->iter_notif)
 		flags |= IWL_UMAC_SCAN_GEN_FLAGS_ITER_COMPLETE;
 
 #ifdef CONFIG_IWLWIFI_DEBUGFS
@@ -2229,7 +2197,8 @@ static int iwl_mvm_build_scan_cmd(struct iwl_mvm *mvm,
 	hcmd->id = iwl_cmd_id(SCAN_REQ_UMAC, IWL_ALWAYS_LONG_GROUP, 0);
 
 	scan_ver = iwl_fw_lookup_cmd_ver(mvm->fw, IWL_ALWAYS_LONG_GROUP,
-					 SCAN_REQ_UMAC);
+					 SCAN_REQ_UMAC,
+					 IWL_FW_CMD_VER_UNKNOWN);
 
 	for (i = 0; i < ARRAY_SIZE(iwl_scan_umac_handlers); i++) {
 		const struct iwl_scan_umac_handler *ver_handler =
@@ -2293,11 +2262,8 @@ int iwl_mvm_reg_scan_start(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 
 	iwl_mvm_fill_scan_type(mvm, &params, vif);
 
-	ret = iwl_mvm_get_measurement_dwell(mvm, req, &params);
-	if (ret < 0)
-		return ret;
-
-	params.measurement_dwell = ret;
+	if (req->duration)
+		params.iter_notif = true;
 
 	iwl_mvm_build_scan_probe(mvm, vif, ies, &params);
 
@@ -2569,7 +2535,8 @@ int iwl_mvm_scan_size(struct iwl_mvm *mvm)
 {
 	int base_size, tail_size;
 	u8 scan_ver = iwl_fw_lookup_cmd_ver(mvm->fw, IWL_ALWAYS_LONG_GROUP,
-					    SCAN_REQ_UMAC);
+					    SCAN_REQ_UMAC,
+					    IWL_FW_CMD_VER_UNKNOWN);
 
 	base_size = iwl_scan_req_umac_get_size(scan_ver);
 	if (base_size)
@@ -2626,6 +2593,15 @@ void iwl_mvm_report_scan_aborted(struct iwl_mvm *mvm)
 			mvm->sched_scan_pass_all = SCHED_SCAN_PASS_ALL_DISABLED;
 			mvm->scan_uid_status[uid] = 0;
 		}
+		uid = iwl_mvm_scan_uid_by_status(mvm,
+						 IWL_MVM_SCAN_STOPPING_REGULAR);
+		if (uid >= 0)
+			mvm->scan_uid_status[uid] = 0;
+
+		uid = iwl_mvm_scan_uid_by_status(mvm,
+						 IWL_MVM_SCAN_STOPPING_SCHED);
+		if (uid >= 0)
+			mvm->scan_uid_status[uid] = 0;
 
 		/* We shouldn't have any UIDs still set.  Loop over all the
 		 * UIDs to make sure there's nothing left there and warn if
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
index 9e124755a3ce..72c9235c6bd5 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
@@ -770,8 +770,6 @@ static int iwl_mvm_tvqm_enable_txq(struct iwl_mvm *mvm,
 	IWL_DEBUG_TX_QUEUES(mvm, "Enabling TXQ #%d for sta %d tid %d\n",
 			    queue, sta_id, tid);
 
-	IWL_DEBUG_TX_QUEUES(mvm, "Enabling TXQ #%d\n", queue);
-
 	return queue;
 }
 
@@ -1997,7 +1995,7 @@ static int iwl_mvm_enable_aux_snif_queue_tvqm(struct iwl_mvm *mvm, u8 sta_id)
 }
 
 static int iwl_mvm_add_int_sta_with_queue(struct iwl_mvm *mvm, int macidx,
-					  int maccolor,
+					  int maccolor, u8 *addr,
 					  struct iwl_mvm_int_sta *sta,
 					  u16 *queue, int fifo)
 {
@@ -2007,7 +2005,7 @@ static int iwl_mvm_add_int_sta_with_queue(struct iwl_mvm *mvm, int macidx,
 	if (!iwl_mvm_has_new_tx_api(mvm))
 		iwl_mvm_enable_aux_snif_queue(mvm, *queue, sta->sta_id, fifo);
 
-	ret = iwl_mvm_add_int_sta_common(mvm, sta, NULL, macidx, maccolor);
+	ret = iwl_mvm_add_int_sta_common(mvm, sta, addr, macidx, maccolor);
 	if (ret) {
 		if (!iwl_mvm_has_new_tx_api(mvm))
 			iwl_mvm_disable_txq(mvm, NULL, *queue,
@@ -2047,7 +2045,7 @@ int iwl_mvm_add_aux_sta(struct iwl_mvm *mvm)
 	if (ret)
 		return ret;
 
-	ret = iwl_mvm_add_int_sta_with_queue(mvm, MAC_INDEX_AUX, 0,
+	ret = iwl_mvm_add_int_sta_with_queue(mvm, MAC_INDEX_AUX, 0, NULL,
 					     &mvm->aux_sta, &mvm->aux_queue,
 					     IWL_MVM_TX_FIFO_MCAST);
 	if (ret) {
@@ -2065,7 +2063,8 @@ int iwl_mvm_add_snif_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif)
 	lockdep_assert_held(&mvm->mutex);
 
 	return iwl_mvm_add_int_sta_with_queue(mvm, mvmvif->id, mvmvif->color,
-					      &mvm->snif_sta, &mvm->snif_queue,
+					      NULL, &mvm->snif_sta,
+					      &mvm->snif_queue,
 					      IWL_MVM_TX_FIFO_BE);
 }
 
@@ -2863,7 +2862,7 @@ int iwl_mvm_sta_tx_agg_start(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 		ret = IEEE80211_AMPDU_TX_START_IMMEDIATE;
 	} else {
 		tid_data->state = IWL_EMPTYING_HW_QUEUE_ADDBA;
-		ret = 0;
+		ret = IEEE80211_AMPDU_TX_START_DELAY_ADDBA;
 	}
 
 out:
@@ -3903,3 +3902,43 @@ u16 iwl_mvm_tid_queued(struct iwl_mvm *mvm, struct iwl_mvm_tid_data *tid_data)
 
 	return ieee80211_sn_sub(sn, tid_data->next_reclaimed);
 }
+
+int iwl_mvm_add_pasn_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
+			 struct iwl_mvm_int_sta *sta, u8 *addr, u32 cipher,
+			 u8 *key, u32 key_len)
+{
+	int ret;
+	u16 queue;
+	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
+	struct ieee80211_key_conf *keyconf;
+
+	ret = iwl_mvm_allocate_int_sta(mvm, sta, 0,
+				       NL80211_IFTYPE_UNSPECIFIED,
+				       IWL_STA_LINK);
+	if (ret)
+		return ret;
+
+	ret = iwl_mvm_add_int_sta_with_queue(mvm, mvmvif->id, mvmvif->color,
+					     addr, sta, &queue,
+					     IWL_MVM_TX_FIFO_BE);
+	if (ret)
+		goto out;
+
+	keyconf = kzalloc(sizeof(*keyconf) + key_len, GFP_KERNEL);
+	if (!keyconf) {
+		ret = -ENOBUFS;
+		goto out;
+	}
+
+	keyconf->cipher = cipher;
+	memcpy(keyconf->key, key, key_len);
+	keyconf->keylen = key_len;
+
+	ret = iwl_mvm_send_sta_key(mvm, sta->sta_id, keyconf, false,
+				   0, NULL, 0, 0, true);
+	kfree(keyconf);
+	return 0;
+out:
+	iwl_mvm_dealloc_int_sta(mvm, sta);
+	return ret;
+}
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.h b/drivers/net/wireless/intel/iwlwifi/mvm/sta.h
index da2d1ac01229..55dd2fb0a779 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.h
@@ -579,5 +579,8 @@ void iwl_mvm_modify_all_sta_disable_tx(struct iwl_mvm *mvm,
 				       bool disable);
 void iwl_mvm_csa_client_absent(struct iwl_mvm *mvm, struct ieee80211_vif *vif);
 void iwl_mvm_add_new_dqa_stream_wk(struct work_struct *wk);
+int iwl_mvm_add_pasn_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
+			 struct iwl_mvm_int_sta *sta, u8 *addr, u32 cipher,
+			 u8 *key, u32 key_len);
 
 #endif /* __sta_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tt.c b/drivers/net/wireless/intel/iwlwifi/mvm/tt.c
index 0c95663bf9ed..94e9b6de425e 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/tt.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/tt.c
@@ -228,24 +228,67 @@ void iwl_mvm_ct_kill_notif(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb)
 	iwl_mvm_enter_ctkill(mvm);
 }
 
-static int iwl_mvm_get_temp_cmd(struct iwl_mvm *mvm)
+/*
+ * send the DTS_MEASUREMENT_TRIGGER command with or without waiting for a
+ * response. If we get a response then the measurement is stored in 'temp'
+ */
+static int iwl_mvm_send_temp_cmd(struct iwl_mvm *mvm, bool response, s32 *temp)
 {
-	struct iwl_dts_measurement_cmd cmd = {
+	struct iwl_host_cmd cmd = {};
+	struct iwl_dts_measurement_cmd dts_cmd = {
 		.flags = cpu_to_le32(DTS_TRIGGER_CMD_FLAGS_TEMP),
 	};
-	struct iwl_ext_dts_measurement_cmd extcmd = {
+	struct iwl_ext_dts_measurement_cmd ext_cmd = {
 		.control_mode = cpu_to_le32(DTS_DIRECT_WITHOUT_MEASURE),
 	};
-	u32 cmdid;
+	struct iwl_dts_measurement_resp *resp;
+	void *cmd_ptr;
+	int ret;
+	u32 cmd_flags = 0;
+	u16 len;
+
+	/* Check which command format is used (regular/extended) */
+	if (fw_has_capa(&mvm->fw->ucode_capa,
+			IWL_UCODE_TLV_CAPA_EXTENDED_DTS_MEASURE)) {
+		len = sizeof(ext_cmd);
+		cmd_ptr = &ext_cmd;
+	} else {
+		len = sizeof(dts_cmd);
+		cmd_ptr = &dts_cmd;
+	}
+	/* The command version where we get a response is zero length */
+	if (response) {
+		cmd_flags = CMD_WANT_SKB;
+		len = 0;
+	}
 
-	cmdid = iwl_cmd_id(CMD_DTS_MEASUREMENT_TRIGGER_WIDE,
-			   PHY_OPS_GROUP, 0);
+	cmd.id =  WIDE_ID(PHY_OPS_GROUP, CMD_DTS_MEASUREMENT_TRIGGER_WIDE);
+	cmd.len[0] = len;
+	cmd.flags = cmd_flags;
+	cmd.data[0] = cmd_ptr;
 
-	if (!fw_has_capa(&mvm->fw->ucode_capa,
-			 IWL_UCODE_TLV_CAPA_EXTENDED_DTS_MEASURE))
-		return iwl_mvm_send_cmd_pdu(mvm, cmdid, 0, sizeof(cmd), &cmd);
+	IWL_DEBUG_TEMP(mvm,
+		       "Sending temperature measurement command - %s response\n",
+		       response ? "with" : "without");
+	ret = iwl_mvm_send_cmd(mvm, &cmd);
 
-	return iwl_mvm_send_cmd_pdu(mvm, cmdid, 0, sizeof(extcmd), &extcmd);
+	if (ret) {
+		IWL_ERR(mvm,
+			"Failed to send the temperature measurement command (err=%d)\n",
+			ret);
+		return ret;
+	}
+
+	if (response) {
+		resp = (void *)cmd.resp_pkt->data;
+		*temp = le32_to_cpu(resp->temp);
+		IWL_DEBUG_TEMP(mvm,
+			       "Got temperature measurement response: temp=%d\n",
+			       *temp);
+		iwl_free_resp(&cmd);
+	}
+
+	return ret;
 }
 
 int iwl_mvm_get_temp(struct iwl_mvm *mvm, s32 *temp)
@@ -254,6 +297,18 @@ int iwl_mvm_get_temp(struct iwl_mvm *mvm, s32 *temp)
 	static u16 temp_notif[] = { WIDE_ID(PHY_OPS_GROUP,
 					    DTS_MEASUREMENT_NOTIF_WIDE) };
 	int ret;
+	u8 cmd_ver;
+
+	/*
+	 * If command version is 1 we send the command and immediately get
+	 * a response. For older versions we send the command and wait for a
+	 * notification (no command TLV for previous versions).
+	 */
+	cmd_ver = iwl_fw_lookup_cmd_ver(mvm->fw, PHY_OPS_GROUP,
+					CMD_DTS_MEASUREMENT_TRIGGER_WIDE,
+					IWL_FW_CMD_VER_UNKNOWN);
+	if (cmd_ver == 1)
+		return iwl_mvm_send_temp_cmd(mvm, true, temp);
 
 	lockdep_assert_held(&mvm->mutex);
 
@@ -261,9 +316,8 @@ int iwl_mvm_get_temp(struct iwl_mvm *mvm, s32 *temp)
 				   temp_notif, ARRAY_SIZE(temp_notif),
 				   iwl_mvm_temp_notif_wait, temp);
 
-	ret = iwl_mvm_get_temp_cmd(mvm);
+	ret = iwl_mvm_send_temp_cmd(mvm, false, temp);
 	if (ret) {
-		IWL_ERR(mvm, "Failed to get the temperature (err=%d)\n", ret);
 		iwl_remove_notification(&mvm->notif_wait, &wait_temp_notif);
 		return ret;
 	}
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
index 2f6484e0d726..a372f32f4571 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
@@ -1768,9 +1768,9 @@ static void iwl_mvm_tx_reclaim(struct iwl_mvm *mvm, int sta_id, int tid,
 			       struct ieee80211_tx_info *ba_info, u32 rate)
 {
 	struct sk_buff_head reclaimed_skbs;
-	struct iwl_mvm_tid_data *tid_data;
+	struct iwl_mvm_tid_data *tid_data = NULL;
 	struct ieee80211_sta *sta;
-	struct iwl_mvm_sta *mvmsta;
+	struct iwl_mvm_sta *mvmsta = NULL;
 	struct sk_buff *skb;
 	int freed;
 
@@ -1784,11 +1784,44 @@ static void iwl_mvm_tx_reclaim(struct iwl_mvm *mvm, int sta_id, int tid,
 	sta = rcu_dereference(mvm->fw_id_to_mac_id[sta_id]);
 
 	/* Reclaiming frames for a station that has been deleted ? */
-	if (WARN_ON_ONCE(IS_ERR_OR_NULL(sta))) {
+	if (WARN_ON_ONCE(!sta)) {
 		rcu_read_unlock();
 		return;
 	}
 
+	__skb_queue_head_init(&reclaimed_skbs);
+
+	/*
+	 * Release all TFDs before the SSN, i.e. all TFDs in front of
+	 * block-ack window (we assume that they've been successfully
+	 * transmitted ... if not, it's too late anyway).
+	 */
+	iwl_trans_reclaim(mvm->trans, txq, index, &reclaimed_skbs);
+
+	skb_queue_walk(&reclaimed_skbs, skb) {
+		struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+
+		iwl_trans_free_tx_cmd(mvm->trans, info->driver_data[1]);
+
+		memset(&info->status, 0, sizeof(info->status));
+		/* Packet was transmitted successfully, failures come as single
+		 * frames because before failing a frame the firmware transmits
+		 * it without aggregation at least once.
+		 */
+		info->flags |= IEEE80211_TX_STAT_ACK;
+	}
+
+	/*
+	 * It's possible to get a BA response after invalidating the rcu (rcu is
+	 * invalidated in order to prevent new Tx from being sent, but there may
+	 * be some frames already in-flight).
+	 * In this case we just want to reclaim, and could skip all the
+	 * sta-dependent stuff since it's in the middle of being removed
+	 * anyways.
+	 */
+	if (IS_ERR(sta))
+		goto out;
+
 	mvmsta = iwl_mvm_sta_from_mac80211(sta);
 	tid_data = &mvmsta->tid_data[tid];
 
@@ -1800,15 +1833,6 @@ static void iwl_mvm_tx_reclaim(struct iwl_mvm *mvm, int sta_id, int tid,
 		return;
 	}
 
-	__skb_queue_head_init(&reclaimed_skbs);
-
-	/*
-	 * Release all TFDs before the SSN, i.e. all TFDs in front of
-	 * block-ack window (we assume that they've been successfully
-	 * transmitted ... if not, it's too late anyway).
-	 */
-	iwl_trans_reclaim(mvm->trans, txq, index, &reclaimed_skbs);
-
 	spin_lock_bh(&mvmsta->lock);
 
 	tid_data->next_reclaimed = index;
@@ -1832,15 +1856,6 @@ static void iwl_mvm_tx_reclaim(struct iwl_mvm *mvm, int sta_id, int tid,
 		else
 			WARN_ON_ONCE(tid != IWL_MAX_TID_COUNT);
 
-		iwl_trans_free_tx_cmd(mvm->trans, info->driver_data[1]);
-
-		memset(&info->status, 0, sizeof(info->status));
-		/* Packet was transmitted successfully, failures come as single
-		 * frames because before failing a frame the firmware transmits
-		 * it without aggregation at least once.
-		 */
-		info->flags |= IEEE80211_TX_STAT_ACK;
-
 		/* this is the first skb we deliver in this batch */
 		/* put the rate scaling data there */
 		if (freed == 1) {
@@ -1917,8 +1932,14 @@ void iwl_mvm_rx_ba_notif(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb)
 		rcu_read_lock();
 
 		mvmsta = iwl_mvm_sta_from_staid_rcu(mvm, sta_id);
-		if (!mvmsta)
-			goto out_unlock;
+		/*
+		 * It's possible to get a BA response after invalidating the rcu
+		 * (rcu is invalidated in order to prevent new Tx from being
+		 * sent, but there may be some frames already in-flight).
+		 * In this case we just want to reclaim, and could skip all the
+		 * sta-dependent stuff since it's in the middle of being removed
+		 * anyways.
+		 */
 
 		/* Free per TID */
 		for (i = 0; i < le16_to_cpu(ba_res->tfd_cnt); i++) {
@@ -1929,7 +1950,9 @@ void iwl_mvm_rx_ba_notif(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb)
 			if (tid == IWL_MGMT_TID)
 				tid = IWL_MAX_TID_COUNT;
 
-			mvmsta->tid_data[i].lq_color = lq_color;
+			if (mvmsta)
+				mvmsta->tid_data[i].lq_color = lq_color;
+
 			iwl_mvm_tx_reclaim(mvm, sta_id, tid,
 					   (int)(le16_to_cpu(ba_tfd->q_num)),
 					   le16_to_cpu(ba_tfd->tfd_index),
@@ -1937,9 +1960,9 @@ void iwl_mvm_rx_ba_notif(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb)
 					   le32_to_cpu(ba_res->tx_rate));
 		}
 
-		iwl_mvm_tx_airtime(mvm, mvmsta,
-				   le32_to_cpu(ba_res->wireless_time));
-out_unlock:
+		if (mvmsta)
+			iwl_mvm_tx_airtime(mvm, mvmsta,
+					   le32_to_cpu(ba_res->wireless_time));
 		rcu_read_unlock();
 out:
 		IWL_DEBUG_TX_REPLY(mvm,
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/utils.c b/drivers/net/wireless/intel/iwlwifi/mvm/utils.c
index be57b8391850..ae39d81d74c6 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/utils.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/utils.c
@@ -67,6 +67,7 @@
 #include "iwl-csr.h"
 #include "mvm.h"
 #include "fw/api/rs.h"
+#include "fw/img.h"
 
 /*
  * Will return 0 even if the cmd failed when RFKILL is asserted unless
@@ -289,45 +290,6 @@ u8 iwl_mvm_next_antenna(struct iwl_mvm *mvm, u8 valid, u8 last_idx)
 	return last_idx;
 }
 
-#define FW_SYSASSERT_CPU_MASK 0xf0000000
-static const struct {
-	const char *name;
-	u8 num;
-} advanced_lookup[] = {
-	{ "NMI_INTERRUPT_WDG", 0x34 },
-	{ "SYSASSERT", 0x35 },
-	{ "UCODE_VERSION_MISMATCH", 0x37 },
-	{ "BAD_COMMAND", 0x38 },
-	{ "BAD_COMMAND", 0x39 },
-	{ "NMI_INTERRUPT_DATA_ACTION_PT", 0x3C },
-	{ "FATAL_ERROR", 0x3D },
-	{ "NMI_TRM_HW_ERR", 0x46 },
-	{ "NMI_INTERRUPT_TRM", 0x4C },
-	{ "NMI_INTERRUPT_BREAK_POINT", 0x54 },
-	{ "NMI_INTERRUPT_WDG_RXF_FULL", 0x5C },
-	{ "NMI_INTERRUPT_WDG_NO_RBD_RXF_FULL", 0x64 },
-	{ "NMI_INTERRUPT_HOST", 0x66 },
-	{ "NMI_INTERRUPT_LMAC_FATAL", 0x70 },
-	{ "NMI_INTERRUPT_UMAC_FATAL", 0x71 },
-	{ "NMI_INTERRUPT_OTHER_LMAC_FATAL", 0x73 },
-	{ "NMI_INTERRUPT_ACTION_PT", 0x7C },
-	{ "NMI_INTERRUPT_UNKNOWN", 0x84 },
-	{ "NMI_INTERRUPT_INST_ACTION_PT", 0x86 },
-	{ "ADVANCED_SYSASSERT", 0 },
-};
-
-static const char *desc_lookup(u32 num)
-{
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(advanced_lookup) - 1; i++)
-		if (advanced_lookup[i].num == (num & ~FW_SYSASSERT_CPU_MASK))
-			return advanced_lookup[i].name;
-
-	/* No entry matches 'num', so it is the last: ADVANCED_SYSASSERT */
-	return advanced_lookup[i].name;
-}
-
 /*
  * Note: This structure is read from the device with IO accesses,
  * and the reading already does the endian conversion. As it is
@@ -463,7 +425,7 @@ static void iwl_mvm_dump_umac_error_log(struct iwl_mvm *mvm)
 	struct iwl_umac_error_event_table table;
 	u32 base = mvm->trans->dbg.umac_error_event_table;
 
-	if (!mvm->support_umac_log &&
+	if (!base &&
 	    !(mvm->trans->dbg.error_event_table_tlv_status &
 	      IWL_ERROR_EVENT_TABLE_UMAC))
 		return;
@@ -480,7 +442,7 @@ static void iwl_mvm_dump_umac_error_log(struct iwl_mvm *mvm)
 	}
 
 	IWL_ERR(mvm, "0x%08X | %s\n", table.error_id,
-		desc_lookup(table.error_id));
+		iwl_fw_lookup_assert_desc(table.error_id));
 	IWL_ERR(mvm, "0x%08X | umac branchlink1\n", table.blink1);
 	IWL_ERR(mvm, "0x%08X | umac branchlink2\n", table.blink2);
 	IWL_ERR(mvm, "0x%08X | umac interruptlink1\n", table.ilink1);
@@ -550,7 +512,7 @@ static void iwl_mvm_dump_lmac_error_log(struct iwl_mvm *mvm, u8 lmac_num)
 	IWL_ERR(mvm, "Loaded firmware version: %s\n", mvm->fw->fw_version);
 
 	IWL_ERR(mvm, "0x%08X | %-28s\n", table.error_id,
-		desc_lookup(table.error_id));
+		iwl_fw_lookup_assert_desc(table.error_id));
 	IWL_ERR(mvm, "0x%08X | trm_hw_status0\n", table.trm_hw_status0);
 	IWL_ERR(mvm, "0x%08X | trm_hw_status1\n", table.trm_hw_status1);
 	IWL_ERR(mvm, "0x%08X | branchlink2\n", table.blink2);
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c
index 23abfbd096b0..2597faea79c4 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c
@@ -73,7 +73,7 @@ static void *_iwl_pcie_ctxt_info_dma_alloc_coherent(struct iwl_trans *trans,
 	if (!result)
 		return NULL;
 
-	if (unlikely(iwl_pcie_crosses_4g_boundary(*phys, size))) {
+	if (unlikely(iwl_txq_crosses_4g_boundary(*phys, size))) {
 		void *old = result;
 		dma_addr_t oldphys = *phys;
 
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
index e02bafb8921f..d7dfda909b93 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
@@ -540,20 +540,33 @@ static const struct pci_device_id iwl_hw_card_ids[] = {
 	{IWL_PCI_DEVICE(0x2725, 0x0510, iwlax210_2ax_cfg_ty_gf_a0)},
 	{IWL_PCI_DEVICE(0x2725, 0x0A10, iwlax210_2ax_cfg_ty_gf_a0)},
 	{IWL_PCI_DEVICE(0x2725, 0x00B0, iwlax411_2ax_cfg_sosnj_gf4_a0)},
+	{IWL_PCI_DEVICE(0x2726, 0x0070, iwlax201_cfg_snj_hr_b0)},
+	{IWL_PCI_DEVICE(0x2726, 0x0074, iwlax201_cfg_snj_hr_b0)},
+	{IWL_PCI_DEVICE(0x2726, 0x0078, iwlax201_cfg_snj_hr_b0)},
+	{IWL_PCI_DEVICE(0x2726, 0x007C, iwlax201_cfg_snj_hr_b0)},
 	{IWL_PCI_DEVICE(0x2726, 0x0090, iwlax211_cfg_snj_gf_a0)},
+	{IWL_PCI_DEVICE(0x2726, 0x0098, iwlax211_cfg_snj_gf_a0)},
 	{IWL_PCI_DEVICE(0x2726, 0x00B0, iwlax411_2ax_cfg_sosnj_gf4_a0)},
 	{IWL_PCI_DEVICE(0x2726, 0x0510, iwlax211_cfg_snj_gf_a0)},
+	{IWL_PCI_DEVICE(0x2726, 0x2074, iwlax201_cfg_snj_hr_b0)},
+	{IWL_PCI_DEVICE(0x2726, 0x4070, iwlax201_cfg_snj_hr_b0)},
 	{IWL_PCI_DEVICE(0x7A70, 0x0090, iwlax211_2ax_cfg_so_gf_a0_long)},
+	{IWL_PCI_DEVICE(0x7A70, 0x0098, iwlax211_2ax_cfg_so_gf_a0_long)},
 	{IWL_PCI_DEVICE(0x7A70, 0x00B0, iwlax411_2ax_cfg_so_gf4_a0_long)},
 	{IWL_PCI_DEVICE(0x7A70, 0x0310, iwlax211_2ax_cfg_so_gf_a0_long)},
 	{IWL_PCI_DEVICE(0x7A70, 0x0510, iwlax211_2ax_cfg_so_gf_a0_long)},
 	{IWL_PCI_DEVICE(0x7A70, 0x0A10, iwlax211_2ax_cfg_so_gf_a0_long)},
 	{IWL_PCI_DEVICE(0x7AF0, 0x0090, iwlax211_2ax_cfg_so_gf_a0)},
+	{IWL_PCI_DEVICE(0x7AF0, 0x0098, iwlax211_2ax_cfg_so_gf_a0)},
 	{IWL_PCI_DEVICE(0x7AF0, 0x00B0, iwlax411_2ax_cfg_so_gf4_a0)},
 	{IWL_PCI_DEVICE(0x7AF0, 0x0310, iwlax211_2ax_cfg_so_gf_a0)},
 	{IWL_PCI_DEVICE(0x7AF0, 0x0510, iwlax211_2ax_cfg_so_gf_a0)},
 	{IWL_PCI_DEVICE(0x7AF0, 0x0A10, iwlax211_2ax_cfg_so_gf_a0)},
 
+/* Ma devices */
+	{IWL_PCI_DEVICE(0x2729, PCI_ANY_ID, iwl_ma_trans_cfg)},
+	{IWL_PCI_DEVICE(0x7E80, PCI_ANY_ID, iwl_ma_trans_cfg)},
+
 #endif /* CONFIG_IWLMVM */
 
 	{0}
@@ -595,6 +608,12 @@ static const struct iwl_dev_info iwl_dev_info_table[] = {
 	/* QnJ with Hr */
 	IWL_DEV_INFO(0x2720, IWL_CFG_ANY, iwl_qnj_b0_hr_b0_cfg, iwl_ax201_name),
 
+	/* SnJ with HR*/
+	IWL_DEV_INFO(0x2726, 0x0244, iwlax201_cfg_snj_hr_b0, iwl_ax101_name),
+	IWL_DEV_INFO(0x2726, 0x1651, iwlax201_cfg_snj_hr_b0, iwl_ax201_killer_1650s_name),
+	IWL_DEV_INFO(0x2726, 0x1652, iwlax201_cfg_snj_hr_b0, iwl_ax201_killer_1650i_name),
+	IWL_DEV_INFO(0x2726, 0x4244, iwlax201_cfg_snj_hr_b0, iwl_ax101_name),
+
 	/* Qu with Hr */
 	IWL_DEV_INFO(0x43F0, 0x0070, iwl_ax201_cfg_qu_hr, NULL),
 	IWL_DEV_INFO(0x43F0, 0x0074, iwl_ax201_cfg_qu_hr, NULL),
@@ -955,6 +974,18 @@ static const struct iwl_dev_info iwl_dev_info_table[] = {
 		      IWL_CFG_ANY, IWL_CFG_ANY,
 		      iwl_quz_a0_hr1_b0, iwl_ax101_name),
 
+/* Ma */
+	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
+		      IWL_CFG_MAC_TYPE_MA, IWL_CFG_ANY,
+		      IWL_CFG_RF_TYPE_GF, IWL_CFG_ANY,
+		      IWL_CFG_ANY, IWL_CFG_ANY,
+		      iwl_cfg_ma_a0_gf_a0, iwl_ax211_name),
+	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
+		      IWL_CFG_MAC_TYPE_MA, IWL_CFG_ANY,
+		      IWL_CFG_RF_TYPE_MR, IWL_CFG_ANY,
+		      IWL_CFG_ANY, IWL_CFG_ANY,
+		      iwl_cfg_ma_a0_mr_a0, iwl_ma_name),
+
 #endif /* CONFIG_IWLMVM */
 };
 
@@ -987,9 +1018,6 @@ static int iwl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	trans_pcie = IWL_TRANS_GET_PCIE_TRANS(iwl_trans);
 
-	/* the trans_cfg should never change, so set it now */
-	iwl_trans->trans_cfg = trans;
-
 	iwl_trans->hw_rf_id = iwl_read32(iwl_trans, CSR_HW_RF_ID);
 
 	for (i = 0; i < ARRAY_SIZE(iwl_dev_info_table); i++) {
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
index 55808ba10d27..033f845a89dc 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
@@ -79,12 +79,7 @@
 #include "iwl-io.h"
 #include "iwl-op-mode.h"
 #include "iwl-drv.h"
-
-/* We need 2 entries for the TX command and header, and another one might
- * be needed for potential data in the SKB's head. The remaining ones can
- * be used for frags.
- */
-#define IWL_PCIE_MAX_FRAGS(x) (x->max_tbs - 3)
+#include "queue/tx.h"
 
 /*
  * RX related structures and functions
@@ -247,16 +242,6 @@ struct iwl_rb_allocator {
 };
 
 /**
- * iwl_queue_inc_wrap - increment queue index, wrap back to beginning
- * @index -- current index
- */
-static inline int iwl_queue_inc_wrap(struct iwl_trans *trans, int index)
-{
-	return ++index &
-		(trans->trans_cfg->base_params->max_tfd_queue_size - 1);
-}
-
-/**
  * iwl_get_closed_rb_stts - get closed rb stts from different structs
  * @rxq - the rxq to get the rb stts from
  */
@@ -274,28 +259,6 @@ static inline __le16 iwl_get_closed_rb_stts(struct iwl_trans *trans,
 	}
 }
 
-/**
- * iwl_queue_dec_wrap - decrement queue index, wrap back to end
- * @index -- current index
- */
-static inline int iwl_queue_dec_wrap(struct iwl_trans *trans, int index)
-{
-	return --index &
-		(trans->trans_cfg->base_params->max_tfd_queue_size - 1);
-}
-
-static inline dma_addr_t
-iwl_pcie_get_first_tb_dma(struct iwl_txq *txq, int idx)
-{
-	return txq->first_tb_dma +
-	       sizeof(struct iwl_pcie_first_tb_buf) * idx;
-}
-
-struct iwl_tso_hdr_page {
-	struct page *page;
-	u8 *pos;
-};
-
 #ifdef CONFIG_IWLWIFI_DEBUGFS
 /**
  * enum iwl_fw_mon_dbgfs_state - the different states of the monitor_data
@@ -375,7 +338,6 @@ struct cont_rec {
  *	count for allocating and freeing the memory.
  * @trans: pointer to the generic transport area
  * @scd_base_addr: scheduler sram base address in SRAM
- * @scd_bc_tbls: pointer to the byte count table of the scheduler
  * @kw: keep warm address
  * @pci_dev: basic pci-network driver stuff
  * @hw_base: pci hardware address support
@@ -384,7 +346,6 @@ struct cont_rec {
  * @cmd_queue - command queue number
  * @def_rx_queue - default rx queue number
  * @rx_buf_size: Rx buffer size
- * @bc_table_dword: true if the BC table expects DWORD (as opposed to bytes)
  * @scd_set_active: should the transport configure the SCD for HCMD queue
  * @sw_csum_tx: if true, then the transport will compute the csum of the TXed
  *	frame.
@@ -434,8 +395,6 @@ struct iwl_trans_pcie {
 
 	struct net_device napi_dev;
 
-	struct __percpu iwl_tso_hdr_page *tso_hdr_page;
-
 	/* INT ICT Table */
 	__le32 *ict_tbl;
 	dma_addr_t ict_tbl_dma;
@@ -449,9 +408,7 @@ struct iwl_trans_pcie {
 	struct mutex mutex;
 	u32 inta_mask;
 	u32 scd_base_addr;
-	struct iwl_dma_ptr scd_bc_tbls;
 	struct iwl_dma_ptr kw;
-	struct dma_pool *bc_pool;
 
 	struct iwl_txq *txq_memory;
 
@@ -465,17 +422,12 @@ struct iwl_trans_pcie {
 	wait_queue_head_t wait_command_queue;
 	wait_queue_head_t sx_waitq;
 
-	u8 page_offs, dev_cmd_offs;
-
 	u8 def_rx_queue;
 	u8 n_no_reclaim_cmds;
 	u8 no_reclaim_cmds[MAX_NO_RECLAIM_CMDS];
-	u8 max_tbs;
-	u16 tfd_size;
 	u16 num_rx_bufs;
 
 	enum iwl_amsdu_size rx_buf_size;
-	bool bc_table_dword;
 	bool scd_set_active;
 	bool sw_csum_tx;
 	bool pcie_dbg_dumped_once;
@@ -579,19 +531,7 @@ void iwl_pcie_disable_ict(struct iwl_trans *trans);
 /*****************************************************
 * TX / HCMD
 ******************************************************/
-/*
- * We need this inline in case dma_addr_t is only 32-bits - since the
- * hardware is always 64-bit, the issue can still occur in that case,
- * so use u64 for 'phys' here to force the addition in 64-bit.
- */
-static inline bool iwl_pcie_crosses_4g_boundary(u64 phys, u16 len)
-{
-	return upper_32_bits(phys) != upper_32_bits(phys + len);
-}
-
 int iwl_pcie_tx_init(struct iwl_trans *trans);
-int iwl_pcie_gen2_tx_init(struct iwl_trans *trans, int txq_id,
-			  int queue_size);
 void iwl_pcie_tx_start(struct iwl_trans *trans, u32 scd_base_addr);
 int iwl_pcie_tx_stop(struct iwl_trans *trans);
 void iwl_pcie_tx_free(struct iwl_trans *trans);
@@ -602,14 +542,10 @@ void iwl_trans_pcie_txq_disable(struct iwl_trans *trans, int queue,
 				bool configure_scd);
 void iwl_trans_pcie_txq_set_shared_mode(struct iwl_trans *trans, u32 txq_id,
 					bool shared_mode);
-void iwl_trans_pcie_log_scd_error(struct iwl_trans *trans,
-				  struct iwl_txq *txq);
 int iwl_trans_pcie_tx(struct iwl_trans *trans, struct sk_buff *skb,
 		      struct iwl_device_tx_cmd *dev_cmd, int txq_id);
 void iwl_pcie_txq_check_wrptrs(struct iwl_trans *trans);
 int iwl_trans_pcie_send_hcmd(struct iwl_trans *trans, struct iwl_host_cmd *cmd);
-void iwl_pcie_gen2_txq_inc_wr_ptr(struct iwl_trans *trans,
-				  struct iwl_txq *txq);
 void iwl_pcie_hcmd_complete(struct iwl_trans *trans,
 			    struct iwl_rx_cmd_buffer *rxb);
 void iwl_trans_pcie_reclaim(struct iwl_trans *trans, int txq_id, int ssn,
@@ -617,22 +553,6 @@ void iwl_trans_pcie_reclaim(struct iwl_trans *trans, int txq_id, int ssn,
 void iwl_trans_pcie_set_q_ptrs(struct iwl_trans *trans, int txq_id, int ptr);
 void iwl_trans_pcie_tx_reset(struct iwl_trans *trans);
 
-static inline u16 iwl_pcie_tfd_tb_get_len(struct iwl_trans *trans, void *_tfd,
-					  u8 idx)
-{
-	if (trans->trans_cfg->use_tfh) {
-		struct iwl_tfh_tfd *tfd = _tfd;
-		struct iwl_tfh_tb *tb = &tfd->tbs[idx];
-
-		return le16_to_cpu(tb->tb_len);
-	} else {
-		struct iwl_tfd *tfd = _tfd;
-		struct iwl_tfd_tb *tb = &tfd->tbs[idx];
-
-		return le16_to_cpu(tb->hi_n_len) >> 4;
-	}
-}
-
 /*****************************************************
 * Error handling
 ******************************************************/
@@ -800,22 +720,6 @@ static inline void iwl_enable_fw_load_int_ctx_info(struct iwl_trans *trans)
 	}
 }
 
-static inline u16 iwl_pcie_get_cmd_index(const struct iwl_txq *q, u32 index)
-{
-	return index & (q->n_window - 1);
-}
-
-static inline void *iwl_pcie_get_tfd(struct iwl_trans *trans,
-				     struct iwl_txq *txq, int idx)
-{
-	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-
-	if (trans->trans_cfg->use_tfh)
-		idx = iwl_pcie_get_cmd_index(txq, idx);
-
-	return txq->tfds + trans_pcie->tfd_size * idx;
-}
-
 static inline const char *queue_name(struct device *dev,
 				     struct iwl_trans_pcie *trans_p, int i)
 {
@@ -867,37 +771,6 @@ static inline void iwl_enable_rfkill_int(struct iwl_trans *trans)
 
 void iwl_pcie_handle_rfkill_irq(struct iwl_trans *trans);
 
-static inline void iwl_wake_queue(struct iwl_trans *trans,
-				  struct iwl_txq *txq)
-{
-	if (test_and_clear_bit(txq->id, trans->txqs.queue_stopped)) {
-		IWL_DEBUG_TX_QUEUES(trans, "Wake hwq %d\n", txq->id);
-		iwl_op_mode_queue_not_full(trans->op_mode, txq->id);
-	}
-}
-
-static inline void iwl_stop_queue(struct iwl_trans *trans,
-				  struct iwl_txq *txq)
-{
-	if (!test_and_set_bit(txq->id, trans->txqs.queue_stopped)) {
-		iwl_op_mode_queue_full(trans->op_mode, txq->id);
-		IWL_DEBUG_TX_QUEUES(trans, "Stop hwq %d\n", txq->id);
-	} else
-		IWL_DEBUG_TX_QUEUES(trans, "hwq %d already stopped\n",
-				    txq->id);
-}
-
-static inline bool iwl_queue_used(const struct iwl_txq *q, int i)
-{
-	int index = iwl_pcie_get_cmd_index(q, i);
-	int r = iwl_pcie_get_cmd_index(q, q->read_ptr);
-	int w = iwl_pcie_get_cmd_index(q, q->write_ptr);
-
-	return w >= r ?
-		(index >= r && index < w) :
-		!(index < r && index >= w);
-}
-
 static inline bool iwl_is_rfkill_set(struct iwl_trans *trans)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
@@ -964,23 +837,12 @@ bool iwl_pcie_check_hw_rf_kill(struct iwl_trans *trans);
 void iwl_trans_pcie_handle_stop_rfkill(struct iwl_trans *trans,
 				       bool was_in_rfkill);
 void iwl_pcie_txq_free_tfd(struct iwl_trans *trans, struct iwl_txq *txq);
-int iwl_queue_space(struct iwl_trans *trans, const struct iwl_txq *q);
 void iwl_pcie_apm_stop_master(struct iwl_trans *trans);
 void iwl_pcie_conf_msix_hw(struct iwl_trans_pcie *trans_pcie);
-int iwl_pcie_txq_init(struct iwl_trans *trans, struct iwl_txq *txq,
-		      int slots_num, bool cmd_queue);
-int iwl_pcie_txq_alloc(struct iwl_trans *trans,
-		       struct iwl_txq *txq, int slots_num,  bool cmd_queue);
 int iwl_pcie_alloc_dma_ptr(struct iwl_trans *trans,
 			   struct iwl_dma_ptr *ptr, size_t size);
 void iwl_pcie_free_dma_ptr(struct iwl_trans *trans, struct iwl_dma_ptr *ptr);
 void iwl_pcie_apply_destination(struct iwl_trans *trans);
-void iwl_pcie_free_tso_page(struct iwl_trans_pcie *trans_pcie,
-			    struct sk_buff *skb);
-#ifdef CONFIG_INET
-struct iwl_tso_hdr_page *get_page_hdr(struct iwl_trans *trans, size_t len,
-				      struct sk_buff *skb);
-#endif
 
 /* common functions that are used by gen3 transport */
 void iwl_pcie_alloc_fw_monitor(struct iwl_trans *trans, u8 max_power);
@@ -989,28 +851,10 @@ void iwl_pcie_alloc_fw_monitor(struct iwl_trans *trans, u8 max_power);
 int iwl_trans_pcie_gen2_start_fw(struct iwl_trans *trans,
 				 const struct fw_img *fw, bool run_in_rfkill);
 void iwl_trans_pcie_gen2_fw_alive(struct iwl_trans *trans, u32 scd_addr);
-void iwl_pcie_gen2_txq_free_memory(struct iwl_trans *trans,
-				   struct iwl_txq *txq);
-int iwl_trans_pcie_dyn_txq_alloc_dma(struct iwl_trans *trans,
-				     struct iwl_txq **intxq, int size,
-				     unsigned int timeout);
-int iwl_trans_pcie_txq_alloc_response(struct iwl_trans *trans,
-				      struct iwl_txq *txq,
-				      struct iwl_host_cmd *hcmd);
-int iwl_trans_pcie_dyn_txq_alloc(struct iwl_trans *trans,
-				 __le16 flags, u8 sta_id, u8 tid,
-				 int cmd_id, int size,
-				 unsigned int timeout);
-void iwl_trans_pcie_dyn_txq_free(struct iwl_trans *trans, int queue);
-int iwl_trans_pcie_gen2_tx(struct iwl_trans *trans, struct sk_buff *skb,
-			   struct iwl_device_tx_cmd *dev_cmd, int txq_id);
 int iwl_trans_pcie_gen2_send_hcmd(struct iwl_trans *trans,
 				  struct iwl_host_cmd *cmd);
 void iwl_trans_pcie_gen2_stop_device(struct iwl_trans *trans);
 void _iwl_trans_pcie_gen2_stop_device(struct iwl_trans *trans);
-void iwl_pcie_gen2_txq_unmap(struct iwl_trans *trans, int txq_id);
-void iwl_pcie_gen2_tx_free(struct iwl_trans *trans);
-void iwl_pcie_gen2_tx_stop(struct iwl_trans *trans);
 void iwl_pcie_d3_complete_suspend(struct iwl_trans *trans,
 				  bool test, bool reset);
 #endif /* __iwl_trans_int_pcie_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
index 9463c108aa96..94299f259518 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
@@ -1359,7 +1359,7 @@ static void iwl_pcie_rx_handle_rb(struct iwl_trans *trans,
 
 		sequence = le16_to_cpu(pkt->hdr.sequence);
 		index = SEQ_TO_INDEX(sequence);
-		cmd_index = iwl_pcie_get_cmd_index(txq, index);
+		cmd_index = iwl_txq_get_cmd_index(txq, index);
 
 		if (rxq->id == trans_pcie->def_rx_queue)
 			iwl_op_mode_rx(trans->op_mode, &rxq->napi,
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c
index 97c9e9c87436..91ec9379c061 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c
@@ -162,7 +162,7 @@ void _iwl_trans_pcie_gen2_stop_device(struct iwl_trans *trans)
 	if (test_and_clear_bit(STATUS_DEVICE_ENABLED, &trans->status)) {
 		IWL_DEBUG_INFO(trans,
 			       "DEVICE_ENABLED bit was set and is now cleared\n");
-		iwl_pcie_gen2_tx_stop(trans);
+		iwl_txq_gen2_tx_stop(trans);
 		iwl_pcie_rx_stop(trans);
 	}
 
@@ -245,7 +245,7 @@ static int iwl_pcie_gen2_nic_init(struct iwl_trans *trans)
 		return -ENOMEM;
 
 	/* Allocate or reset and init all Tx and Command queues */
-	if (iwl_pcie_gen2_tx_init(trans, trans->txqs.cmd.q_id, queue_size))
+	if (iwl_txq_gen2_init(trans, trans->txqs.cmd.q_id, queue_size))
 		return -ENOMEM;
 
 	/* enable shadow regs in HW */
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
index e5160d620868..4ee8b5dd2512 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
@@ -1607,11 +1607,15 @@ iwl_pcie_set_interrupt_capa(struct pci_dev *pdev,
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	int max_irqs, num_irqs, i, ret;
 	u16 pci_cmd;
+	u32 max_rx_queues = IWL_MAX_RX_HW_QUEUES;
 
 	if (!cfg_trans->mq_rx_supported)
 		goto enable_msi;
 
-	max_irqs = min_t(u32, num_online_cpus() + 2, IWL_MAX_RX_HW_QUEUES);
+	if (cfg_trans->device_family <= IWL_DEVICE_FAMILY_9000)
+		max_rx_queues = IWL_9000_MAX_RX_HW_QUEUES;
+
+	max_irqs = min_t(u32, num_online_cpus() + 2, max_rx_queues);
 	for (i = 0; i < max_irqs; i++)
 		trans_pcie->msix_entries[i].entry = i;
 
@@ -1907,6 +1911,9 @@ static void iwl_trans_pcie_configure(struct iwl_trans *trans,
 	trans->txqs.cmd.q_id = trans_cfg->cmd_queue;
 	trans->txqs.cmd.fifo = trans_cfg->cmd_fifo;
 	trans->txqs.cmd.wdg_timeout = trans_cfg->cmd_q_wdg_timeout;
+	trans->txqs.page_offs = trans_cfg->cb_data_offs;
+	trans->txqs.dev_cmd_offs = trans_cfg->cb_data_offs + sizeof(void *);
+
 	if (WARN_ON(trans_cfg->n_no_reclaim_cmds > MAX_NO_RECLAIM_CMDS))
 		trans_pcie->n_no_reclaim_cmds = 0;
 	else
@@ -1924,13 +1931,10 @@ static void iwl_trans_pcie_configure(struct iwl_trans *trans,
 	if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210)
 		trans_pcie->supported_dma_mask = DMA_BIT_MASK(11);
 
-	trans_pcie->bc_table_dword = trans_cfg->bc_table_dword;
+	trans->txqs.bc_table_dword = trans_cfg->bc_table_dword;
 	trans_pcie->scd_set_active = trans_cfg->scd_set_active;
 	trans_pcie->sw_csum_tx = trans_cfg->sw_csum_tx;
 
-	trans_pcie->page_offs = trans_cfg->cb_data_offs;
-	trans_pcie->dev_cmd_offs = trans_cfg->cb_data_offs + sizeof(void *);
-
 	trans->command_groups = trans_cfg->command_groups;
 	trans->command_groups_size = trans_cfg->command_groups_size;
 
@@ -1951,7 +1955,7 @@ void iwl_trans_pcie_free(struct iwl_trans *trans)
 	iwl_pcie_synchronize_irqs(trans);
 
 	if (trans->trans_cfg->gen2)
-		iwl_pcie_gen2_tx_free(trans);
+		iwl_txq_gen2_tx_free(trans);
 	else
 		iwl_pcie_tx_free(trans);
 	iwl_pcie_rx_free(trans);
@@ -1975,15 +1979,6 @@ void iwl_trans_pcie_free(struct iwl_trans *trans)
 
 	iwl_pcie_free_fw_monitor(trans);
 
-	for_each_possible_cpu(i) {
-		struct iwl_tso_hdr_page *p =
-			per_cpu_ptr(trans_pcie->tso_hdr_page, i);
-
-		if (p->page)
-			__free_page(p->page);
-	}
-
-	free_percpu(trans_pcie->tso_hdr_page);
 	mutex_destroy(&trans_pcie->mutex);
 	iwl_trans_free(trans);
 }
@@ -2276,36 +2271,6 @@ static void iwl_trans_pcie_block_txq_ptrs(struct iwl_trans *trans, bool block)
 
 #define IWL_FLUSH_WAIT_MS	2000
 
-void iwl_trans_pcie_log_scd_error(struct iwl_trans *trans, struct iwl_txq *txq)
-{
-	u32 txq_id = txq->id;
-	u32 status;
-	bool active;
-	u8 fifo;
-
-	if (trans->trans_cfg->use_tfh) {
-		IWL_ERR(trans, "Queue %d is stuck %d %d\n", txq_id,
-			txq->read_ptr, txq->write_ptr);
-		/* TODO: access new SCD registers and dump them */
-		return;
-	}
-
-	status = iwl_read_prph(trans, SCD_QUEUE_STATUS_BITS(txq_id));
-	fifo = (status >> SCD_QUEUE_STTS_REG_POS_TXF) & 0x7;
-	active = !!(status & BIT(SCD_QUEUE_STTS_REG_POS_ACTIVE));
-
-	IWL_ERR(trans,
-		"Queue %d is %sactive on fifo %d and stuck for %u ms. SW [%d, %d] HW [%d, %d] FH TRB=0x0%x\n",
-		txq_id, active ? "" : "in", fifo,
-		jiffies_to_msecs(txq->wd_timeout),
-		txq->read_ptr, txq->write_ptr,
-		iwl_read_prph(trans, SCD_QUEUE_RDPTR(txq_id)) &
-			(trans->trans_cfg->base_params->max_tfd_queue_size - 1),
-			iwl_read_prph(trans, SCD_QUEUE_WRPTR(txq_id)) &
-			(trans->trans_cfg->base_params->max_tfd_queue_size - 1),
-			iwl_read_direct32(trans, FH_TX_TRB_REG(fifo)));
-}
-
 static int iwl_trans_pcie_rxq_dma_data(struct iwl_trans *trans, int queue,
 				       struct iwl_trans_rxq_dma_data *data)
 {
@@ -2374,7 +2339,7 @@ static int iwl_trans_pcie_wait_txq_empty(struct iwl_trans *trans, int txq_idx)
 	if (txq->read_ptr != txq->write_ptr) {
 		IWL_ERR(trans,
 			"fail to flush all tx fifo queues Q %d\n", txq_idx);
-		iwl_trans_pcie_log_scd_error(trans, txq);
+		iwl_txq_log_scd_error(trans, txq);
 		return -ETIMEDOUT;
 	}
 
@@ -2985,12 +2950,11 @@ static void iwl_trans_pcie_debugfs_cleanup(struct iwl_trans *trans)
 
 static u32 iwl_trans_pcie_get_cmdlen(struct iwl_trans *trans, void *tfd)
 {
-	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	u32 cmdlen = 0;
 	int i;
 
-	for (i = 0; i < trans_pcie->max_tbs; i++)
-		cmdlen += iwl_pcie_tfd_tb_get_len(trans, tfd, i);
+	for (i = 0; i < trans->txqs.tfd.max_tbs; i++)
+		cmdlen += iwl_txq_gen1_tfd_tb_get_len(trans, tfd, i);
 
 	return cmdlen;
 }
@@ -3329,14 +3293,14 @@ static struct iwl_trans_dump_data
 	data = (void *)dump_data->data;
 
 	if (dump_mask & BIT(IWL_FW_ERROR_DUMP_TXCMD) && cmdq) {
-		u16 tfd_size = trans_pcie->tfd_size;
+		u16 tfd_size = trans->txqs.tfd.size;
 
 		data->type = cpu_to_le32(IWL_FW_ERROR_DUMP_TXCMD);
 		txcmd = (void *)data->data;
 		spin_lock_bh(&cmdq->lock);
 		ptr = cmdq->write_ptr;
 		for (i = 0; i < cmdq->n_window; i++) {
-			u8 idx = iwl_pcie_get_cmd_index(cmdq, ptr);
+			u8 idx = iwl_txq_get_cmd_index(cmdq, ptr);
 			u8 tfdidx;
 			u32 caplen, cmdlen;
 
@@ -3359,7 +3323,7 @@ static struct iwl_trans_dump_data
 				txcmd = (void *)((u8 *)txcmd->data + caplen);
 			}
 
-			ptr = iwl_queue_dec_wrap(trans, ptr);
+			ptr = iwl_txq_dec_wrap(trans, ptr);
 		}
 		spin_unlock_bh(&cmdq->lock);
 
@@ -3478,13 +3442,13 @@ static const struct iwl_trans_ops trans_ops_pcie_gen2 = {
 
 	.send_cmd = iwl_trans_pcie_gen2_send_hcmd,
 
-	.tx = iwl_trans_pcie_gen2_tx,
+	.tx = iwl_txq_gen2_tx,
 	.reclaim = iwl_trans_pcie_reclaim,
 
 	.set_q_ptrs = iwl_trans_pcie_set_q_ptrs,
 
-	.txq_alloc = iwl_trans_pcie_dyn_txq_alloc,
-	.txq_free = iwl_trans_pcie_dyn_txq_free,
+	.txq_alloc = iwl_txq_dyn_alloc,
+	.txq_free = iwl_txq_dyn_free,
 	.wait_txq_empty = iwl_trans_pcie_wait_txq_empty,
 	.rxq_dma_data = iwl_trans_pcie_rxq_dma_data,
 #ifdef CONFIG_IWLWIFI_DEBUGFS
@@ -3498,34 +3462,18 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev,
 {
 	struct iwl_trans_pcie *trans_pcie;
 	struct iwl_trans *trans;
-	int ret, addr_size, txcmd_size, txcmd_align;
+	int ret, addr_size;
 	const struct iwl_trans_ops *ops = &trans_ops_pcie_gen2;
 
-	if (!cfg_trans->gen2) {
+	if (!cfg_trans->gen2)
 		ops = &trans_ops_pcie;
-		txcmd_size = sizeof(struct iwl_tx_cmd);
-		txcmd_align = sizeof(void *);
-	} else if (cfg_trans->device_family < IWL_DEVICE_FAMILY_AX210) {
-		txcmd_size = sizeof(struct iwl_tx_cmd_gen2);
-		txcmd_align = 64;
-	} else {
-		txcmd_size = sizeof(struct iwl_tx_cmd_gen3);
-		txcmd_align = 128;
-	}
-
-	txcmd_size += sizeof(struct iwl_cmd_header);
-	txcmd_size += 36; /* biggest possible 802.11 header */
-
-	/* Ensure device TX cmd cannot reach/cross a page boundary in gen2 */
-	if (WARN_ON(cfg_trans->gen2 && txcmd_size >= txcmd_align))
-		return ERR_PTR(-EINVAL);
 
 	ret = pcim_enable_device(pdev);
 	if (ret)
 		return ERR_PTR(ret);
 
 	trans = iwl_trans_alloc(sizeof(struct iwl_trans_pcie), &pdev->dev, ops,
-				txcmd_size, txcmd_align);
+				cfg_trans);
 	if (!trans)
 		return ERR_PTR(-ENOMEM);
 
@@ -3547,11 +3495,6 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev,
 	}
 	INIT_WORK(&trans_pcie->rba.rx_alloc, iwl_pcie_rx_allocator_work);
 
-	trans_pcie->tso_hdr_page = alloc_percpu(struct iwl_tso_hdr_page);
-	if (!trans_pcie->tso_hdr_page) {
-		ret = -ENOMEM;
-		goto out_no_pci;
-	}
 	trans_pcie->debug_rfkill = -1;
 
 	if (!cfg_trans->base_params->pcie_l1_allowed) {
@@ -3567,19 +3510,9 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev,
 
 	trans_pcie->def_rx_queue = 0;
 
-	if (cfg_trans->use_tfh) {
-		addr_size = 64;
-		trans_pcie->max_tbs = IWL_TFH_NUM_TBS;
-		trans_pcie->tfd_size = sizeof(struct iwl_tfh_tfd);
-	} else {
-		addr_size = 36;
-		trans_pcie->max_tbs = IWL_NUM_OF_TBS;
-		trans_pcie->tfd_size = sizeof(struct iwl_tfd);
-	}
-	trans->max_skb_frags = IWL_PCIE_MAX_FRAGS(trans_pcie);
-
 	pci_set_master(pdev);
 
+	addr_size = trans->txqs.tfd.addr_size;
 	ret = pci_set_dma_mask(pdev, DMA_BIT_MASK(addr_size));
 	if (!ret)
 		ret = pci_set_consistent_dma_mask(pdev,
@@ -3661,24 +3594,6 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev,
 
 	init_waitqueue_head(&trans_pcie->sx_waitq);
 
-	/*
-	 * For gen2 devices, we use a single allocation for each byte-count
-	 * table, but they're pretty small (1k) so use a DMA pool that we
-	 * allocate here.
-	 */
-	if (cfg_trans->gen2) {
-		size_t bc_tbl_size;
-
-		if (cfg_trans->device_family >= IWL_DEVICE_FAMILY_AX210)
-			bc_tbl_size = sizeof(struct iwl_gen3_bc_tbl);
-		else
-			bc_tbl_size = sizeof(struct iwlagn_scd_bc_tbl);
-
-		trans_pcie->bc_pool = dmam_pool_create("iwlwifi:bc", &pdev->dev,
-						       bc_tbl_size, 256, 0);
-		if (!trans_pcie->bc_pool)
-			goto out_no_pci;
-	}
 
 	if (trans_pcie->msix_enabled) {
 		ret = iwl_pcie_init_msix_handler(pdev, trans_pcie);
@@ -3712,7 +3627,6 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev,
 out_free_ict:
 	iwl_pcie_free_ict(trans);
 out_no_pci:
-	free_percpu(trans_pcie->tso_hdr_page);
 	destroy_workqueue(trans_pcie->rba.alloc_wq);
 out_free_trans:
 	iwl_trans_free(trans);
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
index 606bef2ecc7b..baa83a0b8593 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
@@ -58,751 +58,7 @@
 #include "iwl-io.h"
 #include "internal.h"
 #include "fw/api/tx.h"
-
- /*
- * iwl_pcie_gen2_tx_stop - Stop all Tx DMA channels
- */
-void iwl_pcie_gen2_tx_stop(struct iwl_trans *trans)
-{
-	int txq_id;
-
-	/*
-	 * This function can be called before the op_mode disabled the
-	 * queues. This happens when we have an rfkill interrupt.
-	 * Since we stop Tx altogether - mark the queues as stopped.
-	 */
-	memset(trans->txqs.queue_stopped, 0,
-	       sizeof(trans->txqs.queue_stopped));
-	memset(trans->txqs.queue_used, 0, sizeof(trans->txqs.queue_used));
-
-	/* Unmap DMA from host system and free skb's */
-	for (txq_id = 0; txq_id < ARRAY_SIZE(trans->txqs.txq); txq_id++) {
-		if (!trans->txqs.txq[txq_id])
-			continue;
-		iwl_pcie_gen2_txq_unmap(trans, txq_id);
-	}
-}
-
-/*
- * iwl_pcie_txq_update_byte_tbl - Set up entry in Tx byte-count array
- */
-static void iwl_pcie_gen2_update_byte_tbl(struct iwl_trans_pcie *trans_pcie,
-					  struct iwl_txq *txq, u16 byte_cnt,
-					  int num_tbs)
-{
-	struct iwl_trans *trans = iwl_trans_pcie_get_trans(trans_pcie);
-	int idx = iwl_pcie_get_cmd_index(txq, txq->write_ptr);
-	u8 filled_tfd_size, num_fetch_chunks;
-	u16 len = byte_cnt;
-	__le16 bc_ent;
-
-	if (WARN(idx >= txq->n_window, "%d >= %d\n", idx, txq->n_window))
-		return;
-
-	filled_tfd_size = offsetof(struct iwl_tfh_tfd, tbs) +
-			  num_tbs * sizeof(struct iwl_tfh_tb);
-	/*
-	 * filled_tfd_size contains the number of filled bytes in the TFD.
-	 * Dividing it by 64 will give the number of chunks to fetch
-	 * to SRAM- 0 for one chunk, 1 for 2 and so on.
-	 * If, for example, TFD contains only 3 TBs then 32 bytes
-	 * of the TFD are used, and only one chunk of 64 bytes should
-	 * be fetched
-	 */
-	num_fetch_chunks = DIV_ROUND_UP(filled_tfd_size, 64) - 1;
-
-	if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210) {
-		struct iwl_gen3_bc_tbl *scd_bc_tbl_gen3 = txq->bc_tbl.addr;
-
-		/* Starting from AX210, the HW expects bytes */
-		WARN_ON(trans_pcie->bc_table_dword);
-		WARN_ON(len > 0x3FFF);
-		bc_ent = cpu_to_le16(len | (num_fetch_chunks << 14));
-		scd_bc_tbl_gen3->tfd_offset[idx] = bc_ent;
-	} else {
-		struct iwlagn_scd_bc_tbl *scd_bc_tbl = txq->bc_tbl.addr;
-
-		/* Before AX210, the HW expects DW */
-		WARN_ON(!trans_pcie->bc_table_dword);
-		len = DIV_ROUND_UP(len, 4);
-		WARN_ON(len > 0xFFF);
-		bc_ent = cpu_to_le16(len | (num_fetch_chunks << 12));
-		scd_bc_tbl->tfd_offset[idx] = bc_ent;
-	}
-}
-
-/*
- * iwl_pcie_gen2_txq_inc_wr_ptr - Send new write index to hardware
- */
-void iwl_pcie_gen2_txq_inc_wr_ptr(struct iwl_trans *trans,
-				  struct iwl_txq *txq)
-{
-	lockdep_assert_held(&txq->lock);
-
-	IWL_DEBUG_TX(trans, "Q:%d WR: 0x%x\n", txq->id, txq->write_ptr);
-
-	/*
-	 * if not in power-save mode, uCode will never sleep when we're
-	 * trying to tx (during RFKILL, we're not trying to tx).
-	 */
-	iwl_write32(trans, HBUS_TARG_WRPTR, txq->write_ptr | (txq->id << 16));
-}
-
-static u8 iwl_pcie_gen2_get_num_tbs(struct iwl_trans *trans,
-				    struct iwl_tfh_tfd *tfd)
-{
-	return le16_to_cpu(tfd->num_tbs) & 0x1f;
-}
-
-static void iwl_pcie_gen2_tfd_unmap(struct iwl_trans *trans,
-				    struct iwl_cmd_meta *meta,
-				    struct iwl_tfh_tfd *tfd)
-{
-	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-	int i, num_tbs;
-
-	/* Sanity check on number of chunks */
-	num_tbs = iwl_pcie_gen2_get_num_tbs(trans, tfd);
-
-	if (num_tbs > trans_pcie->max_tbs) {
-		IWL_ERR(trans, "Too many chunks: %i\n", num_tbs);
-		return;
-	}
-
-	/* first TB is never freed - it's the bidirectional DMA data */
-	for (i = 1; i < num_tbs; i++) {
-		if (meta->tbs & BIT(i))
-			dma_unmap_page(trans->dev,
-				       le64_to_cpu(tfd->tbs[i].addr),
-				       le16_to_cpu(tfd->tbs[i].tb_len),
-				       DMA_TO_DEVICE);
-		else
-			dma_unmap_single(trans->dev,
-					 le64_to_cpu(tfd->tbs[i].addr),
-					 le16_to_cpu(tfd->tbs[i].tb_len),
-					 DMA_TO_DEVICE);
-	}
-
-	tfd->num_tbs = 0;
-}
-
-static void iwl_pcie_gen2_free_tfd(struct iwl_trans *trans, struct iwl_txq *txq)
-{
-	/* rd_ptr is bounded by TFD_QUEUE_SIZE_MAX and
-	 * idx is bounded by n_window
-	 */
-	int idx = iwl_pcie_get_cmd_index(txq, txq->read_ptr);
-
-	lockdep_assert_held(&txq->lock);
-
-	iwl_pcie_gen2_tfd_unmap(trans, &txq->entries[idx].meta,
-				iwl_pcie_get_tfd(trans, txq, idx));
-
-	/* free SKB */
-	if (txq->entries) {
-		struct sk_buff *skb;
-
-		skb = txq->entries[idx].skb;
-
-		/* Can be called from irqs-disabled context
-		 * If skb is not NULL, it means that the whole queue is being
-		 * freed and that the queue is not empty - free the skb
-		 */
-		if (skb) {
-			iwl_op_mode_free_skb(trans->op_mode, skb);
-			txq->entries[idx].skb = NULL;
-		}
-	}
-}
-
-static int iwl_pcie_gen2_set_tb(struct iwl_trans *trans,
-				struct iwl_tfh_tfd *tfd, dma_addr_t addr,
-				u16 len)
-{
-	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-	int idx = iwl_pcie_gen2_get_num_tbs(trans, tfd);
-	struct iwl_tfh_tb *tb;
-
-	/*
-	 * Only WARN here so we know about the issue, but we mess up our
-	 * unmap path because not every place currently checks for errors
-	 * returned from this function - it can only return an error if
-	 * there's no more space, and so when we know there is enough we
-	 * don't always check ...
-	 */
-	WARN(iwl_pcie_crosses_4g_boundary(addr, len),
-	     "possible DMA problem with iova:0x%llx, len:%d\n",
-	     (unsigned long long)addr, len);
-
-	if (WARN_ON(idx >= IWL_TFH_NUM_TBS))
-		return -EINVAL;
-	tb = &tfd->tbs[idx];
-
-	/* Each TFD can point to a maximum max_tbs Tx buffers */
-	if (le16_to_cpu(tfd->num_tbs) >= trans_pcie->max_tbs) {
-		IWL_ERR(trans, "Error can not send more than %d chunks\n",
-			trans_pcie->max_tbs);
-		return -EINVAL;
-	}
-
-	put_unaligned_le64(addr, &tb->addr);
-	tb->tb_len = cpu_to_le16(len);
-
-	tfd->num_tbs = cpu_to_le16(idx + 1);
-
-	return idx;
-}
-
-static struct page *get_workaround_page(struct iwl_trans *trans,
-					struct sk_buff *skb)
-{
-	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-	struct page **page_ptr;
-	struct page *ret;
-
-	page_ptr = (void *)((u8 *)skb->cb + trans_pcie->page_offs);
-
-	ret = alloc_page(GFP_ATOMIC);
-	if (!ret)
-		return NULL;
-
-	/* set the chaining pointer to the previous page if there */
-	*(void **)(page_address(ret) + PAGE_SIZE - sizeof(void *)) = *page_ptr;
-	*page_ptr = ret;
-
-	return ret;
-}
-
-/*
- * Add a TB and if needed apply the FH HW bug workaround;
- * meta != NULL indicates that it's a page mapping and we
- * need to dma_unmap_page() and set the meta->tbs bit in
- * this case.
- */
-static int iwl_pcie_gen2_set_tb_with_wa(struct iwl_trans *trans,
-					struct sk_buff *skb,
-					struct iwl_tfh_tfd *tfd,
-					dma_addr_t phys, void *virt,
-					u16 len, struct iwl_cmd_meta *meta)
-{
-	dma_addr_t oldphys = phys;
-	struct page *page;
-	int ret;
-
-	if (unlikely(dma_mapping_error(trans->dev, phys)))
-		return -ENOMEM;
-
-	if (likely(!iwl_pcie_crosses_4g_boundary(phys, len))) {
-		ret = iwl_pcie_gen2_set_tb(trans, tfd, phys, len);
-
-		if (ret < 0)
-			goto unmap;
-
-		if (meta)
-			meta->tbs |= BIT(ret);
-
-		ret = 0;
-		goto trace;
-	}
-
-	/*
-	 * Work around a hardware bug. If (as expressed in the
-	 * condition above) the TB ends on a 32-bit boundary,
-	 * then the next TB may be accessed with the wrong
-	 * address.
-	 * To work around it, copy the data elsewhere and make
-	 * a new mapping for it so the device will not fail.
-	 */
-
-	if (WARN_ON(len > PAGE_SIZE - sizeof(void *))) {
-		ret = -ENOBUFS;
-		goto unmap;
-	}
-
-	page = get_workaround_page(trans, skb);
-	if (!page) {
-		ret = -ENOMEM;
-		goto unmap;
-	}
-
-	memcpy(page_address(page), virt, len);
-
-	phys = dma_map_single(trans->dev, page_address(page), len,
-			      DMA_TO_DEVICE);
-	if (unlikely(dma_mapping_error(trans->dev, phys)))
-		return -ENOMEM;
-	ret = iwl_pcie_gen2_set_tb(trans, tfd, phys, len);
-	if (ret < 0) {
-		/* unmap the new allocation as single */
-		oldphys = phys;
-		meta = NULL;
-		goto unmap;
-	}
-	IWL_WARN(trans,
-		 "TB bug workaround: copied %d bytes from 0x%llx to 0x%llx\n",
-		 len, (unsigned long long)oldphys, (unsigned long long)phys);
-
-	ret = 0;
-unmap:
-	if (meta)
-		dma_unmap_page(trans->dev, oldphys, len, DMA_TO_DEVICE);
-	else
-		dma_unmap_single(trans->dev, oldphys, len, DMA_TO_DEVICE);
-trace:
-	trace_iwlwifi_dev_tx_tb(trans->dev, skb, virt, phys, len);
-
-	return ret;
-}
-
-static int iwl_pcie_gen2_build_amsdu(struct iwl_trans *trans,
-				     struct sk_buff *skb,
-				     struct iwl_tfh_tfd *tfd, int start_len,
-				     u8 hdr_len,
-				     struct iwl_device_tx_cmd *dev_cmd)
-{
-#ifdef CONFIG_INET
-	struct iwl_tx_cmd_gen2 *tx_cmd = (void *)dev_cmd->payload;
-	struct ieee80211_hdr *hdr = (void *)skb->data;
-	unsigned int snap_ip_tcp_hdrlen, ip_hdrlen, total_len, hdr_room;
-	unsigned int mss = skb_shinfo(skb)->gso_size;
-	u16 length, amsdu_pad;
-	u8 *start_hdr;
-	struct iwl_tso_hdr_page *hdr_page;
-	struct tso_t tso;
-
-	trace_iwlwifi_dev_tx(trans->dev, skb, tfd, sizeof(*tfd),
-			     &dev_cmd->hdr, start_len, 0);
-
-	ip_hdrlen = skb_transport_header(skb) - skb_network_header(skb);
-	snap_ip_tcp_hdrlen = 8 + ip_hdrlen + tcp_hdrlen(skb);
-	total_len = skb->len - snap_ip_tcp_hdrlen - hdr_len;
-	amsdu_pad = 0;
-
-	/* total amount of header we may need for this A-MSDU */
-	hdr_room = DIV_ROUND_UP(total_len, mss) *
-		(3 + snap_ip_tcp_hdrlen + sizeof(struct ethhdr));
-
-	/* Our device supports 9 segments at most, it will fit in 1 page */
-	hdr_page = get_page_hdr(trans, hdr_room, skb);
-	if (!hdr_page)
-		return -ENOMEM;
-
-	start_hdr = hdr_page->pos;
-
-	/*
-	 * Pull the ieee80211 header to be able to use TSO core,
-	 * we will restore it for the tx_status flow.
-	 */
-	skb_pull(skb, hdr_len);
-
-	/*
-	 * Remove the length of all the headers that we don't actually
-	 * have in the MPDU by themselves, but that we duplicate into
-	 * all the different MSDUs inside the A-MSDU.
-	 */
-	le16_add_cpu(&tx_cmd->len, -snap_ip_tcp_hdrlen);
-
-	tso_start(skb, &tso);
-
-	while (total_len) {
-		/* this is the data left for this subframe */
-		unsigned int data_left = min_t(unsigned int, mss, total_len);
-		struct sk_buff *csum_skb = NULL;
-		unsigned int tb_len;
-		dma_addr_t tb_phys;
-		u8 *subf_hdrs_start = hdr_page->pos;
-
-		total_len -= data_left;
-
-		memset(hdr_page->pos, 0, amsdu_pad);
-		hdr_page->pos += amsdu_pad;
-		amsdu_pad = (4 - (sizeof(struct ethhdr) + snap_ip_tcp_hdrlen +
-				  data_left)) & 0x3;
-		ether_addr_copy(hdr_page->pos, ieee80211_get_DA(hdr));
-		hdr_page->pos += ETH_ALEN;
-		ether_addr_copy(hdr_page->pos, ieee80211_get_SA(hdr));
-		hdr_page->pos += ETH_ALEN;
-
-		length = snap_ip_tcp_hdrlen + data_left;
-		*((__be16 *)hdr_page->pos) = cpu_to_be16(length);
-		hdr_page->pos += sizeof(length);
-
-		/*
-		 * This will copy the SNAP as well which will be considered
-		 * as MAC header.
-		 */
-		tso_build_hdr(skb, hdr_page->pos, &tso, data_left, !total_len);
-
-		hdr_page->pos += snap_ip_tcp_hdrlen;
-
-		tb_len = hdr_page->pos - start_hdr;
-		tb_phys = dma_map_single(trans->dev, start_hdr,
-					 tb_len, DMA_TO_DEVICE);
-		if (unlikely(dma_mapping_error(trans->dev, tb_phys))) {
-			dev_kfree_skb(csum_skb);
-			goto out_err;
-		}
-		/*
-		 * No need for _with_wa, this is from the TSO page and
-		 * we leave some space at the end of it so can't hit
-		 * the buggy scenario.
-		 */
-		iwl_pcie_gen2_set_tb(trans, tfd, tb_phys, tb_len);
-		trace_iwlwifi_dev_tx_tb(trans->dev, skb, start_hdr,
-					tb_phys, tb_len);
-		/* add this subframe's headers' length to the tx_cmd */
-		le16_add_cpu(&tx_cmd->len, hdr_page->pos - subf_hdrs_start);
-
-		/* prepare the start_hdr for the next subframe */
-		start_hdr = hdr_page->pos;
-
-		/* put the payload */
-		while (data_left) {
-			int ret;
-
-			tb_len = min_t(unsigned int, tso.size, data_left);
-			tb_phys = dma_map_single(trans->dev, tso.data,
-						 tb_len, DMA_TO_DEVICE);
-			ret = iwl_pcie_gen2_set_tb_with_wa(trans, skb, tfd,
-							   tb_phys, tso.data,
-							   tb_len, NULL);
-			if (ret) {
-				dev_kfree_skb(csum_skb);
-				goto out_err;
-			}
-
-			data_left -= tb_len;
-			tso_build_data(skb, &tso, tb_len);
-		}
-	}
-
-	/* re -add the WiFi header */
-	skb_push(skb, hdr_len);
-
-	return 0;
-
-out_err:
-#endif
-	return -EINVAL;
-}
-
-static struct
-iwl_tfh_tfd *iwl_pcie_gen2_build_tx_amsdu(struct iwl_trans *trans,
-					  struct iwl_txq *txq,
-					  struct iwl_device_tx_cmd *dev_cmd,
-					  struct sk_buff *skb,
-					  struct iwl_cmd_meta *out_meta,
-					  int hdr_len,
-					  int tx_cmd_len)
-{
-	int idx = iwl_pcie_get_cmd_index(txq, txq->write_ptr);
-	struct iwl_tfh_tfd *tfd = iwl_pcie_get_tfd(trans, txq, idx);
-	dma_addr_t tb_phys;
-	int len;
-	void *tb1_addr;
-
-	tb_phys = iwl_pcie_get_first_tb_dma(txq, idx);
-
-	/*
-	 * No need for _with_wa, the first TB allocation is aligned up
-	 * to a 64-byte boundary and thus can't be at the end or cross
-	 * a page boundary (much less a 2^32 boundary).
-	 */
-	iwl_pcie_gen2_set_tb(trans, tfd, tb_phys, IWL_FIRST_TB_SIZE);
-
-	/*
-	 * The second TB (tb1) points to the remainder of the TX command
-	 * and the 802.11 header - dword aligned size
-	 * (This calculation modifies the TX command, so do it before the
-	 * setup of the first TB)
-	 */
-	len = tx_cmd_len + sizeof(struct iwl_cmd_header) + hdr_len -
-	      IWL_FIRST_TB_SIZE;
-
-	/* do not align A-MSDU to dword as the subframe header aligns it */
-
-	/* map the data for TB1 */
-	tb1_addr = ((u8 *)&dev_cmd->hdr) + IWL_FIRST_TB_SIZE;
-	tb_phys = dma_map_single(trans->dev, tb1_addr, len, DMA_TO_DEVICE);
-	if (unlikely(dma_mapping_error(trans->dev, tb_phys)))
-		goto out_err;
-	/*
-	 * No need for _with_wa(), we ensure (via alignment) that the data
-	 * here can never cross or end at a page boundary.
-	 */
-	iwl_pcie_gen2_set_tb(trans, tfd, tb_phys, len);
-
-	if (iwl_pcie_gen2_build_amsdu(trans, skb, tfd,
-				      len + IWL_FIRST_TB_SIZE,
-				      hdr_len, dev_cmd))
-		goto out_err;
-
-	/* building the A-MSDU might have changed this data, memcpy it now */
-	memcpy(&txq->first_tb_bufs[idx], dev_cmd, IWL_FIRST_TB_SIZE);
-	return tfd;
-
-out_err:
-	iwl_pcie_gen2_tfd_unmap(trans, out_meta, tfd);
-	return NULL;
-}
-
-static int iwl_pcie_gen2_tx_add_frags(struct iwl_trans *trans,
-				      struct sk_buff *skb,
-				      struct iwl_tfh_tfd *tfd,
-				      struct iwl_cmd_meta *out_meta)
-{
-	int i;
-
-	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
-		const skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
-		dma_addr_t tb_phys;
-		unsigned int fragsz = skb_frag_size(frag);
-		int ret;
-
-		if (!fragsz)
-			continue;
-
-		tb_phys = skb_frag_dma_map(trans->dev, frag, 0,
-					   fragsz, DMA_TO_DEVICE);
-		ret = iwl_pcie_gen2_set_tb_with_wa(trans, skb, tfd, tb_phys,
-						   skb_frag_address(frag),
-						   fragsz, out_meta);
-		if (ret)
-			return ret;
-	}
-
-	return 0;
-}
-
-static struct
-iwl_tfh_tfd *iwl_pcie_gen2_build_tx(struct iwl_trans *trans,
-				    struct iwl_txq *txq,
-				    struct iwl_device_tx_cmd *dev_cmd,
-				    struct sk_buff *skb,
-				    struct iwl_cmd_meta *out_meta,
-				    int hdr_len,
-				    int tx_cmd_len,
-				    bool pad)
-{
-	int idx = iwl_pcie_get_cmd_index(txq, txq->write_ptr);
-	struct iwl_tfh_tfd *tfd = iwl_pcie_get_tfd(trans, txq, idx);
-	dma_addr_t tb_phys;
-	int len, tb1_len, tb2_len;
-	void *tb1_addr;
-	struct sk_buff *frag;
-
-	tb_phys = iwl_pcie_get_first_tb_dma(txq, idx);
-
-	/* The first TB points to bi-directional DMA data */
-	memcpy(&txq->first_tb_bufs[idx], dev_cmd, IWL_FIRST_TB_SIZE);
-
-	/*
-	 * No need for _with_wa, the first TB allocation is aligned up
-	 * to a 64-byte boundary and thus can't be at the end or cross
-	 * a page boundary (much less a 2^32 boundary).
-	 */
-	iwl_pcie_gen2_set_tb(trans, tfd, tb_phys, IWL_FIRST_TB_SIZE);
-
-	/*
-	 * The second TB (tb1) points to the remainder of the TX command
-	 * and the 802.11 header - dword aligned size
-	 * (This calculation modifies the TX command, so do it before the
-	 * setup of the first TB)
-	 */
-	len = tx_cmd_len + sizeof(struct iwl_cmd_header) + hdr_len -
-	      IWL_FIRST_TB_SIZE;
-
-	if (pad)
-		tb1_len = ALIGN(len, 4);
-	else
-		tb1_len = len;
-
-	/* map the data for TB1 */
-	tb1_addr = ((u8 *)&dev_cmd->hdr) + IWL_FIRST_TB_SIZE;
-	tb_phys = dma_map_single(trans->dev, tb1_addr, tb1_len, DMA_TO_DEVICE);
-	if (unlikely(dma_mapping_error(trans->dev, tb_phys)))
-		goto out_err;
-	/*
-	 * No need for _with_wa(), we ensure (via alignment) that the data
-	 * here can never cross or end at a page boundary.
-	 */
-	iwl_pcie_gen2_set_tb(trans, tfd, tb_phys, tb1_len);
-	trace_iwlwifi_dev_tx(trans->dev, skb, tfd, sizeof(*tfd), &dev_cmd->hdr,
-			     IWL_FIRST_TB_SIZE + tb1_len, hdr_len);
-
-	/* set up TFD's third entry to point to remainder of skb's head */
-	tb2_len = skb_headlen(skb) - hdr_len;
-
-	if (tb2_len > 0) {
-		int ret;
-
-		tb_phys = dma_map_single(trans->dev, skb->data + hdr_len,
-					 tb2_len, DMA_TO_DEVICE);
-		ret = iwl_pcie_gen2_set_tb_with_wa(trans, skb, tfd, tb_phys,
-						   skb->data + hdr_len, tb2_len,
-						   NULL);
-		if (ret)
-			goto out_err;
-	}
-
-	if (iwl_pcie_gen2_tx_add_frags(trans, skb, tfd, out_meta))
-		goto out_err;
-
-	skb_walk_frags(skb, frag) {
-		int ret;
-
-		tb_phys = dma_map_single(trans->dev, frag->data,
-					 skb_headlen(frag), DMA_TO_DEVICE);
-		ret = iwl_pcie_gen2_set_tb_with_wa(trans, skb, tfd, tb_phys,
-						   frag->data,
-						   skb_headlen(frag), NULL);
-		if (ret)
-			goto out_err;
-		if (iwl_pcie_gen2_tx_add_frags(trans, frag, tfd, out_meta))
-			goto out_err;
-	}
-
-	return tfd;
-
-out_err:
-	iwl_pcie_gen2_tfd_unmap(trans, out_meta, tfd);
-	return NULL;
-}
-
-static
-struct iwl_tfh_tfd *iwl_pcie_gen2_build_tfd(struct iwl_trans *trans,
-					    struct iwl_txq *txq,
-					    struct iwl_device_tx_cmd *dev_cmd,
-					    struct sk_buff *skb,
-					    struct iwl_cmd_meta *out_meta)
-{
-	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
-	int idx = iwl_pcie_get_cmd_index(txq, txq->write_ptr);
-	struct iwl_tfh_tfd *tfd = iwl_pcie_get_tfd(trans, txq, idx);
-	int len, hdr_len;
-	bool amsdu;
-
-	/* There must be data left over for TB1 or this code must be changed */
-	BUILD_BUG_ON(sizeof(struct iwl_tx_cmd_gen2) < IWL_FIRST_TB_SIZE);
-
-	memset(tfd, 0, sizeof(*tfd));
-
-	if (trans->trans_cfg->device_family < IWL_DEVICE_FAMILY_AX210)
-		len = sizeof(struct iwl_tx_cmd_gen2);
-	else
-		len = sizeof(struct iwl_tx_cmd_gen3);
-
-	amsdu = ieee80211_is_data_qos(hdr->frame_control) &&
-			(*ieee80211_get_qos_ctl(hdr) &
-			 IEEE80211_QOS_CTL_A_MSDU_PRESENT);
-
-	hdr_len = ieee80211_hdrlen(hdr->frame_control);
-
-	/*
-	 * Only build A-MSDUs here if doing so by GSO, otherwise it may be
-	 * an A-MSDU for other reasons, e.g. NAN or an A-MSDU having been
-	 * built in the higher layers already.
-	 */
-	if (amsdu && skb_shinfo(skb)->gso_size)
-		return iwl_pcie_gen2_build_tx_amsdu(trans, txq, dev_cmd, skb,
-						    out_meta, hdr_len, len);
-
-	return iwl_pcie_gen2_build_tx(trans, txq, dev_cmd, skb, out_meta,
-				      hdr_len, len, !amsdu);
-}
-
-int iwl_trans_pcie_gen2_tx(struct iwl_trans *trans, struct sk_buff *skb,
-			   struct iwl_device_tx_cmd *dev_cmd, int txq_id)
-{
-	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-	struct iwl_cmd_meta *out_meta;
-	struct iwl_txq *txq = trans->txqs.txq[txq_id];
-	u16 cmd_len;
-	int idx;
-	void *tfd;
-
-	if (WARN_ONCE(txq_id >= IWL_MAX_TVQM_QUEUES,
-		      "queue %d out of range", txq_id))
-		return -EINVAL;
-
-	if (WARN_ONCE(!test_bit(txq_id, trans->txqs.queue_used),
-		      "TX on unused queue %d\n", txq_id))
-		return -EINVAL;
-
-	if (skb_is_nonlinear(skb) &&
-	    skb_shinfo(skb)->nr_frags > IWL_PCIE_MAX_FRAGS(trans_pcie) &&
-	    __skb_linearize(skb))
-		return -ENOMEM;
-
-	spin_lock(&txq->lock);
-
-	if (iwl_queue_space(trans, txq) < txq->high_mark) {
-		iwl_stop_queue(trans, txq);
-
-		/* don't put the packet on the ring, if there is no room */
-		if (unlikely(iwl_queue_space(trans, txq) < 3)) {
-			struct iwl_device_tx_cmd **dev_cmd_ptr;
-
-			dev_cmd_ptr = (void *)((u8 *)skb->cb +
-					       trans_pcie->dev_cmd_offs);
-
-			*dev_cmd_ptr = dev_cmd;
-			__skb_queue_tail(&txq->overflow_q, skb);
-			spin_unlock(&txq->lock);
-			return 0;
-		}
-	}
-
-	idx = iwl_pcie_get_cmd_index(txq, txq->write_ptr);
-
-	/* Set up driver data for this TFD */
-	txq->entries[idx].skb = skb;
-	txq->entries[idx].cmd = dev_cmd;
-
-	dev_cmd->hdr.sequence =
-		cpu_to_le16((u16)(QUEUE_TO_SEQ(txq_id) |
-			    INDEX_TO_SEQ(idx)));
-
-	/* Set up first empty entry in queue's array of Tx/cmd buffers */
-	out_meta = &txq->entries[idx].meta;
-	out_meta->flags = 0;
-
-	tfd = iwl_pcie_gen2_build_tfd(trans, txq, dev_cmd, skb, out_meta);
-	if (!tfd) {
-		spin_unlock(&txq->lock);
-		return -1;
-	}
-
-	if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210) {
-		struct iwl_tx_cmd_gen3 *tx_cmd_gen3 =
-			(void *)dev_cmd->payload;
-
-		cmd_len = le16_to_cpu(tx_cmd_gen3->len);
-	} else {
-		struct iwl_tx_cmd_gen2 *tx_cmd_gen2 =
-			(void *)dev_cmd->payload;
-
-		cmd_len = le16_to_cpu(tx_cmd_gen2->len);
-	}
-
-	/* Set up entry for this TFD in Tx byte-count array */
-	iwl_pcie_gen2_update_byte_tbl(trans_pcie, txq, cmd_len,
-				      iwl_pcie_gen2_get_num_tbs(trans, tfd));
-
-	/* start timer if queue currently empty */
-	if (txq->read_ptr == txq->write_ptr && txq->wd_timeout)
-		mod_timer(&txq->stuck_timer, jiffies + txq->wd_timeout);
-
-	/* Tell device the write index *just past* this latest filled TFD */
-	txq->write_ptr = iwl_queue_inc_wrap(trans, txq->write_ptr);
-	iwl_pcie_gen2_txq_inc_wr_ptr(trans, txq);
-	/*
-	 * At this point the frame is "transmitted" successfully
-	 * and we will get a TX status notification eventually.
-	 */
-	spin_unlock(&txq->lock);
-	return 0;
-}
+#include "queue/tx.h"
 
 /*************** HOST COMMAND QUEUE FUNCTIONS   *****/
 
@@ -902,11 +158,11 @@ static int iwl_pcie_gen2_enqueue_hcmd(struct iwl_trans *trans,
 
 	spin_lock_bh(&txq->lock);
 
-	idx = iwl_pcie_get_cmd_index(txq, txq->write_ptr);
-	tfd = iwl_pcie_get_tfd(trans, txq, txq->write_ptr);
+	idx = iwl_txq_get_cmd_index(txq, txq->write_ptr);
+	tfd = iwl_txq_get_tfd(trans, txq, txq->write_ptr);
 	memset(tfd, 0, sizeof(*tfd));
 
-	if (iwl_queue_space(trans, txq) < ((cmd->flags & CMD_ASYNC) ? 2 : 1)) {
+	if (iwl_txq_space(trans, txq) < ((cmd->flags & CMD_ASYNC) ? 2 : 1)) {
 		spin_unlock_bh(&txq->lock);
 
 		IWL_ERR(trans, "No space in command queue\n");
@@ -984,8 +240,8 @@ static int iwl_pcie_gen2_enqueue_hcmd(struct iwl_trans *trans,
 	/* start the TFD with the minimum copy bytes */
 	tb0_size = min_t(int, copy_size, IWL_FIRST_TB_SIZE);
 	memcpy(&txq->first_tb_bufs[idx], out_cmd, tb0_size);
-	iwl_pcie_gen2_set_tb(trans, tfd, iwl_pcie_get_first_tb_dma(txq, idx),
-			     tb0_size);
+	iwl_txq_gen2_set_tb(trans, tfd, iwl_txq_get_first_tb_dma(txq, idx),
+			    tb0_size);
 
 	/* map first command fragment, if any remains */
 	if (copy_size > tb0_size) {
@@ -995,11 +251,11 @@ static int iwl_pcie_gen2_enqueue_hcmd(struct iwl_trans *trans,
 					   DMA_TO_DEVICE);
 		if (dma_mapping_error(trans->dev, phys_addr)) {
 			idx = -ENOMEM;
-			iwl_pcie_gen2_tfd_unmap(trans, out_meta, tfd);
+			iwl_txq_gen2_tfd_unmap(trans, out_meta, tfd);
 			goto out;
 		}
-		iwl_pcie_gen2_set_tb(trans, tfd, phys_addr,
-				     copy_size - tb0_size);
+		iwl_txq_gen2_set_tb(trans, tfd, phys_addr,
+				    copy_size - tb0_size);
 	}
 
 	/* map the remaining (adjusted) nocopy/dup fragments */
@@ -1017,10 +273,10 @@ static int iwl_pcie_gen2_enqueue_hcmd(struct iwl_trans *trans,
 					   cmdlen[i], DMA_TO_DEVICE);
 		if (dma_mapping_error(trans->dev, phys_addr)) {
 			idx = -ENOMEM;
-			iwl_pcie_gen2_tfd_unmap(trans, out_meta, tfd);
+			iwl_txq_gen2_tfd_unmap(trans, out_meta, tfd);
 			goto out;
 		}
-		iwl_pcie_gen2_set_tb(trans, tfd, phys_addr, cmdlen[i]);
+		iwl_txq_gen2_set_tb(trans, tfd, phys_addr, cmdlen[i]);
 	}
 
 	BUILD_BUG_ON(IWL_TFH_NUM_TBS > sizeof(out_meta->tbs) * BITS_PER_BYTE);
@@ -1037,8 +293,8 @@ static int iwl_pcie_gen2_enqueue_hcmd(struct iwl_trans *trans,
 
 	spin_lock_irqsave(&trans_pcie->reg_lock, flags);
 	/* Increment and update queue's write index */
-	txq->write_ptr = iwl_queue_inc_wrap(trans, txq->write_ptr);
-	iwl_pcie_gen2_txq_inc_wr_ptr(trans, txq);
+	txq->write_ptr = iwl_txq_inc_wrap(trans, txq->write_ptr);
+	iwl_txq_inc_wr_ptr(trans, txq);
 	spin_unlock_irqrestore(&trans_pcie->reg_lock, flags);
 
 out:
@@ -1169,322 +425,3 @@ int iwl_trans_pcie_gen2_send_hcmd(struct iwl_trans *trans,
 	return iwl_pcie_gen2_send_hcmd_sync(trans, cmd);
 }
 
-/*
- * iwl_pcie_gen2_txq_unmap -  Unmap any remaining DMA mappings and free skb's
- */
-void iwl_pcie_gen2_txq_unmap(struct iwl_trans *trans, int txq_id)
-{
-	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-	struct iwl_txq *txq = trans->txqs.txq[txq_id];
-
-	spin_lock_bh(&txq->lock);
-	while (txq->write_ptr != txq->read_ptr) {
-		IWL_DEBUG_TX_REPLY(trans, "Q %d Free %d\n",
-				   txq_id, txq->read_ptr);
-
-		if (txq_id != trans->txqs.cmd.q_id) {
-			int idx = iwl_pcie_get_cmd_index(txq, txq->read_ptr);
-			struct sk_buff *skb = txq->entries[idx].skb;
-
-			if (WARN_ON_ONCE(!skb))
-				continue;
-
-			iwl_pcie_free_tso_page(trans_pcie, skb);
-		}
-		iwl_pcie_gen2_free_tfd(trans, txq);
-		txq->read_ptr = iwl_queue_inc_wrap(trans, txq->read_ptr);
-	}
-
-	while (!skb_queue_empty(&txq->overflow_q)) {
-		struct sk_buff *skb = __skb_dequeue(&txq->overflow_q);
-
-		iwl_op_mode_free_skb(trans->op_mode, skb);
-	}
-
-	spin_unlock_bh(&txq->lock);
-
-	/* just in case - this queue may have been stopped */
-	iwl_wake_queue(trans, txq);
-}
-
-void iwl_pcie_gen2_txq_free_memory(struct iwl_trans *trans,
-				   struct iwl_txq *txq)
-{
-	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-	struct device *dev = trans->dev;
-
-	/* De-alloc circular buffer of TFDs */
-	if (txq->tfds) {
-		dma_free_coherent(dev,
-				  trans_pcie->tfd_size * txq->n_window,
-				  txq->tfds, txq->dma_addr);
-		dma_free_coherent(dev,
-				  sizeof(*txq->first_tb_bufs) * txq->n_window,
-				  txq->first_tb_bufs, txq->first_tb_dma);
-	}
-
-	kfree(txq->entries);
-	if (txq->bc_tbl.addr)
-		dma_pool_free(trans_pcie->bc_pool, txq->bc_tbl.addr,
-			      txq->bc_tbl.dma);
-	kfree(txq);
-}
-
-/*
- * iwl_pcie_txq_free - Deallocate DMA queue.
- * @txq: Transmit queue to deallocate.
- *
- * Empty queue by removing and destroying all BD's.
- * Free all buffers.
- * 0-fill, but do not free "txq" descriptor structure.
- */
-static void iwl_pcie_gen2_txq_free(struct iwl_trans *trans, int txq_id)
-{
-	struct iwl_txq *txq;
-	int i;
-
-	if (WARN_ONCE(txq_id >= IWL_MAX_TVQM_QUEUES,
-		      "queue %d out of range", txq_id))
-		return;
-
-	txq = trans->txqs.txq[txq_id];
-
-	if (WARN_ON(!txq))
-		return;
-
-	iwl_pcie_gen2_txq_unmap(trans, txq_id);
-
-	/* De-alloc array of command/tx buffers */
-	if (txq_id == trans->txqs.cmd.q_id)
-		for (i = 0; i < txq->n_window; i++) {
-			kfree_sensitive(txq->entries[i].cmd);
-			kfree_sensitive(txq->entries[i].free_buf);
-		}
-	del_timer_sync(&txq->stuck_timer);
-
-	iwl_pcie_gen2_txq_free_memory(trans, txq);
-
-	trans->txqs.txq[txq_id] = NULL;
-
-	clear_bit(txq_id, trans->txqs.queue_used);
-}
-
-int iwl_trans_pcie_dyn_txq_alloc_dma(struct iwl_trans *trans,
-				     struct iwl_txq **intxq, int size,
-				     unsigned int timeout)
-{
-	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-	size_t bc_tbl_size, bc_tbl_entries;
-	struct iwl_txq *txq;
-	int ret;
-
-	if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210) {
-		bc_tbl_size = sizeof(struct iwl_gen3_bc_tbl);
-		bc_tbl_entries = bc_tbl_size / sizeof(u16);
-	} else {
-		bc_tbl_size = sizeof(struct iwlagn_scd_bc_tbl);
-		bc_tbl_entries = bc_tbl_size / sizeof(u16);
-	}
-
-	if (WARN_ON(size > bc_tbl_entries))
-		return -EINVAL;
-
-	txq = kzalloc(sizeof(*txq), GFP_KERNEL);
-	if (!txq)
-		return -ENOMEM;
-
-	txq->bc_tbl.addr = dma_pool_alloc(trans_pcie->bc_pool, GFP_KERNEL,
-					  &txq->bc_tbl.dma);
-	if (!txq->bc_tbl.addr) {
-		IWL_ERR(trans, "Scheduler BC Table allocation failed\n");
-		kfree(txq);
-		return -ENOMEM;
-	}
-
-	ret = iwl_pcie_txq_alloc(trans, txq, size, false);
-	if (ret) {
-		IWL_ERR(trans, "Tx queue alloc failed\n");
-		goto error;
-	}
-	ret = iwl_pcie_txq_init(trans, txq, size, false);
-	if (ret) {
-		IWL_ERR(trans, "Tx queue init failed\n");
-		goto error;
-	}
-
-	txq->wd_timeout = msecs_to_jiffies(timeout);
-
-	*intxq = txq;
-	return 0;
-
-error:
-	iwl_pcie_gen2_txq_free_memory(trans, txq);
-	return ret;
-}
-
-int iwl_trans_pcie_txq_alloc_response(struct iwl_trans *trans,
-				      struct iwl_txq *txq,
-				      struct iwl_host_cmd *hcmd)
-{
-	struct iwl_tx_queue_cfg_rsp *rsp;
-	int ret, qid;
-	u32 wr_ptr;
-
-	if (WARN_ON(iwl_rx_packet_payload_len(hcmd->resp_pkt) !=
-		    sizeof(*rsp))) {
-		ret = -EINVAL;
-		goto error_free_resp;
-	}
-
-	rsp = (void *)hcmd->resp_pkt->data;
-	qid = le16_to_cpu(rsp->queue_number);
-	wr_ptr = le16_to_cpu(rsp->write_pointer);
-
-	if (qid >= ARRAY_SIZE(trans->txqs.txq)) {
-		WARN_ONCE(1, "queue index %d unsupported", qid);
-		ret = -EIO;
-		goto error_free_resp;
-	}
-
-	if (test_and_set_bit(qid, trans->txqs.queue_used)) {
-		WARN_ONCE(1, "queue %d already used", qid);
-		ret = -EIO;
-		goto error_free_resp;
-	}
-
-	txq->id = qid;
-	trans->txqs.txq[qid] = txq;
-	wr_ptr &= (trans->trans_cfg->base_params->max_tfd_queue_size - 1);
-
-	/* Place first TFD at index corresponding to start sequence number */
-	txq->read_ptr = wr_ptr;
-	txq->write_ptr = wr_ptr;
-
-	IWL_DEBUG_TX_QUEUES(trans, "Activate queue %d\n", qid);
-
-	iwl_free_resp(hcmd);
-	return qid;
-
-error_free_resp:
-	iwl_free_resp(hcmd);
-	iwl_pcie_gen2_txq_free_memory(trans, txq);
-	return ret;
-}
-
-int iwl_trans_pcie_dyn_txq_alloc(struct iwl_trans *trans,
-				 __le16 flags, u8 sta_id, u8 tid,
-				 int cmd_id, int size,
-				 unsigned int timeout)
-{
-	struct iwl_txq *txq = NULL;
-	struct iwl_tx_queue_cfg_cmd cmd = {
-		.flags = flags,
-		.sta_id = sta_id,
-		.tid = tid,
-	};
-	struct iwl_host_cmd hcmd = {
-		.id = cmd_id,
-		.len = { sizeof(cmd) },
-		.data = { &cmd, },
-		.flags = CMD_WANT_SKB,
-	};
-	int ret;
-
-	ret = iwl_trans_pcie_dyn_txq_alloc_dma(trans, &txq, size, timeout);
-	if (ret)
-		return ret;
-
-	cmd.tfdq_addr = cpu_to_le64(txq->dma_addr);
-	cmd.byte_cnt_addr = cpu_to_le64(txq->bc_tbl.dma);
-	cmd.cb_size = cpu_to_le32(TFD_QUEUE_CB_SIZE(size));
-
-	ret = iwl_trans_send_cmd(trans, &hcmd);
-	if (ret)
-		goto error;
-
-	return iwl_trans_pcie_txq_alloc_response(trans, txq, &hcmd);
-
-error:
-	iwl_pcie_gen2_txq_free_memory(trans, txq);
-	return ret;
-}
-
-void iwl_trans_pcie_dyn_txq_free(struct iwl_trans *trans, int queue)
-{
-	if (WARN(queue >= IWL_MAX_TVQM_QUEUES,
-		 "queue %d out of range", queue))
-		return;
-
-	/*
-	 * Upon HW Rfkill - we stop the device, and then stop the queues
-	 * in the op_mode. Just for the sake of the simplicity of the op_mode,
-	 * allow the op_mode to call txq_disable after it already called
-	 * stop_device.
-	 */
-	if (!test_and_clear_bit(queue, trans->txqs.queue_used)) {
-		WARN_ONCE(test_bit(STATUS_DEVICE_ENABLED, &trans->status),
-			  "queue %d not used", queue);
-		return;
-	}
-
-	iwl_pcie_gen2_txq_unmap(trans, queue);
-
-	iwl_pcie_gen2_txq_free_memory(trans, trans->txqs.txq[queue]);
-	trans->txqs.txq[queue] = NULL;
-
-	IWL_DEBUG_TX_QUEUES(trans, "Deactivate queue %d\n", queue);
-}
-
-void iwl_pcie_gen2_tx_free(struct iwl_trans *trans)
-{
-	int i;
-
-	memset(trans->txqs.queue_used, 0, sizeof(trans->txqs.queue_used));
-
-	/* Free all TX queues */
-	for (i = 0; i < ARRAY_SIZE(trans->txqs.txq); i++) {
-		if (!trans->txqs.txq[i])
-			continue;
-
-		iwl_pcie_gen2_txq_free(trans, i);
-	}
-}
-
-int iwl_pcie_gen2_tx_init(struct iwl_trans *trans, int txq_id, int queue_size)
-{
-	struct iwl_txq *queue;
-	int ret;
-
-	/* alloc and init the tx queue */
-	if (!trans->txqs.txq[txq_id]) {
-		queue = kzalloc(sizeof(*queue), GFP_KERNEL);
-		if (!queue) {
-			IWL_ERR(trans, "Not enough memory for tx queue\n");
-			return -ENOMEM;
-		}
-		trans->txqs.txq[txq_id] = queue;
-		ret = iwl_pcie_txq_alloc(trans, queue, queue_size, true);
-		if (ret) {
-			IWL_ERR(trans, "Tx %d queue init failed\n", txq_id);
-			goto error;
-		}
-	} else {
-		queue = trans->txqs.txq[txq_id];
-	}
-
-	ret = iwl_pcie_txq_init(trans, queue, queue_size,
-				(txq_id == trans->txqs.cmd.q_id));
-	if (ret) {
-		IWL_ERR(trans, "Tx %d queue alloc failed\n", txq_id);
-		goto error;
-	}
-	trans->txqs.txq[txq_id]->id = txq_id;
-	set_bit(txq_id, trans->txqs.queue_used);
-
-	return 0;
-
-error:
-	iwl_pcie_gen2_tx_free(trans);
-	return ret;
-}
-
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
index eb396c06b7fb..8c89e4a2f7f8 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
@@ -77,9 +77,6 @@
 #include "internal.h"
 #include "fw/api/tx.h"
 
-#define IWL_TX_CRC_SIZE 4
-#define IWL_TX_DELIMITER_SIZE 4
-
 /*************** DMA-QUEUE-GENERAL-FUNCTIONS  *****
  * DMA services
  *
@@ -102,60 +99,6 @@
  *
  ***************************************************/
 
-int iwl_queue_space(struct iwl_trans *trans, const struct iwl_txq *q)
-{
-	unsigned int max;
-	unsigned int used;
-
-	/*
-	 * To avoid ambiguity between empty and completely full queues, there
-	 * should always be less than max_tfd_queue_size elements in the queue.
-	 * If q->n_window is smaller than max_tfd_queue_size, there is no need
-	 * to reserve any queue entries for this purpose.
-	 */
-	if (q->n_window < trans->trans_cfg->base_params->max_tfd_queue_size)
-		max = q->n_window;
-	else
-		max = trans->trans_cfg->base_params->max_tfd_queue_size - 1;
-
-	/*
-	 * max_tfd_queue_size is a power of 2, so the following is equivalent to
-	 * modulo by max_tfd_queue_size and is well defined.
-	 */
-	used = (q->write_ptr - q->read_ptr) &
-		(trans->trans_cfg->base_params->max_tfd_queue_size - 1);
-
-	if (WARN_ON(used > max))
-		return 0;
-
-	return max - used;
-}
-
-/*
- * iwl_queue_init - Initialize queue's high/low-water and read/write indexes
- */
-static int iwl_queue_init(struct iwl_txq *q, int slots_num)
-{
-	q->n_window = slots_num;
-
-	/* slots_num must be power-of-two size, otherwise
-	 * iwl_pcie_get_cmd_index is broken. */
-	if (WARN_ON(!is_power_of_2(slots_num)))
-		return -EINVAL;
-
-	q->low_mark = q->n_window / 4;
-	if (q->low_mark < 4)
-		q->low_mark = 4;
-
-	q->high_mark = q->n_window / 8;
-	if (q->high_mark < 2)
-		q->high_mark = 2;
-
-	q->write_ptr = 0;
-	q->read_ptr = 0;
-
-	return 0;
-}
 
 int iwl_pcie_alloc_dma_ptr(struct iwl_trans *trans,
 			   struct iwl_dma_ptr *ptr, size_t size)
@@ -180,99 +123,6 @@ void iwl_pcie_free_dma_ptr(struct iwl_trans *trans, struct iwl_dma_ptr *ptr)
 	memset(ptr, 0, sizeof(*ptr));
 }
 
-static void iwl_pcie_txq_stuck_timer(struct timer_list *t)
-{
-	struct iwl_txq *txq = from_timer(txq, t, stuck_timer);
-	struct iwl_trans *trans = txq->trans;
-
-	spin_lock(&txq->lock);
-	/* check if triggered erroneously */
-	if (txq->read_ptr == txq->write_ptr) {
-		spin_unlock(&txq->lock);
-		return;
-	}
-	spin_unlock(&txq->lock);
-
-	iwl_trans_pcie_log_scd_error(trans, txq);
-
-	iwl_force_nmi(trans);
-}
-
-/*
- * iwl_pcie_txq_update_byte_cnt_tbl - Set up entry in Tx byte-count array
- */
-static void iwl_pcie_txq_update_byte_cnt_tbl(struct iwl_trans *trans,
-					     struct iwl_txq *txq, u16 byte_cnt,
-					     int num_tbs)
-{
-	struct iwlagn_scd_bc_tbl *scd_bc_tbl;
-	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-	int write_ptr = txq->write_ptr;
-	int txq_id = txq->id;
-	u8 sec_ctl = 0;
-	u16 len = byte_cnt + IWL_TX_CRC_SIZE + IWL_TX_DELIMITER_SIZE;
-	__le16 bc_ent;
-	struct iwl_device_tx_cmd *dev_cmd = txq->entries[txq->write_ptr].cmd;
-	struct iwl_tx_cmd *tx_cmd = (void *)dev_cmd->payload;
-	u8 sta_id = tx_cmd->sta_id;
-
-	scd_bc_tbl = trans_pcie->scd_bc_tbls.addr;
-
-	sec_ctl = tx_cmd->sec_ctl;
-
-	switch (sec_ctl & TX_CMD_SEC_MSK) {
-	case TX_CMD_SEC_CCM:
-		len += IEEE80211_CCMP_MIC_LEN;
-		break;
-	case TX_CMD_SEC_TKIP:
-		len += IEEE80211_TKIP_ICV_LEN;
-		break;
-	case TX_CMD_SEC_WEP:
-		len += IEEE80211_WEP_IV_LEN + IEEE80211_WEP_ICV_LEN;
-		break;
-	}
-	if (trans_pcie->bc_table_dword)
-		len = DIV_ROUND_UP(len, 4);
-
-	if (WARN_ON(len > 0xFFF || write_ptr >= TFD_QUEUE_SIZE_MAX))
-		return;
-
-	bc_ent = cpu_to_le16(len | (sta_id << 12));
-
-	scd_bc_tbl[txq_id].tfd_offset[write_ptr] = bc_ent;
-
-	if (write_ptr < TFD_QUEUE_SIZE_BC_DUP)
-		scd_bc_tbl[txq_id].
-			tfd_offset[TFD_QUEUE_SIZE_MAX + write_ptr] = bc_ent;
-}
-
-static void iwl_pcie_txq_inval_byte_cnt_tbl(struct iwl_trans *trans,
-					    struct iwl_txq *txq)
-{
-	struct iwl_trans_pcie *trans_pcie =
-		IWL_TRANS_GET_PCIE_TRANS(trans);
-	struct iwlagn_scd_bc_tbl *scd_bc_tbl = trans_pcie->scd_bc_tbls.addr;
-	int txq_id = txq->id;
-	int read_ptr = txq->read_ptr;
-	u8 sta_id = 0;
-	__le16 bc_ent;
-	struct iwl_device_tx_cmd *dev_cmd = txq->entries[read_ptr].cmd;
-	struct iwl_tx_cmd *tx_cmd = (void *)dev_cmd->payload;
-
-	WARN_ON(read_ptr >= TFD_QUEUE_SIZE_MAX);
-
-	if (txq_id != trans->txqs.cmd.q_id)
-		sta_id = tx_cmd->sta_id;
-
-	bc_ent = cpu_to_le16(1 | (sta_id << 12));
-
-	scd_bc_tbl[txq_id].tfd_offset[read_ptr] = bc_ent;
-
-	if (read_ptr < TFD_QUEUE_SIZE_BC_DUP)
-		scd_bc_tbl[txq_id].
-			tfd_offset[TFD_QUEUE_SIZE_MAX + read_ptr] = bc_ent;
-}
-
 /*
  * iwl_pcie_txq_inc_wr_ptr - Send new write index to hardware
  */
@@ -339,35 +189,6 @@ void iwl_pcie_txq_check_wrptrs(struct iwl_trans *trans)
 	}
 }
 
-static inline dma_addr_t iwl_pcie_tfd_tb_get_addr(struct iwl_trans *trans,
-						  void *_tfd, u8 idx)
-{
-
-	if (trans->trans_cfg->use_tfh) {
-		struct iwl_tfh_tfd *tfd = _tfd;
-		struct iwl_tfh_tb *tb = &tfd->tbs[idx];
-
-		return (dma_addr_t)(le64_to_cpu(tb->addr));
-	} else {
-		struct iwl_tfd *tfd = _tfd;
-		struct iwl_tfd_tb *tb = &tfd->tbs[idx];
-		dma_addr_t addr = get_unaligned_le32(&tb->lo);
-		dma_addr_t hi_len;
-
-		if (sizeof(dma_addr_t) <= sizeof(u32))
-			return addr;
-
-		hi_len = le16_to_cpu(tb->hi_n_len) & 0xF;
-
-		/*
-		 * shift by 16 twice to avoid warnings on 32-bit
-		 * (where this code never runs anyway due to the
-		 * if statement above)
-		 */
-		return addr | ((hi_len << 16) << 16);
-	}
-}
-
 static inline void iwl_pcie_tfd_set_tb(struct iwl_trans *trans, void *tfd,
 				       u8 idx, dma_addr_t addr, u16 len)
 {
@@ -384,67 +205,6 @@ static inline void iwl_pcie_tfd_set_tb(struct iwl_trans *trans, void *tfd,
 	tfd_fh->num_tbs = idx + 1;
 }
 
-static inline u8 iwl_pcie_tfd_get_num_tbs(struct iwl_trans *trans, void *_tfd)
-{
-	if (trans->trans_cfg->use_tfh) {
-		struct iwl_tfh_tfd *tfd = _tfd;
-
-		return le16_to_cpu(tfd->num_tbs) & 0x1f;
-	} else {
-		struct iwl_tfd *tfd = _tfd;
-
-		return tfd->num_tbs & 0x1f;
-	}
-}
-
-static void iwl_pcie_tfd_unmap(struct iwl_trans *trans,
-			       struct iwl_cmd_meta *meta,
-			       struct iwl_txq *txq, int index)
-{
-	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-	int i, num_tbs;
-	void *tfd = iwl_pcie_get_tfd(trans, txq, index);
-
-	/* Sanity check on number of chunks */
-	num_tbs = iwl_pcie_tfd_get_num_tbs(trans, tfd);
-
-	if (num_tbs > trans_pcie->max_tbs) {
-		IWL_ERR(trans, "Too many chunks: %i\n", num_tbs);
-		/* @todo issue fatal error, it is quite serious situation */
-		return;
-	}
-
-	/* first TB is never freed - it's the bidirectional DMA data */
-
-	for (i = 1; i < num_tbs; i++) {
-		if (meta->tbs & BIT(i))
-			dma_unmap_page(trans->dev,
-				       iwl_pcie_tfd_tb_get_addr(trans, tfd, i),
-				       iwl_pcie_tfd_tb_get_len(trans, tfd, i),
-				       DMA_TO_DEVICE);
-		else
-			dma_unmap_single(trans->dev,
-					 iwl_pcie_tfd_tb_get_addr(trans, tfd,
-								  i),
-					 iwl_pcie_tfd_tb_get_len(trans, tfd,
-								 i),
-					 DMA_TO_DEVICE);
-	}
-
-	meta->tbs = 0;
-
-	if (trans->trans_cfg->use_tfh) {
-		struct iwl_tfh_tfd *tfd_fh = (void *)tfd;
-
-		tfd_fh->num_tbs = 0;
-	} else {
-		struct iwl_tfd *tfd_fh = (void *)tfd;
-
-		tfd_fh->num_tbs = 0;
-	}
-
-}
-
 /*
  * iwl_pcie_txq_free_tfd - Free all chunks referenced by TFD [txq->q.read_ptr]
  * @trans - transport private data
@@ -460,14 +220,14 @@ void iwl_pcie_txq_free_tfd(struct iwl_trans *trans, struct iwl_txq *txq)
 	 * idx is bounded by n_window
 	 */
 	int rd_ptr = txq->read_ptr;
-	int idx = iwl_pcie_get_cmd_index(txq, rd_ptr);
+	int idx = iwl_txq_get_cmd_index(txq, rd_ptr);
 
 	lockdep_assert_held(&txq->lock);
 
 	/* We have only q->n_window txq->entries, but we use
 	 * TFD_QUEUE_SIZE_MAX tfds
 	 */
-	iwl_pcie_tfd_unmap(trans, &txq->entries[idx].meta, txq, rd_ptr);
+	iwl_txq_gen1_tfd_unmap(trans, &txq->entries[idx].meta, txq, rd_ptr);
 
 	/* free SKB */
 	if (txq->entries) {
@@ -489,21 +249,20 @@ void iwl_pcie_txq_free_tfd(struct iwl_trans *trans, struct iwl_txq *txq)
 static int iwl_pcie_txq_build_tfd(struct iwl_trans *trans, struct iwl_txq *txq,
 				  dma_addr_t addr, u16 len, bool reset)
 {
-	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	void *tfd;
 	u32 num_tbs;
 
-	tfd = txq->tfds + trans_pcie->tfd_size * txq->write_ptr;
+	tfd = txq->tfds + trans->txqs.tfd.size * txq->write_ptr;
 
 	if (reset)
-		memset(tfd, 0, trans_pcie->tfd_size);
+		memset(tfd, 0, trans->txqs.tfd.size);
 
-	num_tbs = iwl_pcie_tfd_get_num_tbs(trans, tfd);
+	num_tbs = iwl_txq_gen1_tfd_get_num_tbs(trans, tfd);
 
 	/* Each TFD can point to a maximum max_tbs Tx buffers */
-	if (num_tbs >= trans_pcie->max_tbs) {
+	if (num_tbs >= trans->txqs.tfd.max_tbs) {
 		IWL_ERR(trans, "Error can not send more than %d chunks\n",
-			trans_pcie->max_tbs);
+			trans->txqs.tfd.max_tbs);
 		return -EINVAL;
 	}
 
@@ -516,126 +275,6 @@ static int iwl_pcie_txq_build_tfd(struct iwl_trans *trans, struct iwl_txq *txq,
 	return num_tbs;
 }
 
-int iwl_pcie_txq_alloc(struct iwl_trans *trans, struct iwl_txq *txq,
-		       int slots_num, bool cmd_queue)
-{
-	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-	size_t tfd_sz = trans_pcie->tfd_size *
-		trans->trans_cfg->base_params->max_tfd_queue_size;
-	size_t tb0_buf_sz;
-	int i;
-
-	if (WARN_ON(txq->entries || txq->tfds))
-		return -EINVAL;
-
-	if (trans->trans_cfg->use_tfh)
-		tfd_sz = trans_pcie->tfd_size * slots_num;
-
-	timer_setup(&txq->stuck_timer, iwl_pcie_txq_stuck_timer, 0);
-	txq->trans = trans;
-
-	txq->n_window = slots_num;
-
-	txq->entries = kcalloc(slots_num,
-			       sizeof(struct iwl_pcie_txq_entry),
-			       GFP_KERNEL);
-
-	if (!txq->entries)
-		goto error;
-
-	if (cmd_queue)
-		for (i = 0; i < slots_num; i++) {
-			txq->entries[i].cmd =
-				kmalloc(sizeof(struct iwl_device_cmd),
-					GFP_KERNEL);
-			if (!txq->entries[i].cmd)
-				goto error;
-		}
-
-	/* Circular buffer of transmit frame descriptors (TFDs),
-	 * shared with device */
-	txq->tfds = dma_alloc_coherent(trans->dev, tfd_sz,
-				       &txq->dma_addr, GFP_KERNEL);
-	if (!txq->tfds)
-		goto error;
-
-	BUILD_BUG_ON(IWL_FIRST_TB_SIZE_ALIGN != sizeof(*txq->first_tb_bufs));
-
-	tb0_buf_sz = sizeof(*txq->first_tb_bufs) * slots_num;
-
-	txq->first_tb_bufs = dma_alloc_coherent(trans->dev, tb0_buf_sz,
-					      &txq->first_tb_dma,
-					      GFP_KERNEL);
-	if (!txq->first_tb_bufs)
-		goto err_free_tfds;
-
-	return 0;
-err_free_tfds:
-	dma_free_coherent(trans->dev, tfd_sz, txq->tfds, txq->dma_addr);
-error:
-	if (txq->entries && cmd_queue)
-		for (i = 0; i < slots_num; i++)
-			kfree(txq->entries[i].cmd);
-	kfree(txq->entries);
-	txq->entries = NULL;
-
-	return -ENOMEM;
-
-}
-
-int iwl_pcie_txq_init(struct iwl_trans *trans, struct iwl_txq *txq,
-		      int slots_num, bool cmd_queue)
-{
-	int ret;
-	u32 tfd_queue_max_size =
-		trans->trans_cfg->base_params->max_tfd_queue_size;
-
-	txq->need_update = false;
-
-	/* max_tfd_queue_size must be power-of-two size, otherwise
-	 * iwl_queue_inc_wrap and iwl_queue_dec_wrap are broken. */
-	if (WARN_ONCE(tfd_queue_max_size & (tfd_queue_max_size - 1),
-		      "Max tfd queue size must be a power of two, but is %d",
-		      tfd_queue_max_size))
-		return -EINVAL;
-
-	/* Initialize queue's high/low-water marks, and head/tail indexes */
-	ret = iwl_queue_init(txq, slots_num);
-	if (ret)
-		return ret;
-
-	spin_lock_init(&txq->lock);
-
-	if (cmd_queue) {
-		static struct lock_class_key iwl_pcie_cmd_queue_lock_class;
-
-		lockdep_set_class(&txq->lock, &iwl_pcie_cmd_queue_lock_class);
-	}
-
-	__skb_queue_head_init(&txq->overflow_q);
-
-	return 0;
-}
-
-void iwl_pcie_free_tso_page(struct iwl_trans_pcie *trans_pcie,
-			    struct sk_buff *skb)
-{
-	struct page **page_ptr;
-	struct page *next;
-
-	page_ptr = (void *)((u8 *)skb->cb + trans_pcie->page_offs);
-	next = *page_ptr;
-	*page_ptr = NULL;
-
-	while (next) {
-		struct page *tmp = next;
-
-		next = *(void **)(page_address(next) + PAGE_SIZE -
-				  sizeof(void *));
-		__free_page(tmp);
-	}
-}
-
 static void iwl_pcie_clear_cmd_in_flight(struct iwl_trans *trans)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
@@ -671,10 +310,10 @@ static void iwl_pcie_txq_unmap(struct iwl_trans *trans, int txq_id)
 			if (WARN_ON_ONCE(!skb))
 				continue;
 
-			iwl_pcie_free_tso_page(trans_pcie, skb);
+			iwl_txq_free_tso_page(trans, skb);
 		}
 		iwl_pcie_txq_free_tfd(trans, txq);
-		txq->read_ptr = iwl_queue_inc_wrap(trans, txq->read_ptr);
+		txq->read_ptr = iwl_txq_inc_wrap(trans, txq->read_ptr);
 
 		if (txq->read_ptr == txq->write_ptr) {
 			unsigned long flags;
@@ -708,7 +347,6 @@ static void iwl_pcie_txq_unmap(struct iwl_trans *trans, int txq_id)
  */
 static void iwl_pcie_txq_free(struct iwl_trans *trans, int txq_id)
 {
-	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	struct iwl_txq *txq = trans->txqs.txq[txq_id];
 	struct device *dev = trans->dev;
 	int i;
@@ -728,7 +366,7 @@ static void iwl_pcie_txq_free(struct iwl_trans *trans, int txq_id)
 	/* De-alloc circular buffer of TFDs */
 	if (txq->tfds) {
 		dma_free_coherent(dev,
-				  trans_pcie->tfd_size *
+				  trans->txqs.tfd.size *
 				  trans->trans_cfg->base_params->max_tfd_queue_size,
 				  txq->tfds, txq->dma_addr);
 		txq->dma_addr = 0;
@@ -774,7 +412,7 @@ void iwl_pcie_tx_start(struct iwl_trans *trans, u32 scd_base_addr)
 			    NULL, clear_dwords);
 
 	iwl_write_prph(trans, SCD_DRAM_BASE_ADDR,
-		       trans_pcie->scd_bc_tbls.dma >> 10);
+		       trans->txqs.scd_bc_tbls.dma >> 10);
 
 	/* The chain extension of the SCD doesn't work well. This feature is
 	 * enabled by default by the HW, so we need to disable it manually.
@@ -939,7 +577,7 @@ void iwl_pcie_tx_free(struct iwl_trans *trans)
 
 	iwl_pcie_free_dma_ptr(trans, &trans_pcie->kw);
 
-	iwl_pcie_free_dma_ptr(trans, &trans_pcie->scd_bc_tbls);
+	iwl_pcie_free_dma_ptr(trans, &trans->txqs.scd_bc_tbls);
 }
 
 /*
@@ -965,7 +603,7 @@ static int iwl_pcie_tx_alloc(struct iwl_trans *trans)
 		goto error;
 	}
 
-	ret = iwl_pcie_alloc_dma_ptr(trans, &trans_pcie->scd_bc_tbls,
+	ret = iwl_pcie_alloc_dma_ptr(trans, &trans->txqs.scd_bc_tbls,
 				     bc_tbls_size);
 	if (ret) {
 		IWL_ERR(trans, "Scheduler BC Table allocation failed\n");
@@ -1000,8 +638,8 @@ static int iwl_pcie_tx_alloc(struct iwl_trans *trans)
 			slots_num = max_t(u32, IWL_DEFAULT_QUEUE_SIZE,
 					  trans->cfg->min_256_ba_txq_size);
 		trans->txqs.txq[txq_id] = &trans_pcie->txq_memory[txq_id];
-		ret = iwl_pcie_txq_alloc(trans, trans->txqs.txq[txq_id],
-					 slots_num, cmd_queue);
+		ret = iwl_txq_alloc(trans, trans->txqs.txq[txq_id], slots_num,
+				    cmd_queue);
 		if (ret) {
 			IWL_ERR(trans, "Tx %d queue alloc failed\n", txq_id);
 			goto error;
@@ -1053,8 +691,8 @@ int iwl_pcie_tx_init(struct iwl_trans *trans)
 		else
 			slots_num = max_t(u32, IWL_DEFAULT_QUEUE_SIZE,
 					  trans->cfg->min_256_ba_txq_size);
-		ret = iwl_pcie_txq_init(trans, trans->txqs.txq[txq_id],
-					slots_num, cmd_queue);
+		ret = iwl_txq_init(trans, trans->txqs.txq[txq_id], slots_num,
+				   cmd_queue);
 		if (ret) {
 			IWL_ERR(trans, "Tx %d queue init failed\n", txq_id);
 			goto error;
@@ -1111,10 +749,9 @@ static inline void iwl_pcie_txq_progress(struct iwl_txq *txq)
 void iwl_trans_pcie_reclaim(struct iwl_trans *trans, int txq_id, int ssn,
 			    struct sk_buff_head *skbs)
 {
-	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	struct iwl_txq *txq = trans->txqs.txq[txq_id];
-	int tfd_num = iwl_pcie_get_cmd_index(txq, ssn);
-	int read_ptr = iwl_pcie_get_cmd_index(txq, txq->read_ptr);
+	int tfd_num = iwl_txq_get_cmd_index(txq, ssn);
+	int read_ptr = iwl_txq_get_cmd_index(txq, txq->read_ptr);
 	int last_to_free;
 
 	/* This function is not meant to release cmd queue*/
@@ -1137,9 +774,9 @@ void iwl_trans_pcie_reclaim(struct iwl_trans *trans, int txq_id, int ssn,
 
 	/*Since we free until index _not_ inclusive, the one before index is
 	 * the last we will free. This one must be used */
-	last_to_free = iwl_queue_dec_wrap(trans, tfd_num);
+	last_to_free = iwl_txq_dec_wrap(trans, tfd_num);
 
-	if (!iwl_queue_used(txq, last_to_free)) {
+	if (!iwl_txq_used(txq, last_to_free)) {
 		IWL_ERR(trans,
 			"%s: Read index for txq id (%d), last_to_free %d is out of range [0-%d] %d %d.\n",
 			__func__, txq_id, last_to_free,
@@ -1153,28 +790,28 @@ void iwl_trans_pcie_reclaim(struct iwl_trans *trans, int txq_id, int ssn,
 
 	for (;
 	     read_ptr != tfd_num;
-	     txq->read_ptr = iwl_queue_inc_wrap(trans, txq->read_ptr),
-	     read_ptr = iwl_pcie_get_cmd_index(txq, txq->read_ptr)) {
+	     txq->read_ptr = iwl_txq_inc_wrap(trans, txq->read_ptr),
+	     read_ptr = iwl_txq_get_cmd_index(txq, txq->read_ptr)) {
 		struct sk_buff *skb = txq->entries[read_ptr].skb;
 
 		if (WARN_ON_ONCE(!skb))
 			continue;
 
-		iwl_pcie_free_tso_page(trans_pcie, skb);
+		iwl_txq_free_tso_page(trans, skb);
 
 		__skb_queue_tail(skbs, skb);
 
 		txq->entries[read_ptr].skb = NULL;
 
 		if (!trans->trans_cfg->use_tfh)
-			iwl_pcie_txq_inval_byte_cnt_tbl(trans, txq);
+			iwl_txq_gen1_inval_byte_cnt_tbl(trans, txq);
 
 		iwl_pcie_txq_free_tfd(trans, txq);
 	}
 
 	iwl_pcie_txq_progress(txq);
 
-	if (iwl_queue_space(trans, txq) > txq->low_mark &&
+	if (iwl_txq_space(trans, txq) > txq->low_mark &&
 	    test_bit(txq_id, trans->txqs.queue_stopped)) {
 		struct sk_buff_head overflow_skbs;
 
@@ -1204,17 +841,17 @@ void iwl_trans_pcie_reclaim(struct iwl_trans *trans, int txq_id, int ssn,
 			struct iwl_device_tx_cmd *dev_cmd_ptr;
 
 			dev_cmd_ptr = *(void **)((u8 *)skb->cb +
-						 trans_pcie->dev_cmd_offs);
+						 trans->txqs.dev_cmd_offs);
 
 			/*
 			 * Note that we can very well be overflowing again.
-			 * In that case, iwl_queue_space will be small again
+			 * In that case, iwl_txq_space will be small again
 			 * and we won't wake mac80211's queue.
 			 */
 			iwl_trans_tx(trans, skb, dev_cmd_ptr, txq_id);
 		}
 
-		if (iwl_queue_space(trans, txq) > txq->low_mark)
+		if (iwl_txq_space(trans, txq) > txq->low_mark)
 			iwl_wake_queue(trans, txq);
 
 		spin_lock_bh(&txq->lock);
@@ -1295,11 +932,11 @@ static void iwl_pcie_cmdq_reclaim(struct iwl_trans *trans, int txq_id, int idx)
 
 	lockdep_assert_held(&txq->lock);
 
-	idx = iwl_pcie_get_cmd_index(txq, idx);
-	r = iwl_pcie_get_cmd_index(txq, txq->read_ptr);
+	idx = iwl_txq_get_cmd_index(txq, idx);
+	r = iwl_txq_get_cmd_index(txq, txq->read_ptr);
 
 	if (idx >= trans->trans_cfg->base_params->max_tfd_queue_size ||
-	    (!iwl_queue_used(txq, idx))) {
+	    (!iwl_txq_used(txq, idx))) {
 		WARN_ONCE(test_bit(txq_id, trans->txqs.queue_used),
 			  "%s: Read index for DMA queue txq id (%d), index %d is out of range [0-%d] %d %d.\n",
 			  __func__, txq_id, idx,
@@ -1308,9 +945,9 @@ static void iwl_pcie_cmdq_reclaim(struct iwl_trans *trans, int txq_id, int idx)
 		return;
 	}
 
-	for (idx = iwl_queue_inc_wrap(trans, idx); r != idx;
-	     r = iwl_queue_inc_wrap(trans, r)) {
-		txq->read_ptr = iwl_queue_inc_wrap(trans, txq->read_ptr);
+	for (idx = iwl_txq_inc_wrap(trans, idx); r != idx;
+	     r = iwl_txq_inc_wrap(trans, r)) {
+		txq->read_ptr = iwl_txq_inc_wrap(trans, txq->read_ptr);
 
 		if (nfreed++ > 0) {
 			IWL_ERR(trans, "HCMD skipped: index (%d) %d %d\n",
@@ -1543,11 +1180,6 @@ static int iwl_pcie_enqueue_hcmd(struct iwl_trans *trans,
 	const u8 *cmddata[IWL_MAX_CMD_TBS_PER_TFD];
 	u16 cmdlen[IWL_MAX_CMD_TBS_PER_TFD];
 
-	if (WARN(!trans->wide_cmd_header &&
-		 group_id > IWL_ALWAYS_LONG_GROUP,
-		 "unsupported wide command %#x\n", cmd->id))
-		return -EINVAL;
-
 	if (group_id != 0) {
 		copy_size = sizeof(struct iwl_cmd_header_wide);
 		cmd_size = sizeof(struct iwl_cmd_header_wide);
@@ -1627,7 +1259,7 @@ static int iwl_pcie_enqueue_hcmd(struct iwl_trans *trans,
 
 	spin_lock_bh(&txq->lock);
 
-	if (iwl_queue_space(trans, txq) < ((cmd->flags & CMD_ASYNC) ? 2 : 1)) {
+	if (iwl_txq_space(trans, txq) < ((cmd->flags & CMD_ASYNC) ? 2 : 1)) {
 		spin_unlock_bh(&txq->lock);
 
 		IWL_ERR(trans, "No space in command queue\n");
@@ -1636,7 +1268,7 @@ static int iwl_pcie_enqueue_hcmd(struct iwl_trans *trans,
 		goto free_dup_buf;
 	}
 
-	idx = iwl_pcie_get_cmd_index(txq, txq->write_ptr);
+	idx = iwl_txq_get_cmd_index(txq, txq->write_ptr);
 	out_cmd = txq->entries[idx].cmd;
 	out_meta = &txq->entries[idx].meta;
 
@@ -1719,7 +1351,7 @@ static int iwl_pcie_enqueue_hcmd(struct iwl_trans *trans,
 	tb0_size = min_t(int, copy_size, IWL_FIRST_TB_SIZE);
 	memcpy(&txq->first_tb_bufs[idx], &out_cmd->hdr, tb0_size);
 	iwl_pcie_txq_build_tfd(trans, txq,
-			       iwl_pcie_get_first_tb_dma(txq, idx),
+			       iwl_txq_get_first_tb_dma(txq, idx),
 			       tb0_size, true);
 
 	/* map first command fragment, if any remains */
@@ -1729,8 +1361,8 @@ static int iwl_pcie_enqueue_hcmd(struct iwl_trans *trans,
 					   copy_size - tb0_size,
 					   DMA_TO_DEVICE);
 		if (dma_mapping_error(trans->dev, phys_addr)) {
-			iwl_pcie_tfd_unmap(trans, out_meta, txq,
-					   txq->write_ptr);
+			iwl_txq_gen1_tfd_unmap(trans, out_meta, txq,
+					       txq->write_ptr);
 			idx = -ENOMEM;
 			goto out;
 		}
@@ -1753,8 +1385,8 @@ static int iwl_pcie_enqueue_hcmd(struct iwl_trans *trans,
 		phys_addr = dma_map_single(trans->dev, (void *)data,
 					   cmdlen[i], DMA_TO_DEVICE);
 		if (dma_mapping_error(trans->dev, phys_addr)) {
-			iwl_pcie_tfd_unmap(trans, out_meta, txq,
-					   txq->write_ptr);
+			iwl_txq_gen1_tfd_unmap(trans, out_meta, txq,
+					       txq->write_ptr);
 			idx = -ENOMEM;
 			goto out;
 		}
@@ -1783,7 +1415,7 @@ static int iwl_pcie_enqueue_hcmd(struct iwl_trans *trans,
 	}
 
 	/* Increment and update queue's write index */
-	txq->write_ptr = iwl_queue_inc_wrap(trans, txq->write_ptr);
+	txq->write_ptr = iwl_txq_inc_wrap(trans, txq->write_ptr);
 	iwl_pcie_txq_inc_wr_ptr(trans, txq);
 
 	spin_unlock_irqrestore(&trans_pcie->reg_lock, flags);
@@ -1828,13 +1460,13 @@ void iwl_pcie_hcmd_complete(struct iwl_trans *trans,
 
 	spin_lock_bh(&txq->lock);
 
-	cmd_index = iwl_pcie_get_cmd_index(txq, index);
+	cmd_index = iwl_txq_get_cmd_index(txq, index);
 	cmd = txq->entries[cmd_index].cmd;
 	meta = &txq->entries[cmd_index].meta;
 	group_id = cmd->hdr.group_id;
 	cmd_id = iwl_cmd_id(cmd->hdr.cmd, group_id, 0);
 
-	iwl_pcie_tfd_unmap(trans, meta, txq, index);
+	iwl_txq_gen1_tfd_unmap(trans, meta, txq, index);
 
 	/* Input error checking is done when commands are added to queue. */
 	if (meta->flags & CMD_WANT_SKB) {
@@ -2055,51 +1687,6 @@ static int iwl_fill_data_tbs(struct iwl_trans *trans, struct sk_buff *skb,
 }
 
 #ifdef CONFIG_INET
-struct iwl_tso_hdr_page *get_page_hdr(struct iwl_trans *trans, size_t len,
-				      struct sk_buff *skb)
-{
-	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-	struct iwl_tso_hdr_page *p = this_cpu_ptr(trans_pcie->tso_hdr_page);
-	struct page **page_ptr;
-
-	page_ptr = (void *)((u8 *)skb->cb + trans_pcie->page_offs);
-
-	if (WARN_ON(*page_ptr))
-		return NULL;
-
-	if (!p->page)
-		goto alloc;
-
-	/*
-	 * Check if there's enough room on this page
-	 *
-	 * Note that we put a page chaining pointer *last* in the
-	 * page - we need it somewhere, and if it's there then we
-	 * avoid DMA mapping the last bits of the page which may
-	 * trigger the 32-bit boundary hardware bug.
-	 *
-	 * (see also get_workaround_page() in tx-gen2.c)
-	 */
-	if (p->pos + len < (u8 *)page_address(p->page) + PAGE_SIZE -
-			   sizeof(void *))
-		goto out;
-
-	/* We don't have enough room on this page, get a new one. */
-	__free_page(p->page);
-
-alloc:
-	p->page = alloc_page(GFP_ATOMIC);
-	if (!p->page)
-		return NULL;
-	p->pos = page_address(p->page);
-	/* set the chaining pointer to NULL */
-	*(void **)(page_address(p->page) + PAGE_SIZE - sizeof(void *)) = NULL;
-out:
-	*page_ptr = p->page;
-	get_page(p->page);
-	return p;
-}
-
 static void iwl_compute_pseudo_hdr_csum(void *iph, struct tcphdr *tcph,
 					bool ipv6, unsigned int len)
 {
@@ -2142,8 +1729,8 @@ static int iwl_fill_data_tbs_amsdu(struct iwl_trans *trans, struct sk_buff *skb,
 		IEEE80211_CCMP_HDR_LEN : 0;
 
 	trace_iwlwifi_dev_tx(trans->dev, skb,
-			     iwl_pcie_get_tfd(trans, txq, txq->write_ptr),
-			     trans_pcie->tfd_size,
+			     iwl_txq_get_tfd(trans, txq, txq->write_ptr),
+			     trans->txqs.tfd.size,
 			     &dev_cmd->hdr, IWL_FIRST_TB_SIZE + tb1_len, 0);
 
 	ip_hdrlen = skb_transport_header(skb) - skb_network_header(skb);
@@ -2352,7 +1939,7 @@ int iwl_trans_pcie_tx(struct iwl_trans *trans, struct sk_buff *skb,
 	}
 
 	if (skb_is_nonlinear(skb) &&
-	    skb_shinfo(skb)->nr_frags > IWL_PCIE_MAX_FRAGS(trans_pcie) &&
+	    skb_shinfo(skb)->nr_frags > IWL_TRANS_MAX_FRAGS(trans) &&
 	    __skb_linearize(skb))
 		return -ENOMEM;
 
@@ -2365,15 +1952,15 @@ int iwl_trans_pcie_tx(struct iwl_trans *trans, struct sk_buff *skb,
 
 	spin_lock(&txq->lock);
 
-	if (iwl_queue_space(trans, txq) < txq->high_mark) {
-		iwl_stop_queue(trans, txq);
+	if (iwl_txq_space(trans, txq) < txq->high_mark) {
+		iwl_txq_stop(trans, txq);
 
 		/* don't put the packet on the ring, if there is no room */
-		if (unlikely(iwl_queue_space(trans, txq) < 3)) {
+		if (unlikely(iwl_txq_space(trans, txq) < 3)) {
 			struct iwl_device_tx_cmd **dev_cmd_ptr;
 
 			dev_cmd_ptr = (void *)((u8 *)skb->cb +
-					       trans_pcie->dev_cmd_offs);
+					       trans->txqs.dev_cmd_offs);
 
 			*dev_cmd_ptr = dev_cmd;
 			__skb_queue_tail(&txq->overflow_q, skb);
@@ -2402,7 +1989,7 @@ int iwl_trans_pcie_tx(struct iwl_trans *trans, struct sk_buff *skb,
 		cpu_to_le16((u16)(QUEUE_TO_SEQ(txq_id) |
 			    INDEX_TO_SEQ(txq->write_ptr)));
 
-	tb0_phys = iwl_pcie_get_first_tb_dma(txq, txq->write_ptr);
+	tb0_phys = iwl_txq_get_first_tb_dma(txq, txq->write_ptr);
 	scratch_phys = tb0_phys + sizeof(struct iwl_cmd_header) +
 		       offsetof(struct iwl_tx_cmd, scratch);
 
@@ -2452,9 +2039,8 @@ int iwl_trans_pcie_tx(struct iwl_trans *trans, struct sk_buff *skb,
 	iwl_pcie_txq_build_tfd(trans, txq, tb1_phys, tb1_len, false);
 
 	trace_iwlwifi_dev_tx(trans->dev, skb,
-			     iwl_pcie_get_tfd(trans, txq,
-					      txq->write_ptr),
-			     trans_pcie->tfd_size,
+			     iwl_txq_get_tfd(trans, txq, txq->write_ptr),
+			     trans->txqs.tfd.size,
 			     &dev_cmd->hdr, IWL_FIRST_TB_SIZE + tb1_len,
 			     hdr_len);
 
@@ -2486,10 +2072,11 @@ int iwl_trans_pcie_tx(struct iwl_trans *trans, struct sk_buff *skb,
 	/* building the A-MSDU might have changed this data, so memcpy it now */
 	memcpy(&txq->first_tb_bufs[txq->write_ptr], dev_cmd, IWL_FIRST_TB_SIZE);
 
-	tfd = iwl_pcie_get_tfd(trans, txq, txq->write_ptr);
+	tfd = iwl_txq_get_tfd(trans, txq, txq->write_ptr);
 	/* Set up entry for this TFD in Tx byte-count array */
-	iwl_pcie_txq_update_byte_cnt_tbl(trans, txq, le16_to_cpu(tx_cmd->len),
-					 iwl_pcie_tfd_get_num_tbs(trans, tfd));
+	iwl_txq_gen1_update_byte_cnt_tbl(trans, txq, le16_to_cpu(tx_cmd->len),
+					 iwl_txq_gen1_tfd_get_num_tbs(trans,
+								      tfd));
 
 	wait_write_ptr = ieee80211_has_morefrags(fc);
 
@@ -2509,7 +2096,7 @@ int iwl_trans_pcie_tx(struct iwl_trans *trans, struct sk_buff *skb,
 	}
 
 	/* Tell device the write index *just past* this latest filled TFD */
-	txq->write_ptr = iwl_queue_inc_wrap(trans, txq->write_ptr);
+	txq->write_ptr = iwl_txq_inc_wrap(trans, txq->write_ptr);
 	if (!wait_write_ptr)
 		iwl_pcie_txq_inc_wr_ptr(trans, txq);
 
@@ -2520,7 +2107,7 @@ int iwl_trans_pcie_tx(struct iwl_trans *trans, struct sk_buff *skb,
 	spin_unlock(&txq->lock);
 	return 0;
 out_err:
-	iwl_pcie_tfd_unmap(trans, out_meta, txq, txq->write_ptr);
+	iwl_txq_gen1_tfd_unmap(trans, out_meta, txq, txq->write_ptr);
 	spin_unlock(&txq->lock);
 	return -1;
 }
diff --git a/drivers/net/wireless/intel/iwlwifi/queue/tx.c b/drivers/net/wireless/intel/iwlwifi/queue/tx.c
new file mode 100644
index 000000000000..af0b27a68d84
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/queue/tx.c
@@ -0,0 +1,1529 @@
+/******************************************************************************
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * Copyright(c) 2020 Intel Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * BSD LICENSE
+ *
+ * Copyright(c) 2020 Intel Corporation
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ *  * Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ *  * Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in
+ *    the documentation and/or other materials provided with the
+ *    distribution.
+ *  * Neither the name Intel Corporation nor the names of its
+ *    contributors may be used to endorse or promote products derived
+ *    from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ *****************************************************************************/
+#include <net/tso.h>
+#include <linux/tcp.h>
+
+#include "iwl-debug.h"
+#include "iwl-io.h"
+#include "fw/api/tx.h"
+#include "queue/tx.h"
+#include "iwl-fh.h"
+#include "iwl-scd.h"
+#include <linux/dmapool.h>
+
+/*
+ * iwl_txq_gen2_tx_stop - Stop all Tx DMA channels
+ */
+void iwl_txq_gen2_tx_stop(struct iwl_trans *trans)
+{
+	int txq_id;
+
+	/*
+	 * This function can be called before the op_mode disabled the
+	 * queues. This happens when we have an rfkill interrupt.
+	 * Since we stop Tx altogether - mark the queues as stopped.
+	 */
+	memset(trans->txqs.queue_stopped, 0,
+	       sizeof(trans->txqs.queue_stopped));
+	memset(trans->txqs.queue_used, 0, sizeof(trans->txqs.queue_used));
+
+	/* Unmap DMA from host system and free skb's */
+	for (txq_id = 0; txq_id < ARRAY_SIZE(trans->txqs.txq); txq_id++) {
+		if (!trans->txqs.txq[txq_id])
+			continue;
+		iwl_txq_gen2_unmap(trans, txq_id);
+	}
+}
+
+/*
+ * iwl_txq_update_byte_tbl - Set up entry in Tx byte-count array
+ */
+static void iwl_pcie_gen2_update_byte_tbl(struct iwl_trans *trans,
+					  struct iwl_txq *txq, u16 byte_cnt,
+					  int num_tbs)
+{
+	int idx = iwl_txq_get_cmd_index(txq, txq->write_ptr);
+	u8 filled_tfd_size, num_fetch_chunks;
+	u16 len = byte_cnt;
+	__le16 bc_ent;
+
+	if (WARN(idx >= txq->n_window, "%d >= %d\n", idx, txq->n_window))
+		return;
+
+	filled_tfd_size = offsetof(struct iwl_tfh_tfd, tbs) +
+			  num_tbs * sizeof(struct iwl_tfh_tb);
+	/*
+	 * filled_tfd_size contains the number of filled bytes in the TFD.
+	 * Dividing it by 64 will give the number of chunks to fetch
+	 * to SRAM- 0 for one chunk, 1 for 2 and so on.
+	 * If, for example, TFD contains only 3 TBs then 32 bytes
+	 * of the TFD are used, and only one chunk of 64 bytes should
+	 * be fetched
+	 */
+	num_fetch_chunks = DIV_ROUND_UP(filled_tfd_size, 64) - 1;
+
+	if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210) {
+		struct iwl_gen3_bc_tbl *scd_bc_tbl_gen3 = txq->bc_tbl.addr;
+
+		/* Starting from AX210, the HW expects bytes */
+		WARN_ON(trans->txqs.bc_table_dword);
+		WARN_ON(len > 0x3FFF);
+		bc_ent = cpu_to_le16(len | (num_fetch_chunks << 14));
+		scd_bc_tbl_gen3->tfd_offset[idx] = bc_ent;
+	} else {
+		struct iwlagn_scd_bc_tbl *scd_bc_tbl = txq->bc_tbl.addr;
+
+		/* Before AX210, the HW expects DW */
+		WARN_ON(!trans->txqs.bc_table_dword);
+		len = DIV_ROUND_UP(len, 4);
+		WARN_ON(len > 0xFFF);
+		bc_ent = cpu_to_le16(len | (num_fetch_chunks << 12));
+		scd_bc_tbl->tfd_offset[idx] = bc_ent;
+	}
+}
+
+/*
+ * iwl_txq_inc_wr_ptr - Send new write index to hardware
+ */
+void iwl_txq_inc_wr_ptr(struct iwl_trans *trans, struct iwl_txq *txq)
+{
+	lockdep_assert_held(&txq->lock);
+
+	IWL_DEBUG_TX(trans, "Q:%d WR: 0x%x\n", txq->id, txq->write_ptr);
+
+	/*
+	 * if not in power-save mode, uCode will never sleep when we're
+	 * trying to tx (during RFKILL, we're not trying to tx).
+	 */
+	iwl_write32(trans, HBUS_TARG_WRPTR, txq->write_ptr | (txq->id << 16));
+}
+
+static u8 iwl_txq_gen2_get_num_tbs(struct iwl_trans *trans,
+				   struct iwl_tfh_tfd *tfd)
+{
+	return le16_to_cpu(tfd->num_tbs) & 0x1f;
+}
+
+void iwl_txq_gen2_tfd_unmap(struct iwl_trans *trans, struct iwl_cmd_meta *meta,
+			    struct iwl_tfh_tfd *tfd)
+{
+	int i, num_tbs;
+
+	/* Sanity check on number of chunks */
+	num_tbs = iwl_txq_gen2_get_num_tbs(trans, tfd);
+
+	if (num_tbs > trans->txqs.tfd.max_tbs) {
+		IWL_ERR(trans, "Too many chunks: %i\n", num_tbs);
+		return;
+	}
+
+	/* first TB is never freed - it's the bidirectional DMA data */
+	for (i = 1; i < num_tbs; i++) {
+		if (meta->tbs & BIT(i))
+			dma_unmap_page(trans->dev,
+				       le64_to_cpu(tfd->tbs[i].addr),
+				       le16_to_cpu(tfd->tbs[i].tb_len),
+				       DMA_TO_DEVICE);
+		else
+			dma_unmap_single(trans->dev,
+					 le64_to_cpu(tfd->tbs[i].addr),
+					 le16_to_cpu(tfd->tbs[i].tb_len),
+					 DMA_TO_DEVICE);
+	}
+
+	tfd->num_tbs = 0;
+}
+
+void iwl_txq_gen2_free_tfd(struct iwl_trans *trans, struct iwl_txq *txq)
+{
+	/* rd_ptr is bounded by TFD_QUEUE_SIZE_MAX and
+	 * idx is bounded by n_window
+	 */
+	int idx = iwl_txq_get_cmd_index(txq, txq->read_ptr);
+
+	lockdep_assert_held(&txq->lock);
+
+	iwl_txq_gen2_tfd_unmap(trans, &txq->entries[idx].meta,
+			       iwl_txq_get_tfd(trans, txq, idx));
+
+	/* free SKB */
+	if (txq->entries) {
+		struct sk_buff *skb;
+
+		skb = txq->entries[idx].skb;
+
+		/* Can be called from irqs-disabled context
+		 * If skb is not NULL, it means that the whole queue is being
+		 * freed and that the queue is not empty - free the skb
+		 */
+		if (skb) {
+			iwl_op_mode_free_skb(trans->op_mode, skb);
+			txq->entries[idx].skb = NULL;
+		}
+	}
+}
+
+int iwl_txq_gen2_set_tb(struct iwl_trans *trans, struct iwl_tfh_tfd *tfd,
+			dma_addr_t addr, u16 len)
+{
+	int idx = iwl_txq_gen2_get_num_tbs(trans, tfd);
+	struct iwl_tfh_tb *tb;
+
+	/*
+	 * Only WARN here so we know about the issue, but we mess up our
+	 * unmap path because not every place currently checks for errors
+	 * returned from this function - it can only return an error if
+	 * there's no more space, and so when we know there is enough we
+	 * don't always check ...
+	 */
+	WARN(iwl_txq_crosses_4g_boundary(addr, len),
+	     "possible DMA problem with iova:0x%llx, len:%d\n",
+	     (unsigned long long)addr, len);
+
+	if (WARN_ON(idx >= IWL_TFH_NUM_TBS))
+		return -EINVAL;
+	tb = &tfd->tbs[idx];
+
+	/* Each TFD can point to a maximum max_tbs Tx buffers */
+	if (le16_to_cpu(tfd->num_tbs) >= trans->txqs.tfd.max_tbs) {
+		IWL_ERR(trans, "Error can not send more than %d chunks\n",
+			trans->txqs.tfd.max_tbs);
+		return -EINVAL;
+	}
+
+	put_unaligned_le64(addr, &tb->addr);
+	tb->tb_len = cpu_to_le16(len);
+
+	tfd->num_tbs = cpu_to_le16(idx + 1);
+
+	return idx;
+}
+
+static struct page *get_workaround_page(struct iwl_trans *trans,
+					struct sk_buff *skb)
+{
+	struct page **page_ptr;
+	struct page *ret;
+
+	page_ptr = (void *)((u8 *)skb->cb + trans->txqs.page_offs);
+
+	ret = alloc_page(GFP_ATOMIC);
+	if (!ret)
+		return NULL;
+
+	/* set the chaining pointer to the previous page if there */
+	*(void **)(page_address(ret) + PAGE_SIZE - sizeof(void *)) = *page_ptr;
+	*page_ptr = ret;
+
+	return ret;
+}
+
+/*
+ * Add a TB and if needed apply the FH HW bug workaround;
+ * meta != NULL indicates that it's a page mapping and we
+ * need to dma_unmap_page() and set the meta->tbs bit in
+ * this case.
+ */
+static int iwl_txq_gen2_set_tb_with_wa(struct iwl_trans *trans,
+				       struct sk_buff *skb,
+				       struct iwl_tfh_tfd *tfd,
+				       dma_addr_t phys, void *virt,
+				       u16 len, struct iwl_cmd_meta *meta)
+{
+	dma_addr_t oldphys = phys;
+	struct page *page;
+	int ret;
+
+	if (unlikely(dma_mapping_error(trans->dev, phys)))
+		return -ENOMEM;
+
+	if (likely(!iwl_txq_crosses_4g_boundary(phys, len))) {
+		ret = iwl_txq_gen2_set_tb(trans, tfd, phys, len);
+
+		if (ret < 0)
+			goto unmap;
+
+		if (meta)
+			meta->tbs |= BIT(ret);
+
+		ret = 0;
+		goto trace;
+	}
+
+	/*
+	 * Work around a hardware bug. If (as expressed in the
+	 * condition above) the TB ends on a 32-bit boundary,
+	 * then the next TB may be accessed with the wrong
+	 * address.
+	 * To work around it, copy the data elsewhere and make
+	 * a new mapping for it so the device will not fail.
+	 */
+
+	if (WARN_ON(len > PAGE_SIZE - sizeof(void *))) {
+		ret = -ENOBUFS;
+		goto unmap;
+	}
+
+	page = get_workaround_page(trans, skb);
+	if (!page) {
+		ret = -ENOMEM;
+		goto unmap;
+	}
+
+	memcpy(page_address(page), virt, len);
+
+	phys = dma_map_single(trans->dev, page_address(page), len,
+			      DMA_TO_DEVICE);
+	if (unlikely(dma_mapping_error(trans->dev, phys)))
+		return -ENOMEM;
+	ret = iwl_txq_gen2_set_tb(trans, tfd, phys, len);
+	if (ret < 0) {
+		/* unmap the new allocation as single */
+		oldphys = phys;
+		meta = NULL;
+		goto unmap;
+	}
+	IWL_WARN(trans,
+		 "TB bug workaround: copied %d bytes from 0x%llx to 0x%llx\n",
+		 len, (unsigned long long)oldphys, (unsigned long long)phys);
+
+	ret = 0;
+unmap:
+	if (meta)
+		dma_unmap_page(trans->dev, oldphys, len, DMA_TO_DEVICE);
+	else
+		dma_unmap_single(trans->dev, oldphys, len, DMA_TO_DEVICE);
+trace:
+	trace_iwlwifi_dev_tx_tb(trans->dev, skb, virt, phys, len);
+
+	return ret;
+}
+
+#ifdef CONFIG_INET
+struct iwl_tso_hdr_page *get_page_hdr(struct iwl_trans *trans, size_t len,
+				      struct sk_buff *skb)
+{
+	struct iwl_tso_hdr_page *p = this_cpu_ptr(trans->txqs.tso_hdr_page);
+	struct page **page_ptr;
+
+	page_ptr = (void *)((u8 *)skb->cb + trans->txqs.page_offs);
+
+	if (WARN_ON(*page_ptr))
+		return NULL;
+
+	if (!p->page)
+		goto alloc;
+
+	/*
+	 * Check if there's enough room on this page
+	 *
+	 * Note that we put a page chaining pointer *last* in the
+	 * page - we need it somewhere, and if it's there then we
+	 * avoid DMA mapping the last bits of the page which may
+	 * trigger the 32-bit boundary hardware bug.
+	 *
+	 * (see also get_workaround_page() in tx-gen2.c)
+	 */
+	if (p->pos + len < (u8 *)page_address(p->page) + PAGE_SIZE -
+			   sizeof(void *))
+		goto out;
+
+	/* We don't have enough room on this page, get a new one. */
+	__free_page(p->page);
+
+alloc:
+	p->page = alloc_page(GFP_ATOMIC);
+	if (!p->page)
+		return NULL;
+	p->pos = page_address(p->page);
+	/* set the chaining pointer to NULL */
+	*(void **)(page_address(p->page) + PAGE_SIZE - sizeof(void *)) = NULL;
+out:
+	*page_ptr = p->page;
+	get_page(p->page);
+	return p;
+}
+#endif
+
+static int iwl_txq_gen2_build_amsdu(struct iwl_trans *trans,
+				    struct sk_buff *skb,
+				    struct iwl_tfh_tfd *tfd, int start_len,
+				    u8 hdr_len,
+				    struct iwl_device_tx_cmd *dev_cmd)
+{
+#ifdef CONFIG_INET
+	struct iwl_tx_cmd_gen2 *tx_cmd = (void *)dev_cmd->payload;
+	struct ieee80211_hdr *hdr = (void *)skb->data;
+	unsigned int snap_ip_tcp_hdrlen, ip_hdrlen, total_len, hdr_room;
+	unsigned int mss = skb_shinfo(skb)->gso_size;
+	u16 length, amsdu_pad;
+	u8 *start_hdr;
+	struct iwl_tso_hdr_page *hdr_page;
+	struct tso_t tso;
+
+	trace_iwlwifi_dev_tx(trans->dev, skb, tfd, sizeof(*tfd),
+			     &dev_cmd->hdr, start_len, 0);
+
+	ip_hdrlen = skb_transport_header(skb) - skb_network_header(skb);
+	snap_ip_tcp_hdrlen = 8 + ip_hdrlen + tcp_hdrlen(skb);
+	total_len = skb->len - snap_ip_tcp_hdrlen - hdr_len;
+	amsdu_pad = 0;
+
+	/* total amount of header we may need for this A-MSDU */
+	hdr_room = DIV_ROUND_UP(total_len, mss) *
+		(3 + snap_ip_tcp_hdrlen + sizeof(struct ethhdr));
+
+	/* Our device supports 9 segments at most, it will fit in 1 page */
+	hdr_page = get_page_hdr(trans, hdr_room, skb);
+	if (!hdr_page)
+		return -ENOMEM;
+
+	start_hdr = hdr_page->pos;
+
+	/*
+	 * Pull the ieee80211 header to be able to use TSO core,
+	 * we will restore it for the tx_status flow.
+	 */
+	skb_pull(skb, hdr_len);
+
+	/*
+	 * Remove the length of all the headers that we don't actually
+	 * have in the MPDU by themselves, but that we duplicate into
+	 * all the different MSDUs inside the A-MSDU.
+	 */
+	le16_add_cpu(&tx_cmd->len, -snap_ip_tcp_hdrlen);
+
+	tso_start(skb, &tso);
+
+	while (total_len) {
+		/* this is the data left for this subframe */
+		unsigned int data_left = min_t(unsigned int, mss, total_len);
+		struct sk_buff *csum_skb = NULL;
+		unsigned int tb_len;
+		dma_addr_t tb_phys;
+		u8 *subf_hdrs_start = hdr_page->pos;
+
+		total_len -= data_left;
+
+		memset(hdr_page->pos, 0, amsdu_pad);
+		hdr_page->pos += amsdu_pad;
+		amsdu_pad = (4 - (sizeof(struct ethhdr) + snap_ip_tcp_hdrlen +
+				  data_left)) & 0x3;
+		ether_addr_copy(hdr_page->pos, ieee80211_get_DA(hdr));
+		hdr_page->pos += ETH_ALEN;
+		ether_addr_copy(hdr_page->pos, ieee80211_get_SA(hdr));
+		hdr_page->pos += ETH_ALEN;
+
+		length = snap_ip_tcp_hdrlen + data_left;
+		*((__be16 *)hdr_page->pos) = cpu_to_be16(length);
+		hdr_page->pos += sizeof(length);
+
+		/*
+		 * This will copy the SNAP as well which will be considered
+		 * as MAC header.
+		 */
+		tso_build_hdr(skb, hdr_page->pos, &tso, data_left, !total_len);
+
+		hdr_page->pos += snap_ip_tcp_hdrlen;
+
+		tb_len = hdr_page->pos - start_hdr;
+		tb_phys = dma_map_single(trans->dev, start_hdr,
+					 tb_len, DMA_TO_DEVICE);
+		if (unlikely(dma_mapping_error(trans->dev, tb_phys))) {
+			dev_kfree_skb(csum_skb);
+			goto out_err;
+		}
+		/*
+		 * No need for _with_wa, this is from the TSO page and
+		 * we leave some space at the end of it so can't hit
+		 * the buggy scenario.
+		 */
+		iwl_txq_gen2_set_tb(trans, tfd, tb_phys, tb_len);
+		trace_iwlwifi_dev_tx_tb(trans->dev, skb, start_hdr,
+					tb_phys, tb_len);
+		/* add this subframe's headers' length to the tx_cmd */
+		le16_add_cpu(&tx_cmd->len, hdr_page->pos - subf_hdrs_start);
+
+		/* prepare the start_hdr for the next subframe */
+		start_hdr = hdr_page->pos;
+
+		/* put the payload */
+		while (data_left) {
+			int ret;
+
+			tb_len = min_t(unsigned int, tso.size, data_left);
+			tb_phys = dma_map_single(trans->dev, tso.data,
+						 tb_len, DMA_TO_DEVICE);
+			ret = iwl_txq_gen2_set_tb_with_wa(trans, skb, tfd,
+							  tb_phys, tso.data,
+							  tb_len, NULL);
+			if (ret) {
+				dev_kfree_skb(csum_skb);
+				goto out_err;
+			}
+
+			data_left -= tb_len;
+			tso_build_data(skb, &tso, tb_len);
+		}
+	}
+
+	/* re -add the WiFi header */
+	skb_push(skb, hdr_len);
+
+	return 0;
+
+out_err:
+#endif
+	return -EINVAL;
+}
+
+static struct
+iwl_tfh_tfd *iwl_txq_gen2_build_tx_amsdu(struct iwl_trans *trans,
+					 struct iwl_txq *txq,
+					 struct iwl_device_tx_cmd *dev_cmd,
+					 struct sk_buff *skb,
+					 struct iwl_cmd_meta *out_meta,
+					 int hdr_len,
+					 int tx_cmd_len)
+{
+	int idx = iwl_txq_get_cmd_index(txq, txq->write_ptr);
+	struct iwl_tfh_tfd *tfd = iwl_txq_get_tfd(trans, txq, idx);
+	dma_addr_t tb_phys;
+	int len;
+	void *tb1_addr;
+
+	tb_phys = iwl_txq_get_first_tb_dma(txq, idx);
+
+	/*
+	 * No need for _with_wa, the first TB allocation is aligned up
+	 * to a 64-byte boundary and thus can't be at the end or cross
+	 * a page boundary (much less a 2^32 boundary).
+	 */
+	iwl_txq_gen2_set_tb(trans, tfd, tb_phys, IWL_FIRST_TB_SIZE);
+
+	/*
+	 * The second TB (tb1) points to the remainder of the TX command
+	 * and the 802.11 header - dword aligned size
+	 * (This calculation modifies the TX command, so do it before the
+	 * setup of the first TB)
+	 */
+	len = tx_cmd_len + sizeof(struct iwl_cmd_header) + hdr_len -
+	      IWL_FIRST_TB_SIZE;
+
+	/* do not align A-MSDU to dword as the subframe header aligns it */
+
+	/* map the data for TB1 */
+	tb1_addr = ((u8 *)&dev_cmd->hdr) + IWL_FIRST_TB_SIZE;
+	tb_phys = dma_map_single(trans->dev, tb1_addr, len, DMA_TO_DEVICE);
+	if (unlikely(dma_mapping_error(trans->dev, tb_phys)))
+		goto out_err;
+	/*
+	 * No need for _with_wa(), we ensure (via alignment) that the data
+	 * here can never cross or end at a page boundary.
+	 */
+	iwl_txq_gen2_set_tb(trans, tfd, tb_phys, len);
+
+	if (iwl_txq_gen2_build_amsdu(trans, skb, tfd, len + IWL_FIRST_TB_SIZE,
+				     hdr_len, dev_cmd))
+		goto out_err;
+
+	/* building the A-MSDU might have changed this data, memcpy it now */
+	memcpy(&txq->first_tb_bufs[idx], dev_cmd, IWL_FIRST_TB_SIZE);
+	return tfd;
+
+out_err:
+	iwl_txq_gen2_tfd_unmap(trans, out_meta, tfd);
+	return NULL;
+}
+
+static int iwl_txq_gen2_tx_add_frags(struct iwl_trans *trans,
+				     struct sk_buff *skb,
+				     struct iwl_tfh_tfd *tfd,
+				     struct iwl_cmd_meta *out_meta)
+{
+	int i;
+
+	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+		const skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+		dma_addr_t tb_phys;
+		unsigned int fragsz = skb_frag_size(frag);
+		int ret;
+
+		if (!fragsz)
+			continue;
+
+		tb_phys = skb_frag_dma_map(trans->dev, frag, 0,
+					   fragsz, DMA_TO_DEVICE);
+		ret = iwl_txq_gen2_set_tb_with_wa(trans, skb, tfd, tb_phys,
+						  skb_frag_address(frag),
+						  fragsz, out_meta);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static struct
+iwl_tfh_tfd *iwl_txq_gen2_build_tx(struct iwl_trans *trans,
+				   struct iwl_txq *txq,
+				   struct iwl_device_tx_cmd *dev_cmd,
+				   struct sk_buff *skb,
+				   struct iwl_cmd_meta *out_meta,
+				   int hdr_len,
+				   int tx_cmd_len,
+				   bool pad)
+{
+	int idx = iwl_txq_get_cmd_index(txq, txq->write_ptr);
+	struct iwl_tfh_tfd *tfd = iwl_txq_get_tfd(trans, txq, idx);
+	dma_addr_t tb_phys;
+	int len, tb1_len, tb2_len;
+	void *tb1_addr;
+	struct sk_buff *frag;
+
+	tb_phys = iwl_txq_get_first_tb_dma(txq, idx);
+
+	/* The first TB points to bi-directional DMA data */
+	memcpy(&txq->first_tb_bufs[idx], dev_cmd, IWL_FIRST_TB_SIZE);
+
+	/*
+	 * No need for _with_wa, the first TB allocation is aligned up
+	 * to a 64-byte boundary and thus can't be at the end or cross
+	 * a page boundary (much less a 2^32 boundary).
+	 */
+	iwl_txq_gen2_set_tb(trans, tfd, tb_phys, IWL_FIRST_TB_SIZE);
+
+	/*
+	 * The second TB (tb1) points to the remainder of the TX command
+	 * and the 802.11 header - dword aligned size
+	 * (This calculation modifies the TX command, so do it before the
+	 * setup of the first TB)
+	 */
+	len = tx_cmd_len + sizeof(struct iwl_cmd_header) + hdr_len -
+	      IWL_FIRST_TB_SIZE;
+
+	if (pad)
+		tb1_len = ALIGN(len, 4);
+	else
+		tb1_len = len;
+
+	/* map the data for TB1 */
+	tb1_addr = ((u8 *)&dev_cmd->hdr) + IWL_FIRST_TB_SIZE;
+	tb_phys = dma_map_single(trans->dev, tb1_addr, tb1_len, DMA_TO_DEVICE);
+	if (unlikely(dma_mapping_error(trans->dev, tb_phys)))
+		goto out_err;
+	/*
+	 * No need for _with_wa(), we ensure (via alignment) that the data
+	 * here can never cross or end at a page boundary.
+	 */
+	iwl_txq_gen2_set_tb(trans, tfd, tb_phys, tb1_len);
+	trace_iwlwifi_dev_tx(trans->dev, skb, tfd, sizeof(*tfd), &dev_cmd->hdr,
+			     IWL_FIRST_TB_SIZE + tb1_len, hdr_len);
+
+	/* set up TFD's third entry to point to remainder of skb's head */
+	tb2_len = skb_headlen(skb) - hdr_len;
+
+	if (tb2_len > 0) {
+		int ret;
+
+		tb_phys = dma_map_single(trans->dev, skb->data + hdr_len,
+					 tb2_len, DMA_TO_DEVICE);
+		ret = iwl_txq_gen2_set_tb_with_wa(trans, skb, tfd, tb_phys,
+						  skb->data + hdr_len, tb2_len,
+						  NULL);
+		if (ret)
+			goto out_err;
+	}
+
+	if (iwl_txq_gen2_tx_add_frags(trans, skb, tfd, out_meta))
+		goto out_err;
+
+	skb_walk_frags(skb, frag) {
+		int ret;
+
+		tb_phys = dma_map_single(trans->dev, frag->data,
+					 skb_headlen(frag), DMA_TO_DEVICE);
+		ret = iwl_txq_gen2_set_tb_with_wa(trans, skb, tfd, tb_phys,
+						  frag->data,
+						  skb_headlen(frag), NULL);
+		if (ret)
+			goto out_err;
+		if (iwl_txq_gen2_tx_add_frags(trans, frag, tfd, out_meta))
+			goto out_err;
+	}
+
+	return tfd;
+
+out_err:
+	iwl_txq_gen2_tfd_unmap(trans, out_meta, tfd);
+	return NULL;
+}
+
+static
+struct iwl_tfh_tfd *iwl_txq_gen2_build_tfd(struct iwl_trans *trans,
+					   struct iwl_txq *txq,
+					   struct iwl_device_tx_cmd *dev_cmd,
+					   struct sk_buff *skb,
+					   struct iwl_cmd_meta *out_meta)
+{
+	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
+	int idx = iwl_txq_get_cmd_index(txq, txq->write_ptr);
+	struct iwl_tfh_tfd *tfd = iwl_txq_get_tfd(trans, txq, idx);
+	int len, hdr_len;
+	bool amsdu;
+
+	/* There must be data left over for TB1 or this code must be changed */
+	BUILD_BUG_ON(sizeof(struct iwl_tx_cmd_gen2) < IWL_FIRST_TB_SIZE);
+
+	memset(tfd, 0, sizeof(*tfd));
+
+	if (trans->trans_cfg->device_family < IWL_DEVICE_FAMILY_AX210)
+		len = sizeof(struct iwl_tx_cmd_gen2);
+	else
+		len = sizeof(struct iwl_tx_cmd_gen3);
+
+	amsdu = ieee80211_is_data_qos(hdr->frame_control) &&
+			(*ieee80211_get_qos_ctl(hdr) &
+			 IEEE80211_QOS_CTL_A_MSDU_PRESENT);
+
+	hdr_len = ieee80211_hdrlen(hdr->frame_control);
+
+	/*
+	 * Only build A-MSDUs here if doing so by GSO, otherwise it may be
+	 * an A-MSDU for other reasons, e.g. NAN or an A-MSDU having been
+	 * built in the higher layers already.
+	 */
+	if (amsdu && skb_shinfo(skb)->gso_size)
+		return iwl_txq_gen2_build_tx_amsdu(trans, txq, dev_cmd, skb,
+						    out_meta, hdr_len, len);
+	return iwl_txq_gen2_build_tx(trans, txq, dev_cmd, skb, out_meta,
+				      hdr_len, len, !amsdu);
+}
+
+int iwl_txq_space(struct iwl_trans *trans, const struct iwl_txq *q)
+{
+	unsigned int max;
+	unsigned int used;
+
+	/*
+	 * To avoid ambiguity between empty and completely full queues, there
+	 * should always be less than max_tfd_queue_size elements in the queue.
+	 * If q->n_window is smaller than max_tfd_queue_size, there is no need
+	 * to reserve any queue entries for this purpose.
+	 */
+	if (q->n_window < trans->trans_cfg->base_params->max_tfd_queue_size)
+		max = q->n_window;
+	else
+		max = trans->trans_cfg->base_params->max_tfd_queue_size - 1;
+
+	/*
+	 * max_tfd_queue_size is a power of 2, so the following is equivalent to
+	 * modulo by max_tfd_queue_size and is well defined.
+	 */
+	used = (q->write_ptr - q->read_ptr) &
+		(trans->trans_cfg->base_params->max_tfd_queue_size - 1);
+
+	if (WARN_ON(used > max))
+		return 0;
+
+	return max - used;
+}
+
+int iwl_txq_gen2_tx(struct iwl_trans *trans, struct sk_buff *skb,
+		    struct iwl_device_tx_cmd *dev_cmd, int txq_id)
+{
+	struct iwl_cmd_meta *out_meta;
+	struct iwl_txq *txq = trans->txqs.txq[txq_id];
+	u16 cmd_len;
+	int idx;
+	void *tfd;
+
+	if (WARN_ONCE(txq_id >= IWL_MAX_TVQM_QUEUES,
+		      "queue %d out of range", txq_id))
+		return -EINVAL;
+
+	if (WARN_ONCE(!test_bit(txq_id, trans->txqs.queue_used),
+		      "TX on unused queue %d\n", txq_id))
+		return -EINVAL;
+
+	if (skb_is_nonlinear(skb) &&
+	    skb_shinfo(skb)->nr_frags > IWL_TRANS_MAX_FRAGS(trans) &&
+	    __skb_linearize(skb))
+		return -ENOMEM;
+
+	spin_lock(&txq->lock);
+
+	if (iwl_txq_space(trans, txq) < txq->high_mark) {
+		iwl_txq_stop(trans, txq);
+
+		/* don't put the packet on the ring, if there is no room */
+		if (unlikely(iwl_txq_space(trans, txq) < 3)) {
+			struct iwl_device_tx_cmd **dev_cmd_ptr;
+
+			dev_cmd_ptr = (void *)((u8 *)skb->cb +
+					       trans->txqs.dev_cmd_offs);
+
+			*dev_cmd_ptr = dev_cmd;
+			__skb_queue_tail(&txq->overflow_q, skb);
+			spin_unlock(&txq->lock);
+			return 0;
+		}
+	}
+
+	idx = iwl_txq_get_cmd_index(txq, txq->write_ptr);
+
+	/* Set up driver data for this TFD */
+	txq->entries[idx].skb = skb;
+	txq->entries[idx].cmd = dev_cmd;
+
+	dev_cmd->hdr.sequence =
+		cpu_to_le16((u16)(QUEUE_TO_SEQ(txq_id) |
+			    INDEX_TO_SEQ(idx)));
+
+	/* Set up first empty entry in queue's array of Tx/cmd buffers */
+	out_meta = &txq->entries[idx].meta;
+	out_meta->flags = 0;
+
+	tfd = iwl_txq_gen2_build_tfd(trans, txq, dev_cmd, skb, out_meta);
+	if (!tfd) {
+		spin_unlock(&txq->lock);
+		return -1;
+	}
+
+	if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210) {
+		struct iwl_tx_cmd_gen3 *tx_cmd_gen3 =
+			(void *)dev_cmd->payload;
+
+		cmd_len = le16_to_cpu(tx_cmd_gen3->len);
+	} else {
+		struct iwl_tx_cmd_gen2 *tx_cmd_gen2 =
+			(void *)dev_cmd->payload;
+
+		cmd_len = le16_to_cpu(tx_cmd_gen2->len);
+	}
+
+	/* Set up entry for this TFD in Tx byte-count array */
+	iwl_pcie_gen2_update_byte_tbl(trans, txq, cmd_len,
+				      iwl_txq_gen2_get_num_tbs(trans, tfd));
+
+	/* start timer if queue currently empty */
+	if (txq->read_ptr == txq->write_ptr && txq->wd_timeout)
+		mod_timer(&txq->stuck_timer, jiffies + txq->wd_timeout);
+
+	/* Tell device the write index *just past* this latest filled TFD */
+	txq->write_ptr = iwl_txq_inc_wrap(trans, txq->write_ptr);
+	iwl_txq_inc_wr_ptr(trans, txq);
+	/*
+	 * At this point the frame is "transmitted" successfully
+	 * and we will get a TX status notification eventually.
+	 */
+	spin_unlock(&txq->lock);
+	return 0;
+}
+
+/*************** HOST COMMAND QUEUE FUNCTIONS   *****/
+
+/*
+ * iwl_txq_gen2_unmap -  Unmap any remaining DMA mappings and free skb's
+ */
+void iwl_txq_gen2_unmap(struct iwl_trans *trans, int txq_id)
+{
+	struct iwl_txq *txq = trans->txqs.txq[txq_id];
+
+	spin_lock_bh(&txq->lock);
+	while (txq->write_ptr != txq->read_ptr) {
+		IWL_DEBUG_TX_REPLY(trans, "Q %d Free %d\n",
+				   txq_id, txq->read_ptr);
+
+		if (txq_id != trans->txqs.cmd.q_id) {
+			int idx = iwl_txq_get_cmd_index(txq, txq->read_ptr);
+			struct sk_buff *skb = txq->entries[idx].skb;
+
+			if (WARN_ON_ONCE(!skb))
+				continue;
+
+			iwl_txq_free_tso_page(trans, skb);
+		}
+		iwl_txq_gen2_free_tfd(trans, txq);
+		txq->read_ptr = iwl_txq_inc_wrap(trans, txq->read_ptr);
+	}
+
+	while (!skb_queue_empty(&txq->overflow_q)) {
+		struct sk_buff *skb = __skb_dequeue(&txq->overflow_q);
+
+		iwl_op_mode_free_skb(trans->op_mode, skb);
+	}
+
+	spin_unlock_bh(&txq->lock);
+
+	/* just in case - this queue may have been stopped */
+	iwl_wake_queue(trans, txq);
+}
+
+static void iwl_txq_gen2_free_memory(struct iwl_trans *trans,
+				     struct iwl_txq *txq)
+{
+	struct device *dev = trans->dev;
+
+	/* De-alloc circular buffer of TFDs */
+	if (txq->tfds) {
+		dma_free_coherent(dev,
+				  trans->txqs.tfd.size * txq->n_window,
+				  txq->tfds, txq->dma_addr);
+		dma_free_coherent(dev,
+				  sizeof(*txq->first_tb_bufs) * txq->n_window,
+				  txq->first_tb_bufs, txq->first_tb_dma);
+	}
+
+	kfree(txq->entries);
+	if (txq->bc_tbl.addr)
+		dma_pool_free(trans->txqs.bc_pool,
+			      txq->bc_tbl.addr, txq->bc_tbl.dma);
+	kfree(txq);
+}
+
+/*
+ * iwl_pcie_txq_free - Deallocate DMA queue.
+ * @txq: Transmit queue to deallocate.
+ *
+ * Empty queue by removing and destroying all BD's.
+ * Free all buffers.
+ * 0-fill, but do not free "txq" descriptor structure.
+ */
+static void iwl_txq_gen2_free(struct iwl_trans *trans, int txq_id)
+{
+	struct iwl_txq *txq;
+	int i;
+
+	if (WARN_ONCE(txq_id >= IWL_MAX_TVQM_QUEUES,
+		      "queue %d out of range", txq_id))
+		return;
+
+	txq = trans->txqs.txq[txq_id];
+
+	if (WARN_ON(!txq))
+		return;
+
+	iwl_txq_gen2_unmap(trans, txq_id);
+
+	/* De-alloc array of command/tx buffers */
+	if (txq_id == trans->txqs.cmd.q_id)
+		for (i = 0; i < txq->n_window; i++) {
+			kfree_sensitive(txq->entries[i].cmd);
+			kfree_sensitive(txq->entries[i].free_buf);
+		}
+	del_timer_sync(&txq->stuck_timer);
+
+	iwl_txq_gen2_free_memory(trans, txq);
+
+	trans->txqs.txq[txq_id] = NULL;
+
+	clear_bit(txq_id, trans->txqs.queue_used);
+}
+
+/*
+ * iwl_queue_init - Initialize queue's high/low-water and read/write indexes
+ */
+static int iwl_queue_init(struct iwl_txq *q, int slots_num)
+{
+	q->n_window = slots_num;
+
+	/* slots_num must be power-of-two size, otherwise
+	 * iwl_txq_get_cmd_index is broken. */
+	if (WARN_ON(!is_power_of_2(slots_num)))
+		return -EINVAL;
+
+	q->low_mark = q->n_window / 4;
+	if (q->low_mark < 4)
+		q->low_mark = 4;
+
+	q->high_mark = q->n_window / 8;
+	if (q->high_mark < 2)
+		q->high_mark = 2;
+
+	q->write_ptr = 0;
+	q->read_ptr = 0;
+
+	return 0;
+}
+
+int iwl_txq_init(struct iwl_trans *trans, struct iwl_txq *txq, int slots_num,
+		 bool cmd_queue)
+{
+	int ret;
+	u32 tfd_queue_max_size =
+		trans->trans_cfg->base_params->max_tfd_queue_size;
+
+	txq->need_update = false;
+
+	/* max_tfd_queue_size must be power-of-two size, otherwise
+	 * iwl_txq_inc_wrap and iwl_txq_dec_wrap are broken. */
+	if (WARN_ONCE(tfd_queue_max_size & (tfd_queue_max_size - 1),
+		      "Max tfd queue size must be a power of two, but is %d",
+		      tfd_queue_max_size))
+		return -EINVAL;
+
+	/* Initialize queue's high/low-water marks, and head/tail indexes */
+	ret = iwl_queue_init(txq, slots_num);
+	if (ret)
+		return ret;
+
+	spin_lock_init(&txq->lock);
+
+	if (cmd_queue) {
+		static struct lock_class_key iwl_txq_cmd_queue_lock_class;
+
+		lockdep_set_class(&txq->lock, &iwl_txq_cmd_queue_lock_class);
+	}
+
+	__skb_queue_head_init(&txq->overflow_q);
+
+	return 0;
+}
+
+void iwl_txq_free_tso_page(struct iwl_trans *trans, struct sk_buff *skb)
+{
+	struct page **page_ptr;
+	struct page *next;
+
+	page_ptr = (void *)((u8 *)skb->cb + trans->txqs.page_offs);
+	next = *page_ptr;
+	*page_ptr = NULL;
+
+	while (next) {
+		struct page *tmp = next;
+
+		next = *(void **)(page_address(next) + PAGE_SIZE -
+				  sizeof(void *));
+		__free_page(tmp);
+	}
+}
+
+void iwl_txq_log_scd_error(struct iwl_trans *trans, struct iwl_txq *txq)
+{
+	u32 txq_id = txq->id;
+	u32 status;
+	bool active;
+	u8 fifo;
+
+	if (trans->trans_cfg->use_tfh) {
+		IWL_ERR(trans, "Queue %d is stuck %d %d\n", txq_id,
+			txq->read_ptr, txq->write_ptr);
+		/* TODO: access new SCD registers and dump them */
+		return;
+	}
+
+	status = iwl_read_prph(trans, SCD_QUEUE_STATUS_BITS(txq_id));
+	fifo = (status >> SCD_QUEUE_STTS_REG_POS_TXF) & 0x7;
+	active = !!(status & BIT(SCD_QUEUE_STTS_REG_POS_ACTIVE));
+
+	IWL_ERR(trans,
+		"Queue %d is %sactive on fifo %d and stuck for %u ms. SW [%d, %d] HW [%d, %d] FH TRB=0x0%x\n",
+		txq_id, active ? "" : "in", fifo,
+		jiffies_to_msecs(txq->wd_timeout),
+		txq->read_ptr, txq->write_ptr,
+		iwl_read_prph(trans, SCD_QUEUE_RDPTR(txq_id)) &
+			(trans->trans_cfg->base_params->max_tfd_queue_size - 1),
+			iwl_read_prph(trans, SCD_QUEUE_WRPTR(txq_id)) &
+			(trans->trans_cfg->base_params->max_tfd_queue_size - 1),
+			iwl_read_direct32(trans, FH_TX_TRB_REG(fifo)));
+}
+
+static void iwl_txq_stuck_timer(struct timer_list *t)
+{
+	struct iwl_txq *txq = from_timer(txq, t, stuck_timer);
+	struct iwl_trans *trans = txq->trans;
+
+	spin_lock(&txq->lock);
+	/* check if triggered erroneously */
+	if (txq->read_ptr == txq->write_ptr) {
+		spin_unlock(&txq->lock);
+		return;
+	}
+	spin_unlock(&txq->lock);
+
+	iwl_txq_log_scd_error(trans, txq);
+
+	iwl_force_nmi(trans);
+}
+
+int iwl_txq_alloc(struct iwl_trans *trans, struct iwl_txq *txq, int slots_num,
+		  bool cmd_queue)
+{
+	size_t tfd_sz = trans->txqs.tfd.size *
+		trans->trans_cfg->base_params->max_tfd_queue_size;
+	size_t tb0_buf_sz;
+	int i;
+
+	if (WARN_ON(txq->entries || txq->tfds))
+		return -EINVAL;
+
+	if (trans->trans_cfg->use_tfh)
+		tfd_sz = trans->txqs.tfd.size * slots_num;
+
+	timer_setup(&txq->stuck_timer, iwl_txq_stuck_timer, 0);
+	txq->trans = trans;
+
+	txq->n_window = slots_num;
+
+	txq->entries = kcalloc(slots_num,
+			       sizeof(struct iwl_pcie_txq_entry),
+			       GFP_KERNEL);
+
+	if (!txq->entries)
+		goto error;
+
+	if (cmd_queue)
+		for (i = 0; i < slots_num; i++) {
+			txq->entries[i].cmd =
+				kmalloc(sizeof(struct iwl_device_cmd),
+					GFP_KERNEL);
+			if (!txq->entries[i].cmd)
+				goto error;
+		}
+
+	/* Circular buffer of transmit frame descriptors (TFDs),
+	 * shared with device */
+	txq->tfds = dma_alloc_coherent(trans->dev, tfd_sz,
+				       &txq->dma_addr, GFP_KERNEL);
+	if (!txq->tfds)
+		goto error;
+
+	BUILD_BUG_ON(sizeof(*txq->first_tb_bufs) != IWL_FIRST_TB_SIZE_ALIGN);
+
+	tb0_buf_sz = sizeof(*txq->first_tb_bufs) * slots_num;
+
+	txq->first_tb_bufs = dma_alloc_coherent(trans->dev, tb0_buf_sz,
+						&txq->first_tb_dma,
+						GFP_KERNEL);
+	if (!txq->first_tb_bufs)
+		goto err_free_tfds;
+
+	return 0;
+err_free_tfds:
+	dma_free_coherent(trans->dev, tfd_sz, txq->tfds, txq->dma_addr);
+error:
+	if (txq->entries && cmd_queue)
+		for (i = 0; i < slots_num; i++)
+			kfree(txq->entries[i].cmd);
+	kfree(txq->entries);
+	txq->entries = NULL;
+
+	return -ENOMEM;
+}
+
+static int iwl_txq_dyn_alloc_dma(struct iwl_trans *trans,
+				 struct iwl_txq **intxq, int size,
+				 unsigned int timeout)
+{
+	size_t bc_tbl_size, bc_tbl_entries;
+	struct iwl_txq *txq;
+	int ret;
+
+	WARN_ON(!trans->txqs.bc_tbl_size);
+
+	bc_tbl_size = trans->txqs.bc_tbl_size;
+	bc_tbl_entries = bc_tbl_size / sizeof(u16);
+
+	if (WARN_ON(size > bc_tbl_entries))
+		return -EINVAL;
+
+	txq = kzalloc(sizeof(*txq), GFP_KERNEL);
+	if (!txq)
+		return -ENOMEM;
+
+	txq->bc_tbl.addr = dma_pool_alloc(trans->txqs.bc_pool, GFP_KERNEL,
+					  &txq->bc_tbl.dma);
+	if (!txq->bc_tbl.addr) {
+		IWL_ERR(trans, "Scheduler BC Table allocation failed\n");
+		kfree(txq);
+		return -ENOMEM;
+	}
+
+	ret = iwl_txq_alloc(trans, txq, size, false);
+	if (ret) {
+		IWL_ERR(trans, "Tx queue alloc failed\n");
+		goto error;
+	}
+	ret = iwl_txq_init(trans, txq, size, false);
+	if (ret) {
+		IWL_ERR(trans, "Tx queue init failed\n");
+		goto error;
+	}
+
+	txq->wd_timeout = msecs_to_jiffies(timeout);
+
+	*intxq = txq;
+	return 0;
+
+error:
+	iwl_txq_gen2_free_memory(trans, txq);
+	return ret;
+}
+
+static int iwl_txq_alloc_response(struct iwl_trans *trans, struct iwl_txq *txq,
+				  struct iwl_host_cmd *hcmd)
+{
+	struct iwl_tx_queue_cfg_rsp *rsp;
+	int ret, qid;
+	u32 wr_ptr;
+
+	if (WARN_ON(iwl_rx_packet_payload_len(hcmd->resp_pkt) !=
+		    sizeof(*rsp))) {
+		ret = -EINVAL;
+		goto error_free_resp;
+	}
+
+	rsp = (void *)hcmd->resp_pkt->data;
+	qid = le16_to_cpu(rsp->queue_number);
+	wr_ptr = le16_to_cpu(rsp->write_pointer);
+
+	if (qid >= ARRAY_SIZE(trans->txqs.txq)) {
+		WARN_ONCE(1, "queue index %d unsupported", qid);
+		ret = -EIO;
+		goto error_free_resp;
+	}
+
+	if (test_and_set_bit(qid, trans->txqs.queue_used)) {
+		WARN_ONCE(1, "queue %d already used", qid);
+		ret = -EIO;
+		goto error_free_resp;
+	}
+
+	txq->id = qid;
+	trans->txqs.txq[qid] = txq;
+	wr_ptr &= (trans->trans_cfg->base_params->max_tfd_queue_size - 1);
+
+	/* Place first TFD at index corresponding to start sequence number */
+	txq->read_ptr = wr_ptr;
+	txq->write_ptr = wr_ptr;
+
+	IWL_DEBUG_TX_QUEUES(trans, "Activate queue %d\n", qid);
+
+	iwl_free_resp(hcmd);
+	return qid;
+
+error_free_resp:
+	iwl_free_resp(hcmd);
+	iwl_txq_gen2_free_memory(trans, txq);
+	return ret;
+}
+
+int iwl_txq_dyn_alloc(struct iwl_trans *trans, __le16 flags, u8 sta_id, u8 tid,
+		      int cmd_id, int size, unsigned int timeout)
+{
+	struct iwl_txq *txq = NULL;
+	struct iwl_tx_queue_cfg_cmd cmd = {
+		.flags = flags,
+		.sta_id = sta_id,
+		.tid = tid,
+	};
+	struct iwl_host_cmd hcmd = {
+		.id = cmd_id,
+		.len = { sizeof(cmd) },
+		.data = { &cmd, },
+		.flags = CMD_WANT_SKB,
+	};
+	int ret;
+
+	ret = iwl_txq_dyn_alloc_dma(trans, &txq, size, timeout);
+	if (ret)
+		return ret;
+
+	cmd.tfdq_addr = cpu_to_le64(txq->dma_addr);
+	cmd.byte_cnt_addr = cpu_to_le64(txq->bc_tbl.dma);
+	cmd.cb_size = cpu_to_le32(TFD_QUEUE_CB_SIZE(size));
+
+	ret = iwl_trans_send_cmd(trans, &hcmd);
+	if (ret)
+		goto error;
+
+	return iwl_txq_alloc_response(trans, txq, &hcmd);
+
+error:
+	iwl_txq_gen2_free_memory(trans, txq);
+	return ret;
+}
+
+void iwl_txq_dyn_free(struct iwl_trans *trans, int queue)
+{
+	if (WARN(queue >= IWL_MAX_TVQM_QUEUES,
+		 "queue %d out of range", queue))
+		return;
+
+	/*
+	 * Upon HW Rfkill - we stop the device, and then stop the queues
+	 * in the op_mode. Just for the sake of the simplicity of the op_mode,
+	 * allow the op_mode to call txq_disable after it already called
+	 * stop_device.
+	 */
+	if (!test_and_clear_bit(queue, trans->txqs.queue_used)) {
+		WARN_ONCE(test_bit(STATUS_DEVICE_ENABLED, &trans->status),
+			  "queue %d not used", queue);
+		return;
+	}
+
+	iwl_txq_gen2_unmap(trans, queue);
+
+	iwl_txq_gen2_free_memory(trans, trans->txqs.txq[queue]);
+
+	trans->txqs.txq[queue] = NULL;
+
+	IWL_DEBUG_TX_QUEUES(trans, "Deactivate queue %d\n", queue);
+}
+
+void iwl_txq_gen2_tx_free(struct iwl_trans *trans)
+{
+	int i;
+
+	memset(trans->txqs.queue_used, 0, sizeof(trans->txqs.queue_used));
+
+	/* Free all TX queues */
+	for (i = 0; i < ARRAY_SIZE(trans->txqs.txq); i++) {
+		if (!trans->txqs.txq[i])
+			continue;
+
+		iwl_txq_gen2_free(trans, i);
+	}
+}
+
+int iwl_txq_gen2_init(struct iwl_trans *trans, int txq_id, int queue_size)
+{
+	struct iwl_txq *queue;
+	int ret;
+
+	/* alloc and init the tx queue */
+	if (!trans->txqs.txq[txq_id]) {
+		queue = kzalloc(sizeof(*queue), GFP_KERNEL);
+		if (!queue) {
+			IWL_ERR(trans, "Not enough memory for tx queue\n");
+			return -ENOMEM;
+		}
+		trans->txqs.txq[txq_id] = queue;
+		ret = iwl_txq_alloc(trans, queue, queue_size, true);
+		if (ret) {
+			IWL_ERR(trans, "Tx %d queue init failed\n", txq_id);
+			goto error;
+		}
+	} else {
+		queue = trans->txqs.txq[txq_id];
+	}
+
+	ret = iwl_txq_init(trans, queue, queue_size,
+			   (txq_id == trans->txqs.cmd.q_id));
+	if (ret) {
+		IWL_ERR(trans, "Tx %d queue alloc failed\n", txq_id);
+		goto error;
+	}
+	trans->txqs.txq[txq_id]->id = txq_id;
+	set_bit(txq_id, trans->txqs.queue_used);
+
+	return 0;
+
+error:
+	iwl_txq_gen2_tx_free(trans);
+	return ret;
+}
+
+static inline dma_addr_t iwl_txq_gen1_tfd_tb_get_addr(struct iwl_trans *trans,
+						      void *_tfd, u8 idx)
+{
+	struct iwl_tfd *tfd;
+	struct iwl_tfd_tb *tb;
+	dma_addr_t addr;
+	dma_addr_t hi_len;
+
+	if (trans->trans_cfg->use_tfh) {
+		struct iwl_tfh_tfd *tfd = _tfd;
+		struct iwl_tfh_tb *tb = &tfd->tbs[idx];
+
+		return (dma_addr_t)(le64_to_cpu(tb->addr));
+	}
+
+	tfd = _tfd;
+	tb = &tfd->tbs[idx];
+	addr = get_unaligned_le32(&tb->lo);
+
+	if (sizeof(dma_addr_t) <= sizeof(u32))
+		return addr;
+
+	hi_len = le16_to_cpu(tb->hi_n_len) & 0xF;
+
+	/*
+	 * shift by 16 twice to avoid warnings on 32-bit
+	 * (where this code never runs anyway due to the
+	 * if statement above)
+	 */
+	return addr | ((hi_len << 16) << 16);
+}
+
+void iwl_txq_gen1_tfd_unmap(struct iwl_trans *trans,
+			    struct iwl_cmd_meta *meta,
+			    struct iwl_txq *txq, int index)
+{
+	int i, num_tbs;
+	void *tfd = iwl_txq_get_tfd(trans, txq, index);
+
+	/* Sanity check on number of chunks */
+	num_tbs = iwl_txq_gen1_tfd_get_num_tbs(trans, tfd);
+
+	if (num_tbs > trans->txqs.tfd.max_tbs) {
+		IWL_ERR(trans, "Too many chunks: %i\n", num_tbs);
+		/* @todo issue fatal error, it is quite serious situation */
+		return;
+	}
+
+	/* first TB is never freed - it's the bidirectional DMA data */
+
+	for (i = 1; i < num_tbs; i++) {
+		if (meta->tbs & BIT(i))
+			dma_unmap_page(trans->dev,
+				       iwl_txq_gen1_tfd_tb_get_addr(trans,
+								    tfd, i),
+				       iwl_txq_gen1_tfd_tb_get_len(trans,
+								   tfd, i),
+				       DMA_TO_DEVICE);
+		else
+			dma_unmap_single(trans->dev,
+					 iwl_txq_gen1_tfd_tb_get_addr(trans,
+								      tfd, i),
+					 iwl_txq_gen1_tfd_tb_get_len(trans,
+								     tfd, i),
+					 DMA_TO_DEVICE);
+	}
+
+	meta->tbs = 0;
+
+	if (trans->trans_cfg->use_tfh) {
+		struct iwl_tfh_tfd *tfd_fh = (void *)tfd;
+
+		tfd_fh->num_tbs = 0;
+	} else {
+		struct iwl_tfd *tfd_fh = (void *)tfd;
+
+		tfd_fh->num_tbs = 0;
+	}
+}
+
+#define IWL_TX_CRC_SIZE 4
+#define IWL_TX_DELIMITER_SIZE 4
+
+/*
+ * iwl_txq_gen1_update_byte_cnt_tbl - Set up entry in Tx byte-count array
+ */
+void iwl_txq_gen1_update_byte_cnt_tbl(struct iwl_trans *trans,
+				      struct iwl_txq *txq, u16 byte_cnt,
+				      int num_tbs)
+{
+	struct iwlagn_scd_bc_tbl *scd_bc_tbl;
+	int write_ptr = txq->write_ptr;
+	int txq_id = txq->id;
+	u8 sec_ctl = 0;
+	u16 len = byte_cnt + IWL_TX_CRC_SIZE + IWL_TX_DELIMITER_SIZE;
+	__le16 bc_ent;
+	struct iwl_device_tx_cmd *dev_cmd = txq->entries[txq->write_ptr].cmd;
+	struct iwl_tx_cmd *tx_cmd = (void *)dev_cmd->payload;
+	u8 sta_id = tx_cmd->sta_id;
+
+	scd_bc_tbl = trans->txqs.scd_bc_tbls.addr;
+
+	sec_ctl = tx_cmd->sec_ctl;
+
+	switch (sec_ctl & TX_CMD_SEC_MSK) {
+	case TX_CMD_SEC_CCM:
+		len += IEEE80211_CCMP_MIC_LEN;
+		break;
+	case TX_CMD_SEC_TKIP:
+		len += IEEE80211_TKIP_ICV_LEN;
+		break;
+	case TX_CMD_SEC_WEP:
+		len += IEEE80211_WEP_IV_LEN + IEEE80211_WEP_ICV_LEN;
+		break;
+	}
+	if (trans->txqs.bc_table_dword)
+		len = DIV_ROUND_UP(len, 4);
+
+	if (WARN_ON(len > 0xFFF || write_ptr >= TFD_QUEUE_SIZE_MAX))
+		return;
+
+	bc_ent = cpu_to_le16(len | (sta_id << 12));
+
+	scd_bc_tbl[txq_id].tfd_offset[write_ptr] = bc_ent;
+
+	if (write_ptr < TFD_QUEUE_SIZE_BC_DUP)
+		scd_bc_tbl[txq_id].tfd_offset[TFD_QUEUE_SIZE_MAX + write_ptr] =
+			bc_ent;
+}
+
+void iwl_txq_gen1_inval_byte_cnt_tbl(struct iwl_trans *trans,
+				     struct iwl_txq *txq)
+{
+	struct iwlagn_scd_bc_tbl *scd_bc_tbl = trans->txqs.scd_bc_tbls.addr;
+	int txq_id = txq->id;
+	int read_ptr = txq->read_ptr;
+	u8 sta_id = 0;
+	__le16 bc_ent;
+	struct iwl_device_tx_cmd *dev_cmd = txq->entries[read_ptr].cmd;
+	struct iwl_tx_cmd *tx_cmd = (void *)dev_cmd->payload;
+
+	WARN_ON(read_ptr >= TFD_QUEUE_SIZE_MAX);
+
+	if (txq_id != trans->txqs.cmd.q_id)
+		sta_id = tx_cmd->sta_id;
+
+	bc_ent = cpu_to_le16(1 | (sta_id << 12));
+
+	scd_bc_tbl[txq_id].tfd_offset[read_ptr] = bc_ent;
+
+	if (read_ptr < TFD_QUEUE_SIZE_BC_DUP)
+		scd_bc_tbl[txq_id].tfd_offset[TFD_QUEUE_SIZE_MAX + read_ptr] =
+			bc_ent;
+}
diff --git a/drivers/net/wireless/intel/iwlwifi/queue/tx.h b/drivers/net/wireless/intel/iwlwifi/queue/tx.h
new file mode 100644
index 000000000000..c67577dfa21d
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/queue/tx.h
@@ -0,0 +1,230 @@
+/******************************************************************************
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * Copyright(c) 2020 Intel Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * The full GNU General Public License is included in this distribution in the
+ * file called COPYING.
+ *
+ * Contact Information:
+ *  Intel Linux Wireless <linuxwifi@intel.com>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ *
+ * BSD LICENSE
+ *
+ * Copyright(c) 2020 Intel Corporation
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ *  * Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ *  * Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in
+ *    the documentation and/or other materials provided with the
+ *    distribution.
+ *  * Neither the name Intel Corporation nor the names of its
+ *    contributors may be used to endorse or promote products derived
+ *    from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ *****************************************************************************/
+#ifndef __iwl_trans_queue_tx_h__
+#define __iwl_trans_queue_tx_h__
+#include "iwl-fh.h"
+#include "fw/api/tx.h"
+
+struct iwl_tso_hdr_page {
+	struct page *page;
+	u8 *pos;
+};
+
+static inline dma_addr_t
+iwl_txq_get_first_tb_dma(struct iwl_txq *txq, int idx)
+{
+	return txq->first_tb_dma +
+	       sizeof(struct iwl_pcie_first_tb_buf) * idx;
+}
+
+static inline u16 iwl_txq_get_cmd_index(const struct iwl_txq *q, u32 index)
+{
+	return index & (q->n_window - 1);
+}
+
+void iwl_txq_gen2_unmap(struct iwl_trans *trans, int txq_id);
+
+static inline void iwl_wake_queue(struct iwl_trans *trans,
+				  struct iwl_txq *txq)
+{
+	if (test_and_clear_bit(txq->id, trans->txqs.queue_stopped)) {
+		IWL_DEBUG_TX_QUEUES(trans, "Wake hwq %d\n", txq->id);
+		iwl_op_mode_queue_not_full(trans->op_mode, txq->id);
+	}
+}
+
+static inline void *iwl_txq_get_tfd(struct iwl_trans *trans,
+				    struct iwl_txq *txq, int idx)
+{
+	if (trans->trans_cfg->use_tfh)
+		idx = iwl_txq_get_cmd_index(txq, idx);
+
+	return txq->tfds + trans->txqs.tfd.size * idx;
+}
+
+int iwl_txq_alloc(struct iwl_trans *trans, struct iwl_txq *txq, int slots_num,
+		  bool cmd_queue);
+/*
+ * We need this inline in case dma_addr_t is only 32-bits - since the
+ * hardware is always 64-bit, the issue can still occur in that case,
+ * so use u64 for 'phys' here to force the addition in 64-bit.
+ */
+static inline bool iwl_txq_crosses_4g_boundary(u64 phys, u16 len)
+{
+	return upper_32_bits(phys) != upper_32_bits(phys + len);
+}
+
+int iwl_txq_space(struct iwl_trans *trans, const struct iwl_txq *q);
+
+static inline void iwl_txq_stop(struct iwl_trans *trans, struct iwl_txq *txq)
+{
+	if (!test_and_set_bit(txq->id, trans->txqs.queue_stopped)) {
+		iwl_op_mode_queue_full(trans->op_mode, txq->id);
+		IWL_DEBUG_TX_QUEUES(trans, "Stop hwq %d\n", txq->id);
+	} else {
+		IWL_DEBUG_TX_QUEUES(trans, "hwq %d already stopped\n",
+				    txq->id);
+	}
+}
+
+/**
+ * iwl_txq_inc_wrap - increment queue index, wrap back to beginning
+ * @index -- current index
+ */
+static inline int iwl_txq_inc_wrap(struct iwl_trans *trans, int index)
+{
+	return ++index &
+		(trans->trans_cfg->base_params->max_tfd_queue_size - 1);
+}
+
+/**
+ * iwl_txq_dec_wrap - decrement queue index, wrap back to end
+ * @index -- current index
+ */
+static inline int iwl_txq_dec_wrap(struct iwl_trans *trans, int index)
+{
+	return --index &
+		(trans->trans_cfg->base_params->max_tfd_queue_size - 1);
+}
+
+static inline bool iwl_txq_used(const struct iwl_txq *q, int i)
+{
+	int index = iwl_txq_get_cmd_index(q, i);
+	int r = iwl_txq_get_cmd_index(q, q->read_ptr);
+	int w = iwl_txq_get_cmd_index(q, q->write_ptr);
+
+	return w >= r ?
+		(index >= r && index < w) :
+		!(index < r && index >= w);
+}
+
+void iwl_txq_free_tso_page(struct iwl_trans *trans, struct sk_buff *skb);
+
+void iwl_txq_log_scd_error(struct iwl_trans *trans, struct iwl_txq *txq);
+
+int iwl_txq_gen2_set_tb(struct iwl_trans *trans,
+			struct iwl_tfh_tfd *tfd, dma_addr_t addr,
+			u16 len);
+
+void iwl_txq_gen2_tfd_unmap(struct iwl_trans *trans,
+			    struct iwl_cmd_meta *meta,
+			    struct iwl_tfh_tfd *tfd);
+
+int iwl_txq_dyn_alloc(struct iwl_trans *trans,
+		      __le16 flags, u8 sta_id, u8 tid,
+		      int cmd_id, int size,
+		      unsigned int timeout);
+
+int iwl_txq_gen2_tx(struct iwl_trans *trans, struct sk_buff *skb,
+		    struct iwl_device_tx_cmd *dev_cmd, int txq_id);
+
+void iwl_txq_dyn_free(struct iwl_trans *trans, int queue);
+void iwl_txq_gen2_free_tfd(struct iwl_trans *trans, struct iwl_txq *txq);
+void iwl_txq_inc_wr_ptr(struct iwl_trans *trans, struct iwl_txq *txq);
+void iwl_txq_gen2_tx_stop(struct iwl_trans *trans);
+void iwl_txq_gen2_tx_free(struct iwl_trans *trans);
+int iwl_txq_init(struct iwl_trans *trans, struct iwl_txq *txq, int slots_num,
+		 bool cmd_queue);
+int iwl_txq_gen2_init(struct iwl_trans *trans, int txq_id, int queue_size);
+#ifdef CONFIG_INET
+struct iwl_tso_hdr_page *get_page_hdr(struct iwl_trans *trans, size_t len,
+				      struct sk_buff *skb);
+#endif
+static inline u8 iwl_txq_gen1_tfd_get_num_tbs(struct iwl_trans *trans,
+					      void *_tfd)
+{
+	struct iwl_tfd *tfd;
+
+	if (trans->trans_cfg->use_tfh) {
+		struct iwl_tfh_tfd *tfd = _tfd;
+
+		return le16_to_cpu(tfd->num_tbs) & 0x1f;
+	}
+
+	tfd = (struct iwl_tfd *)_tfd;
+	return tfd->num_tbs & 0x1f;
+}
+
+static inline u16 iwl_txq_gen1_tfd_tb_get_len(struct iwl_trans *trans,
+					      void *_tfd, u8 idx)
+{
+	struct iwl_tfd *tfd;
+	struct iwl_tfd_tb *tb;
+
+	if (trans->trans_cfg->use_tfh) {
+		struct iwl_tfh_tfd *tfd = _tfd;
+		struct iwl_tfh_tb *tb = &tfd->tbs[idx];
+
+		return le16_to_cpu(tb->tb_len);
+	}
+
+	tfd = (struct iwl_tfd *)_tfd;
+	tb = &tfd->tbs[idx];
+
+	return le16_to_cpu(tb->hi_n_len) >> 4;
+}
+
+void iwl_txq_gen1_tfd_unmap(struct iwl_trans *trans,
+			    struct iwl_cmd_meta *meta,
+			    struct iwl_txq *txq, int index);
+void iwl_txq_gen1_inval_byte_cnt_tbl(struct iwl_trans *trans,
+				     struct iwl_txq *txq);
+void iwl_txq_gen1_update_byte_cnt_tbl(struct iwl_trans *trans,
+				      struct iwl_txq *txq, u16 byte_cnt,
+				      int num_tbs);
+#endif /* __iwl_trans_queue_tx_h__ */
diff --git a/drivers/net/wireless/intersil/hostap/hostap_hw.c b/drivers/net/wireless/intersil/hostap/hostap_hw.c
index 01a2dd0edd71..22cfb6452644 100644
--- a/drivers/net/wireless/intersil/hostap/hostap_hw.c
+++ b/drivers/net/wireless/intersil/hostap/hostap_hw.c
@@ -320,12 +320,6 @@ static int hfa384x_cmd(struct net_device *dev, u16 cmd, u16 param0,
 	iface = netdev_priv(dev);
 	local = iface->local;
 
-	if (in_interrupt()) {
-		printk(KERN_DEBUG "%s: hfa384x_cmd called from interrupt "
-		       "context\n", dev->name);
-		return -1;
-	}
-
 	if (local->cmd_queue_len >= HOSTAP_CMD_QUEUE_MAX_LEN) {
 		printk(KERN_DEBUG "%s: hfa384x_cmd: cmd_queue full\n",
 		       dev->name);
@@ -1560,12 +1554,6 @@ static void prism2_hw_reset(struct net_device *dev)
 	iface = netdev_priv(dev);
 	local = iface->local;
 
-	if (in_interrupt()) {
-		printk(KERN_DEBUG "%s: driver bug - prism2_hw_reset() called "
-		       "in interrupt context\n", dev->name);
-		return;
-	}
-
 	if (local->hw_downloading)
 		return;
 
diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index dce3bc9c9f84..3b3fc7c9c91d 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -99,7 +99,7 @@ MODULE_PARM_DESC(support_p2p_device, "Support P2P-Device interface type");
  * 	domain requests. The first radio will adhere to the first custom world
  * 	regulatory domain, the second one to the second custom world regulatory
  * 	domain. All other devices will world roam.
- * @HWSIM_REGTEST_STRICT_FOLLOW_: Used for testing strict regulatory domain
+ * @HWSIM_REGTEST_STRICT_FOLLOW: Used for testing strict regulatory domain
  *	settings, only the first radio will send a regulatory domain request
  *	and use strict settings. The rest of the radios are expected to follow.
  * @HWSIM_REGTEST_STRICT_ALL: Used for testing strict regulatory domain
@@ -377,6 +377,49 @@ static const struct ieee80211_channel hwsim_channels_5ghz[] = {
 	CHAN5G(5925), /* Channel 185 */
 };
 
+#define NUM_S1G_CHANS_US 51
+static struct ieee80211_channel hwsim_channels_s1g[NUM_S1G_CHANS_US];
+
+static const struct ieee80211_sta_s1g_cap hwsim_s1g_cap = {
+	.s1g = true,
+	.cap = { S1G_CAP0_SGI_1MHZ | S1G_CAP0_SGI_2MHZ,
+		 0,
+		 0,
+		 S1G_CAP3_MAX_MPDU_LEN,
+		 0,
+		 S1G_CAP5_AMPDU,
+		 0,
+		 S1G_CAP7_DUP_1MHZ,
+		 S1G_CAP8_TWT_RESPOND | S1G_CAP8_TWT_REQUEST,
+		 0},
+	.nss_mcs = { 0xfc | 1, /* MCS 7 for 1 SS */
+	/* RX Highest Supported Long GI Data Rate 0:7 */
+		     0,
+	/* RX Highest Supported Long GI Data Rate 0:7 */
+	/* TX S1G MCS Map 0:6 */
+		     0xfa,
+	/* TX S1G MCS Map :7 */
+	/* TX Highest Supported Long GI Data Rate 0:6 */
+		     0x80,
+	/* TX Highest Supported Long GI Data Rate 7:8 */
+	/* Rx Single spatial stream and S1G-MCS Map for 1MHz */
+	/* Tx Single spatial stream and S1G-MCS Map for 1MHz */
+		     0 },
+};
+
+static void hwsim_init_s1g_channels(struct ieee80211_channel *channels)
+{
+	int ch, freq;
+
+	for (ch = 0; ch < NUM_S1G_CHANS_US; ch++) {
+		freq = 902000 + (ch + 1) * 500;
+		channels[ch].band = NL80211_BAND_S1GHZ;
+		channels[ch].center_freq = KHZ_TO_MHZ(freq);
+		channels[ch].freq_offset = freq % 1000;
+		channels[ch].hw_value = ch + 1;
+	}
+}
+
 static const struct ieee80211_rate hwsim_rates[] = {
 	{ .bitrate = 10 },
 	{ .bitrate = 20, .flags = IEEE80211_RATE_SHORT_PREAMBLE },
@@ -505,6 +548,7 @@ struct mac80211_hwsim_data {
 	struct ieee80211_supported_band bands[NUM_NL80211_BANDS];
 	struct ieee80211_channel channels_2ghz[ARRAY_SIZE(hwsim_channels_2ghz)];
 	struct ieee80211_channel channels_5ghz[ARRAY_SIZE(hwsim_channels_5ghz)];
+	struct ieee80211_channel channels_s1g[ARRAY_SIZE(hwsim_channels_s1g)];
 	struct ieee80211_rate rates[ARRAY_SIZE(hwsim_rates)];
 	struct ieee80211_iface_combination if_combination;
 	struct ieee80211_iface_limit if_limits[3];
@@ -900,12 +944,14 @@ static void mac80211_hwsim_monitor_rx(struct ieee80211_hw *hw,
 	struct mac80211_hwsim_data *data = hw->priv;
 	struct sk_buff *skb;
 	struct hwsim_radiotap_hdr *hdr;
-	u16 flags;
+	u16 flags, bitrate;
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx_skb);
 	struct ieee80211_rate *txrate = ieee80211_get_tx_rate(hw, info);
 
-	if (WARN_ON(!txrate))
-		return;
+	if (!txrate)
+		bitrate = 0;
+	else
+		bitrate = txrate->bitrate;
 
 	if (!netif_running(hwsim_mon))
 		return;
@@ -924,10 +970,10 @@ static void mac80211_hwsim_monitor_rx(struct ieee80211_hw *hw,
 					  (1 << IEEE80211_RADIOTAP_CHANNEL));
 	hdr->rt_tsft = __mac80211_hwsim_get_tsf(data);
 	hdr->rt_flags = 0;
-	hdr->rt_rate = txrate->bitrate / 5;
+	hdr->rt_rate = bitrate / 5;
 	hdr->rt_channel = cpu_to_le16(chan->center_freq);
 	flags = IEEE80211_CHAN_2GHZ;
-	if (txrate->flags & IEEE80211_RATE_ERP_G)
+	if (txrate && txrate->flags & IEEE80211_RATE_ERP_G)
 		flags |= IEEE80211_CHAN_OFDM;
 	else
 		flags |= IEEE80211_CHAN_CCK;
@@ -1341,6 +1387,7 @@ static bool mac80211_hwsim_tx_frame_no_nl(struct ieee80211_hw *hw,
 	memset(&rx_status, 0, sizeof(rx_status));
 	rx_status.flag |= RX_FLAG_MACTIME_START;
 	rx_status.freq = chan->center_freq;
+	rx_status.freq_offset = chan->freq_offset ? 1 : 0;
 	rx_status.band = chan->band;
 	if (info->control.rates[0].flags & IEEE80211_TX_RC_VHT_MCS) {
 		rx_status.rate_idx =
@@ -1522,14 +1569,18 @@ static void mac80211_hwsim_tx(struct ieee80211_hw *hw,
 		/* fake header transmission time */
 		struct ieee80211_mgmt *mgmt;
 		struct ieee80211_rate *txrate;
+		/* TODO: get MCS */
+		int bitrate = 100;
 		u64 ts;
 
 		mgmt = (struct ieee80211_mgmt *)skb->data;
 		txrate = ieee80211_get_tx_rate(hw, txi);
+		if (txrate)
+			bitrate = txrate->bitrate;
 		ts = mac80211_hwsim_get_tsf_raw();
 		mgmt->u.probe_resp.timestamp =
 			cpu_to_le64(ts + data->tsf_offset +
-				    24 * 8 * 10 / txrate->bitrate);
+				    24 * 8 * 10 / bitrate);
 	}
 
 	mac80211_hwsim_monitor_rx(hw, skb, channel);
@@ -1664,6 +1715,8 @@ static void mac80211_hwsim_beacon_tx(void *arg, u8 *mac,
 	struct ieee80211_rate *txrate;
 	struct ieee80211_mgmt *mgmt;
 	struct sk_buff *skb;
+	/* TODO: get MCS */
+	int bitrate = 100;
 
 	hwsim_check_magic(vif);
 
@@ -1683,13 +1736,25 @@ static void mac80211_hwsim_beacon_tx(void *arg, u8 *mac,
 				       ARRAY_SIZE(info->control.rates));
 
 	txrate = ieee80211_get_tx_rate(hw, info);
+	if (txrate)
+		bitrate = txrate->bitrate;
 
 	mgmt = (struct ieee80211_mgmt *) skb->data;
 	/* fake header transmission time */
 	data->abs_bcn_ts = mac80211_hwsim_get_tsf_raw();
-	mgmt->u.beacon.timestamp = cpu_to_le64(data->abs_bcn_ts +
-					       data->tsf_offset +
-					       24 * 8 * 10 / txrate->bitrate);
+	if (ieee80211_is_s1g_beacon(mgmt->frame_control)) {
+		struct ieee80211_ext *ext = (void *) mgmt;
+
+		ext->u.s1g_beacon.timestamp = cpu_to_le32(data->abs_bcn_ts +
+							  data->tsf_offset +
+							  10 * 8 * 10 /
+							  bitrate);
+	} else {
+		mgmt->u.beacon.timestamp = cpu_to_le64(data->abs_bcn_ts +
+						       data->tsf_offset +
+						       24 * 8 * 10 /
+						       bitrate);
+	}
 
 	mac80211_hwsim_tx_frame(hw, skb,
 				rcu_dereference(vif->chanctx_conf)->def.chan);
@@ -1737,6 +1802,11 @@ static const char * const hwsim_chanwidths[] = {
 	[NL80211_CHAN_WIDTH_80] = "vht80",
 	[NL80211_CHAN_WIDTH_80P80] = "vht80p80",
 	[NL80211_CHAN_WIDTH_160] = "vht160",
+	[NL80211_CHAN_WIDTH_1] = "1MHz",
+	[NL80211_CHAN_WIDTH_2] = "2MHz",
+	[NL80211_CHAN_WIDTH_4] = "4MHz",
+	[NL80211_CHAN_WIDTH_8] = "8MHz",
+	[NL80211_CHAN_WIDTH_16] = "16MHz",
 };
 
 static int mac80211_hwsim_config(struct ieee80211_hw *hw, u32 changed)
@@ -3079,6 +3149,8 @@ static int mac80211_hwsim_new_radio(struct genl_info *info,
 		sizeof(hwsim_channels_2ghz));
 	memcpy(data->channels_5ghz, hwsim_channels_5ghz,
 		sizeof(hwsim_channels_5ghz));
+	memcpy(data->channels_s1g, hwsim_channels_s1g,
+	       sizeof(hwsim_channels_s1g));
 	memcpy(data->rates, hwsim_rates, sizeof(hwsim_rates));
 
 	for (band = NL80211_BAND_2GHZ; band < NUM_NL80211_BANDS; band++) {
@@ -3121,6 +3193,12 @@ static int mac80211_hwsim_new_radio(struct genl_info *info,
 			sband->vht_cap.vht_mcs.tx_mcs_map =
 				sband->vht_cap.vht_mcs.rx_mcs_map;
 			break;
+		case NL80211_BAND_S1GHZ:
+			memcpy(&sband->s1g_cap, &hwsim_s1g_cap,
+			       sizeof(sband->s1g_cap));
+			sband->channels = data->channels_s1g;
+			sband->n_channels = ARRAY_SIZE(hwsim_channels_s1g);
+			break;
 		default:
 			continue;
 		}
@@ -3886,7 +3964,7 @@ done:
 }
 
 /* Generic Netlink operations array */
-static const struct genl_ops hwsim_ops[] = {
+static const struct genl_small_ops hwsim_ops[] = {
 	{
 		.cmd = HWSIM_CMD_REGISTER,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
@@ -3930,8 +4008,8 @@ static struct genl_family hwsim_genl_family __ro_after_init = {
 	.policy = hwsim_genl_policy,
 	.netnsok = true,
 	.module = THIS_MODULE,
-	.ops = hwsim_ops,
-	.n_ops = ARRAY_SIZE(hwsim_ops),
+	.small_ops = hwsim_ops,
+	.n_small_ops = ARRAY_SIZE(hwsim_ops),
 	.mcgrps = hwsim_mcgrps,
 	.n_mcgrps = ARRAY_SIZE(hwsim_mcgrps),
 };
@@ -4318,6 +4396,8 @@ static int __init init_mac80211_hwsim(void)
 		goto out_exit_virtio;
 	}
 
+	hwsim_init_s1g_channels(hwsim_channels_s1g);
+
 	for (i = 0; i < radios; i++) {
 		struct hwsim_new_radio_params param = { 0 };
 
diff --git a/drivers/net/wireless/marvell/libertas/defs.h b/drivers/net/wireless/marvell/libertas/defs.h
index 58e2ead7b0cc..f7e7bf56f924 100644
--- a/drivers/net/wireless/marvell/libertas/defs.h
+++ b/drivers/net/wireless/marvell/libertas/defs.h
@@ -50,8 +50,7 @@ extern unsigned int lbs_debug;
 #ifdef DEBUG
 #define LBS_DEB_LL(grp, grpnam, fmt, args...) \
 do { if ((lbs_debug & (grp)) == (grp)) \
-  printk(KERN_DEBUG DRV_NAME grpnam "%s: " fmt, \
-         in_interrupt() ? " (INT)" : "", ## args); } while (0)
+  printk(KERN_DEBUG DRV_NAME grpnam ": " fmt, ## args); } while (0)
 #else
 #define LBS_DEB_LL(grp, grpnam, fmt, args...) do {} while (0)
 #endif
diff --git a/drivers/net/wireless/marvell/libertas/rx.c b/drivers/net/wireless/marvell/libertas/rx.c
index f28aa09d1f9e..9f24b0760e1f 100644
--- a/drivers/net/wireless/marvell/libertas/rx.c
+++ b/drivers/net/wireless/marvell/libertas/rx.c
@@ -147,10 +147,7 @@ int lbs_process_rxed_packet(struct lbs_private *priv, struct sk_buff *skb)
 	dev->stats.rx_packets++;
 
 	skb->protocol = eth_type_trans(skb, dev);
-	if (in_interrupt())
-		netif_rx(skb);
-	else
-		netif_rx_ni(skb);
+	netif_rx_any_context(skb);
 
 	ret = 0;
 done:
@@ -265,11 +262,7 @@ static int process_rxed_802_11_packet(struct lbs_private *priv,
 	dev->stats.rx_packets++;
 
 	skb->protocol = eth_type_trans(skb, priv->dev);
-
-	if (in_interrupt())
-		netif_rx(skb);
-	else
-		netif_rx_ni(skb);
+	netif_rx_any_context(skb);
 
 	ret = 0;
 
diff --git a/drivers/net/wireless/marvell/libertas_tf/deb_defs.h b/drivers/net/wireless/marvell/libertas_tf/deb_defs.h
index 37a98e228b46..0b520df62f1f 100644
--- a/drivers/net/wireless/marvell/libertas_tf/deb_defs.h
+++ b/drivers/net/wireless/marvell/libertas_tf/deb_defs.h
@@ -48,8 +48,7 @@ extern unsigned int lbtf_debug;
 #ifdef DEBUG
 #define LBTF_DEB_LL(grp, grpnam, fmt, args...) \
 do { if ((lbtf_debug & (grp)) == (grp)) \
-  printk(KERN_DEBUG DRV_NAME grpnam "%s: " fmt, \
-         in_interrupt() ? " (INT)" : "", ## args); } while (0)
+  printk(KERN_DEBUG DRV_NAME grpnam ": " fmt, ## args); } while (0)
 #else
 #define LBTF_DEB_LL(grp, grpnam, fmt, args...) do {} while (0)
 #endif
diff --git a/drivers/net/wireless/marvell/mwifiex/fw.h b/drivers/net/wireless/marvell/mwifiex/fw.h
index 1f02c5058aed..470d669c7f14 100644
--- a/drivers/net/wireless/marvell/mwifiex/fw.h
+++ b/drivers/net/wireless/marvell/mwifiex/fw.h
@@ -954,7 +954,7 @@ struct mwifiex_tkip_param {
 struct mwifiex_aes_param {
 	u8 pn[WPA_PN_SIZE];
 	__le16 key_len;
-	u8 key[WLAN_KEY_LEN_CCMP];
+	u8 key[WLAN_KEY_LEN_CCMP_256];
 } __packed;
 
 struct mwifiex_wapi_param {
diff --git a/drivers/net/wireless/marvell/mwifiex/sta_cmdresp.c b/drivers/net/wireless/marvell/mwifiex/sta_cmdresp.c
index 962d8bfe6f10..119ccacd1fcc 100644
--- a/drivers/net/wireless/marvell/mwifiex/sta_cmdresp.c
+++ b/drivers/net/wireless/marvell/mwifiex/sta_cmdresp.c
@@ -619,7 +619,7 @@ static int mwifiex_ret_802_11_key_material_v2(struct mwifiex_private *priv,
 	key_v2 = &resp->params.key_material_v2;
 
 	len = le16_to_cpu(key_v2->key_param_set.key_params.aes.key_len);
-	if (len > WLAN_KEY_LEN_CCMP)
+	if (len > sizeof(key_v2->key_param_set.key_params.aes.key))
 		return -EINVAL;
 
 	if (le16_to_cpu(key_v2->action) == HostCmd_ACT_GEN_SET) {
@@ -635,7 +635,7 @@ static int mwifiex_ret_802_11_key_material_v2(struct mwifiex_private *priv,
 		return 0;
 
 	memset(priv->aes_key_v2.key_param_set.key_params.aes.key, 0,
-	       WLAN_KEY_LEN_CCMP);
+	       sizeof(key_v2->key_param_set.key_params.aes.key));
 	priv->aes_key_v2.key_param_set.key_params.aes.key_len =
 				cpu_to_le16(len);
 	memcpy(priv->aes_key_v2.key_param_set.key_params.aes.key,
diff --git a/drivers/net/wireless/marvell/mwifiex/uap_txrx.c b/drivers/net/wireless/marvell/mwifiex/uap_txrx.c
index 77c8595f84f8..9bbdb8dfce62 100644
--- a/drivers/net/wireless/marvell/mwifiex/uap_txrx.c
+++ b/drivers/net/wireless/marvell/mwifiex/uap_txrx.c
@@ -350,11 +350,7 @@ int mwifiex_uap_recv_packet(struct mwifiex_private *priv,
 		skb->truesize += (skb->len - MWIFIEX_RX_DATA_BUF_SIZE);
 
 	/* Forward multicast/broadcast packet to upper layer*/
-	if (in_interrupt())
-		netif_rx(skb);
-	else
-		netif_rx_ni(skb);
-
+	netif_rx_any_context(skb);
 	return 0;
 }
 
diff --git a/drivers/net/wireless/marvell/mwifiex/util.c b/drivers/net/wireless/marvell/mwifiex/util.c
index de89a1e710b1..d583fa600a29 100644
--- a/drivers/net/wireless/marvell/mwifiex/util.c
+++ b/drivers/net/wireless/marvell/mwifiex/util.c
@@ -488,11 +488,7 @@ int mwifiex_recv_packet(struct mwifiex_private *priv, struct sk_buff *skb)
 	    (skb->truesize > MWIFIEX_RX_DATA_BUF_SIZE))
 		skb->truesize += (skb->len - MWIFIEX_RX_DATA_BUF_SIZE);
 
-	if (in_interrupt())
-		netif_rx(skb);
-	else
-		netif_rx_ni(skb);
-
+	netif_rx_any_context(skb);
 	return 0;
 }
 
diff --git a/drivers/net/wireless/mediatek/mt76/debugfs.c b/drivers/net/wireless/mediatek/mt76/debugfs.c
index 5d58b16bfe9f..52f583cb1418 100644
--- a/drivers/net/wireless/mediatek/mt76/debugfs.c
+++ b/drivers/net/wireless/mediatek/mt76/debugfs.c
@@ -31,15 +31,14 @@ int mt76_queues_read(struct seq_file *s, void *data)
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(dev->q_tx); i++) {
-		struct mt76_sw_queue *q = &dev->q_tx[i];
+		struct mt76_queue *q = dev->q_tx[i];
 
-		if (!q->q)
+		if (!q)
 			continue;
 
 		seq_printf(s,
-			   "%d:	queued=%d head=%d tail=%d swq_queued=%d\n",
-			   i, q->q->queued, q->q->head, q->q->tail,
-			   q->swq_queued);
+			   "%d:	queued=%d head=%d tail=%d\n",
+			   i, q->queued, q->head, q->tail);
 	}
 
 	return 0;
diff --git a/drivers/net/wireless/mediatek/mt76/dma.c b/drivers/net/wireless/mediatek/mt76/dma.c
index 6c25859dd386..214fc95b8a33 100644
--- a/drivers/net/wireless/mediatek/mt76/dma.c
+++ b/drivers/net/wireless/mediatek/mt76/dma.c
@@ -7,6 +7,76 @@
 #include "mt76.h"
 #include "dma.h"
 
+static struct mt76_txwi_cache *
+mt76_alloc_txwi(struct mt76_dev *dev)
+{
+	struct mt76_txwi_cache *t;
+	dma_addr_t addr;
+	u8 *txwi;
+	int size;
+
+	size = L1_CACHE_ALIGN(dev->drv->txwi_size + sizeof(*t));
+	txwi = devm_kzalloc(dev->dev, size, GFP_ATOMIC);
+	if (!txwi)
+		return NULL;
+
+	addr = dma_map_single(dev->dev, txwi, dev->drv->txwi_size,
+			      DMA_TO_DEVICE);
+	t = (struct mt76_txwi_cache *)(txwi + dev->drv->txwi_size);
+	t->dma_addr = addr;
+
+	return t;
+}
+
+static struct mt76_txwi_cache *
+__mt76_get_txwi(struct mt76_dev *dev)
+{
+	struct mt76_txwi_cache *t = NULL;
+
+	spin_lock(&dev->lock);
+	if (!list_empty(&dev->txwi_cache)) {
+		t = list_first_entry(&dev->txwi_cache, struct mt76_txwi_cache,
+				     list);
+		list_del(&t->list);
+	}
+	spin_unlock(&dev->lock);
+
+	return t;
+}
+
+static struct mt76_txwi_cache *
+mt76_get_txwi(struct mt76_dev *dev)
+{
+	struct mt76_txwi_cache *t = __mt76_get_txwi(dev);
+
+	if (t)
+		return t;
+
+	return mt76_alloc_txwi(dev);
+}
+
+void
+mt76_put_txwi(struct mt76_dev *dev, struct mt76_txwi_cache *t)
+{
+	if (!t)
+		return;
+
+	spin_lock(&dev->lock);
+	list_add(&t->list, &dev->txwi_cache);
+	spin_unlock(&dev->lock);
+}
+EXPORT_SYMBOL_GPL(mt76_put_txwi);
+
+static void
+mt76_free_pending_txwi(struct mt76_dev *dev)
+{
+	struct mt76_txwi_cache *t;
+
+	while ((t = __mt76_get_txwi(dev)) != NULL)
+		dma_unmap_single(dev->dev, t->dma_addr, dev->drv->txwi_size,
+				 DMA_TO_DEVICE);
+}
+
 static int
 mt76_dma_alloc_queue(struct mt76_dev *dev, struct mt76_queue *q,
 		     int idx, int n_desc, int bufsize,
@@ -49,6 +119,7 @@ mt76_dma_add_buf(struct mt76_dev *dev, struct mt76_queue *q,
 		 struct mt76_queue_buf *buf, int nbufs, u32 info,
 		 struct sk_buff *skb, void *txwi)
 {
+	struct mt76_queue_entry *entry;
 	struct mt76_desc *desc;
 	u32 ctrl;
 	int i, idx = -1;
@@ -61,10 +132,27 @@ mt76_dma_add_buf(struct mt76_dev *dev, struct mt76_queue *q,
 	for (i = 0; i < nbufs; i += 2, buf += 2) {
 		u32 buf0 = buf[0].addr, buf1 = 0;
 
+		idx = q->head;
+		q->head = (q->head + 1) % q->ndesc;
+
+		desc = &q->desc[idx];
+		entry = &q->entry[idx];
+
+		if (buf[0].skip_unmap)
+			entry->skip_buf0 = true;
+		entry->skip_buf1 = i == nbufs - 1;
+
+		entry->dma_addr[0] = buf[0].addr;
+		entry->dma_len[0] = buf[0].len;
+
 		ctrl = FIELD_PREP(MT_DMA_CTL_SD_LEN0, buf[0].len);
 		if (i < nbufs - 1) {
+			entry->dma_addr[1] = buf[1].addr;
+			entry->dma_len[1] = buf[1].len;
 			buf1 = buf[1].addr;
 			ctrl |= FIELD_PREP(MT_DMA_CTL_SD_LEN1, buf[1].len);
+			if (buf[1].skip_unmap)
+				entry->skip_buf1 = true;
 		}
 
 		if (i == nbufs - 1)
@@ -72,11 +160,6 @@ mt76_dma_add_buf(struct mt76_dev *dev, struct mt76_queue *q,
 		else if (i == nbufs - 2)
 			ctrl |= MT_DMA_CTL_LAST_SEC1;
 
-		idx = q->head;
-		q->head = (q->head + 1) % q->ndesc;
-
-		desc = &q->desc[idx];
-
 		WRITE_ONCE(desc->buf0, cpu_to_le32(buf0));
 		WRITE_ONCE(desc->buf1, cpu_to_le32(buf1));
 		WRITE_ONCE(desc->info, cpu_to_le32(info));
@@ -96,24 +179,14 @@ mt76_dma_tx_cleanup_idx(struct mt76_dev *dev, struct mt76_queue *q, int idx,
 			struct mt76_queue_entry *prev_e)
 {
 	struct mt76_queue_entry *e = &q->entry[idx];
-	__le32 __ctrl = READ_ONCE(q->desc[idx].ctrl);
-	u32 ctrl = le32_to_cpu(__ctrl);
 
-	if (!e->skip_buf0) {
-		__le32 addr = READ_ONCE(q->desc[idx].buf0);
-		u32 len = FIELD_GET(MT_DMA_CTL_SD_LEN0, ctrl);
-
-		dma_unmap_single(dev->dev, le32_to_cpu(addr), len,
+	if (!e->skip_buf0)
+		dma_unmap_single(dev->dev, e->dma_addr[0], e->dma_len[0],
 				 DMA_TO_DEVICE);
-	}
 
-	if (!(ctrl & MT_DMA_CTL_LAST_SEC0)) {
-		__le32 addr = READ_ONCE(q->desc[idx].buf1);
-		u32 len = FIELD_GET(MT_DMA_CTL_SD_LEN1, ctrl);
-
-		dma_unmap_single(dev->dev, le32_to_cpu(addr), len,
+	if (!e->skip_buf1)
+		dma_unmap_single(dev->dev, e->dma_addr[1], e->dma_len[1],
 				 DMA_TO_DEVICE);
-	}
 
 	if (e->txwi == DMA_DUMMY_DATA)
 		e->txwi = NULL;
@@ -137,19 +210,17 @@ mt76_dma_sync_idx(struct mt76_dev *dev, struct mt76_queue *q)
 static void
 mt76_dma_kick_queue(struct mt76_dev *dev, struct mt76_queue *q)
 {
+	wmb();
 	writel(q->head, &q->regs->cpu_idx);
 }
 
 static void
 mt76_dma_tx_cleanup(struct mt76_dev *dev, enum mt76_txq_id qid, bool flush)
 {
-	struct mt76_sw_queue *sq = &dev->q_tx[qid];
-	struct mt76_queue *q = sq->q;
+	struct mt76_queue *q = dev->q_tx[qid];
 	struct mt76_queue_entry entry;
-	unsigned int n_swq_queued[8] = {};
-	unsigned int n_queued = 0;
 	bool wake = false;
-	int i, last;
+	int last;
 
 	if (!q)
 		return;
@@ -159,16 +230,9 @@ mt76_dma_tx_cleanup(struct mt76_dev *dev, enum mt76_txq_id qid, bool flush)
 	else
 		last = readl(&q->regs->dma_idx);
 
-	while ((q->queued > n_queued) && q->tail != last) {
+	while (q->queued > 0 && q->tail != last) {
 		mt76_dma_tx_cleanup_idx(dev, q, q->tail, &entry);
-		if (entry.schedule)
-			n_swq_queued[entry.qid]++;
-
-		q->tail = (q->tail + 1) % q->ndesc;
-		n_queued++;
-
-		if (entry.skb)
-			dev->drv->tx_complete_skb(dev, qid, &entry);
+		mt76_queue_tx_complete(dev, q, &entry);
 
 		if (entry.txwi) {
 			if (!(dev->drv->drv_flags & MT_DRV_TXWI_NO_FREE))
@@ -178,29 +242,14 @@ mt76_dma_tx_cleanup(struct mt76_dev *dev, enum mt76_txq_id qid, bool flush)
 
 		if (!flush && q->tail == last)
 			last = readl(&q->regs->dma_idx);
-	}
-
-	spin_lock_bh(&q->lock);
-
-	q->queued -= n_queued;
-	for (i = 0; i < 4; i++) {
-		if (!n_swq_queued[i])
-			continue;
-
-		dev->q_tx[i].swq_queued -= n_swq_queued[i];
-	}
-
-	/* ext PHY */
-	for (i = 0; i < 4; i++) {
-		if (!n_swq_queued[i])
-			continue;
 
-		dev->q_tx[__MT_TXQ_MAX + i].swq_queued -= n_swq_queued[4 + i];
 	}
 
 	if (flush) {
+		spin_lock_bh(&q->lock);
 		mt76_dma_sync_idx(dev, q);
 		mt76_dma_kick_queue(dev, q);
+		spin_unlock_bh(&q->lock);
 	}
 
 	wake = wake && q->stopped &&
@@ -211,8 +260,6 @@ mt76_dma_tx_cleanup(struct mt76_dev *dev, enum mt76_txq_id qid, bool flush)
 	if (!q->queued)
 		wake_up(&dev->tx_wait);
 
-	spin_unlock_bh(&q->lock);
-
 	if (wake)
 		ieee80211_wake_queue(dev->hw, qid);
 }
@@ -227,7 +274,7 @@ mt76_dma_get_buf(struct mt76_dev *dev, struct mt76_queue *q, int idx,
 	void *buf = e->buf;
 	int buf_len = SKB_WITH_OVERHEAD(q->buf_size);
 
-	buf_addr = le32_to_cpu(READ_ONCE(desc->buf0));
+	buf_addr = e->dma_addr[0];
 	if (len) {
 		u32 ctl = le32_to_cpu(READ_ONCE(desc->ctrl));
 		*len = FIELD_GET(MT_DMA_CTL_SD_LEN0, ctl);
@@ -268,7 +315,7 @@ static int
 mt76_dma_tx_queue_skb_raw(struct mt76_dev *dev, enum mt76_txq_id qid,
 			  struct sk_buff *skb, u32 tx_info)
 {
-	struct mt76_queue *q = dev->q_tx[qid].q;
+	struct mt76_queue *q = dev->q_tx[qid];
 	struct mt76_queue_buf buf;
 	dma_addr_t addr;
 
@@ -300,7 +347,7 @@ mt76_dma_tx_queue_skb(struct mt76_dev *dev, enum mt76_txq_id qid,
 		      struct sk_buff *skb, struct mt76_wcid *wcid,
 		      struct ieee80211_sta *sta)
 {
-	struct mt76_queue *q = dev->q_tx[qid].q;
+	struct mt76_queue *q = dev->q_tx[qid];
 	struct mt76_tx_info tx_info = {
 		.skb = skb,
 	};
@@ -378,7 +425,7 @@ free:
 
 	e.skb = tx_info.skb;
 	e.txwi = t;
-	dev->drv->tx_complete_skb(dev, qid, &e);
+	dev->drv->tx_complete_skb(dev, &e);
 	mt76_put_txwi(dev, t);
 	return ret;
 }
@@ -612,6 +659,7 @@ void mt76_dma_cleanup(struct mt76_dev *dev)
 {
 	int i;
 
+	mt76_worker_disable(&dev->tx_worker);
 	netif_napi_del(&dev->tx_napi);
 	for (i = 0; i < ARRAY_SIZE(dev->q_tx); i++)
 		mt76_dma_tx_cleanup(dev, i, true);
@@ -620,5 +668,7 @@ void mt76_dma_cleanup(struct mt76_dev *dev)
 		netif_napi_del(&dev->napi[i]);
 		mt76_dma_rx_cleanup(dev, &dev->q_rx[i]);
 	}
+
+	mt76_free_pending_txwi(dev);
 }
 EXPORT_SYMBOL_GPL(mt76_dma_cleanup);
diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wireless/mediatek/mt76/mac80211.c
index fbfb991ebd90..4befe7f937a9 100644
--- a/drivers/net/wireless/mediatek/mt76/mac80211.c
+++ b/drivers/net/wireless/mediatek/mt76/mac80211.c
@@ -2,6 +2,7 @@
 /*
  * Copyright (C) 2016 Felix Fietkau <nbd@nbd.name>
  */
+#include <linux/sched.h>
 #include <linux/of.h>
 #include "mt76.h"
 
@@ -304,11 +305,11 @@ mt76_phy_init(struct mt76_dev *dev, struct ieee80211_hw *hw)
 	ieee80211_hw_set(hw, SUPPORT_FAST_XMIT);
 	ieee80211_hw_set(hw, SUPPORTS_CLONED_SKBS);
 	ieee80211_hw_set(hw, SUPPORTS_AMSDU_IN_AMPDU);
-	ieee80211_hw_set(hw, TX_AMSDU);
 
-	/* TODO: avoid linearization for SDIO */
-	if (!mt76_is_sdio(dev))
+	if (!(dev->drv->drv_flags & MT_DRV_AMSDU_OFFLOAD)) {
+		ieee80211_hw_set(hw, TX_AMSDU);
 		ieee80211_hw_set(hw, TX_FRAG_LIST);
+	}
 
 	ieee80211_hw_set(hw, MFP_CAPABLE);
 	ieee80211_hw_set(hw, AP_LINK_PS);
@@ -433,14 +434,13 @@ mt76_alloc_device(struct device *pdev, unsigned int size,
 	skb_queue_head_init(&dev->mcu.res_q);
 	init_waitqueue_head(&dev->mcu.wait);
 	mutex_init(&dev->mcu.mutex);
+	dev->tx_worker.fn = mt76_tx_worker;
 
 	INIT_LIST_HEAD(&dev->txwi_cache);
 
 	for (i = 0; i < ARRAY_SIZE(dev->q_rx); i++)
 		skb_queue_head_init(&dev->rx_skb[i]);
 
-	tasklet_init(&dev->tx_tasklet, mt76_tx_tasklet, (unsigned long)dev);
-
 	dev->wq = alloc_ordered_workqueue("mt76", 0);
 	if (!dev->wq) {
 		ieee80211_free_hw(hw);
@@ -483,7 +483,14 @@ int mt76_register_device(struct mt76_dev *dev, bool vht,
 			return ret;
 	}
 
-	return ieee80211_register_hw(hw);
+	ret = ieee80211_register_hw(hw);
+	if (ret)
+		return ret;
+
+	WARN_ON(mt76_worker_setup(hw, &dev->tx_worker, NULL, "tx"));
+	sched_set_fifo_low(dev->tx_worker.task);
+
+	return 0;
 }
 EXPORT_SYMBOL_GPL(mt76_register_device);
 
@@ -500,12 +507,11 @@ EXPORT_SYMBOL_GPL(mt76_unregister_device);
 
 void mt76_free_device(struct mt76_dev *dev)
 {
+	mt76_worker_teardown(&dev->tx_worker);
 	if (dev->wq) {
 		destroy_workqueue(dev->wq);
 		dev->wq = NULL;
 	}
-	if (mt76_is_mmio(dev))
-		mt76_tx_free(dev);
 	ieee80211_free_hw(dev->hw);
 }
 EXPORT_SYMBOL_GPL(mt76_free_device);
@@ -540,7 +546,7 @@ bool mt76_has_tx_pending(struct mt76_phy *phy)
 	offset = __MT_TXQ_MAX * (phy != &dev->phy);
 
 	for (i = 0; i < __MT_TXQ_MAX; i++) {
-		q = dev->q_tx[offset + i].q;
+		q = dev->q_tx[offset + i];
 		if (q && q->queued)
 			return true;
 	}
@@ -870,7 +876,6 @@ mt76_check_sta(struct mt76_dev *dev, struct sk_buff *skb)
 	struct ieee80211_hw *hw;
 	struct mt76_wcid *wcid = status->wcid;
 	bool ps;
-	int i;
 
 	hw = mt76_phy_hw(dev, status->ext_phy);
 	if (ieee80211_is_pspoll(hdr->frame_control) && !wcid) {
@@ -920,20 +925,6 @@ mt76_check_sta(struct mt76_dev *dev, struct sk_buff *skb)
 
 	dev->drv->sta_ps(dev, sta, ps);
 	ieee80211_sta_ps_transition(sta, ps);
-
-	if (ps)
-		return;
-
-	for (i = 0; i < ARRAY_SIZE(sta->txq); i++) {
-		struct mt76_txq *mtxq;
-
-		if (!sta->txq[i])
-			continue;
-
-		mtxq = (struct mt76_txq *)sta->txq[i]->drv_priv;
-		if (!skb_queue_empty(&mtxq->retry_q))
-			ieee80211_schedule_txq(hw, sta->txq[i]);
-	}
 }
 
 void mt76_rx_complete(struct mt76_dev *dev, struct sk_buff_head *frames,
@@ -995,8 +986,6 @@ mt76_sta_add(struct mt76_dev *dev, struct ieee80211_vif *vif,
 
 		mtxq = (struct mt76_txq *)sta->txq[i]->drv_priv;
 		mtxq->wcid = wcid;
-
-		mt76_txq_init(dev, sta->txq[i]);
 	}
 
 	ewma_signal_init(&wcid->rssi);
@@ -1024,8 +1013,6 @@ void __mt76_sta_remove(struct mt76_dev *dev, struct ieee80211_vif *vif,
 		dev->drv->sta_remove(dev, vif, sta);
 
 	mt76_tx_status_check(dev, wcid, true);
-	for (i = 0; i < ARRAY_SIZE(sta->txq); i++)
-		mt76_txq_remove(dev, sta->txq[i]);
 	mt76_wcid_mask_clear(dev->wcid_mask, idx);
 	mt76_wcid_mask_clear(dev->wcid_phy_mask, idx);
 }
diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h
index af35bc388ae2..a5be66de1cff 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76.h
@@ -17,11 +17,13 @@
 #include "util.h"
 #include "testmode.h"
 
-#define MT_TX_RING_SIZE     256
 #define MT_MCU_RING_SIZE    32
 #define MT_RX_BUF_SIZE      2048
 #define MT_SKB_HEAD_LEN     128
 
+#define MT_MAX_NON_AQL_PKT  16
+#define MT_TXQ_FREE_THR     32
+
 struct mt76_dev;
 struct mt76_phy;
 struct mt76_wcid;
@@ -79,7 +81,8 @@ enum mt76_rxq_id {
 
 struct mt76_queue_buf {
 	dma_addr_t addr;
-	int len;
+	u16 len;
+	bool skip_unmap;
 };
 
 struct mt76_tx_info {
@@ -99,9 +102,11 @@ struct mt76_queue_entry {
 		struct urb *urb;
 		int buf_sz;
 	};
-	enum mt76_txq_id qid;
+	u32 dma_addr[2];
+	u16 dma_len[2];
+	u16 wcid;
 	bool skip_buf0:1;
-	bool schedule:1;
+	bool skip_buf1:1;
 	bool done:1;
 };
 
@@ -135,13 +140,6 @@ struct mt76_queue {
 	struct page_frag_cache rx_page;
 };
 
-struct mt76_sw_queue {
-	struct mt76_queue *q;
-
-	struct list_head swq;
-	int swq_queued;
-};
-
 struct mt76_mcu_ops {
 	u32 headroom;
 	u32 tailroom;
@@ -204,6 +202,7 @@ DECLARE_EWMA(signal, 10, 8);
 struct mt76_wcid {
 	struct mt76_rx_tid __rcu *aggr[IEEE80211_NUM_TIDS];
 
+	atomic_t non_aql_packets;
 	unsigned long flags;
 
 	struct ewma_signal rssi;
@@ -214,6 +213,7 @@ struct mt76_wcid {
 
 	u8 sta:1;
 	u8 ext_phy:1;
+	u8 amsdu:1;
 
 	u8 rx_check_pn;
 	u8 rx_key_pn[IEEE80211_NUM_TIDS][6];
@@ -226,11 +226,8 @@ struct mt76_wcid {
 };
 
 struct mt76_txq {
-	struct mt76_sw_queue *swq;
 	struct mt76_wcid *wcid;
 
-	struct sk_buff_head retry_q;
-
 	u16 agg_ssn;
 	bool send_bar;
 	bool aggr;
@@ -309,6 +306,7 @@ struct mt76_hw_cap {
 #define MT_DRV_SW_RX_AIRTIME		BIT(2)
 #define MT_DRV_RX_DMA_HDR		BIT(3)
 #define MT_DRV_HW_MGMT_TXQ		BIT(4)
+#define MT_DRV_AMSDU_OFFLOAD		BIT(5)
 
 struct mt76_driver_ops {
 	u32 drv_flags;
@@ -322,7 +320,7 @@ struct mt76_driver_ops {
 			      struct ieee80211_sta *sta,
 			      struct mt76_tx_info *tx_info);
 
-	void (*tx_complete_skb)(struct mt76_dev *dev, enum mt76_txq_id qid,
+	void (*tx_complete_skb)(struct mt76_dev *dev,
 				struct mt76_queue_entry *e);
 
 	bool (*tx_status_data)(struct mt76_dev *dev, u8 *update);
@@ -445,14 +443,24 @@ struct mt76_usb {
 	} mcu;
 };
 
+#define MT76S_XMIT_BUF_SZ	(16 * PAGE_SIZE)
 struct mt76_sdio {
-	struct task_struct *tx_kthread;
-	struct task_struct *kthread;
+	struct workqueue_struct *txrx_wq;
+	struct {
+		struct work_struct xmit_work;
+		struct work_struct status_work;
+	} tx;
+	struct {
+		struct work_struct recv_work;
+		struct work_struct net_work;
+	} rx;
+
 	struct work_struct stat_work;
 
-	unsigned long state;
+	u8 *xmit_buf[MT_TXQ_MCU_WA];
 
 	struct sdio_func *func;
+	void *intr_data;
 
 	struct {
 		struct mutex lock;
@@ -593,12 +601,12 @@ struct mt76_dev {
 	struct sk_buff_head rx_skb[__MT_RXQ_MAX];
 
 	struct list_head txwi_cache;
-	struct mt76_sw_queue q_tx[2 * __MT_TXQ_MAX];
+	struct mt76_queue *q_tx[2 * __MT_TXQ_MAX];
 	struct mt76_queue q_rx[__MT_RXQ_MAX];
 	const struct mt76_queue_ops *queue_ops;
 	int tx_dma_idx[4];
 
-	struct tasklet_struct tx_tasklet;
+	struct mt76_worker tx_worker;
 	struct napi_struct tx_napi;
 	struct delayed_work mac_work;
 
@@ -892,14 +900,13 @@ static inline bool mt76_testmode_enabled(struct mt76_dev *dev)
 void mt76_rx(struct mt76_dev *dev, enum mt76_rxq_id q, struct sk_buff *skb);
 void mt76_tx(struct mt76_phy *dev, struct ieee80211_sta *sta,
 	     struct mt76_wcid *wcid, struct sk_buff *skb);
-void mt76_txq_init(struct mt76_dev *dev, struct ieee80211_txq *txq);
-void mt76_txq_remove(struct mt76_dev *dev, struct ieee80211_txq *txq);
 void mt76_wake_tx_queue(struct ieee80211_hw *hw, struct ieee80211_txq *txq);
 void mt76_stop_tx_queues(struct mt76_dev *dev, struct ieee80211_sta *sta,
 			 bool send_bar);
+void mt76_tx_check_agg_ssn(struct ieee80211_sta *sta, struct sk_buff *skb);
 void mt76_txq_schedule(struct mt76_phy *phy, enum mt76_txq_id qid);
 void mt76_txq_schedule_all(struct mt76_phy *phy);
-void mt76_tx_tasklet(unsigned long data);
+void mt76_tx_worker(struct mt76_worker *w);
 void mt76_release_buffered_frames(struct ieee80211_hw *hw,
 				  struct ieee80211_sta *sta,
 				  u16 tids, int nframes,
@@ -932,7 +939,7 @@ struct sk_buff *mt76_tx_status_skb_get(struct mt76_dev *dev,
 				       struct sk_buff_head *list);
 void mt76_tx_status_skb_done(struct mt76_dev *dev, struct sk_buff *skb,
 			     struct sk_buff_head *list);
-void mt76_tx_complete_skb(struct mt76_dev *dev, struct sk_buff *skb);
+void mt76_tx_complete_skb(struct mt76_dev *dev, u16 wcid, struct sk_buff *skb);
 void mt76_tx_status_check(struct mt76_dev *dev, struct mt76_wcid *wcid,
 			  bool flush);
 int mt76_sta_state(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
@@ -996,8 +1003,6 @@ mt76_tx_status_get_hw(struct mt76_dev *dev, struct sk_buff *skb)
 	return hw;
 }
 
-void mt76_tx_free(struct mt76_dev *dev);
-struct mt76_txwi_cache *mt76_get_txwi(struct mt76_dev *dev);
 void mt76_put_txwi(struct mt76_dev *dev, struct mt76_txwi_cache *t);
 void mt76_rx_complete(struct mt76_dev *dev, struct sk_buff_head *frames,
 		      struct napi_struct *napi);
@@ -1005,6 +1010,8 @@ void mt76_rx_poll_complete(struct mt76_dev *dev, enum mt76_rxq_id q,
 			   struct napi_struct *napi);
 void mt76_rx_aggr_reorder(struct sk_buff *skb, struct sk_buff_head *frames);
 void mt76_testmode_tx_pending(struct mt76_dev *dev);
+void mt76_queue_tx_complete(struct mt76_dev *dev, struct mt76_queue *q,
+			    struct mt76_queue_entry *e);
 
 /* usb */
 static inline bool mt76u_urb_error(struct urb *urb)
@@ -1039,7 +1046,7 @@ mt76u_bulk_msg(struct mt76_dev *dev, void *data, int len, int *actual_len,
 	return usb_bulk_msg(udev, pipe, data, len, actual_len, timeout);
 }
 
-int mt76_skb_adjust_pad(struct sk_buff *skb);
+int mt76_skb_adjust_pad(struct sk_buff *skb, int pad);
 int mt76u_vendor_request(struct mt76_dev *dev, u8 req,
 			 u8 req_type, u16 val, u16 offset,
 			 void *buf, size_t len);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/beacon.c b/drivers/net/wireless/mediatek/mt76/mt7603/beacon.c
index 7a41cdf1c4ae..d728c5e43783 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7603/beacon.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7603/beacon.c
@@ -29,7 +29,7 @@ mt7603_update_beacon_iter(void *priv, u8 *mac, struct ieee80211_vif *vif)
 	mt76_wr(dev, MT_DMA_FQCR0, MT_DMA_FQCR0_BUSY |
 		FIELD_PREP(MT_DMA_FQCR0_TARGET_WCID, mvif->sta.wcid.idx) |
 		FIELD_PREP(MT_DMA_FQCR0_TARGET_QID,
-			   dev->mt76.q_tx[MT_TXQ_CAB].q->hw_idx) |
+			   dev->mt76.q_tx[MT_TXQ_CAB]->hw_idx) |
 		FIELD_PREP(MT_DMA_FQCR0_DEST_PORT_ID, 3) |
 		FIELD_PREP(MT_DMA_FQCR0_DEST_QUEUE_ID, 8));
 
@@ -78,7 +78,7 @@ void mt7603_pre_tbtt_tasklet(unsigned long arg)
 	data.dev = dev;
 	__skb_queue_head_init(&data.q);
 
-	q = dev->mt76.q_tx[MT_TXQ_BEACON].q;
+	q = dev->mt76.q_tx[MT_TXQ_BEACON];
 	spin_lock_bh(&q->lock);
 	ieee80211_iterate_active_interfaces_atomic(mt76_hw(dev),
 		IEEE80211_IFACE_ITER_RESUME_ALL,
@@ -95,7 +95,7 @@ void mt7603_pre_tbtt_tasklet(unsigned long arg)
 	if (dev->mt76.csa_complete)
 		goto out;
 
-	q = dev->mt76.q_tx[MT_TXQ_CAB].q;
+	q = dev->mt76.q_tx[MT_TXQ_CAB];
 	do {
 		nframes = skb_queue_len(&data.q);
 		ieee80211_iterate_active_interfaces_atomic(mt76_hw(dev),
@@ -136,7 +136,7 @@ void mt7603_pre_tbtt_tasklet(unsigned long arg)
 
 out:
 	mt76_queue_tx_cleanup(dev, MT_TXQ_BEACON, false);
-	if (dev->mt76.q_tx[MT_TXQ_BEACON].q->queued >
+	if (dev->mt76.q_tx[MT_TXQ_BEACON]->queued >
 	    hweight8(dev->mt76.beacon_mask))
 		dev->beacon_check++;
 }
diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/debugfs.c b/drivers/net/wireless/mediatek/mt76/mt7603/debugfs.c
index 8ce6880b2bb8..f52165dff422 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7603/debugfs.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7603/debugfs.c
@@ -70,7 +70,7 @@ DEFINE_DEBUGFS_ATTRIBUTE(fops_edcca, mt7603_edcca_get,
 			 mt7603_edcca_set, "%lld\n");
 
 static int
-mt7603_ampdu_stat_read(struct seq_file *file, void *data)
+mt7603_ampdu_stat_show(struct seq_file *file, void *data)
 {
 	struct mt7603_dev *dev = file->private;
 	int bound[3], i, range;
@@ -91,18 +91,7 @@ mt7603_ampdu_stat_read(struct seq_file *file, void *data)
 	return 0;
 }
 
-static int
-mt7603_ampdu_stat_open(struct inode *inode, struct file *f)
-{
-	return single_open(f, mt7603_ampdu_stat_read, inode->i_private);
-}
-
-static const struct file_operations fops_ampdu_stat = {
-	.open = mt7603_ampdu_stat_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(mt7603_ampdu_stat);
 
 void mt7603_init_debugfs(struct mt7603_dev *dev)
 {
@@ -112,7 +101,8 @@ void mt7603_init_debugfs(struct mt7603_dev *dev)
 	if (!dir)
 		return;
 
-	debugfs_create_file("ampdu_stat", 0400, dir, dev, &fops_ampdu_stat);
+	debugfs_create_file("ampdu_stat", 0400, dir, dev,
+			     &mt7603_ampdu_stat_fops);
 	debugfs_create_devm_seqfile(dev->mt76.dev, "xmit-queues", dir,
 				    mt76_queues_read);
 	debugfs_create_file("edcca", 0600, dir, dev, &fops_edcca);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/dma.c b/drivers/net/wireless/mediatek/mt76/mt7603/dma.c
index a08b85281170..d60d00f6f6a0 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7603/dma.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7603/dma.c
@@ -5,8 +5,7 @@
 #include "../dma.h"
 
 static int
-mt7603_init_tx_queue(struct mt7603_dev *dev, struct mt76_sw_queue *q,
-		     int idx, int n_desc)
+mt7603_init_tx_queue(struct mt7603_dev *dev, int qid, int idx, int n_desc)
 {
 	struct mt76_queue *hwq;
 	int err;
@@ -19,8 +18,7 @@ mt7603_init_tx_queue(struct mt7603_dev *dev, struct mt76_sw_queue *q,
 	if (err < 0)
 		return err;
 
-	INIT_LIST_HEAD(&q->swq);
-	q->q = hwq;
+	dev->mt76.q_tx[qid] = hwq;
 
 	mt7603_irq_enable(dev, MT_INT_TX_DONE(idx));
 
@@ -123,7 +121,7 @@ void mt7603_queue_rx_skb(struct mt76_dev *mdev, enum mt76_rxq_id q,
 			mt76_rx(&dev->mt76, q, skb);
 			return;
 		}
-		/* fall through */
+		fallthrough;
 	default:
 		dev_kfree_skb(skb);
 		break;
@@ -165,7 +163,7 @@ static int mt7603_poll_tx(struct napi_struct *napi, int budget)
 
 	mt7603_mac_sta_poll(dev);
 
-	tasklet_schedule(&dev->mt76.tx_tasklet);
+	mt76_worker_schedule(&dev->mt76.tx_worker);
 
 	return 0;
 }
@@ -193,29 +191,28 @@ int mt7603_dma_init(struct mt7603_dev *dev)
 	mt7603_pse_client_reset(dev);
 
 	for (i = 0; i < ARRAY_SIZE(wmm_queue_map); i++) {
-		ret = mt7603_init_tx_queue(dev, &dev->mt76.q_tx[i],
-					   wmm_queue_map[i],
-					   MT_TX_RING_SIZE);
+		ret = mt7603_init_tx_queue(dev, i, wmm_queue_map[i],
+					   MT7603_TX_RING_SIZE);
 		if (ret)
 			return ret;
 	}
 
-	ret = mt7603_init_tx_queue(dev, &dev->mt76.q_tx[MT_TXQ_PSD],
-				   MT_TX_HW_QUEUE_MGMT, MT_TX_RING_SIZE);
+	ret = mt7603_init_tx_queue(dev, MT_TXQ_PSD,
+				   MT_TX_HW_QUEUE_MGMT, MT7603_PSD_RING_SIZE);
 	if (ret)
 		return ret;
 
-	ret = mt7603_init_tx_queue(dev, &dev->mt76.q_tx[MT_TXQ_MCU],
+	ret = mt7603_init_tx_queue(dev, MT_TXQ_MCU,
 				   MT_TX_HW_QUEUE_MCU, MT_MCU_RING_SIZE);
 	if (ret)
 		return ret;
 
-	ret = mt7603_init_tx_queue(dev, &dev->mt76.q_tx[MT_TXQ_BEACON],
+	ret = mt7603_init_tx_queue(dev, MT_TXQ_BEACON,
 				   MT_TX_HW_QUEUE_BCN, MT_MCU_RING_SIZE);
 	if (ret)
 		return ret;
 
-	ret = mt7603_init_tx_queue(dev, &dev->mt76.q_tx[MT_TXQ_CAB],
+	ret = mt7603_init_tx_queue(dev, MT_TXQ_CAB,
 				   MT_TX_HW_QUEUE_BMC, MT_MCU_RING_SIZE);
 	if (ret)
 		return ret;
@@ -249,6 +246,5 @@ void mt7603_dma_cleanup(struct mt7603_dev *dev)
 		   MT_WPDMA_GLO_CFG_RX_DMA_EN |
 		   MT_WPDMA_GLO_CFG_TX_WRITEBACK_DONE);
 
-	tasklet_kill(&dev->mt76.tx_tasklet);
 	mt76_dma_cleanup(&dev->mt76);
 }
diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/eeprom.c b/drivers/net/wireless/mediatek/mt76/mt7603/eeprom.c
index 3ee06e2577b8..01f1e0da5ee1 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7603/eeprom.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7603/eeprom.c
@@ -147,8 +147,14 @@ static int mt7603_check_eeprom(struct mt76_dev *dev)
 	}
 }
 
+static inline bool is_mt7688(struct mt7603_dev *dev)
+{
+	return mt76_rr(dev, MT_EFUSE_BASE + 0x64) & BIT(4);
+}
+
 int mt7603_eeprom_init(struct mt7603_dev *dev)
 {
+	u8 *eeprom;
 	int ret;
 
 	ret = mt7603_eeprom_load(dev);
@@ -163,9 +169,16 @@ int mt7603_eeprom_init(struct mt7603_dev *dev)
 			       MT7603_EEPROM_SIZE);
 	}
 
+	eeprom = (u8 *)dev->mt76.eeprom.data;
 	dev->mt76.cap.has_2ghz = true;
-	memcpy(dev->mt76.macaddr, dev->mt76.eeprom.data + MT_EE_MAC_ADDR,
-	       ETH_ALEN);
+	memcpy(dev->mt76.macaddr, eeprom + MT_EE_MAC_ADDR, ETH_ALEN);
+
+	/* Check for 1SS devices */
+	dev->mphy.antenna_mask = 3;
+	if (FIELD_GET(MT_EE_NIC_CONF_0_RX_PATH, eeprom[MT_EE_NIC_CONF_0]) == 1 ||
+	    FIELD_GET(MT_EE_NIC_CONF_0_TX_PATH, eeprom[MT_EE_NIC_CONF_0]) == 1 ||
+	    is_mt7688(dev))
+		dev->mphy.antenna_mask = 1;
 
 	mt76_eeprom_override(&dev->mt76);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/eeprom.h b/drivers/net/wireless/mediatek/mt76/mt7603/eeprom.h
index b893facfba48..4687d6dc00dc 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7603/eeprom.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7603/eeprom.h
@@ -85,4 +85,7 @@ enum mt7603_eeprom_source {
 	MT_EE_SRC_FLASH,
 };
 
+#define MT_EE_NIC_CONF_0_RX_PATH		GENMASK(3, 0)
+#define MT_EE_NIC_CONF_0_TX_PATH		GENMASK(7, 4)
+
 #endif
diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/init.c b/drivers/net/wireless/mediatek/mt76/mt7603/init.c
index 94196599797e..c4848fafd270 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7603/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7603/init.c
@@ -536,11 +536,6 @@ int mt7603_register_device(struct mt7603_dev *dev)
 	tasklet_init(&dev->mt76.pre_tbtt_tasklet, mt7603_pre_tbtt_tasklet,
 		     (unsigned long)dev);
 
-	/* Check for 7688, which only has 1SS */
-	dev->mphy.antenna_mask = 3;
-	if (mt76_rr(dev, MT_EFUSE_BASE + 0x64) & BIT(4))
-		dev->mphy.antenna_mask = 1;
-
 	dev->slottime = 9;
 	dev->sensitivity_limit = 28;
 	dev->dynamic_sensitivity = true;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/mac.c b/drivers/net/wireless/mediatek/mt76/mt7603/mac.c
index 8060c1514396..f665a1c95eed 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7603/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7603/mac.c
@@ -445,7 +445,7 @@ void mt7603_mac_sta_poll(struct mt7603_dev *dev)
 
 		sta = container_of((void *)msta, struct ieee80211_sta, drv_priv);
 		for (i = 0; i < 4; i++) {
-			struct mt76_queue *q = dev->mt76.q_tx[i].q;
+			struct mt76_queue *q = dev->mt76.q_tx[i];
 			u8 qidx = q->hw_idx;
 			u8 tid = ac_to_tid[i];
 			u32 txtime = airtime[qidx];
@@ -592,7 +592,7 @@ mt7603_mac_fill_rx(struct mt7603_dev *dev, struct sk_buff *skb)
 		switch (FIELD_GET(MT_RXV1_TX_MODE, rxdg0)) {
 		case MT_PHY_TYPE_CCK:
 			cck = true;
-			/* fall through */
+			fallthrough;
 		case MT_PHY_TYPE_OFDM:
 			i = mt76_get_rate(&dev->mt76, sband, i, cck);
 			break;
@@ -896,7 +896,7 @@ mt7603_mac_write_txwi(struct mt7603_dev *dev, __le32 *txwi,
 	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
 	struct ieee80211_bar *bar = (struct ieee80211_bar *)skb->data;
 	struct ieee80211_vif *vif = info->control.vif;
-	struct mt76_queue *q = dev->mt76.q_tx[qid].q;
+	struct mt76_queue *q = dev->mt76.q_tx[qid];
 	struct mt7603_vif *mvif;
 	int wlan_idx;
 	int hdr_len = ieee80211_get_hdrlen_from_skb(skb);
@@ -1036,6 +1036,8 @@ int mt7603_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr,
 				    IEEE80211_TX_CTL_CLEAR_PS_FILT)) ||
 		    (info->control.flags & IEEE80211_TX_CTRL_PS_RESPONSE))
 			mt7603_wtbl_set_ps(dev, msta, false);
+
+		mt76_tx_check_agg_ssn(sta, tx_info->skb);
 	}
 
 	pid = mt76_tx_status_skb_add(mdev, wcid, tx_info->skb);
@@ -1161,7 +1163,7 @@ out:
 	switch (FIELD_GET(MT_TX_RATE_MODE, final_rate)) {
 	case MT_PHY_TYPE_CCK:
 		cck = true;
-		/* fall through */
+		fallthrough;
 	case MT_PHY_TYPE_OFDM:
 		if (dev->mphy.chandef.chan->band == NL80211_BAND_5GHZ)
 			sband = &dev->mphy.sband_5g.sband;
@@ -1269,8 +1271,7 @@ out:
 	rcu_read_unlock();
 }
 
-void mt7603_tx_complete_skb(struct mt76_dev *mdev, enum mt76_txq_id qid,
-			    struct mt76_queue_entry *e)
+void mt7603_tx_complete_skb(struct mt76_dev *mdev, struct mt76_queue_entry *e)
 {
 	struct mt7603_dev *dev = container_of(mdev, struct mt7603_dev, mt76);
 	struct sk_buff *skb = e->skb;
@@ -1280,10 +1281,8 @@ void mt7603_tx_complete_skb(struct mt76_dev *mdev, enum mt76_txq_id qid,
 		return;
 	}
 
-	if (qid < 4)
-		dev->tx_hang_check = 0;
-
-	mt76_tx_complete_skb(mdev, skb);
+	dev->tx_hang_check = 0;
+	mt76_tx_complete_skb(mdev, e->wcid, skb);
 }
 
 static bool
@@ -1403,7 +1402,7 @@ static void mt7603_mac_watchdog_reset(struct mt7603_dev *dev)
 	/* lock/unlock all queues to ensure that no tx is pending */
 	mt76_txq_schedule_all(&dev->mphy);
 
-	tasklet_disable(&dev->mt76.tx_tasklet);
+	mt76_worker_disable(&dev->mt76.tx_worker);
 	tasklet_disable(&dev->mt76.pre_tbtt_tasklet);
 	napi_disable(&dev->mt76.napi[0]);
 	napi_disable(&dev->mt76.napi[1]);
@@ -1452,7 +1451,7 @@ skip_dma_reset:
 	clear_bit(MT76_RESET, &dev->mphy.state);
 	mutex_unlock(&dev->mt76.mutex);
 
-	tasklet_enable(&dev->mt76.tx_tasklet);
+	mt76_worker_enable(&dev->mt76.tx_worker);
 	napi_enable(&dev->mt76.tx_napi);
 	napi_schedule(&dev->mt76.tx_napi);
 
@@ -1515,7 +1514,7 @@ static bool mt7603_tx_hang(struct mt7603_dev *dev)
 	int i;
 
 	for (i = 0; i < 4; i++) {
-		q = dev->mt76.q_tx[i].q;
+		q = dev->mt76.q_tx[i];
 
 		if (!q->queued)
 			continue;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/main.c b/drivers/net/wireless/mediatek/mt76/mt7603/main.c
index 447f2c63ef38..c9226dceb510 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7603/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7603/main.c
@@ -75,7 +75,6 @@ mt7603_add_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif)
 
 	mtxq = (struct mt76_txq *)vif->txq->drv_priv;
 	mtxq->wcid = &mvif->sta.wcid;
-	mt76_txq_init(&dev->mt76, vif->txq);
 	rcu_assign_pointer(dev->mt76.wcid[idx], &mvif->sta.wcid);
 
 out:
@@ -99,7 +98,6 @@ mt7603_remove_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif)
 	mt7603_beacon_set_timer(dev, mvif->idx, 0);
 
 	rcu_assign_pointer(dev->mt76.wcid[idx], NULL);
-	mt76_txq_remove(&dev->mt76, vif->txq);
 
 	spin_lock_bh(&dev->sta_poll_lock);
 	if (!list_empty(&msta->poll_list))
@@ -514,7 +512,7 @@ mt7603_conf_tx(struct ieee80211_hw *hw, struct ieee80211_vif *vif, u16 queue,
 	u16 cw_max = (1 << 10) - 1;
 	u32 val;
 
-	queue = dev->mt76.q_tx[queue].q->hw_idx;
+	queue = dev->mt76.q_tx[queue]->hw_idx;
 
 	if (params->cw_min)
 		cw_min = params->cw_min;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/mt7603.h b/drivers/net/wireless/mediatek/mt76/mt7603/mt7603.h
index c86305241e66..2a6e4332ad06 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7603/mt7603.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7603/mt7603.h
@@ -17,6 +17,8 @@
 
 #define MT7603_MCU_RX_RING_SIZE	64
 #define MT7603_RX_RING_SIZE     128
+#define MT7603_TX_RING_SIZE	256
+#define MT7603_PSD_RING_SIZE	128
 
 #define MT7603_FIRMWARE_E1	"mt7603_e1.bin"
 #define MT7603_FIRMWARE_E2	"mt7603_e2.bin"
@@ -241,8 +243,7 @@ int mt7603_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr,
 			  struct ieee80211_sta *sta,
 			  struct mt76_tx_info *tx_info);
 
-void mt7603_tx_complete_skb(struct mt76_dev *mdev, enum mt76_txq_id qid,
-			    struct mt76_queue_entry *e);
+void mt7603_tx_complete_skb(struct mt76_dev *mdev, struct mt76_queue_entry *e);
 
 void mt7603_queue_rx_skb(struct mt76_dev *mdev, enum mt76_rxq_id q,
 			 struct sk_buff *skb);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/pci.c b/drivers/net/wireless/mediatek/mt76/mt7603/pci.c
index 2f2f337e2201..a5845da3547a 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7603/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7603/pci.c
@@ -44,6 +44,8 @@ mt76pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		    (mt76_rr(dev, MT_HW_REV) & 0xff);
 	dev_info(mdev->dev, "ASIC revision: %04x\n", mdev->rev);
 
+	mt76_wr(dev, MT_INT_MASK_CSR, 0);
+
 	ret = devm_request_irq(mdev->dev, pdev->irq, mt7603_irq_handler,
 			       IRQF_SHARED, KBUILD_MODNAME, dev);
 	if (ret)
diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/soc.c b/drivers/net/wireless/mediatek/mt76/mt7603/soc.c
index de170765e938..ba927033bbe8 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7603/soc.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7603/soc.c
@@ -35,6 +35,8 @@ mt76_wmac_probe(struct platform_device *pdev)
 		    (mt76_rr(dev, MT_HW_REV) & 0xff);
 	dev_info(mdev->dev, "ASIC revision: %04x\n", mdev->rev);
 
+	mt76_wr(dev, MT_INT_MASK_CSR, 0);
+
 	ret = devm_request_irq(mdev->dev, irq, mt7603_irq_handler,
 			       IRQF_SHARED, KBUILD_MODNAME, dev);
 	if (ret)
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/debugfs.c b/drivers/net/wireless/mediatek/mt76/mt7615/debugfs.c
index 88931658a9fb..00ba550fc48f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/debugfs.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/debugfs.c
@@ -165,15 +165,14 @@ mt7615_reset_test_set(void *data, u64 val)
 	if (!mt7615_wait_for_mcu_init(dev))
 		return 0;
 
-	mt7615_mutex_acquire(dev);
-
 	skb = alloc_skb(1, GFP_KERNEL);
 	if (!skb)
 		return -ENOMEM;
 
 	skb_put(skb, 1);
-	mt76_tx_queue_skb_raw(dev, 0, skb, 0);
 
+	mt7615_mutex_acquire(dev);
+	mt76_tx_queue_skb_raw(dev, 0, skb, 0);
 	mt7615_mutex_release(dev);
 
 	return 0;
@@ -221,7 +220,7 @@ mt7615_ampdu_stat_read_phy(struct mt7615_phy *phy,
 }
 
 static int
-mt7615_ampdu_stat_read(struct seq_file *file, void *data)
+mt7615_ampdu_stat_show(struct seq_file *file, void *data)
 {
 	struct mt7615_dev *dev = file->private;
 
@@ -235,18 +234,7 @@ mt7615_ampdu_stat_read(struct seq_file *file, void *data)
 	return 0;
 }
 
-static int
-mt7615_ampdu_stat_open(struct inode *inode, struct file *f)
-{
-	return single_open(f, mt7615_ampdu_stat_read, inode->i_private);
-}
-
-static const struct file_operations fops_ampdu_stat = {
-	.open = mt7615_ampdu_stat_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(mt7615_ampdu_stat);
 
 static void
 mt7615_radio_read_phy(struct mt7615_phy *phy, struct seq_file *s)
@@ -340,15 +328,15 @@ mt7615_queues_read(struct seq_file *s, void *data)
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(queue_map); i++) {
-		struct mt76_sw_queue *q = &dev->mt76.q_tx[queue_map[i].id];
+		struct mt76_queue *q = dev->mt76.q_tx[queue_map[i].id];
 
-		if (!q->q)
+		if (!q)
 			continue;
 
 		seq_printf(s,
 			   "%s:	queued=%d head=%d tail=%d\n",
-			   queue_map[i].queue, q->q->queued, q->q->head,
-			   q->q->tail);
+			   queue_map[i].queue, q->queued, q->head,
+			   q->tail);
 	}
 
 	return 0;
@@ -393,7 +381,7 @@ int mt7615_init_debugfs(struct mt7615_dev *dev)
 					    mt76_queues_read);
 	debugfs_create_devm_seqfile(dev->mt76.dev, "acq", dir,
 				    mt7615_queues_acq);
-	debugfs_create_file("ampdu_stat", 0400, dir, dev, &fops_ampdu_stat);
+	debugfs_create_file("ampdu_stat", 0400, dir, dev, &mt7615_ampdu_stat_fops);
 	debugfs_create_file("scs", 0600, dir, dev, &fops_scs);
 	debugfs_create_file("dbdc", 0600, dir, dev, &fops_dbdc);
 	debugfs_create_file("fw_debug", 0600, dir, dev, &fops_fw_debug);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/dma.c b/drivers/net/wireless/mediatek/mt76/mt7615/dma.c
index 1231a5ddf9ea..bf8ae14121db 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/dma.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/dma.c
@@ -12,8 +12,7 @@
 #include "mac.h"
 
 static int
-mt7615_init_tx_queue(struct mt7615_dev *dev, struct mt76_sw_queue *q,
-		      int idx, int n_desc)
+mt7615_init_tx_queue(struct mt7615_dev *dev, int qid, int idx, int n_desc)
 {
 	struct mt76_queue *hwq;
 	int err;
@@ -26,8 +25,7 @@ mt7615_init_tx_queue(struct mt7615_dev *dev, struct mt76_sw_queue *q,
 	if (err < 0)
 		return err;
 
-	INIT_LIST_HEAD(&q->swq);
-	q->q = hwq;
+	dev->mt76.q_tx[qid] = hwq;
 
 	return 0;
 }
@@ -45,19 +43,18 @@ mt7622_init_tx_queues_multi(struct mt7615_dev *dev)
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(wmm_queue_map); i++) {
-		ret = mt7615_init_tx_queue(dev, &dev->mt76.q_tx[i],
-					   wmm_queue_map[i],
+		ret = mt7615_init_tx_queue(dev, i, wmm_queue_map[i],
 					   MT7615_TX_RING_SIZE / 2);
 		if (ret)
 			return ret;
 	}
 
-	ret = mt7615_init_tx_queue(dev, &dev->mt76.q_tx[MT_TXQ_PSD],
+	ret = mt7615_init_tx_queue(dev, MT_TXQ_PSD,
 				   MT7622_TXQ_MGMT, MT7615_TX_MGMT_RING_SIZE);
 	if (ret)
 		return ret;
 
-	ret = mt7615_init_tx_queue(dev, &dev->mt76.q_tx[MT_TXQ_MCU],
+	ret = mt7615_init_tx_queue(dev, MT_TXQ_MCU,
 				   MT7622_TXQ_MCU, MT7615_TX_MCU_RING_SIZE);
 	return ret;
 }
@@ -65,10 +62,9 @@ mt7622_init_tx_queues_multi(struct mt7615_dev *dev)
 static int
 mt7615_init_tx_queues(struct mt7615_dev *dev)
 {
-	struct mt76_sw_queue *q;
 	int ret, i;
 
-	ret = mt7615_init_tx_queue(dev, &dev->mt76.q_tx[MT_TXQ_FWDL],
+	ret = mt7615_init_tx_queue(dev, MT_TXQ_FWDL,
 				   MT7615_TXQ_FWDL,
 				   MT7615_TX_FWDL_RING_SIZE);
 	if (ret)
@@ -77,52 +73,28 @@ mt7615_init_tx_queues(struct mt7615_dev *dev)
 	if (!is_mt7615(&dev->mt76))
 		return mt7622_init_tx_queues_multi(dev);
 
-	ret = mt7615_init_tx_queue(dev, &dev->mt76.q_tx[0], 0,
-				   MT7615_TX_RING_SIZE);
+	ret = mt7615_init_tx_queue(dev, 0, 0, MT7615_TX_RING_SIZE);
 	if (ret)
 		return ret;
 
-	for (i = 1; i < MT_TXQ_MCU; i++) {
-		q = &dev->mt76.q_tx[i];
-		INIT_LIST_HEAD(&q->swq);
-		q->q = dev->mt76.q_tx[0].q;
-	}
+	for (i = 1; i < MT_TXQ_MCU; i++)
+		dev->mt76.q_tx[i] = dev->mt76.q_tx[0];
 
-	ret = mt7615_init_tx_queue(dev, &dev->mt76.q_tx[MT_TXQ_MCU],
-				   MT7615_TXQ_MCU,
+	ret = mt7615_init_tx_queue(dev, MT_TXQ_MCU, MT7615_TXQ_MCU,
 				   MT7615_TX_MCU_RING_SIZE);
 	return 0;
 }
 
-static void
-mt7615_tx_cleanup(struct mt7615_dev *dev)
-{
-	int i;
-
-	mt76_queue_tx_cleanup(dev, MT_TXQ_MCU, false);
-	mt76_queue_tx_cleanup(dev, MT_TXQ_PSD, false);
-	if (is_mt7615(&dev->mt76)) {
-		mt76_queue_tx_cleanup(dev, MT_TXQ_BE, false);
-	} else {
-		for (i = 0; i < IEEE80211_NUM_ACS; i++)
-			mt76_queue_tx_cleanup(dev, i, false);
-	}
-}
-
 static int mt7615_poll_tx(struct napi_struct *napi, int budget)
 {
 	struct mt7615_dev *dev;
 
 	dev = container_of(napi, struct mt7615_dev, mt76.tx_napi);
 
-	mt7615_tx_cleanup(dev);
+	mt76_queue_tx_cleanup(dev, MT_TXQ_MCU, false);
 
 	if (napi_complete_done(napi, 0))
-		mt7615_irq_enable(dev, MT_INT_TX_DONE_ALL);
-
-	mt7615_tx_cleanup(dev);
-
-	tasklet_schedule(&dev->mt76.tx_tasklet);
+		mt7615_irq_enable(dev, mt7615_tx_mcu_int_mask(dev));
 
 	return 0;
 }
@@ -306,7 +278,7 @@ int mt7615_dma_init(struct mt7615_dev *dev)
 		 MT_WPDMA_GLO_CFG_RX_DMA_EN);
 
 	/* enable interrupts for TX/RX rings */
-	mt7615_irq_enable(dev, MT_INT_RX_DONE_ALL | MT_INT_TX_DONE_ALL |
+	mt7615_irq_enable(dev, MT_INT_RX_DONE_ALL | mt7615_tx_mcu_int_mask(dev) |
 			       MT_INT_MCU_CMD);
 
 	if (is_mt7622(&dev->mt76))
@@ -325,6 +297,5 @@ void mt7615_dma_cleanup(struct mt7615_dev *dev)
 		   MT_WPDMA_GLO_CFG_RX_DMA_EN);
 	mt76_set(dev, MT_WPDMA_GLO_CFG, MT_WPDMA_GLO_CFG_SW_RESET);
 
-	tasklet_kill(&dev->mt76.tx_tasklet);
 	mt76_dma_cleanup(&dev->mt76);
 }
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/eeprom.c b/drivers/net/wireless/mediatek/mt76/mt7615/eeprom.c
index 22e4eabe6578..f4756bb946c3 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/eeprom.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/eeprom.c
@@ -125,6 +125,9 @@ mt7615_eeprom_parse_hw_band_cap(struct mt7615_dev *dev)
 	case MT_EE_2GHZ:
 		dev->mt76.cap.has_2ghz = true;
 		break;
+	case MT_EE_DBDC:
+		dev->dbdc_support = true;
+		/* fall through */
 	default:
 		dev->mt76.cap.has_2ghz = true;
 		dev->mt76.cap.has_5ghz = true;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/init.c b/drivers/net/wireless/mediatek/mt76/mt7615/init.c
index fc1ebabfebac..2a4db46727fb 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/init.c
@@ -217,6 +217,22 @@ static const struct ieee80211_iface_limit if_limits[] = {
 	}
 };
 
+static const struct ieee80211_iface_combination if_comb_radar[] = {
+	{
+		.limits = if_limits,
+		.n_limits = ARRAY_SIZE(if_limits),
+		.max_interfaces = 4,
+		.num_different_channels = 1,
+		.beacon_int_infra_match = true,
+		.radar_detect_widths = BIT(NL80211_CHAN_WIDTH_20_NOHT) |
+				       BIT(NL80211_CHAN_WIDTH_20) |
+				       BIT(NL80211_CHAN_WIDTH_40) |
+				       BIT(NL80211_CHAN_WIDTH_80) |
+				       BIT(NL80211_CHAN_WIDTH_160) |
+				       BIT(NL80211_CHAN_WIDTH_80P80),
+	}
+};
+
 static const struct ieee80211_iface_combination if_comb[] = {
 	{
 		.limits = if_limits,
@@ -306,8 +322,13 @@ mt7615_init_wiphy(struct ieee80211_hw *hw)
 	hw->sta_data_size = sizeof(struct mt7615_sta);
 	hw->vif_data_size = sizeof(struct mt7615_vif);
 
-	wiphy->iface_combinations = if_comb;
-	wiphy->n_iface_combinations = ARRAY_SIZE(if_comb);
+	if (is_mt7663(&phy->dev->mt76)) {
+		wiphy->iface_combinations = if_comb;
+		wiphy->n_iface_combinations = ARRAY_SIZE(if_comb);
+	} else {
+		wiphy->iface_combinations = if_comb_radar;
+		wiphy->n_iface_combinations = ARRAY_SIZE(if_comb_radar);
+	}
 	wiphy->reg_notifier = mt7615_regd_notifier;
 
 	wiphy->max_sched_scan_plan_interval = MT7615_MAX_SCHED_SCAN_INTERVAL;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mac.c b/drivers/net/wireless/mediatek/mt76/mt7615/mac.c
index 3dd8dd28690e..8dc645e398fd 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/mac.c
@@ -378,7 +378,7 @@ static int mt7615_mac_fill_rx(struct mt7615_dev *dev, struct sk_buff *skb)
 		switch (FIELD_GET(MT_RXV1_TX_MODE, rxdg0)) {
 		case MT_PHY_TYPE_CCK:
 			cck = true;
-			/* fall through */
+			fallthrough;
 		case MT_PHY_TYPE_OFDM:
 			i = mt76_get_rate(&dev->mt76, sband, i, cck);
 			break;
@@ -1271,7 +1271,7 @@ out:
 	switch (FIELD_GET(MT_TX_RATE_MODE, final_rate)) {
 	case MT_PHY_TYPE_CCK:
 		cck = true;
-		/* fall through */
+		fallthrough;
 	case MT_PHY_TYPE_OFDM:
 		mphy = &dev->mphy;
 		if (sta->wcid.ext_phy && dev->mt76.phy2)
@@ -1400,6 +1400,9 @@ mt7615_mac_tx_free_token(struct mt7615_dev *dev, u16 token)
 {
 	struct mt76_dev *mdev = &dev->mt76;
 	struct mt76_txwi_cache *txwi;
+	__le32 *txwi_data;
+	u32 val;
+	u8 wcid;
 
 	trace_mac_tx_free(dev, token);
 
@@ -1410,9 +1413,13 @@ mt7615_mac_tx_free_token(struct mt7615_dev *dev, u16 token)
 	if (!txwi)
 		return;
 
+	txwi_data = (__le32 *)mt76_get_txwi_ptr(mdev, txwi);
+	val = le32_to_cpu(txwi_data[1]);
+	wcid = FIELD_GET(MT_TXD1_WLAN_IDX, val);
+
 	mt7615_txp_skb_unmap(mdev, txwi);
 	if (txwi->skb) {
-		mt76_tx_complete_skb(mdev, txwi->skb);
+		mt76_tx_complete_skb(mdev, wcid, txwi->skb);
 		txwi->skb = NULL;
 	}
 
@@ -1424,6 +1431,14 @@ static void mt7615_mac_tx_free(struct mt7615_dev *dev, struct sk_buff *skb)
 	struct mt7615_tx_free *free = (struct mt7615_tx_free *)skb->data;
 	u8 i, count;
 
+	mt76_queue_tx_cleanup(dev, MT_TXQ_PSD, false);
+	if (is_mt7615(&dev->mt76)) {
+		mt76_queue_tx_cleanup(dev, MT_TXQ_BE, false);
+	} else {
+		for (i = 0; i < IEEE80211_NUM_ACS; i++)
+			mt76_queue_tx_cleanup(dev, i, false);
+	}
+
 	count = FIELD_GET(MT_TX_FREE_MSDU_ID_CNT, le16_to_cpu(free->ctrl));
 	if (is_mt7615(&dev->mt76)) {
 		__le16 *token = &free->token[0];
@@ -1439,11 +1454,15 @@ static void mt7615_mac_tx_free(struct mt7615_dev *dev, struct sk_buff *skb)
 
 	dev_kfree_skb(skb);
 
+	if (test_bit(MT76_STATE_PM, &dev->phy.mt76->state))
+		return;
+
 	rcu_read_lock();
 	mt7615_mac_sta_poll(dev);
 	rcu_read_unlock();
 
-	tasklet_schedule(&dev->mt76.tx_tasklet);
+	mt7615_pm_power_save_sched(dev);
+	mt76_worker_schedule(&dev->mt76.tx_worker);
 }
 
 void mt7615_queue_rx_skb(struct mt76_dev *mdev, enum mt76_rxq_id q,
@@ -1478,7 +1497,7 @@ void mt7615_queue_rx_skb(struct mt76_dev *mdev, enum mt76_rxq_id q,
 			mt76_rx(&dev->mt76, q, skb);
 			return;
 		}
-		/* fall through */
+		fallthrough;
 	default:
 		dev_kfree_skb(skb);
 		break;
@@ -1845,7 +1864,7 @@ void mt7615_pm_wake_work(struct work_struct *work)
 						pm.wake_work);
 	mphy = dev->phy.mt76;
 
-	if (mt7615_driver_own(dev)) {
+	if (mt7615_mcu_set_drv_ctrl(dev)) {
 		dev_err(mphy->dev->dev, "failed to wake device\n");
 		goto out;
 	}
@@ -1853,12 +1872,13 @@ void mt7615_pm_wake_work(struct work_struct *work)
 	spin_lock_bh(&dev->pm.txq_lock);
 	for (i = 0; i < IEEE80211_NUM_ACS; i++) {
 		struct mt7615_sta *msta = dev->pm.tx_q[i].msta;
-		struct mt76_wcid *wcid = msta ? &msta->wcid : NULL;
 		struct ieee80211_sta *sta = NULL;
+		struct mt76_wcid *wcid;
 
 		if (!dev->pm.tx_q[i].skb)
 			continue;
 
+		wcid = msta ? &msta->wcid : &dev->mt76.global_wcid;
 		if (msta && wcid->sta)
 			sta = container_of((void *)msta, struct ieee80211_sta,
 					   drv_priv);
@@ -1868,7 +1888,7 @@ void mt7615_pm_wake_work(struct work_struct *work)
 	}
 	spin_unlock_bh(&dev->pm.txq_lock);
 
-	tasklet_schedule(&dev->mt76.tx_tasklet);
+	mt76_worker_schedule(&dev->mt76.tx_worker);
 
 out:
 	ieee80211_wake_queues(mphy->hw);
@@ -1943,7 +1963,7 @@ void mt7615_pm_power_save_work(struct work_struct *work)
 		goto out;
 	}
 
-	if (!mt7615_firmware_own(dev))
+	if (!mt7615_mcu_set_fw_ctrl(dev))
 		return;
 out:
 	queue_delayed_work(dev->mt76.wq, &dev->pm.ps_work, delta);
@@ -2110,7 +2130,7 @@ void mt7615_mac_reset_work(struct work_struct *work)
 	if (ext_phy)
 		mt76_txq_schedule_all(ext_phy);
 
-	tasklet_disable(&dev->mt76.tx_tasklet);
+	mt76_worker_disable(&dev->mt76.tx_worker);
 	napi_disable(&dev->mt76.napi[0]);
 	napi_disable(&dev->mt76.napi[1]);
 	napi_disable(&dev->mt76.tx_napi);
@@ -2131,7 +2151,7 @@ void mt7615_mac_reset_work(struct work_struct *work)
 	clear_bit(MT76_MCU_RESET, &dev->mphy.state);
 	clear_bit(MT76_RESET, &dev->mphy.state);
 
-	tasklet_enable(&dev->mt76.tx_tasklet);
+	mt76_worker_enable(&dev->mt76.tx_worker);
 	napi_enable(&dev->mt76.tx_napi);
 	napi_schedule(&dev->mt76.tx_napi);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/main.c b/drivers/net/wireless/mediatek/mt76/mt7615/main.c
index 2d0b1f49fdbc..3186b7b2ca48 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/main.c
@@ -205,7 +205,6 @@ static int mt7615_add_interface(struct ieee80211_hw *hw,
 	if (vif->txq) {
 		mtxq = (struct mt76_txq *)vif->txq->drv_priv;
 		mtxq->wcid = &mvif->sta.wcid;
-		mt76_txq_init(&dev->mt76, vif->txq);
 	}
 
 	ret = mt7615_mcu_add_dev_info(dev, vif, true);
@@ -256,8 +255,6 @@ static void mt7615_remove_interface(struct ieee80211_hw *hw,
 	mt7615_mcu_add_dev_info(dev, vif, false);
 
 	rcu_assign_pointer(dev->mt76.wcid[idx], NULL);
-	if (vif->txq)
-		mt76_txq_remove(&dev->mt76, vif->txq);
 
 	dev->mphy.vif_mask &= ~BIT(mvif->idx);
 	dev->omac_mask &= ~BIT(mvif->omac_idx);
@@ -361,7 +358,10 @@ mt7615_queue_key_update(struct mt7615_dev *dev, enum set_key_cmd cmd,
 	wd->key.keylen = key->keylen;
 	wd->key.cmd = cmd;
 
+	spin_lock_bh(&dev->mt76.lock);
 	list_add_tail(&wd->node, &dev->wd_head);
+	spin_unlock_bh(&dev->mt76.lock);
+
 	queue_work(dev->mt76.wq, &dev->wtbl_work);
 
 	return 0;
@@ -703,7 +703,8 @@ mt7615_wake_tx_queue(struct ieee80211_hw *hw, struct ieee80211_txq *txq)
 		return;
 	}
 
-	tasklet_schedule(&dev->mt76.tx_tasklet);
+	dev->pm.last_activity = jiffies;
+	mt76_worker_schedule(&dev->mt76.tx_worker);
 }
 
 static void mt7615_tx(struct ieee80211_hw *hw,
@@ -732,6 +733,7 @@ static void mt7615_tx(struct ieee80211_hw *hw,
 	}
 
 	if (!test_bit(MT76_STATE_PM, &mphy->state)) {
+		dev->pm.last_activity = jiffies;
 		mt76_tx(mphy, control->sta, wcid, skb);
 		return;
 	}
@@ -813,7 +815,6 @@ mt7615_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	case IEEE80211_AMPDU_TX_START:
 		ssn = mt7615_mac_get_sta_tid_sn(dev, msta->wcid.idx, tid);
 		params->ssn = ssn;
-		mtxq->agg_ssn = IEEE80211_SN_TO_SEQ(ssn);
 		ret = IEEE80211_AMPDU_TX_START_IMMEDIATE;
 		break;
 	case IEEE80211_AMPDU_TX_STOP_CONT:
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c
index 084982eb6abd..31b40fb83f6c 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c
@@ -324,6 +324,97 @@ int mt7615_rf_wr(struct mt7615_dev *dev, u32 wf, u32 reg, u32 val)
 				   sizeof(req), false);
 }
 
+static void mt7622_trigger_hif_int(struct mt7615_dev *dev, bool en)
+{
+	if (!is_mt7622(&dev->mt76))
+		return;
+
+	regmap_update_bits(dev->infracfg, MT_INFRACFG_MISC,
+			   MT_INFRACFG_MISC_AP2CONN_WAKE,
+			   !en * MT_INFRACFG_MISC_AP2CONN_WAKE);
+}
+
+static int mt7615_mcu_drv_pmctrl(struct mt7615_dev *dev)
+{
+	struct mt76_phy *mphy = &dev->mt76.phy;
+	struct mt76_dev *mdev = &dev->mt76;
+	u32 addr;
+	int err;
+
+	addr = is_mt7663(mdev) ? MT_PCIE_DOORBELL_PUSH : MT_CFG_LPCR_HOST;
+	mt76_wr(dev, addr, MT_CFG_LPCR_HOST_DRV_OWN);
+
+	mt7622_trigger_hif_int(dev, true);
+
+	addr = is_mt7663(mdev) ? MT_CONN_HIF_ON_LPCTL : MT_CFG_LPCR_HOST;
+	err = !mt76_poll_msec(dev, addr, MT_CFG_LPCR_HOST_FW_OWN, 0, 3000);
+
+	mt7622_trigger_hif_int(dev, false);
+
+	if (err) {
+		dev_err(mdev->dev, "driver own failed\n");
+		return -ETIMEDOUT;
+	}
+
+	clear_bit(MT76_STATE_PM, &mphy->state);
+
+	return 0;
+}
+
+static int mt7615_mcu_lp_drv_pmctrl(struct mt7615_dev *dev)
+{
+	struct mt76_phy *mphy = &dev->mt76.phy;
+	int i;
+
+	if (!test_and_clear_bit(MT76_STATE_PM, &mphy->state))
+		goto out;
+
+	for (i = 0; i < MT7615_DRV_OWN_RETRY_COUNT; i++) {
+		mt76_wr(dev, MT_PCIE_DOORBELL_PUSH, MT_CFG_LPCR_HOST_DRV_OWN);
+		if (mt76_poll_msec(dev, MT_CONN_HIF_ON_LPCTL,
+				   MT_CFG_LPCR_HOST_FW_OWN, 0, 50))
+			break;
+	}
+
+	if (i == MT7615_DRV_OWN_RETRY_COUNT) {
+		dev_err(dev->mt76.dev, "driver own failed\n");
+		set_bit(MT76_STATE_PM, &mphy->state);
+		return -EIO;
+	}
+
+out:
+	dev->pm.last_activity = jiffies;
+
+	return 0;
+}
+
+static int mt7615_mcu_fw_pmctrl(struct mt7615_dev *dev)
+{
+	struct mt76_phy *mphy = &dev->mt76.phy;
+	int err = 0;
+	u32 addr;
+
+	if (test_and_set_bit(MT76_STATE_PM, &mphy->state))
+		return 0;
+
+	mt7622_trigger_hif_int(dev, true);
+
+	addr = is_mt7663(&dev->mt76) ? MT_CONN_HIF_ON_LPCTL : MT_CFG_LPCR_HOST;
+	mt76_wr(dev, addr, MT_CFG_LPCR_HOST_FW_OWN);
+
+	if (is_mt7622(&dev->mt76) &&
+	    !mt76_poll_msec(dev, addr, MT_CFG_LPCR_HOST_FW_OWN,
+			    MT_CFG_LPCR_HOST_FW_OWN, 3000)) {
+		dev_err(dev->mt76.dev, "Timeout for firmware own\n");
+		clear_bit(MT76_STATE_PM, &mphy->state);
+		err = -EIO;
+	}
+
+	mt7622_trigger_hif_int(dev, false);
+
+	return err;
+}
+
 static void
 mt7615_mcu_csa_finish(void *priv, u8 *mac, struct ieee80211_vif *vif)
 {
@@ -1106,7 +1197,7 @@ mt7615_mcu_wtbl_ht_tlv(struct sk_buff *skb, struct ieee80211_sta *sta,
 		tlv = mt7615_mcu_add_nested_tlv(skb, WTBL_HT, sizeof(*ht),
 						wtbl_tlv, sta_wtbl);
 		ht = (struct wtbl_ht *)tlv;
-		ht->ldpc = sta->ht_cap.cap & IEEE80211_HT_CAP_LDPC_CODING;
+		ht->ldpc = !!(sta->ht_cap.cap & IEEE80211_HT_CAP_LDPC_CODING);
 		ht->af = sta->ht_cap.ampdu_factor;
 		ht->mm = sta->ht_cap.ampdu_density;
 		ht->ht = 1;
@@ -1124,7 +1215,7 @@ mt7615_mcu_wtbl_ht_tlv(struct sk_buff *skb, struct ieee80211_sta *sta,
 		tlv = mt7615_mcu_add_nested_tlv(skb, WTBL_VHT, sizeof(*vht),
 						wtbl_tlv, sta_wtbl);
 		vht = (struct wtbl_vht *)tlv;
-		vht->ldpc = sta->vht_cap.cap & IEEE80211_VHT_CAP_RXLDPC,
+		vht->ldpc = !!(sta->vht_cap.cap & IEEE80211_VHT_CAP_RXLDPC);
 		vht->vht = 1;
 
 		af = (sta->vht_cap.cap &
@@ -1314,6 +1405,8 @@ static const struct mt7615_mcu_ops wtbl_update_ops = {
 	.add_tx_ba = mt7615_mcu_wtbl_tx_ba,
 	.add_rx_ba = mt7615_mcu_wtbl_rx_ba,
 	.sta_add = mt7615_mcu_wtbl_sta_add,
+	.set_drv_ctrl = mt7615_mcu_drv_pmctrl,
+	.set_fw_ctrl = mt7615_mcu_fw_pmctrl,
 };
 
 static int
@@ -1410,6 +1503,8 @@ static const struct mt7615_mcu_ops sta_update_ops = {
 	.add_tx_ba = mt7615_mcu_sta_tx_ba,
 	.add_rx_ba = mt7615_mcu_sta_rx_ba,
 	.sta_add = mt7615_mcu_add_sta,
+	.set_drv_ctrl = mt7615_mcu_drv_pmctrl,
+	.set_fw_ctrl = mt7615_mcu_fw_pmctrl,
 };
 
 static int
@@ -1823,6 +1918,8 @@ static const struct mt7615_mcu_ops uni_update_ops = {
 	.add_tx_ba = mt7615_mcu_uni_tx_ba,
 	.add_rx_ba = mt7615_mcu_uni_rx_ba,
 	.sta_add = mt7615_mcu_uni_add_sta,
+	.set_drv_ctrl = mt7615_mcu_lp_drv_pmctrl,
+	.set_fw_ctrl = mt7615_mcu_fw_pmctrl,
 };
 
 static int mt7615_mcu_send_firmware(struct mt7615_dev *dev, const void *data,
@@ -1895,81 +1992,6 @@ static int mt7615_mcu_start_patch(struct mt7615_dev *dev)
 				   &req, sizeof(req), true);
 }
 
-static void mt7622_trigger_hif_int(struct mt7615_dev *dev, bool en)
-{
-	if (!is_mt7622(&dev->mt76))
-		return;
-
-	regmap_update_bits(dev->infracfg, MT_INFRACFG_MISC,
-			   MT_INFRACFG_MISC_AP2CONN_WAKE,
-			   !en * MT_INFRACFG_MISC_AP2CONN_WAKE);
-}
-
-int mt7615_driver_own(struct mt7615_dev *dev)
-{
-	struct mt76_phy *mphy = &dev->mt76.phy;
-	struct mt76_dev *mdev = &dev->mt76;
-	int i;
-
-	if (!test_and_clear_bit(MT76_STATE_PM, &mphy->state))
-		goto out;
-
-	mt7622_trigger_hif_int(dev, true);
-
-	for (i = 0; i < MT7615_DRV_OWN_RETRY_COUNT; i++) {
-		u32 addr;
-
-		addr = is_mt7663(mdev) ? MT_PCIE_DOORBELL_PUSH : MT_CFG_LPCR_HOST;
-		mt76_wr(dev, addr, MT_CFG_LPCR_HOST_DRV_OWN);
-
-		addr = is_mt7663(mdev) ? MT_CONN_HIF_ON_LPCTL : MT_CFG_LPCR_HOST;
-		if (mt76_poll_msec(dev, addr, MT_CFG_LPCR_HOST_FW_OWN, 0, 50))
-			break;
-	}
-
-	mt7622_trigger_hif_int(dev, false);
-
-	if (i == MT7615_DRV_OWN_RETRY_COUNT) {
-		dev_err(mdev->dev, "driver own failed\n");
-		set_bit(MT76_STATE_PM, &mphy->state);
-		return -EIO;
-	}
-
-out:
-	dev->pm.last_activity = jiffies;
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(mt7615_driver_own);
-
-int mt7615_firmware_own(struct mt7615_dev *dev)
-{
-	struct mt76_phy *mphy = &dev->mt76.phy;
-	int err = 0;
-	u32 addr;
-
-	if (test_and_set_bit(MT76_STATE_PM, &mphy->state))
-		return 0;
-
-	mt7622_trigger_hif_int(dev, true);
-
-	addr = is_mt7663(&dev->mt76) ? MT_CONN_HIF_ON_LPCTL : MT_CFG_LPCR_HOST;
-	mt76_wr(dev, addr, MT_CFG_LPCR_HOST_FW_OWN);
-
-	if (is_mt7622(&dev->mt76) &&
-	    !mt76_poll_msec(dev, addr, MT_CFG_LPCR_HOST_FW_OWN,
-			    MT_CFG_LPCR_HOST_FW_OWN, 300)) {
-		dev_err(dev->mt76.dev, "Timeout for firmware own\n");
-		clear_bit(MT76_STATE_PM, &mphy->state);
-		err = -EIO;
-	}
-
-	mt7622_trigger_hif_int(dev, false);
-
-	return err;
-}
-EXPORT_SYMBOL_GPL(mt7615_firmware_own);
-
 static int mt7615_load_patch(struct mt7615_dev *dev, u32 addr, const char *name)
 {
 	const struct mt7615_patch_hdr *hdr;
@@ -2128,7 +2150,8 @@ static int mt7615_load_n9(struct mt7615_dev *dev, const char *name)
 		 sizeof(dev->mt76.hw->wiphy->fw_version),
 		 "%.10s-%.15s", hdr->fw_ver, hdr->build_date);
 
-	if (!strncmp(hdr->fw_ver, "2.0", sizeof(hdr->fw_ver))) {
+	if (!is_mt7615(&dev->mt76) &&
+	    !strncmp(hdr->fw_ver, "2.0", sizeof(hdr->fw_ver))) {
 		dev->fw_ver = MT7615_FIRMWARE_V2;
 		dev->mcu_ops = &sta_update_ops;
 	} else {
@@ -2451,7 +2474,7 @@ int mt7615_mcu_init(struct mt7615_dev *dev)
 
 	dev->mt76.mcu_ops = &mt7615_mcu_ops,
 
-	ret = mt7615_driver_own(dev);
+	ret = mt7615_mcu_drv_pmctrl(dev);
 	if (ret)
 		return ret;
 
@@ -2481,7 +2504,7 @@ EXPORT_SYMBOL_GPL(mt7615_mcu_init);
 void mt7615_mcu_exit(struct mt7615_dev *dev)
 {
 	__mt76_mcu_restart(&dev->mt76);
-	mt7615_firmware_own(dev);
+	mt7615_mcu_set_fw_ctrl(dev);
 	skb_queue_purge(&dev->mt76.mcu.res_q);
 }
 EXPORT_SYMBOL_GPL(mt7615_mcu_exit);
@@ -2846,14 +2869,6 @@ int mt7615_mcu_set_chan_info(struct mt7615_phy *phy, int cmd)
 		.center_chan2 = ieee80211_frequency_to_channel(freq2),
 	};
 
-#ifdef CONFIG_NL80211_TESTMODE
-	if (dev->mt76.test.state == MT76_TM_STATE_TX_FRAMES &&
-	    dev->mt76.test.tx_antenna_mask) {
-		req.tx_streams = hweight8(dev->mt76.test.tx_antenna_mask);
-		req.rx_streams_mask = dev->mt76.test.tx_antenna_mask;
-	}
-#endif
-
 	if (dev->mt76.hw->conf.flags & IEEE80211_CONF_OFFCHANNEL)
 		req.switch_reason = CH_SWITCH_SCAN_BYPASS_DPD;
 	else if ((chandef->chan->flags & IEEE80211_CHAN_RADAR) &&
@@ -3278,7 +3293,7 @@ static int mt7615_dcoc_freq_idx(u16 freq, u8 bw)
 			freq = freq_bw40[idx];
 			break;
 		}
-		/* fall through */
+		fallthrough;
 	case NL80211_CHAN_WIDTH_40:
 		idx = mt7615_find_freq_idx(freq_bw40, ARRAY_SIZE(freq_bw40),
 					   freq);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mmio.c b/drivers/net/wireless/mediatek/mt76/mt7615/mmio.c
index 133f93a6ed1b..6de492a4cf02 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/mmio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/mmio.c
@@ -101,30 +101,29 @@ static irqreturn_t mt7615_irq_handler(int irq, void *dev_instance)
 static void mt7615_irq_tasklet(unsigned long data)
 {
 	struct mt7615_dev *dev = (struct mt7615_dev *)data;
-	u32 intr, mask = 0;
+	u32 intr, mask = 0, tx_mcu_mask = mt7615_tx_mcu_int_mask(dev);
 
 	mt76_wr(dev, MT_INT_MASK_CSR, 0);
 
 	intr = mt76_rr(dev, MT_INT_SOURCE_CSR);
+	intr &= dev->mt76.mmio.irqmask;
 	mt76_wr(dev, MT_INT_SOURCE_CSR, intr);
 
 	trace_dev_irq(&dev->mt76, intr, dev->mt76.mmio.irqmask);
-	intr &= dev->mt76.mmio.irqmask;
 
-	if (intr & MT_INT_TX_DONE_ALL) {
-		mask |= MT_INT_TX_DONE_ALL;
+	mask |= intr & MT_INT_RX_DONE_ALL;
+	if (intr & tx_mcu_mask)
+		mask |= tx_mcu_mask;
+	mt76_set_irq_mask(&dev->mt76, MT_INT_MASK_CSR, mask, 0);
+
+	if (intr & tx_mcu_mask)
 		napi_schedule(&dev->mt76.tx_napi);
-	}
 
-	if (intr & MT_INT_RX_DONE(0)) {
-		mask |= MT_INT_RX_DONE(0);
+	if (intr & MT_INT_RX_DONE(0))
 		napi_schedule(&dev->mt76.napi[0]);
-	}
 
-	if (intr & MT_INT_RX_DONE(1)) {
-		mask |= MT_INT_RX_DONE(1);
+	if (intr & MT_INT_RX_DONE(1))
 		napi_schedule(&dev->mt76.napi[1]);
-	}
 
 	if (intr & MT_INT_MCU_CMD) {
 		u32 val = mt76_rr(dev, MT_MCU_CMD);
@@ -135,8 +134,6 @@ static void mt7615_irq_tasklet(unsigned long data)
 			wake_up(&dev->reset_wait);
 		}
 	}
-
-	mt76_set_irq_mask(&dev->mt76, MT_INT_MASK_CSR, mask, 0);
 }
 
 static u32 __mt7615_reg_addr(struct mt7615_dev *dev, u32 addr)
@@ -227,6 +224,8 @@ int mt7615_mmio_probe(struct device *pdev, void __iomem *mem_base,
 	bus_ops->rmw = mt7615_rmw;
 	dev->mt76.bus = bus_ops;
 
+	mt76_wr(dev, MT_INT_MASK_CSR, 0);
+
 	ret = devm_request_irq(mdev->dev, irq, mt7615_irq_handler,
 			       IRQF_SHARED, KBUILD_MODNAME, dev);
 	if (ret)
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mt7615.h b/drivers/net/wireless/mediatek/mt76/mt7615/mt7615.h
index 571eadc033a3..6a9f9187f76a 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/mt7615.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/mt7615.h
@@ -220,6 +220,8 @@ struct mt7615_phy {
 #define mt7615_mcu_add_bss_info(phy, ...) (phy->dev)->mcu_ops->add_bss_info((phy),  __VA_ARGS__)
 #define mt7615_mcu_add_beacon(dev, ...)	(dev)->mcu_ops->add_beacon_offload((dev),  __VA_ARGS__)
 #define mt7615_mcu_set_pm(dev, ...)	(dev)->mcu_ops->set_pm_state((dev),  __VA_ARGS__)
+#define mt7615_mcu_set_drv_ctrl(dev)	(dev)->mcu_ops->set_drv_ctrl((dev))
+#define mt7615_mcu_set_fw_ctrl(dev)	(dev)->mcu_ops->set_fw_ctrl((dev))
 struct mt7615_mcu_ops {
 	int (*add_tx_ba)(struct mt7615_dev *dev,
 			 struct ieee80211_ampdu_params *params,
@@ -238,6 +240,8 @@ struct mt7615_mcu_ops {
 				  struct ieee80211_hw *hw,
 				  struct ieee80211_vif *vif, bool enable);
 	int (*set_pm_state)(struct mt7615_dev *dev, int band, int state);
+	int (*set_drv_ctrl)(struct mt7615_dev *dev);
+	int (*set_fw_ctrl)(struct mt7615_dev *dev);
 };
 
 struct mt7615_dev {
@@ -278,6 +282,7 @@ struct mt7615_dev {
 
 	bool fw_debug;
 	bool flash_eeprom;
+	bool dbdc_support;
 
 	spinlock_t token_lock;
 	struct idr token;
@@ -535,6 +540,11 @@ static inline u8 mt7615_lmac_mapping(struct mt7615_dev *dev, u8 ac)
 	return lmac_queue_map[ac];
 }
 
+static inline u32 mt7615_tx_mcu_int_mask(struct mt7615_dev *dev)
+{
+	return MT_INT_TX_DONE(dev->mt76.q_tx[MT_TXQ_MCU]->hw_idx);
+}
+
 void mt7615_dma_reset(struct mt7615_dev *dev);
 void mt7615_scan_work(struct work_struct *work);
 void mt7615_roc_work(struct work_struct *work);
@@ -608,8 +618,7 @@ int mt7615_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr,
 			  struct ieee80211_sta *sta,
 			  struct mt76_tx_info *tx_info);
 
-void mt7615_tx_complete_skb(struct mt76_dev *mdev, enum mt76_txq_id qid,
-			    struct mt76_queue_entry *e);
+void mt7615_tx_complete_skb(struct mt76_dev *mdev, struct mt76_queue_entry *e);
 
 void mt7615_queue_rx_skb(struct mt76_dev *mdev, enum mt76_rxq_id q,
 			 struct sk_buff *skb);
@@ -638,8 +647,6 @@ int mt7615_mcu_set_p2p_oppps(struct ieee80211_hw *hw,
 			     struct ieee80211_vif *vif);
 int mt7615_mcu_set_roc(struct mt7615_phy *phy, struct ieee80211_vif *vif,
 		       struct ieee80211_channel *chan, int duration);
-int mt7615_firmware_own(struct mt7615_dev *dev);
-int mt7615_driver_own(struct mt7615_dev *dev);
 
 int mt7615_init_debugfs(struct mt7615_dev *dev);
 int mt7615_mcu_wait_response(struct mt7615_dev *dev, int cmd, int seq);
@@ -666,7 +673,6 @@ int mt7663_usb_sdio_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr,
 				   struct mt76_tx_info *tx_info);
 bool mt7663_usb_sdio_tx_status_data(struct mt76_dev *mdev, u8 *update);
 void mt7663_usb_sdio_tx_complete_skb(struct mt76_dev *mdev,
-				     enum mt76_txq_id qid,
 				     struct mt76_queue_entry *e);
 void mt7663_usb_sdio_wtbl_work(struct work_struct *work);
 int mt7663_usb_sdio_register_device(struct mt7615_dev *dev);
@@ -675,9 +681,8 @@ int mt7663u_mcu_init(struct mt7615_dev *dev);
 /* sdio */
 u32 mt7663s_read_pcr(struct mt7615_dev *dev);
 int mt7663s_mcu_init(struct mt7615_dev *dev);
-int mt7663s_driver_own(struct mt7615_dev *dev);
-int mt7663s_firmware_own(struct mt7615_dev *dev);
-int mt7663s_kthread_run(void *data);
+void mt7663s_tx_work(struct work_struct *work);
+void mt7663s_rx_work(struct work_struct *work);
 void mt7663s_sdio_irq(struct sdio_func *func);
 
 #endif
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/pci.c b/drivers/net/wireless/mediatek/mt76/mt7615/pci.c
index 2328d78e06a1..dbd29d897b29 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/pci.c
@@ -88,7 +88,7 @@ static int mt7615_pci_suspend(struct pci_dev *pdev, pm_message_t state)
 	}
 
 	napi_disable(&mdev->tx_napi);
-	tasklet_kill(&mdev->tx_tasklet);
+	mt76_worker_disable(&mdev->tx_worker);
 
 	mt76_for_each_q_rx(mdev, i) {
 		napi_disable(&mdev->napi[i]);
@@ -118,7 +118,7 @@ static int mt7615_pci_suspend(struct pci_dev *pdev, pm_message_t state)
 	if (err)
 		goto restore;
 
-	err = mt7615_firmware_own(dev);
+	err = mt7615_mcu_set_fw_ctrl(dev);
 	if (err)
 		goto restore;
 
@@ -142,7 +142,7 @@ static int mt7615_pci_resume(struct pci_dev *pdev)
 	bool pdma_reset;
 	int i, err;
 
-	err = mt7615_driver_own(dev);
+	err = mt7615_mcu_set_drv_ctrl(dev);
 	if (err < 0)
 		return err;
 
@@ -162,6 +162,7 @@ static int mt7615_pci_resume(struct pci_dev *pdev)
 	if (pdma_reset)
 		dev_err(mdev->dev, "PDMA engine must be reinitialized\n");
 
+	mt76_worker_enable(&mdev->tx_worker);
 	mt76_for_each_q_rx(mdev, i) {
 		napi_enable(&mdev->napi[i]);
 		napi_schedule(&mdev->napi[i]);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/pci_init.c b/drivers/net/wireless/mediatek/mt76/mt7615/pci_init.c
index 7224a0078211..06a0f8f7bc89 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/pci_init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/pci_init.c
@@ -25,6 +25,9 @@ static void mt7615_init_work(struct work_struct *work)
 	mt7615_phy_init(dev);
 	mt7615_mcu_del_wtbl_all(dev);
 	mt7615_check_offload_capability(dev);
+
+	if (dev->dbdc_support)
+		mt7615_register_ext_phy(dev);
 }
 
 static int mt7615_init_hardware(struct mt7615_dev *dev)
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/pci_mac.c b/drivers/net/wireless/mediatek/mt76/mt7615/pci_mac.c
index 2d67f9a148cd..4cf7c5d34325 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/pci_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/pci_mac.c
@@ -14,8 +14,7 @@
 #include "../dma.h"
 #include "mac.h"
 
-void mt7615_tx_complete_skb(struct mt76_dev *mdev, enum mt76_txq_id qid,
-			    struct mt76_queue_entry *e)
+void mt7615_tx_complete_skb(struct mt76_dev *mdev, struct mt76_queue_entry *e)
 {
 	if (!e->txwi) {
 		dev_kfree_skb_any(e->skb);
@@ -45,7 +44,7 @@ void mt7615_tx_complete_skb(struct mt76_dev *mdev, enum mt76_txq_id qid,
 	}
 
 	if (e->skb)
-		mt76_tx_complete_skb(mdev, e->skb);
+		mt76_tx_complete_skb(mdev, e->wcid, e->skb);
 }
 
 static void
@@ -107,6 +106,7 @@ mt7615_write_fw_txp(struct mt7615_dev *dev, struct mt76_tx_info *tx_info,
 	/* pass partial skb header to fw */
 	tx_info->buf[0].len = MT_TXD_SIZE + sizeof(*txp);
 	tx_info->buf[1].len = MT_CT_PARSE_LEN;
+	tx_info->buf[1].skip_unmap = true;
 	tx_info->nbuf = MT_CT_DMA_BUF_NUM;
 
 	txp->flags = cpu_to_le16(MT_CT_INFO_APPLY_TXD);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/regs.h b/drivers/net/wireless/mediatek/mt76/mt7615/regs.h
index 9137d9e6b51d..61623f480806 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/regs.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/regs.h
@@ -575,7 +575,7 @@ enum mt7615_reg_base {
 #define MT_MCU_PTA_BASE			0x81060000
 #define MT_MCU_PTA(_n)			(MT_MCU_PTA_BASE + (_n))
 
-#define MT_ANT_SWITCH_CON(n)		MT_MCU_PTA(0x0c8)
+#define MT_ANT_SWITCH_CON(_n)		MT_MCU_PTA(0x0c8 + ((_n) - 1) * 4)
 #define MT_ANT_SWITCH_CON_MODE(_n)	(GENMASK(4, 0) << (_n * 8))
 #define MT_ANT_SWITCH_CON_MODE1(_n)	(GENMASK(3, 0) << (_n * 8))
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/sdio.c b/drivers/net/wireless/mediatek/mt76/mt7615/sdio.c
index dabce51117b0..874c929d8552 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/sdio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/sdio.c
@@ -323,7 +323,7 @@ static int mt7663s_probe(struct sdio_func *func,
 {
 	static const struct mt76_driver_ops drv_ops = {
 		.txwi_size = MT_USB_TXD_SIZE,
-		.drv_flags = MT_DRV_RX_DMA_HDR | MT_DRV_HW_MGMT_TXQ,
+		.drv_flags = MT_DRV_RX_DMA_HDR,
 		.tx_prepare_skb = mt7663_usb_sdio_tx_prepare_skb,
 		.tx_complete_skb = mt7663_usb_sdio_tx_complete_skb,
 		.tx_status_data = mt7663_usb_sdio_tx_status_data,
@@ -346,7 +346,7 @@ static int mt7663s_probe(struct sdio_func *func,
 	struct ieee80211_ops *ops;
 	struct mt7615_dev *dev;
 	struct mt76_dev *mdev;
-	int ret;
+	int i, ret;
 
 	ops = devm_kmemdup(&func->dev, &mt7615_ops, sizeof(mt7615_ops),
 			   GFP_KERNEL);
@@ -364,23 +364,39 @@ static int mt7663s_probe(struct sdio_func *func,
 	dev->ops = ops;
 	sdio_set_drvdata(func, dev);
 
-	mdev->sdio.tx_kthread = kthread_create(mt7663s_kthread_run, dev,
-					       "mt7663s_tx");
-	if (IS_ERR(mdev->sdio.tx_kthread))
-		return PTR_ERR(mdev->sdio.tx_kthread);
-
 	ret = mt76s_init(mdev, func, &mt7663s_ops);
 	if (ret < 0)
 		goto err_free;
 
+	INIT_WORK(&mdev->sdio.tx.xmit_work, mt7663s_tx_work);
+	INIT_WORK(&mdev->sdio.rx.recv_work, mt7663s_rx_work);
+
 	ret = mt7663s_hw_init(dev, func);
 	if (ret)
-		goto err_free;
+		goto err_deinit;
 
 	mdev->rev = (mt76_rr(dev, MT_HW_CHIPID) << 16) |
 		    (mt76_rr(dev, MT_HW_REV) & 0xff);
 	dev_dbg(mdev->dev, "ASIC revision: %04x\n", mdev->rev);
 
+	mdev->sdio.intr_data = devm_kmalloc(mdev->dev,
+					    sizeof(struct mt76s_intr),
+					    GFP_KERNEL);
+	if (!mdev->sdio.intr_data) {
+		ret = -ENOMEM;
+		goto err_deinit;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(mdev->sdio.xmit_buf); i++) {
+		mdev->sdio.xmit_buf[i] = devm_kmalloc(mdev->dev,
+						      MT76S_XMIT_BUF_SZ,
+						      GFP_KERNEL);
+		if (!mdev->sdio.xmit_buf[i]) {
+			ret = -ENOMEM;
+			goto err_deinit;
+		}
+	}
+
 	ret = mt76s_alloc_queues(&dev->mt76);
 	if (ret)
 		goto err_deinit;
@@ -426,9 +442,11 @@ static int mt7663s_suspend(struct device *dev)
 			return err;
 	}
 
+	sdio_set_host_pm_flags(func, MMC_PM_KEEP_POWER);
+
 	mt76s_stop_txrx(&mdev->mt76);
 
-	return mt7663s_firmware_own(mdev);
+	return mt7615_mcu_set_fw_ctrl(mdev);
 }
 
 static int mt7663s_resume(struct device *dev)
@@ -437,7 +455,7 @@ static int mt7663s_resume(struct device *dev)
 	struct mt7615_dev *mdev = sdio_get_drvdata(func);
 	int err;
 
-	err = mt7663s_driver_own(mdev);
+	err = mt7615_mcu_set_drv_ctrl(mdev);
 	if (err)
 		return err;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/sdio_mcu.c b/drivers/net/wireless/mediatek/mt76/mt7615/sdio_mcu.c
index 28b86bec7fc2..38670c00380c 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/sdio_mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/sdio_mcu.c
@@ -53,7 +53,7 @@ mt7663s_mcu_send_message(struct mt76_dev *mdev, struct sk_buff *skb,
 	if (ret)
 		goto out;
 
-	mt76_queue_kick(dev, mdev->q_tx[MT_TXQ_MCU].q);
+	mt76_queue_kick(dev, mdev->q_tx[MT_TXQ_MCU]);
 	if (wait_resp)
 		ret = mt7615_mcu_wait_response(dev, cmd, seq);
 
@@ -63,7 +63,7 @@ out:
 	return ret;
 }
 
-int mt7663s_driver_own(struct mt7615_dev *dev)
+static int mt7663s_mcu_drv_pmctrl(struct mt7615_dev *dev)
 {
 	struct sdio_func *func = dev->mt76.sdio.func;
 	struct mt76_phy *mphy = &dev->mt76.phy;
@@ -75,7 +75,7 @@ int mt7663s_driver_own(struct mt7615_dev *dev)
 
 	sdio_claim_host(func);
 
-	sdio_writel(func, WHLPCR_FW_OWN_REQ_CLR, MCR_WHLPCR, 0);
+	sdio_writel(func, WHLPCR_FW_OWN_REQ_CLR, MCR_WHLPCR, NULL);
 
 	ret = readx_poll_timeout(mt7663s_read_pcr, dev, status,
 				 status & WHLPCR_IS_DRIVER_OWN, 2000, 1000000);
@@ -95,7 +95,7 @@ out:
 	return 0;
 }
 
-int mt7663s_firmware_own(struct mt7615_dev *dev)
+static int mt7663s_mcu_fw_pmctrl(struct mt7615_dev *dev)
 {
 	struct sdio_func *func = dev->mt76.sdio.func;
 	struct mt76_phy *mphy = &dev->mt76.phy;
@@ -107,7 +107,7 @@ int mt7663s_firmware_own(struct mt7615_dev *dev)
 
 	sdio_claim_host(func);
 
-	sdio_writel(func, WHLPCR_FW_OWN_REQ_SET, MCR_WHLPCR, 0);
+	sdio_writel(func, WHLPCR_FW_OWN_REQ_SET, MCR_WHLPCR, NULL);
 
 	ret = readx_poll_timeout(mt7663s_read_pcr, dev, status,
 				 !(status & WHLPCR_IS_DRIVER_OWN), 2000, 1000000);
@@ -132,9 +132,10 @@ int mt7663s_mcu_init(struct mt7615_dev *dev)
 		.mcu_rr = mt7615_mcu_reg_rr,
 		.mcu_wr = mt7615_mcu_reg_wr,
 	};
+	struct mt7615_mcu_ops *mcu_ops;
 	int ret;
 
-	ret = mt7663s_driver_own(dev);
+	ret = mt7663s_mcu_drv_pmctrl(dev);
 	if (ret)
 		return ret;
 
@@ -152,6 +153,15 @@ int mt7663s_mcu_init(struct mt7615_dev *dev)
 	if (ret)
 		return ret;
 
+	mcu_ops = devm_kmemdup(dev->mt76.dev, dev->mcu_ops, sizeof(*mcu_ops),
+			       GFP_KERNEL);
+	if (!mcu_ops)
+		return -ENOMEM;
+
+	mcu_ops->set_drv_ctrl = mt7663s_mcu_drv_pmctrl;
+	mcu_ops->set_fw_ctrl = mt7663s_mcu_fw_pmctrl;
+	dev->mcu_ops = mcu_ops;
+
 	ret = mt7663s_mcu_init_sched(dev);
 	if (ret)
 		return ret;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/sdio_txrx.c b/drivers/net/wireless/mediatek/mt76/mt7615/sdio_txrx.c
index 443a4ecdad3a..2486cda3243b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/sdio_txrx.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/sdio_txrx.c
@@ -19,21 +19,40 @@
 #include "sdio.h"
 #include "mac.h"
 
-static void mt7663s_refill_sched_quota(struct mt7615_dev *dev, u32 *data)
+static int mt7663s_refill_sched_quota(struct mt76_dev *dev, u32 *data)
 {
-	struct mt76_sdio *sdio = &dev->mt76.sdio;
+	u32 ple_ac_data_quota[] = {
+		FIELD_GET(TXQ_CNT_L, data[4]), /* VO */
+		FIELD_GET(TXQ_CNT_H, data[3]), /* VI */
+		FIELD_GET(TXQ_CNT_L, data[3]), /* BE */
+		FIELD_GET(TXQ_CNT_H, data[2]), /* BK */
+	};
+	u32 pse_ac_data_quota[] = {
+		FIELD_GET(TXQ_CNT_H, data[1]), /* VO */
+		FIELD_GET(TXQ_CNT_L, data[1]), /* VI */
+		FIELD_GET(TXQ_CNT_H, data[0]), /* BE */
+		FIELD_GET(TXQ_CNT_L, data[0]), /* BK */
+	};
+	u32 pse_mcu_quota = FIELD_GET(TXQ_CNT_L, data[2]);
+	u32 pse_data_quota = 0, ple_data_quota = 0;
+	struct mt76_sdio *sdio = &dev->sdio;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(pse_ac_data_quota); i++) {
+		pse_data_quota += pse_ac_data_quota[i];
+		ple_data_quota += ple_ac_data_quota[i];
+	}
+
+	if (!pse_data_quota && !ple_data_quota && !pse_mcu_quota)
+		return 0;
 
 	mutex_lock(&sdio->sched.lock);
-	sdio->sched.pse_data_quota += FIELD_GET(TXQ_CNT_L, data[0]) + /* BK */
-				      FIELD_GET(TXQ_CNT_H, data[0]) + /* BE */
-				      FIELD_GET(TXQ_CNT_L, data[1]) + /* VI */
-				      FIELD_GET(TXQ_CNT_H, data[1]);  /* VO */
-	sdio->sched.ple_data_quota += FIELD_GET(TXQ_CNT_H, data[2]) + /* BK */
-				      FIELD_GET(TXQ_CNT_L, data[3]) + /* BE */
-				      FIELD_GET(TXQ_CNT_H, data[3]) + /* VI */
-				      FIELD_GET(TXQ_CNT_L, data[4]);  /* VO */
-	sdio->sched.pse_mcu_quota += FIELD_GET(TXQ_CNT_L, data[2]);
+	sdio->sched.pse_mcu_quota += pse_mcu_quota;
+	sdio->sched.pse_data_quota += pse_data_quota;
+	sdio->sched.ple_data_quota += ple_data_quota;
 	mutex_unlock(&sdio->sched.lock);
+
+	return pse_data_quota + ple_data_quota + pse_mcu_quota;
 }
 
 static struct sk_buff *mt7663s_build_rx_skb(void *data, int data_len,
@@ -61,11 +80,11 @@ static struct sk_buff *mt7663s_build_rx_skb(void *data, int data_len,
 	return skb;
 }
 
-static int mt7663s_rx_run_queue(struct mt7615_dev *dev, enum mt76_rxq_id qid,
+static int mt7663s_rx_run_queue(struct mt76_dev *dev, enum mt76_rxq_id qid,
 				struct mt76s_intr *intr)
 {
-	struct mt76_queue *q = &dev->mt76.q_rx[qid];
-	struct mt76_sdio *sdio = &dev->mt76.sdio;
+	struct mt76_queue *q = &dev->q_rx[qid];
+	struct mt76_sdio *sdio = &dev->sdio;
 	int len = 0, err, i, order;
 	struct page *page;
 	u8 *buf;
@@ -86,15 +105,18 @@ static int mt7663s_rx_run_queue(struct mt7615_dev *dev, enum mt76_rxq_id qid,
 
 	buf = page_address(page);
 
+	sdio_claim_host(sdio->func);
 	err = sdio_readsb(sdio->func, buf, MCR_WRDR(qid), len);
+	sdio_release_host(sdio->func);
+
 	if (err < 0) {
-		dev_err(dev->mt76.dev, "sdio read data failed:%d\n", err);
+		dev_err(dev->dev, "sdio read data failed:%d\n", err);
 		__free_pages(page, order);
 		return err;
 	}
 
 	for (i = 0; i < intr->rx.num[qid]; i++) {
-		int index = (q->tail + i) % q->ndesc;
+		int index = (q->head + i) % q->ndesc;
 		struct mt76_queue_entry *e = &q->entry[index];
 
 		len = intr->rx.len[qid][i];
@@ -109,160 +131,198 @@ static int mt7663s_rx_run_queue(struct mt7615_dev *dev, enum mt76_rxq_id qid,
 	__free_pages(page, order);
 
 	spin_lock_bh(&q->lock);
-	q->tail = (q->tail + i) % q->ndesc;
+	q->head = (q->head + i) % q->ndesc;
 	q->queued += i;
 	spin_unlock_bh(&q->lock);
 
-	return err;
+	return i;
 }
 
-static int mt7663s_tx_update_sched(struct mt7615_dev *dev,
-				   struct mt76_queue_entry *e,
-				   bool mcu)
+static int mt7663s_tx_pick_quota(struct mt76_sdio *sdio, enum mt76_txq_id qid,
+				 int buf_sz, int *pse_size, int *ple_size)
 {
-	struct mt76_sdio *sdio = &dev->mt76.sdio;
-	struct mt76_phy *mphy = &dev->mt76.phy;
-	struct ieee80211_hdr *hdr;
-	int size, ret = -EBUSY;
-
-	size = DIV_ROUND_UP(e->buf_sz + sdio->sched.deficit, MT_PSE_PAGE_SZ);
+	int pse_sz;
 
-	if (mcu) {
-		if (!test_bit(MT76_STATE_MCU_RUNNING, &mphy->state))
-			return 0;
+	pse_sz = DIV_ROUND_UP(buf_sz + sdio->sched.deficit, MT_PSE_PAGE_SZ);
 
-		mutex_lock(&sdio->sched.lock);
-		if (sdio->sched.pse_mcu_quota > size) {
-			sdio->sched.pse_mcu_quota -= size;
-			ret = 0;
-		}
-		mutex_unlock(&sdio->sched.lock);
+	if (qid == MT_TXQ_MCU) {
+		if (sdio->sched.pse_mcu_quota < *pse_size + pse_sz)
+			return -EBUSY;
+	} else {
+		if (sdio->sched.pse_data_quota < *pse_size + pse_sz ||
+		    sdio->sched.ple_data_quota < *ple_size)
+			return -EBUSY;
 
-		return ret;
+		*ple_size = *ple_size + 1;
 	}
+	*pse_size = *pse_size + pse_sz;
 
-	hdr = (struct ieee80211_hdr *)(e->skb->data + MT_USB_TXD_SIZE);
-	if (ieee80211_is_ctl(hdr->frame_control))
-		return 0;
+	return 0;
+}
 
+static void mt7663s_tx_update_quota(struct mt76_sdio *sdio, enum mt76_txq_id qid,
+				    int pse_size, int ple_size)
+{
 	mutex_lock(&sdio->sched.lock);
-	if (sdio->sched.pse_data_quota > size &&
-	    sdio->sched.ple_data_quota > 0) {
-		sdio->sched.pse_data_quota -= size;
-		sdio->sched.ple_data_quota--;
-		ret = 0;
+	if (qid == MT_TXQ_MCU) {
+		sdio->sched.pse_mcu_quota -= pse_size;
+	} else {
+		sdio->sched.pse_data_quota -= pse_size;
+		sdio->sched.ple_data_quota -= ple_size;
 	}
 	mutex_unlock(&sdio->sched.lock);
+}
+
+static int __mt7663s_xmit_queue(struct mt76_dev *dev, u8 *data, int len)
+{
+	struct mt76_sdio *sdio = &dev->sdio;
+	int err;
+
+	if (len > sdio->func->cur_blksize)
+		len = roundup(len, sdio->func->cur_blksize);
+
+	sdio_claim_host(sdio->func);
+	err = sdio_writesb(sdio->func, MCR_WTDR1, data, len);
+	sdio_release_host(sdio->func);
+
+	if (err)
+		dev_err(dev->dev, "sdio write failed: %d\n", err);
 
-	return ret;
+	return err;
 }
 
-static int mt7663s_tx_run_queue(struct mt7615_dev *dev, struct mt76_queue *q)
+static int mt7663s_tx_run_queue(struct mt76_dev *dev, enum mt76_txq_id qid)
 {
-	bool mcu = q == dev->mt76.q_tx[MT_TXQ_MCU].q;
-	struct mt76_sdio *sdio = &dev->mt76.sdio;
-	int nframes = 0;
+	int err, nframes = 0, len = 0, pse_sz = 0, ple_sz = 0;
+	struct mt76_queue *q = dev->q_tx[qid];
+	struct mt76_sdio *sdio = &dev->sdio;
 
-	while (q->first != q->tail) {
+	while (q->first != q->head) {
 		struct mt76_queue_entry *e = &q->entry[q->first];
-		int err, len = e->skb->len;
+		struct sk_buff *iter;
 
-		if (mt7663s_tx_update_sched(dev, e, mcu))
+		if (!test_bit(MT76_STATE_MCU_RUNNING, &dev->phy.state)) {
+			__skb_put_zero(e->skb, 4);
+			err = __mt7663s_xmit_queue(dev, e->skb->data,
+						   e->skb->len);
+			if (err)
+				return err;
+
+			goto next;
+		}
+
+		if (len + e->skb->len + 4 > MT76S_XMIT_BUF_SZ)
 			break;
 
-		if (len > sdio->func->cur_blksize)
-			len = roundup(len, sdio->func->cur_blksize);
+		if (mt7663s_tx_pick_quota(sdio, qid, e->buf_sz, &pse_sz,
+					  &ple_sz))
+			break;
 
-		/* TODO: skb_walk_frags and then write to SDIO port */
-		err = sdio_writesb(sdio->func, MCR_WTDR1, e->skb->data, len);
-		if (err) {
-			dev_err(dev->mt76.dev, "sdio write failed: %d\n", err);
-			return -EIO;
-		}
+		memcpy(sdio->xmit_buf[qid] + len, e->skb->data,
+		       skb_headlen(e->skb));
+		len += skb_headlen(e->skb);
+		nframes++;
 
-		e->done = true;
+		skb_walk_frags(e->skb, iter) {
+			memcpy(sdio->xmit_buf[qid] + len, iter->data,
+			       iter->len);
+			len += iter->len;
+			nframes++;
+		}
+next:
 		q->first = (q->first + 1) % q->ndesc;
-		nframes++;
+		e->done = true;
+	}
+
+	if (nframes) {
+		memset(sdio->xmit_buf[qid] + len, 0, 4);
+		err = __mt7663s_xmit_queue(dev, sdio->xmit_buf[qid], len + 4);
+		if (err)
+			return err;
 	}
+	mt7663s_tx_update_quota(sdio, qid, pse_sz, ple_sz);
 
 	return nframes;
 }
 
-static int mt7663s_tx_run_queues(struct mt7615_dev *dev)
+void mt7663s_tx_work(struct work_struct *work)
 {
+	struct mt76_sdio *sdio = container_of(work, struct mt76_sdio,
+					      tx.xmit_work);
+	struct mt76_dev *dev = container_of(sdio, struct mt76_dev, sdio);
 	int i, nframes = 0;
 
 	for (i = 0; i < MT_TXQ_MCU_WA; i++) {
 		int ret;
 
-		ret = mt7663s_tx_run_queue(dev, dev->mt76.q_tx[i].q);
+		ret = mt7663s_tx_run_queue(dev, i);
 		if (ret < 0)
-			return ret;
+			break;
 
 		nframes += ret;
 	}
+	if (nframes)
+		queue_work(sdio->txrx_wq, &sdio->tx.xmit_work);
 
-	return nframes;
+	queue_work(sdio->txrx_wq, &sdio->tx.status_work);
 }
 
-int mt7663s_kthread_run(void *data)
+void mt7663s_rx_work(struct work_struct *work)
 {
-	struct mt7615_dev *dev = data;
-	struct mt76_phy *mphy = &dev->mt76.phy;
+	struct mt76_sdio *sdio = container_of(work, struct mt76_sdio,
+					      rx.recv_work);
+	struct mt76_dev *dev = container_of(sdio, struct mt76_dev, sdio);
+	struct mt76s_intr *intr = sdio->intr_data;
+	int nframes = 0, ret;
 
-	while (!kthread_should_stop()) {
-		int ret;
+	/* disable interrupt */
+	sdio_claim_host(sdio->func);
+	sdio_writel(sdio->func, WHLPCR_INT_EN_CLR, MCR_WHLPCR, NULL);
+	ret = sdio_readsb(sdio->func, intr, MCR_WHISR, sizeof(*intr));
+	sdio_release_host(sdio->func);
 
-		cond_resched();
+	if (ret < 0)
+		goto out;
 
-		sdio_claim_host(dev->mt76.sdio.func);
-		ret = mt7663s_tx_run_queues(dev);
-		sdio_release_host(dev->mt76.sdio.func);
+	trace_dev_irq(dev, intr->isr, 0);
 
-		if (ret <= 0 || !test_bit(MT76_STATE_RUNNING, &mphy->state)) {
-			set_current_state(TASK_INTERRUPTIBLE);
-			schedule();
-		} else {
-			wake_up_process(dev->mt76.sdio.kthread);
+	if (intr->isr & WHIER_RX0_DONE_INT_EN) {
+		ret = mt7663s_rx_run_queue(dev, 0, intr);
+		if (ret > 0) {
+			queue_work(sdio->txrx_wq, &sdio->rx.net_work);
+			nframes += ret;
 		}
 	}
 
-	return 0;
+	if (intr->isr & WHIER_RX1_DONE_INT_EN) {
+		ret = mt7663s_rx_run_queue(dev, 1, intr);
+		if (ret > 0) {
+			queue_work(sdio->txrx_wq, &sdio->rx.net_work);
+			nframes += ret;
+		}
+	}
+
+	if (mt7663s_refill_sched_quota(dev, intr->tx.wtqcr))
+		queue_work(sdio->txrx_wq, &sdio->tx.xmit_work);
+
+	if (nframes) {
+		queue_work(sdio->txrx_wq, &sdio->rx.recv_work);
+		return;
+	}
+out:
+	/* enable interrupt */
+	sdio_claim_host(sdio->func);
+	sdio_writel(sdio->func, WHLPCR_INT_EN_SET, MCR_WHLPCR, NULL);
+	sdio_release_host(sdio->func);
 }
 
 void mt7663s_sdio_irq(struct sdio_func *func)
 {
 	struct mt7615_dev *dev = sdio_get_drvdata(func);
 	struct mt76_sdio *sdio = &dev->mt76.sdio;
-	struct mt76s_intr intr;
-
-	/* disable interrupt */
-	sdio_writel(func, WHLPCR_INT_EN_CLR, MCR_WHLPCR, 0);
-
-	do {
-		sdio_readsb(func, &intr, MCR_WHISR, sizeof(struct mt76s_intr));
-		trace_dev_irq(&dev->mt76, intr.isr, 0);
 
-		if (!test_bit(MT76_STATE_INITIALIZED, &dev->mt76.phy.state))
-			goto out;
+	if (!test_bit(MT76_STATE_INITIALIZED, &dev->mt76.phy.state))
+		return;
 
-		if (intr.isr & WHIER_RX0_DONE_INT_EN) {
-			mt7663s_rx_run_queue(dev, 0, &intr);
-			wake_up_process(sdio->kthread);
-		}
-
-		if (intr.isr & WHIER_RX1_DONE_INT_EN) {
-			mt7663s_rx_run_queue(dev, 1, &intr);
-			wake_up_process(sdio->kthread);
-		}
-
-		if (intr.isr & WHIER_TX_DONE_INT_EN) {
-			mt7663s_refill_sched_quota(dev, intr.tx.wtqcr);
-			mt7663s_tx_run_queues(dev);
-			wake_up_process(sdio->kthread);
-		}
-	} while (intr.isr);
-out:
-	/* enable interrupt */
-	sdio_writel(func, WHLPCR_INT_EN_SET, MCR_WHLPCR, 0);
+	queue_work(sdio->txrx_wq, &sdio->rx.recv_work);
 }
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/testmode.c b/drivers/net/wireless/mediatek/mt76/mt7615/testmode.c
index 1730751133aa..e4dc62314bae 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/testmode.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/testmode.c
@@ -70,7 +70,7 @@ mt7615_tm_set_tx_power(struct mt7615_phy *phy)
 	if (dev->mt76.test.state != MT76_TM_STATE_OFF)
 		tx_power = dev->mt76.test.tx_power;
 
-	len = sizeof(req_hdr) + MT7615_EE_MAX - MT_EE_NIC_CONF_0;
+	len = MT7615_EE_MAX - MT_EE_NIC_CONF_0;
 	skb = mt76_mcu_msg_alloc(&dev->mt76, NULL, sizeof(req_hdr) + len);
 	if (!skb)
 		return -ENOMEM;
@@ -80,13 +80,12 @@ mt7615_tm_set_tx_power(struct mt7615_phy *phy)
 
 	target_chains = mt7615_ext_pa_enabled(dev, band) ? 1 : n_chains;
 	for (i = 0; i < target_chains; i++) {
-		int index;
-
 		ret = mt7615_eeprom_get_target_power_index(dev, chandef->chan, i);
-		if (ret < 0)
+		if (ret < 0) {
+			dev_kfree_skb(skb);
 			return -EINVAL;
+		}
 
-		index = ret - MT_EE_NIC_CONF_0;
 		if (tx_power && tx_power[i])
 			data[ret - MT_EE_NIC_CONF_0] = tx_power[i];
 	}
@@ -191,7 +190,7 @@ mt7615_tm_set_tx_antenna(struct mt7615_dev *dev, bool en)
 	for (i = 0; i < 4; i++) {
 		mt76_rmw_field(dev, MT_WF_PHY_RFINTF3_0(i),
 			       MT_WF_PHY_RFINTF3_0_ANT,
-			       td->tx_antenna_mask & BIT(i) ? 0 : 0xa);
+			       (td->tx_antenna_mask & BIT(i)) ? 0 : 0xa);
 
 	}
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/usb.c b/drivers/net/wireless/mediatek/mt76/mt7615/usb.c
index 23a21338c46e..f0ad83af9e00 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/usb.c
@@ -180,9 +180,7 @@ static int mt7663u_suspend(struct usb_interface *intf, pm_message_t state)
 	}
 
 	mt76u_stop_rx(&dev->mt76);
-
 	mt76u_stop_tx(&dev->mt76);
-	tasklet_kill(&dev->mt76.tx_tasklet);
 
 	return 0;
 }
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/usb_mcu.c b/drivers/net/wireless/mediatek/mt76/mt7615/usb_mcu.c
index 0b33df3e3bfe..4d8be366af31 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/usb_mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/usb_mcu.c
@@ -18,7 +18,7 @@ mt7663u_mcu_send_message(struct mt76_dev *mdev, struct sk_buff *skb,
 			 int cmd, bool wait_resp)
 {
 	struct mt7615_dev *dev = container_of(mdev, struct mt7615_dev, mt76);
-	int ret, seq, ep;
+	int ret, seq, ep, len, pad;
 
 	mutex_lock(&mdev->mcu.mutex);
 
@@ -28,8 +28,10 @@ mt7663u_mcu_send_message(struct mt76_dev *mdev, struct sk_buff *skb,
 	else
 		ep = MT_EP_OUT_AC_BE;
 
-	put_unaligned_le32(skb->len, skb_push(skb, sizeof(skb->len)));
-	ret = mt76_skb_adjust_pad(skb);
+	len = skb->len;
+	put_unaligned_le32(len, skb_push(skb, sizeof(len)));
+	pad = round_up(skb->len, 4) + 4 - skb->len;
+	ret = mt76_skb_adjust_pad(skb, pad);
 	if (ret < 0)
 		goto out;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/usb_sdio.c b/drivers/net/wireless/mediatek/mt76/mt7615/usb_sdio.c
index 6dffdaaa9ad5..3b29a6d3dc64 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/usb_sdio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/usb_sdio.c
@@ -226,7 +226,6 @@ bool mt7663_usb_sdio_tx_status_data(struct mt76_dev *mdev, u8 *update)
 EXPORT_SYMBOL_GPL(mt7663_usb_sdio_tx_status_data);
 
 void mt7663_usb_sdio_tx_complete_skb(struct mt76_dev *mdev,
-				     enum mt76_txq_id qid,
 				     struct mt76_queue_entry *e)
 {
 	unsigned int headroom = MT_USB_TXD_SIZE;
@@ -235,7 +234,7 @@ void mt7663_usb_sdio_tx_complete_skb(struct mt76_dev *mdev,
 		headroom += MT_USB_HDR_SIZE;
 	skb_pull(e->skb, headroom);
 
-	mt76_tx_complete_skb(mdev, e->skb);
+	mt76_tx_complete_skb(mdev, e->wcid, e->skb);
 }
 EXPORT_SYMBOL_GPL(mt7663_usb_sdio_tx_complete_skb);
 
@@ -248,6 +247,7 @@ int mt7663_usb_sdio_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr,
 	struct mt7615_dev *dev = container_of(mdev, struct mt7615_dev, mt76);
 	struct sk_buff *skb = tx_info->skb;
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+	int pad;
 
 	if ((info->flags & IEEE80211_TX_CTL_RATE_CTRL_PROBE) &&
 	    !msta->rate_probe) {
@@ -259,10 +259,16 @@ int mt7663_usb_sdio_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr,
 	}
 
 	mt7663_usb_sdio_write_txwi(dev, wcid, qid, sta, skb);
-	if (mt76_is_usb(mdev))
-		put_unaligned_le32(skb->len, skb_push(skb, sizeof(skb->len)));
+	if (mt76_is_usb(mdev)) {
+		u32 len = skb->len;
+
+		put_unaligned_le32(len, skb_push(skb, sizeof(len)));
+		pad = round_up(skb->len, 4) + 4 - skb->len;
+	} else {
+		pad = round_up(skb->len, 4) - skb->len;
+	}
 
-	return mt76_skb_adjust_pad(skb);
+	return mt76_skb_adjust_pad(skb, pad);
 }
 EXPORT_SYMBOL_GPL(mt7663_usb_sdio_tx_prepare_skb);
 
@@ -359,14 +365,15 @@ int mt7663_usb_sdio_register_device(struct mt7615_dev *dev)
 	if (err)
 		return err;
 
-	/* check hw sg support in order to enable AMSDU */
-	if (dev->mt76.usb.sg_en || mt76_is_sdio(&dev->mt76))
-		hw->max_tx_fragments = MT_HW_TXP_MAX_BUF_NUM;
-	else
-		hw->max_tx_fragments = 1;
 	hw->extra_tx_headroom += MT_USB_TXD_SIZE;
-	if (mt76_is_usb(&dev->mt76))
+	if (mt76_is_usb(&dev->mt76)) {
 		hw->extra_tx_headroom += MT_USB_HDR_SIZE;
+		/* check hw sg support in order to enable AMSDU */
+		if (dev->mt76.usb.sg_en)
+			hw->max_tx_fragments = MT_HW_TXP_MAX_BUF_NUM;
+		else
+			hw->max_tx_fragments = 1;
+	}
 
 	err = mt76_register_device(&dev->mt76, true, mt7615_rates,
 				   ARRAY_SIZE(mt7615_rates));
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/init.c b/drivers/net/wireless/mediatek/mt76/mt76x0/init.c
index dc8bf4c6969a..d78866bf41ba 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/init.c
@@ -10,6 +10,7 @@
 #include "eeprom.h"
 #include "mcu.h"
 #include "initvals.h"
+#include "initvals_init.h"
 #include "../mt76x02_phy.h"
 
 static void
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/initvals.h b/drivers/net/wireless/mediatek/mt76/mt76x0/initvals.h
index 3dcd9620a126..99808ed0c6cb 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/initvals.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/initvals.h
@@ -11,139 +11,6 @@
 
 #include "phy.h"
 
-static const struct mt76_reg_pair common_mac_reg_table[] = {
-	{ MT_BCN_OFFSET(0),		0xf8f0e8e0 },
-	{ MT_BCN_OFFSET(1),		0x6f77d0c8 },
-	{ MT_LEGACY_BASIC_RATE,		0x0000013f },
-	{ MT_HT_BASIC_RATE,		0x00008003 },
-	{ MT_MAC_SYS_CTRL,		0x00000000 },
-	{ MT_RX_FILTR_CFG,		0x00017f97 },
-	{ MT_BKOFF_SLOT_CFG,		0x00000209 },
-	{ MT_TX_SW_CFG0,		0x00000000 },
-	{ MT_TX_SW_CFG1,		0x00080606 },
-	{ MT_TX_LINK_CFG,		0x00001020 },
-	{ MT_TX_TIMEOUT_CFG,		0x000a2090 },
-	{ MT_MAX_LEN_CFG,		0xa0fff | 0x00001000 },
-	{ MT_LED_CFG,			0x7f031e46 },
-	{ MT_PBF_TX_MAX_PCNT,		0x1fbf1f1f },
-	{ MT_PBF_RX_MAX_PCNT,		0x0000fe9f },
-	{ MT_TX_RETRY_CFG,		0x47d01f0f },
-	{ MT_AUTO_RSP_CFG,		0x00000013 },
-	{ MT_CCK_PROT_CFG,		0x07f40003 },
-	{ MT_OFDM_PROT_CFG,		0x07f42004 },
-	{ MT_PBF_CFG,			0x00f40006 },
-	{ MT_WPDMA_GLO_CFG,		0x00000030 },
-	{ MT_GF20_PROT_CFG,		0x01742004 },
-	{ MT_GF40_PROT_CFG,		0x03f42084 },
-	{ MT_MM20_PROT_CFG,		0x01742004 },
-	{ MT_MM40_PROT_CFG,		0x03f42084 },
-	{ MT_TXOP_CTRL_CFG,		0x0000583f },
-	{ MT_TX_RTS_CFG,		0x00ffff20 },
-	{ MT_EXP_ACK_TIME,		0x002400ca },
-	{ MT_TXOP_HLDR_ET,		0x00000002 },
-	{ MT_XIFS_TIME_CFG,		0x33a41010 },
-	{ MT_PWR_PIN_CFG,		0x00000000 },
-};
-
-static const struct mt76_reg_pair mt76x0_mac_reg_table[] = {
-	{ MT_IOCFG_6,			0xa0040080 },
-	{ MT_PBF_SYS_CTRL,		0x00080c00 },
-	{ MT_PBF_CFG,			0x77723c1f },
-	{ MT_FCE_PSE_CTRL,		0x00000001 },
-	{ MT_AMPDU_MAX_LEN_20M1S,	0xAAA99887 },
-	{ MT_TX_SW_CFG0,		0x00000601 },
-	{ MT_TX_SW_CFG1,		0x00040000 },
-	{ MT_TX_SW_CFG2,		0x00000000 },
-	{ 0xa44,			0x00000000 },
-	{ MT_HEADER_TRANS_CTRL_REG,	0x00000000 },
-	{ MT_TSO_CTRL,			0x00000000 },
-	{ MT_BB_PA_MODE_CFG1,		0x00500055 },
-	{ MT_RF_PA_MODE_CFG1,		0x00500055 },
-	{ MT_TX_ALC_CFG_0,		0x2F2F000C },
-	{ MT_TX0_BB_GAIN_ATTEN,		0x00000000 },
-	{ MT_TX_PWR_CFG_0,		0x3A3A3A3A },
-	{ MT_TX_PWR_CFG_1,		0x3A3A3A3A },
-	{ MT_TX_PWR_CFG_2,		0x3A3A3A3A },
-	{ MT_TX_PWR_CFG_3,		0x3A3A3A3A },
-	{ MT_TX_PWR_CFG_4,		0x3A3A3A3A },
-	{ MT_TX_PWR_CFG_7,		0x3A3A3A3A },
-	{ MT_TX_PWR_CFG_8,		0x0000003A },
-	{ MT_TX_PWR_CFG_9,		0x0000003A },
-	{ 0x150C,			0x00000002 },
-	{ 0x1238,			0x001700C8 },
-	{ MT_LDO_CTRL_0,		0x00A647B6 },
-	{ MT_LDO_CTRL_1,		0x6B006464 },
-	{ MT_HT_BASIC_RATE,		0x00004003 },
-	{ MT_HT_CTRL_CFG,		0x000001FF },
-	{ MT_TXOP_HLDR_ET,		0x00000000 },
-	{ MT_PN_PAD_MODE,		0x00000003 },
-	{ MT_TX_PROT_CFG6,		0xe3f42004 },
-	{ MT_TX_PROT_CFG7,		0xe3f42084 },
-	{ MT_TX_PROT_CFG8,		0xe3f42104 },
-	{ MT_VHT_HT_FBK_CFG1,		0xedcba980 },
-};
-
-static const struct mt76_reg_pair mt76x0_bbp_init_tab[] = {
-	{ MT_BBP(CORE, 1),	0x00000002 },
-	{ MT_BBP(CORE, 4),	0x00000000 },
-	{ MT_BBP(CORE, 24),	0x00000000 },
-	{ MT_BBP(CORE, 32),	0x4003000a },
-	{ MT_BBP(CORE, 42),	0x00000000 },
-	{ MT_BBP(CORE, 44),	0x00000000 },
-	{ MT_BBP(IBI, 11),	0x0FDE8081 },
-	{ MT_BBP(AGC, 0),	0x00021400 },
-	{ MT_BBP(AGC, 1),	0x00000003 },
-	{ MT_BBP(AGC, 2),	0x003A6464 },
-	{ MT_BBP(AGC, 15),	0x88A28CB8 },
-	{ MT_BBP(AGC, 22),	0x00001E21 },
-	{ MT_BBP(AGC, 23),	0x0000272C },
-	{ MT_BBP(AGC, 24),	0x00002F3A },
-	{ MT_BBP(AGC, 25),	0x8000005A },
-	{ MT_BBP(AGC, 26),	0x007C2005 },
-	{ MT_BBP(AGC, 33),	0x00003238 },
-	{ MT_BBP(AGC, 34),	0x000A0C0C },
-	{ MT_BBP(AGC, 37),	0x2121262C },
-	{ MT_BBP(AGC, 41),	0x38383E45 },
-	{ MT_BBP(AGC, 57),	0x00001010 },
-	{ MT_BBP(AGC, 59),	0xBAA20E96 },
-	{ MT_BBP(AGC, 63),	0x00000001 },
-	{ MT_BBP(TXC, 0),	0x00280403 },
-	{ MT_BBP(TXC, 1),	0x00000000 },
-	{ MT_BBP(RXC, 1),	0x00000012 },
-	{ MT_BBP(RXC, 2),	0x00000011 },
-	{ MT_BBP(RXC, 3),	0x00000005 },
-	{ MT_BBP(RXC, 4),	0x00000000 },
-	{ MT_BBP(RXC, 5),	0xF977C4EC },
-	{ MT_BBP(RXC, 7),	0x00000090 },
-	{ MT_BBP(TXO, 8),	0x00000000 },
-	{ MT_BBP(TXBE, 0),	0x00000000 },
-	{ MT_BBP(TXBE, 4),	0x00000004 },
-	{ MT_BBP(TXBE, 6),	0x00000000 },
-	{ MT_BBP(TXBE, 8),	0x00000014 },
-	{ MT_BBP(TXBE, 9),	0x20000000 },
-	{ MT_BBP(TXBE, 10),	0x00000000 },
-	{ MT_BBP(TXBE, 12),	0x00000000 },
-	{ MT_BBP(TXBE, 13),	0x00000000 },
-	{ MT_BBP(TXBE, 14),	0x00000000 },
-	{ MT_BBP(TXBE, 15),	0x00000000 },
-	{ MT_BBP(TXBE, 16),	0x00000000 },
-	{ MT_BBP(TXBE, 17),	0x00000000 },
-	{ MT_BBP(RXFE, 1),	0x00008800 },
-	{ MT_BBP(RXFE, 3),	0x00000000 },
-	{ MT_BBP(RXFE, 4),	0x00000000 },
-	{ MT_BBP(RXO, 13),	0x00000192 },
-	{ MT_BBP(RXO, 14),	0x00060612 },
-	{ MT_BBP(RXO, 15),	0xC8321B18 },
-	{ MT_BBP(RXO, 16),	0x0000001E },
-	{ MT_BBP(RXO, 17),	0x00000000 },
-	{ MT_BBP(RXO, 18),	0xCC00A993 },
-	{ MT_BBP(RXO, 19),	0xB9CB9CB9 },
-	{ MT_BBP(RXO, 20),	0x26c00057 },
-	{ MT_BBP(RXO, 21),	0x00000001 },
-	{ MT_BBP(RXO, 24),	0x00000006 },
-	{ MT_BBP(RXO, 28),	0x0000003F },
-};
-
 static const struct mt76x0_bbp_switch_item mt76x0_bbp_switch_tab[] = {
 	{ RF_G_BAND | RF_BW_20 | RF_BW_40,		{ MT_BBP(AGC, 4),	0x1FEDA049 } },
 	{ RF_A_BAND | RF_BW_20 | RF_BW_40 | RF_BW_80,	{ MT_BBP(AGC, 4),	0x1FECA054 } },
@@ -215,16 +82,4 @@ static const struct mt76x0_bbp_switch_item mt76x0_bbp_switch_tab[] = {
 	{ RF_A_BAND | RF_BW_20 | RF_BW_40 | RF_BW_80,	{ MT_BBP(RXFE, 0),	0x895000E0 } },
 };
 
-static const struct mt76_reg_pair mt76x0_dcoc_tab[] = {
-	{ MT_BBP(CAL, 47), 0x000010F0 },
-	{ MT_BBP(CAL, 48), 0x00008080 },
-	{ MT_BBP(CAL, 49), 0x00000F07 },
-	{ MT_BBP(CAL, 50), 0x00000040 },
-	{ MT_BBP(CAL, 51), 0x00000404 },
-	{ MT_BBP(CAL, 52), 0x00080803 },
-	{ MT_BBP(CAL, 53), 0x00000704 },
-	{ MT_BBP(CAL, 54), 0x00002828 },
-	{ MT_BBP(CAL, 55), 0x00005050 },
-};
-
 #endif
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/initvals_init.h b/drivers/net/wireless/mediatek/mt76/mt76x0/initvals_init.h
new file mode 100644
index 000000000000..9e99ba75f490
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/initvals_init.h
@@ -0,0 +1,159 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * (c) Copyright 2002-2010, Ralink Technology, Inc.
+ * Copyright (C) 2015 Jakub Kicinski <kubakici@wp.pl>
+ * Copyright (C) 2018 Stanislaw Gruszka <stf_xl@wp.pl>
+ * Copyright (C) 2018 Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>
+ */
+
+#ifndef __MT76X0U_INITVALS_INIT_H
+#define __MT76X0U_INITVALS_INIT_H
+
+#include "phy.h"
+
+static const struct mt76_reg_pair common_mac_reg_table[] = {
+	{ MT_BCN_OFFSET(0),		0xf8f0e8e0 },
+	{ MT_BCN_OFFSET(1),		0x6f77d0c8 },
+	{ MT_LEGACY_BASIC_RATE,		0x0000013f },
+	{ MT_HT_BASIC_RATE,		0x00008003 },
+	{ MT_MAC_SYS_CTRL,		0x00000000 },
+	{ MT_RX_FILTR_CFG,		0x00017f97 },
+	{ MT_BKOFF_SLOT_CFG,		0x00000209 },
+	{ MT_TX_SW_CFG0,		0x00000000 },
+	{ MT_TX_SW_CFG1,		0x00080606 },
+	{ MT_TX_LINK_CFG,		0x00001020 },
+	{ MT_TX_TIMEOUT_CFG,		0x000a2090 },
+	{ MT_MAX_LEN_CFG,		0xa0fff | 0x00001000 },
+	{ MT_LED_CFG,			0x7f031e46 },
+	{ MT_PBF_TX_MAX_PCNT,		0x1fbf1f1f },
+	{ MT_PBF_RX_MAX_PCNT,		0x0000fe9f },
+	{ MT_TX_RETRY_CFG,		0x47d01f0f },
+	{ MT_AUTO_RSP_CFG,		0x00000013 },
+	{ MT_CCK_PROT_CFG,		0x07f40003 },
+	{ MT_OFDM_PROT_CFG,		0x07f42004 },
+	{ MT_PBF_CFG,			0x00f40006 },
+	{ MT_WPDMA_GLO_CFG,		0x00000030 },
+	{ MT_GF20_PROT_CFG,		0x01742004 },
+	{ MT_GF40_PROT_CFG,		0x03f42084 },
+	{ MT_MM20_PROT_CFG,		0x01742004 },
+	{ MT_MM40_PROT_CFG,		0x03f42084 },
+	{ MT_TXOP_CTRL_CFG,		0x0000583f },
+	{ MT_TX_RTS_CFG,		0x00ffff20 },
+	{ MT_EXP_ACK_TIME,		0x002400ca },
+	{ MT_TXOP_HLDR_ET,		0x00000002 },
+	{ MT_XIFS_TIME_CFG,		0x33a41010 },
+	{ MT_PWR_PIN_CFG,		0x00000000 },
+};
+
+static const struct mt76_reg_pair mt76x0_mac_reg_table[] = {
+	{ MT_IOCFG_6,			0xa0040080 },
+	{ MT_PBF_SYS_CTRL,		0x00080c00 },
+	{ MT_PBF_CFG,			0x77723c1f },
+	{ MT_FCE_PSE_CTRL,		0x00000001 },
+	{ MT_AMPDU_MAX_LEN_20M1S,	0xAAA99887 },
+	{ MT_TX_SW_CFG0,		0x00000601 },
+	{ MT_TX_SW_CFG1,		0x00040000 },
+	{ MT_TX_SW_CFG2,		0x00000000 },
+	{ 0xa44,			0x00000000 },
+	{ MT_HEADER_TRANS_CTRL_REG,	0x00000000 },
+	{ MT_TSO_CTRL,			0x00000000 },
+	{ MT_BB_PA_MODE_CFG1,		0x00500055 },
+	{ MT_RF_PA_MODE_CFG1,		0x00500055 },
+	{ MT_TX_ALC_CFG_0,		0x2F2F000C },
+	{ MT_TX0_BB_GAIN_ATTEN,		0x00000000 },
+	{ MT_TX_PWR_CFG_0,		0x3A3A3A3A },
+	{ MT_TX_PWR_CFG_1,		0x3A3A3A3A },
+	{ MT_TX_PWR_CFG_2,		0x3A3A3A3A },
+	{ MT_TX_PWR_CFG_3,		0x3A3A3A3A },
+	{ MT_TX_PWR_CFG_4,		0x3A3A3A3A },
+	{ MT_TX_PWR_CFG_7,		0x3A3A3A3A },
+	{ MT_TX_PWR_CFG_8,		0x0000003A },
+	{ MT_TX_PWR_CFG_9,		0x0000003A },
+	{ 0x150C,			0x00000002 },
+	{ 0x1238,			0x001700C8 },
+	{ MT_LDO_CTRL_0,		0x00A647B6 },
+	{ MT_LDO_CTRL_1,		0x6B006464 },
+	{ MT_HT_BASIC_RATE,		0x00004003 },
+	{ MT_HT_CTRL_CFG,		0x000001FF },
+	{ MT_TXOP_HLDR_ET,		0x00000000 },
+	{ MT_PN_PAD_MODE,		0x00000003 },
+	{ MT_TX_PROT_CFG6,		0xe3f42004 },
+	{ MT_TX_PROT_CFG7,		0xe3f42084 },
+	{ MT_TX_PROT_CFG8,		0xe3f42104 },
+	{ MT_VHT_HT_FBK_CFG1,		0xedcba980 },
+};
+
+static const struct mt76_reg_pair mt76x0_bbp_init_tab[] = {
+	{ MT_BBP(CORE, 1),	0x00000002 },
+	{ MT_BBP(CORE, 4),	0x00000000 },
+	{ MT_BBP(CORE, 24),	0x00000000 },
+	{ MT_BBP(CORE, 32),	0x4003000a },
+	{ MT_BBP(CORE, 42),	0x00000000 },
+	{ MT_BBP(CORE, 44),	0x00000000 },
+	{ MT_BBP(IBI, 11),	0x0FDE8081 },
+	{ MT_BBP(AGC, 0),	0x00021400 },
+	{ MT_BBP(AGC, 1),	0x00000003 },
+	{ MT_BBP(AGC, 2),	0x003A6464 },
+	{ MT_BBP(AGC, 15),	0x88A28CB8 },
+	{ MT_BBP(AGC, 22),	0x00001E21 },
+	{ MT_BBP(AGC, 23),	0x0000272C },
+	{ MT_BBP(AGC, 24),	0x00002F3A },
+	{ MT_BBP(AGC, 25),	0x8000005A },
+	{ MT_BBP(AGC, 26),	0x007C2005 },
+	{ MT_BBP(AGC, 33),	0x00003238 },
+	{ MT_BBP(AGC, 34),	0x000A0C0C },
+	{ MT_BBP(AGC, 37),	0x2121262C },
+	{ MT_BBP(AGC, 41),	0x38383E45 },
+	{ MT_BBP(AGC, 57),	0x00001010 },
+	{ MT_BBP(AGC, 59),	0xBAA20E96 },
+	{ MT_BBP(AGC, 63),	0x00000001 },
+	{ MT_BBP(TXC, 0),	0x00280403 },
+	{ MT_BBP(TXC, 1),	0x00000000 },
+	{ MT_BBP(RXC, 1),	0x00000012 },
+	{ MT_BBP(RXC, 2),	0x00000011 },
+	{ MT_BBP(RXC, 3),	0x00000005 },
+	{ MT_BBP(RXC, 4),	0x00000000 },
+	{ MT_BBP(RXC, 5),	0xF977C4EC },
+	{ MT_BBP(RXC, 7),	0x00000090 },
+	{ MT_BBP(TXO, 8),	0x00000000 },
+	{ MT_BBP(TXBE, 0),	0x00000000 },
+	{ MT_BBP(TXBE, 4),	0x00000004 },
+	{ MT_BBP(TXBE, 6),	0x00000000 },
+	{ MT_BBP(TXBE, 8),	0x00000014 },
+	{ MT_BBP(TXBE, 9),	0x20000000 },
+	{ MT_BBP(TXBE, 10),	0x00000000 },
+	{ MT_BBP(TXBE, 12),	0x00000000 },
+	{ MT_BBP(TXBE, 13),	0x00000000 },
+	{ MT_BBP(TXBE, 14),	0x00000000 },
+	{ MT_BBP(TXBE, 15),	0x00000000 },
+	{ MT_BBP(TXBE, 16),	0x00000000 },
+	{ MT_BBP(TXBE, 17),	0x00000000 },
+	{ MT_BBP(RXFE, 1),	0x00008800 },
+	{ MT_BBP(RXFE, 3),	0x00000000 },
+	{ MT_BBP(RXFE, 4),	0x00000000 },
+	{ MT_BBP(RXO, 13),	0x00000192 },
+	{ MT_BBP(RXO, 14),	0x00060612 },
+	{ MT_BBP(RXO, 15),	0xC8321B18 },
+	{ MT_BBP(RXO, 16),	0x0000001E },
+	{ MT_BBP(RXO, 17),	0x00000000 },
+	{ MT_BBP(RXO, 18),	0xCC00A993 },
+	{ MT_BBP(RXO, 19),	0xB9CB9CB9 },
+	{ MT_BBP(RXO, 20),	0x26c00057 },
+	{ MT_BBP(RXO, 21),	0x00000001 },
+	{ MT_BBP(RXO, 24),	0x00000006 },
+	{ MT_BBP(RXO, 28),	0x0000003F },
+};
+
+static const struct mt76_reg_pair mt76x0_dcoc_tab[] = {
+	{ MT_BBP(CAL, 47), 0x000010F0 },
+	{ MT_BBP(CAL, 48), 0x00008080 },
+	{ MT_BBP(CAL, 49), 0x00000F07 },
+	{ MT_BBP(CAL, 50), 0x00000040 },
+	{ MT_BBP(CAL, 51), 0x00000404 },
+	{ MT_BBP(CAL, 52), 0x00080803 },
+	{ MT_BBP(CAL, 53), 0x00000704 },
+	{ MT_BBP(CAL, 54), 0x00002828 },
+	{ MT_BBP(CAL, 55), 0x00005050 },
+};
+
+#endif
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
index f7ec3400e368..dda11c704aba 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
@@ -180,6 +180,8 @@ mt76x0e_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	mdev->rev = mt76_rr(dev, MT_ASIC_VERSION);
 	dev_info(mdev->dev, "ASIC revision: %08x\n", mdev->rev);
 
+	mt76_wr(dev, MT_INT_MASK_CSR, 0);
+
 	ret = devm_request_irq(mdev->dev, pdev->irq, mt76x02_irq_handler,
 			       IRQF_SHARED, KBUILD_MODNAME, dev);
 	if (ret)
@@ -202,7 +204,7 @@ static void mt76x0e_cleanup(struct mt76x02_dev *dev)
 	tasklet_disable(&dev->mt76.pre_tbtt_tasklet);
 	mt76x0_chip_onoff(dev, false, false);
 	mt76x0e_stop_hw(dev);
-	mt76x02_dma_cleanup(dev);
+	mt76_dma_cleanup(&dev->mt76);
 	mt76x02_mcu_cleanup(dev);
 }
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
index 09f34deb6ba1..3de33aadf794 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
@@ -734,7 +734,7 @@ mt76x0_phy_get_delta_power(struct mt76x02_dev *dev, u8 tx_mode,
 	case 1:
 		if (chan->band == NL80211_BAND_2GHZ)
 			tssi_target += 29491; /* 3.6 * 8192 */
-		/* fall through */
+		fallthrough;
 	case 0:
 		break;
 	default:
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02.h b/drivers/net/wireless/mediatek/mt76/mt76x02.h
index 4660b9691ec3..d626817a2103 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02.h
@@ -15,6 +15,8 @@
 #include "mt76x02_dfs.h"
 #include "mt76x02_dma.h"
 
+#define MT76x02_TX_RING_SIZE	512
+#define MT76x02_PSD_RING_SIZE	128
 #define MT76x02_N_WCIDS 128
 #define MT_CALIBRATE_INTERVAL	HZ
 #define MT_MAC_WORK_INTERVAL	(HZ / 10)
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_debugfs.c b/drivers/net/wireless/mediatek/mt76/mt76x02_debugfs.c
index ff448a1ad4e3..c4fe1c436aaa 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_debugfs.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_debugfs.c
@@ -7,7 +7,7 @@
 #include "mt76x02.h"
 
 static int
-mt76x02_ampdu_stat_read(struct seq_file *file, void *data)
+mt76x02_ampdu_stat_show(struct seq_file *file, void *data)
 {
 	struct mt76x02_dev *dev = file->private;
 	int i, j;
@@ -31,11 +31,7 @@ mt76x02_ampdu_stat_read(struct seq_file *file, void *data)
 	return 0;
 }
 
-static int
-mt76x02_ampdu_stat_open(struct inode *inode, struct file *f)
-{
-	return single_open(f, mt76x02_ampdu_stat_read, inode->i_private);
-}
+DEFINE_SHOW_ATTRIBUTE(mt76x02_ampdu_stat);
 
 static int read_txpower(struct seq_file *file, void *data)
 {
@@ -48,15 +44,8 @@ static int read_txpower(struct seq_file *file, void *data)
 	return 0;
 }
 
-static const struct file_operations fops_ampdu_stat = {
-	.open = mt76x02_ampdu_stat_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
-};
-
 static int
-mt76x02_dfs_stat_read(struct seq_file *file, void *data)
+mt76x02_dfs_stat_show(struct seq_file *file, void *data)
 {
 	struct mt76x02_dev *dev = file->private;
 	struct mt76x02_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
@@ -81,18 +70,7 @@ mt76x02_dfs_stat_read(struct seq_file *file, void *data)
 	return 0;
 }
 
-static int
-mt76x02_dfs_stat_open(struct inode *inode, struct file *f)
-{
-	return single_open(f, mt76x02_dfs_stat_read, inode->i_private);
-}
-
-static const struct file_operations fops_dfs_stat = {
-	.open = mt76x02_dfs_stat_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(mt76x02_dfs_stat);
 
 static int read_agc(struct seq_file *file, void *data)
 {
@@ -150,8 +128,8 @@ void mt76x02_init_debugfs(struct mt76x02_dev *dev)
 	debugfs_create_bool("tpc", 0600, dir, &dev->enable_tpc);
 
 	debugfs_create_file("edcca", 0600, dir, dev, &fops_edcca);
-	debugfs_create_file("ampdu_stat", 0400, dir, dev, &fops_ampdu_stat);
-	debugfs_create_file("dfs_stats", 0400, dir, dev, &fops_dfs_stat);
+	debugfs_create_file("ampdu_stat", 0400, dir, dev, &mt76x02_ampdu_stat_fops);
+	debugfs_create_file("dfs_stats", 0400, dir, dev, &mt76x02_dfs_stat_fops);
 	debugfs_create_devm_seqfile(dev->mt76.dev, "txpower", dir,
 				    read_txpower);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_dfs.c b/drivers/net/wireless/mediatek/mt76/mt76x02_dfs.c
index ff6a9e4daac0..b29cd39dc176 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_dfs.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_dfs.c
@@ -429,11 +429,11 @@ static int mt76x02_dfs_create_sequence(struct mt76x02_dev *dev,
 {
 	struct mt76x02_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
 	struct mt76x02_dfs_sw_detector_params *sw_params;
-	u32 width_delta, with_sum, factor, cur_pri;
+	u32 width_delta, with_sum;
 	struct mt76x02_dfs_sequence seq, *seq_p;
 	struct mt76x02_dfs_event_rb *event_rb;
 	struct mt76x02_dfs_event *cur_event;
-	int i, j, end, pri;
+	int i, j, end, pri, factor, cur_pri;
 
 	event_rb = event->engine == 2 ? &dfs_pd->event_rb[1]
 				      : &dfs_pd->event_rb[0];
@@ -517,7 +517,7 @@ static u16 mt76x02_dfs_add_event_to_sequence(struct mt76x02_dev *dev,
 	struct mt76x02_dfs_sw_detector_params *sw_params;
 	struct mt76x02_dfs_sequence *seq, *tmp_seq;
 	u16 max_seq_len = 0;
-	u32 factor, pri;
+	int factor, pri;
 
 	sw_params = &dfs_pd->sw_dpd_params;
 	list_for_each_entry_safe(seq, tmp_seq, &dfs_pd->sequences, head) {
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_dma.h b/drivers/net/wireless/mediatek/mt76/mt76x02_dma.h
index 4aff4f8e87b6..23b0e7d10d57 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_dma.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_dma.h
@@ -61,6 +61,5 @@ mt76x02_wait_for_wpdma(struct mt76_dev *dev, int timeout)
 
 int mt76x02_dma_init(struct mt76x02_dev *dev);
 void mt76x02_dma_disable(struct mt76x02_dev *dev);
-void mt76x02_dma_cleanup(struct mt76x02_dev *dev);
 
 #endif /* __MT76x02_DMA_H */
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c
index e4e03beabe43..da6d3f51f6d4 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c
@@ -300,7 +300,7 @@ mt76x02_mac_process_tx_rate(struct ieee80211_tx_rate *txrate, u16 rate,
 		return 0;
 	case MT_PHY_TYPE_HT_GF:
 		txrate->flags |= IEEE80211_TX_RC_GREEN_FIELD;
-		/* fall through */
+		fallthrough;
 	case MT_PHY_TYPE_HT:
 		txrate->flags |= IEEE80211_TX_RC_MCS;
 		txrate->idx = idx;
@@ -349,6 +349,8 @@ void mt76x02_mac_write_txwi(struct mt76x02_dev *dev, struct mt76x02_txwi *txwi,
 
 	memset(txwi, 0, sizeof(*txwi));
 
+	mt76_tx_check_agg_ssn(sta, skb);
+
 	if (!info->control.hw_key && wcid && wcid->hw_key_idx != 0xff &&
 	    ieee80211_has_protected(hdr->frame_control)) {
 		wcid = NULL;
@@ -462,7 +464,7 @@ mt76x02_tx_rate_fallback(struct ieee80211_tx_rate *rates, int idx, int phy)
 			rates[1].idx = 0;
 			break;
 		}
-		/* fall through */
+		fallthrough;
 	default:
 		rates[1].idx = max_t(int, rates[0].idx - 1, 0);
 		break;
@@ -677,7 +679,7 @@ mt76x02_mac_process_rate(struct mt76x02_dev *dev,
 		return 0;
 	case MT_PHY_TYPE_HT_GF:
 		status->enc_flags |= RX_ENC_FLAG_HT_GF;
-		/* fall through */
+		fallthrough;
 	case MT_PHY_TYPE_HT:
 		status->encoding = RX_ENC_HT;
 		status->rate_idx = idx;
@@ -898,8 +900,7 @@ void mt76x02_mac_poll_tx_status(struct mt76x02_dev *dev, bool irq)
 	}
 }
 
-void mt76x02_tx_complete_skb(struct mt76_dev *mdev, enum mt76_txq_id qid,
-			     struct mt76_queue_entry *e)
+void mt76x02_tx_complete_skb(struct mt76_dev *mdev, struct mt76_queue_entry *e)
 {
 	struct mt76x02_dev *dev = container_of(mdev, struct mt76x02_dev, mt76);
 	struct mt76x02_txwi *txwi;
@@ -916,7 +917,7 @@ void mt76x02_tx_complete_skb(struct mt76_dev *mdev, enum mt76_txq_id qid,
 	txwi = (struct mt76x02_txwi *)txwi_ptr;
 	trace_mac_txdone(mdev, txwi->wcid, txwi->pktid);
 
-	mt76_tx_complete_skb(mdev, e->skb);
+	mt76_tx_complete_skb(mdev, e->wcid, e->skb);
 }
 EXPORT_SYMBOL_GPL(mt76x02_tx_complete_skb);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h
index c70d17b2290c..0cfbaca50210 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h
@@ -194,8 +194,7 @@ void mt76x02_mac_write_txwi(struct mt76x02_dev *dev, struct mt76x02_txwi *txwi,
 			    struct sk_buff *skb, struct mt76_wcid *wcid,
 			    struct ieee80211_sta *sta, int len);
 void mt76x02_mac_poll_tx_status(struct mt76x02_dev *dev, bool irq);
-void mt76x02_tx_complete_skb(struct mt76_dev *mdev, enum mt76_txq_id qid,
-			     struct mt76_queue_entry *e);
+void mt76x02_tx_complete_skb(struct mt76_dev *mdev, struct mt76_queue_entry *e);
 void mt76x02_update_channel(struct mt76_dev *mdev);
 void mt76x02_mac_work(struct work_struct *work);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c b/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c
index bacb1f10a699..cf68731bd094 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c
@@ -14,7 +14,7 @@
 static void mt76x02_pre_tbtt_tasklet(unsigned long arg)
 {
 	struct mt76x02_dev *dev = (struct mt76x02_dev *)arg;
-	struct mt76_queue *q = dev->mt76.q_tx[MT_TXQ_PSD].q;
+	struct mt76_queue *q = dev->mt76.q_tx[MT_TXQ_PSD];
 	struct beacon_bc_data data = {};
 	struct sk_buff *skb;
 	int i;
@@ -104,8 +104,7 @@ void mt76x02e_init_beacon_config(struct mt76x02_dev *dev)
 EXPORT_SYMBOL_GPL(mt76x02e_init_beacon_config);
 
 static int
-mt76x02_init_tx_queue(struct mt76x02_dev *dev, struct mt76_sw_queue *q,
-		      int idx, int n_desc)
+mt76x02_init_tx_queue(struct mt76x02_dev *dev, int qid, int idx, int n_desc)
 {
 	struct mt76_queue *hwq;
 	int err;
@@ -118,8 +117,7 @@ mt76x02_init_tx_queue(struct mt76x02_dev *dev, struct mt76_sw_queue *q,
 	if (err < 0)
 		return err;
 
-	INIT_LIST_HEAD(&q->swq);
-	q->q = hwq;
+	dev->mt76.q_tx[qid] = hwq;
 
 	mt76x02_irq_enable(dev, MT_INT_TX_DONE(idx));
 
@@ -151,9 +149,11 @@ static void mt76x02_process_tx_status_fifo(struct mt76x02_dev *dev)
 		mt76x02_send_tx_status(dev, &stat, &update);
 }
 
-static void mt76x02_tx_tasklet(unsigned long data)
+static void mt76x02_tx_worker(struct mt76_worker *w)
 {
-	struct mt76x02_dev *dev = (struct mt76x02_dev *)data;
+	struct mt76x02_dev *dev;
+
+	dev = container_of(w, struct mt76x02_dev, mt76.tx_worker);
 
 	mt76x02_mac_poll_tx_status(dev, false);
 	mt76x02_process_tx_status_fifo(dev);
@@ -178,7 +178,7 @@ static int mt76x02_poll_tx(struct napi_struct *napi, int budget)
 	for (i = MT_TXQ_MCU; i >= 0; i--)
 		mt76_queue_tx_cleanup(dev, i, false);
 
-	tasklet_schedule(&dev->mt76.tx_tasklet);
+	mt76_worker_schedule(&dev->mt76.tx_worker);
 
 	return 0;
 }
@@ -197,8 +197,7 @@ int mt76x02_dma_init(struct mt76x02_dev *dev)
 	if (!status_fifo)
 		return -ENOMEM;
 
-	tasklet_init(&dev->mt76.tx_tasklet, mt76x02_tx_tasklet,
-		     (unsigned long)dev);
+	dev->mt76.tx_worker.fn = mt76x02_tx_worker;
 	tasklet_init(&dev->mt76.pre_tbtt_tasklet, mt76x02_pre_tbtt_tasklet,
 		     (unsigned long)dev);
 
@@ -210,19 +209,18 @@ int mt76x02_dma_init(struct mt76x02_dev *dev)
 	mt76_wr(dev, MT_WPDMA_RST_IDX, ~0);
 
 	for (i = 0; i < IEEE80211_NUM_ACS; i++) {
-		ret = mt76x02_init_tx_queue(dev, &dev->mt76.q_tx[i],
-					    mt76_ac_to_hwq(i),
-					    MT_TX_RING_SIZE);
+		ret = mt76x02_init_tx_queue(dev, i, mt76_ac_to_hwq(i),
+					    MT76x02_TX_RING_SIZE);
 		if (ret)
 			return ret;
 	}
 
-	ret = mt76x02_init_tx_queue(dev, &dev->mt76.q_tx[MT_TXQ_PSD],
-				    MT_TX_HW_QUEUE_MGMT, MT_TX_RING_SIZE);
+	ret = mt76x02_init_tx_queue(dev, MT_TXQ_PSD,
+				    MT_TX_HW_QUEUE_MGMT, MT76x02_PSD_RING_SIZE);
 	if (ret)
 		return ret;
 
-	ret = mt76x02_init_tx_queue(dev, &dev->mt76.q_tx[MT_TXQ_MCU],
+	ret = mt76x02_init_tx_queue(dev, MT_TXQ_MCU,
 				    MT_TX_HW_QUEUE_MCU, MT_MCU_RING_SIZE);
 	if (ret)
 		return ret;
@@ -263,9 +261,10 @@ EXPORT_SYMBOL_GPL(mt76x02_rx_poll_complete);
 irqreturn_t mt76x02_irq_handler(int irq, void *dev_instance)
 {
 	struct mt76x02_dev *dev = dev_instance;
-	u32 intr;
+	u32 intr, mask;
 
 	intr = mt76_rr(dev, MT_INT_SOURCE_CSR);
+	intr &= dev->mt76.mmio.irqmask;
 	mt76_wr(dev, MT_INT_SOURCE_CSR, intr);
 
 	if (!test_bit(MT76_STATE_INITIALIZED, &dev->mphy.state))
@@ -273,17 +272,17 @@ irqreturn_t mt76x02_irq_handler(int irq, void *dev_instance)
 
 	trace_dev_irq(&dev->mt76, intr, dev->mt76.mmio.irqmask);
 
-	intr &= dev->mt76.mmio.irqmask;
+	mask = intr & (MT_INT_RX_DONE_ALL | MT_INT_GPTIMER);
+	if (intr & (MT_INT_TX_DONE_ALL | MT_INT_TX_STAT))
+		mask |= MT_INT_TX_DONE_ALL;
+
+	mt76x02_irq_disable(dev, mask);
 
-	if (intr & MT_INT_RX_DONE(0)) {
-		mt76x02_irq_disable(dev, MT_INT_RX_DONE(0));
+	if (intr & MT_INT_RX_DONE(0))
 		napi_schedule(&dev->mt76.napi[0]);
-	}
 
-	if (intr & MT_INT_RX_DONE(1)) {
-		mt76x02_irq_disable(dev, MT_INT_RX_DONE(1));
+	if (intr & MT_INT_RX_DONE(1))
 		napi_schedule(&dev->mt76.napi[1]);
-	}
 
 	if (intr & MT_INT_PRE_TBTT)
 		tasklet_schedule(&dev->mt76.pre_tbtt_tasklet);
@@ -293,21 +292,17 @@ irqreturn_t mt76x02_irq_handler(int irq, void *dev_instance)
 		if (dev->mt76.csa_complete)
 			mt76_csa_finish(&dev->mt76);
 		else
-			mt76_queue_kick(dev, dev->mt76.q_tx[MT_TXQ_PSD].q);
+			mt76_queue_kick(dev, dev->mt76.q_tx[MT_TXQ_PSD]);
 	}
 
 	if (intr & MT_INT_TX_STAT)
 		mt76x02_mac_poll_tx_status(dev, true);
 
-	if (intr & (MT_INT_TX_STAT | MT_INT_TX_DONE_ALL)) {
-		mt76x02_irq_disable(dev, MT_INT_TX_DONE_ALL);
+	if (intr & (MT_INT_TX_STAT | MT_INT_TX_DONE_ALL))
 		napi_schedule(&dev->mt76.tx_napi);
-	}
 
-	if (intr & MT_INT_GPTIMER) {
-		mt76x02_irq_disable(dev, MT_INT_GPTIMER);
+	if (intr & MT_INT_GPTIMER)
 		tasklet_schedule(&dev->dfs_pd.dfs_tasklet);
-	}
 
 	return IRQ_HANDLED;
 }
@@ -329,13 +324,6 @@ static void mt76x02_dma_enable(struct mt76x02_dev *dev)
 		   MT_WPDMA_GLO_CFG_TX_WRITEBACK_DONE);
 }
 
-void mt76x02_dma_cleanup(struct mt76x02_dev *dev)
-{
-	tasklet_kill(&dev->mt76.tx_tasklet);
-	mt76_dma_cleanup(&dev->mt76);
-}
-EXPORT_SYMBOL_GPL(mt76x02_dma_cleanup);
-
 void mt76x02_dma_disable(struct mt76x02_dev *dev)
 {
 	u32 val = mt76_rr(dev, MT_WPDMA_GLO_CFG);
@@ -369,7 +357,7 @@ static bool mt76x02_tx_hang(struct mt76x02_dev *dev)
 	int i;
 
 	for (i = 0; i < 4; i++) {
-		q = dev->mt76.q_tx[i].q;
+		q = dev->mt76.q_tx[i];
 
 		if (!q->queued)
 			continue;
@@ -453,7 +441,7 @@ static void mt76x02_watchdog_reset(struct mt76x02_dev *dev)
 	set_bit(MT76_RESET, &dev->mphy.state);
 
 	tasklet_disable(&dev->mt76.pre_tbtt_tasklet);
-	tasklet_disable(&dev->mt76.tx_tasklet);
+	mt76_worker_disable(&dev->mt76.tx_worker);
 	napi_disable(&dev->mt76.tx_napi);
 
 	mt76_for_each_q_rx(&dev->mt76, i) {
@@ -510,7 +498,7 @@ static void mt76x02_watchdog_reset(struct mt76x02_dev *dev)
 
 	clear_bit(MT76_RESET, &dev->mphy.state);
 
-	tasklet_enable(&dev->mt76.tx_tasklet);
+	mt76_worker_enable(&dev->mt76.tx_worker);
 	napi_enable(&dev->mt76.tx_napi);
 	napi_schedule(&dev->mt76.tx_napi);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_usb.h b/drivers/net/wireless/mediatek/mt76/mt76x02_usb.h
index a57dcc8820aa..b5be884b3549 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_usb.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_usb.h
@@ -19,8 +19,7 @@ int mt76x02u_tx_prepare_skb(struct mt76_dev *mdev, void *data,
 			    enum mt76_txq_id qid, struct mt76_wcid *wcid,
 			    struct ieee80211_sta *sta,
 			    struct mt76_tx_info *tx_info);
-void mt76x02u_tx_complete_skb(struct mt76_dev *mdev, enum mt76_txq_id qid,
-			      struct mt76_queue_entry *e);
+void mt76x02u_tx_complete_skb(struct mt76_dev *mdev, struct mt76_queue_entry *e);
 void mt76x02u_init_beacon_config(struct mt76x02_dev *dev);
 void mt76x02u_exit_beacon_config(struct mt76x02_dev *dev);
 #endif /* __MT76x02_USB_H */
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_usb_core.c b/drivers/net/wireless/mediatek/mt76/mt76x02_usb_core.c
index 37321e656776..2c2f56112b57 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_usb_core.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_usb_core.c
@@ -15,11 +15,10 @@ static void mt76x02u_remove_dma_hdr(struct sk_buff *skb)
 		mt76x02_remove_hdr_pad(skb, 2);
 }
 
-void mt76x02u_tx_complete_skb(struct mt76_dev *mdev, enum mt76_txq_id qid,
-			      struct mt76_queue_entry *e)
+void mt76x02u_tx_complete_skb(struct mt76_dev *mdev, struct mt76_queue_entry *e)
 {
 	mt76x02u_remove_dma_hdr(e->skb);
-	mt76_tx_complete_skb(mdev, e->skb);
+	mt76_tx_complete_skb(mdev, e->wcid, e->skb);
 }
 EXPORT_SYMBOL_GPL(mt76x02u_tx_complete_skb);
 
@@ -46,7 +45,7 @@ EXPORT_SYMBOL_GPL(mt76x02u_mac_start);
 
 int mt76x02u_skb_dma_info(struct sk_buff *skb, int port, u32 flags)
 {
-	u32 info;
+	u32 info, pad;
 
 	/* Buffer layout:
 	 *	|   4B   | xfer len |      pad       |  4B  |
@@ -58,7 +57,8 @@ int mt76x02u_skb_dma_info(struct sk_buff *skb, int port, u32 flags)
 	       FIELD_PREP(MT_TXD_INFO_DPORT, port) | flags;
 	put_unaligned_le32(info, skb_push(skb, sizeof(info)));
 
-	return mt76_skb_adjust_pad(skb);
+	pad = round_up(skb->len, 4) + 4 - skb->len;
+	return mt76_skb_adjust_pad(skb, pad);
 }
 
 int mt76x02u_tx_prepare_skb(struct mt76_dev *mdev, void *data,
@@ -67,7 +67,7 @@ int mt76x02u_tx_prepare_skb(struct mt76_dev *mdev, void *data,
 			    struct mt76_tx_info *tx_info)
 {
 	struct mt76x02_dev *dev = container_of(mdev, struct mt76x02_dev, mt76);
-	int pid, len = tx_info->skb->len, ep = q2ep(mdev->q_tx[qid].q->hw_idx);
+	int pid, len = tx_info->skb->len, ep = q2ep(mdev->q_tx[qid]->hw_idx);
 	struct mt76x02_txwi *txwi;
 	bool ampdu = IEEE80211_SKB_CB(tx_info->skb)->flags & IEEE80211_TX_CTL_AMPDU;
 	enum mt76_qsel qsel;
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
index dbd4077ea283..11b769af2f8f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
@@ -294,8 +294,6 @@ mt76x02_vif_init(struct mt76x02_dev *dev, struct ieee80211_vif *vif,
 	mvif->group_wcid.hw_key_idx = -1;
 	mtxq = (struct mt76_txq *)vif->txq->drv_priv;
 	mtxq->wcid = &mvif->group_wcid;
-
-	mt76_txq_init(&dev->mt76, vif->txq);
 }
 
 int
@@ -347,7 +345,6 @@ void mt76x02_remove_interface(struct ieee80211_hw *hw,
 	struct mt76x02_dev *dev = hw->priv;
 	struct mt76x02_vif *mvif = (struct mt76x02_vif *)vif->drv_priv;
 
-	mt76_txq_remove(&dev->mt76, vif->txq);
 	dev->mphy.vif_mask &= ~BIT(mvif->idx);
 }
 EXPORT_SYMBOL_GPL(mt76x02_remove_interface);
@@ -490,7 +487,7 @@ int mt76x02_conf_tx(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	u8 cw_min = 5, cw_max = 10, qid;
 	u32 val;
 
-	qid = dev->mt76.q_tx[queue].q->hw_idx;
+	qid = dev->mt76.q_tx[queue]->hw_idx;
 
 	if (params->cw_min)
 		cw_min = fls(params->cw_min);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c
index 6dfb0df8ec8a..4d50dad29ddf 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c
@@ -63,6 +63,8 @@ mt76x2e_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	mdev->rev = mt76_rr(dev, MT_ASIC_VERSION);
 	dev_info(mdev->dev, "ASIC revision: %08x\n", mdev->rev);
 
+	mt76_wr(dev, MT_INT_MASK_CSR, 0);
+
 	ret = devm_request_irq(mdev->dev, pdev->irq, mt76x02_irq_handler,
 			       IRQF_SHARED, KBUILD_MODNAME, dev);
 	if (ret)
@@ -111,7 +113,7 @@ mt76x2e_suspend(struct pci_dev *pdev, pm_message_t state)
 
 	napi_disable(&mdev->tx_napi);
 	tasklet_kill(&mdev->pre_tbtt_tasklet);
-	tasklet_kill(&mdev->tx_tasklet);
+	mt76_worker_disable(&mdev->tx_worker);
 
 	mt76_for_each_q_rx(mdev, i)
 		napi_disable(&mdev->napi[i]);
@@ -145,6 +147,7 @@ mt76x2e_resume(struct pci_dev *pdev)
 
 	pci_restore_state(pdev);
 
+	mt76_worker_enable(&mdev->tx_worker);
 	mt76_for_each_q_rx(mdev, i) {
 		napi_enable(&mdev->napi[i]);
 		napi_schedule(&mdev->napi[i]);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
index 101a0fe00ef3..48a3ebc9892a 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
@@ -283,7 +283,7 @@ void mt76x2_cleanup(struct mt76x02_dev *dev)
 	tasklet_disable(&dev->dfs_pd.dfs_tasklet);
 	tasklet_disable(&dev->mt76.pre_tbtt_tasklet);
 	mt76x2_stop_hardware(dev);
-	mt76x02_dma_cleanup(dev);
+	mt76_dma_cleanup(&dev->mt76);
 	mt76x02_mcu_cleanup(dev);
 }
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/debugfs.c b/drivers/net/wireless/mediatek/mt76/mt7915/debugfs.c
index 38f473d587c9..1049927faf24 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/debugfs.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/debugfs.c
@@ -21,7 +21,6 @@ static int mt7915_ser_trigger_set(void *data, u64 val)
 	switch (val) {
 	case SER_SET_RECOVER_L1:
 	case SER_SET_RECOVER_L2:
-		/* fall through */
 		ret = mt7915_mcu_set_ser(dev, SER_ENABLE, BIT(val), 0);
 		if (ret)
 			return ret;
@@ -292,15 +291,15 @@ mt7915_queues_read(struct seq_file *s, void *data)
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(queue_map); i++) {
-		struct mt76_sw_queue *q = &dev->mt76.q_tx[queue_map[i].id];
+		struct mt76_queue *q = dev->mt76.q_tx[queue_map[i].id];
 
-		if (!q->q)
+		if (!q)
 			continue;
 
 		seq_printf(s,
 			   "%s:	queued=%d head=%d tail=%d\n",
-			   queue_map[i].queue, q->q->queued, q->q->head,
-			   q->q->tail);
+			   queue_map[i].queue, q->queued, q->head,
+			   q->tail);
 	}
 
 	return 0;
@@ -400,7 +399,7 @@ static int mt7915_sta_fixed_rate_set(void *data, u64 rate)
 	struct ieee80211_sta *sta = data;
 	struct mt7915_sta *msta = (struct mt7915_sta *)sta->drv_priv;
 
-	return mt7915_mcu_set_fixed_rate(msta->vif->dev, sta, rate);
+	return mt7915_mcu_set_fixed_rate(msta->vif->phy->dev, sta, rate);
 }
 
 DEFINE_DEBUGFS_ATTRIBUTE(fops_fixed_rate, NULL,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/dma.c b/drivers/net/wireless/mediatek/mt76/mt7915/dma.c
index a8832c5e6004..cfa12c4c671f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/dma.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/dma.c
@@ -8,7 +8,6 @@
 static int
 mt7915_init_tx_queues(struct mt7915_dev *dev, int n_desc)
 {
-	struct mt76_sw_queue *q;
 	struct mt76_queue *hwq;
 	int err, i;
 
@@ -21,18 +20,14 @@ mt7915_init_tx_queues(struct mt7915_dev *dev, int n_desc)
 	if (err < 0)
 		return err;
 
-	for (i = 0; i < MT_TXQ_MCU; i++) {
-		q = &dev->mt76.q_tx[i];
-		INIT_LIST_HEAD(&q->swq);
-		q->q = hwq;
-	}
+	for (i = 0; i < MT_TXQ_MCU; i++)
+		dev->mt76.q_tx[i] = hwq;
 
 	return 0;
 }
 
 static int
-mt7915_init_mcu_queue(struct mt7915_dev *dev, struct mt76_sw_queue *q,
-		      int idx, int n_desc)
+mt7915_init_mcu_queue(struct mt7915_dev *dev, int qid, int idx, int n_desc)
 {
 	struct mt76_queue *hwq;
 	int err;
@@ -45,8 +40,7 @@ mt7915_init_mcu_queue(struct mt7915_dev *dev, struct mt76_sw_queue *q,
 	if (err < 0)
 		return err;
 
-	INIT_LIST_HEAD(&q->swq);
-	q->q = hwq;
+	dev->mt76.q_tx[qid] = hwq;
 
 	return 0;
 }
@@ -72,7 +66,7 @@ void mt7915_queue_rx_skb(struct mt76_dev *mdev, enum mt76_rxq_id q,
 			mt76_rx(&dev->mt76, q, skb);
 			return;
 		}
-		/* fall through */
+		fallthrough;
 	default:
 		dev_kfree_skb(skb);
 		break;
@@ -84,8 +78,6 @@ mt7915_tx_cleanup(struct mt7915_dev *dev)
 {
 	mt76_queue_tx_cleanup(dev, MT_TXQ_MCU, false);
 	mt76_queue_tx_cleanup(dev, MT_TXQ_MCU_WA, false);
-	mt76_queue_tx_cleanup(dev, MT_TXQ_PSD, false);
-	mt76_queue_tx_cleanup(dev, MT_TXQ_BE, false);
 }
 
 static int mt7915_poll_tx(struct napi_struct *napi, int budget)
@@ -97,13 +89,7 @@ static int mt7915_poll_tx(struct napi_struct *napi, int budget)
 	mt7915_tx_cleanup(dev);
 
 	if (napi_complete_done(napi, 0))
-		mt7915_irq_enable(dev, MT_INT_TX_DONE_ALL);
-
-	mt7915_tx_cleanup(dev);
-
-	mt7915_mac_sta_poll(dev);
-
-	tasklet_schedule(&dev->mt76.tx_tasklet);
+		mt7915_irq_enable(dev, MT_INT_TX_DONE_MCU);
 
 	return 0;
 }
@@ -138,12 +124,120 @@ void mt7915_dma_prefetch(struct mt7915_dev *dev)
 	mt76_wr(dev, MT_WFDMA1_RX_RING3_EXT_CTRL, PREFETCH(0x480, 0x0));
 }
 
+static u32 __mt7915_reg_addr(struct mt7915_dev *dev, u32 addr)
+{
+	static const struct {
+		u32 phys;
+		u32 mapped;
+		u32 size;
+	} fixed_map[] = {
+		{ 0x54000000, 0x02000, 0x1000 }, /* WFDMA PCIE0 MCU DMA0 */
+		{ 0x55000000, 0x03000, 0x1000 }, /* WFDMA PCIE0 MCU DMA1 */
+		{ 0x58000000, 0x06000, 0x1000 }, /* WFDMA PCIE1 MCU DMA0 (MEM_DMA) */
+		{ 0x59000000, 0x07000, 0x1000 }, /* WFDMA PCIE1 MCU DMA1 */
+		{ 0x7c000000, 0xf0000, 0x10000 }, /* CONN_INFRA */
+		{ 0x7c020000, 0xd0000, 0x10000 }, /* CONN_INFRA, WFDMA */
+		{ 0x80020000, 0xb0000, 0x10000 }, /* WF_TOP_MISC_OFF */
+		{ 0x81020000, 0xc0000, 0x10000 }, /* WF_TOP_MISC_ON */
+		{ 0x820c0000, 0x08000, 0x4000 }, /* WF_UMAC_TOP (PLE) */
+		{ 0x820c8000, 0x0c000, 0x2000 }, /* WF_UMAC_TOP (PSE) */
+		{ 0x820cc000, 0x0e000, 0x2000 }, /* WF_UMAC_TOP (PP) */
+		{ 0x820ce000, 0x21c00, 0x0200 }, /* WF_LMAC_TOP (WF_SEC) */
+		{ 0x820cf000, 0x22000, 0x1000 }, /* WF_LMAC_TOP (WF_PF) */
+		{ 0x820d0000, 0x30000, 0x10000 }, /* WF_LMAC_TOP (WF_WTBLON) */
+		{ 0x820e0000, 0x20000, 0x0400 }, /* WF_LMAC_TOP BN0 (WF_CFG) */
+		{ 0x820e1000, 0x20400, 0x0200 }, /* WF_LMAC_TOP BN0 (WF_TRB) */
+		{ 0x820e2000, 0x20800, 0x0400 }, /* WF_LMAC_TOP BN0 (WF_AGG) */
+		{ 0x820e3000, 0x20c00, 0x0400 }, /* WF_LMAC_TOP BN0 (WF_ARB) */
+		{ 0x820e4000, 0x21000, 0x0400 }, /* WF_LMAC_TOP BN0 (WF_TMAC) */
+		{ 0x820e5000, 0x21400, 0x0800 }, /* WF_LMAC_TOP BN0 (WF_RMAC) */
+		{ 0x820e7000, 0x21e00, 0x0200 }, /* WF_LMAC_TOP BN0 (WF_DMA) */
+		{ 0x820e9000, 0x23400, 0x0200 }, /* WF_LMAC_TOP BN0 (WF_WTBLOFF) */
+		{ 0x820ea000, 0x24000, 0x0200 }, /* WF_LMAC_TOP BN0 (WF_ETBF) */
+		{ 0x820eb000, 0x24200, 0x0400 }, /* WF_LMAC_TOP BN0 (WF_LPON) */
+		{ 0x820ec000, 0x24600, 0x0200 }, /* WF_LMAC_TOP BN0 (WF_INT) */
+		{ 0x820ed000, 0x24800, 0x0800 }, /* WF_LMAC_TOP BN0 (WF_MIB) */
+		{ 0x820f0000, 0xa0000, 0x0400 }, /* WF_LMAC_TOP BN1 (WF_CFG) */
+		{ 0x820f1000, 0xa0600, 0x0200 }, /* WF_LMAC_TOP BN1 (WF_TRB) */
+		{ 0x820f2000, 0xa0800, 0x0400 }, /* WF_LMAC_TOP BN1 (WF_AGG) */
+		{ 0x820f3000, 0xa0c00, 0x0400 }, /* WF_LMAC_TOP BN1 (WF_ARB) */
+		{ 0x820f4000, 0xa1000, 0x0400 }, /* WF_LMAC_TOP BN1 (WF_TMAC) */
+		{ 0x820f5000, 0xa1400, 0x0800 }, /* WF_LMAC_TOP BN1 (WF_RMAC) */
+		{ 0x820f7000, 0xa1e00, 0x0200 }, /* WF_LMAC_TOP BN1 (WF_DMA) */
+		{ 0x820f9000, 0xa3400, 0x0200 }, /* WF_LMAC_TOP BN1 (WF_WTBLOFF) */
+		{ 0x820fa000, 0xa4000, 0x0200 }, /* WF_LMAC_TOP BN1 (WF_ETBF) */
+		{ 0x820fb000, 0xa4200, 0x0400 }, /* WF_LMAC_TOP BN1 (WF_LPON) */
+		{ 0x820fc000, 0xa4600, 0x0200 }, /* WF_LMAC_TOP BN1 (WF_INT) */
+		{ 0x820fd000, 0xa4800, 0x0800 }, /* WF_LMAC_TOP BN1 (WF_MIB) */
+	};
+	int i;
+
+	if (addr < 0x100000)
+		return addr;
+
+	for (i = 0; i < ARRAY_SIZE(fixed_map); i++) {
+		u32 ofs;
+
+		if (addr < fixed_map[i].phys)
+			continue;
+
+		ofs = addr - fixed_map[i].phys;
+		if (ofs > fixed_map[i].size)
+			continue;
+
+		return fixed_map[i].mapped + ofs;
+	}
+
+	if ((addr >= 0x18000000 && addr < 0x18c00000) ||
+	    (addr >= 0x70000000 && addr < 0x78000000) ||
+	    (addr >= 0x7c000000 && addr < 0x7c400000))
+		return mt7915_reg_map_l1(dev, addr);
+
+	return mt7915_reg_map_l2(dev, addr);
+}
+
+static u32 mt7915_rr(struct mt76_dev *mdev, u32 offset)
+{
+	struct mt7915_dev *dev = container_of(mdev, struct mt7915_dev, mt76);
+	u32 addr = __mt7915_reg_addr(dev, offset);
+
+	return dev->bus_ops->rr(mdev, addr);
+}
+
+static void mt7915_wr(struct mt76_dev *mdev, u32 offset, u32 val)
+{
+	struct mt7915_dev *dev = container_of(mdev, struct mt7915_dev, mt76);
+	u32 addr = __mt7915_reg_addr(dev, offset);
+
+	dev->bus_ops->wr(mdev, addr, val);
+}
+
+static u32 mt7915_rmw(struct mt76_dev *mdev, u32 offset, u32 mask, u32 val)
+{
+	struct mt7915_dev *dev = container_of(mdev, struct mt7915_dev, mt76);
+	u32 addr = __mt7915_reg_addr(dev, offset);
+
+	return dev->bus_ops->rmw(mdev, addr, mask, val);
+}
+
 int mt7915_dma_init(struct mt7915_dev *dev)
 {
 	/* Increase buffer size to receive large VHT/HE MPDUs */
+	struct mt76_bus_ops *bus_ops;
 	int rx_buf_size = MT_RX_BUF_SIZE * 2;
 	int ret;
 
+	dev->bus_ops = dev->mt76.bus;
+	bus_ops = devm_kmemdup(dev->mt76.dev, dev->bus_ops, sizeof(*bus_ops),
+			       GFP_KERNEL);
+	if (!bus_ops)
+		return -ENOMEM;
+
+	bus_ops->rr = mt7915_rr;
+	bus_ops->wr = mt7915_wr;
+	bus_ops->rmw = mt7915_rmw;
+	dev->mt76.bus = bus_ops;
+
 	mt76_dma_attach(&dev->mt76);
 
 	/* configure global setting */
@@ -168,22 +262,19 @@ int mt7915_dma_init(struct mt7915_dev *dev)
 		return ret;
 
 	/* command to WM */
-	ret = mt7915_init_mcu_queue(dev, &dev->mt76.q_tx[MT_TXQ_MCU],
-				    MT7915_TXQ_MCU_WM,
+	ret = mt7915_init_mcu_queue(dev, MT_TXQ_MCU, MT7915_TXQ_MCU_WM,
 				    MT7915_TX_MCU_RING_SIZE);
 	if (ret)
 		return ret;
 
 	/* command to WA */
-	ret = mt7915_init_mcu_queue(dev, &dev->mt76.q_tx[MT_TXQ_MCU_WA],
-				    MT7915_TXQ_MCU_WA,
+	ret = mt7915_init_mcu_queue(dev, MT_TXQ_MCU_WA, MT7915_TXQ_MCU_WA,
 				    MT7915_TX_MCU_RING_SIZE);
 	if (ret)
 		return ret;
 
 	/* firmware download */
-	ret = mt7915_init_mcu_queue(dev, &dev->mt76.q_tx[MT_TXQ_FWDL],
-				    MT7915_TXQ_FWDL,
+	ret = mt7915_init_mcu_queue(dev, MT_TXQ_FWDL, MT7915_TXQ_FWDL,
 				    MT7915_TX_FWDL_RING_SIZE);
 	if (ret)
 		return ret;
@@ -248,7 +339,7 @@ int mt7915_dma_init(struct mt7915_dev *dev)
 		 MT_WFDMA1_GLO_CFG_TX_DMA_EN | MT_WFDMA1_GLO_CFG_RX_DMA_EN);
 
 	/* enable interrupts for TX/RX rings */
-	mt7915_irq_enable(dev, MT_INT_RX_DONE_ALL | MT_INT_TX_DONE_ALL |
+	mt7915_irq_enable(dev, MT_INT_RX_DONE_ALL | MT_INT_TX_DONE_MCU |
 			  MT_INT_MCU_CMD);
 
 	return 0;
@@ -281,6 +372,5 @@ void mt7915_dma_cleanup(struct mt7915_dev *dev)
 		 MT_WFDMA0_RST_DMASHDL_ALL_RST |
 		 MT_WFDMA0_RST_LOGIC_RST);
 
-	tasklet_kill(&dev->mt76.tx_tasklet);
 	mt76_dma_cleanup(&dev->mt76);
 }
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/init.c b/drivers/net/wireless/mediatek/mt76/mt7915/init.c
index e90d0087e377..0232b66acb4f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/init.c
@@ -135,6 +135,12 @@ static int mt7915_init_hardware(struct mt7915_dev *dev)
 
 	set_bit(MT76_STATE_INITIALIZED, &dev->mphy.state);
 
+	/*
+	 * force firmware operation mode into normal state,
+	 * which should be set before firmware download stage.
+	 */
+	mt76_wr(dev, MT_SWDEF_MODE, MT_SWDEF_NORMAL_MODE);
+
 	ret = mt7915_mcu_init(dev);
 	if (ret)
 		return ret;
@@ -612,6 +618,7 @@ int mt7915_register_ext_phy(struct mt7915_dev *dev)
 	mphy->antenna_mask = BIT(hweight8(phy->chainmask)) - 1;
 	mt7915_init_wiphy(mphy->hw);
 
+	INIT_LIST_HEAD(&phy->stats_list);
 	INIT_DELAYED_WORK(&phy->mac_work, mt7915_mac_work);
 
 	/*
@@ -652,7 +659,10 @@ int mt7915_register_device(struct mt7915_dev *dev)
 	dev->phy.dev = dev;
 	dev->phy.mt76 = &dev->mt76.phy;
 	dev->mt76.phy.priv = &dev->phy;
+	INIT_LIST_HEAD(&dev->phy.stats_list);
+	INIT_WORK(&dev->rc_work, mt7915_mac_sta_rc_work);
 	INIT_DELAYED_WORK(&dev->phy.mac_work, mt7915_mac_work);
+	INIT_LIST_HEAD(&dev->sta_rc_list);
 	INIT_LIST_HEAD(&dev->sta_poll_list);
 	spin_lock_init(&dev->sta_poll_lock);
 
@@ -699,8 +709,12 @@ void mt7915_unregister_device(struct mt7915_dev *dev)
 	spin_lock_bh(&dev->token_lock);
 	idr_for_each_entry(&dev->token, txwi, id) {
 		mt7915_txp_skb_unmap(&dev->mt76, txwi);
-		if (txwi->skb)
-			dev_kfree_skb_any(txwi->skb);
+		if (txwi->skb) {
+			struct ieee80211_hw *hw;
+
+			hw = mt76_tx_status_get_hw(&dev->mt76, txwi->skb);
+			ieee80211_free_txskb(hw, txwi->skb);
+		}
 		mt76_put_txwi(&dev->mt76, txwi);
 	}
 	spin_unlock_bh(&dev->token_lock);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
index 6825afca1efb..6f159d99a596 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
@@ -88,17 +88,16 @@ bool mt7915_mac_wtbl_update(struct mt7915_dev *dev, int idx, u32 mask)
 			 0, 5000);
 }
 
-static u32 mt7915_mac_wtbl_lmac_read(struct mt7915_dev *dev, u16 wcid,
-				     u16 addr)
+static u32 mt7915_mac_wtbl_lmac_addr(struct mt7915_dev *dev, u16 wcid)
 {
 	mt76_wr(dev, MT_WTBLON_TOP_WDUCR,
 		FIELD_PREP(MT_WTBLON_TOP_WDUCR_GROUP, (wcid >> 7)));
 
-	return mt76_rr(dev, MT_WTBL_LMAC_OFFS(wcid, addr));
+	return MT_WTBL_LMAC_OFFS(wcid, 0);
 }
 
 /* TODO: use txfree airtime info to avoid runtime accessing in the long run */
-void mt7915_mac_sta_poll(struct mt7915_dev *dev)
+static void mt7915_mac_sta_poll(struct mt7915_dev *dev)
 {
 	static const u8 ac_to_tid[] = {
 		[IEEE80211_AC_BE] = 0,
@@ -106,47 +105,50 @@ void mt7915_mac_sta_poll(struct mt7915_dev *dev)
 		[IEEE80211_AC_VI] = 4,
 		[IEEE80211_AC_VO] = 6
 	};
-	static const u8 hw_queue_map[] = {
-		[IEEE80211_AC_BK] = 0,
-		[IEEE80211_AC_BE] = 1,
-		[IEEE80211_AC_VI] = 2,
-		[IEEE80211_AC_VO] = 3,
-	};
 	struct ieee80211_sta *sta;
 	struct mt7915_sta *msta;
 	u32 tx_time[IEEE80211_NUM_ACS], rx_time[IEEE80211_NUM_ACS];
+	LIST_HEAD(sta_poll_list);
 	int i;
 
+	spin_lock_bh(&dev->sta_poll_lock);
+	list_splice_init(&dev->sta_poll_list, &sta_poll_list);
+	spin_unlock_bh(&dev->sta_poll_lock);
+
 	rcu_read_lock();
 
 	while (true) {
 		bool clear = false;
+		u32 addr;
 		u16 idx;
 
 		spin_lock_bh(&dev->sta_poll_lock);
-		if (list_empty(&dev->sta_poll_list)) {
+		if (list_empty(&sta_poll_list)) {
 			spin_unlock_bh(&dev->sta_poll_lock);
 			break;
 		}
-		msta = list_first_entry(&dev->sta_poll_list,
+		msta = list_first_entry(&sta_poll_list,
 					struct mt7915_sta, poll_list);
 		list_del_init(&msta->poll_list);
 		spin_unlock_bh(&dev->sta_poll_lock);
 
-		for (i = 0, idx = msta->wcid.idx; i < IEEE80211_NUM_ACS; i++) {
+		idx = msta->wcid.idx;
+		addr = mt7915_mac_wtbl_lmac_addr(dev, idx) + 20 * 4;
+
+		for (i = 0; i < IEEE80211_NUM_ACS; i++) {
 			u32 tx_last = msta->airtime_ac[i];
-			u32 rx_last = msta->airtime_ac[i + IEEE80211_NUM_ACS];
+			u32 rx_last = msta->airtime_ac[i + 4];
+
+			msta->airtime_ac[i] = mt76_rr(dev, addr);
+			msta->airtime_ac[i + 4] = mt76_rr(dev, addr + 4);
 
-			msta->airtime_ac[i] =
-				mt7915_mac_wtbl_lmac_read(dev, idx, 20 + i);
-			msta->airtime_ac[i + IEEE80211_NUM_ACS] =
-				mt7915_mac_wtbl_lmac_read(dev, idx, 21 + i);
 			tx_time[i] = msta->airtime_ac[i] - tx_last;
-			rx_time[i] = msta->airtime_ac[i + IEEE80211_NUM_ACS] -
-				     rx_last;
+			rx_time[i] = msta->airtime_ac[i + 4] - rx_last;
 
 			if ((tx_last | rx_last) & BIT(30))
 				clear = true;
+
+			addr += 8;
 		}
 
 		if (clear) {
@@ -161,8 +163,9 @@ void mt7915_mac_sta_poll(struct mt7915_dev *dev)
 		sta = container_of((void *)msta, struct ieee80211_sta,
 				   drv_priv);
 		for (i = 0; i < IEEE80211_NUM_ACS; i++) {
-			u32 tx_cur = tx_time[i];
-			u32 rx_cur = rx_time[hw_queue_map[i]];
+			u8 q = mt7915_lmac_mapping(dev, i);
+			u32 tx_cur = tx_time[q];
+			u32 rx_cur = rx_time[q];
 			u8 tid = ac_to_tid[i];
 
 			if (!tx_cur && !rx_cur)
@@ -468,7 +471,7 @@ int mt7915_mac_fill_rx(struct mt7915_dev *dev, struct sk_buff *skb)
 			switch (mode) {
 			case MT_PHY_TYPE_CCK:
 				cck = true;
-				/* fall through */
+				fallthrough;
 			case MT_PHY_TYPE_OFDM:
 				i = mt76_get_rate(&dev->mt76, sband, i, cck);
 				break;
@@ -487,7 +490,7 @@ int mt7915_mac_fill_rx(struct mt7915_dev *dev, struct sk_buff *skb)
 				break;
 			case MT_PHY_TYPE_HE_MU:
 				status->flag |= RX_FLAG_RADIOTAP_HE_MU;
-				/* fall through */
+				fallthrough;
 			case MT_PHY_TYPE_HE_SU:
 			case MT_PHY_TYPE_HE_EXT_SU:
 			case MT_PHY_TYPE_HE_TB:
@@ -565,13 +568,15 @@ void mt7915_mac_write_txwi(struct mt7915_dev *dev, __le32 *txwi,
 {
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
 	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
+	struct ieee80211_mgmt *mgmt = (struct ieee80211_mgmt *)skb->data;
 	bool multicast = is_multicast_ether_addr(hdr->addr1);
 	struct ieee80211_vif *vif = info->control.vif;
 	struct mt76_phy *mphy = &dev->mphy;
 	bool ext_phy = info->hw_queue & MT_TX_HW_QUEUE_EXT_PHY;
 	u8 fc_type, fc_stype, p_fmt, q_idx, omac_idx = 0, wmm_idx = 0;
 	__le16 fc = hdr->frame_control;
-	u16 tx_count = 4, seqno = 0;
+	u16 tx_count = 15, seqno = 0;
+	u8 tid = skb->priority & IEEE80211_QOS_CTL_TID_MASK;
 	u32 val;
 
 	if (vif) {
@@ -587,6 +592,10 @@ void mt7915_mac_write_txwi(struct mt7915_dev *dev, __le32 *txwi,
 	fc_type = (le16_to_cpu(fc) & IEEE80211_FCTL_FTYPE) >> 2;
 	fc_stype = (le16_to_cpu(fc) & IEEE80211_FCTL_STYPE) >> 4;
 
+	txwi[4] = 0;
+	txwi[5] = 0;
+	txwi[6] = 0;
+
 	if (beacon) {
 		p_fmt = MT_TX_TYPE_FW;
 		q_idx = MT_LMAC_BCN0;
@@ -599,6 +608,20 @@ void mt7915_mac_write_txwi(struct mt7915_dev *dev, __le32 *txwi,
 			mt7915_lmac_mapping(dev, skb_get_queue_mapping(skb));
 	}
 
+	if (ieee80211_is_action(fc) &&
+	    mgmt->u.action.category == WLAN_CATEGORY_BACK &&
+	    mgmt->u.action.u.addba_req.action_code == WLAN_ACTION_ADDBA_REQ) {
+		u16 capab = le16_to_cpu(mgmt->u.action.u.addba_req.capab);
+
+		txwi[5] |= cpu_to_le32(MT_TXD5_ADD_BA);
+		tid = (capab >> 2) & IEEE80211_QOS_CTL_TID_MASK;
+	} else if (ieee80211_is_back_req(hdr->frame_control)) {
+		struct ieee80211_bar *bar = (struct ieee80211_bar *)hdr;
+		u16 control = le16_to_cpu(bar->control);
+
+		tid = FIELD_GET(IEEE80211_BAR_CTRL_TID_INFO_MASK, control);
+	}
+
 	val = FIELD_PREP(MT_TXD0_TX_BYTES, skb->len + MT_TXD_SIZE) |
 	      FIELD_PREP(MT_TXD0_PKT_FMT, p_fmt) |
 	      FIELD_PREP(MT_TXD0_Q_IDX, q_idx);
@@ -609,8 +632,7 @@ void mt7915_mac_write_txwi(struct mt7915_dev *dev, __le32 *txwi,
 	      FIELD_PREP(MT_TXD1_HDR_FORMAT, MT_HDR_FORMAT_802_11) |
 	      FIELD_PREP(MT_TXD1_HDR_INFO,
 			 ieee80211_get_hdrlen_from_skb(skb) / 2) |
-	      FIELD_PREP(MT_TXD1_TID,
-			 skb->priority & IEEE80211_QOS_CTL_TID_MASK) |
+	      FIELD_PREP(MT_TXD1_TID, tid) |
 	      FIELD_PREP(MT_TXD1_OWN_MAC, omac_idx);
 
 	if (ext_phy && q_idx >= MT_LMAC_ALTX0 && q_idx <= MT_LMAC_BCN0)
@@ -634,10 +656,6 @@ void mt7915_mac_write_txwi(struct mt7915_dev *dev, __le32 *txwi,
 	}
 	txwi[2] = cpu_to_le32(val);
 
-	txwi[4] = 0;
-	txwi[5] = 0;
-	txwi[6] = 0;
-
 	if (!ieee80211_is_data(fc) || multicast) {
 		u16 rate;
 
@@ -665,20 +683,24 @@ void mt7915_mac_write_txwi(struct mt7915_dev *dev, __le32 *txwi,
 
 	val = FIELD_PREP(MT_TXD7_TYPE, fc_type) |
 	      FIELD_PREP(MT_TXD7_SUB_TYPE, fc_stype);
+	if (wcid->amsdu)
+		val |= MT_TXD7_HW_AMSDU;
 	txwi[7] = cpu_to_le32(val);
 
 	val = FIELD_PREP(MT_TXD3_REM_TX_COUNT, tx_count);
-	if (ieee80211_is_data_qos(fc)) {
-		seqno = IEEE80211_SEQ_TO_SN(le16_to_cpu(hdr->seq_ctrl));
-		val |= MT_TXD3_SN_VALID;
-	} else if (ieee80211_is_back_req(fc)) {
-		struct ieee80211_bar *bar;
-
-		bar = (struct ieee80211_bar *)skb->data;
-		seqno = IEEE80211_SEQ_TO_SN(le16_to_cpu(bar->start_seq_num));
-		val |= MT_TXD3_SN_VALID;
+	if (info->flags & IEEE80211_TX_CTL_INJECTED) {
+		seqno = le16_to_cpu(hdr->seq_ctrl);
+
+		if (ieee80211_is_back_req(hdr->frame_control)) {
+			struct ieee80211_bar *bar;
+
+			bar = (struct ieee80211_bar *)skb->data;
+			seqno = le16_to_cpu(bar->start_seq_num);
+		}
+
+		val |= MT_TXD3_SN_VALID |
+		       FIELD_PREP(MT_TXD3_SEQ, IEEE80211_SEQ_TO_SN(seqno));
 	}
-	val |= FIELD_PREP(MT_TXD3_SEQ, seqno);
 	txwi[3] |= cpu_to_le32(val);
 }
 
@@ -715,6 +737,7 @@ int mt7915_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr,
 
 	/* pass partial skb header to fw */
 	tx_info->buf[1].len = MT_CT_PARSE_LEN;
+	tx_info->buf[1].skip_unmap = true;
 	tx_info->nbuf = MT_CT_DMA_BUF_NUM;
 
 	txp->flags = cpu_to_le16(MT_CT_INFO_APPLY_TXD);
@@ -747,45 +770,29 @@ int mt7915_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr,
 	return 0;
 }
 
-static inline bool
-mt7915_tx_check_aggr_tid(struct mt7915_sta *msta, u8 tid)
-{
-	bool ret = false;
-
-	spin_lock_bh(&msta->ampdu_lock);
-	if (msta->ampdu_state[tid] == MT7915_AGGR_STOP)
-		ret = true;
-	spin_unlock_bh(&msta->ampdu_lock);
-
-	return ret;
-}
-
 static void
-mt7915_tx_check_aggr(struct ieee80211_sta *sta, struct sk_buff *skb)
+mt7915_tx_check_aggr(struct ieee80211_sta *sta, __le32 *txwi)
 {
-	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
 	struct mt7915_sta *msta;
-	u16 tid;
-
-	if (!sta->ht_cap.ht_supported)
-		return;
+	u16 fc, tid;
+	u32 val;
 
-	if (skb_get_queue_mapping(skb) == IEEE80211_AC_VO)
+	if (!sta || !sta->ht_cap.ht_supported)
 		return;
 
-	if (unlikely(!ieee80211_is_data_qos(hdr->frame_control)))
+	tid = FIELD_GET(MT_TXD1_TID, le32_to_cpu(txwi[1]));
+	if (tid >= 6) /* skip VO queue */
 		return;
 
-	if (unlikely(skb->protocol == cpu_to_be16(ETH_P_PAE)))
+	val = le32_to_cpu(txwi[2]);
+	fc = FIELD_GET(MT_TXD2_FRAME_TYPE, val) << 2 |
+	     FIELD_GET(MT_TXD2_SUB_TYPE, val) << 4;
+	if (unlikely(fc != (IEEE80211_FTYPE_DATA | IEEE80211_STYPE_QOS_DATA)))
 		return;
 
 	msta = (struct mt7915_sta *)sta->drv_priv;
-	tid = ieee80211_get_tid(hdr);
-
-	if (mt7915_tx_check_aggr_tid(msta, tid)) {
+	if (!test_and_set_bit(tid, &msta->ampdu_state))
 		ieee80211_start_tx_ba_session(sta, tid, 0);
-		mt7915_set_aggr_state(msta, tid, MT7915_AGGR_PROGRESS);
-	}
 }
 
 static inline void
@@ -822,8 +829,6 @@ mt7915_tx_complete_status(struct mt76_dev *mdev, struct sk_buff *skb,
 
 	if (info->flags & IEEE80211_TX_CTL_AMPDU)
 		info->flags |= IEEE80211_TX_STAT_AMPDU;
-	else if (sta)
-		mt7915_tx_check_aggr(sta, skb);
 
 	if (stat)
 		ieee80211_tx_info_clear_status(info);
@@ -841,7 +846,7 @@ mt7915_tx_complete_status(struct mt76_dev *mdev, struct sk_buff *skb,
 	if (sta || !(info->flags & IEEE80211_TX_CTL_NO_ACK))
 		mt7915_tx_status(sta, hw, info, NULL);
 
-	dev_kfree_skb(skb);
+	ieee80211_free_txskb(hw, skb);
 }
 
 void mt7915_txp_skb_unmap(struct mt76_dev *dev,
@@ -864,6 +869,10 @@ void mt7915_mac_tx_free(struct mt7915_dev *dev, struct sk_buff *skb)
 	struct ieee80211_sta *sta = NULL;
 	u8 i, count;
 
+	/* clean DMA queues and unmap buffers first */
+	mt76_queue_tx_cleanup(dev, MT_TXQ_PSD, false);
+	mt76_queue_tx_cleanup(dev, MT_TXQ_BE, false);
+
 	/*
 	 * TODO: MT_TX_FREE_LATENCY is msdu time from the TXD is queued into PLE,
 	 * to the time ack is received or dropped by hw (air + hw queue time).
@@ -880,6 +889,7 @@ void mt7915_mac_tx_free(struct mt7915_dev *dev, struct sk_buff *skb)
 		 */
 		if (info & MT_TX_FREE_PAIR) {
 			struct mt7915_sta *msta;
+			struct mt7915_phy *phy;
 			struct mt76_wcid *wcid;
 			u16 idx;
 
@@ -891,8 +901,13 @@ void mt7915_mac_tx_free(struct mt7915_dev *dev, struct sk_buff *skb)
 				continue;
 
 			msta = container_of(wcid, struct mt7915_sta, wcid);
-			ieee80211_queue_work(mt76_hw(dev), &msta->stats_work);
-			continue;
+			phy = msta->vif->phy;
+			spin_lock_bh(&dev->sta_poll_lock);
+			if (list_empty(&msta->stats_list))
+				list_add_tail(&msta->stats_list, &phy->stats_list);
+			if (list_empty(&msta->poll_list))
+				list_add_tail(&msta->poll_list, &dev->sta_poll_list);
+			spin_unlock_bh(&dev->sta_poll_lock);
 		}
 
 		msdu = FIELD_GET(MT_TX_FREE_MSDU_ID, info);
@@ -907,6 +922,21 @@ void mt7915_mac_tx_free(struct mt7915_dev *dev, struct sk_buff *skb)
 
 		mt7915_txp_skb_unmap(mdev, txwi);
 		if (txwi->skb) {
+			struct ieee80211_tx_info *info = IEEE80211_SKB_CB(txwi->skb);
+			void *txwi_ptr = mt76_get_txwi_ptr(mdev, txwi);
+
+			if (likely(txwi->skb->protocol != cpu_to_be16(ETH_P_PAE)))
+				mt7915_tx_check_aggr(sta, txwi_ptr);
+
+			if (sta && !info->tx_time_est) {
+				struct mt76_wcid *wcid = (struct mt76_wcid *)sta->drv_priv;
+				int pending;
+
+				pending = atomic_dec_return(&wcid->non_aql_packets);
+				if (pending < 0)
+					atomic_cmpxchg(&wcid->non_aql_packets, pending, 0);
+			}
+
 			mt7915_tx_complete_status(mdev, txwi->skb, sta, stat);
 			txwi->skb = NULL;
 		}
@@ -914,10 +944,12 @@ void mt7915_mac_tx_free(struct mt7915_dev *dev, struct sk_buff *skb)
 		mt76_put_txwi(mdev, txwi);
 	}
 	dev_kfree_skb(skb);
+
+	mt7915_mac_sta_poll(dev);
+	mt76_worker_schedule(&dev->mt76.tx_worker);
 }
 
-void mt7915_tx_complete_skb(struct mt76_dev *mdev, enum mt76_txq_id qid,
-			    struct mt76_queue_entry *e)
+void mt7915_tx_complete_skb(struct mt76_dev *mdev, struct mt76_queue_entry *e)
 {
 	struct mt7915_dev *dev;
 
@@ -1186,7 +1218,7 @@ void mt7915_mac_reset_work(struct work_struct *work)
 	if (ext_phy)
 		mt76_txq_schedule_all(ext_phy);
 
-	tasklet_disable(&dev->mt76.tx_tasklet);
+	mt76_worker_disable(&dev->mt76.tx_worker);
 	napi_disable(&dev->mt76.napi[0]);
 	napi_disable(&dev->mt76.napi[1]);
 	napi_disable(&dev->mt76.napi[2]);
@@ -1206,7 +1238,7 @@ void mt7915_mac_reset_work(struct work_struct *work)
 	clear_bit(MT76_MCU_RESET, &dev->mphy.state);
 	clear_bit(MT76_RESET, &dev->mphy.state);
 
-	tasklet_enable(&dev->mt76.tx_tasklet);
+	mt76_worker_enable(&dev->mt76.tx_worker);
 	napi_enable(&dev->mt76.tx_napi);
 	napi_schedule(&dev->mt76.tx_napi);
 
@@ -1281,39 +1313,63 @@ mt7915_mac_update_mib_stats(struct mt7915_phy *phy)
 	}
 }
 
-void mt7915_mac_sta_stats_work(struct work_struct *work)
+static void
+mt7915_mac_sta_stats_work(struct mt7915_phy *phy)
+{
+	struct mt7915_dev *dev = phy->dev;
+	struct mt7915_sta *msta;
+	LIST_HEAD(list);
+
+	spin_lock_bh(&dev->sta_poll_lock);
+	list_splice_init(&phy->stats_list, &list);
+
+	while (!list_empty(&list)) {
+		msta = list_first_entry(&list, struct mt7915_sta, stats_list);
+		list_del_init(&msta->stats_list);
+		spin_unlock_bh(&dev->sta_poll_lock);
+
+		/* use MT_TX_FREE_RATE to report Tx rate for further devices */
+		mt7915_mcu_get_rate_info(dev, RATE_CTRL_RU_INFO, msta->wcid.idx);
+
+		spin_lock_bh(&dev->sta_poll_lock);
+	}
+
+	spin_unlock_bh(&dev->sta_poll_lock);
+}
+
+void mt7915_mac_sta_rc_work(struct work_struct *work)
 {
+	struct mt7915_dev *dev = container_of(work, struct mt7915_dev, rc_work);
 	struct ieee80211_sta *sta;
 	struct ieee80211_vif *vif;
-	struct mt7915_sta_stats *stats;
 	struct mt7915_sta *msta;
-	struct mt7915_dev *dev;
+	u32 changed;
+	LIST_HEAD(list);
 
-	msta = container_of(work, struct mt7915_sta, stats_work);
-	sta = container_of((void *)msta, struct ieee80211_sta, drv_priv);
-	vif = container_of((void *)msta->vif, struct ieee80211_vif, drv_priv);
-	dev = msta->vif->dev;
-	stats = &msta->stats;
+	spin_lock_bh(&dev->sta_poll_lock);
+	list_splice_init(&dev->sta_rc_list, &list);
 
-	/* use MT_TX_FREE_RATE to report Tx rate for further devices */
-	if (time_after(jiffies, stats->jiffies + HZ)) {
-		mt7915_mcu_get_rate_info(dev, RATE_CTRL_RU_INFO,
-					 msta->wcid.idx);
+	while (!list_empty(&list)) {
+		msta = list_first_entry(&list, struct mt7915_sta, rc_list);
+		list_del_init(&msta->rc_list);
+		changed = msta->stats.changed;
+		msta->stats.changed = 0;
+		spin_unlock_bh(&dev->sta_poll_lock);
 
-		stats->jiffies = jiffies;
-	}
+		sta = container_of((void *)msta, struct ieee80211_sta, drv_priv);
+		vif = container_of((void *)msta->vif, struct ieee80211_vif, drv_priv);
 
-	if (test_and_clear_bit(IEEE80211_RC_SUPP_RATES_CHANGED |
+		if (changed & (IEEE80211_RC_SUPP_RATES_CHANGED |
 			       IEEE80211_RC_NSS_CHANGED |
-			       IEEE80211_RC_BW_CHANGED, &stats->changed))
-		mt7915_mcu_add_rate_ctrl(dev, vif, sta);
+			       IEEE80211_RC_BW_CHANGED))
+			mt7915_mcu_add_rate_ctrl(dev, vif, sta);
 
-	if (test_and_clear_bit(IEEE80211_RC_SMPS_CHANGED, &stats->changed))
-		mt7915_mcu_add_smps(dev, vif, sta);
+		if (changed & IEEE80211_RC_SMPS_CHANGED)
+			mt7915_mcu_add_smps(dev, vif, sta);
+
+		spin_lock_bh(&dev->sta_poll_lock);
+	}
 
-	spin_lock_bh(&dev->sta_poll_lock);
-	if (list_empty(&msta->poll_list))
-		list_add_tail(&msta->poll_list, &dev->sta_poll_list);
 	spin_unlock_bh(&dev->sta_poll_lock);
 }
 
@@ -1335,6 +1391,11 @@ void mt7915_mac_work(struct work_struct *work)
 		mt7915_mac_update_mib_stats(phy);
 	}
 
+	if (++phy->sta_work_count == 10) {
+		phy->sta_work_count = 0;
+		mt7915_mac_sta_stats_work(phy);
+	};
+
 	mutex_unlock(&mdev->mutex);
 
 	ieee80211_queue_delayed_work(phy->mt76->hw, &phy->mac_work,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/main.c b/drivers/net/wireless/mediatek/mt76/mt7915/main.c
index f95a0b55c4a2..c48158392057 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/main.c
@@ -137,7 +137,7 @@ static int mt7915_add_interface(struct ieee80211_hw *hw,
 		goto out;
 	}
 	mvif->omac_idx = idx;
-	mvif->dev = dev;
+	mvif->phy = phy;
 	mvif->band_idx = ext_phy;
 
 	if (ext_phy)
@@ -155,6 +155,8 @@ static int mt7915_add_interface(struct ieee80211_hw *hw,
 
 	idx = MT7915_WTBL_RESERVED - mvif->idx;
 
+	INIT_LIST_HEAD(&mvif->sta.rc_list);
+	INIT_LIST_HEAD(&mvif->sta.stats_list);
 	INIT_LIST_HEAD(&mvif->sta.poll_list);
 	mvif->sta.wcid.idx = idx;
 	mvif->sta.wcid.ext_phy = mvif->band_idx;
@@ -167,7 +169,6 @@ static int mt7915_add_interface(struct ieee80211_hw *hw,
 	if (vif->txq) {
 		mtxq = (struct mt76_txq *)vif->txq->drv_priv;
 		mtxq->wcid = &mvif->sta.wcid;
-		mt76_txq_init(&dev->mt76, vif->txq);
 	}
 
 out:
@@ -190,8 +191,6 @@ static void mt7915_remove_interface(struct ieee80211_hw *hw,
 	mt7915_mcu_add_dev_info(dev, vif, false);
 
 	rcu_assign_pointer(dev->mt76.wcid[idx], NULL);
-	if (vif->txq)
-		mt76_txq_remove(&dev->mt76, vif->txq);
 
 	mutex_lock(&dev->mt76.mutex);
 	phy->mt76->vif_mask &= ~BIT(mvif->idx);
@@ -493,9 +492,9 @@ int mt7915_mac_sta_add(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 	if (idx < 0)
 		return -ENOSPC;
 
+	INIT_LIST_HEAD(&msta->rc_list);
+	INIT_LIST_HEAD(&msta->stats_list);
 	INIT_LIST_HEAD(&msta->poll_list);
-	INIT_WORK(&msta->stats_work, mt7915_mac_sta_stats_work);
-	spin_lock_init(&msta->ampdu_lock);
 	msta->vif = mvif;
 	msta->wcid.sta = 1;
 	msta->wcid.idx = idx;
@@ -528,6 +527,10 @@ void mt7915_mac_sta_remove(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 	spin_lock_bh(&dev->sta_poll_lock);
 	if (!list_empty(&msta->poll_list))
 		list_del_init(&msta->poll_list);
+	if (!list_empty(&msta->stats_list))
+		list_del_init(&msta->stats_list);
+	if (!list_empty(&msta->rc_list))
+		list_del_init(&msta->rc_list);
 	spin_unlock_bh(&dev->sta_poll_lock);
 }
 
@@ -603,23 +606,21 @@ mt7915_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	case IEEE80211_AMPDU_TX_OPERATIONAL:
 		mtxq->aggr = true;
 		mtxq->send_bar = false;
-		mt7915_set_aggr_state(msta, tid, MT7915_AGGR_OPERATIONAL);
 		mt7915_mcu_add_tx_ba(dev, params, true);
 		break;
 	case IEEE80211_AMPDU_TX_STOP_FLUSH:
 	case IEEE80211_AMPDU_TX_STOP_FLUSH_CONT:
 		mtxq->aggr = false;
-		mt7915_set_aggr_state(msta, tid, MT7915_AGGR_STOP);
+		clear_bit(tid, &msta->ampdu_state);
 		mt7915_mcu_add_tx_ba(dev, params, false);
 		break;
 	case IEEE80211_AMPDU_TX_START:
-		mtxq->agg_ssn = IEEE80211_SN_TO_SEQ(ssn);
-		mt7915_set_aggr_state(msta, tid, MT7915_AGGR_START);
+		set_bit(tid, &msta->ampdu_state);
 		ret = IEEE80211_AMPDU_TX_START_IMMEDIATE;
 		break;
 	case IEEE80211_AMPDU_TX_STOP_CONT:
 		mtxq->aggr = false;
-		mt7915_set_aggr_state(msta, tid, MT7915_AGGR_STOP);
+		clear_bit(tid, &msta->ampdu_state);
 		mt7915_mcu_add_tx_ba(dev, params, false);
 		ieee80211_stop_tx_ba_cb_irqsafe(vif, sta->addr, tid);
 		break;
@@ -789,18 +790,16 @@ mt7915_sta_rc_update(struct ieee80211_hw *hw,
 		     struct ieee80211_sta *sta,
 		     u32 changed)
 {
+	struct mt7915_dev *dev = mt7915_hw_dev(hw);
 	struct mt7915_sta *msta = (struct mt7915_sta *)sta->drv_priv;
 
-	rcu_read_lock();
-	sta = ieee80211_find_sta(vif, sta->addr);
-	if (!sta) {
-		rcu_read_unlock();
-		return;
-	}
-	rcu_read_unlock();
+	spin_lock_bh(&dev->sta_poll_lock);
+	msta->stats.changed |= changed;
+	if (list_empty(&msta->rc_list))
+		list_add_tail(&msta->rc_list, &dev->sta_rc_list);
+	spin_unlock_bh(&dev->sta_poll_lock);
 
-	set_bit(changed, &msta->stats.changed);
-	ieee80211_queue_work(hw, &msta->stats_work);
+	ieee80211_queue_work(hw, &dev->rc_work);
 }
 
 const struct ieee80211_ops mt7915_ops = {
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
index ac8ec257da03..a3ccc1785661 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
@@ -522,6 +522,9 @@ mt7915_mcu_tx_rate_report(struct mt7915_dev *dev, struct sk_buff *skb)
 		return;
 
 	wcid = rcu_dereference(dev->mt76.wcid[wcidx]);
+	if (!wcid)
+		return;
+
 	msta = container_of(wcid, struct mt7915_sta, wcid);
 	stats = &msta->stats;
 
@@ -714,8 +717,8 @@ mt7915_mcu_add_nested_subtlv(struct sk_buff *skb, int sub_tag, int sub_len,
 	ptlv = skb_put(skb, sub_len);
 	memcpy(ptlv, &tlv, sizeof(tlv));
 
-	*sub_ntlv = cpu_to_le16(le16_to_cpu(*sub_ntlv) + 1);
-	*len = cpu_to_le16(le16_to_cpu(*len) + sub_len);
+	le16_add_cpu(sub_ntlv, 1);
+	le16_add_cpu(len, sub_len);
 
 	return ptlv;
 }
@@ -933,11 +936,11 @@ mt7915_mcu_bss_he_tlv(struct sk_buff *skb, struct ieee80211_vif *vif,
 	tlv = mt7915_mcu_add_tlv(skb, BSS_INFO_HE_BASIC, sizeof(*he));
 
 	he = (struct bss_info_he *)tlv;
-	he->he_pe_duration = vif->bss_conf.htc_trig_based_pkt_ext * 4;
+	he->he_pe_duration = vif->bss_conf.htc_trig_based_pkt_ext;
 	if (!he->he_pe_duration)
 		he->he_pe_duration = DEFAULT_HE_PE_DURATION;
 
-	he->he_rts_thres = cpu_to_le16(vif->bss_conf.frame_time_rts_th * 32);
+	he->he_rts_thres = cpu_to_le16(vif->bss_conf.frame_time_rts_th);
 	if (!he->he_rts_thres)
 		he->he_rts_thres = cpu_to_le16(DEFAULT_HE_DURATION_RTS_THRES);
 
@@ -947,6 +950,23 @@ mt7915_mcu_bss_he_tlv(struct sk_buff *skb, struct ieee80211_vif *vif,
 }
 
 static void
+mt7915_mcu_bss_hw_amsdu_tlv(struct sk_buff *skb)
+{
+#define TXD_CMP_MAP1		GENMASK(15, 0)
+#define TXD_CMP_MAP2		(GENMASK(31, 0) & ~BIT(23))
+	struct bss_info_hw_amsdu *amsdu;
+	struct tlv *tlv;
+
+	tlv = mt7915_mcu_add_tlv(skb, BSS_INFO_HW_AMSDU, sizeof(*amsdu));
+
+	amsdu = (struct bss_info_hw_amsdu *)tlv;
+	amsdu->cmp_bitmap_0 = cpu_to_le32(TXD_CMP_MAP1);
+	amsdu->cmp_bitmap_1 = cpu_to_le32(TXD_CMP_MAP2);
+	amsdu->trig_thres = cpu_to_le16(2);
+	amsdu->enable = true;
+}
+
+static void
 mt7915_mcu_bss_ext_tlv(struct sk_buff *skb, struct mt7915_vif *mvif)
 {
 /* SIFS 20us + 512 byte beacon tranmitted by 1Mbps (3906us) */
@@ -1020,6 +1040,7 @@ int mt7915_mcu_add_bss_info(struct mt7915_phy *phy,
 		mt7915_mcu_bss_rfch_tlv(skb, vif, phy);
 		mt7915_mcu_bss_bmc_tlv(skb, phy);
 		mt7915_mcu_bss_ra_tlv(skb, vif, phy);
+		mt7915_mcu_bss_hw_amsdu_tlv(skb);
 
 		if (vif->bss_conf.he_support)
 			mt7915_mcu_bss_he_tlv(skb, vif, phy);
@@ -1178,6 +1199,9 @@ mt7915_mcu_sta_ba(struct mt7915_dev *dev,
 	struct sk_buff *skb;
 	int ret;
 
+	if (enable && tx && !params->amsdu)
+		msta->wcid.amsdu = false;
+
 	skb = mt7915_mcu_alloc_sta_req(dev, mvif, msta,
 				       MT7915_STA_UPDATE_MAX_SIZE);
 	if (IS_ERR(skb))
@@ -1407,7 +1431,7 @@ mt7915_mcu_sta_he_tlv(struct sk_buff *skb, struct ieee80211_sta *sta)
 
 		he->max_nss_mcs[CMD_HE_MCS_BW160] =
 				he_cap->he_mcs_nss_supp.rx_mcs_160;
-		/* fall through */
+		fallthrough;
 	default:
 		he->max_nss_mcs[CMD_HE_MCS_BW80] =
 				he_cap->he_mcs_nss_supp.rx_mcs_80;
@@ -1441,6 +1465,38 @@ mt7915_mcu_sta_he_tlv(struct sk_buff *skb, struct ieee80211_sta *sta)
 }
 
 static void
+mt7915_mcu_sta_uapsd_tlv(struct sk_buff *skb, struct ieee80211_sta *sta,
+		     struct ieee80211_vif *vif)
+{
+	struct sta_rec_uapsd *uapsd;
+	struct tlv *tlv;
+
+	if (vif->type != NL80211_IFTYPE_AP || !sta->wme)
+		return;
+
+	tlv = mt7915_mcu_add_tlv(skb, STA_REC_APPS, sizeof(*uapsd));
+	uapsd = (struct sta_rec_uapsd *)tlv;
+
+	if (sta->uapsd_queues & IEEE80211_WMM_IE_STA_QOSINFO_AC_VO) {
+		uapsd->dac_map |= BIT(3);
+		uapsd->tac_map |= BIT(3);
+	}
+	if (sta->uapsd_queues & IEEE80211_WMM_IE_STA_QOSINFO_AC_VI) {
+		uapsd->dac_map |= BIT(2);
+		uapsd->tac_map |= BIT(2);
+	}
+	if (sta->uapsd_queues & IEEE80211_WMM_IE_STA_QOSINFO_AC_BE) {
+		uapsd->dac_map |= BIT(1);
+		uapsd->tac_map |= BIT(1);
+	}
+	if (sta->uapsd_queues & IEEE80211_WMM_IE_STA_QOSINFO_AC_BK) {
+		uapsd->dac_map |= BIT(0);
+		uapsd->tac_map |= BIT(0);
+	}
+	uapsd->max_sp = sta->max_sp;
+}
+
+static void
 mt7915_mcu_sta_muru_tlv(struct sk_buff *skb, struct ieee80211_sta *sta)
 {
 	struct ieee80211_sta_he_cap *he_cap = &sta->he_cap;
@@ -1512,8 +1568,39 @@ mt7915_mcu_add_mu(struct mt7915_dev *dev, struct ieee80211_vif *vif,
 }
 
 static void
+mt7915_mcu_sta_amsdu_tlv(struct sk_buff *skb, struct ieee80211_sta *sta)
+{
+	struct mt7915_sta *msta = (struct mt7915_sta *)sta->drv_priv;
+	struct sta_rec_amsdu *amsdu;
+	struct tlv *tlv;
+
+	if (!sta->max_amsdu_len)
+	    return;
+
+	tlv = mt7915_mcu_add_tlv(skb, STA_REC_HW_AMSDU, sizeof(*amsdu));
+	amsdu = (struct sta_rec_amsdu *)tlv;
+	amsdu->max_amsdu_num = 8;
+	amsdu->amsdu_en = true;
+	amsdu->max_mpdu_size = sta->max_amsdu_len >=
+			       IEEE80211_MAX_MPDU_LEN_VHT_7991;
+	msta->wcid.amsdu = true;
+}
+
+static bool
+mt7915_hw_amsdu_supported(struct ieee80211_vif *vif)
+{
+	switch (vif->type) {
+	case NL80211_IFTYPE_AP:
+	case NL80211_IFTYPE_STATION:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static void
 mt7915_mcu_sta_tlv(struct mt7915_dev *dev, struct sk_buff *skb,
-		   struct ieee80211_sta *sta)
+		   struct ieee80211_sta *sta, struct ieee80211_vif *vif)
 {
 	struct tlv *tlv;
 
@@ -1524,6 +1611,9 @@ mt7915_mcu_sta_tlv(struct mt7915_dev *dev, struct sk_buff *skb,
 		tlv = mt7915_mcu_add_tlv(skb, STA_REC_HT, sizeof(*ht));
 		ht = (struct sta_rec_ht *)tlv;
 		ht->ht_cap = cpu_to_le16(sta->ht_cap.cap);
+
+		if (mt7915_hw_amsdu_supported(vif))
+			mt7915_mcu_sta_amsdu_tlv(skb, sta);
 	}
 
 	/* starec vht */
@@ -1540,6 +1630,9 @@ mt7915_mcu_sta_tlv(struct mt7915_dev *dev, struct sk_buff *skb,
 	/* starec he */
 	if (sta->he_cap.has_he)
 		mt7915_mcu_sta_he_tlv(skb, sta);
+
+	/* starec uapsd */
+	mt7915_mcu_sta_uapsd_tlv(skb, sta, vif);
 }
 
 static void
@@ -2176,7 +2269,7 @@ int mt7915_mcu_add_sta(struct mt7915_dev *dev, struct ieee80211_vif *vif,
 
 	mt7915_mcu_sta_basic_tlv(skb, vif, sta, enable);
 	if (enable && sta)
-		mt7915_mcu_sta_tlv(dev, skb, sta);
+		mt7915_mcu_sta_tlv(dev, skb, sta, vif);
 
 	sta_wtbl = mt7915_mcu_add_tlv(skb, STA_REC_WTBL, sizeof(struct tlv));
 
@@ -2335,14 +2428,6 @@ int mt7915_mcu_add_beacon(struct ieee80211_hw *hw,
 	struct bss_info_bcn *bcn;
 	int len = MT7915_BEACON_UPDATE_SIZE + MAX_BEACON_SIZE;
 
-	rskb = mt7915_mcu_alloc_sta_req(dev, mvif, NULL, len);
-	if (IS_ERR(rskb))
-		return PTR_ERR(rskb);
-
-	tlv = mt7915_mcu_add_tlv(rskb, BSS_INFO_OFFLOAD, sizeof(*bcn));
-	bcn = (struct bss_info_bcn *)tlv;
-	bcn->enable = en;
-
 	skb = ieee80211_beacon_get_template(hw, vif, &offs);
 	if (!skb)
 		return -EINVAL;
@@ -2353,6 +2438,16 @@ int mt7915_mcu_add_beacon(struct ieee80211_hw *hw,
 		return -EINVAL;
 	}
 
+	rskb = mt7915_mcu_alloc_sta_req(dev, mvif, NULL, len);
+	if (IS_ERR(rskb)) {
+		dev_kfree_skb(skb);
+		return PTR_ERR(rskb);
+	}
+
+	tlv = mt7915_mcu_add_tlv(rskb, BSS_INFO_OFFLOAD, sizeof(*bcn));
+	bcn = (struct bss_info_bcn *)tlv;
+	bcn->enable = en;
+
 	if (mvif->band_idx) {
 		info = IEEE80211_SKB_CB(skb);
 		info->hw_queue |= MT_TX_HW_QUEUE_EXT_PHY;
@@ -2901,6 +2996,7 @@ int mt7915_mcu_set_tx(struct mt7915_dev *dev, struct ieee80211_vif *vif)
 		struct ieee80211_tx_queue_params *q = &mvif->queue_params[ac];
 		struct edca *e = &req.edca[ac];
 
+		e->set = WMM_PARAM_SET;
 		e->queue = ac + mvif->wmm_idx * MT7915_MAX_WMM_SETS;
 		e->aifs = q->aifs;
 		e->txop = cpu_to_le16(q->txop);
@@ -3052,8 +3148,10 @@ int mt7915_mcu_set_chan_info(struct mt7915_phy *phy, int cmd)
 		.channel_band = chandef->chan->band,
 	};
 
-	if ((chandef->chan->flags & IEEE80211_CHAN_RADAR) &&
-	    chandef->chan->dfs_state != NL80211_DFS_AVAILABLE)
+	if (dev->mt76.hw->conf.flags & IEEE80211_CONF_OFFCHANNEL)
+		req.switch_reason = CH_SWITCH_SCAN_BYPASS_DPD;
+	else if ((chandef->chan->flags & IEEE80211_CHAN_RADAR) &&
+		 chandef->chan->dfs_state != NL80211_DFS_AVAILABLE)
 		req.switch_reason = CH_SWITCH_DFS;
 	else
 		req.switch_reason = CH_SWITCH_NORMAL;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.h b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.h
index cb35e718409a..c656d66385c4 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.h
@@ -402,6 +402,16 @@ struct bss_info_ra {
 	__le32 fast_interval;
 } __packed;
 
+struct bss_info_hw_amsdu {
+	__le16 tag;
+	__le16 len;
+	__le32 cmp_bitmap_0;
+	__le32 cmp_bitmap_1;
+	__le16 trig_thres;
+	u8 enable;
+	u8 rsv;
+} __packed;
+
 struct bss_info_he {
 	__le16 tag;
 	__le16 len;
@@ -645,6 +655,17 @@ struct sta_rec_vht {
 	u8 rsv[3];
 } __packed;
 
+struct sta_rec_uapsd {
+	__le16 tag;
+	__le16 len;
+	u8 dac_map;
+	u8 tac_map;
+	u8 max_sp;
+	u8 rsv0;
+	__le16 listen_interval;
+	u8 rsv1[2];
+} __packed;
+
 struct sta_rec_muru {
 	__le16 tag;
 	__le16 len;
@@ -725,6 +746,15 @@ struct sta_rec_ba {
 	__le16 winsize;
 } __packed;
 
+struct sta_rec_amsdu {
+	__le16 tag;
+	__le16 len;
+	u8 max_amsdu_num;
+	u8 max_mpdu_size;
+	u8 amsdu_en;
+	u8 rsv;
+} __packed;
+
 struct sec_key {
 	u8 cipher_id;
 	u8 cipher_len;
@@ -951,6 +981,8 @@ enum {
 					 sizeof(struct sta_rec_he) +	\
 					 sizeof(struct sta_rec_ba) +	\
 					 sizeof(struct sta_rec_vht) +	\
+					 sizeof(struct sta_rec_uapsd) + \
+					 sizeof(struct sta_rec_amsdu) +	\
 					 sizeof(struct tlv) +		\
 					 MT7915_WTBL_UPDATE_MAX_SIZE)
 
@@ -962,6 +994,7 @@ enum {
 					 sizeof(struct bss_info_basic) +\
 					 sizeof(struct bss_info_rf_ch) +\
 					 sizeof(struct bss_info_ra) +	\
+					 sizeof(struct bss_info_hw_amsdu) +\
 					 sizeof(struct bss_info_he) +	\
 					 sizeof(struct bss_info_bmc_rate) +\
 					 sizeof(struct bss_info_ext_bss) +\
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h b/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h
index d8a13b4a2359..4b8908fa7eda 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h
@@ -62,13 +62,6 @@ enum mt7915_rxq_id {
 	MT7915_RXQ_MCU_WA,
 };
 
-enum mt7915_ampdu_state {
-	MT7915_AGGR_STOP,
-	MT7915_AGGR_PROGRESS,
-	MT7915_AGGR_START,
-	MT7915_AGGR_OPERATIONAL
-};
-
 struct mt7915_sta_stats {
 	struct rate_info prob_rate;
 	struct rate_info tx_rate;
@@ -83,14 +76,14 @@ struct mt7915_sta {
 
 	struct mt7915_vif *vif;
 
+	struct list_head stats_list;
 	struct list_head poll_list;
+	struct list_head rc_list;
 	u32 airtime_ac[8];
 
 	struct mt7915_sta_stats stats;
-	struct work_struct stats_work;
 
-	spinlock_t ampdu_lock;
-	enum mt7915_ampdu_state ampdu_state[IEEE80211_NUM_TIDS];
+	unsigned long ampdu_state;
 };
 
 struct mt7915_vif {
@@ -100,7 +93,7 @@ struct mt7915_vif {
 	u8 wmm_idx;
 
 	struct mt7915_sta sta;
-	struct mt7915_dev *dev;
+	struct mt7915_phy *phy;
 
 	struct ieee80211_tx_queue_params queue_params[IEEE80211_NUM_ACS];
 };
@@ -135,9 +128,11 @@ struct mt7915_phy {
 	u32 ampdu_ref;
 
 	struct mib_stats mib;
+	struct list_head stats_list;
 
 	struct delayed_work mac_work;
 	u8 mac_work_count;
+	u8 sta_work_count;
 };
 
 struct mt7915_dev {
@@ -146,15 +141,18 @@ struct mt7915_dev {
 		struct mt76_phy mphy;
 	};
 
+	const struct mt76_bus_ops *bus_ops;
 	struct mt7915_phy phy;
 
 	u16 chainmask;
 
 	struct work_struct init_work;
+	struct work_struct rc_work;
 	struct work_struct reset_work;
 	wait_queue_head_t reset_wait;
 	u32 reset_state;
 
+	struct list_head sta_rc_list;
 	struct list_head sta_poll_list;
 	spinlock_t sta_poll_lock;
 
@@ -260,26 +258,8 @@ mt7915_ext_phy(struct mt7915_dev *dev)
 
 static inline u8 mt7915_lmac_mapping(struct mt7915_dev *dev, u8 ac)
 {
-	static const u8 lmac_queue_map[] = {
-		[IEEE80211_AC_BK] = MT_LMAC_AC00,
-		[IEEE80211_AC_BE] = MT_LMAC_AC01,
-		[IEEE80211_AC_VI] = MT_LMAC_AC02,
-		[IEEE80211_AC_VO] = MT_LMAC_AC03,
-	};
-
-	if (WARN_ON_ONCE(ac >= ARRAY_SIZE(lmac_queue_map)))
-		return MT_LMAC_AC01; /* BE */
-
-	return lmac_queue_map[ac];
-}
-
-static inline void
-mt7915_set_aggr_state(struct mt7915_sta *msta, u8 tid,
-		      enum mt7915_ampdu_state state)
-{
-	spin_lock_bh(&msta->ampdu_lock);
-	msta->ampdu_state[tid] = state;
-	spin_unlock_bh(&msta->ampdu_lock);
+	/* LMAC uses the reverse order of mac80211 AC indexes */
+	return 3 - ac;
 }
 
 extern const struct ieee80211_ops mt7915_ops;
@@ -448,7 +428,6 @@ mt7915_l2_rmw(struct mt7915_dev *dev, u32 addr, u32 mask, u32 val)
 bool mt7915_mac_wtbl_update(struct mt7915_dev *dev, int idx, u32 mask);
 void mt7915_mac_reset_counters(struct mt7915_phy *phy);
 void mt7915_mac_cca_stats_reset(struct mt7915_phy *phy);
-void mt7915_mac_sta_poll(struct mt7915_dev *dev);
 void mt7915_mac_write_txwi(struct mt7915_dev *dev, __le32 *txwi,
 			   struct sk_buff *skb, struct mt76_wcid *wcid,
 			   struct ieee80211_key_conf *key, bool beacon);
@@ -461,13 +440,12 @@ void mt7915_mac_sta_remove(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 			   struct ieee80211_sta *sta);
 void mt7915_mac_work(struct work_struct *work);
 void mt7915_mac_reset_work(struct work_struct *work);
-void mt7915_mac_sta_stats_work(struct work_struct *work);
+void mt7915_mac_sta_rc_work(struct work_struct *work);
 int mt7915_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr,
 			  enum mt76_txq_id qid, struct mt76_wcid *wcid,
 			  struct ieee80211_sta *sta,
 			  struct mt76_tx_info *tx_info);
-void mt7915_tx_complete_skb(struct mt76_dev *mdev, enum mt76_txq_id qid,
-			    struct mt76_queue_entry *e);
+void mt7915_tx_complete_skb(struct mt76_dev *mdev, struct mt76_queue_entry *e);
 void mt7915_queue_rx_skb(struct mt76_dev *mdev, enum mt76_rxq_id q,
 			 struct sk_buff *skb);
 void mt7915_sta_ps(struct mt76_dev *mdev, struct ieee80211_sta *sta, bool ps);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/pci.c b/drivers/net/wireless/mediatek/mt76/mt7915/pci.c
index 0ec4e184b889..fe62b4d853e4 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/pci.c
@@ -29,9 +29,10 @@ mt7915_rx_poll_complete(struct mt76_dev *mdev, enum mt76_rxq_id q)
 static irqreturn_t mt7915_irq_handler(int irq, void *dev_instance)
 {
 	struct mt7915_dev *dev = dev_instance;
-	u32 intr;
+	u32 intr, mask;
 
 	intr = mt76_rr(dev, MT_INT_SOURCE_CSR);
+	intr &= dev->mt76.mmio.irqmask;
 	mt76_wr(dev, MT_INT_SOURCE_CSR, intr);
 
 	if (!test_bit(MT76_STATE_INITIALIZED, &dev->mphy.state))
@@ -39,27 +40,23 @@ static irqreturn_t mt7915_irq_handler(int irq, void *dev_instance)
 
 	trace_dev_irq(&dev->mt76, intr, dev->mt76.mmio.irqmask);
 
-	intr &= dev->mt76.mmio.irqmask;
+	mask = intr & MT_INT_RX_DONE_ALL;
+	if (intr & MT_INT_TX_DONE_MCU)
+		mask |= MT_INT_TX_DONE_MCU;
 
-	if (intr & MT_INT_TX_DONE_ALL) {
-		mt7915_irq_disable(dev, MT_INT_TX_DONE_ALL);
+	mt7915_irq_disable(dev, mask);
+
+	if (intr & MT_INT_TX_DONE_MCU)
 		napi_schedule(&dev->mt76.tx_napi);
-	}
 
-	if (intr & MT_INT_RX_DONE_DATA) {
-		mt7915_irq_disable(dev, MT_INT_RX_DONE_DATA);
+	if (intr & MT_INT_RX_DONE_DATA)
 		napi_schedule(&dev->mt76.napi[0]);
-	}
 
-	if (intr & MT_INT_RX_DONE_WM) {
-		mt7915_irq_disable(dev, MT_INT_RX_DONE_WM);
+	if (intr & MT_INT_RX_DONE_WM)
 		napi_schedule(&dev->mt76.napi[1]);
-	}
 
-	if (intr & MT_INT_RX_DONE_WA) {
-		mt7915_irq_disable(dev, MT_INT_RX_DONE_WA);
+	if (intr & MT_INT_RX_DONE_WA)
 		napi_schedule(&dev->mt76.napi[2]);
-	}
 
 	if (intr & MT_INT_MCU_CMD) {
 		u32 val = mt76_rr(dev, MT_MCU_CMD);
@@ -103,7 +100,8 @@ static int mt7915_pci_probe(struct pci_dev *pdev,
 	static const struct mt76_driver_ops drv_ops = {
 		/* txwi_size = txd size + txp size */
 		.txwi_size = MT_TXD_SIZE + sizeof(struct mt7915_txp),
-		.drv_flags = MT_DRV_TXWI_NO_FREE | MT_DRV_HW_MGMT_TXQ,
+		.drv_flags = MT_DRV_TXWI_NO_FREE | MT_DRV_HW_MGMT_TXQ |
+			     MT_DRV_AMSDU_OFFLOAD,
 		.survey_flags = SURVEY_INFO_TIME_TX |
 				SURVEY_INFO_TIME_RX |
 				SURVEY_INFO_TIME_BSS_RX,
@@ -149,6 +147,8 @@ static int mt7915_pci_probe(struct pci_dev *pdev,
 		    (mt7915_l1_rr(dev, MT_HW_REV) & 0xff);
 	dev_dbg(mdev->dev, "ASIC revision: %04x\n", mdev->rev);
 
+	mt76_wr(dev, MT_INT_MASK_CSR, 0);
+
 	/* master switch of PCIe tnterrupt enable */
 	mt7915_l1_wr(dev, MT_PCIE_MAC_INT_ENABLE, 0xff);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/regs.h b/drivers/net/wireless/mediatek/mt76/mt7915/regs.h
index e0989141d9da..64327153b7fa 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/regs.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/regs.h
@@ -313,9 +313,17 @@
 #define MT_INT_RX_DONE_WA		BIT(1)
 #define MT_INT_RX_DONE(_n)		((_n) ? BIT((_n) - 1) : BIT(16))
 #define MT_INT_RX_DONE_ALL		(BIT(0) | BIT(1) | BIT(16))
-#define MT_INT_TX_DONE_ALL		(BIT(15) | GENMASK(27, 26) | BIT(30))
+#define MT_INT_TX_DONE_MCU_WA		BIT(15)
+#define MT_INT_TX_DONE_FWDL		BIT(26)
+#define MT_INT_TX_DONE_MCU_WM		BIT(27)
+#define MT_INT_TX_DONE_BAND0		BIT(30)
+#define MT_INT_TX_DONE_BAND1		BIT(31)
 #define MT_INT_MCU_CMD			BIT(29)
 
+#define MT_INT_TX_DONE_MCU		(MT_INT_TX_DONE_MCU_WA |	\
+					 MT_INT_TX_DONE_MCU_WM |	\
+					 MT_INT_TX_DONE_FWDL)
+
 #define MT_WFDMA_EXT_CSR_HIF_MISC	MT_WFDMA_EXT_CSR(0x44)
 #define MT_WFDMA_EXT_CSR_HIF_MISC_BUSY	BIT(0)
 
@@ -352,6 +360,13 @@
 #define MT_HIF_REMAP_L2_BASE		GENMASK(31, 12)
 #define MT_HIF_REMAP_BASE_L2		0x00000
 
+#define MT_SWDEF_BASE			0x41f200
+#define MT_SWDEF(ofs)			(MT_SWDEF_BASE + (ofs))
+#define MT_SWDEF_MODE			MT_SWDEF(0x3c)
+#define MT_SWDEF_NORMAL_MODE		0
+#define MT_SWDEF_ICAP_MODE		1
+#define MT_SWDEF_SPECTRUM_MODE		2
+
 #define MT_TOP_BASE			0x18060000
 #define MT_TOP(ofs)			(MT_TOP_BASE + (ofs))
 
diff --git a/drivers/net/wireless/mediatek/mt76/sdio.c b/drivers/net/wireless/mediatek/mt76/sdio.c
index d2b38ed7f3b4..9a4d95a2a707 100644
--- a/drivers/net/wireless/mediatek/mt76/sdio.c
+++ b/drivers/net/wireless/mediatek/mt76/sdio.c
@@ -42,15 +42,13 @@ static int mt76s_alloc_tx(struct mt76_dev *dev)
 	int i;
 
 	for (i = 0; i < MT_TXQ_MCU_WA; i++) {
-		INIT_LIST_HEAD(&dev->q_tx[i].swq);
-
 		q = devm_kzalloc(dev->dev, sizeof(*q), GFP_KERNEL);
 		if (!q)
 			return -ENOMEM;
 
 		spin_lock_init(&q->lock);
 		q->hw_idx = i;
-		dev->q_tx[i].q = q;
+		dev->q_tx[i] = q;
 
 		q->entry = devm_kcalloc(dev->dev,
 					MT_NUM_TX_ENTRIES, sizeof(*q->entry),
@@ -68,6 +66,10 @@ void mt76s_stop_txrx(struct mt76_dev *dev)
 {
 	struct mt76_sdio *sdio = &dev->sdio;
 
+	cancel_work_sync(&sdio->tx.xmit_work);
+	cancel_work_sync(&sdio->tx.status_work);
+	cancel_work_sync(&sdio->rx.recv_work);
+	cancel_work_sync(&sdio->rx.net_work);
 	cancel_work_sync(&sdio->stat_work);
 	clear_bit(MT76_READING_STATS, &dev->phy.state);
 
@@ -94,8 +96,8 @@ mt76s_get_next_rx_entry(struct mt76_queue *q)
 
 	spin_lock_bh(&q->lock);
 	if (q->queued > 0) {
-		e = &q->entry[q->head];
-		q->head = (q->head + 1) % q->ndesc;
+		e = &q->entry[q->tail];
+		q->tail = (q->tail + 1) % q->ndesc;
 		q->queued--;
 	}
 	spin_unlock_bh(&q->lock);
@@ -129,38 +131,26 @@ mt76s_process_rx_queue(struct mt76_dev *dev, struct mt76_queue *q)
 	return nframes;
 }
 
-static int mt76s_process_tx_queue(struct mt76_dev *dev, enum mt76_txq_id qid)
+static void mt76s_process_tx_queue(struct mt76_dev *dev, enum mt76_txq_id qid)
 {
-	struct mt76_sw_queue *sq = &dev->q_tx[qid];
-	u32 n_dequeued = 0, n_sw_dequeued = 0;
+	struct mt76_queue *q = dev->q_tx[qid];
 	struct mt76_queue_entry entry;
-	struct mt76_queue *q = sq->q;
 	bool wake;
 
-	while (q->queued > n_dequeued) {
-		if (!q->entry[q->head].done)
+	while (q->queued > 0) {
+		if (!q->entry[q->tail].done)
 			break;
 
-		if (q->entry[q->head].schedule) {
-			q->entry[q->head].schedule = false;
-			n_sw_dequeued++;
-		}
-
-		entry = q->entry[q->head];
-		q->entry[q->head].done = false;
-		q->head = (q->head + 1) % q->ndesc;
-		n_dequeued++;
+		entry = q->entry[q->tail];
+		q->entry[q->tail].done = false;
 
-		if (qid == MT_TXQ_MCU)
+		if (qid == MT_TXQ_MCU) {
 			dev_kfree_skb(entry.skb);
-		else
-			dev->drv->tx_complete_skb(dev, qid, &entry);
-	}
-
-	spin_lock_bh(&q->lock);
+			entry.skb = NULL;
+		}
 
-	sq->swq_queued -= n_sw_dequeued;
-	q->queued -= n_dequeued;
+		mt76_queue_tx_complete(dev, q, &entry);
+	}
 
 	wake = q->stopped && q->queued < q->ndesc - 8;
 	if (wake)
@@ -169,19 +159,13 @@ static int mt76s_process_tx_queue(struct mt76_dev *dev, enum mt76_txq_id qid)
 	if (!q->queued)
 		wake_up(&dev->tx_wait);
 
-	spin_unlock_bh(&q->lock);
-
 	if (qid == MT_TXQ_MCU)
-		goto out;
+		return;
 
 	mt76_txq_schedule(&dev->phy, qid);
 
 	if (wake)
 		ieee80211_wake_queue(dev->hw, qid);
-
-	wake_up_process(dev->sdio.tx_kthread);
-out:
-	return n_dequeued;
 }
 
 static void mt76s_tx_status_data(struct work_struct *work)
@@ -214,12 +198,12 @@ mt76s_tx_queue_skb(struct mt76_dev *dev, enum mt76_txq_id qid,
 		   struct sk_buff *skb, struct mt76_wcid *wcid,
 		   struct ieee80211_sta *sta)
 {
-	struct mt76_queue *q = dev->q_tx[qid].q;
+	struct mt76_queue *q = dev->q_tx[qid];
 	struct mt76_tx_info tx_info = {
 		.skb = skb,
 	};
 	int err, len = skb->len;
-	u16 idx = q->tail;
+	u16 idx = q->head;
 
 	if (q->queued == q->ndesc)
 		return -ENOSPC;
@@ -229,9 +213,9 @@ mt76s_tx_queue_skb(struct mt76_dev *dev, enum mt76_txq_id qid,
 	if (err < 0)
 		return err;
 
-	q->entry[q->tail].skb = tx_info.skb;
-	q->entry[q->tail].buf_sz = len;
-	q->tail = (q->tail + 1) % q->ndesc;
+	q->entry[q->head].skb = tx_info.skb;
+	q->entry[q->head].buf_sz = len;
+	q->head = (q->head + 1) % q->ndesc;
 	q->queued++;
 
 	return idx;
@@ -241,25 +225,31 @@ static int
 mt76s_tx_queue_skb_raw(struct mt76_dev *dev, enum mt76_txq_id qid,
 		       struct sk_buff *skb, u32 tx_info)
 {
-	struct mt76_queue *q = dev->q_tx[qid].q;
-	int ret = -ENOSPC, len = skb->len;
+	struct mt76_queue *q = dev->q_tx[qid];
+	int ret = -ENOSPC, len = skb->len, pad;
 
-	spin_lock_bh(&q->lock);
 	if (q->queued == q->ndesc)
-		goto out;
+		goto error;
 
-	ret = mt76_skb_adjust_pad(skb);
+	pad = round_up(skb->len, 4) - skb->len;
+	ret = mt76_skb_adjust_pad(skb, pad);
 	if (ret)
-		goto out;
+		goto error;
 
-	q->entry[q->tail].buf_sz = len;
-	q->entry[q->tail].skb = skb;
-	q->tail = (q->tail + 1) % q->ndesc;
+	spin_lock_bh(&q->lock);
+
+	q->entry[q->head].buf_sz = len;
+	q->entry[q->head].skb = skb;
+	q->head = (q->head + 1) % q->ndesc;
 	q->queued++;
 
-out:
 	spin_unlock_bh(&q->lock);
 
+	return 0;
+
+error:
+	dev_kfree_skb(skb);
+
 	return ret;
 }
 
@@ -267,7 +257,7 @@ static void mt76s_tx_kick(struct mt76_dev *dev, struct mt76_queue *q)
 {
 	struct mt76_sdio *sdio = &dev->sdio;
 
-	wake_up_process(sdio->tx_kthread);
+	queue_work(sdio->txrx_wq, &sdio->tx.xmit_work);
 }
 
 static const struct mt76_queue_ops sdio_queue_ops = {
@@ -276,41 +266,37 @@ static const struct mt76_queue_ops sdio_queue_ops = {
 	.tx_queue_skb_raw = mt76s_tx_queue_skb_raw,
 };
 
-static int mt76s_kthread_run(void *data)
+static void mt76s_tx_work(struct work_struct *work)
 {
-	struct mt76_dev *dev = data;
-	struct mt76_phy *mphy = &dev->phy;
-
-	while (!kthread_should_stop()) {
-		int i, nframes = 0;
-
-		cond_resched();
-
-		/* rx processing */
-		local_bh_disable();
-		rcu_read_lock();
+	struct mt76_sdio *sdio = container_of(work, struct mt76_sdio,
+					      tx.status_work);
+	struct mt76_dev *dev = container_of(sdio, struct mt76_dev, sdio);
+	int i;
 
-		mt76_for_each_q_rx(dev, i)
-			nframes += mt76s_process_rx_queue(dev, &dev->q_rx[i]);
+	for (i = 0; i < MT_TXQ_MCU_WA; i++)
+		mt76s_process_tx_queue(dev, i);
 
-		rcu_read_unlock();
-		local_bh_enable();
+	if (dev->drv->tx_status_data &&
+	    !test_and_set_bit(MT76_READING_STATS, &dev->phy.state))
+		queue_work(dev->wq, &dev->sdio.stat_work);
+}
 
-		/* tx processing */
-		for (i = 0; i < MT_TXQ_MCU_WA; i++)
-			nframes += mt76s_process_tx_queue(dev, i);
+static void mt76s_rx_work(struct work_struct *work)
+{
+	struct mt76_sdio *sdio = container_of(work, struct mt76_sdio,
+					      rx.net_work);
+	struct mt76_dev *dev = container_of(sdio, struct mt76_dev, sdio);
+	int i;
 
-		if (dev->drv->tx_status_data &&
-		    !test_and_set_bit(MT76_READING_STATS, &mphy->state))
-			queue_work(dev->wq, &dev->sdio.stat_work);
+	/* rx processing */
+	local_bh_disable();
+	rcu_read_lock();
 
-		if (!nframes || !test_bit(MT76_STATE_RUNNING, &mphy->state)) {
-			set_current_state(TASK_INTERRUPTIBLE);
-			schedule();
-		}
-	}
+	mt76_for_each_q_rx(dev, i)
+		mt76s_process_rx_queue(dev, &dev->q_rx[i]);
 
-	return 0;
+	rcu_read_unlock();
+	local_bh_enable();
 }
 
 void mt76s_deinit(struct mt76_dev *dev)
@@ -318,9 +304,11 @@ void mt76s_deinit(struct mt76_dev *dev)
 	struct mt76_sdio *sdio = &dev->sdio;
 	int i;
 
-	kthread_stop(sdio->kthread);
-	kthread_stop(sdio->tx_kthread);
 	mt76s_stop_txrx(dev);
+	if (sdio->txrx_wq) {
+		destroy_workqueue(sdio->txrx_wq);
+		sdio->txrx_wq = NULL;
+	}
 
 	sdio_claim_host(sdio->func);
 	sdio_release_irq(sdio->func);
@@ -348,11 +336,15 @@ int mt76s_init(struct mt76_dev *dev, struct sdio_func *func,
 {
 	struct mt76_sdio *sdio = &dev->sdio;
 
-	sdio->kthread = kthread_create(mt76s_kthread_run, dev, "mt76s");
-	if (IS_ERR(sdio->kthread))
-		return PTR_ERR(sdio->kthread);
+	sdio->txrx_wq = alloc_workqueue("mt76s_txrx_wq",
+					WQ_UNBOUND | WQ_HIGHPRI,
+					WQ_UNBOUND_MAX_ACTIVE);
+	if (!sdio->txrx_wq)
+		return -ENOMEM;
 
 	INIT_WORK(&sdio->stat_work, mt76s_tx_status_data);
+	INIT_WORK(&sdio->tx.status_work, mt76s_tx_work);
+	INIT_WORK(&sdio->rx.net_work, mt76s_rx_work);
 
 	mutex_init(&sdio->sched.lock);
 	dev->queue_ops = &sdio_queue_ops;
diff --git a/drivers/net/wireless/mediatek/mt76/testmode.c b/drivers/net/wireless/mediatek/mt76/testmode.c
index 75bb02cdfdae..883f59c7a7e4 100644
--- a/drivers/net/wireless/mediatek/mt76/testmode.c
+++ b/drivers/net/wireless/mediatek/mt76/testmode.c
@@ -29,11 +29,12 @@ void mt76_testmode_tx_pending(struct mt76_dev *dev)
 		return;
 
 	qid = skb_get_queue_mapping(skb);
-	q = dev->q_tx[qid].q;
+	q = dev->q_tx[qid];
 
 	spin_lock_bh(&q->lock);
 
-	while (td->tx_pending > 0 && q->queued < q->ndesc / 2) {
+	while (td->tx_pending > 0 && td->tx_queued - td->tx_done < 1000 &&
+	       q->queued < q->ndesc / 2) {
 		int ret;
 
 		ret = dev->queue_ops->tx_queue_skb(dev, qid, skb_get(skb), wcid, NULL);
@@ -160,7 +161,7 @@ mt76_testmode_tx_start(struct mt76_dev *dev)
 	td->tx_queued = 0;
 	td->tx_done = 0;
 	td->tx_pending = td->tx_count;
-	tasklet_schedule(&dev->tx_tasklet);
+	mt76_worker_schedule(&dev->tx_worker);
 }
 
 static void
@@ -168,11 +169,11 @@ mt76_testmode_tx_stop(struct mt76_dev *dev)
 {
 	struct mt76_testmode_data *td = &dev->test;
 
-	tasklet_disable(&dev->tx_tasklet);
+	mt76_worker_disable(&dev->tx_worker);
 
 	td->tx_pending = 0;
 
-	tasklet_enable(&dev->tx_tasklet);
+	mt76_worker_enable(&dev->tx_worker);
 
 	wait_event_timeout(dev->tx_wait, td->tx_done == td->tx_queued, 10 * HZ);
 
@@ -442,9 +443,13 @@ int mt76_testmode_dump(struct ieee80211_hw *hw, struct sk_buff *msg,
 	mutex_lock(&dev->mutex);
 
 	if (tb[MT76_TM_ATTR_STATS]) {
+		err = -EINVAL;
+
 		a = nla_nest_start(msg, MT76_TM_ATTR_STATS);
-		err = mt76_testmode_dump_stats(dev, msg);
-		nla_nest_end(msg, a);
+		if (a) {
+			err = mt76_testmode_dump_stats(dev, msg);
+			nla_nest_end(msg, a);
+		}
 
 		goto out;
 	}
diff --git a/drivers/net/wireless/mediatek/mt76/tx.c b/drivers/net/wireless/mediatek/mt76/tx.c
index 3afd89ecd6c9..44ef4bc7a46e 100644
--- a/drivers/net/wireless/mediatek/mt76/tx.c
+++ b/drivers/net/wireless/mediatek/mt76/tx.c
@@ -5,75 +5,6 @@
 
 #include "mt76.h"
 
-static struct mt76_txwi_cache *
-mt76_alloc_txwi(struct mt76_dev *dev)
-{
-	struct mt76_txwi_cache *t;
-	dma_addr_t addr;
-	u8 *txwi;
-	int size;
-
-	size = L1_CACHE_ALIGN(dev->drv->txwi_size + sizeof(*t));
-	txwi = devm_kzalloc(dev->dev, size, GFP_ATOMIC);
-	if (!txwi)
-		return NULL;
-
-	addr = dma_map_single(dev->dev, txwi, dev->drv->txwi_size,
-			      DMA_TO_DEVICE);
-	t = (struct mt76_txwi_cache *)(txwi + dev->drv->txwi_size);
-	t->dma_addr = addr;
-
-	return t;
-}
-
-static struct mt76_txwi_cache *
-__mt76_get_txwi(struct mt76_dev *dev)
-{
-	struct mt76_txwi_cache *t = NULL;
-
-	spin_lock_bh(&dev->lock);
-	if (!list_empty(&dev->txwi_cache)) {
-		t = list_first_entry(&dev->txwi_cache, struct mt76_txwi_cache,
-				     list);
-		list_del(&t->list);
-	}
-	spin_unlock_bh(&dev->lock);
-
-	return t;
-}
-
-struct mt76_txwi_cache *
-mt76_get_txwi(struct mt76_dev *dev)
-{
-	struct mt76_txwi_cache *t = __mt76_get_txwi(dev);
-
-	if (t)
-		return t;
-
-	return mt76_alloc_txwi(dev);
-}
-
-void
-mt76_put_txwi(struct mt76_dev *dev, struct mt76_txwi_cache *t)
-{
-	if (!t)
-		return;
-
-	spin_lock_bh(&dev->lock);
-	list_add(&t->list, &dev->txwi_cache);
-	spin_unlock_bh(&dev->lock);
-}
-EXPORT_SYMBOL_GPL(mt76_put_txwi);
-
-void mt76_tx_free(struct mt76_dev *dev)
-{
-	struct mt76_txwi_cache *t;
-
-	while ((t = __mt76_get_txwi(dev)) != NULL)
-		dma_unmap_single(dev->dev, t->dma_addr, dev->drv->txwi_size,
-				 DMA_TO_DEVICE);
-}
-
 static int
 mt76_txq_get_qid(struct ieee80211_txq *txq)
 {
@@ -83,17 +14,27 @@ mt76_txq_get_qid(struct ieee80211_txq *txq)
 	return txq->ac;
 }
 
-static void
-mt76_check_agg_ssn(struct mt76_txq *mtxq, struct sk_buff *skb)
+void
+mt76_tx_check_agg_ssn(struct ieee80211_sta *sta, struct sk_buff *skb)
 {
 	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
+	struct ieee80211_txq *txq;
+	struct mt76_txq *mtxq;
+	u8 tid;
 
-	if (!ieee80211_is_data_qos(hdr->frame_control) ||
+	if (!sta || !ieee80211_is_data_qos(hdr->frame_control) ||
 	    !ieee80211_is_data_present(hdr->frame_control))
 		return;
 
+	tid = skb->priority & IEEE80211_QOS_CTL_TAG1D_MASK;
+	txq = sta->txq[tid];
+	mtxq = (struct mt76_txq *)txq->drv_priv;
+	if (!mtxq->aggr)
+		return;
+
 	mtxq->agg_ssn = le16_to_cpu(hdr->seq_ctrl) + 0x10;
 }
+EXPORT_SYMBOL_GPL(mt76_tx_check_agg_ssn);
 
 void
 mt76_tx_status_lock(struct mt76_dev *dev, struct sk_buff_head *list)
@@ -231,7 +172,32 @@ mt76_tx_status_check(struct mt76_dev *dev, struct mt76_wcid *wcid, bool flush)
 }
 EXPORT_SYMBOL_GPL(mt76_tx_status_check);
 
-void mt76_tx_complete_skb(struct mt76_dev *dev, struct sk_buff *skb)
+static void
+mt76_tx_check_non_aql(struct mt76_dev *dev, u16 wcid_idx, struct sk_buff *skb)
+{
+	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+	struct mt76_wcid *wcid;
+	int pending;
+
+	if (info->tx_time_est)
+		return;
+
+	if (wcid_idx >= ARRAY_SIZE(dev->wcid))
+		return;
+
+	rcu_read_lock();
+
+	wcid = rcu_dereference(dev->wcid[wcid_idx]);
+	if (wcid) {
+		pending = atomic_dec_return(&wcid->non_aql_packets);
+		if (pending < 0)
+			atomic_cmpxchg(&wcid->non_aql_packets, pending, 0);
+	}
+
+	rcu_read_unlock();
+}
+
+void mt76_tx_complete_skb(struct mt76_dev *dev, u16 wcid_idx, struct sk_buff *skb)
 {
 	struct ieee80211_hw *hw;
 	struct sk_buff_head list;
@@ -244,6 +210,8 @@ void mt76_tx_complete_skb(struct mt76_dev *dev, struct sk_buff *skb)
 	}
 #endif
 
+	mt76_tx_check_non_aql(dev, wcid_idx, skb);
+
 	if (!skb->prev) {
 		hw = mt76_tx_status_get_hw(dev, skb);
 		ieee80211_free_txskb(hw, skb);
@@ -256,6 +224,32 @@ void mt76_tx_complete_skb(struct mt76_dev *dev, struct sk_buff *skb)
 }
 EXPORT_SYMBOL_GPL(mt76_tx_complete_skb);
 
+static int
+__mt76_tx_queue_skb(struct mt76_dev *dev, int qid, struct sk_buff *skb,
+		    struct mt76_wcid *wcid, struct ieee80211_sta *sta,
+		    bool *stop)
+{
+	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+	struct mt76_queue *q;
+	bool non_aql;
+	int pending;
+	int idx;
+
+	non_aql = !info->tx_time_est;
+	idx = dev->queue_ops->tx_queue_skb(dev, qid, skb, wcid, sta);
+	if (idx < 0 || !sta || !non_aql)
+		return idx;
+
+	wcid = (struct mt76_wcid *)sta->drv_priv;
+	q = dev->q_tx[qid];
+	q->entry[idx].wcid = wcid->idx;
+	pending = atomic_inc_return(&wcid->non_aql_packets);
+	if (stop && pending >= MT_MAX_NON_AQL_PKT)
+		*stop = true;
+
+	return idx;
+}
+
 void
 mt76_tx(struct mt76_phy *phy, struct ieee80211_sta *sta,
 	struct mt76_wcid *wcid, struct sk_buff *skb)
@@ -288,26 +282,13 @@ mt76_tx(struct mt76_phy *phy, struct ieee80211_sta *sta,
 		ieee80211_get_tx_rates(info->control.vif, sta, skb,
 				       info->control.rates, 1);
 
-	if (sta && ieee80211_is_data_qos(hdr->frame_control)) {
-		struct ieee80211_txq *txq;
-		struct mt76_txq *mtxq;
-		u8 tid;
-
-		tid = skb->priority & IEEE80211_QOS_CTL_TID_MASK;
-		txq = sta->txq[tid];
-		mtxq = (struct mt76_txq *)txq->drv_priv;
-
-		if (mtxq->aggr)
-			mt76_check_agg_ssn(mtxq, skb);
-	}
-
 	if (ext_phy)
 		info->hw_queue |= MT_TX_HW_QUEUE_EXT_PHY;
 
-	q = dev->q_tx[qid].q;
+	q = dev->q_tx[qid];
 
 	spin_lock_bh(&q->lock);
-	dev->queue_ops->tx_queue_skb(dev, qid, skb, wcid, sta);
+	__mt76_tx_queue_skb(dev, qid, skb, wcid, sta, NULL);
 	dev->queue_ops->kick(dev, q);
 
 	if (q->queued > q->ndesc - 8 && !q->stopped) {
@@ -320,23 +301,13 @@ mt76_tx(struct mt76_phy *phy, struct ieee80211_sta *sta,
 EXPORT_SYMBOL_GPL(mt76_tx);
 
 static struct sk_buff *
-mt76_txq_dequeue(struct mt76_phy *phy, struct mt76_txq *mtxq, bool ps)
+mt76_txq_dequeue(struct mt76_phy *phy, struct mt76_txq *mtxq)
 {
 	struct ieee80211_txq *txq = mtxq_to_txq(mtxq);
 	struct ieee80211_tx_info *info;
 	bool ext_phy = phy != &phy->dev->phy;
 	struct sk_buff *skb;
 
-	skb = skb_dequeue(&mtxq->retry_q);
-	if (skb) {
-		u8 tid = skb->priority & IEEE80211_QOS_CTL_TID_MASK;
-
-		if (ps && skb_queue_empty(&mtxq->retry_q))
-			ieee80211_sta_set_buffered(txq->sta, tid, false);
-
-		return skb;
-	}
-
 	skb = ieee80211_tx_dequeue(phy->hw, txq);
 	if (!skb)
 		return NULL;
@@ -361,7 +332,7 @@ mt76_queue_ps_skb(struct mt76_dev *dev, struct ieee80211_sta *sta,
 			       IEEE80211_TX_CTL_REQ_TX_STATUS;
 
 	mt76_skb_set_moredata(skb, !last);
-	dev->queue_ops->tx_queue_skb(dev, MT_TXQ_PSD, skb, wcid, sta);
+	__mt76_tx_queue_skb(dev, MT_TXQ_PSD, skb, wcid, sta, NULL);
 }
 
 void
@@ -373,7 +344,7 @@ mt76_release_buffered_frames(struct ieee80211_hw *hw, struct ieee80211_sta *sta,
 	struct mt76_phy *phy = hw->priv;
 	struct mt76_dev *dev = phy->dev;
 	struct sk_buff *last_skb = NULL;
-	struct mt76_queue *hwq = dev->q_tx[MT_TXQ_PSD].q;
+	struct mt76_queue *hwq = dev->q_tx[MT_TXQ_PSD];
 	int i;
 
 	spin_lock_bh(&hwq->lock);
@@ -386,13 +357,10 @@ mt76_release_buffered_frames(struct ieee80211_hw *hw, struct ieee80211_sta *sta,
 			continue;
 
 		do {
-			skb = mt76_txq_dequeue(phy, mtxq, true);
+			skb = mt76_txq_dequeue(phy, mtxq);
 			if (!skb)
 				break;
 
-			if (mtxq->aggr)
-				mt76_check_agg_ssn(mtxq, skb);
-
 			nframes--;
 			if (last_skb)
 				mt76_queue_ps_skb(dev, sta, last_skb, false);
@@ -413,26 +381,26 @@ mt76_release_buffered_frames(struct ieee80211_hw *hw, struct ieee80211_sta *sta,
 EXPORT_SYMBOL_GPL(mt76_release_buffered_frames);
 
 static int
-mt76_txq_send_burst(struct mt76_phy *phy, struct mt76_sw_queue *sq,
+mt76_txq_send_burst(struct mt76_phy *phy, struct mt76_queue *q,
 		    struct mt76_txq *mtxq)
 {
 	struct mt76_dev *dev = phy->dev;
 	struct ieee80211_txq *txq = mtxq_to_txq(mtxq);
 	enum mt76_txq_id qid = mt76_txq_get_qid(txq);
 	struct mt76_wcid *wcid = mtxq->wcid;
-	struct mt76_queue *hwq = sq->q;
 	struct ieee80211_tx_info *info;
 	struct sk_buff *skb;
-	int n_frames = 1, limit;
-	struct ieee80211_tx_rate tx_rate;
-	bool ampdu;
-	bool probe;
+	int n_frames = 1;
+	bool stop = false;
 	int idx;
 
 	if (test_bit(MT_WCID_FLAG_PS, &wcid->flags))
 		return 0;
 
-	skb = mt76_txq_dequeue(phy, mtxq, false);
+	if (atomic_read(&wcid->non_aql_packets) >= MT_MAX_NON_AQL_PKT)
+		return 0;
+
+	skb = mt76_txq_dequeue(phy, mtxq);
 	if (!skb)
 		return 0;
 
@@ -440,62 +408,39 @@ mt76_txq_send_burst(struct mt76_phy *phy, struct mt76_sw_queue *sq,
 	if (!(wcid->tx_info & MT_WCID_TX_INFO_SET))
 		ieee80211_get_tx_rates(txq->vif, txq->sta, skb,
 				       info->control.rates, 1);
-	tx_rate = info->control.rates[0];
-
-	probe = (info->flags & IEEE80211_TX_CTL_RATE_CTRL_PROBE);
-	ampdu = IEEE80211_SKB_CB(skb)->flags & IEEE80211_TX_CTL_AMPDU;
-	limit = ampdu ? 16 : 3;
-
-	if (ampdu)
-		mt76_check_agg_ssn(mtxq, skb);
-
-	idx = dev->queue_ops->tx_queue_skb(dev, qid, skb, wcid, txq->sta);
 
+	idx = __mt76_tx_queue_skb(dev, qid, skb, wcid, txq->sta, &stop);
 	if (idx < 0)
 		return idx;
 
 	do {
-		bool cur_ampdu;
+		if (test_bit(MT76_STATE_PM, &phy->state) ||
+		    test_bit(MT76_RESET, &phy->state))
+			return -EBUSY;
 
-		if (probe)
+		if (stop)
 			break;
 
-		if (test_bit(MT76_RESET, &phy->state))
-			return -EBUSY;
+		if (q->queued + MT_TXQ_FREE_THR >= q->ndesc)
+			break;
 
-		skb = mt76_txq_dequeue(phy, mtxq, false);
+		skb = mt76_txq_dequeue(phy, mtxq);
 		if (!skb)
 			break;
 
 		info = IEEE80211_SKB_CB(skb);
-		cur_ampdu = info->flags & IEEE80211_TX_CTL_AMPDU;
-
-		if (ampdu != cur_ampdu ||
-		    (info->flags & IEEE80211_TX_CTL_RATE_CTRL_PROBE)) {
-			skb_queue_tail(&mtxq->retry_q, skb);
-			break;
-		}
+		if (!(wcid->tx_info & MT_WCID_TX_INFO_SET))
+			ieee80211_get_tx_rates(txq->vif, txq->sta, skb,
+					       info->control.rates, 1);
 
-		info->control.rates[0] = tx_rate;
-
-		if (cur_ampdu)
-			mt76_check_agg_ssn(mtxq, skb);
-
-		idx = dev->queue_ops->tx_queue_skb(dev, qid, skb, wcid,
-						   txq->sta);
+		idx = __mt76_tx_queue_skb(dev, qid, skb, wcid, txq->sta, &stop);
 		if (idx < 0)
-			return idx;
+			break;
 
 		n_frames++;
-	} while (n_frames < limit);
-
-	if (!probe) {
-		hwq->entry[idx].qid = sq - dev->q_tx;
-		hwq->entry[idx].schedule = true;
-		sq->swq_queued++;
-	}
+	} while (1);
 
-	dev->queue_ops->kick(dev, hwq);
+	dev->queue_ops->kick(dev, q);
 
 	return n_frames;
 }
@@ -504,23 +449,23 @@ static int
 mt76_txq_schedule_list(struct mt76_phy *phy, enum mt76_txq_id qid)
 {
 	struct mt76_dev *dev = phy->dev;
-	struct mt76_sw_queue *sq = &dev->q_tx[qid];
-	struct mt76_queue *hwq = sq->q;
+	struct mt76_queue *q = dev->q_tx[qid];
 	struct ieee80211_txq *txq;
 	struct mt76_txq *mtxq;
 	struct mt76_wcid *wcid;
 	int ret = 0;
 
-	spin_lock_bh(&hwq->lock);
+	spin_lock_bh(&q->lock);
 	while (1) {
-		if (sq->swq_queued >= 4)
-			break;
-
-		if (test_bit(MT76_RESET, &phy->state)) {
+		if (test_bit(MT76_STATE_PM, &phy->state) ||
+		    test_bit(MT76_RESET, &phy->state)) {
 			ret = -EBUSY;
 			break;
 		}
 
+		if (q->queued + MT_TXQ_FREE_THR >= q->ndesc)
+			break;
+
 		txq = ieee80211_next_txq(phy->hw, qid);
 		if (!txq)
 			break;
@@ -538,32 +483,26 @@ mt76_txq_schedule_list(struct mt76_phy *phy, enum mt76_txq_id qid)
 			u8 tid = txq->tid;
 
 			mtxq->send_bar = false;
-			spin_unlock_bh(&hwq->lock);
+			spin_unlock_bh(&q->lock);
 			ieee80211_send_bar(vif, sta->addr, tid, agg_ssn);
-			spin_lock_bh(&hwq->lock);
+			spin_lock_bh(&q->lock);
 		}
 
-		ret += mt76_txq_send_burst(phy, sq, mtxq);
-		ieee80211_return_txq(phy->hw, txq,
-				     !skb_queue_empty(&mtxq->retry_q));
+		ret += mt76_txq_send_burst(phy, q, mtxq);
+		ieee80211_return_txq(phy->hw, txq, false);
 	}
-	spin_unlock_bh(&hwq->lock);
+	spin_unlock_bh(&q->lock);
 
 	return ret;
 }
 
 void mt76_txq_schedule(struct mt76_phy *phy, enum mt76_txq_id qid)
 {
-	struct mt76_dev *dev = phy->dev;
-	struct mt76_sw_queue *sq = &dev->q_tx[qid];
 	int len;
 
 	if (qid >= 4)
 		return;
 
-	if (sq->swq_queued >= 4)
-		return;
-
 	rcu_read_lock();
 
 	do {
@@ -585,9 +524,9 @@ void mt76_txq_schedule_all(struct mt76_phy *phy)
 }
 EXPORT_SYMBOL_GPL(mt76_txq_schedule_all);
 
-void mt76_tx_tasklet(unsigned long data)
+void mt76_tx_worker(struct mt76_worker *w)
 {
-	struct mt76_dev *dev = (struct mt76_dev *)data;
+	struct mt76_dev *dev = container_of(w, struct mt76_dev, tx_worker);
 
 	mt76_txq_schedule_all(&dev->phy);
 	if (dev->phy2)
@@ -612,8 +551,8 @@ void mt76_stop_tx_queues(struct mt76_dev *dev, struct ieee80211_sta *sta,
 		if (!txq)
 			continue;
 
+		hwq = dev->q_tx[mt76_txq_get_qid(txq)];
 		mtxq = (struct mt76_txq *)txq->drv_priv;
-		hwq = mtxq->swq->q;
 
 		spin_lock_bh(&hwq->lock);
 		mtxq->send_bar = mtxq->aggr && send_bar;
@@ -630,38 +569,10 @@ void mt76_wake_tx_queue(struct ieee80211_hw *hw, struct ieee80211_txq *txq)
 	if (!test_bit(MT76_STATE_RUNNING, &phy->state))
 		return;
 
-	tasklet_schedule(&dev->tx_tasklet);
+	mt76_worker_schedule(&dev->tx_worker);
 }
 EXPORT_SYMBOL_GPL(mt76_wake_tx_queue);
 
-void mt76_txq_remove(struct mt76_dev *dev, struct ieee80211_txq *txq)
-{
-	struct ieee80211_hw *hw;
-	struct mt76_txq *mtxq;
-	struct sk_buff *skb;
-
-	if (!txq)
-		return;
-
-	mtxq = (struct mt76_txq *)txq->drv_priv;
-
-	while ((skb = skb_dequeue(&mtxq->retry_q)) != NULL) {
-		hw = mt76_tx_status_get_hw(dev, skb);
-		ieee80211_free_txskb(hw, skb);
-	}
-}
-EXPORT_SYMBOL_GPL(mt76_txq_remove);
-
-void mt76_txq_init(struct mt76_dev *dev, struct ieee80211_txq *txq)
-{
-	struct mt76_txq *mtxq = (struct mt76_txq *)txq->drv_priv;
-
-	skb_queue_head_init(&mtxq->retry_q);
-
-	mtxq->swq = &dev->q_tx[mt76_txq_get_qid(txq)];
-}
-EXPORT_SYMBOL_GPL(mt76_txq_init);
-
 u8 mt76_ac_to_hwq(u8 ac)
 {
 	static const u8 wmm_queue_map[] = {
@@ -678,13 +589,9 @@ u8 mt76_ac_to_hwq(u8 ac)
 }
 EXPORT_SYMBOL_GPL(mt76_ac_to_hwq);
 
-int mt76_skb_adjust_pad(struct sk_buff *skb)
+int mt76_skb_adjust_pad(struct sk_buff *skb, int pad)
 {
 	struct sk_buff *iter, *last = skb;
-	u32 pad;
-
-	/* Add zero pad of 4 - 7 bytes */
-	pad = round_up(skb->len, 4) + 4 - skb->len;
 
 	/* First packet of a A-MSDU burst keeps track of the whole burst
 	 * length, need to update length of it and the last packet.
@@ -706,3 +613,16 @@ int mt76_skb_adjust_pad(struct sk_buff *skb)
 	return 0;
 }
 EXPORT_SYMBOL_GPL(mt76_skb_adjust_pad);
+
+void mt76_queue_tx_complete(struct mt76_dev *dev, struct mt76_queue *q,
+			    struct mt76_queue_entry *e)
+{
+	if (e->skb)
+		dev->drv->tx_complete_skb(dev, e);
+
+	spin_lock_bh(&q->lock);
+	q->tail = (q->tail + 1) % q->ndesc;
+	q->queued--;
+	spin_unlock_bh(&q->lock);
+}
+EXPORT_SYMBOL_GPL(mt76_queue_tx_complete);
diff --git a/drivers/net/wireless/mediatek/mt76/usb.c b/drivers/net/wireless/mediatek/mt76/usb.c
index dcab5993763a..7d3f0a2e5fa0 100644
--- a/drivers/net/wireless/mediatek/mt76/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/usb.c
@@ -497,8 +497,8 @@ mt76u_get_next_rx_entry(struct mt76_queue *q)
 
 	spin_lock_irqsave(&q->lock, flags);
 	if (q->queued > 0) {
-		urb = q->entry[q->head].urb;
-		q->head = (q->head + 1) % q->ndesc;
+		urb = q->entry[q->tail].urb;
+		q->tail = (q->tail + 1) % q->ndesc;
 		q->queued--;
 	}
 	spin_unlock_irqrestore(&q->lock, flags);
@@ -616,16 +616,16 @@ static void mt76u_complete_rx(struct urb *urb)
 	default:
 		dev_err_ratelimited(dev->dev, "rx urb failed: %d\n",
 				    urb->status);
-		/* fall through */
+		fallthrough;
 	case 0:
 		break;
 	}
 
 	spin_lock_irqsave(&q->lock, flags);
-	if (WARN_ONCE(q->entry[q->tail].urb != urb, "rx urb mismatch"))
+	if (WARN_ONCE(q->entry[q->head].urb != urb, "rx urb mismatch"))
 		goto out;
 
-	q->tail = (q->tail + 1) % q->ndesc;
+	q->head = (q->head + 1) % q->ndesc;
 	q->queued++;
 	tasklet_schedule(&dev->usb.rx_tasklet);
 out:
@@ -792,43 +792,27 @@ int mt76u_resume_rx(struct mt76_dev *dev)
 }
 EXPORT_SYMBOL_GPL(mt76u_resume_rx);
 
-static void mt76u_tx_tasklet(unsigned long data)
+static void mt76u_tx_worker(struct mt76_worker *w)
 {
-	struct mt76_dev *dev = (struct mt76_dev *)data;
+	struct mt76_dev *dev = container_of(w, struct mt76_dev, tx_worker);
 	struct mt76_queue_entry entry;
-	struct mt76_sw_queue *sq;
 	struct mt76_queue *q;
 	bool wake;
 	int i;
 
 	for (i = 0; i < IEEE80211_NUM_ACS; i++) {
-		u32 n_dequeued = 0, n_sw_dequeued = 0;
-
-		sq = &dev->q_tx[i];
-		q = sq->q;
+		q = dev->q_tx[i];
 
-		while (q->queued > n_dequeued) {
-			if (!q->entry[q->head].done)
+		while (q->queued > 0) {
+			if (!q->entry[q->tail].done)
 				break;
 
-			if (q->entry[q->head].schedule) {
-				q->entry[q->head].schedule = false;
-				n_sw_dequeued++;
-			}
-
-			entry = q->entry[q->head];
-			q->entry[q->head].done = false;
-			q->head = (q->head + 1) % q->ndesc;
-			n_dequeued++;
+			entry = q->entry[q->tail];
+			q->entry[q->tail].done = false;
 
-			dev->drv->tx_complete_skb(dev, i, &entry);
+			mt76_queue_tx_complete(dev, q, &entry);
 		}
 
-		spin_lock_bh(&q->lock);
-
-		sq->swq_queued -= n_sw_dequeued;
-		q->queued -= n_dequeued;
-
 		wake = q->stopped && q->queued < q->ndesc - 8;
 		if (wake)
 			q->stopped = false;
@@ -836,8 +820,6 @@ static void mt76u_tx_tasklet(unsigned long data)
 		if (!q->queued)
 			wake_up(&dev->tx_wait);
 
-		spin_unlock_bh(&q->lock);
-
 		mt76_txq_schedule(&dev->phy, i);
 
 		if (dev->drv->tx_status_data &&
@@ -882,7 +864,7 @@ static void mt76u_complete_tx(struct urb *urb)
 		dev_err(dev->dev, "tx urb failed: %d\n", urb->status);
 	e->done = true;
 
-	tasklet_schedule(&dev->tx_tasklet);
+	mt76_worker_schedule(&dev->tx_worker);
 }
 
 static int
@@ -909,11 +891,11 @@ mt76u_tx_queue_skb(struct mt76_dev *dev, enum mt76_txq_id qid,
 		   struct sk_buff *skb, struct mt76_wcid *wcid,
 		   struct ieee80211_sta *sta)
 {
-	struct mt76_queue *q = dev->q_tx[qid].q;
+	struct mt76_queue *q = dev->q_tx[qid];
 	struct mt76_tx_info tx_info = {
 		.skb = skb,
 	};
-	u16 idx = q->tail;
+	u16 idx = q->head;
 	int err;
 
 	if (q->queued == q->ndesc)
@@ -932,7 +914,7 @@ mt76u_tx_queue_skb(struct mt76_dev *dev, enum mt76_txq_id qid,
 			    q->entry[idx].urb, mt76u_complete_tx,
 			    &q->entry[idx]);
 
-	q->tail = (q->tail + 1) % q->ndesc;
+	q->head = (q->head + 1) % q->ndesc;
 	q->entry[idx].skb = tx_info.skb;
 	q->queued++;
 
@@ -944,7 +926,7 @@ static void mt76u_tx_kick(struct mt76_dev *dev, struct mt76_queue *q)
 	struct urb *urb;
 	int err;
 
-	while (q->first != q->tail) {
+	while (q->first != q->head) {
 		urb = q->entry[q->first].urb;
 
 		trace_submit_urb(dev, urb);
@@ -987,10 +969,8 @@ static int mt76u_alloc_tx(struct mt76_dev *dev)
 	int i, j, err;
 
 	for (i = 0; i <= MT_TXQ_PSD; i++) {
-		INIT_LIST_HEAD(&dev->q_tx[i].swq);
-
 		if (i >= IEEE80211_NUM_ACS) {
-			dev->q_tx[i].q = dev->q_tx[0].q;
+			dev->q_tx[i] = dev->q_tx[0];
 			continue;
 		}
 
@@ -1000,7 +980,7 @@ static int mt76u_alloc_tx(struct mt76_dev *dev)
 
 		spin_lock_init(&q->lock);
 		q->hw_idx = mt76u_ac_to_hwq(dev, i);
-		dev->q_tx[i].q = q;
+		dev->q_tx[i] = q;
 
 		q->entry = devm_kcalloc(dev->dev,
 					MT_NUM_TX_ENTRIES, sizeof(*q->entry),
@@ -1027,7 +1007,7 @@ static void mt76u_free_tx(struct mt76_dev *dev)
 		struct mt76_queue *q;
 		int j;
 
-		q = dev->q_tx[i].q;
+		q = dev->q_tx[i];
 		if (!q)
 			continue;
 
@@ -1040,6 +1020,8 @@ void mt76u_stop_tx(struct mt76_dev *dev)
 {
 	int ret;
 
+	mt76_worker_disable(&dev->tx_worker);
+
 	ret = wait_event_timeout(dev->tx_wait, !mt76_has_tx_pending(&dev->phy),
 				 HZ / 5);
 	if (!ret) {
@@ -1050,7 +1032,7 @@ void mt76u_stop_tx(struct mt76_dev *dev)
 		dev_err(dev->dev, "timed out waiting for pending tx\n");
 
 		for (i = 0; i < IEEE80211_NUM_ACS; i++) {
-			q = dev->q_tx[i].q;
+			q = dev->q_tx[i];
 			if (!q)
 				continue;
 
@@ -1058,32 +1040,26 @@ void mt76u_stop_tx(struct mt76_dev *dev)
 				usb_kill_urb(q->entry[j].urb);
 		}
 
-		tasklet_kill(&dev->tx_tasklet);
-
 		/* On device removal we maight queue skb's, but mt76u_tx_kick()
 		 * will fail to submit urb, cleanup those skb's manually.
 		 */
 		for (i = 0; i < IEEE80211_NUM_ACS; i++) {
-			q = dev->q_tx[i].q;
+			q = dev->q_tx[i];
 			if (!q)
 				continue;
 
-			/* Assure we are in sync with killed tasklet. */
-			spin_lock_bh(&q->lock);
-			while (q->queued) {
-				entry = q->entry[q->head];
-				q->head = (q->head + 1) % q->ndesc;
-				q->queued--;
+			entry = q->entry[q->tail];
+			q->entry[q->tail].done = false;
 
-				dev->drv->tx_complete_skb(dev, i, &entry);
-			}
-			spin_unlock_bh(&q->lock);
+			mt76_queue_tx_complete(dev, q, &entry);
 		}
 	}
 
 	cancel_work_sync(&dev->usb.stat_work);
 	clear_bit(MT76_READING_STATS, &dev->phy.state);
 
+	mt76_worker_enable(&dev->tx_worker);
+
 	mt76_tx_status_check(dev, NULL, true);
 }
 EXPORT_SYMBOL_GPL(mt76u_stop_tx);
@@ -1133,8 +1109,8 @@ int mt76u_init(struct mt76_dev *dev,
 	mt76u_ops.rmw = ext ? mt76u_rmw_ext : mt76u_rmw;
 	mt76u_ops.write_copy = ext ? mt76u_copy_ext : mt76u_copy;
 
+	dev->tx_worker.fn = mt76u_tx_worker;
 	tasklet_init(&usb->rx_tasklet, mt76u_rx_tasklet, (unsigned long)dev);
-	tasklet_init(&dev->tx_tasklet, mt76u_tx_tasklet, (unsigned long)dev);
 	INIT_WORK(&usb->stat_work, mt76u_tx_status_data);
 
 	usb->data_len = usb_maxpacket(udev, usb_sndctrlpipe(udev, 0), 1);
diff --git a/drivers/net/wireless/mediatek/mt76/util.c b/drivers/net/wireless/mediatek/mt76/util.c
index f53bb4ae5001..581964425468 100644
--- a/drivers/net/wireless/mediatek/mt76/util.c
+++ b/drivers/net/wireless/mediatek/mt76/util.c
@@ -110,4 +110,32 @@ int mt76_get_min_avg_rssi(struct mt76_dev *dev, bool ext_phy)
 }
 EXPORT_SYMBOL_GPL(mt76_get_min_avg_rssi);
 
+int __mt76_worker_fn(void *ptr)
+{
+	struct mt76_worker *w = ptr;
+
+	while (!kthread_should_stop()) {
+		set_current_state(TASK_INTERRUPTIBLE);
+
+		if (kthread_should_park()) {
+			kthread_parkme();
+			continue;
+		}
+
+		if (!test_and_clear_bit(MT76_WORKER_SCHEDULED, &w->state)) {
+			schedule();
+			continue;
+		}
+
+		set_bit(MT76_WORKER_RUNNING, &w->state);
+		set_current_state(TASK_RUNNING);
+		w->fn(w);
+		cond_resched();
+		clear_bit(MT76_WORKER_RUNNING, &w->state);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(__mt76_worker_fn);
+
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/util.h b/drivers/net/wireless/mediatek/mt76/util.h
index fd1a68820e0a..1c363ea9ab9c 100644
--- a/drivers/net/wireless/mediatek/mt76/util.h
+++ b/drivers/net/wireless/mediatek/mt76/util.h
@@ -10,6 +10,19 @@
 #include <linux/skbuff.h>
 #include <linux/bitops.h>
 #include <linux/bitfield.h>
+#include <net/mac80211.h>
+
+struct mt76_worker
+{
+	struct task_struct *task;
+	void (*fn)(struct mt76_worker *);
+	unsigned long state;
+};
+
+enum {
+	MT76_WORKER_SCHEDULED,
+	MT76_WORKER_RUNNING,
+};
 
 #define MT76_INCR(_var, _size) \
 	(_var = (((_var) + 1) % (_size)))
@@ -45,4 +58,67 @@ mt76_skb_set_moredata(struct sk_buff *skb, bool enable)
 		hdr->frame_control &= ~cpu_to_le16(IEEE80211_FCTL_MOREDATA);
 }
 
+int __mt76_worker_fn(void *ptr);
+
+static inline int
+mt76_worker_setup(struct ieee80211_hw *hw, struct mt76_worker *w,
+		  void (*fn)(struct mt76_worker *),
+		  const char *name)
+{
+	const char *dev_name = wiphy_name(hw->wiphy);
+	int ret;
+
+	if (fn)
+		w->fn = fn;
+	w->task = kthread_create(__mt76_worker_fn, w, "mt76-%s %s",
+				 name, dev_name);
+
+	ret = PTR_ERR_OR_ZERO(w->task);
+	if (ret) {
+		w->task = NULL;
+		return ret;
+	}
+
+	wake_up_process(w->task);
+
+	return 0;
+}
+
+static inline void mt76_worker_schedule(struct mt76_worker *w)
+{
+	if (!w->task)
+		return;
+
+	if (!test_and_set_bit(MT76_WORKER_SCHEDULED, &w->state) &&
+	    !test_bit(MT76_WORKER_RUNNING, &w->state))
+		wake_up_process(w->task);
+}
+
+static inline void mt76_worker_disable(struct mt76_worker *w)
+{
+	if (!w->task)
+		return;
+
+	kthread_park(w->task);
+	WRITE_ONCE(w->state, 0);
+}
+
+static inline void mt76_worker_enable(struct mt76_worker *w)
+{
+	if (!w->task)
+		return;
+
+	kthread_unpark(w->task);
+	mt76_worker_schedule(w);
+}
+
+static inline void mt76_worker_teardown(struct mt76_worker *w)
+{
+	if (!w->task)
+		return;
+
+	kthread_stop(w->task);
+	w->task = NULL;
+}
+
 #endif
diff --git a/drivers/net/wireless/mediatek/mt7601u/debugfs.c b/drivers/net/wireless/mediatek/mt7601u/debugfs.c
index 300242bce799..20669eacb66e 100644
--- a/drivers/net/wireless/mediatek/mt7601u/debugfs.c
+++ b/drivers/net/wireless/mediatek/mt7601u/debugfs.c
@@ -30,7 +30,7 @@ mt76_reg_get(void *data, u64 *val)
 DEFINE_DEBUGFS_ATTRIBUTE(fops_regval, mt76_reg_get, mt76_reg_set, "0x%08llx\n");
 
 static int
-mt7601u_ampdu_stat_read(struct seq_file *file, void *data)
+mt7601u_ampdu_stat_show(struct seq_file *file, void *data)
 {
 	struct mt7601u_dev *dev = file->private;
 	int i, j;
@@ -73,21 +73,10 @@ mt7601u_ampdu_stat_read(struct seq_file *file, void *data)
 	return 0;
 }
 
-static int
-mt7601u_ampdu_stat_open(struct inode *inode, struct file *f)
-{
-	return single_open(f, mt7601u_ampdu_stat_read, inode->i_private);
-}
-
-static const struct file_operations fops_ampdu_stat = {
-	.open = mt7601u_ampdu_stat_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(mt7601u_ampdu_stat);
 
 static int
-mt7601u_eeprom_param_read(struct seq_file *file, void *data)
+mt7601u_eeprom_param_show(struct seq_file *file, void *data)
 {
 	struct mt7601u_dev *dev = file->private;
 	struct mt7601u_rate_power *rp = &dev->ee->power_rate_table;
@@ -131,18 +120,7 @@ mt7601u_eeprom_param_read(struct seq_file *file, void *data)
 	return 0;
 }
 
-static int
-mt7601u_eeprom_param_open(struct inode *inode, struct file *f)
-{
-	return single_open(f, mt7601u_eeprom_param_read, inode->i_private);
-}
-
-static const struct file_operations fops_eeprom_param = {
-	.open = mt7601u_eeprom_param_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(mt7601u_eeprom_param);
 
 void mt7601u_init_debugfs(struct mt7601u_dev *dev)
 {
@@ -157,6 +135,6 @@ void mt7601u_init_debugfs(struct mt7601u_dev *dev)
 
 	debugfs_create_u32("regidx", 0600, dir, &dev->debugfs_reg);
 	debugfs_create_file("regval", 0600, dir, dev, &fops_regval);
-	debugfs_create_file("ampdu_stat", 0400, dir, dev, &fops_ampdu_stat);
-	debugfs_create_file("eeprom_param", 0400, dir, dev, &fops_eeprom_param);
+	debugfs_create_file("ampdu_stat", 0400, dir, dev, &mt7601u_ampdu_stat_fops);
+	debugfs_create_file("eeprom_param", 0400, dir, dev, &mt7601u_eeprom_param_fops);
 }
diff --git a/drivers/net/wireless/microchip/wilc1000/mon.c b/drivers/net/wireless/microchip/wilc1000/mon.c
index 358ac8601333..b5a1b65c087c 100644
--- a/drivers/net/wireless/microchip/wilc1000/mon.c
+++ b/drivers/net/wireless/microchip/wilc1000/mon.c
@@ -235,11 +235,10 @@ struct net_device *wilc_wfi_init_mon_interface(struct wilc *wl,
 
 	if (register_netdevice(wl->monitor_dev)) {
 		netdev_err(real_dev, "register_netdevice failed\n");
+		free_netdev(wl->monitor_dev);
 		return NULL;
 	}
 	priv = netdev_priv(wl->monitor_dev);
-	if (!priv)
-		return NULL;
 
 	priv->real_ndev = real_dev;
 
diff --git a/drivers/net/wireless/quantenna/qtnfmac/commands.c b/drivers/net/wireless/quantenna/qtnfmac/commands.c
index f40d8c3c3d9e..f3ccbd2b1084 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/commands.c
+++ b/drivers/net/wireless/quantenna/qtnfmac/commands.c
@@ -869,6 +869,7 @@ int qtnf_cmd_send_del_intf(struct qtnf_vif *vif)
 	default:
 		pr_warn("VIF%u.%u: unsupported iftype %d\n", vif->mac->macid,
 			vif->vifid, vif->wdev.iftype);
+		dev_kfree_skb(cmd_skb);
 		ret = -EINVAL;
 		goto out;
 	}
@@ -1924,6 +1925,7 @@ int qtnf_cmd_send_change_sta(struct qtnf_vif *vif, const u8 *mac,
 		break;
 	default:
 		pr_err("unsupported iftype %d\n", vif->wdev.iftype);
+		dev_kfree_skb(cmd_skb);
 		ret = -EINVAL;
 		goto out;
 	}
diff --git a/drivers/net/wireless/quantenna/qtnfmac/core.c b/drivers/net/wireless/quantenna/qtnfmac/core.c
index 6aafff9d4231..a36d5ec297ab 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/core.c
+++ b/drivers/net/wireless/quantenna/qtnfmac/core.c
@@ -15,7 +15,6 @@
 #include "util.h"
 #include "switchdev.h"
 
-#define QTNF_DMP_MAX_LEN 48
 #define QTNF_PRIMARY_VIF_IDX	0
 
 static bool slave_radar = true;
diff --git a/drivers/net/wireless/realtek/rtlwifi/base.c b/drivers/net/wireless/realtek/rtlwifi/base.c
index 8e6f07b3c87e..6e8bd99e8911 100644
--- a/drivers/net/wireless/realtek/rtlwifi/base.c
+++ b/drivers/net/wireless/realtek/rtlwifi/base.c
@@ -436,6 +436,10 @@ static void _rtl_init_mac80211(struct ieee80211_hw *hw)
 	}
 }
 
+static void rtl_watchdog_wq_callback(struct work_struct *work);
+static void rtl_fwevt_wq_callback(struct work_struct *work);
+static void rtl_c2hcmd_wq_callback(struct work_struct *work);
+
 static void _rtl_init_deferred_work(struct ieee80211_hw *hw)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
@@ -454,17 +458,14 @@ static void _rtl_init_deferred_work(struct ieee80211_hw *hw)
 	}
 
 	INIT_DELAYED_WORK(&rtlpriv->works.watchdog_wq,
-			  (void *)rtl_watchdog_wq_callback);
+			  rtl_watchdog_wq_callback);
 	INIT_DELAYED_WORK(&rtlpriv->works.ips_nic_off_wq,
-			  (void *)rtl_ips_nic_off_wq_callback);
-	INIT_DELAYED_WORK(&rtlpriv->works.ps_work,
-			  (void *)rtl_swlps_wq_callback);
+			  rtl_ips_nic_off_wq_callback);
+	INIT_DELAYED_WORK(&rtlpriv->works.ps_work, rtl_swlps_wq_callback);
 	INIT_DELAYED_WORK(&rtlpriv->works.ps_rfon_wq,
-			  (void *)rtl_swlps_rfon_wq_callback);
-	INIT_DELAYED_WORK(&rtlpriv->works.fwevt_wq,
-			  (void *)rtl_fwevt_wq_callback);
-	INIT_DELAYED_WORK(&rtlpriv->works.c2hcmd_wq,
-			  (void *)rtl_c2hcmd_wq_callback);
+			  rtl_swlps_rfon_wq_callback);
+	INIT_DELAYED_WORK(&rtlpriv->works.fwevt_wq, rtl_fwevt_wq_callback);
+	INIT_DELAYED_WORK(&rtlpriv->works.c2hcmd_wq, rtl_c2hcmd_wq_callback);
 }
 
 void rtl_deinit_deferred_work(struct ieee80211_hw *hw, bool ips_wq)
@@ -1455,7 +1456,7 @@ static void setup_special_tx(struct rtl_priv *rtlpriv, struct rtl_ps_ctl *ppsc,
 	if (rtlpriv->cfg->ops->get_btc_status())
 		rtlpriv->btcoexist.btc_ops->btc_special_packet_notify(
 					rtlpriv, type);
-	rtl_lps_leave(hw);
+	rtl_lps_leave(hw, false);
 	ppsc->last_delaylps_stamp_jiffies = jiffies;
 }
 
@@ -1545,7 +1546,7 @@ u8 rtl_is_special_data(struct ieee80211_hw *hw, struct sk_buff *skb, u8 is_tx,
 
 		if (is_tx) {
 			rtlpriv->ra.is_special_data = true;
-			rtl_lps_leave(hw);
+			rtl_lps_leave(hw, false);
 			ppsc->last_delaylps_stamp_jiffies = jiffies;
 
 			setup_special_tx(rtlpriv, ppsc, PACKET_EAPOL);
@@ -2042,11 +2043,10 @@ label_err:
 }
 EXPORT_SYMBOL(rtl_collect_scan_list);
 
-void rtl_watchdog_wq_callback(void *data)
+static void rtl_watchdog_wq_callback(struct work_struct *work)
 {
-	struct rtl_works *rtlworks = container_of_dwork_rtl(data,
-							    struct rtl_works,
-							    watchdog_wq);
+	struct rtl_works *rtlworks = container_of(work, struct rtl_works,
+						  watchdog_wq.work);
 	struct ieee80211_hw *hw = rtlworks->hw;
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_hal *rtlhal = rtl_hal(rtl_priv(hw));
@@ -2147,9 +2147,9 @@ void rtl_watchdog_wq_callback(void *data)
 		if (rtlpriv->link_info.num_rx_inperiod +
 		      rtlpriv->link_info.num_tx_inperiod > 8 ||
 		    rtlpriv->link_info.num_rx_inperiod > 2)
-			rtl_lps_leave(hw);
+			rtl_lps_leave(hw, true);
 		else
-			rtl_lps_enter(hw);
+			rtl_lps_enter(hw, true);
 
 label_lps_done:
 		;
@@ -2239,10 +2239,10 @@ void rtl_watch_dog_timer_callback(struct timer_list *t)
 		  jiffies + MSECS(RTL_WATCH_DOG_TIME));
 }
 
-void rtl_fwevt_wq_callback(void *data)
+static void rtl_fwevt_wq_callback(struct work_struct *work)
 {
-	struct rtl_works *rtlworks =
-		container_of_dwork_rtl(data, struct rtl_works, fwevt_wq);
+	struct rtl_works *rtlworks = container_of(work, struct rtl_works,
+						  fwevt_wq.work);
 	struct ieee80211_hw *hw = rtlworks->hw;
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 
@@ -2368,11 +2368,10 @@ void rtl_c2hcmd_launcher(struct ieee80211_hw *hw, int exec)
 	}
 }
 
-void rtl_c2hcmd_wq_callback(void *data)
+static void rtl_c2hcmd_wq_callback(struct work_struct *work)
 {
-	struct rtl_works *rtlworks = container_of_dwork_rtl(data,
-							    struct rtl_works,
-							    c2hcmd_wq);
+	struct rtl_works *rtlworks = container_of(work, struct rtl_works,
+						  c2hcmd_wq.work);
 	struct ieee80211_hw *hw = rtlworks->hw;
 
 	rtl_c2hcmd_launcher(hw, 1);
diff --git a/drivers/net/wireless/realtek/rtlwifi/base.h b/drivers/net/wireless/realtek/rtlwifi/base.h
index fa92e29fffda..0e4f8a8ae3a5 100644
--- a/drivers/net/wireless/realtek/rtlwifi/base.h
+++ b/drivers/net/wireless/realtek/rtlwifi/base.h
@@ -108,9 +108,6 @@ int rtl_rx_agg_start(struct ieee80211_hw *hw,
 int rtl_rx_agg_stop(struct ieee80211_hw *hw,
 		    struct ieee80211_sta *sta, u16 tid);
 void rtl_rx_ampdu_apply(struct rtl_priv *rtlpriv);
-void rtl_watchdog_wq_callback(void *data);
-void rtl_fwevt_wq_callback(void *data);
-void rtl_c2hcmd_wq_callback(void *data);
 void rtl_c2hcmd_launcher(struct ieee80211_hw *hw, int exec);
 void rtl_c2hcmd_enqueue(struct ieee80211_hw *hw, struct sk_buff *skb);
 
diff --git a/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtcoutsrc.c b/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtcoutsrc.c
index fa4486669d9a..2c05369b79e4 100644
--- a/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtcoutsrc.c
+++ b/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtcoutsrc.c
@@ -285,7 +285,8 @@ static void halbtc_leave_lps(struct btc_coexist *btcoexist)
 
 	btcoexist->bt_info.bt_ctrl_lps = true;
 	btcoexist->bt_info.bt_lps_on = false;
-	rtl_lps_leave(rtlpriv->mac80211.hw);
+	/* FIXME: Context is unclear. Is it allowed to block? */
+	rtl_lps_leave(rtlpriv->mac80211.hw, false);
 }
 
 static void halbtc_enter_lps(struct btc_coexist *btcoexist)
@@ -306,7 +307,8 @@ static void halbtc_enter_lps(struct btc_coexist *btcoexist)
 
 	btcoexist->bt_info.bt_ctrl_lps = true;
 	btcoexist->bt_info.bt_lps_on = true;
-	rtl_lps_enter(rtlpriv->mac80211.hw);
+	/* FIXME: Context is unclear. Is it allowed to block? */
+	rtl_lps_enter(rtlpriv->mac80211.hw, false);
 }
 
 static void halbtc_normal_lps(struct btc_coexist *btcoexist)
@@ -317,7 +319,8 @@ static void halbtc_normal_lps(struct btc_coexist *btcoexist)
 
 	if (btcoexist->bt_info.bt_ctrl_lps) {
 		btcoexist->bt_info.bt_lps_on = false;
-		rtl_lps_leave(rtlpriv->mac80211.hw);
+		/* FIXME: Context is unclear. Is it allowed to block? */
+		rtl_lps_leave(rtlpriv->mac80211.hw, false);
 		btcoexist->bt_info.bt_ctrl_lps = false;
 	}
 }
@@ -328,7 +331,8 @@ static void halbtc_pre_normal_lps(struct btc_coexist *btcoexist)
 
 	if (btcoexist->bt_info.bt_ctrl_lps) {
 		btcoexist->bt_info.bt_lps_on = false;
-		rtl_lps_leave(rtlpriv->mac80211.hw);
+		/* FIXME: Context is unclear. Is it allowed to block? */
+		rtl_lps_leave(rtlpriv->mac80211.hw, false);
 	}
 }
 
diff --git a/drivers/net/wireless/realtek/rtlwifi/core.c b/drivers/net/wireless/realtek/rtlwifi/core.c
index 2529b6e0fd76..a7259dbc953d 100644
--- a/drivers/net/wireless/realtek/rtlwifi/core.c
+++ b/drivers/net/wireless/realtek/rtlwifi/core.c
@@ -544,7 +544,7 @@ static int rtl_op_suspend(struct ieee80211_hw *hw,
 	rtlhal->driver_is_goingto_unload = true;
 	rtlhal->enter_pnp_sleep = true;
 
-	rtl_lps_leave(hw);
+	rtl_lps_leave(hw, true);
 	rtl_op_stop(hw);
 	device_set_wakeup_enable(wiphy_dev(hw->wiphy), true);
 	return 0;
@@ -1151,7 +1151,7 @@ static void rtl_op_bss_info_changed(struct ieee80211_hw *hw,
 			mstatus = RT_MEDIA_DISCONNECT;
 
 			if (mac->link_state == MAC80211_LINKED)
-				rtl_lps_leave(hw);
+				rtl_lps_leave(hw, true);
 			if (ppsc->p2p_ps_info.p2p_ps_mode > P2P_PS_NONE)
 				rtl_p2p_ps_cmd(hw, P2P_PS_DISABLE);
 			mac->link_state = MAC80211_NOLINK;
@@ -1448,7 +1448,7 @@ static void rtl_op_sw_scan_start(struct ieee80211_hw *hw,
 	}
 
 	if (mac->link_state == MAC80211_LINKED) {
-		rtl_lps_leave(hw);
+		rtl_lps_leave(hw, true);
 		mac->link_state = MAC80211_LINKED_SCANNING;
 	} else {
 		rtl_ips_nic_on(hw);
diff --git a/drivers/net/wireless/realtek/rtlwifi/debug.c b/drivers/net/wireless/realtek/rtlwifi/debug.c
index 455b87e7548b..901cdfe3723c 100644
--- a/drivers/net/wireless/realtek/rtlwifi/debug.c
+++ b/drivers/net/wireless/realtek/rtlwifi/debug.c
@@ -8,26 +8,6 @@
 #include <linux/vmalloc.h>
 
 #ifdef CONFIG_RTLWIFI_DEBUG
-void _rtl_dbg_out(struct rtl_priv *rtlpriv, u64 comp, int level,
-		  const char *fmt, ...)
-{
-	if (unlikely((comp & rtlpriv->cfg->mod_params->debug_mask) &&
-		     level <= rtlpriv->cfg->mod_params->debug_level)) {
-		struct va_format vaf;
-		va_list args;
-
-		va_start(args, fmt);
-
-		vaf.fmt = fmt;
-		vaf.va = &args;
-
-		pr_info(":<%lx> %pV", in_interrupt(), &vaf);
-
-		va_end(args);
-	}
-}
-EXPORT_SYMBOL_GPL(_rtl_dbg_out);
-
 void _rtl_dbg_print(struct rtl_priv *rtlpriv, u64 comp, int level,
 		    const char *fmt, ...)
 {
diff --git a/drivers/net/wireless/realtek/rtlwifi/debug.h b/drivers/net/wireless/realtek/rtlwifi/debug.h
index 6028f1ffa5da..1c0bcf8ec1a9 100644
--- a/drivers/net/wireless/realtek/rtlwifi/debug.h
+++ b/drivers/net/wireless/realtek/rtlwifi/debug.h
@@ -149,10 +149,6 @@ enum dbgp_flag_e {
 struct rtl_priv;
 
 __printf(4, 5)
-void _rtl_dbg_out(struct rtl_priv *rtlpriv, u64 comp, int level,
-		  const char *fmt, ...);
-
-__printf(4, 5)
 void _rtl_dbg_print(struct rtl_priv *rtlpriv, u64 comp, int level,
 		    const char *fmt, ...);
 
@@ -160,8 +156,8 @@ void _rtl_dbg_print_data(struct rtl_priv *rtlpriv, u64 comp, int level,
 			 const char *titlestring,
 			 const void *hexdata, int hexdatalen);
 
-#define rtl_dbg(rtlpriv, comp, level, fmt, ...)			\
-	_rtl_dbg_out(rtlpriv, comp, level,				\
+#define rtl_dbg(rtlpriv, comp, level, fmt, ...)				\
+	_rtl_dbg_print(rtlpriv, comp, level,				\
 		       fmt, ##__VA_ARGS__)
 
 #define RTPRINT(rtlpriv, dbgtype, dbgflag, fmt, ...)			\
diff --git a/drivers/net/wireless/realtek/rtlwifi/pci.c b/drivers/net/wireless/realtek/rtlwifi/pci.c
index d9f901111e58..3776495fd9d0 100644
--- a/drivers/net/wireless/realtek/rtlwifi/pci.c
+++ b/drivers/net/wireless/realtek/rtlwifi/pci.c
@@ -621,7 +621,7 @@ tx_status_ok:
 	if (((rtlpriv->link_info.num_rx_inperiod +
 	      rtlpriv->link_info.num_tx_inperiod) > 8) ||
 	      rtlpriv->link_info.num_rx_inperiod > 2)
-		rtl_lps_leave(hw);
+		rtl_lps_leave(hw, false);
 }
 
 static int _rtl_pci_init_one_rxdesc(struct ieee80211_hw *hw,
@@ -874,7 +874,7 @@ new_trx_end:
 		if (((rtlpriv->link_info.num_rx_inperiod +
 		      rtlpriv->link_info.num_tx_inperiod) > 8) ||
 		      rtlpriv->link_info.num_rx_inperiod > 2)
-			rtl_lps_leave(hw);
+			rtl_lps_leave(hw, false);
 		skb = new_skb;
 no_new:
 		if (rtlpriv->use_new_trx_flow) {
diff --git a/drivers/net/wireless/realtek/rtlwifi/ps.c b/drivers/net/wireless/realtek/rtlwifi/ps.c
index 38442a36f599..f99882255d48 100644
--- a/drivers/net/wireless/realtek/rtlwifi/ps.c
+++ b/drivers/net/wireless/realtek/rtlwifi/ps.c
@@ -179,10 +179,10 @@ static void _rtl_ps_inactive_ps(struct ieee80211_hw *hw)
 	ppsc->swrf_processing = false;
 }
 
-void rtl_ips_nic_off_wq_callback(void *data)
+void rtl_ips_nic_off_wq_callback(struct work_struct *work)
 {
-	struct rtl_works *rtlworks =
-	    container_of_dwork_rtl(data, struct rtl_works, ips_nic_off_wq);
+	struct rtl_works *rtlworks = container_of(work, struct rtl_works,
+						  ips_nic_off_wq.work);
 	struct ieee80211_hw *hw = rtlworks->hw;
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_hal *rtlhal = rtl_hal(rtl_priv(hw));
@@ -562,10 +562,10 @@ void rtl_swlps_rf_awake(struct ieee80211_hw *hw)
 	mutex_unlock(&rtlpriv->locks.lps_mutex);
 }
 
-void rtl_swlps_rfon_wq_callback(void *data)
+void rtl_swlps_rfon_wq_callback(struct work_struct *work)
 {
-	struct rtl_works *rtlworks =
-	    container_of_dwork_rtl(data, struct rtl_works, ps_rfon_wq);
+	struct rtl_works *rtlworks = container_of(work, struct rtl_works,
+						  ps_rfon_wq.work);
 	struct ieee80211_hw *hw = rtlworks->hw;
 
 	rtl_swlps_rf_awake(hw);
@@ -653,33 +653,32 @@ void rtl_lps_change_work_callback(struct work_struct *work)
 }
 EXPORT_SYMBOL_GPL(rtl_lps_change_work_callback);
 
-void rtl_lps_enter(struct ieee80211_hw *hw)
+void rtl_lps_enter(struct ieee80211_hw *hw, bool may_block)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 
-	if (!in_interrupt())
+	if (may_block)
 		return rtl_lps_enter_core(hw);
 	rtlpriv->enter_ps = true;
 	schedule_work(&rtlpriv->works.lps_change_work);
 }
 EXPORT_SYMBOL_GPL(rtl_lps_enter);
 
-void rtl_lps_leave(struct ieee80211_hw *hw)
+void rtl_lps_leave(struct ieee80211_hw *hw, bool may_block)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 
-	if (!in_interrupt())
+	if (may_block)
 		return rtl_lps_leave_core(hw);
 	rtlpriv->enter_ps = false;
 	schedule_work(&rtlpriv->works.lps_change_work);
 }
 EXPORT_SYMBOL_GPL(rtl_lps_leave);
 
-void rtl_swlps_wq_callback(void *data)
+void rtl_swlps_wq_callback(struct work_struct *work)
 {
-	struct rtl_works *rtlworks = container_of_dwork_rtl(data,
-				     struct rtl_works,
-				     ps_work);
+	struct rtl_works *rtlworks = container_of(work, struct rtl_works,
+						  ps_work.work);
 	struct ieee80211_hw *hw = rtlworks->hw;
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	bool ps = false;
diff --git a/drivers/net/wireless/realtek/rtlwifi/ps.h b/drivers/net/wireless/realtek/rtlwifi/ps.h
index aaa2ed2bbe16..b37a929def82 100644
--- a/drivers/net/wireless/realtek/rtlwifi/ps.h
+++ b/drivers/net/wireless/realtek/rtlwifi/ps.h
@@ -10,15 +10,15 @@ bool rtl_ps_enable_nic(struct ieee80211_hw *hw);
 bool rtl_ps_disable_nic(struct ieee80211_hw *hw);
 void rtl_ips_nic_off(struct ieee80211_hw *hw);
 void rtl_ips_nic_on(struct ieee80211_hw *hw);
-void rtl_ips_nic_off_wq_callback(void *data);
-void rtl_lps_enter(struct ieee80211_hw *hw);
-void rtl_lps_leave(struct ieee80211_hw *hw);
+void rtl_ips_nic_off_wq_callback(struct work_struct *work);
+void rtl_lps_enter(struct ieee80211_hw *hw, bool may_block);
+void rtl_lps_leave(struct ieee80211_hw *hw, bool may_block);
 
 void rtl_lps_set_psmode(struct ieee80211_hw *hw, u8 rt_psmode);
 
 void rtl_swlps_beacon(struct ieee80211_hw *hw, void *data, unsigned int len);
-void rtl_swlps_wq_callback(void *data);
-void rtl_swlps_rfon_wq_callback(void *data);
+void rtl_swlps_wq_callback(struct work_struct *work);
+void rtl_swlps_rfon_wq_callback(struct work_struct *work);
 void rtl_swlps_rf_awake(struct ieee80211_hw *hw);
 void rtl_swlps_rf_sleep(struct ieee80211_hw *hw);
 void rtl_p2p_ps_cmd(struct ieee80211_hw *hw , u8 p2p_ps_state);
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/hw.c
index 4c8d71fbdd7a..63f9ea21962f 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/hw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/hw.c
@@ -774,22 +774,22 @@ static bool _rtl88ee_llt_table_init(struct ieee80211_hw *hw)
 
 	for (i = 0; i < (txpktbuf_bndy - 1); i++) {
 		status = _rtl88ee_llt_write(hw, i, i + 1);
-		if (true != status)
+		if (!status)
 			return status;
 	}
 
 	status = _rtl88ee_llt_write(hw, (txpktbuf_bndy - 1), 0xFF);
-	if (true != status)
+	if (!status)
 		return status;
 
 	for (i = txpktbuf_bndy; i < maxpage; i++) {
 		status = _rtl88ee_llt_write(hw, i, (i + 1));
-		if (true != status)
+		if (!status)
 			return status;
 	}
 
 	status = _rtl88ee_llt_write(hw, maxpage, txpktbuf_bndy);
-	if (true != status)
+	if (!status)
 		return status;
 
 	return true;
@@ -868,7 +868,7 @@ static bool _rtl88ee_init_mac(struct ieee80211_hw *hw)
 	rtl_write_byte(rtlpriv, MSR, 0x00);
 
 	if (!rtlhal->mac_func_enable) {
-		if (_rtl88ee_llt_table_init(hw) == false) {
+		if (!_rtl88ee_llt_table_init(hw)) {
 			rtl_dbg(rtlpriv, COMP_INIT, DBG_LOUD,
 				"LLT table init fail\n");
 			return false;
@@ -1067,7 +1067,7 @@ int rtl88ee_hw_init(struct ieee80211_hw *hw)
 	}
 
 	rtstatus = _rtl88ee_init_mac(hw);
-	if (rtstatus != true) {
+	if (!rtstatus) {
 		pr_info("Init MAC failed\n");
 		err = 1;
 		goto exit;
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/phy.c b/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/phy.c
index 63ec5a20b67b..9be032e8ec95 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/phy.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/phy.c
@@ -16,7 +16,12 @@ static u32 _rtl88e_phy_rf_serial_read(struct ieee80211_hw *hw,
 static void _rtl88e_phy_rf_serial_write(struct ieee80211_hw *hw,
 					enum radio_path rfpath, u32 offset,
 					u32 data);
-static u32 _rtl88e_phy_calculate_bit_shift(u32 bitmask);
+static u32 _rtl88e_phy_calculate_bit_shift(u32 bitmask)
+{
+	u32 i = ffs(bitmask);
+
+	return i ? i - 1 : 32;
+}
 static bool _rtl88e_phy_bb8188e_config_parafile(struct ieee80211_hw *hw);
 static bool _rtl88e_phy_config_mac_with_headerfile(struct ieee80211_hw *hw);
 static bool phy_config_bb_with_headerfile(struct ieee80211_hw *hw,
@@ -208,17 +213,6 @@ static void _rtl88e_phy_rf_serial_write(struct ieee80211_hw *hw,
 		rfpath, pphyreg->rf3wire_offset, data_and_addr);
 }
 
-static u32 _rtl88e_phy_calculate_bit_shift(u32 bitmask)
-{
-	u32 i;
-
-	for (i = 0; i <= 31; i++) {
-		if (((bitmask >> i) & 0x1) == 1)
-			break;
-	}
-	return i;
-}
-
 bool rtl88e_phy_mac_config(struct ieee80211_hw *hw)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
@@ -1581,7 +1575,7 @@ static void _rtl88e_phy_path_adda_on(struct ieee80211_hw *hw,
 	u32 i;
 
 	pathon = is_patha_on ? 0x04db25a4 : 0x0b1b25a4;
-	if (false == is2t) {
+	if (!is2t) {
 		pathon = 0x0bdb25a0;
 		rtl_set_bbreg(hw, addareg[0], MASKDWORD, 0x0b1b25a0);
 	} else {
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/trx.c b/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/trx.c
index 8f7689225393..b9775eec4c54 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/trx.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/trx.c
@@ -732,7 +732,7 @@ void rtl88ee_set_desc(struct ieee80211_hw *hw, u8 *pdesc8,
 {
 	__le32 *pdesc = (__le32 *)pdesc8;
 
-	if (istx == true) {
+	if (istx) {
 		switch (desc_name) {
 		case HW_DESC_OWN:
 			set_tx_desc_own(pdesc, 1);
@@ -773,7 +773,7 @@ u64 rtl88ee_get_desc(struct ieee80211_hw *hw,
 	u32 ret = 0;
 	__le32 *pdesc = (__le32 *)pdesc8;
 
-	if (istx == true) {
+	if (istx) {
 		switch (desc_name) {
 		case HW_DESC_OWN:
 			ret = get_tx_desc_own(pdesc);
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192c/phy_common.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192c/phy_common.c
index fc6c81291cf5..3d29c8dbb255 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192c/phy_common.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192c/phy_common.c
@@ -145,13 +145,9 @@ EXPORT_SYMBOL(_rtl92c_phy_rf_serial_write);
 
 u32 _rtl92c_phy_calculate_bit_shift(u32 bitmask)
 {
-	u32 i;
+	u32 i = ffs(bitmask);
 
-	for (i = 0; i <= 31; i++) {
-		if (((bitmask >> i) & 0x1) == 1)
-			break;
-	}
-	return i;
+	return i ? i - 1 : 32;
 }
 EXPORT_SYMBOL(_rtl92c_phy_calculate_bit_shift);
 
@@ -1103,7 +1099,7 @@ static void _rtl92c_phy_path_adda_on(struct ieee80211_hw *hw,
 	u32 i;
 
 	pathon = is_patha_on ? 0x04db25a4 : 0x0b1b25a4;
-	if (false == is2t) {
+	if (!is2t) {
 		pathon = 0x0bdb25a0;
 		rtl_set_bbreg(hw, addareg[0], MASKDWORD, 0x0b1b25a0);
 	} else {
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/hw.c
index d4cd186036fd..bb5a0c4aec93 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/hw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/hw.c
@@ -613,22 +613,22 @@ static bool _rtl92ce_llt_table_init(struct ieee80211_hw *hw)
 
 	for (i = 0; i < (txpktbuf_bndy - 1); i++) {
 		status = _rtl92ce_llt_write(hw, i, i + 1);
-		if (true != status)
+		if (!status)
 			return status;
 	}
 
 	status = _rtl92ce_llt_write(hw, (txpktbuf_bndy - 1), 0xFF);
-	if (true != status)
+	if (!status)
 		return status;
 
 	for (i = txpktbuf_bndy; i < maxpage; i++) {
 		status = _rtl92ce_llt_write(hw, i, (i + 1));
-		if (true != status)
+		if (!status)
 			return status;
 	}
 
 	status = _rtl92ce_llt_write(hw, maxpage, txpktbuf_bndy);
-	if (true != status)
+	if (!status)
 		return status;
 
 	return true;
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/hw.c
index 3061bd81f39e..6312fddd9c00 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/hw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/hw.c
@@ -828,7 +828,7 @@ static int _rtl92cu_init_mac(struct ieee80211_hw *hw)
 					? WMM_CHIP_B_TX_PAGE_BOUNDARY
 					: WMM_CHIP_A_TX_PAGE_BOUNDARY;
 	}
-	if (false == rtl92c_init_llt_table(hw, boundary)) {
+	if (!rtl92c_init_llt_table(hw, boundary)) {
 		pr_err("Failed to init LLT Table!\n");
 		return -EINVAL;
 	}
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/mac.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/mac.c
index d7afb6a186df..2890a495a23e 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/mac.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/mac.c
@@ -158,14 +158,14 @@ bool rtl92c_init_llt_table(struct ieee80211_hw *hw, u32 boundary)
 
 	for (i = 0; i < (boundary - 1); i++) {
 		rst = rtl92c_llt_write(hw, i , i + 1);
-		if (true != rst) {
+		if (!rst) {
 			pr_err("===> %s #1 fail\n", __func__);
 			return rst;
 		}
 	}
 	/* end of list */
 	rst = rtl92c_llt_write(hw, (boundary - 1), 0xFF);
-	if (true != rst) {
+	if (!rst) {
 		pr_err("===> %s #2 fail\n", __func__);
 		return rst;
 	}
@@ -176,14 +176,14 @@ bool rtl92c_init_llt_table(struct ieee80211_hw *hw, u32 boundary)
 	 */
 	for (i = boundary; i < LLT_LAST_ENTRY_OF_TX_PKT_BUFFER; i++) {
 		rst = rtl92c_llt_write(hw, i, (i + 1));
-		if (true != rst) {
+		if (!rst) {
 			pr_err("===> %s #3 fail\n", __func__);
 			return rst;
 		}
 	}
 	/* Let last entry point to the start entry of ring buffer */
 	rst = rtl92c_llt_write(hw, LLT_LAST_ENTRY_OF_TX_PKT_BUFFER, boundary);
-	if (true != rst) {
+	if (!rst) {
 		pr_err("===> %s #4 fail\n", __func__);
 		return rst;
 	}
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/hw.c
index 2deadc7339ce..f849291cc587 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/hw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/hw.c
@@ -563,13 +563,13 @@ static bool _rtl92de_llt_table_init(struct ieee80211_hw *hw)
 	/* 18.  LLT_table_init(Adapter);  */
 	for (i = 0; i < (txpktbuf_bndy - 1); i++) {
 		status = _rtl92de_llt_write(hw, i, i + 1);
-		if (true != status)
+		if (!status)
 			return status;
 	}
 
 	/* end of list */
 	status = _rtl92de_llt_write(hw, (txpktbuf_bndy - 1), 0xFF);
-	if (true != status)
+	if (!status)
 		return status;
 
 	/* Make the other pages as ring buffer */
@@ -578,13 +578,13 @@ static bool _rtl92de_llt_table_init(struct ieee80211_hw *hw)
 	/* Otherwise used as local loopback buffer.  */
 	for (i = txpktbuf_bndy; i < maxpage; i++) {
 		status = _rtl92de_llt_write(hw, i, (i + 1));
-		if (true != status)
+		if (!status)
 			return status;
 	}
 
 	/* Let last entry point to the start entry of ring buffer */
 	status = _rtl92de_llt_write(hw, maxpage, txpktbuf_bndy);
-	if (true != status)
+	if (!status)
 		return status;
 
 	return true;
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c
index 87804325928a..e34d33e73e52 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c
@@ -162,14 +162,9 @@ static u32 targetchnl_2g[TARGET_CHNL_NUM_2G] = {
 
 static u32 _rtl92d_phy_calculate_bit_shift(u32 bitmask)
 {
-	u32 i;
-
-	for (i = 0; i <= 31; i++) {
-		if (((bitmask >> i) & 0x1) == 1)
-			break;
-	}
+	u32 i = ffs(bitmask);
 
-	return i;
+	return i ? i - 1 : 32;
 }
 
 u32 rtl92d_phy_query_bb_reg(struct ieee80211_hw *hw, u32 regaddr, u32 bitmask)
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/dm.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/dm.c
index 140f33089c4d..997ff115b9ab 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/dm.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/dm.c
@@ -718,11 +718,11 @@ static void rtl92ee_dm_dynamic_atc_switch(struct ieee80211_hw *hw)
 			       (rtldm->cfo_ave_pre - cfo_ave) :
 			       (cfo_ave - rtldm->cfo_ave_pre);
 
-		if (cfo_ave_diff > 20 && rtldm->large_cfo_hit == 0) {
-			rtldm->large_cfo_hit = 1;
+		if (cfo_ave_diff > 20 && !rtldm->large_cfo_hit) {
+			rtldm->large_cfo_hit = true;
 			return;
 		}
-		rtldm->large_cfo_hit = 0;
+		rtldm->large_cfo_hit = false;
 
 		rtldm->cfo_ave_pre = cfo_ave;
 
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/hw.c
index 473296e808ba..88fa2e593fef 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/hw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/hw.c
@@ -794,7 +794,7 @@ static bool _rtl92ee_init_mac(struct ieee80211_hw *hw)
 	rtl_write_word(rtlpriv, REG_CR, 0x2ff);
 
 	if (!rtlhal->mac_func_enable) {
-		if (_rtl92ee_llt_table_init(hw) == false) {
+		if (!_rtl92ee_llt_table_init(hw)) {
 			rtl_dbg(rtlpriv, COMP_INIT, DBG_LOUD,
 				"LLT table init fail\n");
 			return false;
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/phy.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/phy.c
index f107a30a96f0..cc0bcaf13e96 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/phy.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/phy.c
@@ -203,13 +203,9 @@ static void _rtl92ee_phy_rf_serial_write(struct ieee80211_hw *hw,
 
 static u32 _rtl92ee_phy_calculate_bit_shift(u32 bitmask)
 {
-	u32 i;
+	u32 i = ffs(bitmask);
 
-	for (i = 0; i <= 31; i++) {
-		if (((bitmask >> i) & 0x1) == 1)
-			break;
-	}
-	return i;
+	return i ? i - 1 : 32;
 }
 
 bool rtl92ee_phy_mac_config(struct ieee80211_hw *hw)
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192se/phy.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192se/phy.c
index 3d482b8675e2..63283d9e7485 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192se/phy.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192se/phy.c
@@ -16,14 +16,9 @@
 
 static u32 _rtl92s_phy_calculate_bit_shift(u32 bitmask)
 {
-	u32 i;
-
-	for (i = 0; i <= 31; i++) {
-		if (((bitmask >> i) & 0x1) == 1)
-			break;
-	}
+	u32 i = ffs(bitmask);
 
-	return i;
+	return i ? i - 1 : 32;
 }
 
 u32 rtl92s_phy_query_bb_reg(struct ieee80211_hw *hw, u32 regaddr, u32 bitmask)
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/phy.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/phy.c
index 5ba645bc46dc..fa0eed434d4f 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/phy.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/phy.c
@@ -188,7 +188,7 @@ static bool _rtl8723e_phy_bb8192c_config_parafile(struct ieee80211_hw *hw)
 	rtl_dbg(rtlpriv, COMP_INIT, DBG_TRACE, "\n");
 	rtstatus = _rtl8723e_phy_config_bb_with_headerfile(hw,
 						BASEBAND_CONFIG_PHY_REG);
-	if (rtstatus != true) {
+	if (!rtstatus) {
 		pr_err("Write BB Reg Fail!!\n");
 		return false;
 	}
@@ -202,13 +202,13 @@ static bool _rtl8723e_phy_bb8192c_config_parafile(struct ieee80211_hw *hw)
 		rtstatus = _rtl8723e_phy_config_bb_with_pgheaderfile(hw,
 					BASEBAND_CONFIG_PHY_REG);
 	}
-	if (rtstatus != true) {
+	if (!rtstatus) {
 		pr_err("BB_PG Reg Fail!!\n");
 		return false;
 	}
 	rtstatus =
 	  _rtl8723e_phy_config_bb_with_headerfile(hw, BASEBAND_CONFIG_AGC_TAB);
-	if (rtstatus != true) {
+	if (!rtstatus) {
 		pr_err("AGC Table Fail\n");
 		return false;
 	}
@@ -622,7 +622,7 @@ void rtl8723e_phy_set_txpower_level(struct ieee80211_hw *hw, u8 channel)
 	struct rtl_efuse *rtlefuse = rtl_efuse(rtl_priv(hw));
 	u8 cckpowerlevel[2], ofdmpowerlevel[2];
 
-	if (rtlefuse->txpwr_fromeprom == false)
+	if (!rtlefuse->txpwr_fromeprom)
 		return;
 	_rtl8723e_get_txpower_index(hw, channel,
 				    &cckpowerlevel[0], &ofdmpowerlevel[0]);
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/rf.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/rf.c
index ecec8c9f0992..b8ed80c84266 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/rf.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/rf.c
@@ -49,7 +49,7 @@ void rtl8723e_phy_rf6052_set_cck_txpower(struct ieee80211_hw *hw,
 	if (rtlefuse->eeprom_regulatory != 0)
 		turbo_scanoff = true;
 
-	if (mac->act_scanning == true) {
+	if (mac->act_scanning) {
 		tx_agc[RF90_PATH_A] = 0x3f3f3f3f;
 		tx_agc[RF90_PATH_B] = 0x3f3f3f3f;
 
@@ -479,7 +479,7 @@ static bool _rtl8723e_phy_rf6052_config_parafile(struct ieee80211_hw *hw)
 			break;
 		}
 
-		if (rtstatus != true) {
+		if (!rtstatus) {
 			rtl_dbg(rtlpriv, COMP_INIT, DBG_TRACE,
 				"Radio[%d] Fail!!\n", rfpath);
 			return false;
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/trx.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/trx.c
index 159f86e665f9..e3ee91b7ea8d 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/trx.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/trx.c
@@ -589,7 +589,7 @@ void rtl8723e_set_desc(struct ieee80211_hw *hw, u8 *pdesc8,
 {
 	__le32 *pdesc = (__le32 *)pdesc8;
 
-	if (istx == true) {
+	if (istx) {
 		switch (desc_name) {
 		case HW_DESC_OWN:
 			set_tx_desc_own(pdesc, 1);
@@ -630,7 +630,7 @@ u64 rtl8723e_get_desc(struct ieee80211_hw *hw,
 	u32 ret = 0;
 	__le32 *pdesc = (__le32 *)pdesc8;
 
-	if (istx == true) {
+	if (istx) {
 		switch (desc_name) {
 		case HW_DESC_OWN:
 			ret = get_tx_desc_own(pdesc);
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/dm.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/dm.c
index fbcff23eb058..c3c990cc032f 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/dm.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/dm.c
@@ -1152,11 +1152,11 @@ static void rtl8723be_dm_dynamic_atc_switch(struct ieee80211_hw *hw)
 			       (rtldm->cfo_ave_pre - cfo_ave) :
 			       (cfo_ave - rtldm->cfo_ave_pre);
 
-		if (cfo_ave_diff > 20 && rtldm->large_cfo_hit == 0) {
-			rtldm->large_cfo_hit = 1;
+		if (cfo_ave_diff > 20 && !rtldm->large_cfo_hit) {
+			rtldm->large_cfo_hit = true;
 			return;
 		} else
-			rtldm->large_cfo_hit = 0;
+			rtldm->large_cfo_hit = false;
 
 		rtldm->cfo_ave_pre = cfo_ave;
 
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/hw.c
index 3c7ba8214daf..0748aedce2ad 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/hw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/hw.c
@@ -858,7 +858,7 @@ static bool _rtl8723be_init_mac(struct ieee80211_hw *hw)
 	rtl_write_word(rtlpriv, REG_CR, 0x2ff);
 
 	if (!rtlhal->mac_func_enable) {
-		if (_rtl8723be_llt_table_init(hw) == false)
+		if (!_rtl8723be_llt_table_init(hw))
 			return false;
 	}
 
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723com/phy_common.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723com/phy_common.c
index 097f21f6d35b..47b6c1aa36b0 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8723com/phy_common.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723com/phy_common.c
@@ -53,13 +53,9 @@ EXPORT_SYMBOL_GPL(rtl8723_phy_set_bb_reg);
 
 u32 rtl8723_phy_calculate_bit_shift(u32 bitmask)
 {
-	u32 i;
+	u32 i = ffs(bitmask);
 
-	for (i = 0; i <= 31; i++) {
-		if (((bitmask >> i) & 0x1) == 1)
-			break;
-	}
-	return i;
+	return i ? i - 1 : 32;
 }
 EXPORT_SYMBOL_GPL(rtl8723_phy_calculate_bit_shift);
 
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/dm.c b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/dm.c
index 93893825e6d6..f6bff0ebd6b0 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/dm.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/dm.c
@@ -2677,13 +2677,13 @@ static void rtl8821ae_dm_dynamic_atc_switch(struct ieee80211_hw *hw)
 						(rtldm->cfo_ave_pre - cfo_ave) :
 						(cfo_ave - rtldm->cfo_ave_pre);
 
-		if (cfo_ave_diff > 20 && rtldm->large_cfo_hit == 0) {
+		if (cfo_ave_diff > 20 && !rtldm->large_cfo_hit) {
 			rtl_dbg(rtlpriv, COMP_DIG, DBG_LOUD,
 				"first large CFO hit\n");
-			rtldm->large_cfo_hit = 1;
+			rtldm->large_cfo_hit = true;
 			return;
 		} else
-			rtldm->large_cfo_hit = 0;
+			rtldm->large_cfo_hit = false;
 
 		rtldm->cfo_ave_pre = cfo_ave;
 
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.c
index b2e5b9fda669..33ffc24d3675 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.c
@@ -1894,7 +1894,7 @@ int rtl8821ae_hw_init(struct ieee80211_hw *hw)
 	}
 
 	rtstatus = _rtl8821ae_init_mac(hw);
-	if (rtstatus != true) {
+	if (!rtstatus) {
 		pr_err("Init MAC failed\n");
 		err = 1;
 		return err;
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/phy.c b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/phy.c
index 7832fae3d00f..f41a7643b9c4 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/phy.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/phy.c
@@ -27,7 +27,12 @@ static u32 _rtl8821ae_phy_rf_serial_read(struct ieee80211_hw *hw,
 static void _rtl8821ae_phy_rf_serial_write(struct ieee80211_hw *hw,
 					   enum radio_path rfpath, u32 offset,
 					   u32 data);
-static u32 _rtl8821ae_phy_calculate_bit_shift(u32 bitmask);
+static u32 _rtl8821ae_phy_calculate_bit_shift(u32 bitmask)
+{
+	u32 i = ffs(bitmask);
+
+	return i ? i - 1 : 32;
+}
 static bool _rtl8821ae_phy_bb8821a_config_parafile(struct ieee80211_hw *hw);
 /*static bool _rtl8812ae_phy_config_mac_with_headerfile(struct ieee80211_hw *hw);*/
 static bool _rtl8821ae_phy_config_mac_with_headerfile(struct ieee80211_hw *hw);
@@ -272,17 +277,6 @@ static void _rtl8821ae_phy_rf_serial_write(struct ieee80211_hw *hw,
 		rfpath, pphyreg->rf3wire_offset, data_and_addr);
 }
 
-static u32 _rtl8821ae_phy_calculate_bit_shift(u32 bitmask)
-{
-	u32 i;
-
-	for (i = 0; i <= 31; i++) {
-		if (((bitmask >> i) & 0x1) == 1)
-			break;
-	}
-	return i;
-}
-
 bool rtl8821ae_phy_mac_config(struct ieee80211_hw *hw)
 {
 	bool rtstatus = 0;
@@ -1813,7 +1807,7 @@ static bool _rtl8821ae_phy_bb8821a_config_parafile(struct ieee80211_hw *hw)
 
 	rtstatus = _rtl8821ae_phy_config_bb_with_headerfile(hw,
 						       BASEBAND_CONFIG_PHY_REG);
-	if (rtstatus != true) {
+	if (!rtstatus) {
 		pr_err("Write BB Reg Fail!!\n");
 		return false;
 	}
@@ -1822,7 +1816,7 @@ static bool _rtl8821ae_phy_bb8821a_config_parafile(struct ieee80211_hw *hw)
 		rtstatus = _rtl8821ae_phy_config_bb_with_pgheaderfile(hw,
 						    BASEBAND_CONFIG_PHY_REG);
 	}
-	if (rtstatus != true) {
+	if (!rtstatus) {
 		pr_err("BB_PG Reg Fail!!\n");
 		return false;
 	}
@@ -1836,7 +1830,7 @@ static bool _rtl8821ae_phy_bb8821a_config_parafile(struct ieee80211_hw *hw)
 	rtstatus = _rtl8821ae_phy_config_bb_with_headerfile(hw,
 						BASEBAND_CONFIG_AGC_TAB);
 
-	if (rtstatus != true) {
+	if (!rtstatus) {
 		pr_err("AGC Table Fail\n");
 		return false;
 	}
diff --git a/drivers/net/wireless/realtek/rtlwifi/wifi.h b/drivers/net/wireless/realtek/rtlwifi/wifi.h
index 13421cf2d201..7e80fd829014 100644
--- a/drivers/net/wireless/realtek/rtlwifi/wifi.h
+++ b/drivers/net/wireless/realtek/rtlwifi/wifi.h
@@ -2936,9 +2936,6 @@ enum bt_radio_shared {
 #define	RT_SET_PS_LEVEL(ppsc, _ps_flg)		\
 	(ppsc->cur_ps_level |= _ps_flg)
 
-#define container_of_dwork_rtl(x, y, z) \
-	container_of(to_delayed_work(x), y, z)
-
 #define FILL_OCTET_STRING(_os, _octet, _len)	\
 		(_os).octet = (u8 *)(_octet);		\
 		(_os).length = (_len);
diff --git a/drivers/net/wireless/realtek/rtw88/debug.c b/drivers/net/wireless/realtek/rtw88/debug.c
index 985cf5d60615..3852c4f0ac0b 100644
--- a/drivers/net/wireless/realtek/rtw88/debug.c
+++ b/drivers/net/wireless/realtek/rtw88/debug.c
@@ -229,7 +229,8 @@ static int rtw_debugfs_get_rsvd_page(struct seq_file *m, void *v)
 	if (!buf)
 		return -ENOMEM;
 
-	ret = rtw_dump_drv_rsvd_page(rtwdev, offset, buf_size, (u32 *)buf);
+	ret = rtw_fw_dump_fifo(rtwdev, RTW_FW_FIFO_SEL_RSVD_PAGE, offset,
+			       buf_size, (u32 *)buf);
 	if (ret) {
 		rtw_err(rtwdev, "failed to dump rsvd page\n");
 		vfree(buf);
@@ -543,6 +544,28 @@ static void rtw_print_rate(struct seq_file *m, u8 rate)
 	}
 }
 
+#define case_REGD(src) \
+	case RTW_REGD_##src: return #src
+
+static const char *rtw_get_regd_string(u8 regd)
+{
+	switch (regd) {
+	case_REGD(FCC);
+	case_REGD(MKK);
+	case_REGD(ETSI);
+	case_REGD(IC);
+	case_REGD(KCC);
+	case_REGD(ACMA);
+	case_REGD(CHILE);
+	case_REGD(UKRAINE);
+	case_REGD(MEXICO);
+	case_REGD(CN);
+	case_REGD(WW);
+	default:
+		return "Unknown";
+	}
+}
+
 static int rtw_debugfs_get_tx_pwr_tbl(struct seq_file *m, void *v)
 {
 	struct rtw_debugfs_priv *debugfs_priv = m->private;
@@ -554,6 +577,7 @@ static int rtw_debugfs_get_tx_pwr_tbl(struct seq_file *m, void *v)
 	u8 ch = hal->current_channel;
 	u8 regd = rtwdev->regd.txpwr_regd;
 
+	seq_printf(m, "regulatory: %s\n", rtw_get_regd_string(regd));
 	seq_printf(m, "%-4s %-10s %-3s%6s %-4s %4s (%-4s %-4s) %-4s\n",
 		   "path", "rate", "pwr", "", "base", "", "byr", "lmt", "rem");
 
diff --git a/drivers/net/wireless/realtek/rtw88/fw.c b/drivers/net/wireless/realtek/rtw88/fw.c
index 63b00bc19000..042015bc8055 100644
--- a/drivers/net/wireless/realtek/rtw88/fw.c
+++ b/drivers/net/wireless/realtek/rtw88/fw.c
@@ -193,6 +193,15 @@ void rtw_fw_c2h_cmd_rx_irqsafe(struct rtw_dev *rtwdev, u32 pkt_offset,
 }
 EXPORT_SYMBOL(rtw_fw_c2h_cmd_rx_irqsafe);
 
+void rtw_fw_c2h_cmd_isr(struct rtw_dev *rtwdev)
+{
+	if (rtw_read8(rtwdev, REG_MCU_TST_CFG) == VAL_FW_TRIGGER)
+		rtw_fw_recovery(rtwdev);
+	else
+		rtw_warn(rtwdev, "unhandled firmware c2h interrupt\n");
+}
+EXPORT_SYMBOL(rtw_fw_c2h_cmd_isr);
+
 static void rtw_fw_send_h2c_command(struct rtw_dev *rtwdev,
 				    u8 *h2c)
 {
@@ -1404,29 +1413,16 @@ free:
 	return ret;
 }
 
-int rtw_dump_drv_rsvd_page(struct rtw_dev *rtwdev,
-			   u32 offset, u32 size, u32 *buf)
+static void rtw_fw_read_fifo_page(struct rtw_dev *rtwdev, u32 offset, u32 size,
+				  u32 *buf, u32 residue, u16 start_pg)
 {
-	struct rtw_fifo_conf *fifo = &rtwdev->fifo;
-	u32 residue, i;
-	u16 start_pg;
+	u32 i;
 	u16 idx = 0;
 	u16 ctl;
 	u8 rcr;
 
-	if (size & 0x3) {
-		rtw_warn(rtwdev, "should be 4-byte aligned\n");
-		return -EINVAL;
-	}
-
-	offset += fifo->rsvd_boundary << TX_PAGE_SIZE_SHIFT;
-	residue = offset & (FIFO_PAGE_SIZE - 1);
-	start_pg = offset >> FIFO_PAGE_SIZE_SHIFT;
-	start_pg += RSVD_PAGE_START_ADDR;
-
 	rcr = rtw_read8(rtwdev, REG_RCR + 2);
 	ctl = rtw_read16(rtwdev, REG_PKTBUF_DBG_CTRL) & 0xf000;
-
 	/* disable rx clock gate */
 	rtw_write8(rtwdev, REG_RCR, rcr | BIT(3));
 
@@ -1448,6 +1444,64 @@ int rtw_dump_drv_rsvd_page(struct rtw_dev *rtwdev,
 out:
 	rtw_write16(rtwdev, REG_PKTBUF_DBG_CTRL, ctl);
 	rtw_write8(rtwdev, REG_RCR + 2, rcr);
+}
+
+static void rtw_fw_read_fifo(struct rtw_dev *rtwdev, enum rtw_fw_fifo_sel sel,
+			     u32 offset, u32 size, u32 *buf)
+{
+	struct rtw_chip_info *chip = rtwdev->chip;
+	u32 start_pg, residue;
+
+	if (sel >= RTW_FW_FIFO_MAX) {
+		rtw_dbg(rtwdev, RTW_DBG_FW, "wrong fw fifo sel\n");
+		return;
+	}
+	if (sel == RTW_FW_FIFO_SEL_RSVD_PAGE)
+		offset += rtwdev->fifo.rsvd_boundary << TX_PAGE_SIZE_SHIFT;
+	residue = offset & (FIFO_PAGE_SIZE - 1);
+	start_pg = (offset >> FIFO_PAGE_SIZE_SHIFT) + chip->fw_fifo_addr[sel];
+
+	rtw_fw_read_fifo_page(rtwdev, offset, size, buf, residue, start_pg);
+}
+
+static bool rtw_fw_dump_check_size(struct rtw_dev *rtwdev,
+				   enum rtw_fw_fifo_sel sel,
+				   u32 start_addr, u32 size)
+{
+	switch (sel) {
+	case RTW_FW_FIFO_SEL_TX:
+	case RTW_FW_FIFO_SEL_RX:
+		if ((start_addr + size) > rtwdev->chip->fw_fifo_addr[sel])
+			return false;
+		/*fall through*/
+	default:
+		return true;
+	}
+}
+
+int rtw_fw_dump_fifo(struct rtw_dev *rtwdev, u8 fifo_sel, u32 addr, u32 size,
+		     u32 *buffer)
+{
+	if (!rtwdev->chip->fw_fifo_addr) {
+		rtw_dbg(rtwdev, RTW_DBG_FW, "chip not support dump fw fifo\n");
+		return -ENOTSUPP;
+	}
+
+	if (size == 0 || !buffer)
+		return -EINVAL;
+
+	if (size & 0x3) {
+		rtw_dbg(rtwdev, RTW_DBG_FW, "not 4byte alignment\n");
+		return -EINVAL;
+	}
+
+	if (!rtw_fw_dump_check_size(rtwdev, fifo_sel, addr, size)) {
+		rtw_dbg(rtwdev, RTW_DBG_FW, "fw fifo dump size overflow\n");
+		return -EINVAL;
+	}
+
+	rtw_fw_read_fifo(rtwdev, fifo_sel, addr, size, buffer);
+
 	return 0;
 }
 
diff --git a/drivers/net/wireless/realtek/rtw88/fw.h b/drivers/net/wireless/realtek/rtw88/fw.h
index 686dcd3bbda6..08644540d259 100644
--- a/drivers/net/wireless/realtek/rtw88/fw.h
+++ b/drivers/net/wireless/realtek/rtw88/fw.h
@@ -16,7 +16,6 @@
 
 #define FIFO_PAGE_SIZE_SHIFT		12
 #define FIFO_PAGE_SIZE			4096
-#define RSVD_PAGE_START_ADDR		0x780
 #define FIFO_DUMP_ADDR			0x8000
 
 #define DLFW_PAGE_SIZE_SHIFT_LEGACY	12
@@ -508,6 +507,20 @@ static inline void rtw_h2c_pkt_set_header(u8 *h2c_pkt, u8 sub_id)
 #define SET_NLO_LOC_NLO_INFO(h2c_pkt, value)                                   \
 	le32p_replace_bits((__le32 *)(h2c_pkt) + 0x00, value, GENMASK(23, 16))
 
+#define GET_FW_DUMP_LEN(_header)					\
+	le32_get_bits(*((__le32 *)(_header) + 0x00), GENMASK(15, 0))
+#define GET_FW_DUMP_SEQ(_header)					\
+	le32_get_bits(*((__le32 *)(_header) + 0x00), GENMASK(22, 16))
+#define GET_FW_DUMP_MORE(_header)					\
+	le32_get_bits(*((__le32 *)(_header) + 0x00), BIT(23))
+#define GET_FW_DUMP_VERSION(_header)					\
+	le32_get_bits(*((__le32 *)(_header) + 0x00), GENMASK(31, 24))
+#define GET_FW_DUMP_TLV_TYPE(_header)					\
+	le32_get_bits(*((__le32 *)(_header) + 0x01), GENMASK(15, 0))
+#define GET_FW_DUMP_TLV_LEN(_header)					\
+	le32_get_bits(*((__le32 *)(_header) + 0x01), GENMASK(31, 16))
+#define GET_FW_DUMP_TLV_VAL(_header)					\
+	le32_get_bits(*((__le32 *)(_header) + 0x02), GENMASK(31, 0))
 static inline struct rtw_c2h_cmd *get_c2h_from_skb(struct sk_buff *skb)
 {
 	u32 pkt_offset;
@@ -564,5 +577,8 @@ void rtw_fw_update_pkt_probe_req(struct rtw_dev *rtwdev,
 				 struct cfg80211_ssid *ssid);
 void rtw_fw_channel_switch(struct rtw_dev *rtwdev, bool enable);
 void rtw_fw_h2c_cmd_dbg(struct rtw_dev *rtwdev, u8 *h2c);
+void rtw_fw_c2h_cmd_isr(struct rtw_dev *rtwdev);
+int rtw_fw_dump_fifo(struct rtw_dev *rtwdev, u8 fifo_sel, u32 addr, u32 size,
+		     u32 *buffer);
 
 #endif
diff --git a/drivers/net/wireless/realtek/rtw88/mac80211.c b/drivers/net/wireless/realtek/rtw88/mac80211.c
index 6b199152abcf..c92fba2fa480 100644
--- a/drivers/net/wireless/realtek/rtw88/mac80211.c
+++ b/drivers/net/wireless/realtek/rtw88/mac80211.c
@@ -358,13 +358,10 @@ static void rtw_ops_bss_info_changed(struct ieee80211_hw *hw,
 	rtw_leave_lps_deep(rtwdev);
 
 	if (changed & BSS_CHANGED_ASSOC) {
-		enum rtw_net_type net_type;
-
+		rtw_vif_assoc_changed(rtwvif, conf);
 		if (conf->assoc) {
 			rtw_coex_connect_notify(rtwdev, COEX_ASSOCIATE_FINISH);
-			net_type = RTW_NET_MGD_LINKED;
 
-			rtwvif->aid = conf->aid;
 			rtw_fw_download_rsvd_page(rtwdev);
 			rtw_send_rsvd_page_h2c(rtwdev);
 			rtw_coex_media_status_notify(rtwdev, conf->assoc);
@@ -372,12 +369,9 @@ static void rtw_ops_bss_info_changed(struct ieee80211_hw *hw,
 				rtw_bf_assoc(rtwdev, vif, conf);
 		} else {
 			rtw_leave_lps(rtwdev);
-			net_type = RTW_NET_NO_LINK;
-			rtwvif->aid = 0;
 			rtw_bf_disassoc(rtwdev, vif, conf);
 		}
 
-		rtwvif->net_type = net_type;
 		config |= PORT_SET_NET_TYPE;
 		config |= PORT_SET_AID;
 	}
@@ -429,56 +423,17 @@ static int rtw_ops_conf_tx(struct ieee80211_hw *hw,
 	return 0;
 }
 
-static u8 rtw_acquire_macid(struct rtw_dev *rtwdev)
-{
-	unsigned long mac_id;
-
-	mac_id = find_first_zero_bit(rtwdev->mac_id_map, RTW_MAX_MAC_ID_NUM);
-	if (mac_id < RTW_MAX_MAC_ID_NUM)
-		set_bit(mac_id, rtwdev->mac_id_map);
-
-	return mac_id;
-}
-
-static void rtw_release_macid(struct rtw_dev *rtwdev, u8 mac_id)
-{
-	clear_bit(mac_id, rtwdev->mac_id_map);
-}
-
 static int rtw_ops_sta_add(struct ieee80211_hw *hw,
 			   struct ieee80211_vif *vif,
 			   struct ieee80211_sta *sta)
 {
 	struct rtw_dev *rtwdev = hw->priv;
-	struct rtw_sta_info *si = (struct rtw_sta_info *)sta->drv_priv;
-	int i;
 	int ret = 0;
 
 	mutex_lock(&rtwdev->mutex);
-
-	si->mac_id = rtw_acquire_macid(rtwdev);
-	if (si->mac_id >= RTW_MAX_MAC_ID_NUM) {
-		ret = -ENOSPC;
-		goto out;
-	}
-
-	si->sta = sta;
-	si->vif = vif;
-	si->init_ra_lv = 1;
-	ewma_rssi_init(&si->avg_rssi);
-	for (i = 0; i < ARRAY_SIZE(sta->txq); i++)
-		rtw_txq_init(rtwdev, sta->txq[i]);
-
-	rtw_update_sta_info(rtwdev, si);
-	rtw_fw_media_status_report(rtwdev, si->mac_id, true);
-
-	rtwdev->sta_cnt++;
-
-	rtw_info(rtwdev, "sta %pM joined with macid %d\n",
-		 sta->addr, si->mac_id);
-
-out:
+	ret = rtw_sta_add(rtwdev, sta, vif);
 	mutex_unlock(&rtwdev->mutex);
+
 	return ret;
 }
 
@@ -487,25 +442,11 @@ static int rtw_ops_sta_remove(struct ieee80211_hw *hw,
 			      struct ieee80211_sta *sta)
 {
 	struct rtw_dev *rtwdev = hw->priv;
-	struct rtw_sta_info *si = (struct rtw_sta_info *)sta->drv_priv;
-	int i;
 
 	mutex_lock(&rtwdev->mutex);
-
-	rtw_release_macid(rtwdev, si->mac_id);
-	rtw_fw_media_status_report(rtwdev, si->mac_id, false);
-
-	for (i = 0; i < ARRAY_SIZE(sta->txq); i++)
-		rtw_txq_cleanup(rtwdev, sta->txq[i]);
-
-	kfree(si->mask);
-
-	rtwdev->sta_cnt--;
-
-	rtw_info(rtwdev, "sta %pM with macid %d left\n",
-		 sta->addr, si->mac_id);
-
+	rtw_sta_remove(rtwdev, sta, true);
 	mutex_unlock(&rtwdev->mutex);
+
 	return 0;
 }
 
@@ -845,6 +786,17 @@ static void rtw_ops_set_wakeup(struct ieee80211_hw *hw, bool enabled)
 }
 #endif
 
+static void rtw_reconfig_complete(struct ieee80211_hw *hw,
+				  enum ieee80211_reconfig_type reconfig_type)
+{
+	struct rtw_dev *rtwdev = hw->priv;
+
+	mutex_lock(&rtwdev->mutex);
+	if (reconfig_type == IEEE80211_RECONFIG_TYPE_RESTART)
+		clear_bit(RTW_FLAG_RESTARTING, rtwdev->flags);
+	mutex_unlock(&rtwdev->mutex);
+}
+
 const struct ieee80211_ops rtw_ops = {
 	.tx			= rtw_ops_tx,
 	.wake_tx_queue		= rtw_ops_wake_tx_queue,
@@ -871,6 +823,7 @@ const struct ieee80211_ops rtw_ops = {
 	.set_bitrate_mask	= rtw_ops_set_bitrate_mask,
 	.set_antenna		= rtw_ops_set_antenna,
 	.get_antenna		= rtw_ops_get_antenna,
+	.reconfig_complete	= rtw_reconfig_complete,
 #ifdef CONFIG_PM
 	.suspend		= rtw_ops_suspend,
 	.resume			= rtw_ops_resume,
diff --git a/drivers/net/wireless/realtek/rtw88/main.c b/drivers/net/wireless/realtek/rtw88/main.c
index 9770982b2f14..565efd880624 100644
--- a/drivers/net/wireless/realtek/rtw88/main.c
+++ b/drivers/net/wireless/realtek/rtw88/main.c
@@ -259,6 +259,198 @@ static void rtw_c2h_work(struct work_struct *work)
 	}
 }
 
+static u8 rtw_acquire_macid(struct rtw_dev *rtwdev)
+{
+	unsigned long mac_id;
+
+	mac_id = find_first_zero_bit(rtwdev->mac_id_map, RTW_MAX_MAC_ID_NUM);
+	if (mac_id < RTW_MAX_MAC_ID_NUM)
+		set_bit(mac_id, rtwdev->mac_id_map);
+
+	return mac_id;
+}
+
+int rtw_sta_add(struct rtw_dev *rtwdev, struct ieee80211_sta *sta,
+		struct ieee80211_vif *vif)
+{
+	struct rtw_sta_info *si = (struct rtw_sta_info *)sta->drv_priv;
+	int i;
+
+	si->mac_id = rtw_acquire_macid(rtwdev);
+	if (si->mac_id >= RTW_MAX_MAC_ID_NUM)
+		return -ENOSPC;
+
+	si->sta = sta;
+	si->vif = vif;
+	si->init_ra_lv = 1;
+	ewma_rssi_init(&si->avg_rssi);
+	for (i = 0; i < ARRAY_SIZE(sta->txq); i++)
+		rtw_txq_init(rtwdev, sta->txq[i]);
+
+	rtw_update_sta_info(rtwdev, si);
+	rtw_fw_media_status_report(rtwdev, si->mac_id, true);
+
+	rtwdev->sta_cnt++;
+	rtw_info(rtwdev, "sta %pM joined with macid %d\n",
+		 sta->addr, si->mac_id);
+
+	return 0;
+}
+
+void rtw_sta_remove(struct rtw_dev *rtwdev, struct ieee80211_sta *sta,
+		    bool fw_exist)
+{
+	struct rtw_sta_info *si = (struct rtw_sta_info *)sta->drv_priv;
+	int i;
+
+	rtw_release_macid(rtwdev, si->mac_id);
+	if (fw_exist)
+		rtw_fw_media_status_report(rtwdev, si->mac_id, false);
+
+	for (i = 0; i < ARRAY_SIZE(sta->txq); i++)
+		rtw_txq_cleanup(rtwdev, sta->txq[i]);
+
+	kfree(si->mask);
+
+	rtwdev->sta_cnt--;
+	rtw_info(rtwdev, "sta %pM with macid %d left\n",
+		 sta->addr, si->mac_id);
+}
+
+static bool rtw_fw_dump_crash_log(struct rtw_dev *rtwdev)
+{
+	u32 size = rtwdev->chip->fw_rxff_size;
+	u32 *buf;
+	u8 seq;
+	bool ret = true;
+
+	buf = vmalloc(size);
+	if (!buf)
+		goto exit;
+
+	if (rtw_fw_dump_fifo(rtwdev, RTW_FW_FIFO_SEL_RXBUF_FW, 0, size, buf)) {
+		rtw_dbg(rtwdev, RTW_DBG_FW, "dump fw fifo fail\n");
+		goto free_buf;
+	}
+
+	if (GET_FW_DUMP_LEN(buf) == 0) {
+		rtw_dbg(rtwdev, RTW_DBG_FW, "fw crash dump's length is 0\n");
+		goto free_buf;
+	}
+
+	seq = GET_FW_DUMP_SEQ(buf);
+	if (seq > 0 && seq != (rtwdev->fw.prev_dump_seq + 1)) {
+		rtw_dbg(rtwdev, RTW_DBG_FW,
+			"fw crash dump's seq is wrong: %d\n", seq);
+		goto free_buf;
+	}
+	if (seq == 0 &&
+	    (GET_FW_DUMP_TLV_TYPE(buf) != FW_CD_TYPE ||
+	     GET_FW_DUMP_TLV_LEN(buf) != FW_CD_LEN ||
+	     GET_FW_DUMP_TLV_VAL(buf) != FW_CD_VAL)) {
+		rtw_dbg(rtwdev, RTW_DBG_FW, "fw crash dump's tlv is wrong\n");
+		goto free_buf;
+	}
+
+	print_hex_dump_bytes("rtw88 fw dump: ", DUMP_PREFIX_OFFSET, buf, size);
+
+	if (GET_FW_DUMP_MORE(buf) == 1) {
+		rtwdev->fw.prev_dump_seq = seq;
+		ret = false;
+	}
+
+free_buf:
+	vfree(buf);
+exit:
+	rtw_write8(rtwdev, REG_MCU_TST_CFG, 0);
+
+	return ret;
+}
+
+void rtw_vif_assoc_changed(struct rtw_vif *rtwvif,
+			   struct ieee80211_bss_conf *conf)
+{
+	if (conf && conf->assoc) {
+		rtwvif->aid = conf->aid;
+		rtwvif->net_type = RTW_NET_MGD_LINKED;
+	} else {
+		rtwvif->aid = 0;
+		rtwvif->net_type = RTW_NET_NO_LINK;
+	}
+}
+
+static void rtw_reset_key_iter(struct ieee80211_hw *hw,
+			       struct ieee80211_vif *vif,
+			       struct ieee80211_sta *sta,
+			       struct ieee80211_key_conf *key,
+			       void *data)
+{
+	struct rtw_dev *rtwdev = (struct rtw_dev *)data;
+	struct rtw_sec_desc *sec = &rtwdev->sec;
+
+	rtw_sec_clear_cam(rtwdev, sec, key->hw_key_idx);
+}
+
+static void rtw_reset_sta_iter(void *data, struct ieee80211_sta *sta)
+{
+	struct rtw_dev *rtwdev = (struct rtw_dev *)data;
+
+	if (rtwdev->sta_cnt == 0) {
+		rtw_warn(rtwdev, "sta count before reset should not be 0\n");
+		return;
+	}
+	rtw_sta_remove(rtwdev, sta, false);
+}
+
+static void rtw_reset_vif_iter(void *data, u8 *mac, struct ieee80211_vif *vif)
+{
+	struct rtw_dev *rtwdev = (struct rtw_dev *)data;
+	struct rtw_vif *rtwvif = (struct rtw_vif *)vif->drv_priv;
+
+	rtw_bf_disassoc(rtwdev, vif, NULL);
+	rtw_vif_assoc_changed(rtwvif, NULL);
+	rtw_txq_cleanup(rtwdev, vif->txq);
+}
+
+void rtw_fw_recovery(struct rtw_dev *rtwdev)
+{
+	if (!test_bit(RTW_FLAG_RESTARTING, rtwdev->flags))
+		ieee80211_queue_work(rtwdev->hw, &rtwdev->fw_recovery_work);
+}
+
+static void rtw_fw_recovery_work(struct work_struct *work)
+{
+	struct rtw_dev *rtwdev = container_of(work, struct rtw_dev,
+					      fw_recovery_work);
+
+	/* rtw_fw_dump_crash_log() returns false indicates that there are
+	 * still more log to dump. Driver set 0x1cf[7:0] = 0x1 to tell firmware
+	 * to dump the remaining part of the log, and firmware will trigger an
+	 * IMR_C2HCMD interrupt to inform driver the log is ready.
+	 */
+	if (!rtw_fw_dump_crash_log(rtwdev)) {
+		rtw_write8(rtwdev, REG_HRCV_MSG, 1);
+		return;
+	}
+	rtwdev->fw.prev_dump_seq = 0;
+
+	WARN(1, "firmware crash, start reset and recover\n");
+
+	mutex_lock(&rtwdev->mutex);
+
+	set_bit(RTW_FLAG_RESTARTING, rtwdev->flags);
+	rcu_read_lock();
+	rtw_iterate_keys_rcu(rtwdev, NULL, rtw_reset_key_iter, rtwdev);
+	rcu_read_unlock();
+	rtw_iterate_stas_atomic(rtwdev, rtw_reset_sta_iter, rtwdev);
+	rtw_iterate_vifs_atomic(rtwdev, rtw_reset_vif_iter, rtwdev);
+	rtw_enter_ips(rtwdev);
+
+	mutex_unlock(&rtwdev->mutex);
+
+	ieee80211_restart_hw(rtwdev->hw);
+}
+
 struct rtw_txq_ba_iter_data {
 };
 
@@ -1431,6 +1623,7 @@ int rtw_core_init(struct rtw_dev *rtwdev)
 	INIT_DELAYED_WORK(&coex->wl_remain_work, rtw_coex_wl_remain_work);
 	INIT_DELAYED_WORK(&coex->bt_remain_work, rtw_coex_bt_remain_work);
 	INIT_WORK(&rtwdev->c2h_work, rtw_c2h_work);
+	INIT_WORK(&rtwdev->fw_recovery_work, rtw_fw_recovery_work);
 	INIT_WORK(&rtwdev->ba_work, rtw_txq_ba_work);
 	skb_queue_head_init(&rtwdev->c2h_queue);
 	skb_queue_head_init(&rtwdev->coex.queue);
@@ -1472,6 +1665,9 @@ int rtw_core_init(struct rtw_dev *rtwdev)
 		ret = rtw_load_firmware(rtwdev, RTW_WOWLAN_FW);
 		if (ret) {
 			rtw_warn(rtwdev, "no wow firmware loaded\n");
+			wait_for_completion(&rtwdev->fw.completion);
+			if (rtwdev->fw.firmware)
+				release_firmware(rtwdev->fw.firmware);
 			return ret;
 		}
 	}
@@ -1486,6 +1682,8 @@ void rtw_core_deinit(struct rtw_dev *rtwdev)
 	struct rtw_rsvd_page *rsvd_pkt, *tmp;
 	unsigned long flags;
 
+	rtw_wait_firmware_completion(rtwdev);
+
 	if (fw->firmware)
 		release_firmware(fw->firmware);
 
diff --git a/drivers/net/wireless/realtek/rtw88/main.h b/drivers/net/wireless/realtek/rtw88/main.h
index 276b5d381467..ffb02e614217 100644
--- a/drivers/net/wireless/realtek/rtw88/main.h
+++ b/drivers/net/wireless/realtek/rtw88/main.h
@@ -359,6 +359,7 @@ enum rtw_flags {
 	RTW_FLAG_DIG_DISABLE,
 	RTW_FLAG_BUSY_TRAFFIC,
 	RTW_FLAG_WOWLAN,
+	RTW_FLAG_RESTARTING,
 
 	NUM_OF_RTW_FLAGS,
 };
@@ -1082,6 +1083,17 @@ enum rtw_wlan_cpu {
 	RTW_WCPU_11N,
 };
 
+enum rtw_fw_fifo_sel {
+	RTW_FW_FIFO_SEL_TX,
+	RTW_FW_FIFO_SEL_RX,
+	RTW_FW_FIFO_SEL_RSVD_PAGE,
+	RTW_FW_FIFO_SEL_REPORT,
+	RTW_FW_FIFO_SEL_LLT,
+	RTW_FW_FIFO_SEL_RXBUF_FW,
+
+	RTW_FW_FIFO_MAX,
+};
+
 /* hardware configuration for each IC */
 struct rtw_chip_info {
 	struct rtw_chip_ops *ops;
@@ -1098,6 +1110,7 @@ struct rtw_chip_info {
 	u32 ptct_efuse_size;
 	u32 txff_size;
 	u32 rxff_size;
+	u32 fw_rxff_size;
 	u8 band;
 	u8 page_size;
 	u8 csi_buf_pg_num;
@@ -1108,6 +1121,8 @@ struct rtw_chip_info {
 	bool rx_ldpc;
 	u8 max_power_index;
 
+	u16 fw_fifo_addr[RTW_FW_FIFO_MAX];
+
 	bool ht_supported;
 	bool vht_supported;
 	u8 lps_deep_mode_supported;
@@ -1606,6 +1621,9 @@ struct rtw_fifo_conf {
 	const struct rtw_rqpn *rqpn;
 };
 
+#define FW_CD_TYPE 0xffff
+#define FW_CD_LEN 4
+#define FW_CD_VAL 0xaabbccdd
 struct rtw_fw_state {
 	const struct firmware *firmware;
 	struct rtw_dev *rtwdev;
@@ -1614,6 +1632,7 @@ struct rtw_fw_state {
 	u8 sub_version;
 	u8 sub_index;
 	u16 h2c_version;
+	u8 prev_dump_seq;
 };
 
 struct rtw_hal {
@@ -1699,6 +1718,7 @@ struct rtw_dev {
 	/* c2h cmd queue & handler work */
 	struct sk_buff_head c2h_queue;
 	struct work_struct c2h_work;
+	struct work_struct fw_recovery_work;
 
 	/* used to protect txqs list */
 	spinlock_t txq_lock;
@@ -1799,6 +1819,11 @@ static inline bool rtw_chip_has_rx_ldpc(struct rtw_dev *rtwdev)
 	return rtwdev->chip->rx_ldpc;
 }
 
+static inline void rtw_release_macid(struct rtw_dev *rtwdev, u8 mac_id)
+{
+	clear_bit(mac_id, rtwdev->mac_id_map);
+}
+
 void rtw_get_channel_params(struct cfg80211_chan_def *chandef,
 			    struct rtw_channel_params *ch_param);
 bool check_hw_ready(struct rtw_dev *rtwdev, u32 addr, u32 mask, u32 target);
@@ -1821,5 +1846,12 @@ void rtw_core_deinit(struct rtw_dev *rtwdev);
 int rtw_register_hw(struct rtw_dev *rtwdev, struct ieee80211_hw *hw);
 void rtw_unregister_hw(struct rtw_dev *rtwdev, struct ieee80211_hw *hw);
 u16 rtw_desc_to_bitrate(u8 desc_rate);
+void rtw_vif_assoc_changed(struct rtw_vif *rtwvif,
+			   struct ieee80211_bss_conf *conf);
+int rtw_sta_add(struct rtw_dev *rtwdev, struct ieee80211_sta *sta,
+		struct ieee80211_vif *vif);
+void rtw_sta_remove(struct rtw_dev *rtwdev, struct ieee80211_sta *sta,
+		    bool fw_exist);
+void rtw_fw_recovery(struct rtw_dev *rtwdev);
 
 #endif
diff --git a/drivers/net/wireless/realtek/rtw88/pci.c b/drivers/net/wireless/realtek/rtw88/pci.c
index 135dd331691c..676d861aaf99 100644
--- a/drivers/net/wireless/realtek/rtw88/pci.c
+++ b/drivers/net/wireless/realtek/rtw88/pci.c
@@ -389,6 +389,7 @@ static int rtw_pci_init(struct rtw_dev *rtwdev)
 			      IMR_VODOK |
 			      IMR_ROK |
 			      IMR_BCNDMAINT_E |
+			      IMR_C2HCMD |
 			      0;
 	rtwpci->irq_mask[1] = IMR_TXFOVW |
 			      0;
@@ -1079,6 +1080,8 @@ static irqreturn_t rtw_pci_interrupt_threadfn(int irq, void *dev)
 		rtw_pci_tx_isr(rtwdev, rtwpci, RTW_TX_QUEUE_H2C);
 	if (irq_status[0] & IMR_ROK)
 		rtw_pci_rx_isr(rtwdev, rtwpci, RTW_RX_QUEUE_MPDU);
+	if (unlikely(irq_status[0] & IMR_C2HCMD))
+		rtw_fw_c2h_cmd_isr(rtwdev);
 
 	/* all of the jobs for this interrupt have been done */
 	rtw_pci_enable_interrupt(rtwdev, rtwpci);
@@ -1598,6 +1601,8 @@ void rtw_pci_shutdown(struct pci_dev *pdev)
 
 	if (chip->ops->shutdown)
 		chip->ops->shutdown(rtwdev);
+
+	pci_set_power_state(pdev, PCI_D3hot);
 }
 EXPORT_SYMBOL(rtw_pci_shutdown);
 
diff --git a/drivers/net/wireless/realtek/rtw88/pci.h b/drivers/net/wireless/realtek/rtw88/pci.h
index 024c2bc275cb..ca17aa9cf7dc 100644
--- a/drivers/net/wireless/realtek/rtw88/pci.h
+++ b/drivers/net/wireless/realtek/rtw88/pci.h
@@ -9,8 +9,8 @@
 #define RTK_BEQ_TX_DESC_NUM	256
 
 #define RTK_MAX_RX_DESC_NUM	512
-/* 8K + rx desc size */
-#define RTK_PCI_RX_BUF_SIZE	(8192 + 24)
+/* 11K + rx desc size */
+#define RTK_PCI_RX_BUF_SIZE	(11454 + 24)
 
 #define RTK_PCI_CTRL		0x300
 #define BIT_RST_TRXDMA_INTF	BIT(20)
diff --git a/drivers/net/wireless/realtek/rtw88/reg.h b/drivers/net/wireless/realtek/rtw88/reg.h
index 8f468d6b5f78..86b94c008a27 100644
--- a/drivers/net/wireless/realtek/rtw88/reg.h
+++ b/drivers/net/wireless/realtek/rtw88/reg.h
@@ -126,6 +126,9 @@
 				 BIT_WINTINI_RDY | BIT_RAM_DL_SEL)
 #define FW_READY_MASK		0xffff
 
+#define REG_MCU_TST_CFG		0x84
+#define VAL_FW_TRIGGER		0x1
+
 #define REG_EFUSE_ACCESS	0x00CF
 #define EFUSE_ACCESS_ON		0x69
 #define EFUSE_ACCESS_OFF	0x00
@@ -616,6 +619,8 @@
 #define BIT_ANAPAR_BTPS	BIT(22)
 #define REG_RSTB_SEL	0x1c38
 
+#define REG_HRCV_MSG	0x1cf
+
 #define REG_IGN_GNTBT4	0x4160
 
 #define RF_MODE		0x00
diff --git a/drivers/net/wireless/realtek/rtw88/rtw8822b.c b/drivers/net/wireless/realtek/rtw88/rtw8822b.c
index b7a98dbbb09c..22d0dd640ac9 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8822b.c
+++ b/drivers/net/wireless/realtek/rtw88/rtw8822b.c
@@ -2442,6 +2442,7 @@ struct rtw_chip_info rtw8822b_hw_spec = {
 	.ptct_efuse_size = 96,
 	.txff_size = 262144,
 	.rxff_size = 24576,
+	.fw_rxff_size = 12288,
 	.txgi_factor = 1,
 	.is_pwr_by_rate_dec = true,
 	.max_power_index = 0x3f,
@@ -2504,6 +2505,8 @@ struct rtw_chip_info rtw8822b_hw_spec = {
 
 	.coex_info_hw_regs_num = ARRAY_SIZE(coex_info_hw_regs_8822b),
 	.coex_info_hw_regs = coex_info_hw_regs_8822b,
+
+	.fw_fifo_addr = {0x780, 0x700, 0x780, 0x660, 0x650, 0x680},
 };
 EXPORT_SYMBOL(rtw8822b_hw_spec);
 
diff --git a/drivers/net/wireless/realtek/rtw88/rtw8822c.c b/drivers/net/wireless/realtek/rtw88/rtw8822c.c
index ed1c14af082b..e37300e98517 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8822c.c
+++ b/drivers/net/wireless/realtek/rtw88/rtw8822c.c
@@ -154,25 +154,16 @@ static void rtw8822c_rf_minmax_cmp(struct rtw_dev *rtwdev, u32 value,
 	}
 }
 
-static void swap_u32(u32 *v1, u32 *v2)
-{
-	u32 tmp;
-
-	tmp = *v1;
-	*v1 = *v2;
-	*v2 = tmp;
-}
-
 static void __rtw8822c_dac_iq_sort(struct rtw_dev *rtwdev, u32 *v1, u32 *v2)
 {
 	if (*v1 >= 0x200 && *v2 >= 0x200) {
 		if (*v1 > *v2)
-			swap_u32(v1, v2);
+			swap(*v1, *v2);
 	} else if (*v1 < 0x200 && *v2 < 0x200) {
 		if (*v1 > *v2)
-			swap_u32(v1, v2);
+			swap(*v1, *v2);
 	} else if (*v1 < 0x200 && *v2 >= 0x200) {
-		swap_u32(v1, v2);
+		swap(*v1, *v2);
 	}
 }
 
@@ -4303,6 +4294,7 @@ struct rtw_chip_info rtw8822c_hw_spec = {
 	.ptct_efuse_size = 124,
 	.txff_size = 262144,
 	.rxff_size = 24576,
+	.fw_rxff_size = 12288,
 	.txgi_factor = 2,
 	.is_pwr_by_rate_dec = false,
 	.max_power_index = 0x7f,
@@ -4373,6 +4365,8 @@ struct rtw_chip_info rtw8822c_hw_spec = {
 
 	.coex_info_hw_regs_num = ARRAY_SIZE(coex_info_hw_regs_8822c),
 	.coex_info_hw_regs = coex_info_hw_regs_8822c,
+
+	.fw_fifo_addr = {0x780, 0x700, 0x780, 0x660, 0x650, 0x680},
 };
 EXPORT_SYMBOL(rtw8822c_hw_spec);
 
diff --git a/drivers/net/wireless/realtek/rtw88/util.h b/drivers/net/wireless/realtek/rtw88/util.h
index 41c10e7144df..0c23b5069be0 100644
--- a/drivers/net/wireless/realtek/rtw88/util.h
+++ b/drivers/net/wireless/realtek/rtw88/util.h
@@ -17,6 +17,8 @@ struct rtw_dev;
 	ieee80211_iterate_stations_atomic(rtwdev->hw, iterator, data)
 #define rtw_iterate_keys(rtwdev, vif, iterator, data)			       \
 	ieee80211_iter_keys(rtwdev->hw, vif, iterator, data)
+#define rtw_iterate_keys_rcu(rtwdev, vif, iterator, data)		       \
+	ieee80211_iter_keys_rcu((rtwdev)->hw, vif, iterator, data)
 
 static inline u8 *get_hdr_bssid(struct ieee80211_hdr *hdr)
 {
diff --git a/drivers/net/wireless/ti/wl1251/reg.h b/drivers/net/wireless/ti/wl1251/reg.h
index e03f8321ea60..890176c915ab 100644
--- a/drivers/net/wireless/ti/wl1251/reg.h
+++ b/drivers/net/wireless/ti/wl1251/reg.h
@@ -217,7 +217,7 @@ enum wl12xx_acx_int_reg {
  Halt eCPU   - 32bit RW
  ------------------------------------------
  0 HALT_ECPU Halt Embedded CPU - This bit is the
- compliment of bit 1 (MDATA2) in the SOR_CFG register.
+ complement of bit 1 (MDATA2) in the SOR_CFG register.
  During a hardware reset, this bit holds
  the inverse of MDATA2.
  When downloading firmware from the host,
diff --git a/drivers/net/wireless/ti/wl12xx/reg.h b/drivers/net/wireless/ti/wl12xx/reg.h
index 247f558ba630..8ff018808020 100644
--- a/drivers/net/wireless/ti/wl12xx/reg.h
+++ b/drivers/net/wireless/ti/wl12xx/reg.h
@@ -139,7 +139,7 @@
  Halt eCPU   - 32bit RW
  ------------------------------------------
  0 HALT_ECPU Halt Embedded CPU - This bit is the
- compliment of bit 1 (MDATA2) in the SOR_CFG register.
+ complement of bit 1 (MDATA2) in the SOR_CFG register.
  During a hardware reset, this bit holds
  the inverse of MDATA2.
  When downloading firmware from the host,
diff --git a/drivers/net/wireless/ti/wlcore/cmd.h b/drivers/net/wireless/ti/wlcore/cmd.h
index 9acd8a41ea61..f2609d5b6bf7 100644
--- a/drivers/net/wireless/ti/wlcore/cmd.h
+++ b/drivers/net/wireless/ti/wlcore/cmd.h
@@ -458,7 +458,6 @@ enum wl1271_cmd_key_type {
 	KEY_TKIP = 2,
 	KEY_AES  = 3,
 	KEY_GEM  = 4,
-	KEY_IGTK  = 5,
 };
 
 struct wl1271_cmd_set_keys {
diff --git a/drivers/net/wireless/ti/wlcore/debugfs.c b/drivers/net/wireless/ti/wlcore/debugfs.c
index 48adb1876ab9..cce8d75d8b81 100644
--- a/drivers/net/wireless/ti/wlcore/debugfs.c
+++ b/drivers/net/wireless/ti/wlcore/debugfs.c
@@ -122,13 +122,6 @@ static void chip_op_handler(struct wl1271 *wl, unsigned long value,
 	pm_runtime_put_autosuspend(wl->dev);
 }
 
-
-static inline void no_write_handler(struct wl1271 *wl,
-				    unsigned long value,
-				    unsigned long param)
-{
-}
-
 #define WL12XX_CONF_DEBUGFS(param, conf_sub_struct,			\
 			    min_val, max_val, write_handler_locked,	\
 			    write_handler_arg)				\
diff --git a/drivers/net/wireless/ti/wlcore/main.c b/drivers/net/wireless/ti/wlcore/main.c
index 821ad1acd505..6863fd552d5e 100644
--- a/drivers/net/wireless/ti/wlcore/main.c
+++ b/drivers/net/wireless/ti/wlcore/main.c
@@ -30,7 +30,6 @@
 #include "sysfs.h"
 
 #define WL1271_BOOT_RETRIES 3
-#define WL1271_SUSPEND_SLEEP 100
 #define WL1271_WAKEUP_TIMEOUT 500
 
 static char *fwlog_param;
@@ -3559,9 +3558,6 @@ int wlcore_set_key(struct wl1271 *wl, enum set_key_cmd cmd,
 	case WL1271_CIPHER_SUITE_GEM:
 		key_type = KEY_GEM;
 		break;
-	case WLAN_CIPHER_SUITE_AES_CMAC:
-		key_type = KEY_IGTK;
-		break;
 	default:
 		wl1271_error("Unknown key algo 0x%x", key_conf->cipher);
 
@@ -6231,7 +6227,6 @@ static int wl1271_init_ieee80211(struct wl1271 *wl)
 		WLAN_CIPHER_SUITE_TKIP,
 		WLAN_CIPHER_SUITE_CCMP,
 		WL1271_CIPHER_SUITE_GEM,
-		WLAN_CIPHER_SUITE_AES_CMAC,
 	};
 
 	/* The tx descriptor buffer */
diff --git a/drivers/net/wireless/wl3501_cs.c b/drivers/net/wireless/wl3501_cs.c
index 4e7a2140649b..026e88b80bfc 100644
--- a/drivers/net/wireless/wl3501_cs.c
+++ b/drivers/net/wireless/wl3501_cs.c
@@ -1433,9 +1433,7 @@ static void wl3501_detach(struct pcmcia_device *link)
 	wl3501_release(link);
 
 	unregister_netdev(dev);
-
-	if (link->priv)
-		free_netdev(link->priv);
+	free_netdev(dev);
 }
 
 static int wl3501_get_name(struct net_device *dev, struct iw_request_info *info,
diff --git a/drivers/net/wireless/zydas/zd1201.c b/drivers/net/wireless/zydas/zd1201.c
index 41641fc2be74..718c4ee865ba 100644
--- a/drivers/net/wireless/zydas/zd1201.c
+++ b/drivers/net/wireless/zydas/zd1201.c
@@ -1652,15 +1652,11 @@ static int zd1201_set_maxassoc(struct net_device *dev,
     struct iw_request_info *info, struct iw_param *rrq, char *extra)
 {
 	struct zd1201 *zd = netdev_priv(dev);
-	int err;
 
 	if (!zd->ap)
 		return -EOPNOTSUPP;
 
-	err = zd1201_setconfig16(zd, ZD1201_RID_CNFMAXASSOCSTATIONS, rrq->value);
-	if (err)
-		return err;
-	return 0;
+	return zd1201_setconfig16(zd, ZD1201_RID_CNFMAXASSOCSTATIONS, rrq->value);
 }
 
 static int zd1201_get_maxassoc(struct net_device *dev,
diff --git a/drivers/net/wireless/zydas/zd1211rw/zd_usb.c b/drivers/net/wireless/zydas/zd1211rw/zd_usb.c
index 71ec3d4231ef..66367ab7e4c1 100644
--- a/drivers/net/wireless/zydas/zd1211rw/zd_usb.c
+++ b/drivers/net/wireless/zydas/zd1211rw/zd_usb.c
@@ -378,7 +378,6 @@ static inline void handle_regs_int(struct urb *urb)
 	int len;
 	u16 int_num;
 
-	ZD_ASSERT(in_interrupt());
 	spin_lock_irqsave(&intr->lock, flags);
 
 	int_num = le16_to_cpu(*(__le16 *)(urb->transfer_buffer+2));
diff --git a/drivers/nvme/host/Kconfig b/drivers/nvme/host/Kconfig
index 3ed9786b88d8..a44d49d63968 100644
--- a/drivers/nvme/host/Kconfig
+++ b/drivers/nvme/host/Kconfig
@@ -73,6 +73,7 @@ config NVME_TCP
 	depends on INET
 	depends on BLK_DEV_NVME
 	select NVME_FABRICS
+	select CRYPTO
 	select CRYPTO_CRC32C
 	help
 	  This provides support for the NVMe over Fabrics protocol using
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index d543bc1747fd..2f249052c95d 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -3261,10 +3261,24 @@ static int nvme_dev_open(struct inode *inode, struct file *file)
 		return -EWOULDBLOCK;
 	}
 
+	nvme_get_ctrl(ctrl);
+	if (!try_module_get(ctrl->ops->module))
+		return -EINVAL;
+
 	file->private_data = ctrl;
 	return 0;
 }
 
+static int nvme_dev_release(struct inode *inode, struct file *file)
+{
+	struct nvme_ctrl *ctrl =
+		container_of(inode->i_cdev, struct nvme_ctrl, cdev);
+
+	module_put(ctrl->ops->module);
+	nvme_put_ctrl(ctrl);
+	return 0;
+}
+
 static int nvme_dev_user_cmd(struct nvme_ctrl *ctrl, void __user *argp)
 {
 	struct nvme_ns *ns;
@@ -3327,6 +3341,7 @@ static long nvme_dev_ioctl(struct file *file, unsigned int cmd,
 static const struct file_operations nvme_dev_fops = {
 	.owner		= THIS_MODULE,
 	.open		= nvme_dev_open,
+	.release	= nvme_dev_release,
 	.unlocked_ioctl	= nvme_dev_ioctl,
 	.compat_ioctl	= compat_ptr_ioctl,
 };
@@ -3525,10 +3540,6 @@ static ssize_t nvme_sysfs_delete(struct device *dev,
 {
 	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
 
-	/* Can't delete non-created controllers */
-	if (!ctrl->created)
-		return -EBUSY;
-
 	if (device_remove_file_self(dev, attr))
 		nvme_delete_ctrl_sync(ctrl);
 	return count;
@@ -4403,7 +4414,6 @@ void nvme_start_ctrl(struct nvme_ctrl *ctrl)
 		nvme_queue_scan(ctrl);
 		nvme_start_queues(ctrl);
 	}
-	ctrl->created = true;
 }
 EXPORT_SYMBOL_GPL(nvme_start_ctrl);
 
diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c
index 32f61fc5f4c5..8575724734e0 100644
--- a/drivers/nvme/host/fabrics.c
+++ b/drivers/nvme/host/fabrics.c
@@ -565,10 +565,14 @@ bool __nvmf_check_ready(struct nvme_ctrl *ctrl, struct request *rq,
 	struct nvme_request *req = nvme_req(rq);
 
 	/*
-	 * If we are in some state of setup or teardown only allow
-	 * internally generated commands.
+	 * currently we have a problem sending passthru commands
+	 * on the admin_q if the controller is not LIVE because we can't
+	 * make sure that they are going out after the admin connect,
+	 * controller enable and/or other commands in the initialization
+	 * sequence. until the controller will be LIVE, fail with
+	 * BLK_STS_RESOURCE so that they will be rescheduled.
 	 */
-	if (!blk_rq_is_passthrough(rq) || (req->flags & NVME_REQ_USERCMD))
+	if (rq->q == ctrl->admin_q && (req->flags & NVME_REQ_USERCMD))
 		return false;
 
 	/*
@@ -577,7 +581,7 @@ bool __nvmf_check_ready(struct nvme_ctrl *ctrl, struct request *rq,
 	 */
 	switch (ctrl->state) {
 	case NVME_CTRL_CONNECTING:
-		if (nvme_is_fabrics(req->cmd) &&
+		if (blk_rq_is_passthrough(rq) && nvme_is_fabrics(req->cmd) &&
 		    req->cmd->fabrics.fctype == nvme_fabrics_type_connect)
 			return true;
 		break;
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index a7f474ddfff7..e8ef42b9d50c 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -2160,6 +2160,7 @@ nvme_fc_term_aen_ops(struct nvme_fc_ctrl *ctrl)
 	struct nvme_fc_fcp_op *aen_op;
 	int i;
 
+	cancel_work_sync(&ctrl->ctrl.async_event_work);
 	aen_op = ctrl->aen_ops;
 	for (i = 0; i < NVME_NR_AEN_COMMANDS; i++, aen_op++) {
 		__nvme_fc_exit_request(ctrl, aen_op);
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 2910f6caab7d..9fd45ff656da 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -307,7 +307,6 @@ struct nvme_ctrl {
 	struct nvme_command ka_cmd;
 	struct work_struct fw_act_work;
 	unsigned long events;
-	bool created;
 
 #ifdef CONFIG_NVME_MULTIPATH
 	/* asymmetric namespace access: */
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 899d2f4d7ab6..08c5a9b438f3 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -3153,7 +3153,8 @@ static const struct pci_device_id nvme_id_table[] = {
 	{ PCI_VDEVICE(INTEL, 0xf1a5),	/* Intel 600P/P3100 */
 		.driver_data = NVME_QUIRK_NO_DEEPEST_PS |
 				NVME_QUIRK_MEDIUM_PRIO_SQ |
-				NVME_QUIRK_NO_TEMP_THRESH_CHANGE },
+				NVME_QUIRK_NO_TEMP_THRESH_CHANGE |
+				NVME_QUIRK_DISABLE_WRITE_ZEROES, },
 	{ PCI_VDEVICE(INTEL, 0xf1a6),	/* Intel 760p/Pro 7600p */
 		.driver_data = NVME_QUIRK_IGNORE_DEV_SUBNQN, },
 	{ PCI_VDEVICE(INTEL, 0x5845),	/* Qemu emulated controller */
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 8e5ffe2f117d..9e378d0a0c01 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -835,6 +835,7 @@ static void nvme_rdma_destroy_admin_queue(struct nvme_rdma_ctrl *ctrl,
 		blk_mq_free_tag_set(ctrl->ctrl.admin_tagset);
 	}
 	if (ctrl->async_event_sqe.data) {
+		cancel_work_sync(&ctrl->ctrl.async_event_work);
 		nvme_rdma_free_qe(ctrl->device->dev, &ctrl->async_event_sqe,
 				sizeof(struct nvme_command), DMA_TO_DEVICE);
 		ctrl->async_event_sqe.data = NULL;
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 16851ae3bddf..8f4f29f18b8c 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -1596,6 +1596,7 @@ static struct blk_mq_tag_set *nvme_tcp_alloc_tagset(struct nvme_ctrl *nctrl,
 static void nvme_tcp_free_admin_queue(struct nvme_ctrl *ctrl)
 {
 	if (to_tcp_ctrl(ctrl)->async_req.pdu) {
+		cancel_work_sync(&ctrl->async_event_work);
 		nvme_tcp_free_async_req(to_tcp_ctrl(ctrl));
 		to_tcp_ctrl(ctrl)->async_req.pdu = NULL;
 	}
diff --git a/drivers/nvme/target/passthru.c b/drivers/nvme/target/passthru.c
index 8bd7f656e240..dacfa7435d0b 100644
--- a/drivers/nvme/target/passthru.c
+++ b/drivers/nvme/target/passthru.c
@@ -517,6 +517,7 @@ int nvmet_passthru_ctrl_enable(struct nvmet_subsys *subsys)
 		subsys->ver = NVME_VS(1, 2, 1);
 	}
 
+	__module_get(subsys->passthru_ctrl->ops->module);
 	mutex_unlock(&subsys->lock);
 	return 0;
 
@@ -531,6 +532,7 @@ static void __nvmet_passthru_ctrl_disable(struct nvmet_subsys *subsys)
 {
 	if (subsys->passthru_ctrl) {
 		xa_erase(&passthru_subsystems, subsys->passthru_ctrl->cntlid);
+		module_put(subsys->passthru_ctrl->ops->module);
 		nvme_put_ctrl(subsys->passthru_ctrl);
 	}
 	subsys->passthru_ctrl = NULL;
diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c
index cb32d7ef4938..4daf94bb56a5 100644
--- a/drivers/of/of_mdio.c
+++ b/drivers/of/of_mdio.c
@@ -338,6 +338,29 @@ unregister:
 EXPORT_SYMBOL(of_mdiobus_register);
 
 /**
+ * of_mdio_find_device - Given a device tree node, find the mdio_device
+ * @np: pointer to the mdio_device's device tree node
+ *
+ * If successful, returns a pointer to the mdio_device with the embedded
+ * struct device refcount incremented by one, or NULL on failure.
+ * The caller should call put_device() on the mdio_device after its use
+ */
+struct mdio_device *of_mdio_find_device(struct device_node *np)
+{
+	struct device *d;
+
+	if (!np)
+		return NULL;
+
+	d = bus_find_device_by_of_node(&mdio_bus_type, np);
+	if (!d)
+		return NULL;
+
+	return to_mdio_device(d);
+}
+EXPORT_SYMBOL(of_mdio_find_device);
+
+/**
  * of_phy_find_device - Give a PHY node, find the phy_device
  * @phy_np: Pointer to the phy's device tree node
  *
@@ -346,19 +369,16 @@ EXPORT_SYMBOL(of_mdiobus_register);
  */
 struct phy_device *of_phy_find_device(struct device_node *phy_np)
 {
-	struct device *d;
 	struct mdio_device *mdiodev;
 
-	if (!phy_np)
+	mdiodev = of_mdio_find_device(phy_np);
+	if (!mdiodev)
 		return NULL;
 
-	d = bus_find_device_by_of_node(&mdio_bus_type, phy_np);
-	if (d) {
-		mdiodev = to_mdio_device(d);
-		if (mdiodev->flags & MDIO_DEVICE_FLAG_PHY)
-			return to_phy_device(d);
-		put_device(d);
-	}
+	if (mdiodev->flags & MDIO_DEVICE_FLAG_PHY)
+		return to_phy_device(&mdiodev->dev);
+
+	put_device(&mdiodev->dev);
 
 	return NULL;
 }
diff --git a/drivers/phy/qualcomm/phy-qcom-ipq806x-usb.c b/drivers/phy/qualcomm/phy-qcom-ipq806x-usb.c
index 71f257b4a7f5..9061ece7ff6a 100644
--- a/drivers/phy/qualcomm/phy-qcom-ipq806x-usb.c
+++ b/drivers/phy/qualcomm/phy-qcom-ipq806x-usb.c
@@ -505,9 +505,9 @@ static int qcom_ipq806x_usb_phy_probe(struct platform_device *pdev)
 	size = resource_size(res);
 	phy_dwc3->base = devm_ioremap(phy_dwc3->dev, res->start, size);
 
-	if (IS_ERR(phy_dwc3->base)) {
+	if (!phy_dwc3->base) {
 		dev_err(phy_dwc3->dev, "failed to map reg\n");
-		return PTR_ERR(phy_dwc3->base);
+		return -ENOMEM;
 	}
 
 	phy_dwc3->ref_clk = devm_clk_get(phy_dwc3->dev, "ref");
@@ -557,7 +557,6 @@ static struct platform_driver qcom_ipq806x_usb_phy_driver = {
 	.probe		= qcom_ipq806x_usb_phy_probe,
 	.driver		= {
 		.name	= "qcom-ipq806x-usb-phy",
-		.owner	= THIS_MODULE,
 		.of_match_table = qcom_ipq806x_usb_phy_table,
 	},
 };
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp.c b/drivers/phy/qualcomm/phy-qcom-qmp.c
index 562053ce9455..6e6f992a9524 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp.c
+++ b/drivers/phy/qualcomm/phy-qcom-qmp.c
@@ -604,8 +604,8 @@ static const struct qmp_phy_init_tbl ipq8074_pcie_serdes_tbl[] = {
 	QMP_PHY_INIT_CFG(QSERDES_COM_BG_TRIM, 0xf),
 	QMP_PHY_INIT_CFG(QSERDES_COM_LOCK_CMP_EN, 0x1),
 	QMP_PHY_INIT_CFG(QSERDES_COM_VCO_TUNE_MAP, 0x0),
-	QMP_PHY_INIT_CFG(QSERDES_COM_VCO_TUNE_TIMER1, 0x1f),
-	QMP_PHY_INIT_CFG(QSERDES_COM_VCO_TUNE_TIMER2, 0x3f),
+	QMP_PHY_INIT_CFG(QSERDES_COM_VCO_TUNE_TIMER1, 0xff),
+	QMP_PHY_INIT_CFG(QSERDES_COM_VCO_TUNE_TIMER2, 0x1f),
 	QMP_PHY_INIT_CFG(QSERDES_COM_CMN_CONFIG, 0x6),
 	QMP_PHY_INIT_CFG(QSERDES_COM_PLL_IVCO, 0xf),
 	QMP_PHY_INIT_CFG(QSERDES_COM_HSCLK_SEL, 0x0),
@@ -631,7 +631,6 @@ static const struct qmp_phy_init_tbl ipq8074_pcie_serdes_tbl[] = {
 	QMP_PHY_INIT_CFG(QSERDES_COM_INTEGLOOP_GAIN1_MODE0, 0x0),
 	QMP_PHY_INIT_CFG(QSERDES_COM_INTEGLOOP_GAIN0_MODE0, 0x80),
 	QMP_PHY_INIT_CFG(QSERDES_COM_BIAS_EN_CTRL_BY_PSM, 0x1),
-	QMP_PHY_INIT_CFG(QSERDES_COM_VCO_TUNE_CTRL, 0xa),
 	QMP_PHY_INIT_CFG(QSERDES_COM_SSC_EN_CENTER, 0x1),
 	QMP_PHY_INIT_CFG(QSERDES_COM_SSC_PER1, 0x31),
 	QMP_PHY_INIT_CFG(QSERDES_COM_SSC_PER2, 0x1),
@@ -640,7 +639,6 @@ static const struct qmp_phy_init_tbl ipq8074_pcie_serdes_tbl[] = {
 	QMP_PHY_INIT_CFG(QSERDES_COM_SSC_STEP_SIZE1, 0x2f),
 	QMP_PHY_INIT_CFG(QSERDES_COM_SSC_STEP_SIZE2, 0x19),
 	QMP_PHY_INIT_CFG(QSERDES_COM_CLK_EP_DIV, 0x19),
-	QMP_PHY_INIT_CFG(QSERDES_RX_SIGDET_CNTRL, 0x7),
 };
 
 static const struct qmp_phy_init_tbl ipq8074_pcie_tx_tbl[] = {
@@ -648,6 +646,8 @@ static const struct qmp_phy_init_tbl ipq8074_pcie_tx_tbl[] = {
 	QMP_PHY_INIT_CFG(QSERDES_TX_LANE_MODE, 0x6),
 	QMP_PHY_INIT_CFG(QSERDES_TX_RES_CODE_LANE_OFFSET, 0x2),
 	QMP_PHY_INIT_CFG(QSERDES_TX_RCV_DETECT_LVL_2, 0x12),
+	QMP_PHY_INIT_CFG(QSERDES_TX_EMP_POST1_LVL, 0x36),
+	QMP_PHY_INIT_CFG(QSERDES_TX_SLEW_CNTL, 0x0a),
 };
 
 static const struct qmp_phy_init_tbl ipq8074_pcie_rx_tbl[] = {
@@ -658,7 +658,6 @@ static const struct qmp_phy_init_tbl ipq8074_pcie_rx_tbl[] = {
 	QMP_PHY_INIT_CFG(QSERDES_RX_RX_EQU_ADAPTOR_CNTRL4, 0xdb),
 	QMP_PHY_INIT_CFG(QSERDES_RX_UCDR_SO_SATURATION_AND_ENABLE, 0x4b),
 	QMP_PHY_INIT_CFG(QSERDES_RX_UCDR_SO_GAIN, 0x4),
-	QMP_PHY_INIT_CFG(QSERDES_RX_UCDR_SO_GAIN_HALF, 0x4),
 };
 
 static const struct qmp_phy_init_tbl ipq8074_pcie_pcs_tbl[] = {
@@ -2046,6 +2045,9 @@ static const struct qmp_phy_cfg msm8996_usb3phy_cfg = {
 	.pwrdn_ctrl		= SW_PWRDN,
 };
 
+static const char * const ipq8074_pciephy_clk_l[] = {
+	"aux", "cfg_ahb",
+};
 /* list of resets */
 static const char * const ipq8074_pciephy_reset_l[] = {
 	"phy", "common",
@@ -2063,8 +2065,8 @@ static const struct qmp_phy_cfg ipq8074_pciephy_cfg = {
 	.rx_tbl_num		= ARRAY_SIZE(ipq8074_pcie_rx_tbl),
 	.pcs_tbl		= ipq8074_pcie_pcs_tbl,
 	.pcs_tbl_num		= ARRAY_SIZE(ipq8074_pcie_pcs_tbl),
-	.clk_list		= NULL,
-	.num_clks		= 0,
+	.clk_list		= ipq8074_pciephy_clk_l,
+	.num_clks		= ARRAY_SIZE(ipq8074_pciephy_clk_l),
 	.reset_list		= ipq8074_pciephy_reset_l,
 	.num_resets		= ARRAY_SIZE(ipq8074_pciephy_reset_l),
 	.vreg_list		= NULL,
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp.h b/drivers/phy/qualcomm/phy-qcom-qmp.h
index 4277f592684b..904b80ab9009 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp.h
+++ b/drivers/phy/qualcomm/phy-qcom-qmp.h
@@ -77,6 +77,8 @@
 #define QSERDES_COM_CORECLK_DIV_MODE1			0x1bc
 
 /* Only for QMP V2 PHY - TX registers */
+#define QSERDES_TX_EMP_POST1_LVL			0x018
+#define QSERDES_TX_SLEW_CNTL				0x040
 #define QSERDES_TX_RES_CODE_LANE_OFFSET			0x054
 #define QSERDES_TX_DEBUG_BUS_SEL			0x064
 #define QSERDES_TX_HIGHZ_TRANSCEIVEREN_BIAS_DRVR_EN	0x068
diff --git a/drivers/phy/ti/phy-omap-usb2.c b/drivers/phy/ti/phy-omap-usb2.c
index cb2dd3230fa7..507f79d14adb 100644
--- a/drivers/phy/ti/phy-omap-usb2.c
+++ b/drivers/phy/ti/phy-omap-usb2.c
@@ -22,10 +22,15 @@
 #include <linux/mfd/syscon.h>
 #include <linux/regmap.h>
 #include <linux/of_platform.h>
+#include <linux/sys_soc.h>
 
 #define USB2PHY_ANA_CONFIG1		0x4c
 #define USB2PHY_DISCON_BYP_LATCH	BIT(31)
 
+#define USB2PHY_CHRG_DET			0x14
+#define USB2PHY_CHRG_DET_USE_CHG_DET_REG	BIT(29)
+#define USB2PHY_CHRG_DET_DIS_CHG_DET		BIT(28)
+
 /* SoC Specific USB2_OTG register definitions */
 #define AM654_USB2_OTG_PD		BIT(8)
 #define AM654_USB2_VBUS_DET_EN		BIT(5)
@@ -43,6 +48,7 @@
 #define OMAP_USB2_HAS_START_SRP			BIT(0)
 #define OMAP_USB2_HAS_SET_VBUS			BIT(1)
 #define OMAP_USB2_CALIBRATE_FALSE_DISCONNECT	BIT(2)
+#define OMAP_USB2_DISABLE_CHRG_DET		BIT(3)
 
 struct omap_usb {
 	struct usb_phy		phy;
@@ -236,6 +242,13 @@ static int omap_usb_init(struct phy *x)
 		omap_usb_writel(phy->phy_base, USB2PHY_ANA_CONFIG1, val);
 	}
 
+	if (phy->flags & OMAP_USB2_DISABLE_CHRG_DET) {
+		val = omap_usb_readl(phy->phy_base, USB2PHY_CHRG_DET);
+		val |= USB2PHY_CHRG_DET_USE_CHG_DET_REG |
+		       USB2PHY_CHRG_DET_DIS_CHG_DET;
+		omap_usb_writel(phy->phy_base, USB2PHY_CHRG_DET, val);
+	}
+
 	return 0;
 }
 
@@ -329,6 +342,26 @@ static const struct of_device_id omap_usb2_id_table[] = {
 };
 MODULE_DEVICE_TABLE(of, omap_usb2_id_table);
 
+static void omap_usb2_init_errata(struct omap_usb *phy)
+{
+	static const struct soc_device_attribute am65x_sr10_soc_devices[] = {
+		{ .family = "AM65X", .revision = "SR1.0" },
+		{ /* sentinel */ }
+	};
+
+	/*
+	 * Errata i2075: USB2PHY: USB2PHY Charger Detect is Enabled by
+	 * Default Without VBUS Presence.
+	 *
+	 * AM654x SR1.0 has a silicon bug due to which D+ is pulled high after
+	 * POR, which could cause enumeration failure with some USB hubs.
+	 * Disabling the USB2_PHY Charger Detect function will put D+
+	 * into the normal state.
+	 */
+	if (soc_device_match(am65x_sr10_soc_devices))
+		phy->flags |= OMAP_USB2_DISABLE_CHRG_DET;
+}
+
 static int omap_usb2_probe(struct platform_device *pdev)
 {
 	struct omap_usb	*phy;
@@ -366,14 +399,14 @@ static int omap_usb2_probe(struct platform_device *pdev)
 	phy->mask		= phy_data->mask;
 	phy->power_on		= phy_data->power_on;
 	phy->power_off		= phy_data->power_off;
+	phy->flags		= phy_data->flags;
 
-	if (phy_data->flags & OMAP_USB2_CALIBRATE_FALSE_DISCONNECT) {
-		res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-		phy->phy_base = devm_ioremap_resource(&pdev->dev, res);
-		if (IS_ERR(phy->phy_base))
-			return PTR_ERR(phy->phy_base);
-		phy->flags |= OMAP_USB2_CALIBRATE_FALSE_DISCONNECT;
-	}
+	omap_usb2_init_errata(phy);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	phy->phy_base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(phy->phy_base))
+		return PTR_ERR(phy->phy_base);
 
 	phy->syscon_phy_power = syscon_regmap_lookup_by_phandle(node,
 							"syscon-phy-power");
diff --git a/drivers/powercap/intel_rapl_common.c b/drivers/powercap/intel_rapl_common.c
index 6f55aaef8afc..983d75bd5bd1 100644
--- a/drivers/powercap/intel_rapl_common.c
+++ b/drivers/powercap/intel_rapl_common.c
@@ -1035,7 +1035,11 @@ static const struct x86_cpu_id rapl_ids[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE_L,		&rapl_defaults_core),
 	X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE,		&rapl_defaults_core),
 	X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE_L,		&rapl_defaults_core),
+	X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE,		&rapl_defaults_core),
+	X86_MATCH_INTEL_FAM6_MODEL(ROCKETLAKE,		&rapl_defaults_core),
+	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE,		&rapl_defaults_core),
 	X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X,	&rapl_defaults_spr_server),
+	X86_MATCH_INTEL_FAM6_MODEL(LAKEFIELD,		&rapl_defaults_core),
 
 	X86_MATCH_INTEL_FAM6_MODEL(ATOM_SILVERMONT,	&rapl_defaults_byt),
 	X86_MATCH_INTEL_FAM6_MODEL(ATOM_AIRMONT,	&rapl_defaults_cht),
diff --git a/drivers/rapidio/Kconfig b/drivers/rapidio/Kconfig
index e4c422d806be..b9f8514909bf 100644
--- a/drivers/rapidio/Kconfig
+++ b/drivers/rapidio/Kconfig
@@ -37,7 +37,7 @@ config RAPIDIO_ENABLE_RX_TX_PORTS
 config RAPIDIO_DMA_ENGINE
 	bool "DMA Engine support for RapidIO"
 	depends on RAPIDIO
-	select DMADEVICES
+	depends on DMADEVICES
 	select DMA_ENGINE
 	help
 	  Say Y here if you want to use DMA Engine frameork for RapidIO data
diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index 3fd359914690..7ff507ec875a 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -236,8 +236,8 @@ static bool regulator_supply_is_couple(struct regulator_dev *rdev)
 static void regulator_unlock_recursive(struct regulator_dev *rdev,
 				       unsigned int n_coupled)
 {
-	struct regulator_dev *c_rdev;
-	int i;
+	struct regulator_dev *c_rdev, *supply_rdev;
+	int i, supply_n_coupled;
 
 	for (i = n_coupled; i > 0; i--) {
 		c_rdev = rdev->coupling_desc.coupled_rdevs[i - 1];
@@ -245,10 +245,13 @@ static void regulator_unlock_recursive(struct regulator_dev *rdev,
 		if (!c_rdev)
 			continue;
 
-		if (c_rdev->supply && !regulator_supply_is_couple(c_rdev))
-			regulator_unlock_recursive(
-					c_rdev->supply->rdev,
-					c_rdev->coupling_desc.n_coupled);
+		if (c_rdev->supply && !regulator_supply_is_couple(c_rdev)) {
+			supply_rdev = c_rdev->supply->rdev;
+			supply_n_coupled = supply_rdev->coupling_desc.n_coupled;
+
+			regulator_unlock_recursive(supply_rdev,
+						   supply_n_coupled);
+		}
 
 		regulator_unlock(c_rdev);
 	}
@@ -1461,7 +1464,7 @@ static int set_consumer_device_supply(struct regulator_dev *rdev,
 				      const char *consumer_dev_name,
 				      const char *supply)
 {
-	struct regulator_map *node;
+	struct regulator_map *node, *new_node;
 	int has_dev;
 
 	if (supply == NULL)
@@ -1472,6 +1475,22 @@ static int set_consumer_device_supply(struct regulator_dev *rdev,
 	else
 		has_dev = 0;
 
+	new_node = kzalloc(sizeof(struct regulator_map), GFP_KERNEL);
+	if (new_node == NULL)
+		return -ENOMEM;
+
+	new_node->regulator = rdev;
+	new_node->supply = supply;
+
+	if (has_dev) {
+		new_node->dev_name = kstrdup(consumer_dev_name, GFP_KERNEL);
+		if (new_node->dev_name == NULL) {
+			kfree(new_node);
+			return -ENOMEM;
+		}
+	}
+
+	mutex_lock(&regulator_list_mutex);
 	list_for_each_entry(node, &regulator_map_list, list) {
 		if (node->dev_name && consumer_dev_name) {
 			if (strcmp(node->dev_name, consumer_dev_name) != 0)
@@ -1489,26 +1508,19 @@ static int set_consumer_device_supply(struct regulator_dev *rdev,
 			 node->regulator->desc->name,
 			 supply,
 			 dev_name(&rdev->dev), rdev_get_name(rdev));
-		return -EBUSY;
+		goto fail;
 	}
 
-	node = kzalloc(sizeof(struct regulator_map), GFP_KERNEL);
-	if (node == NULL)
-		return -ENOMEM;
-
-	node->regulator = rdev;
-	node->supply = supply;
-
-	if (has_dev) {
-		node->dev_name = kstrdup(consumer_dev_name, GFP_KERNEL);
-		if (node->dev_name == NULL) {
-			kfree(node);
-			return -ENOMEM;
-		}
-	}
+	list_add(&new_node->list, &regulator_map_list);
+	mutex_unlock(&regulator_list_mutex);
 
-	list_add(&node->list, &regulator_map_list);
 	return 0;
+
+fail:
+	mutex_unlock(&regulator_list_mutex);
+	kfree(new_node->dev_name);
+	kfree(new_node);
+	return -EBUSY;
 }
 
 static void unset_regulator_supplies(struct regulator_dev *rdev)
@@ -1580,44 +1592,53 @@ static struct regulator *create_regulator(struct regulator_dev *rdev,
 					  const char *supply_name)
 {
 	struct regulator *regulator;
-	char buf[REG_STR_SIZE];
-	int err, size;
+	int err;
+
+	if (dev) {
+		char buf[REG_STR_SIZE];
+		int size;
+
+		size = snprintf(buf, REG_STR_SIZE, "%s-%s",
+				dev->kobj.name, supply_name);
+		if (size >= REG_STR_SIZE)
+			return NULL;
+
+		supply_name = kstrdup(buf, GFP_KERNEL);
+		if (supply_name == NULL)
+			return NULL;
+	} else {
+		supply_name = kstrdup_const(supply_name, GFP_KERNEL);
+		if (supply_name == NULL)
+			return NULL;
+	}
 
 	regulator = kzalloc(sizeof(*regulator), GFP_KERNEL);
-	if (regulator == NULL)
+	if (regulator == NULL) {
+		kfree(supply_name);
 		return NULL;
+	}
 
-	regulator_lock(rdev);
 	regulator->rdev = rdev;
+	regulator->supply_name = supply_name;
+
+	regulator_lock(rdev);
 	list_add(&regulator->list, &rdev->consumer_list);
+	regulator_unlock(rdev);
 
 	if (dev) {
 		regulator->dev = dev;
 
 		/* Add a link to the device sysfs entry */
-		size = snprintf(buf, REG_STR_SIZE, "%s-%s",
-				dev->kobj.name, supply_name);
-		if (size >= REG_STR_SIZE)
-			goto overflow_err;
-
-		regulator->supply_name = kstrdup(buf, GFP_KERNEL);
-		if (regulator->supply_name == NULL)
-			goto overflow_err;
-
 		err = sysfs_create_link_nowarn(&rdev->dev.kobj, &dev->kobj,
-					buf);
+					       supply_name);
 		if (err) {
 			rdev_dbg(rdev, "could not add device link %s err %d\n",
 				  dev->kobj.name, err);
 			/* non-fatal */
 		}
-	} else {
-		regulator->supply_name = kstrdup_const(supply_name, GFP_KERNEL);
-		if (regulator->supply_name == NULL)
-			goto overflow_err;
 	}
 
-	regulator->debugfs = debugfs_create_dir(regulator->supply_name,
+	regulator->debugfs = debugfs_create_dir(supply_name,
 						rdev->debugfs);
 	if (!regulator->debugfs) {
 		rdev_dbg(rdev, "Failed to create debugfs directory\n");
@@ -1642,13 +1663,7 @@ static struct regulator *create_regulator(struct regulator_dev *rdev,
 	    _regulator_is_enabled(rdev))
 		regulator->always_on = true;
 
-	regulator_unlock(rdev);
 	return regulator;
-overflow_err:
-	list_del(&regulator->list);
-	kfree(regulator);
-	regulator_unlock(rdev);
-	return NULL;
 }
 
 static int _regulator_get_enable_time(struct regulator_dev *rdev)
@@ -2230,10 +2245,13 @@ EXPORT_SYMBOL_GPL(regulator_bulk_unregister_supply_alias);
 static int regulator_ena_gpio_request(struct regulator_dev *rdev,
 				const struct regulator_config *config)
 {
-	struct regulator_enable_gpio *pin;
+	struct regulator_enable_gpio *pin, *new_pin;
 	struct gpio_desc *gpiod;
 
 	gpiod = config->ena_gpiod;
+	new_pin = kzalloc(sizeof(*new_pin), GFP_KERNEL);
+
+	mutex_lock(&regulator_list_mutex);
 
 	list_for_each_entry(pin, &regulator_ena_gpio_list, list) {
 		if (pin->gpiod == gpiod) {
@@ -2242,9 +2260,13 @@ static int regulator_ena_gpio_request(struct regulator_dev *rdev,
 		}
 	}
 
-	pin = kzalloc(sizeof(struct regulator_enable_gpio), GFP_KERNEL);
-	if (pin == NULL)
+	if (new_pin == NULL) {
+		mutex_unlock(&regulator_list_mutex);
 		return -ENOMEM;
+	}
+
+	pin = new_pin;
+	new_pin = NULL;
 
 	pin->gpiod = gpiod;
 	list_add(&pin->list, &regulator_ena_gpio_list);
@@ -2252,6 +2274,10 @@ static int regulator_ena_gpio_request(struct regulator_dev *rdev,
 update_ena_gpio_to_rdev:
 	pin->request_count++;
 	rdev->ena_pin = pin;
+
+	mutex_unlock(&regulator_list_mutex);
+	kfree(new_pin);
+
 	return 0;
 }
 
@@ -2264,19 +2290,19 @@ static void regulator_ena_gpio_free(struct regulator_dev *rdev)
 
 	/* Free the GPIO only in case of no use */
 	list_for_each_entry_safe(pin, n, &regulator_ena_gpio_list, list) {
-		if (pin->gpiod == rdev->ena_pin->gpiod) {
-			if (pin->request_count <= 1) {
-				pin->request_count = 0;
-				gpiod_put(pin->gpiod);
-				list_del(&pin->list);
-				kfree(pin);
-				rdev->ena_pin = NULL;
-				return;
-			} else {
-				pin->request_count--;
-			}
-		}
+		if (pin != rdev->ena_pin)
+			continue;
+
+		if (--pin->request_count)
+			break;
+
+		gpiod_put(pin->gpiod);
+		list_del(&pin->list);
+		kfree(pin);
+		break;
 	}
+
+	rdev->ena_pin = NULL;
 }
 
 /**
@@ -4949,13 +4975,9 @@ static void regulator_resolve_coupling(struct regulator_dev *rdev)
 			return;
 		}
 
-		regulator_lock(c_rdev);
-
 		c_desc->coupled_rdevs[i] = c_rdev;
 		c_desc->n_resolved++;
 
-		regulator_unlock(c_rdev);
-
 		regulator_resolve_coupling(c_rdev);
 	}
 }
@@ -5040,7 +5062,10 @@ static int regulator_init_coupling(struct regulator_dev *rdev)
 	if (!of_check_coupling_data(rdev))
 		return -EPERM;
 
+	mutex_lock(&regulator_list_mutex);
 	rdev->coupling_desc.coupler = regulator_find_coupler(rdev);
+	mutex_unlock(&regulator_list_mutex);
+
 	if (IS_ERR(rdev->coupling_desc.coupler)) {
 		err = PTR_ERR(rdev->coupling_desc.coupler);
 		rdev_err(rdev, "failed to get coupler: %d\n", err);
@@ -5141,6 +5166,7 @@ regulator_register(const struct regulator_desc *regulator_desc,
 		ret = -ENOMEM;
 		goto rinse;
 	}
+	device_initialize(&rdev->dev);
 
 	/*
 	 * Duplicate the config so the driver could override it after
@@ -5148,9 +5174,8 @@ regulator_register(const struct regulator_desc *regulator_desc,
 	 */
 	config = kmemdup(cfg, sizeof(*cfg), GFP_KERNEL);
 	if (config == NULL) {
-		kfree(rdev);
 		ret = -ENOMEM;
-		goto rinse;
+		goto clean;
 	}
 
 	init_data = regulator_of_get_init_data(dev, regulator_desc, config,
@@ -5162,10 +5187,8 @@ regulator_register(const struct regulator_desc *regulator_desc,
 	 * from a gpio extender or something else.
 	 */
 	if (PTR_ERR(init_data) == -EPROBE_DEFER) {
-		kfree(config);
-		kfree(rdev);
 		ret = -EPROBE_DEFER;
-		goto rinse;
+		goto clean;
 	}
 
 	/*
@@ -5206,9 +5229,7 @@ regulator_register(const struct regulator_desc *regulator_desc,
 	}
 
 	if (config->ena_gpiod) {
-		mutex_lock(&regulator_list_mutex);
 		ret = regulator_ena_gpio_request(rdev, config);
-		mutex_unlock(&regulator_list_mutex);
 		if (ret != 0) {
 			rdev_err(rdev, "Failed to request enable GPIO: %d\n",
 				 ret);
@@ -5220,7 +5241,6 @@ regulator_register(const struct regulator_desc *regulator_desc,
 	}
 
 	/* register with sysfs */
-	device_initialize(&rdev->dev);
 	rdev->dev.class = &regulator_class;
 	rdev->dev.parent = dev;
 	dev_set_name(&rdev->dev, "regulator.%lu",
@@ -5248,27 +5268,22 @@ regulator_register(const struct regulator_desc *regulator_desc,
 	if (ret < 0)
 		goto wash;
 
-	mutex_lock(&regulator_list_mutex);
 	ret = regulator_init_coupling(rdev);
-	mutex_unlock(&regulator_list_mutex);
 	if (ret < 0)
 		goto wash;
 
 	/* add consumers devices */
 	if (init_data) {
-		mutex_lock(&regulator_list_mutex);
 		for (i = 0; i < init_data->num_consumer_supplies; i++) {
 			ret = set_consumer_device_supply(rdev,
 				init_data->consumer_supplies[i].dev_name,
 				init_data->consumer_supplies[i].supply);
 			if (ret < 0) {
-				mutex_unlock(&regulator_list_mutex);
 				dev_err(dev, "Failed to set supply %s\n",
 					init_data->consumer_supplies[i].supply);
 				goto unset_supplies;
 			}
 		}
-		mutex_unlock(&regulator_list_mutex);
 	}
 
 	if (!rdev->desc->ops->get_voltage &&
@@ -5303,13 +5318,11 @@ wash:
 	mutex_lock(&regulator_list_mutex);
 	regulator_ena_gpio_free(rdev);
 	mutex_unlock(&regulator_list_mutex);
-	put_device(&rdev->dev);
-	rdev = NULL;
 clean:
 	if (dangling_of_gpiod)
 		gpiod_put(config->ena_gpiod);
-	kfree(rdev);
 	kfree(config);
+	put_device(&rdev->dev);
 rinse:
 	if (dangling_cfg_gpiod)
 		gpiod_put(cfg->ena_gpiod);
diff --git a/drivers/regulator/cros-ec-regulator.c b/drivers/regulator/cros-ec-regulator.c
index 3117bbd2826b..eb3fc1db4edc 100644
--- a/drivers/regulator/cros-ec-regulator.c
+++ b/drivers/regulator/cros-ec-regulator.c
@@ -170,6 +170,9 @@ static int cros_ec_regulator_init_info(struct device *dev,
 	data->voltages_mV =
 		devm_kmemdup(dev, resp.voltages_mv,
 			     sizeof(u16) * data->num_voltages, GFP_KERNEL);
+	if (!data->voltages_mV)
+		return -ENOMEM;
+
 	data->desc.n_voltages = data->num_voltages;
 
 	/* Make sure the returned name is always a valid string */
diff --git a/drivers/regulator/fixed.c b/drivers/regulator/fixed.c
index d54830e48b8d..142a70a89153 100644
--- a/drivers/regulator/fixed.c
+++ b/drivers/regulator/fixed.c
@@ -182,7 +182,7 @@ static int reg_fixed_voltage_probe(struct platform_device *pdev)
 
 		drvdata->enable_clock = devm_clk_get(dev, NULL);
 		if (IS_ERR(drvdata->enable_clock)) {
-			dev_err(dev, "Cant get enable-clock from devicetree\n");
+			dev_err(dev, "Can't get enable-clock from devicetree\n");
 			return -ENOENT;
 		}
 	} else {
diff --git a/drivers/regulator/pwm-regulator.c b/drivers/regulator/pwm-regulator.c
index 3234b118b53e..990bd50771d8 100644
--- a/drivers/regulator/pwm-regulator.c
+++ b/drivers/regulator/pwm-regulator.c
@@ -279,7 +279,7 @@ static int pwm_regulator_init_table(struct platform_device *pdev,
 		return ret;
 	}
 
-	drvdata->state			= -EINVAL;
+	drvdata->state			= -ENOTRECOVERABLE;
 	drvdata->duty_cycle_table	= duty_cycle_table;
 	drvdata->desc.ops = &pwm_regulator_voltage_table_ops;
 	drvdata->desc.n_voltages	= length / sizeof(*duty_cycle_table);
diff --git a/drivers/s390/block/dasd_fba.c b/drivers/s390/block/dasd_fba.c
index cbb770824226..1a44e321b54e 100644
--- a/drivers/s390/block/dasd_fba.c
+++ b/drivers/s390/block/dasd_fba.c
@@ -40,6 +40,7 @@
 MODULE_LICENSE("GPL");
 
 static struct dasd_discipline dasd_fba_discipline;
+static void *dasd_fba_zero_page;
 
 struct dasd_fba_private {
 	struct dasd_fba_characteristics rdc_data;
@@ -270,7 +271,7 @@ static void ccw_write_zero(struct ccw1 *ccw, int count)
 	ccw->cmd_code = DASD_FBA_CCW_WRITE;
 	ccw->flags |= CCW_FLAG_SLI;
 	ccw->count = count;
-	ccw->cda = (__u32) (addr_t) page_to_phys(ZERO_PAGE(0));
+	ccw->cda = (__u32) (addr_t) dasd_fba_zero_page;
 }
 
 /*
@@ -830,6 +831,11 @@ dasd_fba_init(void)
 	int ret;
 
 	ASCEBC(dasd_fba_discipline.ebcname, 4);
+
+	dasd_fba_zero_page = (void *)get_zeroed_page(GFP_KERNEL | GFP_DMA);
+	if (!dasd_fba_zero_page)
+		return -ENOMEM;
+
 	ret = ccw_driver_register(&dasd_fba_driver);
 	if (!ret)
 		wait_for_device_probe();
@@ -841,6 +847,7 @@ static void __exit
 dasd_fba_cleanup(void)
 {
 	ccw_driver_unregister(&dasd_fba_driver);
+	free_page((unsigned long)dasd_fba_zero_page);
 }
 
 module_init(dasd_fba_init);
diff --git a/drivers/s390/crypto/zcrypt_ccamisc.c b/drivers/s390/crypto/zcrypt_ccamisc.c
index 3f5b61351cde..c793dcabd551 100644
--- a/drivers/s390/crypto/zcrypt_ccamisc.c
+++ b/drivers/s390/crypto/zcrypt_ccamisc.c
@@ -1692,9 +1692,9 @@ int cca_findcard2(u32 **apqns, u32 *nr_apqns, u16 cardnr, u16 domain,
 	*nr_apqns = 0;
 
 	/* fetch status of all crypto cards */
-	device_status = kmalloc_array(MAX_ZDEV_ENTRIES_EXT,
-				      sizeof(struct zcrypt_device_status_ext),
-				      GFP_KERNEL);
+	device_status = kvmalloc_array(MAX_ZDEV_ENTRIES_EXT,
+				       sizeof(struct zcrypt_device_status_ext),
+				       GFP_KERNEL);
 	if (!device_status)
 		return -ENOMEM;
 	zcrypt_device_status_mask_ext(device_status);
@@ -1762,7 +1762,7 @@ int cca_findcard2(u32 **apqns, u32 *nr_apqns, u16 cardnr, u16 domain,
 		verify = 0;
 	}
 
-	kfree(device_status);
+	kvfree(device_status);
 	return rc;
 }
 EXPORT_SYMBOL(cca_findcard2);
diff --git a/drivers/s390/net/ctcm_fsms.h b/drivers/s390/net/ctcm_fsms.h
index 225737295cb4..d98c486724d4 100644
--- a/drivers/s390/net/ctcm_fsms.h
+++ b/drivers/s390/net/ctcm_fsms.h
@@ -159,7 +159,6 @@ extern const char *ctc_ch_state_names[];
 
 void ctcm_ccw_check_rc(struct channel *ch, int rc, char *msg);
 void ctcm_purge_skb_queue(struct sk_buff_head *q);
-void fsm_action_nop(fsm_instance *fi, int event, void *arg);
 
 /*
  * ----- non-static actions for ctcm channel statemachine -----
diff --git a/drivers/s390/net/ctcm_mpc.h b/drivers/s390/net/ctcm_mpc.h
index 441d7b211f0f..da41b26f76d1 100644
--- a/drivers/s390/net/ctcm_mpc.h
+++ b/drivers/s390/net/ctcm_mpc.h
@@ -228,7 +228,6 @@ static inline void ctcmpc_dump32(char *buf, int len)
 		ctcmpc_dumpit(buf, 32);
 }
 
-int ctcmpc_open(struct net_device *);
 void ctcm_ccw_check_rc(struct channel *, int, char *);
 void mpc_group_ready(unsigned long adev);
 void mpc_channel_action(struct channel *ch, int direction, int action);
diff --git a/drivers/s390/net/ism.h b/drivers/s390/net/ism.h
index 1901e9c80ed8..38fe90c2597d 100644
--- a/drivers/s390/net/ism.h
+++ b/drivers/s390/net/ism.h
@@ -16,6 +16,7 @@
 #define ISM_DMB_WORD_OFFSET	1
 #define ISM_DMB_BIT_OFFSET	(ISM_DMB_WORD_OFFSET * 32)
 #define ISM_NR_DMBS		1920
+#define ISM_IDENT_MASK		0x00FFFF
 
 #define ISM_REG_SBA	0x1
 #define ISM_REG_IEQ	0x2
@@ -206,6 +207,12 @@ struct ism_dev {
 #define ISM_CREATE_REQ(dmb, idx, sf, offset)		\
 	((dmb) | (idx) << 24 | (sf) << 23 | (offset))
 
+struct ism_systemeid {
+	u8	seid_string[24];
+	u8	serial_number[4];
+	u8	type[4];
+};
+
 static inline void __ism_read_cmd(struct ism_dev *ism, void *data,
 				  unsigned long offset, unsigned long len)
 {
diff --git a/drivers/s390/net/ism_drv.c b/drivers/s390/net/ism_drv.c
index 5fbe9eae84d1..fe96ca3c88a5 100644
--- a/drivers/s390/net/ism_drv.c
+++ b/drivers/s390/net/ism_drv.c
@@ -13,6 +13,8 @@
 #include <linux/device.h>
 #include <linux/pci.h>
 #include <linux/err.h>
+#include <linux/ctype.h>
+#include <linux/processor.h>
 #include <net/smc.h>
 
 #include <asm/debug.h>
@@ -387,6 +389,42 @@ static int ism_move(struct smcd_dev *smcd, u64 dmb_tok, unsigned int idx,
 	return 0;
 }
 
+static struct ism_systemeid SYSTEM_EID = {
+	.seid_string = "IBM-SYSZ-IBMSEID00000000",
+	.serial_number = "0000",
+	.type = "0000",
+};
+
+static void ism_create_system_eid(void)
+{
+	struct cpuid id;
+	u16 ident_tail;
+	char tmp[5];
+
+	get_cpu_id(&id);
+	ident_tail = (u16)(id.ident & ISM_IDENT_MASK);
+	snprintf(tmp, 5, "%04X", ident_tail);
+	memcpy(&SYSTEM_EID.serial_number, tmp, 4);
+	snprintf(tmp, 5, "%04X", id.machine);
+	memcpy(&SYSTEM_EID.type, tmp, 4);
+}
+
+static void ism_get_system_eid(struct smcd_dev *smcd, u8 **eid)
+{
+	*eid = &SYSTEM_EID.seid_string[0];
+}
+
+static u16 ism_get_chid(struct smcd_dev *smcd)
+{
+	struct ism_dev *ismdev;
+
+	ismdev = (struct ism_dev *)smcd->priv;
+	if (!ismdev || !ismdev->pdev)
+		return 0;
+
+	return to_zpci(ismdev->pdev)->pchid;
+}
+
 static void ism_handle_event(struct ism_dev *ism)
 {
 	struct smcd_event *entry;
@@ -443,6 +481,8 @@ static const struct smcd_ops ism_ops = {
 	.reset_vlan_required = ism_reset_vlan_required,
 	.signal_event = ism_signal_ieq,
 	.move_data = ism_move,
+	.get_system_eid = ism_get_system_eid,
+	.get_chid = ism_get_chid,
 };
 
 static int ism_dev_init(struct ism_dev *ism)
@@ -471,6 +511,10 @@ static int ism_dev_init(struct ism_dev *ism)
 	if (ret)
 		goto unreg_ieq;
 
+	if (!ism_add_vlan_id(ism->smcd, ISM_RESERVED_VLANID))
+		/* hardware is V2 capable */
+		ism_create_system_eid();
+
 	ret = smcd_register_dev(ism->smcd);
 	if (ret)
 		goto unreg_ieq;
@@ -550,6 +594,9 @@ static void ism_dev_exit(struct ism_dev *ism)
 	struct pci_dev *pdev = ism->pdev;
 
 	smcd_unregister_dev(ism->smcd);
+	if (SYSTEM_EID.serial_number[0] != '0' ||
+	    SYSTEM_EID.type[0] != '0')
+		ism_del_vlan_id(ism->smcd, ISM_RESERVED_VLANID);
 	unregister_ieq(ism);
 	unregister_sba(ism);
 	free_irq(pci_irq_vector(pdev, 0), ism);
diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index 2c14012ca35d..f73b4756ed5e 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -177,8 +177,8 @@ struct qeth_vnicc_info {
 /**
  * some more defs
  */
-#define QETH_TX_TIMEOUT		100 * HZ
-#define QETH_RCD_TIMEOUT	60 * HZ
+#define QETH_TX_TIMEOUT		(100 * HZ)
+#define QETH_RCD_TIMEOUT	(60 * HZ)
 #define QETH_RECLAIM_WORK_TIME	HZ
 #define QETH_MAX_PORTNO		15
 
@@ -195,8 +195,8 @@ struct qeth_vnicc_info {
 #define QETH_IN_BUF_SIZE_DEFAULT 65536
 #define QETH_IN_BUF_COUNT_DEFAULT 64
 #define QETH_IN_BUF_COUNT_HSDEFAULT 128
-#define QETH_IN_BUF_COUNT_MIN 8
-#define QETH_IN_BUF_COUNT_MAX 128
+#define QETH_IN_BUF_COUNT_MIN	8U
+#define QETH_IN_BUF_COUNT_MAX	128U
 #define QETH_MAX_BUFFER_ELEMENTS(card) ((card)->qdio.in_buf_size >> 12)
 #define QETH_IN_BUF_REQUEUE_THRESHOLD(card) \
 		 ((card)->qdio.in_buf_pool.buf_count / 2)
@@ -278,6 +278,26 @@ struct qeth_hdr {
 	} hdr;
 } __attribute__ ((packed));
 
+#define QETH_QIB_PQUE_ORDER_RR		0
+#define QETH_QIB_PQUE_UNITS_SBAL	2
+#define QETH_QIB_PQUE_PRIO_DEFAULT	4
+
+struct qeth_qib_parms {
+	char pcit_magic[4];
+	u32 pcit_a;
+	u32 pcit_b;
+	u32 pcit_c;
+	char blkt_magic[4];
+	u32 blkt_total;
+	u32 blkt_inter_packet;
+	u32 blkt_inter_packet_jumbo;
+	char pque_magic[4];
+	u8 pque_order;
+	u8 pque_units;
+	u16 reserved;
+	u32 pque_priority[4];
+};
+
 /*TCP Segmentation Offload header*/
 struct qeth_hdr_ext_tso {
 	__u16 hdr_tot_len;
@@ -481,6 +501,7 @@ struct qeth_qdio_out_q {
 	struct qdio_outbuf_state *bufstates; /* convenience pointer */
 	struct qeth_out_q_stats stats;
 	spinlock_t lock;
+	unsigned int priority;
 	u8 next_buf_to_fill;
 	u8 max_elements;
 	u8 queue_no;
@@ -538,7 +559,7 @@ struct qeth_qdio_info {
 	int in_buf_size;
 
 	/* output */
-	int no_out_queues;
+	unsigned int no_out_queues;
 	struct qeth_qdio_out_q *out_qs[QETH_MAX_OUT_QUEUES];
 	struct qdio_outbuf_state *out_bufstates;
 
@@ -753,7 +774,7 @@ struct qeth_discipline {
 	const struct device_type *devtype;
 	int (*setup) (struct ccwgroup_device *);
 	void (*remove) (struct ccwgroup_device *);
-	int (*set_online)(struct qeth_card *card);
+	int (*set_online)(struct qeth_card *card, bool carrier_ok);
 	void (*set_offline)(struct qeth_card *card);
 	int (*do_ioctl)(struct net_device *dev, struct ifreq *rq, int cmd);
 	int (*control_event_handler)(struct qeth_card *card,
@@ -788,6 +809,7 @@ struct qeth_switch_info {
 
 struct qeth_priv {
 	unsigned int rx_copybreak;
+	unsigned int tx_wanted_queues;
 	u32 brport_hw_features;
 	u32 brport_features;
 };
@@ -814,12 +836,16 @@ struct qeth_card {
 	struct workqueue_struct *event_wq;
 	struct workqueue_struct *cmd_wq;
 	wait_queue_head_t wait_q;
+
+	struct mutex ip_lock;
+	/* protected by ip_lock: */
 	DECLARE_HASHTABLE(ip_htable, 4);
+	struct qeth_ipato ipato;
+
 	DECLARE_HASHTABLE(local_addrs4, 4);
 	DECLARE_HASHTABLE(local_addrs6, 4);
 	spinlock_t local_addrs4_lock;
 	spinlock_t local_addrs6_lock;
-	struct mutex ip_lock;
 	DECLARE_HASHTABLE(rx_mode_addrs, 4);
 	struct work_struct rx_mode_work;
 	struct work_struct kernel_thread_starter;
@@ -827,13 +853,12 @@ struct qeth_card {
 	unsigned long thread_start_mask;
 	unsigned long thread_allowed_mask;
 	unsigned long thread_running_mask;
-	struct qeth_ipato ipato;
 	struct list_head cmd_waiter_list;
 	/* QDIO buffer handling */
 	struct qeth_qdio_info qdio;
 	int read_or_write_problem;
 	struct qeth_osn_info osn_info;
-	struct qeth_discipline *discipline;
+	const struct qeth_discipline *discipline;
 	atomic_t force_alloc_skb;
 	struct service_level qeth_service_level;
 	struct qdio_ssqd_desc ssqd;
@@ -867,8 +892,20 @@ struct qeth_trap_id {
 	__u16 devno;
 } __packed;
 
-/*some helper functions*/
-#define QETH_CARD_IFNAME(card) (((card)->dev)? (card)->dev->name : "")
+static inline bool qeth_uses_tx_prio_queueing(struct qeth_card *card)
+{
+	return card->qdio.do_prio_queueing != QETH_NO_PRIO_QUEUEING;
+}
+
+static inline unsigned int qeth_tx_actual_queues(struct qeth_card *card)
+{
+	struct qeth_priv *priv = netdev_priv(card->dev);
+
+	if (qeth_uses_tx_prio_queueing(card))
+		return min(card->dev->num_tx_queues, card->qdio.no_out_queues);
+
+	return min(priv->tx_wanted_queues, card->qdio.no_out_queues);
+}
 
 static inline u16 qeth_iqd_translate_txq(struct net_device *dev, u16 txq)
 {
@@ -1011,8 +1048,8 @@ static inline int qeth_send_simple_setassparms_v6(struct qeth_card *card,
 
 int qeth_get_priority_queue(struct qeth_card *card, struct sk_buff *skb);
 
-extern struct qeth_discipline qeth_l2_discipline;
-extern struct qeth_discipline qeth_l3_discipline;
+extern const struct qeth_discipline qeth_l2_discipline;
+extern const struct qeth_discipline qeth_l3_discipline;
 extern const struct ethtool_ops qeth_ethtool_ops;
 extern const struct ethtool_ops qeth_osn_ethtool_ops;
 extern const struct attribute_group *qeth_generic_attr_groups[];
@@ -1032,13 +1069,11 @@ extern struct qeth_dbf_info qeth_dbf[QETH_DBF_INFOS];
 
 struct net_device *qeth_clone_netdev(struct net_device *orig);
 struct qeth_card *qeth_get_card_by_busid(char *bus_id);
-void qeth_set_allowed_threads(struct qeth_card *, unsigned long , int);
+void qeth_set_allowed_threads(struct qeth_card *card, unsigned long threads,
+			      int clear_start_mask);
 int qeth_threads_running(struct qeth_card *, unsigned long);
-int qeth_core_hardsetup_card(struct qeth_card *card, bool *carrier_ok);
-int qeth_stop_channel(struct qeth_channel *channel);
 int qeth_set_offline(struct qeth_card *card, bool resetting);
 
-void qeth_print_status_message(struct qeth_card *);
 int qeth_send_ipa_cmd(struct qeth_card *, struct qeth_cmd_buffer *,
 		  int (*reply_cb)
 		  (struct qeth_card *, struct qeth_reply *, unsigned long),
@@ -1062,12 +1097,7 @@ void qeth_notify_cmd(struct qeth_cmd_buffer *iob, int reason);
 void qeth_put_cmd(struct qeth_cmd_buffer *iob);
 
 int qeth_schedule_recovery(struct qeth_card *card);
-void qeth_flush_local_addrs(struct qeth_card *card);
 int qeth_poll(struct napi_struct *napi, int budget);
-void qeth_clear_ipacmd_list(struct qeth_card *);
-int qeth_qdio_clear_card(struct qeth_card *, int);
-void qeth_clear_working_pool_list(struct qeth_card *);
-void qeth_drain_output_queues(struct qeth_card *card);
 void qeth_setadp_promisc_mode(struct qeth_card *card, bool enable);
 int qeth_setadpparms_change_macaddr(struct qeth_card *);
 void qeth_tx_timeout(struct net_device *, unsigned int txqueue);
@@ -1091,9 +1121,7 @@ int qeth_do_ioctl(struct net_device *dev, struct ifreq *rq, int cmd);
 void qeth_dbf_longtext(debug_info_t *id, int level, char *text, ...);
 int qeth_configure_cq(struct qeth_card *, enum qeth_cq);
 int qeth_hw_trap(struct qeth_card *, enum qeth_diags_trap_action);
-void qeth_trace_features(struct qeth_card *);
 int qeth_setassparms_cb(struct qeth_card *, struct qeth_reply *, unsigned long);
-int qeth_setup_netdev(struct qeth_card *card);
 int qeth_set_features(struct net_device *, netdev_features_t);
 void qeth_enable_hw_features(struct net_device *dev);
 netdev_features_t qeth_fix_features(struct net_device *, netdev_features_t);
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 7cd0cbf8a4f0..93c9b30ab17a 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -17,6 +17,7 @@
 #include <linux/errno.h>
 #include <linux/kernel.h>
 #include <linux/log2.h>
+#include <linux/io.h>
 #include <linux/ip.h>
 #include <linux/tcp.h>
 #include <linux/mii.h>
@@ -35,7 +36,6 @@
 
 #include <asm/ebcdic.h>
 #include <asm/chpid.h>
-#include <asm/io.h>
 #include <asm/sysinfo.h>
 #include <asm/diag.h>
 #include <asm/cio.h>
@@ -201,7 +201,7 @@ int qeth_threads_running(struct qeth_card *card, unsigned long threads)
 }
 EXPORT_SYMBOL_GPL(qeth_threads_running);
 
-void qeth_clear_working_pool_list(struct qeth_card *card)
+static void qeth_clear_working_pool_list(struct qeth_card *card)
 {
 	struct qeth_buffer_pool_entry *pool_entry, *tmp;
 	struct qeth_qdio_q *queue = card->qdio.in_q;
@@ -209,14 +209,12 @@ void qeth_clear_working_pool_list(struct qeth_card *card)
 
 	QETH_CARD_TEXT(card, 5, "clwrklst");
 	list_for_each_entry_safe(pool_entry, tmp,
-			    &card->qdio.in_buf_pool.entry_list, list){
-			list_del(&pool_entry->list);
-	}
+				 &card->qdio.in_buf_pool.entry_list, list)
+		list_del(&pool_entry->list);
 
 	for (i = 0; i < ARRAY_SIZE(queue->bufs); i++)
 		queue->bufs[i].pool_entry = NULL;
 }
-EXPORT_SYMBOL_GPL(qeth_clear_working_pool_list);
 
 static void qeth_free_pool_entry(struct qeth_buffer_pool_entry *entry)
 {
@@ -482,6 +480,7 @@ static void qeth_cleanup_handled_pending(struct qeth_qdio_out_q *q, int bidx,
 			    atomic_read(&c->state) ==
 			      QETH_QDIO_BUF_HANDLED_DELAYED) {
 				struct qeth_qdio_out_buffer *f = c;
+
 				QETH_CARD_TEXT(f->q->card, 5, "fp");
 				QETH_CARD_TEXT_(f->q->card, 5, "%lx", (long) f);
 				/* release here to avoid interleaving between
@@ -508,7 +507,6 @@ static void qeth_cleanup_handled_pending(struct qeth_qdio_out_q *q, int bidx,
 	}
 }
 
-
 static void qeth_qdio_handle_aob(struct qeth_card *card,
 				 unsigned long phys_aob_addr)
 {
@@ -658,12 +656,11 @@ static void qeth_flush_local_addrs6(struct qeth_card *card)
 	spin_unlock_irq(&card->local_addrs6_lock);
 }
 
-void qeth_flush_local_addrs(struct qeth_card *card)
+static void qeth_flush_local_addrs(struct qeth_card *card)
 {
 	qeth_flush_local_addrs4(card);
 	qeth_flush_local_addrs6(card);
 }
-EXPORT_SYMBOL_GPL(qeth_flush_local_addrs);
 
 static void qeth_add_local_addrs4(struct qeth_card *card,
 				  struct qeth_ipacmd_local_addrs4 *cmd)
@@ -886,6 +883,7 @@ static void qeth_issue_ipa_msg(struct qeth_ipa_cmd *cmd, int rc,
 {
 	const char *ipa_name;
 	int com = cmd->hdr.command;
+
 	ipa_name = qeth_get_ipa_cmd_name(com);
 
 	if (rc)
@@ -917,12 +915,12 @@ static struct qeth_ipa_cmd *qeth_check_ipa_data(struct qeth_card *card,
 		if (cmd->hdr.return_code == IPA_RC_VEPA_TO_VEB_TRANSITION) {
 			dev_err(&card->gdev->dev,
 				"Interface %s is down because the adjacent port is no longer in reflective relay mode\n",
-				QETH_CARD_IFNAME(card));
+				netdev_name(card->dev));
 			schedule_work(&card->close_dev_work);
 		} else {
 			dev_warn(&card->gdev->dev,
 				 "The link for interface %s on CHPID 0x%X failed\n",
-				 QETH_CARD_IFNAME(card), card->info.chpid);
+				 netdev_name(card->dev), card->info.chpid);
 			qeth_issue_ipa_msg(cmd, cmd->hdr.return_code, card);
 			netif_carrier_off(card->dev);
 		}
@@ -930,7 +928,7 @@ static struct qeth_ipa_cmd *qeth_check_ipa_data(struct qeth_card *card,
 	case IPA_CMD_STARTLAN:
 		dev_info(&card->gdev->dev,
 			 "The link for %s on CHPID 0x%X has been restored\n",
-			 QETH_CARD_IFNAME(card), card->info.chpid);
+			 netdev_name(card->dev), card->info.chpid);
 		if (card->info.hwtrap)
 			card->info.hwtrap = 2;
 		qeth_schedule_recovery(card);
@@ -965,7 +963,7 @@ static struct qeth_ipa_cmd *qeth_check_ipa_data(struct qeth_card *card,
 	}
 }
 
-void qeth_clear_ipacmd_list(struct qeth_card *card)
+static void qeth_clear_ipacmd_list(struct qeth_card *card)
 {
 	struct qeth_cmd_buffer *iob;
 	unsigned long flags;
@@ -977,7 +975,6 @@ void qeth_clear_ipacmd_list(struct qeth_card *card)
 		qeth_notify_cmd(iob, -ECANCELED);
 	spin_unlock_irqrestore(&card->lock, flags);
 }
-EXPORT_SYMBOL_GPL(qeth_clear_ipacmd_list);
 
 static int qeth_check_idx_response(struct qeth_card *card,
 	unsigned char *buffer)
@@ -1256,7 +1253,7 @@ static int qeth_get_problem(struct qeth_card *card, struct ccw_device *cdev,
 			return 0;
 		}
 		QETH_CARD_TEXT(card, 2, "DGENCHK");
-			return -EIO;
+		return -EIO;
 	}
 	return 0;
 }
@@ -1502,7 +1499,7 @@ static void qeth_drain_output_queue(struct qeth_qdio_out_q *q, bool free)
 	}
 }
 
-void qeth_drain_output_queues(struct qeth_card *card)
+static void qeth_drain_output_queues(struct qeth_card *card)
 {
 	int i;
 
@@ -1513,25 +1510,13 @@ void qeth_drain_output_queues(struct qeth_card *card)
 			qeth_drain_output_queue(card->qdio.out_qs[i], false);
 	}
 }
-EXPORT_SYMBOL_GPL(qeth_drain_output_queues);
 
-static int qeth_osa_set_output_queues(struct qeth_card *card, bool single)
+static void qeth_osa_set_output_queues(struct qeth_card *card, bool single)
 {
 	unsigned int max = single ? 1 : card->dev->num_tx_queues;
-	unsigned int count;
-	int rc;
-
-	count = IS_VM_NIC(card) ? min(max, card->dev->real_num_tx_queues) : max;
-
-	rtnl_lock();
-	rc = netif_set_real_num_tx_queues(card->dev, count);
-	rtnl_unlock();
-
-	if (rc)
-		return rc;
 
 	if (card->qdio.no_out_queues == max)
-		return 0;
+		return;
 
 	if (atomic_read(&card->qdio.state) != QETH_QDIO_UNINITIALIZED)
 		qeth_free_qdio_queues(card);
@@ -1540,14 +1525,12 @@ static int qeth_osa_set_output_queues(struct qeth_card *card, bool single)
 		dev_info(&card->gdev->dev, "Priority Queueing not supported\n");
 
 	card->qdio.no_out_queues = max;
-	return 0;
 }
 
 static int qeth_update_from_chp_desc(struct qeth_card *card)
 {
 	struct ccw_device *ccwdev;
 	struct channel_path_desc_fmt0 *chp_dsc;
-	int rc = 0;
 
 	QETH_CARD_TEXT(card, 2, "chp_desc");
 
@@ -1560,12 +1543,12 @@ static int qeth_update_from_chp_desc(struct qeth_card *card)
 
 	if (IS_OSD(card) || IS_OSX(card))
 		/* CHPP field bit 6 == 1 -> single queue */
-		rc = qeth_osa_set_output_queues(card, chp_dsc->chpp & 0x02);
+		qeth_osa_set_output_queues(card, chp_dsc->chpp & 0x02);
 
 	kfree(chp_dsc);
 	QETH_CARD_TEXT_(card, 2, "nr:%x", card->qdio.no_out_queues);
 	QETH_CARD_TEXT_(card, 2, "lvl:%02x", card->info.func_level);
-	return rc;
+	return 0;
 }
 
 static void qeth_init_qdio_info(struct qeth_card *card)
@@ -1617,7 +1600,7 @@ static void qeth_start_kernel_thread(struct work_struct *work)
 	struct task_struct *ts;
 	struct qeth_card *card = container_of(work, struct qeth_card,
 					kernel_thread_starter);
-	QETH_CARD_TEXT(card , 2, "strthrd");
+	QETH_CARD_TEXT(card, 2, "strthrd");
 
 	if (card->read.state != CH_STATE_UP &&
 	    card->write.state != CH_STATE_UP)
@@ -1754,7 +1737,7 @@ static int qeth_halt_channel(struct qeth_card *card,
 	return 0;
 }
 
-int qeth_stop_channel(struct qeth_channel *channel)
+static int qeth_stop_channel(struct qeth_channel *channel)
 {
 	struct ccw_device *cdev = channel->ccwdev;
 	int rc;
@@ -1772,7 +1755,6 @@ int qeth_stop_channel(struct qeth_channel *channel)
 
 	return rc;
 }
-EXPORT_SYMBOL_GPL(qeth_stop_channel);
 
 static int qeth_start_channel(struct qeth_channel *channel)
 {
@@ -1842,7 +1824,7 @@ static int qeth_clear_halt_card(struct qeth_card *card, int halt)
 	return qeth_clear_channels(card);
 }
 
-int qeth_qdio_clear_card(struct qeth_card *card, int use_halt)
+static int qeth_qdio_clear_card(struct qeth_card *card, int use_halt)
 {
 	int rc = 0;
 
@@ -1870,7 +1852,6 @@ int qeth_qdio_clear_card(struct qeth_card *card, int use_halt)
 		QETH_CARD_TEXT_(card, 3, "2err%d", rc);
 	return rc;
 }
-EXPORT_SYMBOL_GPL(qeth_qdio_clear_card);
 
 static enum qeth_discipline_id qeth_vm_detect_layer(struct qeth_card *card)
 {
@@ -2702,6 +2683,7 @@ static int qeth_alloc_qdio_queues(struct qeth_card *card)
 		timer_setup(&queue->timer, qeth_tx_completion_timer, 0);
 		queue->coalesce_usecs = QETH_TX_COALESCE_USECS;
 		queue->max_coalesced_frames = QETH_TX_MAX_COALESCED_FRAMES;
+		queue->priority = QETH_QIB_PQUE_PRIO_DEFAULT;
 
 		/* give outbound qeth_qdio_buffers their qdio_buffers */
 		for (j = 0; j < QDIO_MAX_BUFFERS_PER_Q; ++j) {
@@ -2762,30 +2744,44 @@ static void qeth_free_qdio_queues(struct qeth_card *card)
 	}
 }
 
-static void qeth_create_qib_param_field(struct qeth_card *card,
-		char *param_field)
+static void qeth_fill_qib_parms(struct qeth_card *card,
+				struct qeth_qib_parms *parms)
 {
+	struct qeth_qdio_out_q *queue;
+	unsigned int i;
 
-	param_field[0] = _ascebc['P'];
-	param_field[1] = _ascebc['C'];
-	param_field[2] = _ascebc['I'];
-	param_field[3] = _ascebc['T'];
-	*((unsigned int *) (&param_field[4])) = QETH_PCI_THRESHOLD_A(card);
-	*((unsigned int *) (&param_field[8])) = QETH_PCI_THRESHOLD_B(card);
-	*((unsigned int *) (&param_field[12])) = QETH_PCI_TIMER_VALUE(card);
-}
+	parms->pcit_magic[0] = 'P';
+	parms->pcit_magic[1] = 'C';
+	parms->pcit_magic[2] = 'I';
+	parms->pcit_magic[3] = 'T';
+	ASCEBC(parms->pcit_magic, sizeof(parms->pcit_magic));
+	parms->pcit_a = QETH_PCI_THRESHOLD_A(card);
+	parms->pcit_b = QETH_PCI_THRESHOLD_B(card);
+	parms->pcit_c = QETH_PCI_TIMER_VALUE(card);
+
+	parms->blkt_magic[0] = 'B';
+	parms->blkt_magic[1] = 'L';
+	parms->blkt_magic[2] = 'K';
+	parms->blkt_magic[3] = 'T';
+	ASCEBC(parms->blkt_magic, sizeof(parms->blkt_magic));
+	parms->blkt_total = card->info.blkt.time_total;
+	parms->blkt_inter_packet = card->info.blkt.inter_packet;
+	parms->blkt_inter_packet_jumbo = card->info.blkt.inter_packet_jumbo;
+
+	/* Prio-queueing implicitly uses the default priorities: */
+	if (qeth_uses_tx_prio_queueing(card) || card->qdio.no_out_queues == 1)
+		return;
 
-static void qeth_create_qib_param_field_blkt(struct qeth_card *card,
-		char *param_field)
-{
-	param_field[16] = _ascebc['B'];
-	param_field[17] = _ascebc['L'];
-	param_field[18] = _ascebc['K'];
-	param_field[19] = _ascebc['T'];
-	*((unsigned int *) (&param_field[20])) = card->info.blkt.time_total;
-	*((unsigned int *) (&param_field[24])) = card->info.blkt.inter_packet;
-	*((unsigned int *) (&param_field[28])) =
-		card->info.blkt.inter_packet_jumbo;
+	parms->pque_magic[0] = 'P';
+	parms->pque_magic[1] = 'Q';
+	parms->pque_magic[2] = 'U';
+	parms->pque_magic[3] = 'E';
+	ASCEBC(parms->pque_magic, sizeof(parms->pque_magic));
+	parms->pque_order = QETH_QIB_PQUE_ORDER_RR;
+	parms->pque_units = QETH_QIB_PQUE_UNITS_SBAL;
+
+	qeth_for_each_output_queue(card, queue, i)
+		parms->pque_priority[i] = queue->priority;
 }
 
 static int qeth_qdio_activate(struct qeth_card *card)
@@ -2867,7 +2863,7 @@ static int qeth_mpc_initialize(struct qeth_card *card)
 	return 0;
 }
 
-void qeth_print_status_message(struct qeth_card *card)
+static void qeth_print_status_message(struct qeth_card *card)
 {
 	switch (card->info.type) {
 	case QETH_CARD_TYPE_OSD:
@@ -2908,7 +2904,6 @@ void qeth_print_status_message(struct qeth_card *card)
 		 (card->info.mcl_level[0]) ? ")" : "",
 		 qeth_get_cardname_short(card));
 }
-EXPORT_SYMBOL_GPL(qeth_print_status_message);
 
 static void qeth_initialize_working_pool_list(struct qeth_card *card)
 {
@@ -3421,7 +3416,6 @@ static void qeth_get_trap_id(struct qeth_card *card, struct qeth_trap_id *tid)
 		memcpy(tid->vmname, info322->vm[0].name, sizeof(tid->vmname));
 	}
 	free_page(info);
-	return;
 }
 
 static int qeth_hw_trap_cb(struct qeth_card *card,
@@ -5003,7 +4997,6 @@ static void qeth_determine_capabilities(struct qeth_card *card)
 		card->options.cq = QETH_CQ_NOTAVAILABLE;
 	}
 
-
 out_offline:
 	if (ddev_offline == 1)
 		qeth_stop_channel(channel);
@@ -5042,21 +5035,20 @@ static int qeth_qdio_establish(struct qeth_card *card)
 {
 	struct qdio_buffer **out_sbal_ptrs[QETH_MAX_OUT_QUEUES];
 	struct qdio_buffer **in_sbal_ptrs[QETH_MAX_IN_QUEUES];
+	struct qeth_qib_parms *qib_parms = NULL;
 	struct qdio_initialize init_data;
-	char *qib_param_field;
 	unsigned int i;
 	int rc = 0;
 
 	QETH_CARD_TEXT(card, 2, "qdioest");
 
-	qib_param_field = kzalloc(sizeof_field(struct qib, parm), GFP_KERNEL);
-	if (!qib_param_field) {
-		rc =  -ENOMEM;
-		goto out_free_nothing;
-	}
+	if (!IS_IQD(card) && !IS_VM_NIC(card)) {
+		qib_parms = kzalloc(sizeof_field(struct qib, parm), GFP_KERNEL);
+		if (!qib_parms)
+			return -ENOMEM;
 
-	qeth_create_qib_param_field(card, qib_param_field);
-	qeth_create_qib_param_field_blkt(card, qib_param_field);
+		qeth_fill_qib_parms(card, qib_parms);
+	}
 
 	in_sbal_ptrs[0] = card->qdio.in_q->qdio_bufs;
 	if (card->options.cq == QETH_CQ_ENABLED)
@@ -5069,7 +5061,7 @@ static int qeth_qdio_establish(struct qeth_card *card)
 	init_data.q_format		 = IS_IQD(card) ? QDIO_IQDIO_QFMT :
 							  QDIO_QETH_QFMT;
 	init_data.qib_param_field_format = 0;
-	init_data.qib_param_field        = qib_param_field;
+	init_data.qib_param_field	 = (void *)qib_parms;
 	init_data.no_input_qs            = card->qdio.no_in_queues;
 	init_data.no_output_qs           = card->qdio.no_out_queues;
 	init_data.input_handler		 = qeth_qdio_input_handler;
@@ -5106,9 +5098,9 @@ static int qeth_qdio_establish(struct qeth_card *card)
 	default:
 		break;
 	}
+
 out:
-	kfree(qib_param_field);
-out_free_nothing:
+	kfree(qib_parms);
 	return rc;
 }
 
@@ -5124,7 +5116,7 @@ static void qeth_core_free_card(struct qeth_card *card)
 	kfree(card);
 }
 
-void qeth_trace_features(struct qeth_card *card)
+static void qeth_trace_features(struct qeth_card *card)
 {
 	QETH_CARD_TEXT(card, 2, "features");
 	QETH_CARD_HEX(card, 2, &card->options.ipa4, sizeof(card->options.ipa4));
@@ -5133,7 +5125,6 @@ void qeth_trace_features(struct qeth_card *card)
 	QETH_CARD_HEX(card, 2, &card->info.diagass_support,
 		      sizeof(card->info.diagass_support));
 }
-EXPORT_SYMBOL_GPL(qeth_trace_features);
 
 static struct ccw_device_id qeth_ids[] = {
 	{CCW_DEVICE_DEVTYPE(0x1731, 0x01, 0x1732, 0x01),
@@ -5164,7 +5155,7 @@ static struct ccw_driver qeth_ccw_driver = {
 	.remove = ccwgroup_remove_ccwdev,
 };
 
-int qeth_core_hardsetup_card(struct qeth_card *card, bool *carrier_ok)
+static int qeth_hardsetup_card(struct qeth_card *card, bool *carrier_ok)
 {
 	int retries = 3;
 	int rc;
@@ -5278,6 +5269,8 @@ retriable:
 			QETH_CARD_TEXT_(card, 2, "8err%d", rc);
 	}
 
+	qeth_trace_features(card);
+
 	if (!qeth_is_diagass_supported(card, QETH_DIAGS_CMD_TRAP) ||
 	    (card->info.hwtrap && qeth_hw_trap(card, QETH_DIAGS_TRAP_ARM)))
 		card->info.hwtrap = 0;
@@ -5303,21 +5296,53 @@ out:
 			 CARD_DEVID(card), rc);
 	return rc;
 }
-EXPORT_SYMBOL_GPL(qeth_core_hardsetup_card);
 
 static int qeth_set_online(struct qeth_card *card)
 {
+	bool carrier_ok;
 	int rc;
 
 	mutex_lock(&card->discipline_mutex);
 	mutex_lock(&card->conf_mutex);
 	QETH_CARD_TEXT(card, 2, "setonlin");
 
-	rc = card->discipline->set_online(card);
+	rc = qeth_hardsetup_card(card, &carrier_ok);
+	if (rc) {
+		QETH_CARD_TEXT_(card, 2, "2err%04x", rc);
+		rc = -ENODEV;
+		goto err_hardsetup;
+	}
+
+	qeth_print_status_message(card);
+
+	if (card->dev->reg_state != NETREG_REGISTERED)
+		/* no need for locking / error handling at this early stage: */
+		qeth_set_real_num_tx_queues(card, qeth_tx_actual_queues(card));
+
+	rc = card->discipline->set_online(card, carrier_ok);
+	if (rc)
+		goto err_online;
+
+	/* let user_space know that device is online */
+	kobject_uevent(&card->gdev->dev.kobj, KOBJ_CHANGE);
 
 	mutex_unlock(&card->conf_mutex);
 	mutex_unlock(&card->discipline_mutex);
+	return 0;
+
+err_online:
+err_hardsetup:
+	qeth_qdio_clear_card(card, 0);
+	qeth_clear_working_pool_list(card);
+	qeth_flush_local_addrs(card);
+
+	qeth_stop_channel(&card->data);
+	qeth_stop_channel(&card->write);
+	qeth_stop_channel(&card->read);
+	qdio_free(CARD_DDEV(card));
 
+	mutex_unlock(&card->conf_mutex);
+	mutex_unlock(&card->discipline_mutex);
 	return rc;
 }
 
@@ -5334,6 +5359,9 @@ int qeth_set_offline(struct qeth_card *card, bool resetting)
 		card->info.hwtrap = 1;
 	}
 
+	/* cancel any stalled cmd that might block the rtnl: */
+	qeth_clear_ipacmd_list(card);
+
 	rtnl_lock();
 	card->info.open_when_online = card->dev->flags & IFF_UP;
 	dev_close(card->dev);
@@ -5341,8 +5369,16 @@ int qeth_set_offline(struct qeth_card *card, bool resetting)
 	netif_carrier_off(card->dev);
 	rtnl_unlock();
 
+	cancel_work_sync(&card->rx_mode_work);
+
 	card->discipline->set_offline(card);
 
+	qeth_qdio_clear_card(card, 0);
+	qeth_drain_output_queues(card);
+	qeth_clear_working_pool_list(card);
+	qeth_flush_local_addrs(card);
+	card->info.promisc_mode = 0;
+
 	rc  = qeth_stop_channel(&card->data);
 	rc2 = qeth_stop_channel(&card->write);
 	rc3 = qeth_stop_channel(&card->read);
@@ -6012,6 +6048,7 @@ EXPORT_SYMBOL_GPL(qeth_send_simple_setassparms_prot);
 static void qeth_unregister_dbf_views(void)
 {
 	int x;
+
 	for (x = 0; x < QETH_DBF_INFOS; x++) {
 		debug_unregister(qeth_dbf[x].id);
 		qeth_dbf[x].id = NULL;
@@ -6207,6 +6244,7 @@ static struct net_device *qeth_alloc_netdev(struct qeth_card *card)
 
 	priv = netdev_priv(dev);
 	priv->rx_copybreak = QETH_RX_COPYBREAK;
+	priv->tx_wanted_queues = IS_IQD(card) ? QETH_IQD_MIN_TXQ : 1;
 
 	dev->ml_priv = card;
 	dev->watchdog_timeo = QETH_TX_TIMEOUT;
@@ -6217,8 +6255,16 @@ static struct net_device *qeth_alloc_netdev(struct qeth_card *card)
 	SET_NETDEV_DEV(dev, &card->gdev->dev);
 	netif_carrier_off(dev);
 
-	dev->ethtool_ops = IS_OSN(card) ? &qeth_osn_ethtool_ops :
-					  &qeth_ethtool_ops;
+	if (IS_OSN(card)) {
+		dev->ethtool_ops = &qeth_osn_ethtool_ops;
+	} else {
+		dev->ethtool_ops = &qeth_ethtool_ops;
+		dev->priv_flags &= ~IFF_TX_SKB_SHARING;
+		dev->hw_features |= NETIF_F_SG;
+		dev->vlan_features |= NETIF_F_SG;
+		if (IS_IQD(card))
+			dev->features |= NETIF_F_SG;
+	}
 
 	return dev;
 }
@@ -6234,28 +6280,6 @@ struct net_device *qeth_clone_netdev(struct net_device *orig)
 	return clone;
 }
 
-int qeth_setup_netdev(struct qeth_card *card)
-{
-	struct net_device *dev = card->dev;
-	unsigned int num_tx_queues;
-
-	dev->priv_flags &= ~IFF_TX_SKB_SHARING;
-	dev->hw_features |= NETIF_F_SG;
-	dev->vlan_features |= NETIF_F_SG;
-
-	if (IS_IQD(card)) {
-		dev->features |= NETIF_F_SG;
-		num_tx_queues = QETH_IQD_MIN_TXQ;
-	} else if (IS_VM_NIC(card)) {
-		num_tx_queues = 1;
-	} else {
-		num_tx_queues = dev->real_num_tx_queues;
-	}
-
-	return qeth_set_real_num_tx_queues(card, num_tx_queues);
-}
-EXPORT_SYMBOL_GPL(qeth_setup_netdev);
-
 static int qeth_core_probe_device(struct ccwgroup_device *gdev)
 {
 	struct qeth_card *card;
@@ -6388,6 +6412,7 @@ static int qeth_core_set_offline(struct ccwgroup_device *gdev)
 static void qeth_core_shutdown(struct ccwgroup_device *gdev)
 {
 	struct qeth_card *card = dev_get_drvdata(&gdev->dev);
+
 	qeth_set_allowed_threads(card, 0, 1);
 	if ((gdev->state == CCWGROUP_ONLINE) && card->info.hwtrap)
 		qeth_hw_trap(card, QETH_DIAGS_TRAP_DISARM);
@@ -6926,6 +6951,7 @@ int qeth_set_real_num_tx_queues(struct qeth_card *card, unsigned int count)
 
 	return rc;
 }
+EXPORT_SYMBOL_GPL(qeth_set_real_num_tx_queues);
 
 u16 qeth_iqd_select_queue(struct net_device *dev, struct sk_buff *skb,
 			  u8 cast_type, struct net_device *sb_dev)
diff --git a/drivers/s390/net/qeth_core_sys.c b/drivers/s390/net/qeth_core_sys.c
index 8def82336f53..4441b3393eaf 100644
--- a/drivers/s390/net/qeth_core_sys.c
+++ b/drivers/s390/net/qeth_core_sys.c
@@ -52,7 +52,7 @@ static ssize_t qeth_dev_if_name_show(struct device *dev,
 {
 	struct qeth_card *card = dev_get_drvdata(dev);
 
-	return sprintf(buf, "%s\n", QETH_CARD_IFNAME(card));
+	return sprintf(buf, "%s\n", netdev_name(card->dev));
 }
 
 static DEVICE_ATTR(if_name, 0444, qeth_dev_if_name_show, NULL);
@@ -103,21 +103,21 @@ static ssize_t qeth_dev_portno_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t count)
 {
 	struct qeth_card *card = dev_get_drvdata(dev);
-	char *tmp;
 	unsigned int portno, limit;
 	int rc = 0;
 
+	rc = kstrtouint(buf, 16, &portno);
+	if (rc)
+		return rc;
+	if (portno > QETH_MAX_PORTNO)
+		return -EINVAL;
+
 	mutex_lock(&card->conf_mutex);
 	if (card->state != CARD_STATE_DOWN) {
 		rc = -EPERM;
 		goto out;
 	}
 
-	portno = simple_strtoul(buf, &tmp, 16);
-	if (portno > QETH_MAX_PORTNO) {
-		rc = -EINVAL;
-		goto out;
-	}
 	limit = (card->ssqd.pcnt ? card->ssqd.pcnt - 1 : card->ssqd.pcnt);
 	if (portno > limit) {
 		rc = -EINVAL;
@@ -164,9 +164,11 @@ static ssize_t qeth_dev_prioqing_show(struct device *dev,
 		return sprintf(buf, "%s\n", "by skb-priority");
 	case QETH_PRIO_Q_ING_VLAN:
 		return sprintf(buf, "%s\n", "by VLAN headers");
-	default:
+	case QETH_PRIO_Q_ING_FIXED:
 		return sprintf(buf, "always queue %i\n",
 			       card->qdio.default_out_queue);
+	default:
+		return sprintf(buf, "disabled\n");
 	}
 }
 
@@ -248,19 +250,19 @@ static ssize_t qeth_dev_bufcnt_store(struct device *dev,
 {
 	struct qeth_card *card = dev_get_drvdata(dev);
 	unsigned int cnt;
-	char *tmp;
 	int rc = 0;
 
+	rc = kstrtouint(buf, 10, &cnt);
+	if (rc)
+		return rc;
+
 	mutex_lock(&card->conf_mutex);
 	if (card->state != CARD_STATE_DOWN) {
 		rc = -EPERM;
 		goto out;
 	}
 
-	cnt = simple_strtoul(buf, &tmp, 10);
-	cnt = (cnt < QETH_IN_BUF_COUNT_MIN) ? QETH_IN_BUF_COUNT_MIN :
-		((cnt > QETH_IN_BUF_COUNT_MAX) ? QETH_IN_BUF_COUNT_MAX : cnt);
-
+	cnt = clamp(cnt, QETH_IN_BUF_COUNT_MIN, QETH_IN_BUF_COUNT_MAX);
 	rc = qeth_resize_buffer_pool(card, cnt);
 
 out:
@@ -341,18 +343,15 @@ static ssize_t qeth_dev_layer2_store(struct device *dev,
 {
 	struct qeth_card *card = dev_get_drvdata(dev);
 	struct net_device *ndev;
-	char *tmp;
-	int i, rc = 0;
 	enum qeth_discipline_id newdis;
+	unsigned int input;
+	int rc;
 
-	mutex_lock(&card->discipline_mutex);
-	if (card->state != CARD_STATE_DOWN) {
-		rc = -EPERM;
-		goto out;
-	}
+	rc = kstrtouint(buf, 16, &input);
+	if (rc)
+		return rc;
 
-	i = simple_strtoul(buf, &tmp, 16);
-	switch (i) {
+	switch (input) {
 	case 0:
 		newdis = QETH_DISCIPLINE_LAYER3;
 		break;
@@ -360,7 +359,12 @@ static ssize_t qeth_dev_layer2_store(struct device *dev,
 		newdis = QETH_DISCIPLINE_LAYER2;
 		break;
 	default:
-		rc = -EINVAL;
+		return -EINVAL;
+	}
+
+	mutex_lock(&card->discipline_mutex);
+	if (card->state != CARD_STATE_DOWN) {
+		rc = -EPERM;
 		goto out;
 	}
 
@@ -551,20 +555,21 @@ static DEVICE_ATTR(hw_trap, 0644, qeth_hw_trap_show,
 static ssize_t qeth_dev_blkt_store(struct qeth_card *card,
 		const char *buf, size_t count, int *value, int max_value)
 {
-	char *tmp;
-	int i, rc = 0;
+	unsigned int input;
+	int rc;
+
+	rc = kstrtouint(buf, 10, &input);
+	if (rc)
+		return rc;
+
+	if (input > max_value)
+		return -EINVAL;
 
 	mutex_lock(&card->conf_mutex);
-	if (card->state != CARD_STATE_DOWN) {
+	if (card->state != CARD_STATE_DOWN)
 		rc = -EPERM;
-		goto out;
-	}
-	i = simple_strtoul(buf, &tmp, 10);
-	if (i <= max_value)
-		*value = i;
 	else
-		rc = -EINVAL;
-out:
+		*value = input;
 	mutex_unlock(&card->conf_mutex);
 	return rc ? rc : count;
 }
diff --git a/drivers/s390/net/qeth_ethtool.c b/drivers/s390/net/qeth_ethtool.c
index f870c5322bfe..b5caa723326e 100644
--- a/drivers/s390/net/qeth_ethtool.c
+++ b/drivers/s390/net/qeth_ethtool.c
@@ -211,13 +211,19 @@ static void qeth_get_channels(struct net_device *dev,
 static int qeth_set_channels(struct net_device *dev,
 			     struct ethtool_channels *channels)
 {
+	struct qeth_priv *priv = netdev_priv(dev);
 	struct qeth_card *card = dev->ml_priv;
+	int rc;
 
 	if (channels->rx_count == 0 || channels->tx_count == 0)
 		return -EINVAL;
 	if (channels->tx_count > card->qdio.no_out_queues)
 		return -EINVAL;
 
+	/* Prio-queueing needs all TX queues: */
+	if (qeth_uses_tx_prio_queueing(card))
+		return -EPERM;
+
 	if (IS_IQD(card)) {
 		if (channels->tx_count < QETH_IQD_MIN_TXQ)
 			return -EINVAL;
@@ -228,13 +234,13 @@ static int qeth_set_channels(struct net_device *dev,
 		if (netif_running(dev) &&
 		    channels->tx_count < dev->real_num_tx_queues)
 			return -EPERM;
-	} else {
-		/* OSA still uses the legacy prio-queue mechanism: */
-		if (!IS_VM_NIC(card))
-			return -EOPNOTSUPP;
 	}
 
-	return qeth_set_real_num_tx_queues(card, channels->tx_count);
+	rc = qeth_set_real_num_tx_queues(card, channels->tx_count);
+	if (!rc)
+		priv->tx_wanted_queues = channels->tx_count;
+
+	return rc;
 }
 
 static int qeth_get_ts_info(struct net_device *dev,
diff --git a/drivers/s390/net/qeth_l2.h b/drivers/s390/net/qeth_l2.h
index cc95675c8bc4..296d73d84326 100644
--- a/drivers/s390/net/qeth_l2.h
+++ b/drivers/s390/net/qeth_l2.h
@@ -31,4 +31,11 @@ struct qeth_mac {
 	struct hlist_node hnode;
 };
 
+static inline bool qeth_bridgeport_is_in_use(struct qeth_card *card)
+{
+	return card->options.sbp.role ||
+	       card->options.sbp.reflect_promisc ||
+	       card->options.sbp.hostnotification;
+}
+
 #endif /* __QETH_L2_H__ */
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index 54e02518ce08..28f6dda95736 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -28,17 +28,6 @@
 #include "qeth_core.h"
 #include "qeth_l2.h"
 
-static void qeth_bridgeport_query_support(struct qeth_card *card);
-static void qeth_bridge_state_change(struct qeth_card *card,
-					struct qeth_ipa_cmd *cmd);
-static void qeth_addr_change_event(struct qeth_card *card,
-				   struct qeth_ipa_cmd *cmd);
-static bool qeth_bridgeport_is_in_use(struct qeth_card *card);
-static void qeth_l2_vnicc_set_defaults(struct qeth_card *card);
-static void qeth_l2_vnicc_init(struct qeth_card *card);
-static bool qeth_l2_vnicc_recover_timeout(struct qeth_card *card, u32 vnicc,
-					  u32 *timeout);
-
 static int qeth_l2_setdelmac_makerc(struct qeth_card *card, u16 retcode)
 {
 	int rc;
@@ -194,7 +183,7 @@ static void qeth_l2_fill_header(struct qeth_qdio_out_q *queue,
 	/* VSWITCH relies on the VLAN
 	 * information to be present in
 	 * the QDIO header */
-	if (veth->h_vlan_proto == __constant_htons(ETH_P_8021Q)) {
+	if (veth->h_vlan_proto == htons(ETH_P_8021Q)) {
 		hdr->hdr.l2.flags[2] |= QETH_LAYER2_FLAG_VLAN;
 		hdr->hdr.l2.vlan_id = ntohs(veth->h_vlan_TCI);
 	}
@@ -304,36 +293,6 @@ static void qeth_l2_dev2br_fdb_flush(struct qeth_card *card)
 				 card->dev, &info.info, NULL);
 }
 
-static void qeth_l2_stop_card(struct qeth_card *card)
-{
-	struct qeth_priv *priv = netdev_priv(card->dev);
-
-	QETH_CARD_TEXT(card, 2, "stopcard");
-
-	qeth_set_allowed_threads(card, 0, 1);
-
-	cancel_work_sync(&card->rx_mode_work);
-	qeth_l2_drain_rx_mode_cache(card);
-
-	if (card->state == CARD_STATE_SOFTSETUP) {
-		qeth_clear_ipacmd_list(card);
-		qeth_drain_output_queues(card);
-		card->state = CARD_STATE_DOWN;
-	}
-
-	qeth_qdio_clear_card(card, 0);
-	qeth_clear_working_pool_list(card);
-	qeth_l2_set_pnso_mode(card, QETH_PNSO_NONE);
-	qeth_flush_local_addrs(card);
-	card->info.promisc_mode = 0;
-
-	if (priv->brport_features & BR_LEARNING_SYNC) {
-		rtnl_lock();
-		qeth_l2_dev2br_fdb_flush(card);
-		rtnl_unlock();
-	}
-}
-
 static int qeth_l2_request_initial_mac(struct qeth_card *card)
 {
 	int rc = 0;
@@ -612,52 +571,10 @@ static u16 qeth_l2_select_queue(struct net_device *dev, struct sk_buff *skb,
 		return qeth_iqd_select_queue(dev, skb,
 					     qeth_get_ether_cast_type(skb),
 					     sb_dev);
+	if (qeth_uses_tx_prio_queueing(card))
+		return qeth_get_priority_queue(card, skb);
 
-	return IS_VM_NIC(card) ? netdev_pick_tx(dev, skb, sb_dev) :
-				 qeth_get_priority_queue(card, skb);
-}
-
-static const struct device_type qeth_l2_devtype = {
-	.name = "qeth_layer2",
-	.groups = qeth_l2_attr_groups,
-};
-
-static int qeth_l2_probe_device(struct ccwgroup_device *gdev)
-{
-	struct qeth_card *card = dev_get_drvdata(&gdev->dev);
-	int rc;
-
-	if (IS_OSN(card))
-		dev_notice(&gdev->dev, "OSN support will be dropped in 2021\n");
-
-	qeth_l2_vnicc_set_defaults(card);
-	mutex_init(&card->sbp_lock);
-
-	if (gdev->dev.type == &qeth_generic_devtype) {
-		rc = qeth_l2_create_device_attributes(&gdev->dev);
-		if (rc)
-			return rc;
-	}
-
-	INIT_WORK(&card->rx_mode_work, qeth_l2_rx_mode_work);
-	return 0;
-}
-
-static void qeth_l2_remove_device(struct ccwgroup_device *cgdev)
-{
-	struct qeth_card *card = dev_get_drvdata(&cgdev->dev);
-
-	if (cgdev->dev.type == &qeth_generic_devtype)
-		qeth_l2_remove_device_attributes(&cgdev->dev);
-	qeth_set_allowed_threads(card, 0, 1);
-	wait_event(card->wait_q, qeth_threads_running(card, 0xffffffff) == 0);
-
-	if (cgdev->state == CCWGROUP_ONLINE)
-		qeth_set_offline(card, false);
-
-	cancel_work_sync(&card->close_dev_work);
-	if (card->dev->reg_state == NETREG_REGISTERED)
-		unregister_netdev(card->dev);
+	return netdev_pick_tx(dev, skb, sb_dev);
 }
 
 static void qeth_l2_set_rx_mode(struct net_device *dev)
@@ -960,7 +877,7 @@ static const struct net_device_ops qeth_l2_netdev_ops = {
 	.ndo_set_mac_address    = qeth_l2_set_mac_address,
 	.ndo_vlan_rx_add_vid	= qeth_l2_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid   = qeth_l2_vlan_rx_kill_vid,
-	.ndo_tx_timeout	   	= qeth_tx_timeout,
+	.ndo_tx_timeout		= qeth_tx_timeout,
 	.ndo_fix_features	= qeth_fix_features,
 	.ndo_set_features	= qeth_set_features,
 	.ndo_bridge_getlink	= qeth_l2_bridge_getlink,
@@ -978,18 +895,12 @@ static const struct net_device_ops qeth_osn_netdev_ops = {
 
 static int qeth_l2_setup_netdev(struct qeth_card *card)
 {
-	int rc;
-
 	if (IS_OSN(card)) {
 		card->dev->netdev_ops = &qeth_osn_netdev_ops;
 		card->dev->flags |= IFF_NOARP;
 		goto add_napi;
 	}
 
-	rc = qeth_setup_netdev(card);
-	if (rc)
-		return rc;
-
 	card->dev->needed_headroom = sizeof(struct qeth_hdr);
 	card->dev->netdev_ops = &qeth_l2_netdev_ops;
 	card->dev->priv_flags |= IFF_UNICAST_FLT;
@@ -1140,134 +1051,6 @@ static void qeth_l2_enable_brport_features(struct qeth_card *card)
 	}
 }
 
-static int qeth_l2_set_online(struct qeth_card *card)
-{
-	struct ccwgroup_device *gdev = card->gdev;
-	struct net_device *dev = card->dev;
-	int rc = 0;
-	bool carrier_ok;
-
-	rc = qeth_core_hardsetup_card(card, &carrier_ok);
-	if (rc) {
-		QETH_CARD_TEXT_(card, 2, "2err%04x", rc);
-		rc = -ENODEV;
-		goto out_remove;
-	}
-
-	/* query before bridgeport_notification may be enabled */
-	qeth_l2_detect_dev2br_support(card);
-
-	mutex_lock(&card->sbp_lock);
-	qeth_bridgeport_query_support(card);
-	if (card->options.sbp.supported_funcs) {
-		qeth_l2_setup_bridgeport_attrs(card);
-		dev_info(&card->gdev->dev,
-			 "The device represents a Bridge Capable Port\n");
-	}
-	mutex_unlock(&card->sbp_lock);
-
-	qeth_l2_register_dev_addr(card);
-
-	/* for the rx_bcast characteristic, init VNICC after setmac */
-	qeth_l2_vnicc_init(card);
-
-	qeth_trace_features(card);
-	qeth_l2_trace_features(card);
-
-	qeth_print_status_message(card);
-
-	/* softsetup */
-	QETH_CARD_TEXT(card, 2, "softsetp");
-
-	card->state = CARD_STATE_SOFTSETUP;
-
-	qeth_set_allowed_threads(card, 0xffffffff, 0);
-
-	if (dev->reg_state != NETREG_REGISTERED) {
-		rc = qeth_l2_setup_netdev(card);
-		if (rc)
-			goto out_remove;
-
-		if (carrier_ok)
-			netif_carrier_on(dev);
-	} else {
-		rtnl_lock();
-		if (carrier_ok)
-			netif_carrier_on(dev);
-		else
-			netif_carrier_off(dev);
-
-		netif_device_attach(dev);
-		qeth_enable_hw_features(dev);
-		qeth_l2_enable_brport_features(card);
-
-		if (card->info.open_when_online) {
-			card->info.open_when_online = 0;
-			dev_open(dev, NULL);
-		}
-		rtnl_unlock();
-	}
-	/* let user_space know that device is online */
-	kobject_uevent(&gdev->dev.kobj, KOBJ_CHANGE);
-	return 0;
-
-out_remove:
-	qeth_l2_stop_card(card);
-	qeth_stop_channel(&card->data);
-	qeth_stop_channel(&card->write);
-	qeth_stop_channel(&card->read);
-	qdio_free(CARD_DDEV(card));
-	return rc;
-}
-
-static void qeth_l2_set_offline(struct qeth_card *card)
-{
-	qeth_l2_stop_card(card);
-}
-
-static int __init qeth_l2_init(void)
-{
-	pr_info("register layer 2 discipline\n");
-	return 0;
-}
-
-static void __exit qeth_l2_exit(void)
-{
-	pr_info("unregister layer 2 discipline\n");
-}
-
-/* Returns zero if the command is successfully "consumed" */
-static int qeth_l2_control_event(struct qeth_card *card,
-					struct qeth_ipa_cmd *cmd)
-{
-	switch (cmd->hdr.command) {
-	case IPA_CMD_SETBRIDGEPORT_OSA:
-	case IPA_CMD_SETBRIDGEPORT_IQD:
-		if (cmd->data.sbp.hdr.command_code ==
-				IPA_SBP_BRIDGE_PORT_STATE_CHANGE) {
-			qeth_bridge_state_change(card, cmd);
-			return 0;
-		} else
-			return 1;
-	case IPA_CMD_ADDRESS_CHANGE_NOTIF:
-		qeth_addr_change_event(card, cmd);
-		return 0;
-	default:
-		return 1;
-	}
-}
-
-struct qeth_discipline qeth_l2_discipline = {
-	.devtype = &qeth_l2_devtype,
-	.setup = qeth_l2_probe_device,
-	.remove = qeth_l2_remove_device,
-	.set_online = qeth_l2_set_online,
-	.set_offline = qeth_l2_set_offline,
-	.do_ioctl = NULL,
-	.control_event_handler = qeth_l2_control_event,
-};
-EXPORT_SYMBOL_GPL(qeth_l2_discipline);
-
 #ifdef CONFIG_QETH_OSN
 static void qeth_osn_assist_cb(struct qeth_card *card,
 			       struct qeth_cmd_buffer *iob,
@@ -1342,7 +1125,6 @@ void qeth_osn_deregister(struct net_device *dev)
 	QETH_CARD_TEXT(card, 2, "osndereg");
 	card->osn_info.assist_cb = NULL;
 	card->osn_info.data_cb = NULL;
-	return;
 }
 EXPORT_SYMBOL(qeth_osn_deregister);
 #endif
@@ -1589,7 +1371,7 @@ static void qeth_addr_change_event_worker(struct work_struct *work)
 
 		dev_info(&data->card->gdev->dev,
 			 "Address change notification stopped on %s (%s)\n",
-			 data->card->dev->name,
+			 netdev_name(card->dev),
 			(data->ac_event.lost_event_mask == 0x01)
 			? "Overflow"
 			: (data->ac_event.lost_event_mask == 0x02)
@@ -1987,12 +1769,6 @@ int qeth_bridgeport_an_set(struct qeth_card *card, int enable)
 	return rc;
 }
 
-static bool qeth_bridgeport_is_in_use(struct qeth_card *card)
-{
-	return (card->options.sbp.role || card->options.sbp.reflect_promisc ||
-		card->options.sbp.hostnotification);
-}
-
 /* VNIC Characteristics support */
 
 /* handle VNICC IPA command return codes; convert to error codes */
@@ -2138,6 +1914,19 @@ static int qeth_l2_vnicc_getset_timeout(struct qeth_card *card, u32 vnicc,
 	return qeth_send_ipa_cmd(card, iob, qeth_l2_vnicc_request_cb, timeout);
 }
 
+/* recover user timeout setting */
+static bool qeth_l2_vnicc_recover_timeout(struct qeth_card *card, u32 vnicc,
+					  u32 *timeout)
+{
+	if (card->options.vnicc.sup_chars & vnicc &&
+	    card->options.vnicc.getset_timeout_sup & vnicc &&
+	    !qeth_l2_vnicc_getset_timeout(card, vnicc, IPA_VNICC_SET_TIMEOUT,
+					  timeout))
+		return false;
+	*timeout = QETH_VNICC_DEFAULT_TIMEOUT;
+	return true;
+}
+
 /* set current VNICC flag state; called from sysfs store function */
 int qeth_l2_vnicc_set_state(struct qeth_card *card, u32 vnicc, bool state)
 {
@@ -2308,19 +2097,6 @@ bool qeth_bridgeport_allowed(struct qeth_card *card)
 		!(priv->brport_features & BR_LEARNING_SYNC));
 }
 
-/* recover user timeout setting */
-static bool qeth_l2_vnicc_recover_timeout(struct qeth_card *card, u32 vnicc,
-					  u32 *timeout)
-{
-	if (card->options.vnicc.sup_chars & vnicc &&
-	    card->options.vnicc.getset_timeout_sup & vnicc &&
-	    !qeth_l2_vnicc_getset_timeout(card, vnicc, IPA_VNICC_SET_TIMEOUT,
-					  timeout))
-		return false;
-	*timeout = QETH_VNICC_DEFAULT_TIMEOUT;
-	return true;
-}
-
 /* recover user characteristic setting */
 static bool qeth_l2_vnicc_recover_char(struct qeth_card *card, u32 vnicc,
 				       bool enable)
@@ -2409,6 +2185,182 @@ static void qeth_l2_vnicc_set_defaults(struct qeth_card *card)
 	card->options.vnicc.wanted_chars = QETH_VNICC_DEFAULT;
 }
 
+static const struct device_type qeth_l2_devtype = {
+	.name = "qeth_layer2",
+	.groups = qeth_l2_attr_groups,
+};
+
+static int qeth_l2_probe_device(struct ccwgroup_device *gdev)
+{
+	struct qeth_card *card = dev_get_drvdata(&gdev->dev);
+	int rc;
+
+	if (IS_OSN(card))
+		dev_notice(&gdev->dev, "OSN support will be dropped in 2021\n");
+
+	qeth_l2_vnicc_set_defaults(card);
+	mutex_init(&card->sbp_lock);
+
+	if (gdev->dev.type == &qeth_generic_devtype) {
+		rc = qeth_l2_create_device_attributes(&gdev->dev);
+		if (rc)
+			return rc;
+	}
+
+	INIT_WORK(&card->rx_mode_work, qeth_l2_rx_mode_work);
+	return 0;
+}
+
+static void qeth_l2_remove_device(struct ccwgroup_device *gdev)
+{
+	struct qeth_card *card = dev_get_drvdata(&gdev->dev);
+
+	if (gdev->dev.type == &qeth_generic_devtype)
+		qeth_l2_remove_device_attributes(&gdev->dev);
+	qeth_set_allowed_threads(card, 0, 1);
+	wait_event(card->wait_q, qeth_threads_running(card, 0xffffffff) == 0);
+
+	if (gdev->state == CCWGROUP_ONLINE)
+		qeth_set_offline(card, false);
+
+	cancel_work_sync(&card->close_dev_work);
+	if (card->dev->reg_state == NETREG_REGISTERED)
+		unregister_netdev(card->dev);
+}
+
+static int qeth_l2_set_online(struct qeth_card *card, bool carrier_ok)
+{
+	struct net_device *dev = card->dev;
+	int rc = 0;
+
+	/* query before bridgeport_notification may be enabled */
+	qeth_l2_detect_dev2br_support(card);
+
+	mutex_lock(&card->sbp_lock);
+	qeth_bridgeport_query_support(card);
+	if (card->options.sbp.supported_funcs) {
+		qeth_l2_setup_bridgeport_attrs(card);
+		dev_info(&card->gdev->dev,
+			 "The device represents a Bridge Capable Port\n");
+	}
+	mutex_unlock(&card->sbp_lock);
+
+	qeth_l2_register_dev_addr(card);
+
+	/* for the rx_bcast characteristic, init VNICC after setmac */
+	qeth_l2_vnicc_init(card);
+
+	qeth_l2_trace_features(card);
+
+	/* softsetup */
+	QETH_CARD_TEXT(card, 2, "softsetp");
+
+	card->state = CARD_STATE_SOFTSETUP;
+
+	qeth_set_allowed_threads(card, 0xffffffff, 0);
+
+	if (dev->reg_state != NETREG_REGISTERED) {
+		rc = qeth_l2_setup_netdev(card);
+		if (rc)
+			goto err_setup;
+
+		if (carrier_ok)
+			netif_carrier_on(dev);
+	} else {
+		rtnl_lock();
+		rc = qeth_set_real_num_tx_queues(card,
+						 qeth_tx_actual_queues(card));
+		if (rc) {
+			rtnl_unlock();
+			goto err_set_queues;
+		}
+
+		if (carrier_ok)
+			netif_carrier_on(dev);
+		else
+			netif_carrier_off(dev);
+
+		netif_device_attach(dev);
+		qeth_enable_hw_features(dev);
+		qeth_l2_enable_brport_features(card);
+
+		if (card->info.open_when_online) {
+			card->info.open_when_online = 0;
+			dev_open(dev, NULL);
+		}
+		rtnl_unlock();
+	}
+	return 0;
+
+err_set_queues:
+err_setup:
+	qeth_set_allowed_threads(card, 0, 1);
+	card->state = CARD_STATE_DOWN;
+	return rc;
+}
+
+static void qeth_l2_set_offline(struct qeth_card *card)
+{
+	struct qeth_priv *priv = netdev_priv(card->dev);
+
+	qeth_set_allowed_threads(card, 0, 1);
+	qeth_l2_drain_rx_mode_cache(card);
+
+	if (card->state == CARD_STATE_SOFTSETUP)
+		card->state = CARD_STATE_DOWN;
+
+	qeth_l2_set_pnso_mode(card, QETH_PNSO_NONE);
+	if (priv->brport_features & BR_LEARNING_SYNC) {
+		rtnl_lock();
+		qeth_l2_dev2br_fdb_flush(card);
+		rtnl_unlock();
+	}
+}
+
+/* Returns zero if the command is successfully "consumed" */
+static int qeth_l2_control_event(struct qeth_card *card,
+				 struct qeth_ipa_cmd *cmd)
+{
+	switch (cmd->hdr.command) {
+	case IPA_CMD_SETBRIDGEPORT_OSA:
+	case IPA_CMD_SETBRIDGEPORT_IQD:
+		if (cmd->data.sbp.hdr.command_code ==
+		    IPA_SBP_BRIDGE_PORT_STATE_CHANGE) {
+			qeth_bridge_state_change(card, cmd);
+			return 0;
+		}
+
+		return 1;
+	case IPA_CMD_ADDRESS_CHANGE_NOTIF:
+		qeth_addr_change_event(card, cmd);
+		return 0;
+	default:
+		return 1;
+	}
+}
+
+const struct qeth_discipline qeth_l2_discipline = {
+	.devtype = &qeth_l2_devtype,
+	.setup = qeth_l2_probe_device,
+	.remove = qeth_l2_remove_device,
+	.set_online = qeth_l2_set_online,
+	.set_offline = qeth_l2_set_offline,
+	.do_ioctl = NULL,
+	.control_event_handler = qeth_l2_control_event,
+};
+EXPORT_SYMBOL_GPL(qeth_l2_discipline);
+
+static int __init qeth_l2_init(void)
+{
+	pr_info("register layer 2 discipline\n");
+	return 0;
+}
+
+static void __exit qeth_l2_exit(void)
+{
+	pr_info("unregister layer 2 discipline\n");
+}
+
 module_init(qeth_l2_init);
 module_exit(qeth_l2_exit);
 MODULE_AUTHOR("Frank Blaschka <frank.blaschka@de.ibm.com>");
diff --git a/drivers/s390/net/qeth_l3.h b/drivers/s390/net/qeth_l3.h
index 6ccfe2121095..acd130cfbab3 100644
--- a/drivers/s390/net/qeth_l3.h
+++ b/drivers/s390/net/qeth_l3.h
@@ -96,7 +96,7 @@ struct qeth_ipato_entry {
 	struct list_head entry;
 	enum qeth_prot_versions proto;
 	char addr[16];
-	int mask_bits;
+	unsigned int mask_bits;
 };
 
 extern const struct attribute_group *qeth_l3_attr_groups[];
@@ -110,7 +110,7 @@ int qeth_l3_setrouting_v6(struct qeth_card *);
 int qeth_l3_add_ipato_entry(struct qeth_card *, struct qeth_ipato_entry *);
 int qeth_l3_del_ipato_entry(struct qeth_card *card,
 			    enum qeth_prot_versions proto, u8 *addr,
-			    int mask_bits);
+			    unsigned int mask_bits);
 void qeth_l3_update_ipato(struct qeth_card *card);
 int qeth_l3_modify_hsuid(struct qeth_card *card, bool add);
 int qeth_l3_modify_rxip_vipa(struct qeth_card *card, bool add, const u8 *ip,
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index 767c5bb7c24c..b1c1d2510d55 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -97,7 +97,7 @@ static bool qeth_l3_is_addr_covered_by_ipato(struct qeth_card *card,
 		return false;
 
 	qeth_l3_convert_addr_to_bits((u8 *) &addr->u, addr_bits,
-				  (addr->proto == QETH_PROT_IPV4)? 4:16);
+				     (addr->proto == QETH_PROT_IPV4) ? 4 : 16);
 	list_for_each_entry(ipatoe, &card->ipato.entries, entry) {
 		if (addr->proto != ipatoe->proto)
 			continue;
@@ -105,11 +105,9 @@ static bool qeth_l3_is_addr_covered_by_ipato(struct qeth_card *card,
 					  (ipatoe->proto == QETH_PROT_IPV4) ?
 					  4 : 16);
 		if (addr->proto == QETH_PROT_IPV4)
-			rc = !memcmp(addr_bits, ipatoe_bits,
-				     min(32, ipatoe->mask_bits));
+			rc = !memcmp(addr_bits, ipatoe_bits, ipatoe->mask_bits);
 		else
-			rc = !memcmp(addr_bits, ipatoe_bits,
-				     min(128, ipatoe->mask_bits));
+			rc = !memcmp(addr_bits, ipatoe_bits, ipatoe->mask_bits);
 		if (rc)
 			break;
 	}
@@ -536,14 +534,13 @@ int qeth_l3_add_ipato_entry(struct qeth_card *card,
 
 	QETH_CARD_TEXT(card, 2, "addipato");
 
-	mutex_lock(&card->conf_mutex);
 	mutex_lock(&card->ip_lock);
 
 	list_for_each_entry(ipatoe, &card->ipato.entries, entry) {
 		if (ipatoe->proto != new->proto)
 			continue;
 		if (!memcmp(ipatoe->addr, new->addr,
-			    (ipatoe->proto == QETH_PROT_IPV4)? 4:16) &&
+			    (ipatoe->proto == QETH_PROT_IPV4) ? 4 : 16) &&
 		    (ipatoe->mask_bits == new->mask_bits)) {
 			rc = -EEXIST;
 			break;
@@ -556,28 +553,26 @@ int qeth_l3_add_ipato_entry(struct qeth_card *card,
 	}
 
 	mutex_unlock(&card->ip_lock);
-	mutex_unlock(&card->conf_mutex);
 
 	return rc;
 }
 
 int qeth_l3_del_ipato_entry(struct qeth_card *card,
 			    enum qeth_prot_versions proto, u8 *addr,
-			    int mask_bits)
+			    unsigned int mask_bits)
 {
 	struct qeth_ipato_entry *ipatoe, *tmp;
 	int rc = -ENOENT;
 
 	QETH_CARD_TEXT(card, 2, "delipato");
 
-	mutex_lock(&card->conf_mutex);
 	mutex_lock(&card->ip_lock);
 
 	list_for_each_entry_safe(ipatoe, tmp, &card->ipato.entries, entry) {
 		if (ipatoe->proto != proto)
 			continue;
 		if (!memcmp(ipatoe->addr, addr,
-			    (proto == QETH_PROT_IPV4)? 4:16) &&
+			    (proto == QETH_PROT_IPV4) ? 4 : 16) &&
 		    (ipatoe->mask_bits == mask_bits)) {
 			list_del(&ipatoe->entry);
 			qeth_l3_update_ipato(card);
@@ -587,7 +582,6 @@ int qeth_l3_del_ipato_entry(struct qeth_card *card,
 	}
 
 	mutex_unlock(&card->ip_lock);
-	mutex_unlock(&card->conf_mutex);
 
 	return rc;
 }
@@ -597,7 +591,6 @@ int qeth_l3_modify_rxip_vipa(struct qeth_card *card, bool add, const u8 *ip,
 			     enum qeth_prot_versions proto)
 {
 	struct qeth_ipaddr addr;
-	int rc;
 
 	qeth_l3_init_ipaddr(&addr, type, proto);
 	if (proto == QETH_PROT_IPV4)
@@ -605,11 +598,7 @@ int qeth_l3_modify_rxip_vipa(struct qeth_card *card, bool add, const u8 *ip,
 	else
 		memcpy(&addr.u.a6.addr, ip, 16);
 
-	mutex_lock(&card->conf_mutex);
-	rc = qeth_l3_modify_ip(card, &addr, add);
-	mutex_unlock(&card->conf_mutex);
-
-	return rc;
+	return qeth_l3_modify_ip(card, &addr, add);
 }
 
 int qeth_l3_modify_hsuid(struct qeth_card *card, bool add)
@@ -717,16 +706,16 @@ static int qeth_l3_start_ipa_arp_processing(struct qeth_card *card)
 
 	if (!qeth_is_supported(card, IPA_ARP_PROCESSING)) {
 		dev_info(&card->gdev->dev,
-			"ARP processing not supported on %s!\n",
-			QETH_CARD_IFNAME(card));
+			 "ARP processing not supported on %s!\n",
+			 netdev_name(card->dev));
 		return 0;
 	}
 	rc = qeth_send_simple_setassparms(card, IPA_ARP_PROCESSING,
 					  IPA_CMD_ASS_START, NULL);
 	if (rc) {
 		dev_warn(&card->gdev->dev,
-			"Starting ARP processing support for %s failed\n",
-			QETH_CARD_IFNAME(card));
+			 "Starting ARP processing support for %s failed\n",
+			 netdev_name(card->dev));
 	}
 	return rc;
 }
@@ -739,8 +728,8 @@ static int qeth_l3_start_ipa_source_mac(struct qeth_card *card)
 
 	if (!qeth_is_supported(card, IPA_SOURCE_MAC)) {
 		dev_info(&card->gdev->dev,
-			"Inbound source MAC-address not supported on %s\n",
-			QETH_CARD_IFNAME(card));
+			 "Inbound source MAC-address not supported on %s\n",
+			 netdev_name(card->dev));
 		return -EOPNOTSUPP;
 	}
 
@@ -748,8 +737,8 @@ static int qeth_l3_start_ipa_source_mac(struct qeth_card *card)
 					  IPA_CMD_ASS_START, NULL);
 	if (rc)
 		dev_warn(&card->gdev->dev,
-			"Starting source MAC-address support for %s failed\n",
-			QETH_CARD_IFNAME(card));
+			 "Starting source MAC-address support for %s failed\n",
+			 netdev_name(card->dev));
 	return rc;
 }
 
@@ -761,7 +750,7 @@ static int qeth_l3_start_ipa_vlan(struct qeth_card *card)
 
 	if (!qeth_is_supported(card, IPA_FULL_VLAN)) {
 		dev_info(&card->gdev->dev,
-			"VLAN not supported on %s\n", QETH_CARD_IFNAME(card));
+			 "VLAN not supported on %s\n", netdev_name(card->dev));
 		return -EOPNOTSUPP;
 	}
 
@@ -769,8 +758,8 @@ static int qeth_l3_start_ipa_vlan(struct qeth_card *card)
 					  IPA_CMD_ASS_START, NULL);
 	if (rc) {
 		dev_warn(&card->gdev->dev,
-			"Starting VLAN support for %s failed\n",
-			QETH_CARD_IFNAME(card));
+			 "Starting VLAN support for %s failed\n",
+			 netdev_name(card->dev));
 	} else {
 		dev_info(&card->gdev->dev, "VLAN enabled\n");
 	}
@@ -785,8 +774,8 @@ static int qeth_l3_start_ipa_multicast(struct qeth_card *card)
 
 	if (!qeth_is_supported(card, IPA_MULTICASTING)) {
 		dev_info(&card->gdev->dev,
-			"Multicast not supported on %s\n",
-			QETH_CARD_IFNAME(card));
+			 "Multicast not supported on %s\n",
+			 netdev_name(card->dev));
 		return -EOPNOTSUPP;
 	}
 
@@ -794,8 +783,8 @@ static int qeth_l3_start_ipa_multicast(struct qeth_card *card)
 					  IPA_CMD_ASS_START, NULL);
 	if (rc) {
 		dev_warn(&card->gdev->dev,
-			"Starting multicast support for %s failed\n",
-			QETH_CARD_IFNAME(card));
+			 "Starting multicast support for %s failed\n",
+			 netdev_name(card->dev));
 	} else {
 		dev_info(&card->gdev->dev, "Multicast enabled\n");
 		card->dev->flags |= IFF_MULTICAST;
@@ -818,7 +807,7 @@ static int qeth_l3_softsetup_ipv6(struct qeth_card *card)
 	if (rc) {
 		dev_err(&card->gdev->dev,
 			"Activating IPv6 support for %s failed\n",
-			QETH_CARD_IFNAME(card));
+			netdev_name(card->dev));
 		return rc;
 	}
 	rc = qeth_send_simple_setassparms_v6(card, IPA_IPV6, IPA_CMD_ASS_START,
@@ -826,15 +815,15 @@ static int qeth_l3_softsetup_ipv6(struct qeth_card *card)
 	if (rc) {
 		dev_err(&card->gdev->dev,
 			"Activating IPv6 support for %s failed\n",
-			 QETH_CARD_IFNAME(card));
+			 netdev_name(card->dev));
 		return rc;
 	}
 	rc = qeth_send_simple_setassparms_v6(card, IPA_PASSTHRU,
 					     IPA_CMD_ASS_START, NULL);
 	if (rc) {
 		dev_warn(&card->gdev->dev,
-			"Enabling the passthrough mode for %s failed\n",
-			QETH_CARD_IFNAME(card));
+			 "Enabling the passthrough mode for %s failed\n",
+			 netdev_name(card->dev));
 		return rc;
 	}
 out:
@@ -848,7 +837,7 @@ static int qeth_l3_start_ipa_ipv6(struct qeth_card *card)
 
 	if (!qeth_is_supported(card, IPA_IPV6)) {
 		dev_info(&card->gdev->dev,
-			"IPv6 not supported on %s\n", QETH_CARD_IFNAME(card));
+			 "IPv6 not supported on %s\n", netdev_name(card->dev));
 		return 0;
 	}
 	return qeth_l3_softsetup_ipv6(card);
@@ -863,16 +852,17 @@ static int qeth_l3_start_ipa_broadcast(struct qeth_card *card)
 	card->info.broadcast_capable = 0;
 	if (!qeth_is_supported(card, IPA_FILTERING)) {
 		dev_info(&card->gdev->dev,
-			"Broadcast not supported on %s\n",
-			QETH_CARD_IFNAME(card));
+			 "Broadcast not supported on %s\n",
+			 netdev_name(card->dev));
 		rc = -EOPNOTSUPP;
 		goto out;
 	}
 	rc = qeth_send_simple_setassparms(card, IPA_FILTERING,
 					  IPA_CMD_ASS_START, NULL);
 	if (rc) {
-		dev_warn(&card->gdev->dev, "Enabling broadcast filtering for "
-			"%s failed\n", QETH_CARD_IFNAME(card));
+		dev_warn(&card->gdev->dev,
+			 "Enabling broadcast filtering for %s failed\n",
+			 netdev_name(card->dev));
 		goto out;
 	}
 
@@ -880,8 +870,8 @@ static int qeth_l3_start_ipa_broadcast(struct qeth_card *card)
 					  IPA_CMD_ASS_CONFIGURE, &filter_data);
 	if (rc) {
 		dev_warn(&card->gdev->dev,
-			"Setting up broadcast filtering for %s failed\n",
-			QETH_CARD_IFNAME(card));
+			 "Setting up broadcast filtering for %s failed\n",
+			 netdev_name(card->dev));
 		goto out;
 	}
 	card->info.broadcast_capable = QETH_BROADCAST_WITH_ECHO;
@@ -889,8 +879,9 @@ static int qeth_l3_start_ipa_broadcast(struct qeth_card *card)
 	rc = qeth_send_simple_setassparms(card, IPA_FILTERING,
 					  IPA_CMD_ASS_ENABLE, &filter_data);
 	if (rc) {
-		dev_warn(&card->gdev->dev, "Setting up broadcast echo "
-			"filtering for %s failed\n", QETH_CARD_IFNAME(card));
+		dev_warn(&card->gdev->dev,
+			 "Setting up broadcast echo filtering for %s failed\n",
+			 netdev_name(card->dev));
 		goto out;
 	}
 	card->info.broadcast_capable = QETH_BROADCAST_WITHOUT_ECHO;
@@ -1153,33 +1144,6 @@ static int qeth_l3_vlan_rx_kill_vid(struct net_device *dev,
 	return 0;
 }
 
-static void qeth_l3_stop_card(struct qeth_card *card)
-{
-	QETH_CARD_TEXT(card, 2, "stopcard");
-
-	qeth_set_allowed_threads(card, 0, 1);
-
-	cancel_work_sync(&card->rx_mode_work);
-	qeth_l3_drain_rx_mode_cache(card);
-
-	if (card->options.sniffer &&
-	    (card->info.promisc_mode == SET_PROMISC_MODE_ON))
-		qeth_diags_trace(card, QETH_DIAGS_CMD_TRACE_DISABLE);
-
-	if (card->state == CARD_STATE_SOFTSETUP) {
-		qeth_l3_clear_ip_htable(card, 1);
-		qeth_clear_ipacmd_list(card);
-		qeth_drain_output_queues(card);
-		card->state = CARD_STATE_DOWN;
-	}
-
-	qeth_qdio_clear_card(card, 0);
-	qeth_clear_working_pool_list(card);
-	flush_workqueue(card->event_wq);
-	qeth_flush_local_addrs(card);
-	card->info.promisc_mode = 0;
-}
-
 static void qeth_l3_set_promisc_mode(struct qeth_card *card)
 {
 	bool enable = card->dev->flags & IFF_PROMISC;
@@ -1235,7 +1199,6 @@ static void qeth_l3_rx_mode_work(struct work_struct *work)
 					kfree(addr);
 					break;
 				}
-				addr->ref_counter = 1;
 				fallthrough;
 			default:
 				/* for next call to set_rx_mode(): */
@@ -1870,8 +1833,10 @@ static u16 qeth_l3_osa_select_queue(struct net_device *dev, struct sk_buff *skb,
 {
 	struct qeth_card *card = dev->ml_priv;
 
-	return IS_VM_NIC(card) ? netdev_pick_tx(dev, skb, sb_dev) :
-				 qeth_get_priority_queue(card, skb);
+	if (qeth_uses_tx_prio_queueing(card))
+		return qeth_get_priority_queue(card, skb);
+
+	return netdev_pick_tx(dev, skb, sb_dev);
 }
 
 static const struct net_device_ops qeth_l3_netdev_ops = {
@@ -1914,10 +1879,6 @@ static int qeth_l3_setup_netdev(struct qeth_card *card)
 	unsigned int headroom;
 	int rc;
 
-	rc = qeth_setup_netdev(card);
-	if (rc)
-		return rc;
-
 	if (IS_OSD(card) || IS_OSX(card)) {
 		card->dev->netdev_ops = &qeth_l3_osa_netdev_ops;
 
@@ -2025,21 +1986,10 @@ static void qeth_l3_remove_device(struct ccwgroup_device *cgdev)
 	qeth_l3_clear_ipato_list(card);
 }
 
-static int qeth_l3_set_online(struct qeth_card *card)
+static int qeth_l3_set_online(struct qeth_card *card, bool carrier_ok)
 {
-	struct ccwgroup_device *gdev = card->gdev;
 	struct net_device *dev = card->dev;
 	int rc = 0;
-	bool carrier_ok;
-
-	rc = qeth_core_hardsetup_card(card, &carrier_ok);
-	if (rc) {
-		QETH_CARD_TEXT_(card, 2, "2err%04x", rc);
-		rc = -ENODEV;
-		goto out_remove;
-	}
-
-	qeth_print_status_message(card);
 
 	/* softsetup */
 	QETH_CARD_TEXT(card, 2, "softsetp");
@@ -2066,12 +2016,19 @@ static int qeth_l3_set_online(struct qeth_card *card)
 	if (dev->reg_state != NETREG_REGISTERED) {
 		rc = qeth_l3_setup_netdev(card);
 		if (rc)
-			goto out_remove;
+			goto err_setup;
 
 		if (carrier_ok)
 			netif_carrier_on(dev);
 	} else {
 		rtnl_lock();
+		rc = qeth_set_real_num_tx_queues(card,
+						 qeth_tx_actual_queues(card));
+		if (rc) {
+			rtnl_unlock();
+			goto err_set_queues;
+		}
+
 		if (carrier_ok)
 			netif_carrier_on(dev);
 		else
@@ -2086,22 +2043,29 @@ static int qeth_l3_set_online(struct qeth_card *card)
 		}
 		rtnl_unlock();
 	}
-	qeth_trace_features(card);
-	/* let user_space know that device is online */
-	kobject_uevent(&gdev->dev.kobj, KOBJ_CHANGE);
 	return 0;
-out_remove:
-	qeth_l3_stop_card(card);
-	qeth_stop_channel(&card->data);
-	qeth_stop_channel(&card->write);
-	qeth_stop_channel(&card->read);
-	qdio_free(CARD_DDEV(card));
+
+err_set_queues:
+err_setup:
+	qeth_set_allowed_threads(card, 0, 1);
+	card->state = CARD_STATE_DOWN;
+	qeth_l3_clear_ip_htable(card, 1);
 	return rc;
 }
 
 static void qeth_l3_set_offline(struct qeth_card *card)
 {
-	qeth_l3_stop_card(card);
+	qeth_set_allowed_threads(card, 0, 1);
+	qeth_l3_drain_rx_mode_cache(card);
+
+	if (card->options.sniffer &&
+	    (card->info.promisc_mode == SET_PROMISC_MODE_ON))
+		qeth_diags_trace(card, QETH_DIAGS_CMD_TRACE_DISABLE);
+
+	if (card->state == CARD_STATE_SOFTSETUP) {
+		card->state = CARD_STATE_DOWN;
+		qeth_l3_clear_ip_htable(card, 1);
+	}
 }
 
 /* Returns zero if the command is successfully "consumed" */
@@ -2111,7 +2075,7 @@ static int qeth_l3_control_event(struct qeth_card *card,
 	return 1;
 }
 
-struct qeth_discipline qeth_l3_discipline = {
+const struct qeth_discipline qeth_l3_discipline = {
 	.devtype = &qeth_l3_devtype,
 	.setup = qeth_l3_probe_device,
 	.remove = qeth_l3_remove_device,
@@ -2175,7 +2139,6 @@ static struct qeth_card *qeth_l3_get_card_from_dev(struct net_device *dev)
 static int qeth_l3_ip_event(struct notifier_block *this,
 			    unsigned long event, void *ptr)
 {
-
 	struct in_ifaddr *ifa = (struct in_ifaddr *)ptr;
 	struct net_device *dev = ifa->ifa_dev->dev;
 	struct qeth_ipaddr addr;
diff --git a/drivers/s390/net/qeth_l3_sys.c b/drivers/s390/net/qeth_l3_sys.c
index dd0b39082534..997fbb7006a7 100644
--- a/drivers/s390/net/qeth_l3_sys.c
+++ b/drivers/s390/net/qeth_l3_sys.c
@@ -285,7 +285,7 @@ static ssize_t qeth_l3_dev_ipato_enable_show(struct device *dev,
 {
 	struct qeth_card *card = dev_get_drvdata(dev);
 
-	return sprintf(buf, "%i\n", card->ipato.enabled? 1:0);
+	return sprintf(buf, "%u\n", card->ipato.enabled ? 1 : 0);
 }
 
 static ssize_t qeth_l3_dev_ipato_enable_store(struct device *dev,
@@ -301,19 +301,21 @@ static ssize_t qeth_l3_dev_ipato_enable_store(struct device *dev,
 		goto out;
 	}
 
+	mutex_lock(&card->ip_lock);
 	if (sysfs_streq(buf, "toggle")) {
 		enable = !card->ipato.enabled;
 	} else if (kstrtobool(buf, &enable)) {
 		rc = -EINVAL;
-		goto out;
+		goto unlock_ip;
 	}
 
 	if (card->ipato.enabled != enable) {
 		card->ipato.enabled = enable;
-		mutex_lock(&card->ip_lock);
 		qeth_l3_update_ipato(card);
-		mutex_unlock(&card->ip_lock);
 	}
+
+unlock_ip:
+	mutex_unlock(&card->ip_lock);
 out:
 	mutex_unlock(&card->conf_mutex);
 	return rc ? rc : count;
@@ -328,7 +330,7 @@ static ssize_t qeth_l3_dev_ipato_invert4_show(struct device *dev,
 {
 	struct qeth_card *card = dev_get_drvdata(dev);
 
-	return sprintf(buf, "%i\n", card->ipato.invert4? 1:0);
+	return sprintf(buf, "%u\n", card->ipato.invert4 ? 1 : 0);
 }
 
 static ssize_t qeth_l3_dev_ipato_invert4_store(struct device *dev,
@@ -339,7 +341,7 @@ static ssize_t qeth_l3_dev_ipato_invert4_store(struct device *dev,
 	bool invert;
 	int rc = 0;
 
-	mutex_lock(&card->conf_mutex);
+	mutex_lock(&card->ip_lock);
 	if (sysfs_streq(buf, "toggle")) {
 		invert = !card->ipato.invert4;
 	} else if (kstrtobool(buf, &invert)) {
@@ -349,12 +351,11 @@ static ssize_t qeth_l3_dev_ipato_invert4_store(struct device *dev,
 
 	if (card->ipato.invert4 != invert) {
 		card->ipato.invert4 = invert;
-		mutex_lock(&card->ip_lock);
 		qeth_l3_update_ipato(card);
-		mutex_unlock(&card->ip_lock);
 	}
+
 out:
-	mutex_unlock(&card->conf_mutex);
+	mutex_unlock(&card->ip_lock);
 	return rc ? rc : count;
 }
 
@@ -406,29 +407,29 @@ static ssize_t qeth_l3_dev_ipato_add4_show(struct device *dev,
 }
 
 static int qeth_l3_parse_ipatoe(const char *buf, enum qeth_prot_versions proto,
-		  u8 *addr, int *mask_bits)
+				u8 *addr, unsigned int *mask_bits)
 {
-	const char *start, *end;
-	char *tmp;
-	char buffer[40] = {0, };
+	char *sep;
+	int rc;
 
-	start = buf;
-	/* get address string */
-	end = strchr(start, '/');
-	if (!end || (end - start >= 40)) {
+	/* Expected input pattern: %addr/%mask */
+	sep = strnchr(buf, 40, '/');
+	if (!sep)
 		return -EINVAL;
-	}
-	strncpy(buffer, start, end - start);
-	if (qeth_l3_string_to_ipaddr(buffer, proto, addr)) {
-		return -EINVAL;
-	}
-	start = end + 1;
-	*mask_bits = simple_strtoul(start, &tmp, 10);
-	if (!strlen(start) ||
-	    (tmp == start) ||
-	    (*mask_bits > ((proto == QETH_PROT_IPV4) ? 32 : 128))) {
+
+	/* Terminate the %addr sub-string, and parse it: */
+	*sep = '\0';
+	rc = qeth_l3_string_to_ipaddr(buf, proto, addr);
+	if (rc)
+		return rc;
+
+	rc = kstrtouint(sep + 1, 10, mask_bits);
+	if (rc)
+		return rc;
+
+	if (*mask_bits > ((proto == QETH_PROT_IPV4) ? 32 : 128))
 		return -EINVAL;
-	}
+
 	return 0;
 }
 
@@ -436,8 +437,8 @@ static ssize_t qeth_l3_dev_ipato_add_store(const char *buf, size_t count,
 			 struct qeth_card *card, enum qeth_prot_versions proto)
 {
 	struct qeth_ipato_entry *ipatoe;
+	unsigned int mask_bits;
 	u8 addr[16];
-	int mask_bits;
 	int rc = 0;
 
 	rc = qeth_l3_parse_ipatoe(buf, proto, addr, &mask_bits);
@@ -449,7 +450,7 @@ static ssize_t qeth_l3_dev_ipato_add_store(const char *buf, size_t count,
 		return -ENOMEM;
 
 	ipatoe->proto = proto;
-	memcpy(ipatoe->addr, addr, (proto == QETH_PROT_IPV4)? 4:16);
+	memcpy(ipatoe->addr, addr, (proto == QETH_PROT_IPV4) ? 4 : 16);
 	ipatoe->mask_bits = mask_bits;
 
 	rc = qeth_l3_add_ipato_entry(card, ipatoe);
@@ -474,8 +475,8 @@ static QETH_DEVICE_ATTR(ipato_add4, add4, 0644,
 static ssize_t qeth_l3_dev_ipato_del_store(const char *buf, size_t count,
 			 struct qeth_card *card, enum qeth_prot_versions proto)
 {
+	unsigned int mask_bits;
 	u8 addr[16];
-	int mask_bits;
 	int rc = 0;
 
 	rc = qeth_l3_parse_ipatoe(buf, proto, addr, &mask_bits);
@@ -500,7 +501,7 @@ static ssize_t qeth_l3_dev_ipato_invert6_show(struct device *dev,
 {
 	struct qeth_card *card = dev_get_drvdata(dev);
 
-	return sprintf(buf, "%i\n", card->ipato.invert6? 1:0);
+	return sprintf(buf, "%u\n", card->ipato.invert6 ? 1 : 0);
 }
 
 static ssize_t qeth_l3_dev_ipato_invert6_store(struct device *dev,
@@ -510,7 +511,7 @@ static ssize_t qeth_l3_dev_ipato_invert6_store(struct device *dev,
 	bool invert;
 	int rc = 0;
 
-	mutex_lock(&card->conf_mutex);
+	mutex_lock(&card->ip_lock);
 	if (sysfs_streq(buf, "toggle")) {
 		invert = !card->ipato.invert6;
 	} else if (kstrtobool(buf, &invert)) {
@@ -520,12 +521,11 @@ static ssize_t qeth_l3_dev_ipato_invert6_store(struct device *dev,
 
 	if (card->ipato.invert6 != invert) {
 		card->ipato.invert6 = invert;
-		mutex_lock(&card->ip_lock);
 		qeth_l3_update_ipato(card);
-		mutex_unlock(&card->ip_lock);
 	}
+
 out:
-	mutex_unlock(&card->conf_mutex);
+	mutex_unlock(&card->ip_lock);
 	return rc ? rc : count;
 }
 
diff --git a/drivers/scsi/libfc/fc_disc.c b/drivers/scsi/libfc/fc_disc.c
index d8cbc9c0e766..e67abb184a8a 100644
--- a/drivers/scsi/libfc/fc_disc.c
+++ b/drivers/scsi/libfc/fc_disc.c
@@ -634,8 +634,6 @@ free_fp:
 	fc_frame_free(fp);
 out:
 	kref_put(&rdata->kref, fc_rport_destroy);
-	if (!IS_ERR(fp))
-		fc_frame_free(fp);
 }
 
 /**
diff --git a/drivers/scsi/libsas/sas_ata.c b/drivers/scsi/libsas/sas_ata.c
index 6a521ba7a616..a4887985aad6 100644
--- a/drivers/scsi/libsas/sas_ata.c
+++ b/drivers/scsi/libsas/sas_ata.c
@@ -209,7 +209,10 @@ static unsigned int sas_ata_qc_issue(struct ata_queued_cmd *qc)
 		task->num_scatter = si;
 	}
 
-	task->data_dir = qc->dma_dir;
+	if (qc->tf.protocol == ATA_PROT_NODATA)
+		task->data_dir = DMA_NONE;
+	else
+		task->data_dir = qc->dma_dir;
 	task->scatter = qc->sg;
 	task->ata_task.retry_count = 1;
 	task->task_state_flags = SAS_TASK_STATE_PENDING;
diff --git a/drivers/scsi/libsas/sas_discover.c b/drivers/scsi/libsas/sas_discover.c
index cd7c7d269f6f..d0f9e90e3279 100644
--- a/drivers/scsi/libsas/sas_discover.c
+++ b/drivers/scsi/libsas/sas_discover.c
@@ -182,10 +182,11 @@ int sas_notify_lldd_dev_found(struct domain_device *dev)
 		pr_warn("driver on host %s cannot handle device %016llx, error:%d\n",
 			dev_name(sas_ha->dev),
 			SAS_ADDR(dev->sas_addr), res);
+		return res;
 	}
 	set_bit(SAS_DEV_FOUND, &dev->state);
 	kref_get(&dev->kref);
-	return res;
+	return 0;
 }
 
 
diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c
index 6aae61d6ee16..b60945182db8 100644
--- a/drivers/scsi/lpfc/lpfc_els.c
+++ b/drivers/scsi/lpfc/lpfc_els.c
@@ -3517,6 +3517,9 @@ lpfc_issue_els_rdf(struct lpfc_vport *vport, uint8_t retry)
 				FC_TLV_DESC_LENGTH_FROM_SZ(prdf->reg_d1));
 	prdf->reg_d1.reg_desc.count = cpu_to_be32(ELS_RDF_REG_TAG_CNT);
 	prdf->reg_d1.desc_tags[0] = cpu_to_be32(ELS_DTAG_LNK_INTEGRITY);
+	prdf->reg_d1.desc_tags[1] = cpu_to_be32(ELS_DTAG_DELIVERY);
+	prdf->reg_d1.desc_tags[2] = cpu_to_be32(ELS_DTAG_PEER_CONGEST);
+	prdf->reg_d1.desc_tags[3] = cpu_to_be32(ELS_DTAG_CONGESTION);
 
 	lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_CMD,
 			      "Issue RDF:       did:x%x",
@@ -4656,7 +4659,9 @@ lpfc_cmpl_els_rsp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 out:
 	if (ndlp && NLP_CHK_NODE_ACT(ndlp) && shost) {
 		spin_lock_irq(shost->host_lock);
-		ndlp->nlp_flag &= ~(NLP_ACC_REGLOGIN | NLP_RM_DFLT_RPI);
+		if (mbox)
+			ndlp->nlp_flag &= ~NLP_ACC_REGLOGIN;
+		ndlp->nlp_flag &= ~NLP_RM_DFLT_RPI;
 		spin_unlock_irq(shost->host_lock);
 
 		/* If the node is not being used by another discovery thread,
diff --git a/drivers/scsi/lpfc/lpfc_hw4.h b/drivers/scsi/lpfc/lpfc_hw4.h
index c4ba8273a63f..12e4e76233e6 100644
--- a/drivers/scsi/lpfc/lpfc_hw4.h
+++ b/drivers/scsi/lpfc/lpfc_hw4.h
@@ -4800,7 +4800,7 @@ struct send_frame_wqe {
 	uint32_t fc_hdr_wd5;           /* word 15 */
 };
 
-#define ELS_RDF_REG_TAG_CNT		1
+#define ELS_RDF_REG_TAG_CNT		4
 struct lpfc_els_rdf_reg_desc {
 	struct fc_df_desc_fpin_reg	reg_desc;	/* descriptor header */
 	__be32				desc_tags[ELS_RDF_REG_TAG_CNT];
diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index c69725999315..ca25e54bb782 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -11376,7 +11376,6 @@ lpfc_irq_clear_aff(struct lpfc_hba_eq_hdl *eqhdl)
 {
 	cpumask_clear(&eqhdl->aff_mask);
 	irq_clear_status_flags(eqhdl->irq, IRQ_NO_BALANCING);
-	irq_set_affinity_hint(eqhdl->irq, &eqhdl->aff_mask);
 }
 
 /**
diff --git a/drivers/scsi/lpfc/lpfc_version.h b/drivers/scsi/lpfc/lpfc_version.h
index 20adec4387f0..c657abf22b75 100644
--- a/drivers/scsi/lpfc/lpfc_version.h
+++ b/drivers/scsi/lpfc/lpfc_version.h
@@ -20,7 +20,7 @@
  * included with this package.                                     *
  *******************************************************************/
 
-#define LPFC_DRIVER_VERSION "12.8.0.3"
+#define LPFC_DRIVER_VERSION "12.8.0.4"
 #define LPFC_DRIVER_NAME		"lpfc"
 
 /* Used for SLI 2/3 */
diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c
index 883cccb59c2d..b0c01cf0428f 100644
--- a/drivers/scsi/megaraid/megaraid_sas_fusion.c
+++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c
@@ -3689,7 +3689,7 @@ int megasas_irqpoll(struct irq_poll *irqpoll, int budget)
 	instance = irq_ctx->instance;
 
 	if (irq_ctx->irq_line_enable) {
-		disable_irq(irq_ctx->os_irq);
+		disable_irq_nosync(irq_ctx->os_irq);
 		irq_ctx->irq_line_enable = false;
 	}
 
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
index 5730f32496b6..8062bd99add8 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -1733,7 +1733,7 @@ _base_irqpoll(struct irq_poll *irqpoll, int budget)
 	reply_q = container_of(irqpoll, struct adapter_reply_queue,
 			irqpoll);
 	if (reply_q->irq_line_enable) {
-		disable_irq(reply_q->os_irq);
+		disable_irq_nosync(reply_q->os_irq);
 		reply_q->irq_line_enable = false;
 	}
 	num_entries = _base_process_reply_queue(reply_q);
diff --git a/drivers/scsi/pm8001/pm8001_sas.c b/drivers/scsi/pm8001/pm8001_sas.c
index 337e79d6837f..9889bab7d31c 100644
--- a/drivers/scsi/pm8001/pm8001_sas.c
+++ b/drivers/scsi/pm8001/pm8001_sas.c
@@ -818,7 +818,7 @@ pm8001_exec_internal_task_abort(struct pm8001_hba_info *pm8001_ha,
 
 		res = pm8001_tag_alloc(pm8001_ha, &ccb_tag);
 		if (res)
-			return res;
+			goto ex_err;
 		ccb = &pm8001_ha->ccb_info[ccb_tag];
 		ccb->device = pm8001_dev;
 		ccb->ccb_tag = ccb_tag;
diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index 1bc090d8a71b..a165120d2976 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -1626,7 +1626,7 @@ typedef struct {
 	 */
 	uint8_t	 firmware_options[2];
 
-	uint16_t frame_payload_size;
+	__le16	frame_payload_size;
 	__le16	max_iocb_allocation;
 	__le16	execution_throttle;
 	uint8_t	 retry_count;
diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index 507919d4ab36..0bd04a62af83 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -4603,18 +4603,18 @@ qla2x00_nvram_config(scsi_qla_host_t *vha)
 			nv->firmware_options[1] = BIT_7 | BIT_5;
 			nv->add_firmware_options[0] = BIT_5;
 			nv->add_firmware_options[1] = BIT_5 | BIT_4;
-			nv->frame_payload_size = 2048;
+			nv->frame_payload_size = cpu_to_le16(2048);
 			nv->special_options[1] = BIT_7;
 		} else if (IS_QLA2200(ha)) {
 			nv->firmware_options[0] = BIT_2 | BIT_1;
 			nv->firmware_options[1] = BIT_7 | BIT_5;
 			nv->add_firmware_options[0] = BIT_5;
 			nv->add_firmware_options[1] = BIT_5 | BIT_4;
-			nv->frame_payload_size = 1024;
+			nv->frame_payload_size = cpu_to_le16(1024);
 		} else if (IS_QLA2100(ha)) {
 			nv->firmware_options[0] = BIT_3 | BIT_1;
 			nv->firmware_options[1] = BIT_5;
-			nv->frame_payload_size = 1024;
+			nv->frame_payload_size = cpu_to_le16(1024);
 		}
 
 		nv->max_iocb_allocation = cpu_to_le16(256);
diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c
index e6e0fb9a81b4..da0201693c24 100644
--- a/drivers/soundwire/bus.c
+++ b/drivers/soundwire/bus.c
@@ -1372,7 +1372,7 @@ static int sdw_handle_slave_alerts(struct sdw_slave *slave)
 		return ret;
 	}
 
-	/* Read Instat 1, Instat 2 and Instat 3 registers */
+	/* Read Intstat 1, Intstat 2 and Intstat 3 registers */
 	ret = sdw_read(slave, SDW_SCP_INT1);
 	if (ret < 0) {
 		dev_err(slave->bus->dev,
diff --git a/drivers/soundwire/stream.c b/drivers/soundwire/stream.c
index 37290a799023..6e36deb505b1 100644
--- a/drivers/soundwire/stream.c
+++ b/drivers/soundwire/stream.c
@@ -717,6 +717,7 @@ error:
 	kfree(wbuf);
 error_1:
 	kfree(wr_msg);
+	bus->defer_msg.msg = NULL;
 	return ret;
 }
 
@@ -840,9 +841,10 @@ static int do_bank_switch(struct sdw_stream_runtime *stream)
 error:
 	list_for_each_entry(m_rt, &stream->master_list, stream_node) {
 		bus = m_rt->bus;
-
-		kfree(bus->defer_msg.msg->buf);
-		kfree(bus->defer_msg.msg);
+		if (bus->defer_msg.msg) {
+			kfree(bus->defer_msg.msg->buf);
+			kfree(bus->defer_msg.msg);
+		}
 	}
 
 msg_unlock:
diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c
index 1c1a9d17eec0..c6795c684b16 100644
--- a/drivers/spi/spi-cadence-quadspi.c
+++ b/drivers/spi/spi-cadence-quadspi.c
@@ -907,14 +907,16 @@ static int cqspi_direct_read_execute(struct cqspi_flash_pdata *f_pdata,
 	struct dma_async_tx_descriptor *tx;
 	dma_cookie_t cookie;
 	dma_addr_t dma_dst;
+	struct device *ddev;
 
 	if (!cqspi->rx_chan || !virt_addr_valid(buf)) {
 		memcpy_fromio(buf, cqspi->ahb_base + from, len);
 		return 0;
 	}
 
-	dma_dst = dma_map_single(dev, buf, len, DMA_FROM_DEVICE);
-	if (dma_mapping_error(dev, dma_dst)) {
+	ddev = cqspi->rx_chan->device->dev;
+	dma_dst = dma_map_single(ddev, buf, len, DMA_FROM_DEVICE);
+	if (dma_mapping_error(ddev, dma_dst)) {
 		dev_err(dev, "dma mapping failed\n");
 		return -ENOMEM;
 	}
@@ -948,7 +950,7 @@ static int cqspi_direct_read_execute(struct cqspi_flash_pdata *f_pdata,
 	}
 
 err_unmap:
-	dma_unmap_single(dev, dma_dst, len, DMA_FROM_DEVICE);
+	dma_unmap_single(ddev, dma_dst, len, DMA_FROM_DEVICE);
 
 	return ret;
 }
@@ -1128,8 +1130,17 @@ static int cqspi_request_mmap_dma(struct cqspi_st *cqspi)
 	return 0;
 }
 
+static const char *cqspi_get_name(struct spi_mem *mem)
+{
+	struct cqspi_st *cqspi = spi_master_get_devdata(mem->spi->master);
+	struct device *dev = &cqspi->pdev->dev;
+
+	return devm_kasprintf(dev, GFP_KERNEL, "%s.%d", dev_name(dev), mem->spi->chip_select);
+}
+
 static const struct spi_controller_mem_ops cqspi_mem_ops = {
 	.exec_op = cqspi_exec_mem_op,
+	.get_name = cqspi_get_name,
 };
 
 static int cqspi_setup_flash(struct cqspi_st *cqspi)
diff --git a/drivers/spi/spi-loopback-test.c b/drivers/spi/spi-loopback-test.c
index 9522d1b5786d..df981e55c24c 100644
--- a/drivers/spi/spi-loopback-test.c
+++ b/drivers/spi/spi-loopback-test.c
@@ -90,7 +90,7 @@ static struct spi_test spi_tests[] = {
 	{
 		.description	= "tx/rx-transfer - crossing PAGE_SIZE",
 		.fill_option	= FILL_COUNT_8,
-		.iterate_len    = { ITERATE_MAX_LEN },
+		.iterate_len    = { ITERATE_LEN },
 		.iterate_tx_align = ITERATE_ALIGN,
 		.iterate_rx_align = ITERATE_ALIGN,
 		.transfer_count = 1,
diff --git a/drivers/spi/spi-stm32.c b/drivers/spi/spi-stm32.c
index d4b33b358a31..3056428b09f3 100644
--- a/drivers/spi/spi-stm32.c
+++ b/drivers/spi/spi-stm32.c
@@ -936,7 +936,11 @@ static irqreturn_t stm32h7_spi_irq_thread(int irq, void *dev_id)
 	}
 
 	if (sr & STM32H7_SPI_SR_SUSP) {
-		dev_warn(spi->dev, "Communication suspended\n");
+		static DEFINE_RATELIMIT_STATE(rs,
+					      DEFAULT_RATELIMIT_INTERVAL * 10,
+					      1);
+		if (__ratelimit(&rs))
+			dev_dbg_ratelimited(spi->dev, "Communication suspended\n");
 		if (!spi->cur_usedma && (spi->rx_buf && (spi->rx_len > 0)))
 			stm32h7_spi_read_rxfifo(spi, false);
 		/*
@@ -2060,7 +2064,7 @@ static int stm32_spi_resume(struct device *dev)
 	}
 
 	ret = pm_runtime_get_sync(dev);
-	if (ret) {
+	if (ret < 0) {
 		dev_err(dev, "Unable to power device:%d\n", ret);
 		return ret;
 	}
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index dc12af018350..0cab239d8e7f 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -1327,8 +1327,6 @@ out:
 	if (msg->status && ctlr->handle_err)
 		ctlr->handle_err(ctlr, msg);
 
-	spi_res_release(ctlr, msg);
-
 	spi_finalize_current_message(ctlr);
 
 	return ret;
@@ -1725,6 +1723,13 @@ void spi_finalize_current_message(struct spi_controller *ctlr)
 
 	spi_unmap_msg(ctlr, mesg);
 
+	/* In the prepare_messages callback the spi bus has the opportunity to
+	 * split a transfer to smaller chunks.
+	 * Release splited transfers here since spi_map_msg is done on the
+	 * splited transfers.
+	 */
+	spi_res_release(ctlr, mesg);
+
 	if (ctlr->cur_msg_prepared && ctlr->unprepare_message) {
 		ret = ctlr->unprepare_message(ctlr, mesg);
 		if (ret) {
diff --git a/drivers/ssb/pci.c b/drivers/ssb/pci.c
index 7c3ae52f2b15..dac54041ad8d 100644
--- a/drivers/ssb/pci.c
+++ b/drivers/ssb/pci.c
@@ -1164,17 +1164,12 @@ void ssb_pci_exit(struct ssb_bus *bus)
 int ssb_pci_init(struct ssb_bus *bus)
 {
 	struct pci_dev *pdev;
-	int err;
 
 	if (bus->bustype != SSB_BUSTYPE_PCI)
 		return 0;
 
 	pdev = bus->host_pci;
 	mutex_init(&bus->sprom_mutex);
-	err = device_create_file(&pdev->dev, &dev_attr_ssb_sprom);
-	if (err)
-		goto out;
 
-out:
-	return err;
+	return device_create_file(&pdev->dev, &dev_attr_ssb_sprom);
 }
diff --git a/drivers/staging/greybus/audio_helper.c b/drivers/staging/greybus/audio_helper.c
index 8b100a71f02e..237531ba60f3 100644
--- a/drivers/staging/greybus/audio_helper.c
+++ b/drivers/staging/greybus/audio_helper.c
@@ -173,8 +173,7 @@ static int gbaudio_remove_controls(struct snd_card *card, struct device *dev,
 		id.index = control->index;
 		kctl = snd_ctl_find_id(card, &id);
 		if (!kctl) {
-			dev_err(dev, "%d: Failed to find %s\n", err,
-				control->name);
+			dev_err(dev, "Failed to find %s\n", control->name);
 			continue;
 		}
 		err = snd_ctl_remove(card, kctl);
diff --git a/drivers/staging/greybus/audio_topology.c b/drivers/staging/greybus/audio_topology.c
index 2f9fdbdcd547..83b38ae8908c 100644
--- a/drivers/staging/greybus/audio_topology.c
+++ b/drivers/staging/greybus/audio_topology.c
@@ -456,6 +456,15 @@ static int gbcodec_mixer_dapm_ctl_put(struct snd_kcontrol *kcontrol,
 	val = ucontrol->value.integer.value[0] & mask;
 	connect = !!val;
 
+	ret = gb_pm_runtime_get_sync(bundle);
+	if (ret)
+		return ret;
+
+	ret = gb_audio_gb_get_control(module->mgmt_connection, data->ctl_id,
+				      GB_AUDIO_INVALID_INDEX, &gbvalue);
+	if (ret)
+		goto exit;
+
 	/* update ucontrol */
 	if (gbvalue.value.integer_value[0] != val) {
 		for (wi = 0; wi < wlist->num_widgets; wi++) {
@@ -466,25 +475,17 @@ static int gbcodec_mixer_dapm_ctl_put(struct snd_kcontrol *kcontrol,
 		gbvalue.value.integer_value[0] =
 			cpu_to_le32(ucontrol->value.integer.value[0]);
 
-		ret = gb_pm_runtime_get_sync(bundle);
-		if (ret)
-			return ret;
-
 		ret = gb_audio_gb_set_control(module->mgmt_connection,
 					      data->ctl_id,
 					      GB_AUDIO_INVALID_INDEX, &gbvalue);
-
-		gb_pm_runtime_put_autosuspend(bundle);
-
-		if (ret) {
-			dev_err_ratelimited(codec_dev,
-					    "%d:Error in %s for %s\n", ret,
-					    __func__, kcontrol->id.name);
-			return ret;
-		}
 	}
 
-	return 0;
+exit:
+	gb_pm_runtime_put_autosuspend(bundle);
+	if (ret)
+		dev_err_ratelimited(codec_dev, "%d:Error in %s for %s\n", ret,
+				    __func__, kcontrol->id.name);
+	return ret;
 }
 
 #define SOC_DAPM_MIXER_GB(xname, kcount, data) \
diff --git a/drivers/staging/wlan-ng/hfa384x_usb.c b/drivers/staging/wlan-ng/hfa384x_usb.c
index fa1bf8b069fd..2720f7319a3d 100644
--- a/drivers/staging/wlan-ng/hfa384x_usb.c
+++ b/drivers/staging/wlan-ng/hfa384x_usb.c
@@ -524,13 +524,8 @@ static void hfa384x_usb_defer(struct work_struct *data)
  */
 void hfa384x_create(struct hfa384x *hw, struct usb_device *usb)
 {
-	memset(hw, 0, sizeof(*hw));
 	hw->usb = usb;
 
-	/* set up the endpoints */
-	hw->endp_in = usb_rcvbulkpipe(usb, 1);
-	hw->endp_out = usb_sndbulkpipe(usb, 2);
-
 	/* Set up the waitq */
 	init_waitqueue_head(&hw->cmdq);
 
diff --git a/drivers/staging/wlan-ng/prism2usb.c b/drivers/staging/wlan-ng/prism2usb.c
index 456603fd26c0..4b08dc1da4f9 100644
--- a/drivers/staging/wlan-ng/prism2usb.c
+++ b/drivers/staging/wlan-ng/prism2usb.c
@@ -61,23 +61,14 @@ static int prism2sta_probe_usb(struct usb_interface *interface,
 			       const struct usb_device_id *id)
 {
 	struct usb_device *dev;
-	const struct usb_endpoint_descriptor *epd;
-	const struct usb_host_interface *iface_desc = interface->cur_altsetting;
+	struct usb_endpoint_descriptor *bulk_in, *bulk_out;
+	struct usb_host_interface *iface_desc = interface->cur_altsetting;
 	struct wlandevice *wlandev = NULL;
 	struct hfa384x *hw = NULL;
 	int result = 0;
 
-	if (iface_desc->desc.bNumEndpoints != 2) {
-		result = -ENODEV;
-		goto failed;
-	}
-
-	result = -EINVAL;
-	epd = &iface_desc->endpoint[1].desc;
-	if (!usb_endpoint_is_bulk_in(epd))
-		goto failed;
-	epd = &iface_desc->endpoint[2].desc;
-	if (!usb_endpoint_is_bulk_out(epd))
+	result = usb_find_common_endpoints(iface_desc, &bulk_in, &bulk_out, NULL, NULL);
+	if (result)
 		goto failed;
 
 	dev = interface_to_usbdev(interface);
@@ -96,6 +87,8 @@ static int prism2sta_probe_usb(struct usb_interface *interface,
 	}
 
 	/* Initialize the hw data */
+	hw->endp_in = usb_rcvbulkpipe(dev, bulk_in->bEndpointAddress);
+	hw->endp_out = usb_sndbulkpipe(dev, bulk_out->bEndpointAddress);
 	hfa384x_create(hw, dev);
 	hw->wlandev = wlandev;
 
diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c
index cd045dc75a58..7b56fe9f1062 100644
--- a/drivers/target/iscsi/iscsi_target.c
+++ b/drivers/target/iscsi/iscsi_target.c
@@ -1389,14 +1389,27 @@ static u32 iscsit_do_crypto_hash_sg(
 	sg = cmd->first_data_sg;
 	page_off = cmd->first_data_sg_off;
 
+	if (data_length && page_off) {
+		struct scatterlist first_sg;
+		u32 len = min_t(u32, data_length, sg->length - page_off);
+
+		sg_init_table(&first_sg, 1);
+		sg_set_page(&first_sg, sg_page(sg), len, sg->offset + page_off);
+
+		ahash_request_set_crypt(hash, &first_sg, NULL, len);
+		crypto_ahash_update(hash);
+
+		data_length -= len;
+		sg = sg_next(sg);
+	}
+
 	while (data_length) {
-		u32 cur_len = min_t(u32, data_length, (sg->length - page_off));
+		u32 cur_len = min_t(u32, data_length, sg->length);
 
 		ahash_request_set_crypt(hash, sg, NULL, cur_len);
 		crypto_ahash_update(hash);
 
 		data_length -= cur_len;
-		page_off = 0;
 		/* iscsit_map_iovec has already checked for invalid sg pointers */
 		sg = sg_next(sg);
 	}
diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c
index 85748e338858..893d1b406c29 100644
--- a/drivers/target/iscsi/iscsi_target_login.c
+++ b/drivers/target/iscsi/iscsi_target_login.c
@@ -1149,7 +1149,7 @@ void iscsit_free_conn(struct iscsi_conn *conn)
 }
 
 void iscsi_target_login_sess_out(struct iscsi_conn *conn,
-		struct iscsi_np *np, bool zero_tsih, bool new_sess)
+				 bool zero_tsih, bool new_sess)
 {
 	if (!new_sess)
 		goto old_sess_out;
@@ -1167,7 +1167,6 @@ void iscsi_target_login_sess_out(struct iscsi_conn *conn,
 	conn->sess = NULL;
 
 old_sess_out:
-	iscsi_stop_login_thread_timer(np);
 	/*
 	 * If login negotiation fails check if the Time2Retain timer
 	 * needs to be restarted.
@@ -1407,8 +1406,9 @@ static int __iscsi_target_login_thread(struct iscsi_np *np)
 new_sess_out:
 	new_sess = true;
 old_sess_out:
+	iscsi_stop_login_thread_timer(np);
 	tpg_np = conn->tpg_np;
-	iscsi_target_login_sess_out(conn, np, zero_tsih, new_sess);
+	iscsi_target_login_sess_out(conn, zero_tsih, new_sess);
 	new_sess = false;
 
 	if (tpg) {
diff --git a/drivers/target/iscsi/iscsi_target_login.h b/drivers/target/iscsi/iscsi_target_login.h
index 3b8e3639ff5d..fc95e6150253 100644
--- a/drivers/target/iscsi/iscsi_target_login.h
+++ b/drivers/target/iscsi/iscsi_target_login.h
@@ -22,8 +22,7 @@ extern int iscsit_put_login_tx(struct iscsi_conn *, struct iscsi_login *, u32);
 extern void iscsit_free_conn(struct iscsi_conn *);
 extern int iscsit_start_kthreads(struct iscsi_conn *);
 extern void iscsi_post_login_handler(struct iscsi_np *, struct iscsi_conn *, u8);
-extern void iscsi_target_login_sess_out(struct iscsi_conn *, struct iscsi_np *,
-				bool, bool);
+extern void iscsi_target_login_sess_out(struct iscsi_conn *, bool, bool);
 extern int iscsi_target_login_thread(void *);
 extern void iscsi_handle_login_thread_timeout(struct timer_list *t);
 
diff --git a/drivers/target/iscsi/iscsi_target_nego.c b/drivers/target/iscsi/iscsi_target_nego.c
index f88a52fec889..8b40f10976ff 100644
--- a/drivers/target/iscsi/iscsi_target_nego.c
+++ b/drivers/target/iscsi/iscsi_target_nego.c
@@ -535,12 +535,11 @@ static bool iscsi_target_sk_check_and_clear(struct iscsi_conn *conn, unsigned in
 
 static void iscsi_target_login_drop(struct iscsi_conn *conn, struct iscsi_login *login)
 {
-	struct iscsi_np *np = login->np;
 	bool zero_tsih = login->zero_tsih;
 
 	iscsi_remove_failed_auth_entry(conn);
 	iscsi_target_nego_release(conn);
-	iscsi_target_login_sess_out(conn, np, zero_tsih, true);
+	iscsi_target_login_sess_out(conn, zero_tsih, true);
 }
 
 struct conn_timeout {
diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c
index 9b7592350502..1a060a2c98d6 100644
--- a/drivers/target/target_core_user.c
+++ b/drivers/target/target_core_user.c
@@ -436,7 +436,7 @@ static int tcmu_genl_set_features(struct sk_buff *skb, struct genl_info *info)
 	return 0;
 }
 
-static const struct genl_ops tcmu_genl_ops[] = {
+static const struct genl_small_ops tcmu_genl_ops[] = {
 	{
 		.cmd	= TCMU_CMD_SET_FEATURES,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
@@ -474,8 +474,8 @@ static struct genl_family tcmu_genl_family __ro_after_init = {
 	.mcgrps = tcmu_mcgrps,
 	.n_mcgrps = ARRAY_SIZE(tcmu_mcgrps),
 	.netnsok = true,
-	.ops = tcmu_genl_ops,
-	.n_ops = ARRAY_SIZE(tcmu_genl_ops),
+	.small_ops = tcmu_genl_ops,
+	.n_small_ops = ARRAY_SIZE(tcmu_genl_ops),
 };
 
 #define tcmu_cmd_set_dbi_cur(cmd, index) ((cmd)->dbi_cur = (index))
diff --git a/drivers/thermal/thermal_netlink.c b/drivers/thermal/thermal_netlink.c
index af7b2383e8f6..da2891fcac89 100644
--- a/drivers/thermal/thermal_netlink.c
+++ b/drivers/thermal/thermal_netlink.c
@@ -545,7 +545,7 @@ static int thermal_genl_cmd_dumpit(struct sk_buff *skb,
 {
 	struct param p = { .msg = skb };
 	const struct genl_dumpit_info *info = genl_dumpit_info(cb);
-	int cmd = info->ops->cmd;
+	int cmd = info->op.cmd;
 	int ret;
 	void *hdr;
 
@@ -601,7 +601,7 @@ out_free_msg:
 	return ret;
 }
 
-static const struct genl_ops thermal_genl_ops[] = {
+static const struct genl_small_ops thermal_genl_ops[] = {
 	{
 		.cmd = THERMAL_GENL_CMD_TZ_GET_ID,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
@@ -635,8 +635,8 @@ static struct genl_family thermal_gnl_family __ro_after_init = {
 	.version	= THERMAL_GENL_VERSION,
 	.maxattr	= THERMAL_GENL_ATTR_MAX,
 	.policy		= thermal_genl_policy,
-	.ops		= thermal_genl_ops,
-	.n_ops		= ARRAY_SIZE(thermal_genl_ops),
+	.small_ops	= thermal_genl_ops,
+	.n_small_ops	= ARRAY_SIZE(thermal_genl_ops),
 	.mcgrps		= thermal_genl_mcgrps,
 	.n_mcgrps	= ARRAY_SIZE(thermal_genl_mcgrps),
 };
diff --git a/drivers/thunderbolt/eeprom.c b/drivers/thunderbolt/eeprom.c
index 3ebca44ab3fa..0c8471be3e32 100644
--- a/drivers/thunderbolt/eeprom.c
+++ b/drivers/thunderbolt/eeprom.c
@@ -7,6 +7,7 @@
  */
 
 #include <linux/crc32.h>
+#include <linux/delay.h>
 #include <linux/property.h>
 #include <linux/slab.h>
 #include "tb.h"
@@ -389,8 +390,8 @@ static int tb_drom_parse_entries(struct tb_switch *sw)
 		struct tb_drom_entry_header *entry = (void *) (sw->drom + pos);
 		if (pos + 1 == drom_size || pos + entry->len > drom_size
 				|| !entry->len) {
-			tb_sw_warn(sw, "drom buffer overrun, aborting\n");
-			return -EIO;
+			tb_sw_warn(sw, "DROM buffer overrun\n");
+			return -EILSEQ;
 		}
 
 		switch (entry->type) {
@@ -526,7 +527,8 @@ int tb_drom_read(struct tb_switch *sw)
 	u16 size;
 	u32 crc;
 	struct tb_drom_header *header;
-	int res;
+	int res, retries = 1;
+
 	if (sw->drom)
 		return 0;
 
@@ -612,7 +614,17 @@ parse:
 		tb_sw_warn(sw, "drom device_rom_revision %#x unknown\n",
 			header->device_rom_revision);
 
-	return tb_drom_parse_entries(sw);
+	res = tb_drom_parse_entries(sw);
+	/* If the DROM parsing fails, wait a moment and retry once */
+	if (res == -EILSEQ && retries--) {
+		tb_sw_warn(sw, "parsing DROM failed, retrying\n");
+		msleep(100);
+		res = tb_drom_read_n(sw, 0, sw->drom, size);
+		if (!res)
+			goto parse;
+	}
+
+	return res;
 err:
 	kfree(sw->drom);
 	sw->drom = NULL;
diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c
index 3845db569e4c..a921de9ce7cb 100644
--- a/drivers/thunderbolt/switch.c
+++ b/drivers/thunderbolt/switch.c
@@ -684,6 +684,7 @@ static int tb_init_port(struct tb_port *port)
 		if (res == -ENODEV) {
 			tb_dbg(port->sw->tb, " Port %d: not implemented\n",
 			       port->port);
+			port->disabled = true;
 			return 0;
 		}
 		return res;
diff --git a/drivers/thunderbolt/tb.h b/drivers/thunderbolt/tb.h
index a413d55b5f8b..3c620a9203c5 100644
--- a/drivers/thunderbolt/tb.h
+++ b/drivers/thunderbolt/tb.h
@@ -186,7 +186,7 @@ struct tb_switch {
  * @cap_adap: Offset of the adapter specific capability (%0 if not present)
  * @cap_usb4: Offset to the USB4 port capability (%0 if not present)
  * @port: Port number on switch
- * @disabled: Disabled by eeprom
+ * @disabled: Disabled by eeprom or enabled but not implemented
  * @bonded: true if the port is bonded (two lanes combined as one)
  * @dual_link_port: If the switch is connected using two ports, points
  *		    to the other port.
diff --git a/drivers/thunderbolt/tunnel.c b/drivers/thunderbolt/tunnel.c
index 1a7e849840b2..829b6ccdd5d4 100644
--- a/drivers/thunderbolt/tunnel.c
+++ b/drivers/thunderbolt/tunnel.c
@@ -951,10 +951,18 @@ static void tb_usb3_reclaim_available_bandwidth(struct tb_tunnel *tunnel,
 	int ret, max_rate, allocate_up, allocate_down;
 
 	ret = usb4_usb3_port_actual_link_rate(tunnel->src_port);
-	if (ret <= 0) {
-		tb_tunnel_warn(tunnel, "tunnel is not up\n");
+	if (ret < 0) {
+		tb_tunnel_warn(tunnel, "failed to read actual link rate\n");
 		return;
+	} else if (!ret) {
+		/* Use maximum link rate if the link valid is not set */
+		ret = usb4_usb3_port_max_link_rate(tunnel->src_port);
+		if (ret < 0) {
+			tb_tunnel_warn(tunnel, "failed to read maximum link rate\n");
+			return;
+		}
 	}
+
 	/*
 	 * 90% of the max rate can be allocated for isochronous
 	 * transfers.
diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c
index 3eb2d485eaeb..55bb7b897d97 100644
--- a/drivers/tty/serial/8250/8250_pci.c
+++ b/drivers/tty/serial/8250/8250_pci.c
@@ -5566,6 +5566,17 @@ static const struct pci_device_id serial_pci_tbl[] = {
 		PCI_ANY_ID, PCI_ANY_ID,
 		0, 0, pbn_wch384_4 },
 
+	/*
+	 * Realtek RealManage
+	 */
+	{	PCI_VENDOR_ID_REALTEK, 0x816a,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0, pbn_b0_1_115200 },
+
+	{	PCI_VENDOR_ID_REALTEK, 0x816b,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0, pbn_b0_1_115200 },
+
 	/* Fintek PCI serial cards */
 	{ PCI_DEVICE(0x1c29, 0x1104), .driver_data = pbn_fintek_4 },
 	{ PCI_DEVICE(0x1c29, 0x1108), .driver_data = pbn_fintek_8 },
diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index f797c971cd82..124524ecfe26 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -1916,24 +1916,12 @@ static inline bool uart_console_enabled(struct uart_port *port)
 	return uart_console(port) && (port->cons->flags & CON_ENABLED);
 }
 
-static void __uart_port_spin_lock_init(struct uart_port *port)
+static void uart_port_spin_lock_init(struct uart_port *port)
 {
 	spin_lock_init(&port->lock);
 	lockdep_set_class(&port->lock, &port_lock_key);
 }
 
-/*
- * Ensure that the serial console lock is initialised early.
- * If this port is a console, then the spinlock is already initialised.
- */
-static inline void uart_port_spin_lock_init(struct uart_port *port)
-{
-	if (uart_console(port))
-		return;
-
-	__uart_port_spin_lock_init(port);
-}
-
 #if defined(CONFIG_SERIAL_CORE_CONSOLE) || defined(CONFIG_CONSOLE_POLL)
 /**
  *	uart_console_write - write a console message to a serial port
@@ -2086,7 +2074,15 @@ uart_set_options(struct uart_port *port, struct console *co,
 	struct ktermios termios;
 	static struct ktermios dummy;
 
-	uart_port_spin_lock_init(port);
+	/*
+	 * Ensure that the serial-console lock is initialised early.
+	 *
+	 * Note that the console-enabled check is needed because of kgdboc,
+	 * which can end up calling uart_set_options() for an already enabled
+	 * console via tty_find_polling_driver() and uart_poll_init().
+	 */
+	if (!uart_console_enabled(port) && !port->console_reinit)
+		uart_port_spin_lock_init(port);
 
 	memset(&termios, 0, sizeof(struct ktermios));
 
@@ -2379,13 +2375,6 @@ uart_configure_port(struct uart_driver *drv, struct uart_state *state,
 		uart_change_pm(state, UART_PM_STATE_ON);
 
 		/*
-		 * If this driver supports console, and it hasn't been
-		 * successfully registered yet, initialise spin lock for it.
-		 */
-		if (port->cons && !(port->cons->flags & CON_ENABLED))
-			__uart_port_spin_lock_init(port);
-
-		/*
 		 * Ensure that the modem control lines are de-activated.
 		 * keep the DTR setting that is set in uart_set_options()
 		 * We probably don't need a spinlock around this, but
@@ -2801,10 +2790,12 @@ static ssize_t console_store(struct device *dev,
 		if (oldconsole && !newconsole) {
 			ret = unregister_console(uport->cons);
 		} else if (!oldconsole && newconsole) {
-			if (uart_console(uport))
+			if (uart_console(uport)) {
+				uport->console_reinit = 1;
 				register_console(uport->cons);
-			else
+			} else {
 				ret = -ENOENT;
+			}
 		}
 	} else {
 		ret = -ENXIO;
@@ -2900,7 +2891,12 @@ int uart_add_one_port(struct uart_driver *drv, struct uart_port *uport)
 		goto out;
 	}
 
-	uart_port_spin_lock_init(uport);
+	/*
+	 * If this port is in use as a console then the spinlock is already
+	 * initialised.
+	 */
+	if (!uart_console_enabled(uport))
+		uart_port_spin_lock_init(uport);
 
 	if (uport->cons && uport->dev)
 		of_console_check(uport->dev->of_node, uport->cons->name, uport->line);
diff --git a/drivers/usb/class/usblp.c b/drivers/usb/class/usblp.c
index 084c48c5848f..67cbd42421be 100644
--- a/drivers/usb/class/usblp.c
+++ b/drivers/usb/class/usblp.c
@@ -827,6 +827,11 @@ static ssize_t usblp_read(struct file *file, char __user *buffer, size_t len, lo
 	if (rv < 0)
 		return rv;
 
+	if (!usblp->present) {
+		count = -ENODEV;
+		goto done;
+	}
+
 	if ((avail = usblp->rstatus) < 0) {
 		printk(KERN_ERR "usblp%d: error %d reading from printer\n",
 		    usblp->minor, (int)avail);
diff --git a/drivers/usb/core/message.c b/drivers/usb/core/message.c
index 6197938dcc2d..ae1de9cc4b09 100644
--- a/drivers/usb/core/message.c
+++ b/drivers/usb/core/message.c
@@ -1205,6 +1205,34 @@ void usb_disable_interface(struct usb_device *dev, struct usb_interface *intf,
 	}
 }
 
+/*
+ * usb_disable_device_endpoints -- Disable all endpoints for a device
+ * @dev: the device whose endpoints are being disabled
+ * @skip_ep0: 0 to disable endpoint 0, 1 to skip it.
+ */
+static void usb_disable_device_endpoints(struct usb_device *dev, int skip_ep0)
+{
+	struct usb_hcd *hcd = bus_to_hcd(dev->bus);
+	int i;
+
+	if (hcd->driver->check_bandwidth) {
+		/* First pass: Cancel URBs, leave endpoint pointers intact. */
+		for (i = skip_ep0; i < 16; ++i) {
+			usb_disable_endpoint(dev, i, false);
+			usb_disable_endpoint(dev, i + USB_DIR_IN, false);
+		}
+		/* Remove endpoints from the host controller internal state */
+		mutex_lock(hcd->bandwidth_mutex);
+		usb_hcd_alloc_bandwidth(dev, NULL, NULL, NULL);
+		mutex_unlock(hcd->bandwidth_mutex);
+	}
+	/* Second pass: remove endpoint pointers */
+	for (i = skip_ep0; i < 16; ++i) {
+		usb_disable_endpoint(dev, i, true);
+		usb_disable_endpoint(dev, i + USB_DIR_IN, true);
+	}
+}
+
 /**
  * usb_disable_device - Disable all the endpoints for a USB device
  * @dev: the device whose endpoints are being disabled
@@ -1218,7 +1246,6 @@ void usb_disable_interface(struct usb_device *dev, struct usb_interface *intf,
 void usb_disable_device(struct usb_device *dev, int skip_ep0)
 {
 	int i;
-	struct usb_hcd *hcd = bus_to_hcd(dev->bus);
 
 	/* getting rid of interfaces will disconnect
 	 * any drivers bound to them (a key side effect)
@@ -1264,22 +1291,8 @@ void usb_disable_device(struct usb_device *dev, int skip_ep0)
 
 	dev_dbg(&dev->dev, "%s nuking %s URBs\n", __func__,
 		skip_ep0 ? "non-ep0" : "all");
-	if (hcd->driver->check_bandwidth) {
-		/* First pass: Cancel URBs, leave endpoint pointers intact. */
-		for (i = skip_ep0; i < 16; ++i) {
-			usb_disable_endpoint(dev, i, false);
-			usb_disable_endpoint(dev, i + USB_DIR_IN, false);
-		}
-		/* Remove endpoints from the host controller internal state */
-		mutex_lock(hcd->bandwidth_mutex);
-		usb_hcd_alloc_bandwidth(dev, NULL, NULL, NULL);
-		mutex_unlock(hcd->bandwidth_mutex);
-		/* Second pass: remove endpoint pointers */
-	}
-	for (i = skip_ep0; i < 16; ++i) {
-		usb_disable_endpoint(dev, i, true);
-		usb_disable_endpoint(dev, i + USB_DIR_IN, true);
-	}
+
+	usb_disable_device_endpoints(dev, skip_ep0);
 }
 
 /**
@@ -1522,6 +1535,9 @@ EXPORT_SYMBOL_GPL(usb_set_interface);
  * The caller must own the device lock.
  *
  * Return: Zero on success, else a negative error code.
+ *
+ * If this routine fails the device will probably be in an unusable state
+ * with endpoints disabled, and interfaces only partially enabled.
  */
 int usb_reset_configuration(struct usb_device *dev)
 {
@@ -1537,10 +1553,7 @@ int usb_reset_configuration(struct usb_device *dev)
 	 * calls during probe() are fine
 	 */
 
-	for (i = 1; i < 16; ++i) {
-		usb_disable_endpoint(dev, i, true);
-		usb_disable_endpoint(dev, i + USB_DIR_IN, true);
-	}
+	usb_disable_device_endpoints(dev, 1); /* skip ep0*/
 
 	config = dev->actconfig;
 	retval = 0;
@@ -1553,34 +1566,10 @@ int usb_reset_configuration(struct usb_device *dev)
 		mutex_unlock(hcd->bandwidth_mutex);
 		return -ENOMEM;
 	}
-	/* Make sure we have enough bandwidth for each alternate setting 0 */
-	for (i = 0; i < config->desc.bNumInterfaces; i++) {
-		struct usb_interface *intf = config->interface[i];
-		struct usb_host_interface *alt;
 
-		alt = usb_altnum_to_altsetting(intf, 0);
-		if (!alt)
-			alt = &intf->altsetting[0];
-		if (alt != intf->cur_altsetting)
-			retval = usb_hcd_alloc_bandwidth(dev, NULL,
-					intf->cur_altsetting, alt);
-		if (retval < 0)
-			break;
-	}
-	/* If not, reinstate the old alternate settings */
+	/* xHCI adds all endpoints in usb_hcd_alloc_bandwidth */
+	retval = usb_hcd_alloc_bandwidth(dev, config, NULL, NULL);
 	if (retval < 0) {
-reset_old_alts:
-		for (i--; i >= 0; i--) {
-			struct usb_interface *intf = config->interface[i];
-			struct usb_host_interface *alt;
-
-			alt = usb_altnum_to_altsetting(intf, 0);
-			if (!alt)
-				alt = &intf->altsetting[0];
-			if (alt != intf->cur_altsetting)
-				usb_hcd_alloc_bandwidth(dev, NULL,
-						alt, intf->cur_altsetting);
-		}
 		usb_enable_lpm(dev);
 		mutex_unlock(hcd->bandwidth_mutex);
 		return retval;
@@ -1589,8 +1578,12 @@ reset_old_alts:
 			USB_REQ_SET_CONFIGURATION, 0,
 			config->desc.bConfigurationValue, 0,
 			NULL, 0, USB_CTRL_SET_TIMEOUT);
-	if (retval < 0)
-		goto reset_old_alts;
+	if (retval < 0) {
+		usb_hcd_alloc_bandwidth(dev, NULL, NULL, NULL);
+		usb_enable_lpm(dev);
+		mutex_unlock(hcd->bandwidth_mutex);
+		return retval;
+	}
 	mutex_unlock(hcd->bandwidth_mutex);
 
 	/* re-init hc/hcd interface/endpoint state */
diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index f232914de5fd..10574fa3f927 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -397,6 +397,10 @@ static const struct usb_device_id usb_quirk_list[] = {
 	/* Generic RTL8153 based ethernet adapters */
 	{ USB_DEVICE(0x0bda, 0x8153), .driver_info = USB_QUIRK_NO_LPM },
 
+	/* SONiX USB DEVICE Touchpad */
+	{ USB_DEVICE(0x0c45, 0x7056), .driver_info =
+			USB_QUIRK_IGNORE_REMOTE_WAKEUP },
+
 	/* Action Semiconductor flash disk */
 	{ USB_DEVICE(0x10d6, 0x2200), .driver_info =
 			USB_QUIRK_STRING_FETCH_255 },
diff --git a/drivers/usb/core/sysfs.c b/drivers/usb/core/sysfs.c
index a2ca38e25e0c..8d134193fa0c 100644
--- a/drivers/usb/core/sysfs.c
+++ b/drivers/usb/core/sysfs.c
@@ -889,7 +889,11 @@ read_descriptors(struct file *filp, struct kobject *kobj,
 	size_t srclen, n;
 	int cfgno;
 	void *src;
+	int retval;
 
+	retval = usb_lock_device_interruptible(udev);
+	if (retval < 0)
+		return -EINTR;
 	/* The binary attribute begins with the device descriptor.
 	 * Following that are the raw descriptor entries for all the
 	 * configurations (config plus subsidiary descriptors).
@@ -914,6 +918,7 @@ read_descriptors(struct file *filp, struct kobject *kobj,
 			off -= srclen;
 		}
 	}
+	usb_unlock_device(udev);
 	return count - nleft;
 }
 
diff --git a/drivers/usb/dwc3/dwc3-meson-g12a.c b/drivers/usb/dwc3/dwc3-meson-g12a.c
index 88b75b5a039c..1f7f4d88ed9d 100644
--- a/drivers/usb/dwc3/dwc3-meson-g12a.c
+++ b/drivers/usb/dwc3/dwc3-meson-g12a.c
@@ -737,13 +737,13 @@ static int dwc3_meson_g12a_probe(struct platform_device *pdev)
 		goto err_disable_clks;
 	}
 
-	ret = reset_control_deassert(priv->reset);
+	ret = reset_control_reset(priv->reset);
 	if (ret)
-		goto err_assert_reset;
+		goto err_disable_clks;
 
 	ret = dwc3_meson_g12a_get_phys(priv);
 	if (ret)
-		goto err_assert_reset;
+		goto err_disable_clks;
 
 	ret = priv->drvdata->setup_regmaps(priv, base);
 	if (ret)
@@ -752,7 +752,7 @@ static int dwc3_meson_g12a_probe(struct platform_device *pdev)
 	if (priv->vbus) {
 		ret = regulator_enable(priv->vbus);
 		if (ret)
-			goto err_assert_reset;
+			goto err_disable_clks;
 	}
 
 	/* Get dr_mode */
@@ -765,13 +765,13 @@ static int dwc3_meson_g12a_probe(struct platform_device *pdev)
 
 	ret = priv->drvdata->usb_init(priv);
 	if (ret)
-		goto err_assert_reset;
+		goto err_disable_clks;
 
 	/* Init PHYs */
 	for (i = 0 ; i < PHY_COUNT ; ++i) {
 		ret = phy_init(priv->phys[i]);
 		if (ret)
-			goto err_assert_reset;
+			goto err_disable_clks;
 	}
 
 	/* Set PHY Power */
@@ -809,9 +809,6 @@ err_phys_exit:
 	for (i = 0 ; i < PHY_COUNT ; ++i)
 		phy_exit(priv->phys[i]);
 
-err_assert_reset:
-	reset_control_assert(priv->reset);
-
 err_disable_clks:
 	clk_bulk_disable_unprepare(priv->drvdata->num_clks,
 				   priv->drvdata->clks);
diff --git a/drivers/usb/host/ehci-hcd.c b/drivers/usb/host/ehci-hcd.c
index 6257be4110ca..3575b7201881 100644
--- a/drivers/usb/host/ehci-hcd.c
+++ b/drivers/usb/host/ehci-hcd.c
@@ -22,6 +22,7 @@
 #include <linux/interrupt.h>
 #include <linux/usb.h>
 #include <linux/usb/hcd.h>
+#include <linux/usb/otg.h>
 #include <linux/moduleparam.h>
 #include <linux/dma-mapping.h>
 #include <linux/debugfs.h>
diff --git a/drivers/usb/host/ehci-hub.c b/drivers/usb/host/ehci-hub.c
index ce0eaf7d7c12..087402aec5cb 100644
--- a/drivers/usb/host/ehci-hub.c
+++ b/drivers/usb/host/ehci-hub.c
@@ -14,7 +14,6 @@
  */
 
 /*-------------------------------------------------------------------------*/
-#include <linux/usb/otg.h>
 
 #define	PORT_WAKE_BITS	(PORT_WKOC_E|PORT_WKDISC_E|PORT_WKCONN_E)
 
diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index 871cdccf3a5f..9823bb424abd 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -713,6 +713,7 @@ static const struct usb_device_id id_table_combined[] = {
 	{ USB_DEVICE(XSENS_VID, XSENS_AWINDA_STATION_PID) },
 	{ USB_DEVICE(XSENS_VID, XSENS_CONVERTER_PID) },
 	{ USB_DEVICE(XSENS_VID, XSENS_MTDEVBOARD_PID) },
+	{ USB_DEVICE(XSENS_VID, XSENS_MTIUSBCONVERTER_PID) },
 	{ USB_DEVICE(XSENS_VID, XSENS_MTW_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_OMNI1509) },
 	{ USB_DEVICE(MOBILITY_VID, MOBILITY_USB_SERIAL_PID) },
diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h
index e8373528264c..b5ca17a5967a 100644
--- a/drivers/usb/serial/ftdi_sio_ids.h
+++ b/drivers/usb/serial/ftdi_sio_ids.h
@@ -160,6 +160,7 @@
 #define XSENS_AWINDA_DONGLE_PID 0x0102
 #define XSENS_MTW_PID		0x0200	/* Xsens MTw */
 #define XSENS_MTDEVBOARD_PID	0x0300	/* Motion Tracker Development Board */
+#define XSENS_MTIUSBCONVERTER_PID	0x0301	/* MTi USB converter */
 #define XSENS_CONVERTER_PID	0xD00D	/* Xsens USB-serial converter */
 
 /* Xsens devices using FTDI VID */
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 89b3192af326..0c6f160a214a 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -1094,14 +1094,18 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE(QUALCOMM_VENDOR_ID, UBLOX_PRODUCT_R410M),
 	  .driver_info = RSVD(1) | RSVD(3) },
 	/* Quectel products using Quectel vendor ID */
-	{ USB_DEVICE(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC21),
-	  .driver_info = RSVD(4) },
-	{ USB_DEVICE(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC25),
-	  .driver_info = RSVD(4) },
-	{ USB_DEVICE(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EG95),
-	  .driver_info = RSVD(4) },
-	{ USB_DEVICE(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_BG96),
-	  .driver_info = RSVD(4) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC21, 0xff, 0xff, 0xff),
+	  .driver_info = NUMEP2 },
+	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC21, 0xff, 0, 0) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC25, 0xff, 0xff, 0xff),
+	  .driver_info = NUMEP2 },
+	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC25, 0xff, 0, 0) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EG95, 0xff, 0xff, 0xff),
+	  .driver_info = NUMEP2 },
+	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EG95, 0xff, 0, 0) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_BG96, 0xff, 0xff, 0xff),
+	  .driver_info = NUMEP2 },
+	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_BG96, 0xff, 0, 0) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EP06, 0xff, 0xff, 0xff),
 	  .driver_info = RSVD(1) | RSVD(2) | RSVD(3) | RSVD(4) | NUMEP2 },
 	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EP06, 0xff, 0, 0) },
@@ -1819,6 +1823,8 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE_INTERFACE_CLASS(0x1e0e, 0x9003, 0xff) },	/* Simcom SIM7500/SIM7600 MBIM mode */
 	{ USB_DEVICE_INTERFACE_CLASS(0x1e0e, 0x9011, 0xff),	/* Simcom SIM7500/SIM7600 RNDIS mode */
 	  .driver_info = RSVD(7) },
+	{ USB_DEVICE_INTERFACE_CLASS(0x1e0e, 0x9205, 0xff) },	/* Simcom SIM7070/SIM7080/SIM7090 AT+ECM mode */
+	{ USB_DEVICE_INTERFACE_CLASS(0x1e0e, 0x9206, 0xff) },	/* Simcom SIM7070/SIM7080/SIM7090 AT-only mode */
 	{ USB_DEVICE(ALCATEL_VENDOR_ID, ALCATEL_PRODUCT_X060S_X200),
 	  .driver_info = NCTRL(0) | NCTRL(1) | RSVD(4) },
 	{ USB_DEVICE(ALCATEL_VENDOR_ID, ALCATEL_PRODUCT_X220_X500D),
diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c
index 08f9296431e9..8183504e3abb 100644
--- a/drivers/usb/storage/uas.c
+++ b/drivers/usb/storage/uas.c
@@ -662,8 +662,7 @@ static int uas_queuecommand_lck(struct scsi_cmnd *cmnd,
 	if (devinfo->resetting) {
 		cmnd->result = DID_ERROR << 16;
 		cmnd->scsi_done(cmnd);
-		spin_unlock_irqrestore(&devinfo->lock, flags);
-		return 0;
+		goto zombie;
 	}
 
 	/* Find a free uas-tag */
@@ -699,6 +698,16 @@ static int uas_queuecommand_lck(struct scsi_cmnd *cmnd,
 		cmdinfo->state &= ~(SUBMIT_DATA_IN_URB | SUBMIT_DATA_OUT_URB);
 
 	err = uas_submit_urbs(cmnd, devinfo);
+	/*
+	 * in case of fatal errors the SCSI layer is peculiar
+	 * a command that has finished is a success for the purpose
+	 * of queueing, no matter how fatal the error
+	 */
+	if (err == -ENODEV) {
+		cmnd->result = DID_ERROR << 16;
+		cmnd->scsi_done(cmnd);
+		goto zombie;
+	}
 	if (err) {
 		/* If we did nothing, give up now */
 		if (cmdinfo->state & SUBMIT_STATUS_URB) {
@@ -709,6 +718,7 @@ static int uas_queuecommand_lck(struct scsi_cmnd *cmnd,
 	}
 
 	devinfo->cmnd[idx] = cmnd;
+zombie:
 	spin_unlock_irqrestore(&devinfo->lock, flags);
 	return 0;
 }
diff --git a/drivers/usb/typec/mux/intel_pmc_mux.c b/drivers/usb/typec/mux/intel_pmc_mux.c
index e4021e13af40..676b525c2a66 100644
--- a/drivers/usb/typec/mux/intel_pmc_mux.c
+++ b/drivers/usb/typec/mux/intel_pmc_mux.c
@@ -61,14 +61,11 @@ enum {
 
 #define PMC_USB_ALTMODE_ORI_SHIFT	1
 #define PMC_USB_ALTMODE_UFP_SHIFT	3
-#define PMC_USB_ALTMODE_ORI_AUX_SHIFT	4
-#define PMC_USB_ALTMODE_ORI_HSL_SHIFT	5
 
 /* DP specific Mode Data bits */
 #define PMC_USB_ALTMODE_DP_MODE_SHIFT	8
 
 /* TBT specific Mode Data bits */
-#define PMC_USB_ALTMODE_HPD_HIGH	BIT(14)
 #define PMC_USB_ALTMODE_TBT_TYPE	BIT(17)
 #define PMC_USB_ALTMODE_CABLE_TYPE	BIT(18)
 #define PMC_USB_ALTMODE_ACTIVE_LINK	BIT(20)
@@ -128,13 +125,19 @@ static int hsl_orientation(struct pmc_usb_port *port)
 static int pmc_usb_command(struct pmc_usb_port *port, u8 *msg, u32 len)
 {
 	u8 response[4];
+	int ret;
 
 	/*
 	 * Error bit will always be 0 with the USBC command.
-	 * Status can be checked from the response message.
+	 * Status can be checked from the response message if the
+	 * function intel_scu_ipc_dev_command succeeds.
 	 */
-	intel_scu_ipc_dev_command(port->pmc->ipc, PMC_USBC_CMD, 0, msg, len,
-				  response, sizeof(response));
+	ret = intel_scu_ipc_dev_command(port->pmc->ipc, PMC_USBC_CMD, 0, msg,
+					len, response, sizeof(response));
+
+	if (ret)
+		return ret;
+
 	if (response[2] & PMC_USB_RESP_STATUS_FAILURE) {
 		if (response[2] & PMC_USB_RESP_STATUS_FATAL)
 			return -EIO;
@@ -179,15 +182,9 @@ pmc_usb_mux_dp(struct pmc_usb_port *port, struct typec_mux_state *state)
 	req.mode_data = (port->orientation - 1) << PMC_USB_ALTMODE_ORI_SHIFT;
 	req.mode_data |= (port->role - 1) << PMC_USB_ALTMODE_UFP_SHIFT;
 
-	req.mode_data |= sbu_orientation(port) << PMC_USB_ALTMODE_ORI_AUX_SHIFT;
-	req.mode_data |= hsl_orientation(port) << PMC_USB_ALTMODE_ORI_HSL_SHIFT;
-
 	req.mode_data |= (state->mode - TYPEC_STATE_MODAL) <<
 			 PMC_USB_ALTMODE_DP_MODE_SHIFT;
 
-	if (data->status & DP_STATUS_HPD_STATE)
-		req.mode_data |= PMC_USB_ALTMODE_HPD_HIGH;
-
 	ret = pmc_usb_command(port, (void *)&req, sizeof(req));
 	if (ret)
 		return ret;
@@ -212,9 +209,6 @@ pmc_usb_mux_tbt(struct pmc_usb_port *port, struct typec_mux_state *state)
 	req.mode_data = (port->orientation - 1) << PMC_USB_ALTMODE_ORI_SHIFT;
 	req.mode_data |= (port->role - 1) << PMC_USB_ALTMODE_UFP_SHIFT;
 
-	req.mode_data |= sbu_orientation(port) << PMC_USB_ALTMODE_ORI_AUX_SHIFT;
-	req.mode_data |= hsl_orientation(port) << PMC_USB_ALTMODE_ORI_HSL_SHIFT;
-
 	if (TBT_ADAPTER(data->device_mode) == TBT_ADAPTER_TBT3)
 		req.mode_data |= PMC_USB_ALTMODE_TBT_TYPE;
 
@@ -497,6 +491,7 @@ err_remove_ports:
 	for (i = 0; i < pmc->num_ports; i++) {
 		typec_switch_unregister(pmc->port[i].typec_sw);
 		typec_mux_unregister(pmc->port[i].typec_mux);
+		usb_role_switch_unregister(pmc->port[i].usb_sw);
 	}
 
 	return ret;
@@ -510,6 +505,7 @@ static int pmc_usb_remove(struct platform_device *pdev)
 	for (i = 0; i < pmc->num_ports; i++) {
 		typec_switch_unregister(pmc->port[i].typec_sw);
 		typec_mux_unregister(pmc->port[i].typec_mux);
+		usb_role_switch_unregister(pmc->port[i].usb_sw);
 	}
 
 	return 0;
diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c
index e680fcfdee60..758b988ac518 100644
--- a/drivers/usb/typec/ucsi/ucsi.c
+++ b/drivers/usb/typec/ucsi/ucsi.c
@@ -216,14 +216,18 @@ void ucsi_altmode_update_active(struct ucsi_connector *con)
 					    con->partner_altmode[i] == altmode);
 }
 
-static u8 ucsi_altmode_next_mode(struct typec_altmode **alt, u16 svid)
+static int ucsi_altmode_next_mode(struct typec_altmode **alt, u16 svid)
 {
 	u8 mode = 1;
 	int i;
 
-	for (i = 0; alt[i]; i++)
+	for (i = 0; alt[i]; i++) {
+		if (i > MODE_DISCOVERY_MAX)
+			return -ERANGE;
+
 		if (alt[i]->svid == svid)
 			mode++;
+	}
 
 	return mode;
 }
@@ -258,8 +262,11 @@ static int ucsi_register_altmode(struct ucsi_connector *con,
 			goto err;
 		}
 
-		desc->mode = ucsi_altmode_next_mode(con->port_altmode,
-						    desc->svid);
+		ret = ucsi_altmode_next_mode(con->port_altmode, desc->svid);
+		if (ret < 0)
+			return ret;
+
+		desc->mode = ret;
 
 		switch (desc->svid) {
 		case USB_TYPEC_DP_SID:
@@ -292,8 +299,11 @@ static int ucsi_register_altmode(struct ucsi_connector *con,
 			goto err;
 		}
 
-		desc->mode = ucsi_altmode_next_mode(con->partner_altmode,
-						    desc->svid);
+		ret = ucsi_altmode_next_mode(con->partner_altmode, desc->svid);
+		if (ret < 0)
+			return ret;
+
+		desc->mode = ret;
 
 		alt = typec_partner_register_altmode(con->partner, desc);
 		if (IS_ERR(alt)) {
diff --git a/drivers/usb/typec/ucsi/ucsi_acpi.c b/drivers/usb/typec/ucsi/ucsi_acpi.c
index 9fc4f338e870..fbfe8f5933af 100644
--- a/drivers/usb/typec/ucsi/ucsi_acpi.c
+++ b/drivers/usb/typec/ucsi/ucsi_acpi.c
@@ -78,7 +78,7 @@ static int ucsi_acpi_sync_write(struct ucsi *ucsi, unsigned int offset,
 	if (ret)
 		goto out_clear_bit;
 
-	if (!wait_for_completion_timeout(&ua->complete, msecs_to_jiffies(5000)))
+	if (!wait_for_completion_timeout(&ua->complete, 60 * HZ))
 		ret = -ETIMEDOUT;
 
 out_clear_bit:
@@ -112,11 +112,15 @@ static void ucsi_acpi_notify(acpi_handle handle, u32 event, void *data)
 
 static int ucsi_acpi_probe(struct platform_device *pdev)
 {
+	struct acpi_device *adev = ACPI_COMPANION(&pdev->dev);
 	struct ucsi_acpi *ua;
 	struct resource *res;
 	acpi_status status;
 	int ret;
 
+	if (adev->dep_unmet)
+		return -EPROBE_DEFER;
+
 	ua = devm_kzalloc(&pdev->dev, sizeof(*ua), GFP_KERNEL);
 	if (!ua)
 		return -ENOMEM;
diff --git a/drivers/video/console/Kconfig b/drivers/video/console/Kconfig
index 5e850cc9f891..39deb22a4180 100644
--- a/drivers/video/console/Kconfig
+++ b/drivers/video/console/Kconfig
@@ -22,52 +22,6 @@ config VGA_CONSOLE
 
 	  Say Y.
 
-config VGACON_SOFT_SCROLLBACK
-       bool "Enable Scrollback Buffer in System RAM"
-       depends on VGA_CONSOLE
-       default n
-       help
-	 The scrollback buffer of the standard VGA console is located in
-	 the VGA RAM.  The size of this RAM is fixed and is quite small.
-	 If you require a larger scrollback buffer, this can be placed in
-	 System RAM which is dynamically allocated during initialization.
-	 Placing the scrollback buffer in System RAM will slightly slow
-	 down the console.
-
-	 If you want this feature, say 'Y' here and enter the amount of
-	 RAM to allocate for this buffer.  If unsure, say 'N'.
-
-config VGACON_SOFT_SCROLLBACK_SIZE
-       int "Scrollback Buffer Size (in KB)"
-       depends on VGACON_SOFT_SCROLLBACK
-       range 1 1024
-       default "64"
-       help
-	  Enter the amount of System RAM to allocate for scrollback
-	  buffers of VGA consoles. Each 64KB will give you approximately
-	  16 80x25 screenfuls of scrollback buffer.
-
-config VGACON_SOFT_SCROLLBACK_PERSISTENT_ENABLE_BY_DEFAULT
-	bool "Persistent Scrollback History for each console by default"
-	depends on VGACON_SOFT_SCROLLBACK
-	default n
-	help
-	  Say Y here if the scrollback history should persist by default when
-	  switching between consoles. Otherwise, the scrollback history will be
-	  flushed each time the console is switched. This feature can also be
-	  enabled using the boot command line parameter
-	  'vgacon.scrollback_persistent=1'.
-
-	  This feature might break your tool of choice to flush the scrollback
-	  buffer, e.g. clear(1) will work fine but Debian's clear_console(1)
-	  will be broken, which might cause security issues.
-	  You can use the escape sequence \e[3J instead if this feature is
-	  activated.
-
-	  Note that a buffer of VGACON_SOFT_SCROLLBACK_SIZE is taken for each
-	  created tty device.
-	  So if you use a RAM-constrained system, say N here.
-
 config MDA_CONSOLE
 	depends on !M68K && !PARISC && ISA
 	tristate "MDA text console (dual-headed)"
diff --git a/drivers/video/console/vgacon.c b/drivers/video/console/vgacon.c
index a52bb3740073..17876f0179b5 100644
--- a/drivers/video/console/vgacon.c
+++ b/drivers/video/console/vgacon.c
@@ -165,214 +165,6 @@ static inline void vga_set_mem_top(struct vc_data *c)
 	write_vga(12, (c->vc_visible_origin - vga_vram_base) / 2);
 }
 
-#ifdef CONFIG_VGACON_SOFT_SCROLLBACK
-/* software scrollback */
-struct vgacon_scrollback_info {
-	void *data;
-	int tail;
-	int size;
-	int rows;
-	int cnt;
-	int cur;
-	int save;
-	int restore;
-};
-
-static struct vgacon_scrollback_info *vgacon_scrollback_cur;
-static struct vgacon_scrollback_info vgacon_scrollbacks[MAX_NR_CONSOLES];
-static bool scrollback_persistent = \
-	IS_ENABLED(CONFIG_VGACON_SOFT_SCROLLBACK_PERSISTENT_ENABLE_BY_DEFAULT);
-module_param_named(scrollback_persistent, scrollback_persistent, bool, 0000);
-MODULE_PARM_DESC(scrollback_persistent, "Enable persistent scrollback for all vga consoles");
-
-static void vgacon_scrollback_reset(int vc_num, size_t reset_size)
-{
-	struct vgacon_scrollback_info *scrollback = &vgacon_scrollbacks[vc_num];
-
-	if (scrollback->data && reset_size > 0)
-		memset(scrollback->data, 0, reset_size);
-
-	scrollback->cnt  = 0;
-	scrollback->tail = 0;
-	scrollback->cur  = 0;
-}
-
-static void vgacon_scrollback_init(int vc_num)
-{
-	int pitch = vga_video_num_columns * 2;
-	size_t size = CONFIG_VGACON_SOFT_SCROLLBACK_SIZE * 1024;
-	int rows = size / pitch;
-	void *data;
-
-	data = kmalloc_array(CONFIG_VGACON_SOFT_SCROLLBACK_SIZE, 1024,
-			     GFP_NOWAIT);
-
-	vgacon_scrollbacks[vc_num].data = data;
-	vgacon_scrollback_cur = &vgacon_scrollbacks[vc_num];
-
-	vgacon_scrollback_cur->rows = rows - 1;
-	vgacon_scrollback_cur->size = rows * pitch;
-
-	vgacon_scrollback_reset(vc_num, size);
-}
-
-static void vgacon_scrollback_switch(int vc_num)
-{
-	if (!scrollback_persistent)
-		vc_num = 0;
-
-	if (!vgacon_scrollbacks[vc_num].data) {
-		vgacon_scrollback_init(vc_num);
-	} else {
-		if (scrollback_persistent) {
-			vgacon_scrollback_cur = &vgacon_scrollbacks[vc_num];
-		} else {
-			size_t size = CONFIG_VGACON_SOFT_SCROLLBACK_SIZE * 1024;
-
-			vgacon_scrollback_reset(vc_num, size);
-		}
-	}
-}
-
-static void vgacon_scrollback_startup(void)
-{
-	vgacon_scrollback_cur = &vgacon_scrollbacks[0];
-	vgacon_scrollback_init(0);
-}
-
-static void vgacon_scrollback_update(struct vc_data *c, int t, int count)
-{
-	void *p;
-
-	if (!vgacon_scrollback_cur->data || !vgacon_scrollback_cur->size ||
-	    c->vc_num != fg_console)
-		return;
-
-	p = (void *) (c->vc_origin + t * c->vc_size_row);
-
-	while (count--) {
-		if ((vgacon_scrollback_cur->tail + c->vc_size_row) >
-		    vgacon_scrollback_cur->size)
-			vgacon_scrollback_cur->tail = 0;
-
-		scr_memcpyw(vgacon_scrollback_cur->data +
-			    vgacon_scrollback_cur->tail,
-			    p, c->vc_size_row);
-
-		vgacon_scrollback_cur->cnt++;
-		p += c->vc_size_row;
-		vgacon_scrollback_cur->tail += c->vc_size_row;
-
-		if (vgacon_scrollback_cur->tail >= vgacon_scrollback_cur->size)
-			vgacon_scrollback_cur->tail = 0;
-
-		if (vgacon_scrollback_cur->cnt > vgacon_scrollback_cur->rows)
-			vgacon_scrollback_cur->cnt = vgacon_scrollback_cur->rows;
-
-		vgacon_scrollback_cur->cur = vgacon_scrollback_cur->cnt;
-	}
-}
-
-static void vgacon_restore_screen(struct vc_data *c)
-{
-	c->vc_origin = c->vc_visible_origin;
-	vgacon_scrollback_cur->save = 0;
-
-	if (!vga_is_gfx && !vgacon_scrollback_cur->restore) {
-		scr_memcpyw((u16 *) c->vc_origin, (u16 *) c->vc_screenbuf,
-			    c->vc_screenbuf_size > vga_vram_size ?
-			    vga_vram_size : c->vc_screenbuf_size);
-		vgacon_scrollback_cur->restore = 1;
-		vgacon_scrollback_cur->cur = vgacon_scrollback_cur->cnt;
-	}
-}
-
-static void vgacon_scrolldelta(struct vc_data *c, int lines)
-{
-	int start, end, count, soff;
-
-	if (!lines) {
-		vgacon_restore_screen(c);
-		return;
-	}
-
-	if (!vgacon_scrollback_cur->data)
-		return;
-
-	if (!vgacon_scrollback_cur->save) {
-		vgacon_cursor(c, CM_ERASE);
-		vgacon_save_screen(c);
-		c->vc_origin = (unsigned long)c->vc_screenbuf;
-		vgacon_scrollback_cur->save = 1;
-	}
-
-	vgacon_scrollback_cur->restore = 0;
-	start = vgacon_scrollback_cur->cur + lines;
-	end = start + abs(lines);
-
-	if (start < 0)
-		start = 0;
-
-	if (start > vgacon_scrollback_cur->cnt)
-		start = vgacon_scrollback_cur->cnt;
-
-	if (end < 0)
-		end = 0;
-
-	if (end > vgacon_scrollback_cur->cnt)
-		end = vgacon_scrollback_cur->cnt;
-
-	vgacon_scrollback_cur->cur = start;
-	count = end - start;
-	soff = vgacon_scrollback_cur->tail -
-		((vgacon_scrollback_cur->cnt - end) * c->vc_size_row);
-	soff -= count * c->vc_size_row;
-
-	if (soff < 0)
-		soff += vgacon_scrollback_cur->size;
-
-	count = vgacon_scrollback_cur->cnt - start;
-
-	if (count > c->vc_rows)
-		count = c->vc_rows;
-
-	if (count) {
-		int copysize;
-
-		int diff = c->vc_rows - count;
-		void *d = (void *) c->vc_visible_origin;
-		void *s = (void *) c->vc_screenbuf;
-
-		count *= c->vc_size_row;
-		/* how much memory to end of buffer left? */
-		copysize = min(count, vgacon_scrollback_cur->size - soff);
-		scr_memcpyw(d, vgacon_scrollback_cur->data + soff, copysize);
-		d += copysize;
-		count -= copysize;
-
-		if (count) {
-			scr_memcpyw(d, vgacon_scrollback_cur->data, count);
-			d += count;
-		}
-
-		if (diff)
-			scr_memcpyw(d, s, diff * c->vc_size_row);
-	} else
-		vgacon_cursor(c, CM_MOVE);
-}
-
-static void vgacon_flush_scrollback(struct vc_data *c)
-{
-	size_t size = CONFIG_VGACON_SOFT_SCROLLBACK_SIZE * 1024;
-
-	vgacon_scrollback_reset(c->vc_num, size);
-}
-#else
-#define vgacon_scrollback_startup(...) do { } while (0)
-#define vgacon_scrollback_init(...)    do { } while (0)
-#define vgacon_scrollback_update(...)  do { } while (0)
-#define vgacon_scrollback_switch(...)  do { } while (0)
-
 static void vgacon_restore_screen(struct vc_data *c)
 {
 	if (c->vc_origin != c->vc_visible_origin)
@@ -386,11 +178,6 @@ static void vgacon_scrolldelta(struct vc_data *c, int lines)
 	vga_set_mem_top(c);
 }
 
-static void vgacon_flush_scrollback(struct vc_data *c)
-{
-}
-#endif /* CONFIG_VGACON_SOFT_SCROLLBACK */
-
 static const char *vgacon_startup(void)
 {
 	const char *display_desc = NULL;
@@ -573,10 +360,7 @@ static const char *vgacon_startup(void)
 	vgacon_xres = screen_info.orig_video_cols * VGA_FONTWIDTH;
 	vgacon_yres = vga_scan_lines;
 
-	if (!vga_init_done) {
-		vgacon_scrollback_startup();
-		vga_init_done = true;
-	}
+	vga_init_done = true;
 
 	return display_desc;
 }
@@ -869,7 +653,6 @@ static int vgacon_switch(struct vc_data *c)
 			vgacon_doresize(c, c->vc_cols, c->vc_rows);
 	}
 
-	vgacon_scrollback_switch(c->vc_num);
 	return 0;		/* Redrawing not needed */
 }
 
@@ -1386,7 +1169,6 @@ static bool vgacon_scroll(struct vc_data *c, unsigned int t, unsigned int b,
 	oldo = c->vc_origin;
 	delta = lines * c->vc_size_row;
 	if (dir == SM_UP) {
-		vgacon_scrollback_update(c, t, lines);
 		if (c->vc_scr_end + delta >= vga_vram_end) {
 			scr_memcpyw((u16 *) vga_vram_base,
 				    (u16 *) (oldo + delta),
@@ -1450,7 +1232,6 @@ const struct consw vga_con = {
 	.con_save_screen = vgacon_save_screen,
 	.con_build_attr = vgacon_build_attr,
 	.con_invert_region = vgacon_invert_region,
-	.con_flush_scrollback = vgacon_flush_scrollback,
 };
 EXPORT_SYMBOL(vga_con);
 
diff --git a/drivers/video/fbdev/core/bitblit.c b/drivers/video/fbdev/core/bitblit.c
index 4e6cbc24346d..9725ecd1255b 100644
--- a/drivers/video/fbdev/core/bitblit.c
+++ b/drivers/video/fbdev/core/bitblit.c
@@ -234,7 +234,7 @@ static void bit_clear_margins(struct vc_data *vc, struct fb_info *info,
 }
 
 static void bit_cursor(struct vc_data *vc, struct fb_info *info, int mode,
-		       int softback_lines, int fg, int bg)
+		       int fg, int bg)
 {
 	struct fb_cursor cursor;
 	struct fbcon_ops *ops = info->fbcon_par;
@@ -247,15 +247,6 @@ static void bit_cursor(struct vc_data *vc, struct fb_info *info, int mode,
 
 	cursor.set = 0;
 
-	if (softback_lines) {
-		if (y + softback_lines >= vc->vc_rows) {
-			mode = CM_ERASE;
-			ops->cursor_flash = 0;
-			return;
-		} else
-			y += softback_lines;
-	}
-
  	c = scr_readw((u16 *) vc->vc_pos);
 	attribute = get_attribute(info, c);
 	src = vc->vc_font.data + ((c & charmask) * (w * vc->vc_font.height));
diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c
index 66167830fefd..41f3fa3db6d4 100644
--- a/drivers/video/fbdev/core/fbcon.c
+++ b/drivers/video/fbdev/core/fbcon.c
@@ -122,12 +122,6 @@ static int logo_lines;
 /* logo_shown is an index to vc_cons when >= 0; otherwise follows FBCON_LOGO
    enums.  */
 static int logo_shown = FBCON_LOGO_CANSHOW;
-/* Software scrollback */
-static int fbcon_softback_size = 32768;
-static unsigned long softback_buf, softback_curr;
-static unsigned long softback_in;
-static unsigned long softback_top, softback_end;
-static int softback_lines;
 /* console mappings */
 static int first_fb_vc;
 static int last_fb_vc = MAX_NR_CONSOLES - 1;
@@ -167,8 +161,6 @@ static int margin_color;
 
 static const struct consw fb_con;
 
-#define CM_SOFTBACK	(8)
-
 #define advance_row(p, delta) (unsigned short *)((unsigned long)(p) + (delta) * vc->vc_size_row)
 
 static int fbcon_set_origin(struct vc_data *);
@@ -373,18 +365,6 @@ static int get_color(struct vc_data *vc, struct fb_info *info,
 	return color;
 }
 
-static void fbcon_update_softback(struct vc_data *vc)
-{
-	int l = fbcon_softback_size / vc->vc_size_row;
-
-	if (l > 5)
-		softback_end = softback_buf + l * vc->vc_size_row;
-	else
-		/* Smaller scrollback makes no sense, and 0 would screw
-		   the operation totally */
-		softback_top = 0;
-}
-
 static void fb_flashcursor(struct work_struct *work)
 {
 	struct fb_info *info = container_of(work, struct fb_info, queue);
@@ -414,7 +394,7 @@ static void fb_flashcursor(struct work_struct *work)
 	c = scr_readw((u16 *) vc->vc_pos);
 	mode = (!ops->cursor_flash || ops->cursor_state.enable) ?
 		CM_ERASE : CM_DRAW;
-	ops->cursor(vc, info, mode, softback_lines, get_color(vc, info, c, 1),
+	ops->cursor(vc, info, mode, get_color(vc, info, c, 1),
 		    get_color(vc, info, c, 0));
 	console_unlock();
 }
@@ -471,13 +451,7 @@ static int __init fb_console_setup(char *this_opt)
 		}
 		
 		if (!strncmp(options, "scrollback:", 11)) {
-			options += 11;
-			if (*options) {
-				fbcon_softback_size = simple_strtoul(options, &options, 0);
-				if (*options == 'k' || *options == 'K') {
-					fbcon_softback_size *= 1024;
-				}
-			}
+			pr_warn("Ignoring scrollback size option\n");
 			continue;
 		}
 		
@@ -1022,31 +996,6 @@ static const char *fbcon_startup(void)
 
 	set_blitting_type(vc, info);
 
-	if (info->fix.type != FB_TYPE_TEXT) {
-		if (fbcon_softback_size) {
-			if (!softback_buf) {
-				softback_buf =
-				    (unsigned long)
-				    kvmalloc(fbcon_softback_size,
-					    GFP_KERNEL);
-				if (!softback_buf) {
-					fbcon_softback_size = 0;
-					softback_top = 0;
-				}
-			}
-		} else {
-			if (softback_buf) {
-				kvfree((void *) softback_buf);
-				softback_buf = 0;
-				softback_top = 0;
-			}
-		}
-		if (softback_buf)
-			softback_in = softback_top = softback_curr =
-			    softback_buf;
-		softback_lines = 0;
-	}
-
 	/* Setup default font */
 	if (!p->fontdata && !vc->vc_font.data) {
 		if (!fontname[0] || !(font = find_font(fontname)))
@@ -1220,9 +1169,6 @@ static void fbcon_init(struct vc_data *vc, int init)
 	if (logo)
 		fbcon_prepare_logo(vc, info, cols, rows, new_cols, new_rows);
 
-	if (vc == svc && softback_buf)
-		fbcon_update_softback(vc);
-
 	if (ops->rotate_font && ops->rotate_font(info, vc)) {
 		ops->rotate = FB_ROTATE_UR;
 		set_blitting_type(vc, info);
@@ -1385,7 +1331,6 @@ static void fbcon_cursor(struct vc_data *vc, int mode)
 {
 	struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]];
 	struct fbcon_ops *ops = info->fbcon_par;
-	int y;
  	int c = scr_readw((u16 *) vc->vc_pos);
 
 	ops->cur_blink_jiffies = msecs_to_jiffies(vc->vc_cur_blink_ms);
@@ -1399,16 +1344,8 @@ static void fbcon_cursor(struct vc_data *vc, int mode)
 		fbcon_add_cursor_timer(info);
 
 	ops->cursor_flash = (mode == CM_ERASE) ? 0 : 1;
-	if (mode & CM_SOFTBACK) {
-		mode &= ~CM_SOFTBACK;
-		y = softback_lines;
-	} else {
-		if (softback_lines)
-			fbcon_set_origin(vc);
-		y = 0;
-	}
 
-	ops->cursor(vc, info, mode, y, get_color(vc, info, c, 1),
+	ops->cursor(vc, info, mode, get_color(vc, info, c, 1),
 		    get_color(vc, info, c, 0));
 }
 
@@ -1479,8 +1416,6 @@ static void fbcon_set_disp(struct fb_info *info, struct fb_var_screeninfo *var,
 
 	if (con_is_visible(vc)) {
 		update_screen(vc);
-		if (softback_buf)
-			fbcon_update_softback(vc);
 	}
 }
 
@@ -1618,99 +1553,6 @@ static __inline__ void ypan_down_redraw(struct vc_data *vc, int t, int count)
 	scrollback_current = 0;
 }
 
-static void fbcon_redraw_softback(struct vc_data *vc, struct fbcon_display *p,
-				  long delta)
-{
-	int count = vc->vc_rows;
-	unsigned short *d, *s;
-	unsigned long n;
-	int line = 0;
-
-	d = (u16 *) softback_curr;
-	if (d == (u16 *) softback_in)
-		d = (u16 *) vc->vc_origin;
-	n = softback_curr + delta * vc->vc_size_row;
-	softback_lines -= delta;
-	if (delta < 0) {
-		if (softback_curr < softback_top && n < softback_buf) {
-			n += softback_end - softback_buf;
-			if (n < softback_top) {
-				softback_lines -=
-				    (softback_top - n) / vc->vc_size_row;
-				n = softback_top;
-			}
-		} else if (softback_curr >= softback_top
-			   && n < softback_top) {
-			softback_lines -=
-			    (softback_top - n) / vc->vc_size_row;
-			n = softback_top;
-		}
-	} else {
-		if (softback_curr > softback_in && n >= softback_end) {
-			n += softback_buf - softback_end;
-			if (n > softback_in) {
-				n = softback_in;
-				softback_lines = 0;
-			}
-		} else if (softback_curr <= softback_in && n > softback_in) {
-			n = softback_in;
-			softback_lines = 0;
-		}
-	}
-	if (n == softback_curr)
-		return;
-	softback_curr = n;
-	s = (u16 *) softback_curr;
-	if (s == (u16 *) softback_in)
-		s = (u16 *) vc->vc_origin;
-	while (count--) {
-		unsigned short *start;
-		unsigned short *le;
-		unsigned short c;
-		int x = 0;
-		unsigned short attr = 1;
-
-		start = s;
-		le = advance_row(s, 1);
-		do {
-			c = scr_readw(s);
-			if (attr != (c & 0xff00)) {
-				attr = c & 0xff00;
-				if (s > start) {
-					fbcon_putcs(vc, start, s - start,
-						    line, x);
-					x += s - start;
-					start = s;
-				}
-			}
-			if (c == scr_readw(d)) {
-				if (s > start) {
-					fbcon_putcs(vc, start, s - start,
-						    line, x);
-					x += s - start + 1;
-					start = s + 1;
-				} else {
-					x++;
-					start++;
-				}
-			}
-			s++;
-			d++;
-		} while (s < le);
-		if (s > start)
-			fbcon_putcs(vc, start, s - start, line, x);
-		line++;
-		if (d == (u16 *) softback_end)
-			d = (u16 *) softback_buf;
-		if (d == (u16 *) softback_in)
-			d = (u16 *) vc->vc_origin;
-		if (s == (u16 *) softback_end)
-			s = (u16 *) softback_buf;
-		if (s == (u16 *) softback_in)
-			s = (u16 *) vc->vc_origin;
-	}
-}
-
 static void fbcon_redraw_move(struct vc_data *vc, struct fbcon_display *p,
 			      int line, int count, int dy)
 {
@@ -1850,31 +1692,6 @@ static void fbcon_redraw(struct vc_data *vc, struct fbcon_display *p,
 	}
 }
 
-static inline void fbcon_softback_note(struct vc_data *vc, int t,
-				       int count)
-{
-	unsigned short *p;
-
-	if (vc->vc_num != fg_console)
-		return;
-	p = (unsigned short *) (vc->vc_origin + t * vc->vc_size_row);
-
-	while (count) {
-		scr_memcpyw((u16 *) softback_in, p, vc->vc_size_row);
-		count--;
-		p = advance_row(p, 1);
-		softback_in += vc->vc_size_row;
-		if (softback_in == softback_end)
-			softback_in = softback_buf;
-		if (softback_in == softback_top) {
-			softback_top += vc->vc_size_row;
-			if (softback_top == softback_end)
-				softback_top = softback_buf;
-		}
-	}
-	softback_curr = softback_in;
-}
-
 static bool fbcon_scroll(struct vc_data *vc, unsigned int t, unsigned int b,
 		enum con_scroll dir, unsigned int count)
 {
@@ -1897,8 +1714,6 @@ static bool fbcon_scroll(struct vc_data *vc, unsigned int t, unsigned int b,
 	case SM_UP:
 		if (count > vc->vc_rows)	/* Maximum realistic size */
 			count = vc->vc_rows;
-		if (softback_top)
-			fbcon_softback_note(vc, t, count);
 		if (logo_shown >= 0)
 			goto redraw_up;
 		switch (p->scrollmode) {
@@ -2203,7 +2018,7 @@ static int fbcon_resize(struct vc_data *vc, unsigned int width,
 	struct fb_var_screeninfo var = info->var;
 	int x_diff, y_diff, virt_w, virt_h, virt_fw, virt_fh;
 
-	if (ops->p && ops->p->userfont && FNTSIZE(vc->vc_font.data)) {
+	if (p->userfont && FNTSIZE(vc->vc_font.data)) {
 		int size;
 		int pitch = PITCH(vc->vc_font.width);
 
@@ -2269,14 +2084,6 @@ static int fbcon_switch(struct vc_data *vc)
 	info = registered_fb[con2fb_map[vc->vc_num]];
 	ops = info->fbcon_par;
 
-	if (softback_top) {
-		if (softback_lines)
-			fbcon_set_origin(vc);
-		softback_top = softback_curr = softback_in = softback_buf;
-		softback_lines = 0;
-		fbcon_update_softback(vc);
-	}
-
 	if (logo_shown >= 0) {
 		struct vc_data *conp2 = vc_cons[logo_shown].d;
 
@@ -2600,9 +2407,6 @@ static int fbcon_do_set_font(struct vc_data *vc, int w, int h,
 	int cnt;
 	char *old_data = NULL;
 
-	if (con_is_visible(vc) && softback_lines)
-		fbcon_set_origin(vc);
-
 	resize = (w != vc->vc_font.width) || (h != vc->vc_font.height);
 	if (p->userfont)
 		old_data = vc->vc_font.data;
@@ -2628,8 +2432,6 @@ static int fbcon_do_set_font(struct vc_data *vc, int w, int h,
 		cols /= w;
 		rows /= h;
 		vc_resize(vc, cols, rows);
-		if (con_is_visible(vc) && softback_buf)
-			fbcon_update_softback(vc);
 	} else if (con_is_visible(vc)
 		   && vc->vc_mode == KD_TEXT) {
 		fbcon_clear_margins(vc, 0);
@@ -2788,19 +2590,7 @@ static void fbcon_set_palette(struct vc_data *vc, const unsigned char *table)
 
 static u16 *fbcon_screen_pos(struct vc_data *vc, int offset)
 {
-	unsigned long p;
-	int line;
-	
-	if (vc->vc_num != fg_console || !softback_lines)
-		return (u16 *) (vc->vc_origin + offset);
-	line = offset / vc->vc_size_row;
-	if (line >= softback_lines)
-		return (u16 *) (vc->vc_origin + offset -
-				softback_lines * vc->vc_size_row);
-	p = softback_curr + offset;
-	if (p >= softback_end)
-		p += softback_buf - softback_end;
-	return (u16 *) p;
+	return (u16 *) (vc->vc_origin + offset);
 }
 
 static unsigned long fbcon_getxy(struct vc_data *vc, unsigned long pos,
@@ -2814,22 +2604,7 @@ static unsigned long fbcon_getxy(struct vc_data *vc, unsigned long pos,
 
 		x = offset % vc->vc_cols;
 		y = offset / vc->vc_cols;
-		if (vc->vc_num == fg_console)
-			y += softback_lines;
 		ret = pos + (vc->vc_cols - x) * 2;
-	} else if (vc->vc_num == fg_console && softback_lines) {
-		unsigned long offset = pos - softback_curr;
-
-		if (pos < softback_curr)
-			offset += softback_end - softback_buf;
-		offset /= 2;
-		x = offset % vc->vc_cols;
-		y = offset / vc->vc_cols;
-		ret = pos + (vc->vc_cols - x) * 2;
-		if (ret == softback_end)
-			ret = softback_buf;
-		if (ret == softback_in)
-			ret = vc->vc_origin;
 	} else {
 		/* Should not happen */
 		x = y = 0;
@@ -2857,106 +2632,11 @@ static void fbcon_invert_region(struct vc_data *vc, u16 * p, int cnt)
 			a = ((a) & 0x88ff) | (((a) & 0x7000) >> 4) |
 			    (((a) & 0x0700) << 4);
 		scr_writew(a, p++);
-		if (p == (u16 *) softback_end)
-			p = (u16 *) softback_buf;
-		if (p == (u16 *) softback_in)
-			p = (u16 *) vc->vc_origin;
-	}
-}
-
-static void fbcon_scrolldelta(struct vc_data *vc, int lines)
-{
-	struct fb_info *info = registered_fb[con2fb_map[fg_console]];
-	struct fbcon_ops *ops = info->fbcon_par;
-	struct fbcon_display *disp = &fb_display[fg_console];
-	int offset, limit, scrollback_old;
-
-	if (softback_top) {
-		if (vc->vc_num != fg_console)
-			return;
-		if (vc->vc_mode != KD_TEXT || !lines)
-			return;
-		if (logo_shown >= 0) {
-			struct vc_data *conp2 = vc_cons[logo_shown].d;
-
-			if (conp2->vc_top == logo_lines
-			    && conp2->vc_bottom == conp2->vc_rows)
-				conp2->vc_top = 0;
-			if (logo_shown == vc->vc_num) {
-				unsigned long p, q;
-				int i;
-
-				p = softback_in;
-				q = vc->vc_origin +
-				    logo_lines * vc->vc_size_row;
-				for (i = 0; i < logo_lines; i++) {
-					if (p == softback_top)
-						break;
-					if (p == softback_buf)
-						p = softback_end;
-					p -= vc->vc_size_row;
-					q -= vc->vc_size_row;
-					scr_memcpyw((u16 *) q, (u16 *) p,
-						    vc->vc_size_row);
-				}
-				softback_in = softback_curr = p;
-				update_region(vc, vc->vc_origin,
-					      logo_lines * vc->vc_cols);
-			}
-			logo_shown = FBCON_LOGO_CANSHOW;
-		}
-		fbcon_cursor(vc, CM_ERASE | CM_SOFTBACK);
-		fbcon_redraw_softback(vc, disp, lines);
-		fbcon_cursor(vc, CM_DRAW | CM_SOFTBACK);
-		return;
 	}
-
-	if (!scrollback_phys_max)
-		return;
-
-	scrollback_old = scrollback_current;
-	scrollback_current -= lines;
-	if (scrollback_current < 0)
-		scrollback_current = 0;
-	else if (scrollback_current > scrollback_max)
-		scrollback_current = scrollback_max;
-	if (scrollback_current == scrollback_old)
-		return;
-
-	if (fbcon_is_inactive(vc, info))
-		return;
-
-	fbcon_cursor(vc, CM_ERASE);
-
-	offset = disp->yscroll - scrollback_current;
-	limit = disp->vrows;
-	switch (disp->scrollmode) {
-	case SCROLL_WRAP_MOVE:
-		info->var.vmode |= FB_VMODE_YWRAP;
-		break;
-	case SCROLL_PAN_MOVE:
-	case SCROLL_PAN_REDRAW:
-		limit -= vc->vc_rows;
-		info->var.vmode &= ~FB_VMODE_YWRAP;
-		break;
-	}
-	if (offset < 0)
-		offset += limit;
-	else if (offset >= limit)
-		offset -= limit;
-
-	ops->var.xoffset = 0;
-	ops->var.yoffset = offset * vc->vc_font.height;
-	ops->update_start(info);
-
-	if (!scrollback_current)
-		fbcon_cursor(vc, CM_DRAW);
 }
 
 static int fbcon_set_origin(struct vc_data *vc)
 {
-	if (softback_lines)
-		fbcon_scrolldelta(vc, softback_lines);
 	return 0;
 }
 
@@ -3020,8 +2700,6 @@ static void fbcon_modechanged(struct fb_info *info)
 
 		fbcon_set_palette(vc, color_table);
 		update_screen(vc);
-		if (softback_buf)
-			fbcon_update_softback(vc);
 	}
 }
 
@@ -3432,7 +3110,6 @@ static const struct consw fb_con = {
 	.con_font_default	= fbcon_set_def_font,
 	.con_font_copy 		= fbcon_copy_font,
 	.con_set_palette 	= fbcon_set_palette,
-	.con_scrolldelta 	= fbcon_scrolldelta,
 	.con_set_origin 	= fbcon_set_origin,
 	.con_invert_region 	= fbcon_invert_region,
 	.con_screen_pos 	= fbcon_screen_pos,
@@ -3667,9 +3344,6 @@ static void fbcon_exit(void)
 	}
 #endif
 
-	kvfree((void *)softback_buf);
-	softback_buf = 0UL;
-
 	for_each_registered_fb(i) {
 		int pending = 0;
 
diff --git a/drivers/video/fbdev/core/fbcon.h b/drivers/video/fbdev/core/fbcon.h
index 20dea853765f..78bb14c03643 100644
--- a/drivers/video/fbdev/core/fbcon.h
+++ b/drivers/video/fbdev/core/fbcon.h
@@ -62,7 +62,7 @@ struct fbcon_ops {
 	void (*clear_margins)(struct vc_data *vc, struct fb_info *info,
 			      int color, int bottom_only);
 	void (*cursor)(struct vc_data *vc, struct fb_info *info, int mode,
-		       int softback_lines, int fg, int bg);
+		       int fg, int bg);
 	int  (*update_start)(struct fb_info *info);
 	int  (*rotate_font)(struct fb_info *info, struct vc_data *vc);
 	struct fb_var_screeninfo var;  /* copy of the current fb_var_screeninfo */
diff --git a/drivers/video/fbdev/core/fbcon_ccw.c b/drivers/video/fbdev/core/fbcon_ccw.c
index 5b177131e062..bbd869efd03b 100644
--- a/drivers/video/fbdev/core/fbcon_ccw.c
+++ b/drivers/video/fbdev/core/fbcon_ccw.c
@@ -219,7 +219,7 @@ static void ccw_clear_margins(struct vc_data *vc, struct fb_info *info,
 }
 
 static void ccw_cursor(struct vc_data *vc, struct fb_info *info, int mode,
-		       int softback_lines, int fg, int bg)
+		       int fg, int bg)
 {
 	struct fb_cursor cursor;
 	struct fbcon_ops *ops = info->fbcon_par;
@@ -236,15 +236,6 @@ static void ccw_cursor(struct vc_data *vc, struct fb_info *info, int mode,
 
 	cursor.set = 0;
 
-	if (softback_lines) {
-		if (y + softback_lines >= vc->vc_rows) {
-			mode = CM_ERASE;
-			ops->cursor_flash = 0;
-			return;
-		} else
-			y += softback_lines;
-	}
-
  	c = scr_readw((u16 *) vc->vc_pos);
 	attribute = get_attribute(info, c);
 	src = ops->fontbuffer + ((c & charmask) * (w * vc->vc_font.width));
diff --git a/drivers/video/fbdev/core/fbcon_cw.c b/drivers/video/fbdev/core/fbcon_cw.c
index 894d01a62f30..a34cbe8e9874 100644
--- a/drivers/video/fbdev/core/fbcon_cw.c
+++ b/drivers/video/fbdev/core/fbcon_cw.c
@@ -202,7 +202,7 @@ static void cw_clear_margins(struct vc_data *vc, struct fb_info *info,
 }
 
 static void cw_cursor(struct vc_data *vc, struct fb_info *info, int mode,
-		      int softback_lines, int fg, int bg)
+		      int fg, int bg)
 {
 	struct fb_cursor cursor;
 	struct fbcon_ops *ops = info->fbcon_par;
@@ -219,15 +219,6 @@ static void cw_cursor(struct vc_data *vc, struct fb_info *info, int mode,
 
 	cursor.set = 0;
 
-	if (softback_lines) {
-		if (y + softback_lines >= vc->vc_rows) {
-			mode = CM_ERASE;
-			ops->cursor_flash = 0;
-			return;
-		} else
-			y += softback_lines;
-	}
-
  	c = scr_readw((u16 *) vc->vc_pos);
 	attribute = get_attribute(info, c);
 	src = ops->fontbuffer + ((c & charmask) * (w * vc->vc_font.width));
diff --git a/drivers/video/fbdev/core/fbcon_ud.c b/drivers/video/fbdev/core/fbcon_ud.c
index 01b87f278d79..199cbc7abe35 100644
--- a/drivers/video/fbdev/core/fbcon_ud.c
+++ b/drivers/video/fbdev/core/fbcon_ud.c
@@ -249,7 +249,7 @@ static void ud_clear_margins(struct vc_data *vc, struct fb_info *info,
 }
 
 static void ud_cursor(struct vc_data *vc, struct fb_info *info, int mode,
-		      int softback_lines, int fg, int bg)
+		      int fg, int bg)
 {
 	struct fb_cursor cursor;
 	struct fbcon_ops *ops = info->fbcon_par;
@@ -267,15 +267,6 @@ static void ud_cursor(struct vc_data *vc, struct fb_info *info, int mode,
 
 	cursor.set = 0;
 
-	if (softback_lines) {
-		if (y + softback_lines >= vc->vc_rows) {
-			mode = CM_ERASE;
-			ops->cursor_flash = 0;
-			return;
-		} else
-			y += softback_lines;
-	}
-
  	c = scr_readw((u16 *) vc->vc_pos);
 	attribute = get_attribute(info, c);
 	src = ops->fontbuffer + ((c & charmask) * (w * vc->vc_font.height));
diff --git a/drivers/video/fbdev/core/tileblit.c b/drivers/video/fbdev/core/tileblit.c
index 1dfaff0881fb..31b85b71cc37 100644
--- a/drivers/video/fbdev/core/tileblit.c
+++ b/drivers/video/fbdev/core/tileblit.c
@@ -80,7 +80,7 @@ static void tile_clear_margins(struct vc_data *vc, struct fb_info *info,
 }
 
 static void tile_cursor(struct vc_data *vc, struct fb_info *info, int mode,
-			int softback_lines, int fg, int bg)
+			int fg, int bg)
 {
 	struct fb_tilecursor cursor;
 	int use_sw = vc->vc_cursor_type & CUR_SW;
diff --git a/drivers/video/fbdev/vga16fb.c b/drivers/video/fbdev/vga16fb.c
index a20eeb8308ff..578d3541e3d6 100644
--- a/drivers/video/fbdev/vga16fb.c
+++ b/drivers/video/fbdev/vga16fb.c
@@ -1121,7 +1121,7 @@ static void vga_8planes_imageblit(struct fb_info *info, const struct fb_image *i
         char oldop = setop(0);
         char oldsr = setsr(0);
         char oldmask = selectmask();
-        const char *cdat = image->data;
+	const unsigned char *cdat = image->data;
 	u32 dx = image->dx;
         char __iomem *where;
         int y;
diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig
index ea6c1e7e3e42..41645fe6ad48 100644
--- a/drivers/xen/Kconfig
+++ b/drivers/xen/Kconfig
@@ -325,4 +325,14 @@ config XEN_HAVE_VPMU
 config XEN_FRONT_PGDIR_SHBUF
 	tristate
 
+config XEN_UNPOPULATED_ALLOC
+	bool "Use unpopulated memory ranges for guest mappings"
+	depends on X86 && ZONE_DEVICE
+	default XEN_BACKEND || XEN_GNTDEV || XEN_DOM0
+	help
+	  Use unpopulated memory ranges in order to create mappings for guest
+	  memory regions, including grant maps and foreign pages. This avoids
+	  having to balloon out RAM regions in order to obtain physical memory
+	  space to create such mappings.
+
 endmenu
diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile
index c25c9a699b48..babdca808861 100644
--- a/drivers/xen/Makefile
+++ b/drivers/xen/Makefile
@@ -41,3 +41,4 @@ xen-gntdev-$(CONFIG_XEN_GNTDEV_DMABUF)	+= gntdev-dmabuf.o
 xen-gntalloc-y				:= gntalloc.o
 xen-privcmd-y				:= privcmd.o privcmd-buf.o
 obj-$(CONFIG_XEN_FRONT_PGDIR_SHBUF)	+= xen-front-pgdir-shbuf.o
+obj-$(CONFIG_XEN_UNPOPULATED_ALLOC)	+= unpopulated-alloc.o
diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index 37ffccda8bb8..51427c752b37 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -653,7 +653,7 @@ void free_xenballooned_pages(int nr_pages, struct page **pages)
 }
 EXPORT_SYMBOL(free_xenballooned_pages);
 
-#ifdef CONFIG_XEN_PV
+#if defined(CONFIG_XEN_PV) && !defined(CONFIG_XEN_UNPOPULATED_ALLOC)
 static void __init balloon_add_region(unsigned long start_pfn,
 				      unsigned long pages)
 {
@@ -707,7 +707,7 @@ static int __init balloon_init(void)
 	register_sysctl_table(xen_root);
 #endif
 
-#ifdef CONFIG_XEN_PV
+#if defined(CONFIG_XEN_PV) && !defined(CONFIG_XEN_UNPOPULATED_ALLOC)
 	{
 		int i;
 
diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c
index 8d06bf1cc347..523dcdf39cc9 100644
--- a/drivers/xen/grant-table.c
+++ b/drivers/xen/grant-table.c
@@ -801,7 +801,7 @@ int gnttab_alloc_pages(int nr_pages, struct page **pages)
 {
 	int ret;
 
-	ret = alloc_xenballooned_pages(nr_pages, pages);
+	ret = xen_alloc_unpopulated_pages(nr_pages, pages);
 	if (ret < 0)
 		return ret;
 
@@ -836,7 +836,7 @@ EXPORT_SYMBOL_GPL(gnttab_pages_clear_private);
 void gnttab_free_pages(int nr_pages, struct page **pages)
 {
 	gnttab_pages_clear_private(nr_pages, pages);
-	free_xenballooned_pages(nr_pages, pages);
+	xen_free_unpopulated_pages(nr_pages, pages);
 }
 EXPORT_SYMBOL_GPL(gnttab_free_pages);
 
diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c
index 63abe6c3642b..b0c73c58f987 100644
--- a/drivers/xen/privcmd.c
+++ b/drivers/xen/privcmd.c
@@ -424,7 +424,7 @@ static int alloc_empty_pages(struct vm_area_struct *vma, int numpgs)
 	if (pages == NULL)
 		return -ENOMEM;
 
-	rc = alloc_xenballooned_pages(numpgs, pages);
+	rc = xen_alloc_unpopulated_pages(numpgs, pages);
 	if (rc != 0) {
 		pr_warn("%s Could not alloc %d pfns rc:%d\n", __func__,
 			numpgs, rc);
@@ -895,7 +895,7 @@ static void privcmd_close(struct vm_area_struct *vma)
 
 	rc = xen_unmap_domain_gfn_range(vma, numgfns, pages);
 	if (rc == 0)
-		free_xenballooned_pages(numpgs, pages);
+		xen_free_unpopulated_pages(numpgs, pages);
 	else
 		pr_crit("unable to unmap MFN range: leaking %d pages. rc=%d\n",
 			numpgs, rc);
diff --git a/drivers/xen/unpopulated-alloc.c b/drivers/xen/unpopulated-alloc.c
new file mode 100644
index 000000000000..3b98dc921426
--- /dev/null
+++ b/drivers/xen/unpopulated-alloc.c
@@ -0,0 +1,183 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/errno.h>
+#include <linux/gfp.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/memremap.h>
+#include <linux/slab.h>
+
+#include <asm/page.h>
+
+#include <xen/page.h>
+#include <xen/xen.h>
+
+static DEFINE_MUTEX(list_lock);
+static LIST_HEAD(page_list);
+static unsigned int list_count;
+
+static int fill_list(unsigned int nr_pages)
+{
+	struct dev_pagemap *pgmap;
+	void *vaddr;
+	unsigned int i, alloc_pages = round_up(nr_pages, PAGES_PER_SECTION);
+	int ret;
+
+	pgmap = kzalloc(sizeof(*pgmap), GFP_KERNEL);
+	if (!pgmap)
+		return -ENOMEM;
+
+	pgmap->type = MEMORY_DEVICE_GENERIC;
+	pgmap->res.name = "Xen scratch";
+	pgmap->res.flags = IORESOURCE_MEM | IORESOURCE_BUSY;
+
+	ret = allocate_resource(&iomem_resource, &pgmap->res,
+				alloc_pages * PAGE_SIZE, 0, -1,
+				PAGES_PER_SECTION * PAGE_SIZE, NULL, NULL);
+	if (ret < 0) {
+		pr_err("Cannot allocate new IOMEM resource\n");
+		kfree(pgmap);
+		return ret;
+	}
+
+#ifdef CONFIG_XEN_HAVE_PVMMU
+        /*
+         * memremap will build page tables for the new memory so
+         * the p2m must contain invalid entries so the correct
+         * non-present PTEs will be written.
+         *
+         * If a failure occurs, the original (identity) p2m entries
+         * are not restored since this region is now known not to
+         * conflict with any devices.
+         */
+	if (!xen_feature(XENFEAT_auto_translated_physmap)) {
+		xen_pfn_t pfn = PFN_DOWN(pgmap->res.start);
+
+		for (i = 0; i < alloc_pages; i++) {
+			if (!set_phys_to_machine(pfn + i, INVALID_P2M_ENTRY)) {
+				pr_warn("set_phys_to_machine() failed, no memory added\n");
+				release_resource(&pgmap->res);
+				kfree(pgmap);
+				return -ENOMEM;
+			}
+                }
+	}
+#endif
+
+	vaddr = memremap_pages(pgmap, NUMA_NO_NODE);
+	if (IS_ERR(vaddr)) {
+		pr_err("Cannot remap memory range\n");
+		release_resource(&pgmap->res);
+		kfree(pgmap);
+		return PTR_ERR(vaddr);
+	}
+
+	for (i = 0; i < alloc_pages; i++) {
+		struct page *pg = virt_to_page(vaddr + PAGE_SIZE * i);
+
+		BUG_ON(!virt_addr_valid(vaddr + PAGE_SIZE * i));
+		list_add(&pg->lru, &page_list);
+		list_count++;
+	}
+
+	return 0;
+}
+
+/**
+ * xen_alloc_unpopulated_pages - alloc unpopulated pages
+ * @nr_pages: Number of pages
+ * @pages: pages returned
+ * @return 0 on success, error otherwise
+ */
+int xen_alloc_unpopulated_pages(unsigned int nr_pages, struct page **pages)
+{
+	unsigned int i;
+	int ret = 0;
+
+	mutex_lock(&list_lock);
+	if (list_count < nr_pages) {
+		ret = fill_list(nr_pages - list_count);
+		if (ret)
+			goto out;
+	}
+
+	for (i = 0; i < nr_pages; i++) {
+		struct page *pg = list_first_entry_or_null(&page_list,
+							   struct page,
+							   lru);
+
+		BUG_ON(!pg);
+		list_del(&pg->lru);
+		list_count--;
+		pages[i] = pg;
+
+#ifdef CONFIG_XEN_HAVE_PVMMU
+		if (!xen_feature(XENFEAT_auto_translated_physmap)) {
+			ret = xen_alloc_p2m_entry(page_to_pfn(pg));
+			if (ret < 0) {
+				unsigned int j;
+
+				for (j = 0; j <= i; j++) {
+					list_add(&pages[j]->lru, &page_list);
+					list_count++;
+				}
+				goto out;
+			}
+		}
+#endif
+	}
+
+out:
+	mutex_unlock(&list_lock);
+	return ret;
+}
+EXPORT_SYMBOL(xen_alloc_unpopulated_pages);
+
+/**
+ * xen_free_unpopulated_pages - return unpopulated pages
+ * @nr_pages: Number of pages
+ * @pages: pages to return
+ */
+void xen_free_unpopulated_pages(unsigned int nr_pages, struct page **pages)
+{
+	unsigned int i;
+
+	mutex_lock(&list_lock);
+	for (i = 0; i < nr_pages; i++) {
+		list_add(&pages[i]->lru, &page_list);
+		list_count++;
+	}
+	mutex_unlock(&list_lock);
+}
+EXPORT_SYMBOL(xen_free_unpopulated_pages);
+
+#ifdef CONFIG_XEN_PV
+static int __init init(void)
+{
+	unsigned int i;
+
+	if (!xen_domain())
+		return -ENODEV;
+
+	if (!xen_pv_domain())
+		return 0;
+
+	/*
+	 * Initialize with pages from the extra memory regions (see
+	 * arch/x86/xen/setup.c).
+	 */
+	for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) {
+		unsigned int j;
+
+		for (j = 0; j < xen_extra_mem[i].n_pfns; j++) {
+			struct page *pg =
+				pfn_to_page(xen_extra_mem[i].start_pfn + j);
+
+			list_add(&pg->lru, &page_list);
+			list_count++;
+		}
+	}
+
+	return 0;
+}
+subsys_initcall(init);
+#endif
diff --git a/drivers/xen/xenbus/xenbus_client.c b/drivers/xen/xenbus/xenbus_client.c
index 907bcbb93afb..2690318ad50f 100644
--- a/drivers/xen/xenbus/xenbus_client.c
+++ b/drivers/xen/xenbus/xenbus_client.c
@@ -621,7 +621,7 @@ static int xenbus_map_ring_hvm(struct xenbus_device *dev,
 	bool leaked = false;
 	unsigned int nr_pages = XENBUS_PAGES(nr_grefs);
 
-	err = alloc_xenballooned_pages(nr_pages, node->hvm.pages);
+	err = xen_alloc_unpopulated_pages(nr_pages, node->hvm.pages);
 	if (err)
 		goto out_err;
 
@@ -662,7 +662,7 @@ static int xenbus_map_ring_hvm(struct xenbus_device *dev,
 			 addr, nr_pages);
  out_free_ballooned_pages:
 	if (!leaked)
-		free_xenballooned_pages(nr_pages, node->hvm.pages);
+		xen_free_unpopulated_pages(nr_pages, node->hvm.pages);
  out_err:
 	return err;
 }
@@ -858,7 +858,7 @@ static int xenbus_unmap_ring_hvm(struct xenbus_device *dev, void *vaddr)
 			       info.addrs);
 	if (!rv) {
 		vunmap(vaddr);
-		free_xenballooned_pages(nr_pages, node->hvm.pages);
+		xen_free_unpopulated_pages(nr_pages, node->hvm.pages);
 	}
 	else
 		WARN(1, "Leaking %p, size %u page(s)\n", vaddr, nr_pages);
diff --git a/drivers/xen/xlate_mmu.c b/drivers/xen/xlate_mmu.c
index 7b1077f0abcb..34742c6e189e 100644
--- a/drivers/xen/xlate_mmu.c
+++ b/drivers/xen/xlate_mmu.c
@@ -232,7 +232,7 @@ int __init xen_xlate_map_ballooned_pages(xen_pfn_t **gfns, void **virt,
 		kfree(pages);
 		return -ENOMEM;
 	}
-	rc = alloc_xenballooned_pages(nr_pages, pages);
+	rc = xen_alloc_unpopulated_pages(nr_pages, pages);
 	if (rc) {
 		pr_warn("%s Couldn't balloon alloc %ld pages rc:%d\n", __func__,
 			nr_pages, rc);
@@ -249,7 +249,7 @@ int __init xen_xlate_map_ballooned_pages(xen_pfn_t **gfns, void **virt,
 	if (!vaddr) {
 		pr_warn("%s Couldn't map %ld pages rc:%d\n", __func__,
 			nr_pages, rc);
-		free_xenballooned_pages(nr_pages, pages);
+		xen_free_unpopulated_pages(nr_pages, pages);
 		kfree(pages);
 		kfree(pfns);
 		return -ENOMEM;
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index f6bba7eb1fa1..abf86b202b43 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3418,6 +3418,8 @@ fail_block_groups:
 	btrfs_put_block_group_cache(fs_info);
 
 fail_tree_roots:
+	if (fs_info->data_reloc_root)
+		btrfs_drop_and_free_fs_root(fs_info, fs_info->data_reloc_root);
 	free_root_pointers(fs_info, true);
 	invalidate_inode_pages2(fs_info->btree_inode->i_mapping);
 
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index e9eedc053fc5..780b9c9a98fe 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -400,12 +400,11 @@ int btrfs_get_extent_inline_ref_type(const struct extent_buffer *eb,
 			if (type == BTRFS_SHARED_BLOCK_REF_KEY) {
 				ASSERT(eb->fs_info);
 				/*
-				 * Every shared one has parent tree
-				 * block, which must be aligned to
-				 * nodesize.
+				 * Every shared one has parent tree block,
+				 * which must be aligned to sector size.
 				 */
 				if (offset &&
-				    IS_ALIGNED(offset, eb->fs_info->nodesize))
+				    IS_ALIGNED(offset, eb->fs_info->sectorsize))
 					return type;
 			}
 		} else if (is_data == BTRFS_REF_TYPE_DATA) {
@@ -414,12 +413,11 @@ int btrfs_get_extent_inline_ref_type(const struct extent_buffer *eb,
 			if (type == BTRFS_SHARED_DATA_REF_KEY) {
 				ASSERT(eb->fs_info);
 				/*
-				 * Every shared one has parent tree
-				 * block, which must be aligned to
-				 * nodesize.
+				 * Every shared one has parent tree block,
+				 * which must be aligned to sector size.
 				 */
 				if (offset &&
-				    IS_ALIGNED(offset, eb->fs_info->nodesize))
+				    IS_ALIGNED(offset, eb->fs_info->sectorsize))
 					return type;
 			}
 		} else {
@@ -429,8 +427,9 @@ int btrfs_get_extent_inline_ref_type(const struct extent_buffer *eb,
 	}
 
 	btrfs_print_leaf((struct extent_buffer *)eb);
-	btrfs_err(eb->fs_info, "eb %llu invalid extent inline ref type %d",
-		  eb->start, type);
+	btrfs_err(eb->fs_info,
+		  "eb %llu iref 0x%lx invalid extent inline ref type %d",
+		  eb->start, (unsigned long)iref, type);
 	WARN_ON(1);
 
 	return BTRFS_REF_TYPE_INVALID;
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index ac45f022b495..2d9109d9e98f 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -2193,7 +2193,8 @@ static noinline int search_ioctl(struct inode *inode,
 	key.offset = sk->min_offset;
 
 	while (1) {
-		ret = fault_in_pages_writeable(ubuf, *buf_size - sk_offset);
+		ret = fault_in_pages_writeable(ubuf + sk_offset,
+					       *buf_size - sk_offset);
 		if (ret)
 			break;
 
diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c
index 61f44e78e3c9..80567c11ec12 100644
--- a/fs/btrfs/print-tree.c
+++ b/fs/btrfs/print-tree.c
@@ -95,9 +95,10 @@ static void print_extent_item(struct extent_buffer *eb, int slot, int type)
 			 * offset is supposed to be a tree block which
 			 * must be aligned to nodesize.
 			 */
-			if (!IS_ALIGNED(offset, eb->fs_info->nodesize))
-				pr_info("\t\t\t(parent %llu is NOT ALIGNED to nodesize %llu)\n",
-					offset, (unsigned long long)eb->fs_info->nodesize);
+			if (!IS_ALIGNED(offset, eb->fs_info->sectorsize))
+				pr_info(
+			"\t\t\t(parent %llu not aligned to sectorsize %u)\n",
+					offset, eb->fs_info->sectorsize);
 			break;
 		case BTRFS_EXTENT_DATA_REF_KEY:
 			dref = (struct btrfs_extent_data_ref *)(&iref->offset);
@@ -112,8 +113,9 @@ static void print_extent_item(struct extent_buffer *eb, int slot, int type)
 			 * must be aligned to nodesize.
 			 */
 			if (!IS_ALIGNED(offset, eb->fs_info->nodesize))
-				pr_info("\t\t\t(parent %llu is NOT ALIGNED to nodesize %llu)\n",
-				     offset, (unsigned long long)eb->fs_info->nodesize);
+				pr_info(
+			"\t\t\t(parent %llu not aligned to sectorsize %u)\n",
+				     offset, eb->fs_info->sectorsize);
 			break;
 		default:
 			pr_cont("(extent %llu has INVALID ref type %d)\n",
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 20c6ac1a5de7..d2fc292ac61b 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -1636,6 +1636,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 	pending->snap = btrfs_get_new_fs_root(fs_info, objectid, pending->anon_dev);
 	if (IS_ERR(pending->snap)) {
 		ret = PTR_ERR(pending->snap);
+		pending->snap = NULL;
 		btrfs_abort_transaction(trans, ret);
 		goto fail;
 	}
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 214856c4ccb1..117b43367629 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -4,6 +4,7 @@
  */
 
 #include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/bio.h>
 #include <linux/slab.h>
 #include <linux/blkdev.h>
@@ -6484,8 +6485,17 @@ static struct btrfs_device *add_missing_dev(struct btrfs_fs_devices *fs_devices,
 					    u64 devid, u8 *dev_uuid)
 {
 	struct btrfs_device *device;
+	unsigned int nofs_flag;
 
+	/*
+	 * We call this under the chunk_mutex, so we want to use NOFS for this
+	 * allocation, however we don't want to change btrfs_alloc_device() to
+	 * always do NOFS because we use it in a lot of other GFP_KERNEL safe
+	 * places.
+	 */
+	nofs_flag = memalloc_nofs_save();
 	device = btrfs_alloc_device(NULL, &devid, dev_uuid);
+	memalloc_nofs_restore(nofs_flag);
 	if (IS_ERR(device))
 		return device;
 
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 3989d08396ac..1f75b25e559a 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -1017,6 +1017,8 @@ handle_mnt_opt:
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MODE_FROM_SID) {
 		rc = cifs_acl_to_fattr(cifs_sb, &fattr, *inode, true,
 				       full_path, fid);
+		if (rc == -EREMOTE)
+			rc = 0;
 		if (rc) {
 			cifs_dbg(FYI, "%s: Get mode from SID failed. rc=%d\n",
 				 __func__, rc);
@@ -1025,6 +1027,8 @@ handle_mnt_opt:
 	} else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL) {
 		rc = cifs_acl_to_fattr(cifs_sb, &fattr, *inode, false,
 				       full_path, fid);
+		if (rc == -EREMOTE)
+			rc = 0;
 		if (rc) {
 			cifs_dbg(FYI, "%s: Getting ACL failed with error: %d\n",
 				 __func__, rc);
diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c
index b167d2d02148..a768a09430c3 100644
--- a/fs/debugfs/file.c
+++ b/fs/debugfs/file.c
@@ -177,7 +177,7 @@ static int open_proxy_open(struct inode *inode, struct file *filp)
 		goto out;
 
 	if (!fops_get(real_fops)) {
-#ifdef MODULE
+#ifdef CONFIG_MODULES
 		if (real_fops->owner &&
 		    real_fops->owner->state == MODULE_STATE_GOING)
 			goto out;
@@ -312,7 +312,7 @@ static int full_proxy_open(struct inode *inode, struct file *filp)
 		goto out;
 
 	if (!fops_get(real_fops)) {
-#ifdef MODULE
+#ifdef CONFIG_MODULES
 		if (real_fops->owner &&
 		    real_fops->owner->state == MODULE_STATE_GOING)
 			goto out;
diff --git a/fs/dlm/netlink.c b/fs/dlm/netlink.c
index e338c407cb75..67f68d48d60c 100644
--- a/fs/dlm/netlink.c
+++ b/fs/dlm/netlink.c
@@ -62,7 +62,7 @@ static int user_cmd(struct sk_buff *skb, struct genl_info *info)
 	return 0;
 }
 
-static const struct genl_ops dlm_nl_ops[] = {
+static const struct genl_small_ops dlm_nl_ops[] = {
 	{
 		.cmd	= DLM_CMD_HELLO,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
@@ -73,8 +73,8 @@ static const struct genl_ops dlm_nl_ops[] = {
 static struct genl_family family __ro_after_init = {
 	.name		= DLM_GENL_NAME,
 	.version	= DLM_GENL_VERSION,
-	.ops		= dlm_nl_ops,
-	.n_ops		= ARRAY_SIZE(dlm_nl_ops),
+	.small_ops	= dlm_nl_ops,
+	.n_small_ops	= ARRAY_SIZE(dlm_nl_ops),
 	.module		= THIS_MODULE,
 };
 
diff --git a/fs/ext2/file.c b/fs/ext2/file.c
index 60378ddf1424..96044f5dbc0e 100644
--- a/fs/ext2/file.c
+++ b/fs/ext2/file.c
@@ -93,8 +93,10 @@ static vm_fault_t ext2_dax_fault(struct vm_fault *vmf)
 	struct inode *inode = file_inode(vmf->vma->vm_file);
 	struct ext2_inode_info *ei = EXT2_I(inode);
 	vm_fault_t ret;
+	bool write = (vmf->flags & FAULT_FLAG_WRITE) &&
+		(vmf->vma->vm_flags & VM_SHARED);
 
-	if (vmf->flags & FAULT_FLAG_WRITE) {
+	if (write) {
 		sb_start_pagefault(inode->i_sb);
 		file_update_time(vmf->vma->vm_file);
 	}
@@ -103,7 +105,7 @@ static vm_fault_t ext2_dax_fault(struct vm_fault *vmf)
 	ret = dax_iomap_fault(vmf, PE_SIZE_PTE, NULL, NULL, &ext2_iomap_ops);
 
 	up_read(&ei->dax_sem);
-	if (vmf->flags & FAULT_FLAG_WRITE)
+	if (write)
 		sb_end_pagefault(inode->i_sb);
 	return ret;
 }
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index ed2bca0fce92..73683e58a08d 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -3550,6 +3550,9 @@ static int check_direct_IO(struct inode *inode, struct iov_iter *iter,
 	unsigned long align = offset | iov_iter_alignment(iter);
 	struct block_device *bdev = inode->i_sb->s_bdev;
 
+	if (iov_iter_rw(iter) == READ && offset >= i_size_read(inode))
+		return 1;
+
 	if (align & blocksize_mask) {
 		if (bdev)
 			blkbits = blksize_bits(bdev_logical_block_size(bdev));
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 3ad7bdbda5ca..cb1b5b61a1da 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -2373,6 +2373,9 @@ static int __f2fs_build_free_nids(struct f2fs_sb_info *sbi,
 	if (unlikely(nid >= nm_i->max_nid))
 		nid = 0;
 
+	if (unlikely(nid % NAT_ENTRY_PER_BLOCK))
+		nid = NAT_BLOCK_OFFSET(nid) * NAT_ENTRY_PER_BLOCK;
+
 	/* Enough entries */
 	if (nm_i->nid_cnt[FREE_NID] >= NAT_ENTRY_PER_BLOCK)
 		return 0;
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index a65d357f89a9..e247a5ef3713 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -799,7 +799,7 @@ static void __locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno,
 
 		if (__is_large_section(sbi)) {
 			unsigned int secno = GET_SEC_FROM_SEG(sbi, segno);
-			unsigned short valid_blocks =
+			block_t valid_blocks =
 				get_valid_blocks(sbi, segno, true);
 
 			f2fs_bug_on(sbi, unlikely(!valid_blocks ||
@@ -815,7 +815,7 @@ static void __remove_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno,
 		enum dirty_type dirty_type)
 {
 	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
-	unsigned short valid_blocks;
+	block_t valid_blocks;
 
 	if (test_and_clear_bit(segno, dirty_i->dirty_segmap[dirty_type]))
 		dirty_i->nr_dirty[dirty_type]--;
@@ -4316,8 +4316,8 @@ static void init_dirty_segmap(struct f2fs_sb_info *sbi)
 	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
 	struct free_segmap_info *free_i = FREE_I(sbi);
 	unsigned int segno = 0, offset = 0, secno;
-	unsigned short valid_blocks;
-	unsigned short blks_per_sec = BLKS_PER_SEC(sbi);
+	block_t valid_blocks;
+	block_t blks_per_sec = BLKS_PER_SEC(sbi);
 
 	while (1) {
 		/* find dirty segment based on free segmap */
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 149227160ff0..58b27e4070a3 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -2184,7 +2184,7 @@ static int __init start_dirtytime_writeback(void)
 __initcall(start_dirtytime_writeback);
 
 int dirtytime_interval_handler(struct ctl_table *table, int write,
-			       void __user *buffer, size_t *lenp, loff_t *ppos)
+			       void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int ret;
 
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 6611ef3269a8..43c165e796da 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -3091,11 +3091,10 @@ fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 	ssize_t ret = 0;
 	struct file *file = iocb->ki_filp;
 	struct fuse_file *ff = file->private_data;
-	bool async_dio = ff->fc->async_dio;
 	loff_t pos = 0;
 	struct inode *inode;
 	loff_t i_size;
-	size_t count = iov_iter_count(iter);
+	size_t count = iov_iter_count(iter), shortened = 0;
 	loff_t offset = iocb->ki_pos;
 	struct fuse_io_priv *io;
 
@@ -3103,17 +3102,9 @@ fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 	inode = file->f_mapping->host;
 	i_size = i_size_read(inode);
 
-	if ((iov_iter_rw(iter) == READ) && (offset > i_size))
+	if ((iov_iter_rw(iter) == READ) && (offset >= i_size))
 		return 0;
 
-	/* optimization for short read */
-	if (async_dio && iov_iter_rw(iter) != WRITE && offset + count > i_size) {
-		if (offset >= i_size)
-			return 0;
-		iov_iter_truncate(iter, fuse_round_up(ff->fc, i_size - offset));
-		count = iov_iter_count(iter);
-	}
-
 	io = kmalloc(sizeof(struct fuse_io_priv), GFP_KERNEL);
 	if (!io)
 		return -ENOMEM;
@@ -3129,15 +3120,22 @@ fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 	 * By default, we want to optimize all I/Os with async request
 	 * submission to the client filesystem if supported.
 	 */
-	io->async = async_dio;
+	io->async = ff->fc->async_dio;
 	io->iocb = iocb;
 	io->blocking = is_sync_kiocb(iocb);
 
+	/* optimization for short read */
+	if (io->async && !io->write && offset + count > i_size) {
+		iov_iter_truncate(iter, fuse_round_up(ff->fc, i_size - offset));
+		shortened = count - iov_iter_count(iter);
+		count -= shortened;
+	}
+
 	/*
 	 * We cannot asynchronously extend the size of a file.
 	 * In such case the aio will behave exactly like sync io.
 	 */
-	if ((offset + count > i_size) && iov_iter_rw(iter) == WRITE)
+	if ((offset + count > i_size) && io->write)
 		io->blocking = true;
 
 	if (io->async && io->blocking) {
@@ -3155,6 +3153,7 @@ fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 	} else {
 		ret = __fuse_direct_read(io, iter, &pos);
 	}
+	iov_iter_reexpand(iter, iov_iter_count(iter) + shortened);
 
 	if (io->async) {
 		bool blocking = io->blocking;
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 522b891dd187..c9aea6c44372 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1753,6 +1753,9 @@ static int io_req_task_work_add(struct io_kiocb *req, struct callback_head *cb,
 	struct io_ring_ctx *ctx = req->ctx;
 	int ret, notify;
 
+	if (tsk->flags & PF_EXITING)
+		return -ESRCH;
+
 	/*
 	 * SQPOLL kernel thread doesn't need notification, just a wakeup. For
 	 * all other cases, use TWA_SIGNAL unconditionally to ensure we're
@@ -1787,8 +1790,10 @@ static void __io_req_task_cancel(struct io_kiocb *req, int error)
 static void io_req_task_cancel(struct callback_head *cb)
 {
 	struct io_kiocb *req = container_of(cb, struct io_kiocb, task_work);
+	struct io_ring_ctx *ctx = req->ctx;
 
 	__io_req_task_cancel(req, -ECANCELED);
+	percpu_ref_put(&ctx->refs);
 }
 
 static void __io_req_task_submit(struct io_kiocb *req)
@@ -2010,6 +2015,12 @@ static inline unsigned int io_put_rw_kbuf(struct io_kiocb *req)
 
 static inline bool io_run_task_work(void)
 {
+	/*
+	 * Not safe to run on exiting task, and the task_work handling will
+	 * not add work to such a task.
+	 */
+	if (unlikely(current->flags & PF_EXITING))
+		return false;
 	if (current->task_works) {
 		__set_current_state(TASK_RUNNING);
 		task_work_run();
@@ -2283,13 +2294,17 @@ static bool io_resubmit_prep(struct io_kiocb *req, int error)
 		goto end_req;
 	}
 
-	ret = io_import_iovec(rw, req, &iovec, &iter, false);
-	if (ret < 0)
-		goto end_req;
-	ret = io_setup_async_rw(req, iovec, inline_vecs, &iter, false);
-	if (!ret)
+	if (!req->io) {
+		ret = io_import_iovec(rw, req, &iovec, &iter, false);
+		if (ret < 0)
+			goto end_req;
+		ret = io_setup_async_rw(req, iovec, inline_vecs, &iter, false);
+		if (!ret)
+			return true;
+		kfree(iovec);
+	} else {
 		return true;
-	kfree(iovec);
+	}
 end_req:
 	req_set_fail_links(req);
 	io_req_complete(req, ret);
@@ -2980,14 +2995,15 @@ static inline int io_rw_prep_async(struct io_kiocb *req, int rw,
 				   bool force_nonblock)
 {
 	struct io_async_rw *iorw = &req->io->rw;
+	struct iovec *iov;
 	ssize_t ret;
 
-	iorw->iter.iov = iorw->fast_iov;
-	ret = __io_import_iovec(rw, req, (struct iovec **) &iorw->iter.iov,
-				&iorw->iter, !force_nonblock);
+	iorw->iter.iov = iov = iorw->fast_iov;
+	ret = __io_import_iovec(rw, req, &iov, &iorw->iter, !force_nonblock);
 	if (unlikely(ret < 0))
 		return ret;
 
+	iorw->iter.iov = iov;
 	io_req_map_rw(req, iorw->iter.iov, iorw->fast_iov, &iorw->iter);
 	return 0;
 }
@@ -3114,6 +3130,7 @@ static int io_read(struct io_kiocb *req, bool force_nonblock,
 	struct iov_iter __iter, *iter = &__iter;
 	ssize_t io_size, ret, ret2;
 	size_t iov_count;
+	bool no_async;
 
 	if (req->io)
 		iter = &req->io->rw.iter;
@@ -3131,7 +3148,8 @@ static int io_read(struct io_kiocb *req, bool force_nonblock,
 		kiocb->ki_flags &= ~IOCB_NOWAIT;
 
 	/* If the file doesn't support async, just async punt */
-	if (force_nonblock && !io_file_supports_async(req->file, READ))
+	no_async = force_nonblock && !io_file_supports_async(req->file, READ);
+	if (no_async)
 		goto copy_iov;
 
 	ret = rw_verify_area(READ, req->file, io_kiocb_ppos(kiocb), iov_count);
@@ -3175,6 +3193,8 @@ copy_iov:
 		ret = ret2;
 		goto out_free;
 	}
+	if (no_async)
+		return -EAGAIN;
 	/* it's copied and will be cleaned with ->io */
 	iovec = NULL;
 	/* now use our persistent iterator, if we aren't already */
@@ -3507,8 +3527,6 @@ static int __io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe
 	const char __user *fname;
 	int ret;
 
-	if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL|IORING_SETUP_SQPOLL)))
-		return -EINVAL;
 	if (unlikely(sqe->ioprio || sqe->buf_index))
 		return -EINVAL;
 	if (unlikely(req->flags & REQ_F_FIXED_FILE))
@@ -3535,6 +3553,8 @@ static int io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
 	u64 flags, mode;
 
+	if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL|IORING_SETUP_SQPOLL)))
+		return -EINVAL;
 	if (req->flags & REQ_F_NEED_CLEANUP)
 		return 0;
 	mode = READ_ONCE(sqe->len);
@@ -3549,6 +3569,8 @@ static int io_openat2_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	size_t len;
 	int ret;
 
+	if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL|IORING_SETUP_SQPOLL)))
+		return -EINVAL;
 	if (req->flags & REQ_F_NEED_CLEANUP)
 		return 0;
 	how = u64_to_user_ptr(READ_ONCE(sqe->addr2));
@@ -3766,7 +3788,7 @@ static int io_epoll_ctl_prep(struct io_kiocb *req,
 #if defined(CONFIG_EPOLL)
 	if (sqe->ioprio || sqe->buf_index)
 		return -EINVAL;
-	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
+	if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL | IORING_SETUP_SQPOLL)))
 		return -EINVAL;
 
 	req->epoll.epfd = READ_ONCE(sqe->fd);
@@ -3881,7 +3903,7 @@ static int io_fadvise(struct io_kiocb *req, bool force_nonblock)
 
 static int io_statx_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
-	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
+	if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL | IORING_SETUP_SQPOLL)))
 		return -EINVAL;
 	if (sqe->ioprio || sqe->buf_index)
 		return -EINVAL;
@@ -5404,6 +5426,8 @@ static int io_async_cancel(struct io_kiocb *req)
 static int io_files_update_prep(struct io_kiocb *req,
 				const struct io_uring_sqe *sqe)
 {
+	if (unlikely(req->ctx->flags & IORING_SETUP_SQPOLL))
+		return -EINVAL;
 	if (unlikely(req->flags & (REQ_F_FIXED_FILE | REQ_F_BUFFER_SELECT)))
 		return -EINVAL;
 	if (sqe->ioprio || sqe->rw_flags)
@@ -5454,6 +5478,8 @@ static int io_req_defer_prep(struct io_kiocb *req,
 	if (unlikely(ret))
 		return ret;
 
+	io_prep_async_work(req);
+
 	switch (req->opcode) {
 	case IORING_OP_NOP:
 		break;
@@ -8029,6 +8055,28 @@ static bool io_match_link(struct io_kiocb *preq, struct io_kiocb *req)
 	return false;
 }
 
+static inline bool io_match_files(struct io_kiocb *req,
+				       struct files_struct *files)
+{
+	return (req->flags & REQ_F_WORK_INITIALIZED) && req->work.files == files;
+}
+
+static bool io_match_link_files(struct io_kiocb *req,
+				struct files_struct *files)
+{
+	struct io_kiocb *link;
+
+	if (io_match_files(req, files))
+		return true;
+	if (req->flags & REQ_F_LINK_HEAD) {
+		list_for_each_entry(link, &req->link_list, link_list) {
+			if (io_match_files(link, files))
+				return true;
+		}
+	}
+	return false;
+}
+
 /*
  * We're looking to cancel 'req' because it's holding on to our files, but
  * 'req' could be a link to another request. See if it is, and cancel that
@@ -8103,12 +8151,38 @@ static void io_attempt_cancel(struct io_ring_ctx *ctx, struct io_kiocb *req)
 	io_timeout_remove_link(ctx, req);
 }
 
+static void io_cancel_defer_files(struct io_ring_ctx *ctx,
+				  struct files_struct *files)
+{
+	struct io_defer_entry *de = NULL;
+	LIST_HEAD(list);
+
+	spin_lock_irq(&ctx->completion_lock);
+	list_for_each_entry_reverse(de, &ctx->defer_list, list) {
+		if (io_match_link_files(de->req, files)) {
+			list_cut_position(&list, &ctx->defer_list, &de->list);
+			break;
+		}
+	}
+	spin_unlock_irq(&ctx->completion_lock);
+
+	while (!list_empty(&list)) {
+		de = list_first_entry(&list, struct io_defer_entry, list);
+		list_del_init(&de->list);
+		req_set_fail_links(de->req);
+		io_put_req(de->req);
+		io_req_complete(de->req, -ECANCELED);
+		kfree(de);
+	}
+}
+
 static void io_uring_cancel_files(struct io_ring_ctx *ctx,
 				  struct files_struct *files)
 {
 	if (list_empty_careful(&ctx->inflight_list))
 		return;
 
+	io_cancel_defer_files(ctx, files);
 	/* cancel all at once, should be faster than doing it one by one*/
 	io_wq_cancel_cb(ctx->io_wq, io_wq_files_match, files, true);
 
@@ -8137,6 +8211,8 @@ static void io_uring_cancel_files(struct io_ring_ctx *ctx,
 		/* cancel this request, or head link requests */
 		io_attempt_cancel(ctx, cancel_req);
 		io_put_req(cancel_req);
+		/* cancellations _may_ trigger task work */
+		io_run_task_work();
 		schedule();
 		finish_wait(&ctx->inflight_wait, &wait);
 	}
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index f8946b9468ef..6e95c85fe395 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -3293,8 +3293,10 @@ static int _nfs4_do_setattr(struct inode *inode,
 
 	/* Servers should only apply open mode checks for file size changes */
 	truncate = (arg->iap->ia_valid & ATTR_SIZE) ? true : false;
-	if (!truncate)
+	if (!truncate) {
+		nfs4_inode_make_writeable(inode);
 		goto zero_stateid;
+	}
 
 	if (nfs4_copy_delegation_stateid(inode, FMODE_WRITE, &arg->stateid, &delegation_cred)) {
 		/* Use that stateid */
@@ -7298,7 +7300,12 @@ int nfs4_lock_delegation_recall(struct file_lock *fl, struct nfs4_state *state,
 	err = nfs4_set_lock_state(state, fl);
 	if (err != 0)
 		return err;
-	err = _nfs4_do_setlk(state, F_SETLK, fl, NFS_LOCK_NEW);
+	do {
+		err = _nfs4_do_setlk(state, F_SETLK, fl, NFS_LOCK_NEW);
+		if (err != -NFS4ERR_DELAY)
+			break;
+		ssleep(1);
+	} while (err == -NFS4ERR_DELAY);
 	return nfs4_handle_delegation_recall_error(server, state, stateid, fl, err);
 }
 
diff --git a/fs/vboxsf/super.c b/fs/vboxsf/super.c
index 8fe03b4a0d2b..25aade344192 100644
--- a/fs/vboxsf/super.c
+++ b/fs/vboxsf/super.c
@@ -384,7 +384,7 @@ fail_nomem:
 
 static int vboxsf_parse_monolithic(struct fs_context *fc, void *data)
 {
-	char *options = data;
+	unsigned char *options = data;
 
 	if (options && options[0] == VBSF_MOUNT_SIGNATURE_BYTE_0 &&
 		       options[1] == VBSF_MOUNT_SIGNATURE_BYTE_1 &&
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 9c40d5971035..1b0a01b06a05 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -6226,7 +6226,7 @@ xfs_bmap_validate_extent(
 
 	isrt = XFS_IS_REALTIME_INODE(ip);
 	endfsb = irec->br_startblock + irec->br_blockcount - 1;
-	if (isrt) {
+	if (isrt && whichfork == XFS_DATA_FORK) {
 		if (!xfs_verify_rtbno(mp, irec->br_startblock))
 			return __this_address;
 		if (!xfs_verify_rtbno(mp, endfsb))
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index c31cd3be9fb2..a29f78a663ca 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -1223,6 +1223,14 @@ __xfs_filemap_fault(
 	return ret;
 }
 
+static inline bool
+xfs_is_write_fault(
+	struct vm_fault		*vmf)
+{
+	return (vmf->flags & FAULT_FLAG_WRITE) &&
+	       (vmf->vma->vm_flags & VM_SHARED);
+}
+
 static vm_fault_t
 xfs_filemap_fault(
 	struct vm_fault		*vmf)
@@ -1230,7 +1238,7 @@ xfs_filemap_fault(
 	/* DAX can shortcut the normal fault path on write faults! */
 	return __xfs_filemap_fault(vmf, PE_SIZE_PTE,
 			IS_DAX(file_inode(vmf->vma->vm_file)) &&
-			(vmf->flags & FAULT_FLAG_WRITE));
+			xfs_is_write_fault(vmf));
 }
 
 static vm_fault_t
@@ -1243,7 +1251,7 @@ xfs_filemap_huge_fault(
 
 	/* DAX can shortcut the normal fault path on write faults! */
 	return __xfs_filemap_fault(vmf, pe_size,
-			(vmf->flags & FAULT_FLAG_WRITE));
+			xfs_is_write_fault(vmf));
 }
 
 static vm_fault_t
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index c6d9f2c444f4..50e5c4b52bd1 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -292,6 +292,8 @@ enum bpf_arg_type {
 	ARG_PTR_TO_ALLOC_MEM,	/* pointer to dynamically allocated memory */
 	ARG_PTR_TO_ALLOC_MEM_OR_NULL,	/* pointer to dynamically allocated memory or NULL */
 	ARG_CONST_ALLOC_SIZE_OR_ZERO,	/* number of allocated bytes requested */
+	ARG_PTR_TO_BTF_ID_SOCK_COMMON,	/* pointer to in-kernel sock_common or bpf-mirrored bpf_sock */
+	__BPF_ARG_TYPE_MAX,
 };
 
 /* type of values returned from helper functions */
@@ -326,12 +328,16 @@ struct bpf_func_proto {
 		};
 		enum bpf_arg_type arg_type[5];
 	};
-	int *btf_id; /* BTF ids of arguments */
-	bool (*check_btf_id)(u32 btf_id, u32 arg); /* if the argument btf_id is
-						    * valid. Often used if more
-						    * than one btf id is permitted
-						    * for this argument.
-						    */
+	union {
+		struct {
+			u32 *arg1_btf_id;
+			u32 *arg2_btf_id;
+			u32 *arg3_btf_id;
+			u32 *arg4_btf_id;
+			u32 *arg5_btf_id;
+		};
+		u32 *arg_btf_id[5];
+	};
 	int *ret_btf_id; /* return value btf_id */
 	bool (*allowed)(const struct bpf_prog *prog);
 };
@@ -377,8 +383,22 @@ enum bpf_reg_type {
 	PTR_TO_TCP_SOCK_OR_NULL, /* reg points to struct tcp_sock or NULL */
 	PTR_TO_TP_BUFFER,	 /* reg points to a writable raw tp's buffer */
 	PTR_TO_XDP_SOCK,	 /* reg points to struct xdp_sock */
-	PTR_TO_BTF_ID,		 /* reg points to kernel struct */
-	PTR_TO_BTF_ID_OR_NULL,	 /* reg points to kernel struct or NULL */
+	/* PTR_TO_BTF_ID points to a kernel struct that does not need
+	 * to be null checked by the BPF program. This does not imply the
+	 * pointer is _not_ null and in practice this can easily be a null
+	 * pointer when reading pointer chains. The assumption is program
+	 * context will handle null pointer dereference typically via fault
+	 * handling. The verifier must keep this in mind and can make no
+	 * assumptions about null or non-null when doing branch analysis.
+	 * Further, when passed into helpers the helpers can not, without
+	 * additional context, assume the value is non-null.
+	 */
+	PTR_TO_BTF_ID,
+	/* PTR_TO_BTF_ID_OR_NULL points to a kernel struct that has not
+	 * been checked for null. Used primarily to inform the verifier
+	 * an explicit null check is required for this struct.
+	 */
+	PTR_TO_BTF_ID_OR_NULL,
 	PTR_TO_MEM,		 /* reg points to valid memory region */
 	PTR_TO_MEM_OR_NULL,	 /* reg points to valid memory region or NULL */
 	PTR_TO_RDONLY_BUF,	 /* reg points to a readonly buffer */
@@ -586,6 +606,13 @@ struct bpf_trampoline {
 	struct bpf_ksym ksym;
 };
 
+struct bpf_attach_target_info {
+	struct btf_func_model fmodel;
+	long tgt_addr;
+	const char *tgt_name;
+	const struct btf_type *tgt_type;
+};
+
 #define BPF_DISPATCHER_MAX 48 /* Fits in 2048B */
 
 struct bpf_dispatcher_prog {
@@ -613,9 +640,10 @@ static __always_inline unsigned int bpf_dispatcher_nop_func(
 	return bpf_func(ctx, insnsi);
 }
 #ifdef CONFIG_BPF_JIT
-struct bpf_trampoline *bpf_trampoline_lookup(u64 key);
-int bpf_trampoline_link_prog(struct bpf_prog *prog);
-int bpf_trampoline_unlink_prog(struct bpf_prog *prog);
+int bpf_trampoline_link_prog(struct bpf_prog *prog, struct bpf_trampoline *tr);
+int bpf_trampoline_unlink_prog(struct bpf_prog *prog, struct bpf_trampoline *tr);
+struct bpf_trampoline *bpf_trampoline_get(u64 key,
+					  struct bpf_attach_target_info *tgt_info);
 void bpf_trampoline_put(struct bpf_trampoline *tr);
 #define BPF_DISPATCHER_INIT(_name) {				\
 	.mutex = __MUTEX_INITIALIZER(_name.mutex),		\
@@ -660,17 +688,20 @@ void bpf_image_ksym_del(struct bpf_ksym *ksym);
 void bpf_ksym_add(struct bpf_ksym *ksym);
 void bpf_ksym_del(struct bpf_ksym *ksym);
 #else
-static inline struct bpf_trampoline *bpf_trampoline_lookup(u64 key)
+static inline int bpf_trampoline_link_prog(struct bpf_prog *prog,
+					   struct bpf_trampoline *tr)
 {
-	return NULL;
+	return -ENOTSUPP;
 }
-static inline int bpf_trampoline_link_prog(struct bpf_prog *prog)
+static inline int bpf_trampoline_unlink_prog(struct bpf_prog *prog,
+					     struct bpf_trampoline *tr)
 {
 	return -ENOTSUPP;
 }
-static inline int bpf_trampoline_unlink_prog(struct bpf_prog *prog)
+static inline struct bpf_trampoline *bpf_trampoline_get(u64 key,
+							struct bpf_attach_target_info *tgt_info)
 {
-	return -ENOTSUPP;
+	return ERR_PTR(-EOPNOTSUPP);
 }
 static inline void bpf_trampoline_put(struct bpf_trampoline *tr) {}
 #define DEFINE_BPF_DISPATCHER(name)
@@ -697,16 +728,19 @@ enum bpf_jit_poke_reason {
 
 /* Descriptor of pokes pointing /into/ the JITed image. */
 struct bpf_jit_poke_descriptor {
-	void *ip;
+	void *tailcall_target;
+	void *tailcall_bypass;
+	void *bypass_addr;
 	union {
 		struct {
 			struct bpf_map *map;
 			u32 key;
 		} tail_call;
 	};
-	bool ip_stable;
+	bool tailcall_target_stable;
 	u8 adj_off;
 	u16 reason;
+	u32 insn_idx;
 };
 
 /* reg_type info for ctx arguments */
@@ -731,14 +765,18 @@ struct bpf_prog_aux {
 	u32 max_rdonly_access;
 	u32 max_rdwr_access;
 	const struct bpf_ctx_arg_aux *ctx_arg_info;
-	struct bpf_prog *linked_prog;
+	struct mutex dst_mutex; /* protects dst_* pointers below, *after* prog becomes visible */
+	struct bpf_prog *dst_prog;
+	struct bpf_trampoline *dst_trampoline;
+	enum bpf_prog_type saved_dst_prog_type;
+	enum bpf_attach_type saved_dst_attach_type;
 	bool verifier_zext; /* Zero extensions has been inserted by verifier. */
 	bool offload_requested;
 	bool attach_btf_trace; /* true if attaching to BTF-enabled raw tp */
 	bool func_proto_unreliable;
 	bool sleepable;
+	bool tail_call_reachable;
 	enum bpf_tramp_prog_type trampoline_prog_type;
-	struct bpf_trampoline *trampoline;
 	struct hlist_node tramp_hlist;
 	/* BTF_KIND_FUNC_PROTO for valid attach_btf_id */
 	const struct btf_type *attach_func_proto;
@@ -751,6 +789,7 @@ struct bpf_prog_aux {
 	struct bpf_ksym ksym;
 	const struct bpf_prog_ops *ops;
 	struct bpf_map **used_maps;
+	struct mutex used_maps_mutex; /* mutex for used_maps and used_map_cnt */
 	struct bpf_prog *prog;
 	struct user_struct *user;
 	u64 load_time; /* ns since boottime */
@@ -1330,6 +1369,8 @@ int bpf_check(struct bpf_prog **fp, union bpf_attr *attr,
 	      union bpf_attr __user *uattr);
 void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth);
 
+struct btf *bpf_get_btf_vmlinux(void);
+
 /* Map specifics */
 struct xdp_buff;
 struct sk_buff;
@@ -1371,6 +1412,9 @@ int bpf_prog_test_run_tracing(struct bpf_prog *prog,
 int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog,
 				     const union bpf_attr *kattr,
 				     union bpf_attr __user *uattr);
+int bpf_prog_test_run_raw_tp(struct bpf_prog *prog,
+			     const union bpf_attr *kattr,
+			     union bpf_attr __user *uattr);
 bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 		    const struct bpf_prog *prog,
 		    struct bpf_insn_access_aux *info);
@@ -1380,8 +1424,6 @@ int btf_struct_access(struct bpf_verifier_log *log,
 		      u32 *next_btf_id);
 bool btf_struct_ids_match(struct bpf_verifier_log *log,
 			  int off, u32 id, u32 need_type_id);
-int btf_resolve_helper_id(struct bpf_verifier_log *log,
-			  const struct bpf_func_proto *fn, int);
 
 int btf_distill_func_proto(struct bpf_verifier_log *log,
 			   struct btf *btf,
@@ -1394,7 +1436,7 @@ int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog,
 			     struct bpf_reg_state *regs);
 int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
 			  struct bpf_reg_state *reg);
-int btf_check_type_match(struct bpf_verifier_env *env, struct bpf_prog *prog,
+int btf_check_type_match(struct bpf_verifier_log *log, const struct bpf_prog *prog,
 			 struct btf *btf, const struct btf_type *t);
 
 struct bpf_prog *bpf_prog_by_id(u32 id);
@@ -1785,6 +1827,7 @@ extern const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto;
 extern const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto;
 extern const struct bpf_func_proto bpf_skc_to_udp6_sock_proto;
 extern const struct bpf_func_proto bpf_copy_from_user_proto;
+extern const struct bpf_func_proto bpf_snprintf_btf_proto;
 
 const struct bpf_func_proto *bpf_tracing_func_proto(
 	enum bpf_func_id func_id, const struct bpf_prog *prog);
@@ -1900,6 +1943,6 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
 		       void *addr1, void *addr2);
 
 struct btf_id_set;
-bool btf_id_set_contains(struct btf_id_set *set, u32 id);
+bool btf_id_set_contains(const struct btf_id_set *set, u32 id);
 
 #endif /* _LINUX_BPF_H */
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 53c7bd568c5d..363b4f1c562a 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -347,8 +347,9 @@ static inline bool bpf_verifier_log_full(const struct bpf_verifier_log *log)
 
 static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log)
 {
-	return (log->level && log->ubuf && !bpf_verifier_log_full(log)) ||
-		log->level == BPF_LOG_KERNEL;
+	return log &&
+		((log->level && log->ubuf && !bpf_verifier_log_full(log)) ||
+		 log->level == BPF_LOG_KERNEL);
 }
 
 #define BPF_MAX_SUBPROGS 256
@@ -358,6 +359,9 @@ struct bpf_subprog_info {
 	u32 start; /* insn idx of function entry point */
 	u32 linfo_idx; /* The idx to the main_prog->aux->linfo */
 	u16 stack_depth; /* max. stack depth used by this function */
+	bool has_tail_call;
+	bool tail_call_reachable;
+	bool has_ld_abs;
 };
 
 /* single container for all structs
@@ -446,4 +450,17 @@ bpf_prog_offload_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt);
 int check_ctx_reg(struct bpf_verifier_env *env,
 		  const struct bpf_reg_state *reg, int regno);
 
+/* this lives here instead of in bpf.h because it needs to dereference tgt_prog */
+static inline u64 bpf_trampoline_compute_key(const struct bpf_prog *tgt_prog,
+					     u32 btf_id)
+{
+        return tgt_prog ? (((u64)tgt_prog->aux->id) << 32 | btf_id) : btf_id;
+}
+
+int bpf_check_attach_target(struct bpf_verifier_log *log,
+			    const struct bpf_prog *prog,
+			    const struct bpf_prog *tgt_prog,
+			    u32 btf_id,
+			    struct bpf_attach_target_info *tgt_info);
+
 #endif /* _LINUX_BPF_VERIFIER_H */
diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h
index 6ad4c000661a..d0bd226d6bd9 100644
--- a/include/linux/brcmphy.h
+++ b/include/linux/brcmphy.h
@@ -30,6 +30,7 @@
 #define PHY_ID_BCM57780			0x03625d90
 #define PHY_ID_BCM89610			0x03625cd0
 
+#define PHY_ID_BCM72113			0x35905310
 #define PHY_ID_BCM7250			0xae025280
 #define PHY_ID_BCM7255			0xae025120
 #define PHY_ID_BCM7260			0xae025190
diff --git a/include/linux/btf.h b/include/linux/btf.h
index a9af5e7a7ece..024e16ff7dcc 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -6,6 +6,7 @@
 
 #include <linux/types.h>
 #include <uapi/linux/btf.h>
+#include <uapi/linux/bpf.h>
 
 #define BTF_TYPE_EMIT(type) ((void)(type *)0)
 
@@ -13,6 +14,7 @@ struct btf;
 struct btf_member;
 struct btf_type;
 union bpf_attr;
+struct btf_show;
 
 extern const struct file_operations btf_fops;
 
@@ -46,8 +48,45 @@ int btf_get_info_by_fd(const struct btf *btf,
 const struct btf_type *btf_type_id_size(const struct btf *btf,
 					u32 *type_id,
 					u32 *ret_size);
+
+/*
+ * Options to control show behaviour.
+ *	- BTF_SHOW_COMPACT: no formatting around type information
+ *	- BTF_SHOW_NONAME: no struct/union member names/types
+ *	- BTF_SHOW_PTR_RAW: show raw (unobfuscated) pointer values;
+ *	  equivalent to %px.
+ *	- BTF_SHOW_ZERO: show zero-valued struct/union members; they
+ *	  are not displayed by default
+ *	- BTF_SHOW_UNSAFE: skip use of bpf_probe_read() to safely read
+ *	  data before displaying it.
+ */
+#define BTF_SHOW_COMPACT	BTF_F_COMPACT
+#define BTF_SHOW_NONAME		BTF_F_NONAME
+#define BTF_SHOW_PTR_RAW	BTF_F_PTR_RAW
+#define BTF_SHOW_ZERO		BTF_F_ZERO
+#define BTF_SHOW_UNSAFE		(1ULL << 4)
+
 void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj,
 		       struct seq_file *m);
+int btf_type_seq_show_flags(const struct btf *btf, u32 type_id, void *obj,
+			    struct seq_file *m, u64 flags);
+
+/*
+ * Copy len bytes of string representation of obj of BTF type_id into buf.
+ *
+ * @btf: struct btf object
+ * @type_id: type id of type obj points to
+ * @obj: pointer to typed data
+ * @buf: buffer to write to
+ * @len: maximum length to write to buf
+ * @flags: show options (see above)
+ *
+ * Return: length that would have been/was copied as per snprintf, or
+ *	   negative error.
+ */
+int btf_type_snprintf_show(const struct btf *btf, u32 type_id, void *obj,
+			   char *buf, int len, u64 flags);
+
 int btf_get_fd_by_id(u32 id);
 u32 btf_id(const struct btf *btf);
 bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s,
diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h
index 210b086188a3..57890b357f85 100644
--- a/include/linux/btf_ids.h
+++ b/include/linux/btf_ids.h
@@ -76,6 +76,13 @@ extern u32 name[];
 #define BTF_ID_LIST_GLOBAL(name)			\
 __BTF_ID_LIST(name, globl)
 
+/* The BTF_ID_LIST_SINGLE macro defines a BTF_ID_LIST with
+ * a single entry.
+ */
+#define BTF_ID_LIST_SINGLE(name, prefix, typename)	\
+	BTF_ID_LIST(name) \
+	BTF_ID(prefix, typename)
+
 /*
  * The BTF_ID_UNUSED macro defines 4 zero bytes.
  * It's used when we want to define 'unused' entry
@@ -140,6 +147,7 @@ extern struct btf_id_set name;
 #define BTF_ID(prefix, name)
 #define BTF_ID_UNUSED
 #define BTF_ID_LIST_GLOBAL(name) u32 name[1];
+#define BTF_ID_LIST_SINGLE(name, prefix, typename) static u32 name[1];
 #define BTF_SET_START(name) static struct btf_id_set name = { 0 };
 #define BTF_SET_START_GLOBAL(name) static struct btf_id_set name = { 0 };
 #define BTF_SET_END(name)
diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h
index 6122efdad6ad..ea7b756b1c8f 100644
--- a/include/linux/compiler_attributes.h
+++ b/include/linux/compiler_attributes.h
@@ -22,14 +22,8 @@
 
 /*
  * __has_attribute is supported on gcc >= 5, clang >= 2.9 and icc >= 17.
- * In the meantime, to support 4.6 <= gcc < 5, we implement __has_attribute
+ * In the meantime, to support gcc < 5, we implement __has_attribute
  * by hand.
- *
- * sparse does not support __has_attribute (yet) and defines __GNUC_MINOR__
- * depending on the compiler used to build it; however, these attributes have
- * no semantic effects for sparse, so it does not matter. Also note that,
- * in order to avoid sparse's warnings, even the unsupported ones must be
- * defined to 0.
  */
 #ifndef __has_attribute
 # define __has_attribute(x) __GCC4_has_attribute_##x
diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h
index 4b33cb385f96..6e390d58a9f8 100644
--- a/include/linux/compiler_types.h
+++ b/include/linux/compiler_types.h
@@ -11,8 +11,8 @@
 # define __iomem	__attribute__((noderef, address_space(__iomem)))
 # define __percpu	__attribute__((noderef, address_space(__percpu)))
 # define __rcu		__attribute__((noderef, address_space(__rcu)))
-extern void __chk_user_ptr(const volatile void __user *);
-extern void __chk_io_ptr(const volatile void __iomem *);
+static inline void __chk_user_ptr(const volatile void __user *ptr) { }
+static inline void __chk_io_ptr(const volatile void __iomem *ptr) { }
 /* context/locking */
 # define __must_hold(x)	__attribute__((context(x,1,1)))
 # define __acquires(x)	__attribute__((context(x,0,1)))
diff --git a/include/linux/cookie.h b/include/linux/cookie.h
new file mode 100644
index 000000000000..0c159f585109
--- /dev/null
+++ b/include/linux/cookie.h
@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_COOKIE_H
+#define __LINUX_COOKIE_H
+
+#include <linux/atomic.h>
+#include <linux/percpu.h>
+#include <asm/local.h>
+
+struct pcpu_gen_cookie {
+	local_t nesting;
+	u64 last;
+} __aligned(16);
+
+struct gen_cookie {
+	struct pcpu_gen_cookie __percpu *local;
+	atomic64_t forward_last ____cacheline_aligned_in_smp;
+	atomic64_t reverse_last;
+};
+
+#define COOKIE_LOCAL_BATCH	4096
+
+#define DEFINE_COOKIE(name)						\
+	static DEFINE_PER_CPU(struct pcpu_gen_cookie, __##name);	\
+	static struct gen_cookie name = {				\
+		.local		= &__##name,				\
+		.forward_last	= ATOMIC64_INIT(0),			\
+		.reverse_last	= ATOMIC64_INIT(0),			\
+	}
+
+static __always_inline u64 gen_cookie_next(struct gen_cookie *gc)
+{
+	struct pcpu_gen_cookie *local = this_cpu_ptr(gc->local);
+	u64 val;
+
+	if (likely(local_inc_return(&local->nesting) == 1)) {
+		val = local->last;
+		if (__is_defined(CONFIG_SMP) &&
+		    unlikely((val & (COOKIE_LOCAL_BATCH - 1)) == 0)) {
+			s64 next = atomic64_add_return(COOKIE_LOCAL_BATCH,
+						       &gc->forward_last);
+			val = next - COOKIE_LOCAL_BATCH;
+		}
+		local->last = ++val;
+	} else {
+		val = atomic64_dec_return(&gc->reverse_last);
+	}
+	local_dec(&local->nesting);
+	return val;
+}
+
+#endif /* __LINUX_COOKIE_H */
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 3215023d4852..bf9181cef444 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -142,7 +142,6 @@ enum cpuhp_state {
 	/* Must be the last timer callback */
 	CPUHP_AP_DUMMY_TIMER_STARTING,
 	CPUHP_AP_ARM_XEN_STARTING,
-	CPUHP_AP_ARM_KVMPV_STARTING,
 	CPUHP_AP_ARM_CORESIGHT_STARTING,
 	CPUHP_AP_ARM_CORESIGHT_CTI_STARTING,
 	CPUHP_AP_ARM64_ISNDEP_STARTING,
diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h
index 75895e6363b8..6175c77bf25e 100644
--- a/include/linux/cpuidle.h
+++ b/include/linux/cpuidle.h
@@ -82,6 +82,7 @@ struct cpuidle_state {
 #define CPUIDLE_FLAG_UNUSABLE		BIT(3) /* avoid using this state */
 #define CPUIDLE_FLAG_OFF		BIT(4) /* disable this state by default */
 #define CPUIDLE_FLAG_TLB_FLUSHED	BIT(5) /* idle-state flushes TLBs */
+#define CPUIDLE_FLAG_RCU_IDLE		BIT(6) /* idle-state takes care of RCU */
 
 struct cpuidle_device_kobj;
 struct cpuidle_state_kobj;
diff --git a/include/linux/dax.h b/include/linux/dax.h
index 6904d4e0b2e0..43b39ab9de1a 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -58,6 +58,8 @@ static inline void set_dax_synchronous(struct dax_device *dax_dev)
 {
 	__set_dax_synchronous(dax_dev);
 }
+bool dax_supported(struct dax_device *dax_dev, struct block_device *bdev,
+		int blocksize, sector_t start, sector_t len);
 /*
  * Check if given mapping is supported by the file / underlying device.
  */
@@ -104,6 +106,12 @@ static inline bool dax_synchronous(struct dax_device *dax_dev)
 static inline void set_dax_synchronous(struct dax_device *dax_dev)
 {
 }
+static inline bool dax_supported(struct dax_device *dax_dev,
+		struct block_device *bdev, int blocksize, sector_t start,
+		sector_t len)
+{
+	return false;
+}
 static inline bool daxdev_mapping_supported(struct vm_area_struct *vma,
 				struct dax_device *dax_dev)
 {
@@ -189,14 +197,23 @@ static inline void dax_unlock_page(struct page *page, dax_entry_t cookie)
 }
 #endif
 
+#if IS_ENABLED(CONFIG_DAX)
 int dax_read_lock(void);
 void dax_read_unlock(int id);
+#else
+static inline int dax_read_lock(void)
+{
+	return 0;
+}
+
+static inline void dax_read_unlock(int id)
+{
+}
+#endif /* CONFIG_DAX */
 bool dax_alive(struct dax_device *dax_dev);
 void *dax_get_private(struct dax_device *dax_dev);
 long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages,
 		void **kaddr, pfn_t *pfn);
-bool dax_supported(struct dax_device *dax_dev, struct block_device *bdev,
-		int blocksize, sector_t start, sector_t len);
 size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
 		size_t bytes, struct iov_iter *i);
 size_t dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
diff --git a/include/linux/device.h b/include/linux/device.h
index ca18da4768e3..9e6ea8931a52 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -454,6 +454,7 @@ struct dev_links_info {
  * @pm_domain:	Provide callbacks that are executed during system suspend,
  * 		hibernation, system resume and during runtime PM transitions
  * 		along with subsystem-level and driver-level callbacks.
+ * @em_pd:	device's energy model performance domain
  * @pins:	For device pin management.
  *		See Documentation/driver-api/pinctl.rst for details.
  * @msi_list:	Hosts MSI descriptors
diff --git a/include/linux/dynamic_debug.h b/include/linux/dynamic_debug.h
index aa9ff9e1c0b3..8aa0c7c2608c 100644
--- a/include/linux/dynamic_debug.h
+++ b/include/linux/dynamic_debug.h
@@ -49,6 +49,10 @@ struct _ddebug {
 
 
 #if defined(CONFIG_DYNAMIC_DEBUG_CORE)
+
+/* exported for module authors to exercise >control */
+int dynamic_debug_exec_queries(const char *query, const char *modname);
+
 int ddebug_add_module(struct _ddebug *tab, unsigned int n,
 				const char *modname);
 extern int ddebug_remove_module(const char *mod_name);
@@ -105,7 +109,7 @@ void __dynamic_ibdev_dbg(struct _ddebug *descriptor,
 	static_branch_unlikely(&descriptor.key.dd_key_false)
 #endif
 
-#else /* !HAVE_JUMP_LABEL */
+#else /* !CONFIG_JUMP_LABEL */
 
 #define _DPRINTK_KEY_INIT
 
@@ -117,7 +121,7 @@ void __dynamic_ibdev_dbg(struct _ddebug *descriptor,
 	unlikely(descriptor.flags & _DPRINTK_FLAGS_PRINT)
 #endif
 
-#endif
+#endif /* CONFIG_JUMP_LABEL */
 
 #define __dynamic_func_call(id, fmt, func, ...) do {	\
 	DEFINE_DYNAMIC_DEBUG_METADATA(id, fmt);		\
@@ -172,10 +176,11 @@ void __dynamic_ibdev_dbg(struct _ddebug *descriptor,
 				   KERN_DEBUG, prefix_str, prefix_type,	\
 				   rowsize, groupsize, buf, len, ascii)
 
-#else
+#else /* !CONFIG_DYNAMIC_DEBUG_CORE */
 
 #include <linux/string.h>
 #include <linux/errno.h>
+#include <linux/printk.h>
 
 static inline int ddebug_add_module(struct _ddebug *tab, unsigned int n,
 				    const char *modname)
@@ -210,6 +215,13 @@ static inline int ddebug_dyndbg_module_param_cb(char *param, char *val,
 		print_hex_dump(KERN_DEBUG, prefix_str, prefix_type,	\
 				rowsize, groupsize, buf, len, ascii);	\
 	} while (0)
-#endif
+
+static inline int dynamic_debug_exec_queries(const char *query, const char *modname)
+{
+	pr_warn("kernel not built with CONFIG_DYNAMIC_DEBUG_CORE\n");
+	return 0;
+}
+
+#endif /* !CONFIG_DYNAMIC_DEBUG_CORE */
 
 #endif
diff --git a/include/linux/efi_embedded_fw.h b/include/linux/efi_embedded_fw.h
index 57eac5241303..a97a12bb2c9e 100644
--- a/include/linux/efi_embedded_fw.h
+++ b/include/linux/efi_embedded_fw.h
@@ -8,8 +8,8 @@
 #define EFI_EMBEDDED_FW_PREFIX_LEN		8
 
 /*
- * This struct and efi_embedded_fw_list are private to the efi-embedded fw
- * implementation they are in this header for use by lib/test_firmware.c only!
+ * This struct is private to the efi-embedded fw implementation.
+ * They are in this header for use by lib/test_firmware.c only!
  */
 struct efi_embedded_fw {
 	struct list_head list;
@@ -18,8 +18,6 @@ struct efi_embedded_fw {
 	size_t length;
 };
 
-extern struct list_head efi_embedded_fw_list;
-
 /**
  * struct efi_embedded_fw_desc - This struct is used by the EFI embedded-fw
  *                               code to search for embedded firmwares.
diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h
index efebbffcd5cc..159c7476b11b 100644
--- a/include/linux/entry-common.h
+++ b/include/linux/entry-common.h
@@ -110,15 +110,30 @@ static inline __must_check int arch_syscall_enter_tracehook(struct pt_regs *regs
 #endif
 
 /**
- * syscall_enter_from_user_mode - Check and handle work before invoking
- *				 a syscall
+ * syscall_enter_from_user_mode_prepare - Establish state and enable interrupts
  * @regs:	Pointer to currents pt_regs
- * @syscall:	The syscall number
  *
  * Invoked from architecture specific syscall entry code with interrupts
  * disabled. The calling code has to be non-instrumentable. When the
- * function returns all state is correct and the subsequent functions can be
- * instrumented.
+ * function returns all state is correct, interrupts are enabled and the
+ * subsequent functions can be instrumented.
+ *
+ * This handles lockdep, RCU (context tracking) and tracing state.
+ *
+ * This is invoked when there is extra architecture specific functionality
+ * to be done between establishing state and handling user mode entry work.
+ */
+void syscall_enter_from_user_mode_prepare(struct pt_regs *regs);
+
+/**
+ * syscall_enter_from_user_mode_work - Check and handle work before invoking
+ *				       a syscall
+ * @regs:	Pointer to currents pt_regs
+ * @syscall:	The syscall number
+ *
+ * Invoked from architecture specific syscall entry code with interrupts
+ * enabled after invoking syscall_enter_from_user_mode_prepare() and extra
+ * architecture specific work.
  *
  * Returns: The original or a modified syscall number
  *
@@ -127,12 +142,30 @@ static inline __must_check int arch_syscall_enter_tracehook(struct pt_regs *regs
  * syscall_set_return_value() first.  If neither of those are called and -1
  * is returned, then the syscall will fail with ENOSYS.
  *
- * The following functionality is handled here:
+ * It handles the following work items:
  *
- *  1) Establish state (lockdep, RCU (context tracking), tracing)
- *  2) TIF flag dependent invocations of arch_syscall_enter_tracehook(),
+ *  1) TIF flag dependent invocations of arch_syscall_enter_tracehook(),
  *     __secure_computing(), trace_sys_enter()
- *  3) Invocation of audit_syscall_entry()
+ *  2) Invocation of audit_syscall_entry()
+ */
+long syscall_enter_from_user_mode_work(struct pt_regs *regs, long syscall);
+
+/**
+ * syscall_enter_from_user_mode - Establish state and check and handle work
+ *				  before invoking a syscall
+ * @regs:	Pointer to currents pt_regs
+ * @syscall:	The syscall number
+ *
+ * Invoked from architecture specific syscall entry code with interrupts
+ * disabled. The calling code has to be non-instrumentable. When the
+ * function returns all state is correct, interrupts are enabled and the
+ * subsequent functions can be instrumented.
+ *
+ * This is combination of syscall_enter_from_user_mode_prepare() and
+ * syscall_enter_from_user_mode_work().
+ *
+ * Returns: The original or a modified syscall number. See
+ * syscall_enter_from_user_mode_work() for further explanation.
  */
 long syscall_enter_from_user_mode(struct pt_regs *regs, long syscall);
 
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 05b4052715b9..20fc24c9779a 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1287,6 +1287,8 @@ int copy_bpf_fprog_from_user(struct sock_fprog *dst, sockptr_t src, int len);
 struct bpf_sk_lookup_kern {
 	u16		family;
 	u16		protocol;
+	__be16		sport;
+	u16		dport;
 	struct {
 		__be32 saddr;
 		__be32 daddr;
@@ -1295,8 +1297,6 @@ struct bpf_sk_lookup_kern {
 		const struct in6_addr *saddr;
 		const struct in6_addr *daddr;
 	} v6;
-	__be16		sport;
-	u16		dport;
 	struct sock	*selected_sk;
 	bool		no_reuseport;
 };
diff --git a/include/linux/fs_parser.h b/include/linux/fs_parser.h
index 2eab6d5f6736..aab0ffc6bac6 100644
--- a/include/linux/fs_parser.h
+++ b/include/linux/fs_parser.h
@@ -120,7 +120,7 @@ static inline bool fs_validate_description(const char *name,
 #define fsparam_u32oct(NAME, OPT) \
 			__fsparam(fs_param_is_u32, NAME, OPT, 0, (void *)8)
 #define fsparam_u32hex(NAME, OPT) \
-			__fsparam(fs_param_is_u32_hex, NAME, OPT, 0, (void *16))
+			__fsparam(fs_param_is_u32_hex, NAME, OPT, 0, (void *)16)
 #define fsparam_s32(NAME, OPT)	__fsparam(fs_param_is_s32, NAME, OPT, 0, NULL)
 #define fsparam_u64(NAME, OPT)	__fsparam(fs_param_is_u64, NAME, OPT, 0, NULL)
 #define fsparam_enum(NAME, OPT, array)	__fsparam(fs_param_is_enum, NAME, OPT, 0, array)
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index ce2c06f72e86..e5c2d5cc6e6a 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -85,8 +85,7 @@ static inline int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *val
 extern int ftrace_enabled;
 extern int
 ftrace_enable_sysctl(struct ctl_table *table, int write,
-		     void __user *buffer, size_t *lenp,
-		     loff_t *ppos);
+		     void *buffer, size_t *lenp, loff_t *ppos);
 
 struct ftrace_ops;
 
diff --git a/include/linux/i2c-algo-pca.h b/include/linux/i2c-algo-pca.h
index d03071732db4..7c522fdd9ea7 100644
--- a/include/linux/i2c-algo-pca.h
+++ b/include/linux/i2c-algo-pca.h
@@ -53,6 +53,20 @@
 #define I2C_PCA_CON_SI		0x08 /* Serial Interrupt */
 #define I2C_PCA_CON_CR		0x07 /* Clock Rate (MASK) */
 
+/**
+ * struct pca_i2c_bus_settings - The configured PCA i2c bus settings
+ * @mode: Configured i2c bus mode
+ * @tlow: Configured SCL LOW period
+ * @thi: Configured SCL HIGH period
+ * @clock_freq: The configured clock frequency
+ */
+struct pca_i2c_bus_settings {
+	int mode;
+	int tlow;
+	int thi;
+	int clock_freq;
+};
+
 struct i2c_algo_pca_data {
 	void 				*data;	/* private low level data */
 	void (*write_byte)		(void *data, int reg, int val);
@@ -64,6 +78,7 @@ struct i2c_algo_pca_data {
 	 * For PCA9665, use the frequency you want here. */
 	unsigned int			i2c_clock;
 	unsigned int			chip;
+	struct pca_i2c_bus_settings		bus_settings;
 };
 
 int i2c_pca_add_bus(struct i2c_adapter *);
diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 53fba39d4ba6..770408b2fdaf 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -151,6 +151,9 @@
 
 #define IEEE80211_ANO_NETTYPE_WILD              15
 
+/* bits unique to S1G beacon */
+#define IEEE80211_S1G_BCN_NEXT_TBTT    0x100
+
 /* control extension - for IEEE80211_FTYPE_CTL | IEEE80211_STYPE_CTL_EXT */
 #define IEEE80211_CTL_EXT_POLL		0x2000
 #define IEEE80211_CTL_EXT_SPR		0x3000
@@ -554,6 +557,28 @@ static inline bool ieee80211_is_s1g_beacon(__le16 fc)
 }
 
 /**
+ * ieee80211_next_tbtt_present - check if IEEE80211_FTYPE_EXT &&
+ * IEEE80211_STYPE_S1G_BEACON && IEEE80211_S1G_BCN_NEXT_TBTT
+ * @fc: frame control bytes in little-endian byteorder
+ */
+static inline bool ieee80211_next_tbtt_present(__le16 fc)
+{
+	return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) ==
+	       cpu_to_le16(IEEE80211_FTYPE_EXT | IEEE80211_STYPE_S1G_BEACON) &&
+	       fc & cpu_to_le16(IEEE80211_S1G_BCN_NEXT_TBTT);
+}
+
+/**
+ * ieee80211_is_s1g_short_beacon - check if next tbtt present bit is set. Only
+ * true for S1G beacons when they're short.
+ * @fc: frame control bytes in little-endian byteorder
+ */
+static inline bool ieee80211_is_s1g_short_beacon(__le16 fc)
+{
+	return ieee80211_is_s1g_beacon(fc) && ieee80211_next_tbtt_present(fc);
+}
+
+/**
  * ieee80211_is_atim - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_ATIM
  * @fc: frame control bytes in little-endian byteorder
  */
@@ -962,6 +987,25 @@ enum ieee80211_vht_opmode_bits {
 	IEEE80211_OPMODE_NOTIF_RX_NSS_TYPE_BF	= 0x80,
 };
 
+/**
+ * enum ieee80211_s1g_chanwidth
+ * These are defined in IEEE802.11-2016ah Table 10-20
+ * as BSS Channel Width
+ *
+ * @IEEE80211_S1G_CHANWIDTH_1MHZ: 1MHz operating channel
+ * @IEEE80211_S1G_CHANWIDTH_2MHZ: 2MHz operating channel
+ * @IEEE80211_S1G_CHANWIDTH_4MHZ: 4MHz operating channel
+ * @IEEE80211_S1G_CHANWIDTH_8MHZ: 8MHz operating channel
+ * @IEEE80211_S1G_CHANWIDTH_16MHZ: 16MHz operating channel
+ */
+enum ieee80211_s1g_chanwidth {
+	IEEE80211_S1G_CHANWIDTH_1MHZ = 0,
+	IEEE80211_S1G_CHANWIDTH_2MHZ = 1,
+	IEEE80211_S1G_CHANWIDTH_4MHZ = 3,
+	IEEE80211_S1G_CHANWIDTH_8MHZ = 7,
+	IEEE80211_S1G_CHANWIDTH_16MHZ = 15,
+};
+
 #define WLAN_SA_QUERY_TR_ID_LEN 2
 #define WLAN_MEMBERSHIP_LEN 8
 #define WLAN_USER_POSITION_LEN 16
@@ -1034,6 +1078,13 @@ struct ieee80211_ext {
 			u8 change_seq;
 			u8 variable[0];
 		} __packed s1g_beacon;
+		struct {
+			u8 sa[ETH_ALEN];
+			__le32 timestamp;
+			u8 change_seq;
+			u8 next_tbtt[3];
+			u8 variable[0];
+		} __packed s1g_short_beacon;
 	} u;
 } __packed __aligned(2);
 
@@ -1070,6 +1121,11 @@ struct ieee80211_mgmt {
 		} __packed assoc_resp, reassoc_resp;
 		struct {
 			__le16 capab_info;
+			__le16 status_code;
+			u8 variable[0];
+		} __packed s1g_assoc_resp, s1g_reassoc_resp;
+		struct {
+			__le16 capab_info;
 			__le16 listen_interval;
 			u8 current_ap[ETH_ALEN];
 			/* followed by SSID and Supported rates */
@@ -2294,8 +2350,11 @@ ieee80211_he_6ghz_oper(const struct ieee80211_he_operation *he_oper)
 }
 
 /* HE Spatial Reuse defines */
-#define IEEE80211_HE_SPR_NON_SRG_OFFSET_PRESENT			0x4
-#define IEEE80211_HE_SPR_SRG_INFORMATION_PRESENT		0x8
+#define IEEE80211_HE_SPR_PSR_DISALLOWED				BIT(0)
+#define IEEE80211_HE_SPR_NON_SRG_OBSS_PD_SR_DISALLOWED		BIT(1)
+#define IEEE80211_HE_SPR_NON_SRG_OFFSET_PRESENT			BIT(2)
+#define IEEE80211_HE_SPR_SRG_INFORMATION_PRESENT		BIT(3)
+#define IEEE80211_HE_SPR_HESIGA_SR_VAL15_ALLOWED		BIT(4)
 
 /*
  * ieee80211_he_spr_size - calculate 802.11ax HE Spatial Reuse IE size
@@ -2330,6 +2389,8 @@ ieee80211_he_spr_size(const u8 *he_spr_ie)
 }
 
 /* S1G Capabilities Information field */
+#define IEEE80211_S1G_CAPABILITY_LEN	15
+
 #define S1G_CAP0_S1G_LONG	BIT(0)
 #define S1G_CAP0_SGI_1MHZ	BIT(1)
 #define S1G_CAP0_SGI_2MHZ	BIT(2)
@@ -2409,6 +2470,13 @@ ieee80211_he_spr_size(const u8 *he_spr_ie)
 #define S1G_OPER_CH_WIDTH_PRIMARY_1MHZ	BIT(0)
 #define S1G_OPER_CH_WIDTH_OPER		GENMASK(4, 1)
 
+
+#define LISTEN_INT_USF	GENMASK(15, 14)
+#define LISTEN_INT_UI	GENMASK(13, 0)
+
+#define IEEE80211_MAX_USF	FIELD_MAX(LISTEN_INT_USF)
+#define IEEE80211_MAX_UI	FIELD_MAX(LISTEN_INT_UI)
+
 /* Authentication algorithms */
 #define WLAN_AUTH_OPEN 0
 #define WLAN_AUTH_SHARED_KEY 1
@@ -2808,6 +2876,8 @@ enum ieee80211_eid {
 
 	WLAN_EID_REDUCED_NEIGHBOR_REPORT = 201,
 
+	WLAN_EID_AID_REQUEST = 210,
+	WLAN_EID_AID_RESPONSE = 211,
 	WLAN_EID_S1G_BCN_COMPAT = 213,
 	WLAN_EID_S1G_SHORT_BCN_INTERVAL = 214,
 	WLAN_EID_S1G_CAPABILITIES = 217,
diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h
index 6479a38e52fa..556caed00258 100644
--- a/include/linux/if_bridge.h
+++ b/include/linux/if_bridge.h
@@ -19,7 +19,13 @@ struct br_ip {
 #if IS_ENABLED(CONFIG_IPV6)
 		struct in6_addr ip6;
 #endif
-	} u;
+	} src;
+	union {
+		__be32	ip4;
+#if IS_ENABLED(CONFIG_IPV6)
+		struct in6_addr ip6;
+#endif
+	} dst;
 	__be16		proto;
 	__u16           vid;
 };
diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index 9be1bff4f586..8aab327b5539 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -373,6 +373,8 @@ void unregister_kretprobes(struct kretprobe **rps, int num);
 void kprobe_flush_task(struct task_struct *tk);
 void recycle_rp_inst(struct kretprobe_instance *ri, struct hlist_head *head);
 
+void kprobe_free_init_mem(void);
+
 int disable_kprobe(struct kprobe *kp);
 int enable_kprobe(struct kprobe *kp);
 
@@ -435,6 +437,9 @@ static inline void unregister_kretprobes(struct kretprobe **rps, int num)
 static inline void kprobe_flush_task(struct task_struct *tk)
 {
 }
+static inline void kprobe_free_init_mem(void)
+{
+}
 static inline int disable_kprobe(struct kprobe *kp)
 {
 	return -ENOSYS;
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index a23076765b4c..05e3c2fb3ef7 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -749,25 +749,46 @@ int kvm_write_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
 int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
 			      gpa_t gpa, unsigned long len);
 
-#define __kvm_put_guest(kvm, gfn, offset, value, type)			\
+#define __kvm_get_guest(kvm, gfn, offset, v)				\
 ({									\
 	unsigned long __addr = gfn_to_hva(kvm, gfn);			\
-	type __user *__uaddr = (type __user *)(__addr + offset);	\
+	typeof(v) __user *__uaddr = (typeof(__uaddr))(__addr + offset);	\
 	int __ret = -EFAULT;						\
 									\
 	if (!kvm_is_error_hva(__addr))					\
-		__ret = put_user(value, __uaddr);			\
+		__ret = get_user(v, __uaddr);				\
+	__ret;								\
+})
+
+#define kvm_get_guest(kvm, gpa, v)					\
+({									\
+	gpa_t __gpa = gpa;						\
+	struct kvm *__kvm = kvm;					\
+									\
+	__kvm_get_guest(__kvm, __gpa >> PAGE_SHIFT,			\
+			offset_in_page(__gpa), v);			\
+})
+
+#define __kvm_put_guest(kvm, gfn, offset, v)				\
+({									\
+	unsigned long __addr = gfn_to_hva(kvm, gfn);			\
+	typeof(v) __user *__uaddr = (typeof(__uaddr))(__addr + offset);	\
+	int __ret = -EFAULT;						\
+									\
+	if (!kvm_is_error_hva(__addr))					\
+		__ret = put_user(v, __uaddr);				\
 	if (!__ret)							\
 		mark_page_dirty(kvm, gfn);				\
 	__ret;								\
 })
 
-#define kvm_put_guest(kvm, gpa, value, type)				\
+#define kvm_put_guest(kvm, gpa, v)					\
 ({									\
 	gpa_t __gpa = gpa;						\
 	struct kvm *__kvm = kvm;					\
+									\
 	__kvm_put_guest(__kvm, __gpa >> PAGE_SHIFT,			\
-			offset_in_page(__gpa), (value), type);		\
+			offset_in_page(__gpa), v);			\
 })
 
 int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len);
diff --git a/include/linux/log2.h b/include/linux/log2.h
index 83a4a3ca3e8a..c619ec6eff4a 100644
--- a/include/linux/log2.h
+++ b/include/linux/log2.h
@@ -173,7 +173,7 @@ unsigned long __rounddown_pow_of_two(unsigned long n)
 #define roundup_pow_of_two(n)			\
 (						\
 	__builtin_constant_p(n) ? (		\
-		(n == 1) ? 1 :			\
+		((n) == 1) ? 1 :		\
 		(1UL << (ilog2((n) - 1) + 1))	\
 				   ) :		\
 	__roundup_pow_of_two(n)			\
diff --git a/include/linux/mdio.h b/include/linux/mdio.h
index 3a88b699b758..dbd69b3d170b 100644
--- a/include/linux/mdio.h
+++ b/include/linux/mdio.h
@@ -306,7 +306,7 @@ static inline u32 linkmode_adv_to_mii_10gbt_adv_t(unsigned long *advertising)
 /**
  * mii_10gbt_stat_mod_linkmode_lpa_t
  * @advertising: target the linkmode advertisement settings
- * @adv: value of the C45 10GBASE-T AN STATUS register
+ * @lpa: value of the C45 10GBASE-T AN STATUS register
  *
  * A small helper function that translates C45 10GBASE-T AN STATUS register bits
  * to linkmode advertisement settings. Other bits in advertising aren't changed.
@@ -371,6 +371,7 @@ struct phy_device *mdiobus_get_phy(struct mii_bus *bus, int addr);
 
 /**
  * mdio_module_driver() - Helper macro for registering mdio drivers
+ * @_mdio_driver: driver to register
  *
  * Helper macro for MDIO drivers which do not do anything special in module
  * init/exit. Each module may only use this macro once, and calling it
diff --git a/include/linux/memremap.h b/include/linux/memremap.h
index 5f5b2df06e61..e5862746751b 100644
--- a/include/linux/memremap.h
+++ b/include/linux/memremap.h
@@ -46,11 +46,10 @@ struct vmem_altmap {
  * wakeup is used to coordinate physical address space management (ex:
  * fs truncate/hole punch) vs pinned pages (ex: device dma).
  *
- * MEMORY_DEVICE_DEVDAX:
+ * MEMORY_DEVICE_GENERIC:
  * Host memory that has similar access semantics as System RAM i.e. DMA
- * coherent and supports page pinning. In contrast to
- * MEMORY_DEVICE_FS_DAX, this memory is access via a device-dax
- * character device.
+ * coherent and supports page pinning. This is for example used by DAX devices
+ * that expose memory using a character device.
  *
  * MEMORY_DEVICE_PCI_P2PDMA:
  * Device memory residing in a PCI BAR intended for use with Peer-to-Peer
@@ -60,7 +59,7 @@ enum memory_type {
 	/* 0 is reserved to catch uninitialized type fields */
 	MEMORY_DEVICE_PRIVATE = 1,
 	MEMORY_DEVICE_FS_DAX,
-	MEMORY_DEVICE_DEVDAX,
+	MEMORY_DEVICE_GENERIC,
 	MEMORY_DEVICE_PCI_P2PDMA,
 };
 
diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h
index c16827eeba9c..b0ae8020f13e 100644
--- a/include/linux/mlx5/eswitch.h
+++ b/include/linux/mlx5/eswitch.h
@@ -74,15 +74,16 @@ bool mlx5_eswitch_reg_c1_loopback_enabled(const struct mlx5_eswitch *esw);
 bool mlx5_eswitch_vport_match_metadata_enabled(const struct mlx5_eswitch *esw);
 
 /* Reg C0 usage:
- * Reg C0 = < ESW_VHCA_ID_BITS(8) | ESW_VPORT BITS(8) | ESW_CHAIN_TAG(16) >
+ * Reg C0 = < ESW_PFNUM_BITS(4) | ESW_VPORT BITS(12) | ESW_CHAIN_TAG(16) >
  *
- * Highest 8 bits of the reg c0 is the vhca_id, next 8 bits is vport_num,
- * the rest (lowest 16 bits) is left for tc chain tag restoration.
- * VHCA_ID + VPORT comprise the SOURCE_PORT matching.
+ * Highest 4 bits of the reg c0 is the PF_NUM (range 0-15), 12 bits of
+ * unique non-zero vport id (range 1-4095). The rest (lowest 16 bits) is left
+ * for tc chain tag restoration.
+ * PFNUM + VPORT comprise the SOURCE_PORT matching.
  */
-#define ESW_VHCA_ID_BITS 8
-#define ESW_VPORT_BITS 8
-#define ESW_SOURCE_PORT_METADATA_BITS (ESW_VHCA_ID_BITS + ESW_VPORT_BITS)
+#define ESW_VPORT_BITS 12
+#define ESW_PFNUM_BITS 4
+#define ESW_SOURCE_PORT_METADATA_BITS (ESW_PFNUM_BITS + ESW_VPORT_BITS)
 #define ESW_SOURCE_PORT_METADATA_OFFSET (32 - ESW_SOURCE_PORT_METADATA_BITS)
 #define ESW_CHAIN_TAG_METADATA_BITS (32 - ESW_SOURCE_PORT_METADATA_BITS)
 #define ESW_CHAIN_TAG_METADATA_MASK GENMASK(ESW_CHAIN_TAG_METADATA_BITS - 1,\
diff --git a/include/linux/mm.h b/include/linux/mm.h
index ca6e6a81576b..b2f370f0b420 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -41,6 +41,8 @@ struct writeback_control;
 struct bdi_writeback;
 struct pt_regs;
 
+extern int sysctl_page_lock_unfairness;
+
 void init_mm_internals(void);
 
 #ifndef CONFIG_NEED_MULTIPLE_NODES	/* Don't use mapnrs, do it properly */
diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h
index 2cc3cf80b49a..0b17c4322b09 100644
--- a/include/linux/netdev_features.h
+++ b/include/linux/netdev_features.h
@@ -193,7 +193,7 @@ static inline int find_next_netdev_feature(u64 feature, unsigned long start)
 #define NETIF_F_GSO_MASK	(__NETIF_F_BIT(NETIF_F_GSO_LAST + 1) - \
 		__NETIF_F_BIT(NETIF_F_GSO_SHIFT))
 
-/* List of IP checksum features. Note that NETIF_F_ HW_CSUM should not be
+/* List of IP checksum features. Note that NETIF_F_HW_CSUM should not be
  * set in features when NETIF_F_IP_CSUM or NETIF_F_IPV6_CSUM are set--
  * this would be contradictory
  */
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index fef0eb96cf69..0c79d9e56a5e 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -212,9 +212,8 @@ struct netdev_hw_addr {
 	unsigned char		type;
 #define NETDEV_HW_ADDR_T_LAN		1
 #define NETDEV_HW_ADDR_T_SAN		2
-#define NETDEV_HW_ADDR_T_SLAVE		3
-#define NETDEV_HW_ADDR_T_UNICAST	4
-#define NETDEV_HW_ADDR_T_MULTICAST	5
+#define NETDEV_HW_ADDR_T_UNICAST	3
+#define NETDEV_HW_ADDR_T_MULTICAST	4
 	bool			global_use;
 	int			sync_cnt;
 	int			refcount;
@@ -1776,6 +1775,7 @@ enum netdev_priv_flags {
  *				the watchdog (see dev_watchdog())
  *	@watchdog_timer:	List of timers
  *
+ *	@proto_down_reason:	reason a netdev interface is held down
  *	@pcpu_refcnt:		Number of references to this device
  *	@todo_list:		Delayed register/unregister
  *	@link_watch_list:	XXX: need comments on this one
@@ -1840,6 +1840,7 @@ enum netdev_priv_flags {
  *	@udp_tunnel_nic_info:	static structure describing the UDP tunnel
  *				offload capabilities of the device
  *	@udp_tunnel_nic:	UDP tunnel offload state
+ *	@xdp_state:		stores info on attached XDP BPF programs
  *
  *	FIXME: cleanup struct net_device such that network protocol info
  *	moves out.
@@ -3783,6 +3784,7 @@ void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog);
 int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff *skb);
 int netif_rx(struct sk_buff *skb);
 int netif_rx_ni(struct sk_buff *skb);
+int netif_rx_any_context(struct sk_buff *skb);
 int netif_receive_skb(struct sk_buff *skb);
 int netif_receive_skb_core(struct sk_buff *skb);
 void netif_receive_skb_list(struct list_head *head);
diff --git a/include/linux/of_mdio.h b/include/linux/of_mdio.h
index 1efb88d9f892..cfe8c607a628 100644
--- a/include/linux/of_mdio.h
+++ b/include/linux/of_mdio.h
@@ -17,6 +17,7 @@ bool of_mdiobus_child_is_phy(struct device_node *child);
 int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np);
 int devm_of_mdiobus_register(struct device *dev, struct mii_bus *mdio,
 			     struct device_node *np);
+struct mdio_device *of_mdio_find_device(struct device_node *np);
 struct phy_device *of_phy_find_device(struct device_node *phy_np);
 struct phy_device *
 of_phy_connect(struct net_device *dev, struct device_node *phy_np,
@@ -74,6 +75,11 @@ static inline int of_mdiobus_register(struct mii_bus *mdio, struct device_node *
 	return mdiobus_register(mdio);
 }
 
+static inline struct mdio_device *of_mdio_find_device(struct device_node *np)
+{
+	return NULL;
+}
+
 static inline struct phy_device *of_phy_find_device(struct device_node *phy_np)
 {
 	return NULL;
diff --git a/include/linux/percpu-rwsem.h b/include/linux/percpu-rwsem.h
index 5e033fe1ff4e..5fda40f97fe9 100644
--- a/include/linux/percpu-rwsem.h
+++ b/include/linux/percpu-rwsem.h
@@ -60,7 +60,7 @@ static inline void percpu_down_read(struct percpu_rw_semaphore *sem)
 	 * anything we did within this RCU-sched read-size critical section.
 	 */
 	if (likely(rcu_sync_is_idle(&sem->rss)))
-		__this_cpu_inc(*sem->read_count);
+		this_cpu_inc(*sem->read_count);
 	else
 		__percpu_down_read(sem, false); /* Unconditional memory barrier */
 	/*
@@ -79,7 +79,7 @@ static inline bool percpu_down_read_trylock(struct percpu_rw_semaphore *sem)
 	 * Same as in percpu_down_read().
 	 */
 	if (likely(rcu_sync_is_idle(&sem->rss)))
-		__this_cpu_inc(*sem->read_count);
+		this_cpu_inc(*sem->read_count);
 	else
 		ret = __percpu_down_read(sem, true); /* Unconditional memory barrier */
 	preempt_enable();
@@ -103,7 +103,7 @@ static inline void percpu_up_read(struct percpu_rw_semaphore *sem)
 	 * Same as in percpu_down_read().
 	 */
 	if (likely(rcu_sync_is_idle(&sem->rss))) {
-		__this_cpu_dec(*sem->read_count);
+		this_cpu_dec(*sem->read_count);
 	} else {
 		/*
 		 * slowpath; reader will only ever wake a single blocked
@@ -115,7 +115,7 @@ static inline void percpu_up_read(struct percpu_rw_semaphore *sem)
 		 * aggregate zero, as that is the only time it matters) they
 		 * will also see our critical section.
 		 */
-		__this_cpu_dec(*sem->read_count);
+		this_cpu_dec(*sem->read_count);
 		rcuwait_wake_up(&sem->writer);
 	}
 	preempt_enable();
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 3a09d2bf69ea..eb3cb1a98b45 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -82,7 +82,39 @@ extern const int phy_10gbit_features_array[1];
 #define PHY_POLL_CABLE_TEST	0x00000004
 #define MDIO_DEVICE_IS_PHY	0x80000000
 
-/* Interface Mode definitions */
+/**
+ * enum phy_interface_t - Interface Mode definitions
+ *
+ * @PHY_INTERFACE_MODE_NA: Not Applicable - don't touch
+ * @PHY_INTERFACE_MODE_INTERNAL: No interface, MAC and PHY combined
+ * @PHY_INTERFACE_MODE_MII: Median-independent interface
+ * @PHY_INTERFACE_MODE_GMII: Gigabit median-independent interface
+ * @PHY_INTERFACE_MODE_SGMII: Serial gigabit media-independent interface
+ * @PHY_INTERFACE_MODE_TBI: Ten Bit Interface
+ * @PHY_INTERFACE_MODE_REVMII: Reverse Media Independent Interface
+ * @PHY_INTERFACE_MODE_RMII: Reduced Media Independent Interface
+ * @PHY_INTERFACE_MODE_RGMII: Reduced gigabit media-independent interface
+ * @PHY_INTERFACE_MODE_RGMII_ID: RGMII with Internal RX+TX delay
+ * @PHY_INTERFACE_MODE_RGMII_RXID: RGMII with Internal RX delay
+ * @PHY_INTERFACE_MODE_RGMII_TXID: RGMII with Internal RX delay
+ * @PHY_INTERFACE_MODE_RTBI: Reduced TBI
+ * @PHY_INTERFACE_MODE_SMII: ??? MII
+ * @PHY_INTERFACE_MODE_XGMII: 10 gigabit media-independent interface
+ * @PHY_INTERFACE_MODE_XLGMII:40 gigabit media-independent interface
+ * @PHY_INTERFACE_MODE_MOCA: Multimedia over Coax
+ * @PHY_INTERFACE_MODE_QSGMII: Quad SGMII
+ * @PHY_INTERFACE_MODE_TRGMII: Turbo RGMII
+ * @PHY_INTERFACE_MODE_1000BASEX: 1000 BaseX
+ * @PHY_INTERFACE_MODE_2500BASEX: 2500 BaseX
+ * @PHY_INTERFACE_MODE_RXAUI: Reduced XAUI
+ * @PHY_INTERFACE_MODE_XAUI: 10 Gigabit Attachment Unit Interface
+ * @PHY_INTERFACE_MODE_10GBASER: 10G BaseR
+ * @PHY_INTERFACE_MODE_USXGMII:  Universal Serial 10GE MII
+ * @PHY_INTERFACE_MODE_10GKR: 10GBASE-KR - with Clause 73 AN
+ * @PHY_INTERFACE_MODE_MAX: Book keeping
+ *
+ * Describes the interface between the MAC and PHY.
+ */
 typedef enum {
 	PHY_INTERFACE_MODE_NA,
 	PHY_INTERFACE_MODE_INTERNAL,
@@ -116,8 +148,8 @@ typedef enum {
 } phy_interface_t;
 
 /**
- * phy_supported_speeds - return all speeds currently supported by a phy device
- * @phy: The phy device to return supported speeds of.
+ * phy_supported_speeds - return all speeds currently supported by a PHY device
+ * @phy: The PHY device to return supported speeds of.
  * @speeds: buffer to store supported speeds in.
  * @size: size of speeds buffer.
  *
@@ -134,9 +166,9 @@ unsigned int phy_supported_speeds(struct phy_device *phy,
  * phy_modes - map phy_interface_t enum to device tree binding of phy-mode
  * @interface: enum phy_interface_t value
  *
- * Description: maps 'enum phy_interface_t' defined in this file
+ * Description: maps enum &phy_interface_t defined in this file
  * into the device tree binding of 'phy-mode', so that Ethernet
- * device driver can get phy interface from device tree.
+ * device driver can get PHY interface from device tree.
  */
 static inline const char *phy_modes(phy_interface_t interface)
 {
@@ -215,6 +247,14 @@ struct sfp_bus;
 struct sfp_upstream_ops;
 struct sk_buff;
 
+/**
+ * struct mdio_bus_stats - Statistics counters for MDIO busses
+ * @transfers: Total number of transfers, i.e. @writes + @reads
+ * @errors: Number of MDIO transfers that returned an error
+ * @writes: Number of write transfers
+ * @reads: Number of read transfers
+ * @syncp: Synchronisation for incrementing statistics
+ */
 struct mdio_bus_stats {
 	u64_stats_t transfers;
 	u64_stats_t errors;
@@ -224,7 +264,15 @@ struct mdio_bus_stats {
 	struct u64_stats_sync syncp;
 };
 
-/* Represents a shared structure between different phydev's in the same
+/**
+ * struct phy_package_shared - Shared information in PHY packages
+ * @addr: Common PHY address used to combine PHYs in one package
+ * @refcnt: Number of PHYs connected to this shared data
+ * @flags: Initialization of PHY package
+ * @priv_size: Size of the shared private data @priv
+ * @priv: Driver private data shared across a PHY package
+ *
+ * Represents a shared structure between different phydev's in the same
  * package, for example a quad PHY. See phy_package_join() and
  * phy_package_leave().
  */
@@ -247,7 +295,14 @@ struct phy_package_shared {
 #define PHY_SHARED_F_INIT_DONE  0
 #define PHY_SHARED_F_PROBE_DONE 1
 
-/*
+/**
+ * struct mii_bus - Represents an MDIO bus
+ *
+ * @owner: Who owns this device
+ * @name: User friendly name for this MDIO device, or driver name
+ * @id: Unique identifier for this bus, typical from bus hierarchy
+ * @priv: Driver private data
+ *
  * The Bus class for PHYs.  Devices which provide access to
  * PHYs should register using this structure
  */
@@ -256,49 +311,58 @@ struct mii_bus {
 	const char *name;
 	char id[MII_BUS_ID_SIZE];
 	void *priv;
+	/** @read: Perform a read transfer on the bus */
 	int (*read)(struct mii_bus *bus, int addr, int regnum);
+	/** @write: Perform a write transfer on the bus */
 	int (*write)(struct mii_bus *bus, int addr, int regnum, u16 val);
+	/** @reset: Perform a reset of the bus */
 	int (*reset)(struct mii_bus *bus);
+
+	/** @stats: Statistic counters per device on the bus */
 	struct mdio_bus_stats stats[PHY_MAX_ADDR];
 
-	/*
-	 * A lock to ensure that only one thing can read/write
+	/**
+	 * @mdio_lock: A lock to ensure that only one thing can read/write
 	 * the MDIO bus at a time
 	 */
 	struct mutex mdio_lock;
 
+	/** @parent: Parent device of this bus */
 	struct device *parent;
+	/** @state: State of bus structure */
 	enum {
 		MDIOBUS_ALLOCATED = 1,
 		MDIOBUS_REGISTERED,
 		MDIOBUS_UNREGISTERED,
 		MDIOBUS_RELEASED,
 	} state;
+
+	/** @dev: Kernel device representation */
 	struct device dev;
 
-	/* list of all PHYs on bus */
+	/** @mdio_map: list of all MDIO devices on bus */
 	struct mdio_device *mdio_map[PHY_MAX_ADDR];
 
-	/* PHY addresses to be ignored when probing */
+	/** @phy_mask: PHY addresses to be ignored when probing */
 	u32 phy_mask;
 
-	/* PHY addresses to ignore the TA/read failure */
+	/** @phy_ignore_ta_mask: PHY addresses to ignore the TA/read failure */
 	u32 phy_ignore_ta_mask;
 
-	/*
-	 * An array of interrupts, each PHY's interrupt at the index
+	/**
+	 * @irq: An array of interrupts, each PHY's interrupt at the index
 	 * matching its address
 	 */
 	int irq[PHY_MAX_ADDR];
 
-	/* GPIO reset pulse width in microseconds */
+	/** @reset_delay_us: GPIO reset pulse width in microseconds */
 	int reset_delay_us;
-	/* GPIO reset deassert delay in microseconds */
+	/** @reset_post_delay_us: GPIO reset deassert delay in microseconds */
 	int reset_post_delay_us;
-	/* RESET GPIO descriptor pointer */
+	/** @reset_gpiod: Reset GPIO descriptor pointer */
 	struct gpio_desc *reset_gpiod;
 
-	/* bus capabilities, used for probing */
+	/** @probe_capabilities: bus capabilities, used for probing */
 	enum {
 		MDIOBUS_NO_CAP = 0,
 		MDIOBUS_C22,
@@ -306,15 +370,22 @@ struct mii_bus {
 		MDIOBUS_C22_C45,
 	} probe_capabilities;
 
-	/* protect access to the shared element */
+	/** @shared_lock: protect access to the shared element */
 	struct mutex shared_lock;
 
-	/* shared state across different PHYs */
+	/** @shared: shared state across different PHYs */
 	struct phy_package_shared *shared[PHY_MAX_ADDR];
 };
 #define to_mii_bus(d) container_of(d, struct mii_bus, dev)
 
-struct mii_bus *mdiobus_alloc_size(size_t);
+struct mii_bus *mdiobus_alloc_size(size_t size);
+
+/**
+ * mdiobus_alloc - Allocate an MDIO bus structure
+ *
+ * The internal state of the MDIO bus will be set of MDIOBUS_ALLOCATED ready
+ * for the driver to register the bus.
+ */
 static inline struct mii_bus *mdiobus_alloc(void)
 {
 	return mdiobus_alloc_size(0);
@@ -341,40 +412,41 @@ struct phy_device *mdiobus_scan(struct mii_bus *bus, int addr);
 #define PHY_INTERRUPT_DISABLED	false
 #define PHY_INTERRUPT_ENABLED	true
 
-/* PHY state machine states:
+/**
+ * enum phy_state - PHY state machine states:
  *
- * DOWN: PHY device and driver are not ready for anything.  probe
+ * @PHY_DOWN: PHY device and driver are not ready for anything.  probe
  * should be called if and only if the PHY is in this state,
  * given that the PHY device exists.
- * - PHY driver probe function will set the state to READY
+ * - PHY driver probe function will set the state to @PHY_READY
  *
- * READY: PHY is ready to send and receive packets, but the
+ * @PHY_READY: PHY is ready to send and receive packets, but the
  * controller is not.  By default, PHYs which do not implement
  * probe will be set to this state by phy_probe().
  * - start will set the state to UP
  *
- * UP: The PHY and attached device are ready to do work.
+ * @PHY_UP: The PHY and attached device are ready to do work.
  * Interrupts should be started here.
- * - timer moves to NOLINK or RUNNING
+ * - timer moves to @PHY_NOLINK or @PHY_RUNNING
  *
- * NOLINK: PHY is up, but not currently plugged in.
- * - irq or timer will set RUNNING if link comes back
- * - phy_stop moves to HALTED
+ * @PHY_NOLINK: PHY is up, but not currently plugged in.
+ * - irq or timer will set @PHY_RUNNING if link comes back
+ * - phy_stop moves to @PHY_HALTED
  *
- * RUNNING: PHY is currently up, running, and possibly sending
+ * @PHY_RUNNING: PHY is currently up, running, and possibly sending
  * and/or receiving packets
- * - irq or timer will set NOLINK if link goes down
- * - phy_stop moves to HALTED
+ * - irq or timer will set @PHY_NOLINK if link goes down
+ * - phy_stop moves to @PHY_HALTED
  *
- * CABLETEST: PHY is performing a cable test. Packet reception/sending
+ * @PHY_CABLETEST: PHY is performing a cable test. Packet reception/sending
  * is not expected to work, carrier will be indicated as down. PHY will be
  * poll once per second, or on interrupt for it current state.
  * Once complete, move to UP to restart the PHY.
- * - phy_stop aborts the running test and moves to HALTED
+ * - phy_stop aborts the running test and moves to @PHY_HALTED
  *
- * HALTED: PHY is up, but no polling or interrupts are done. Or
+ * @PHY_HALTED: PHY is up, but no polling or interrupts are done. Or
  * PHY is in an error state.
- * - phy_start moves to UP
+ * - phy_start moves to @PHY_UP
  */
 enum phy_state {
 	PHY_DOWN = 0,
@@ -403,34 +475,67 @@ struct phy_c45_device_ids {
 struct macsec_context;
 struct macsec_ops;
 
-/* phy_device: An instance of a PHY
+/**
+ * struct phy_device - An instance of a PHY
  *
- * drv: Pointer to the driver for this PHY instance
- * phy_id: UID for this device found during discovery
- * c45_ids: 802.3-c45 Device Identifers if is_c45.
- * is_c45:  Set to true if this phy uses clause 45 addressing.
- * is_internal: Set to true if this phy is internal to a MAC.
- * is_pseudo_fixed_link: Set to true if this phy is an Ethernet switch, etc.
- * is_gigabit_capable: Set to true if PHY supports 1000Mbps
- * has_fixups: Set to true if this phy has fixups/quirks.
- * suspended: Set to true if this phy has been suspended successfully.
- * suspended_by_mdio_bus: Set to true if this phy was suspended by MDIO bus.
- * sysfs_links: Internal boolean tracking sysfs symbolic links setup/removal.
- * loopback_enabled: Set true if this phy has been loopbacked successfully.
- * downshifted_rate: Set true if link speed has been downshifted.
- * state: state of the PHY for management purposes
- * dev_flags: Device-specific flags used by the PHY driver.
- * irq: IRQ number of the PHY's interrupt (-1 if none)
- * phy_timer: The timer for handling the state machine
- * sfp_bus_attached: flag indicating whether the SFP bus has been attached
- * sfp_bus: SFP bus attached to this PHY's fiber port
- * attached_dev: The attached enet driver's device instance ptr
- * adjust_link: Callback for the enet controller to respond to
- * changes in the link state.
- * macsec_ops: MACsec offloading ops.
+ * @mdio: MDIO bus this PHY is on
+ * @drv: Pointer to the driver for this PHY instance
+ * @phy_id: UID for this device found during discovery
+ * @c45_ids: 802.3-c45 Device Identifiers if is_c45.
+ * @is_c45:  Set to true if this PHY uses clause 45 addressing.
+ * @is_internal: Set to true if this PHY is internal to a MAC.
+ * @is_pseudo_fixed_link: Set to true if this PHY is an Ethernet switch, etc.
+ * @is_gigabit_capable: Set to true if PHY supports 1000Mbps
+ * @has_fixups: Set to true if this PHY has fixups/quirks.
+ * @suspended: Set to true if this PHY has been suspended successfully.
+ * @suspended_by_mdio_bus: Set to true if this PHY was suspended by MDIO bus.
+ * @sysfs_links: Internal boolean tracking sysfs symbolic links setup/removal.
+ * @loopback_enabled: Set true if this PHY has been loopbacked successfully.
+ * @downshifted_rate: Set true if link speed has been downshifted.
+ * @state: State of the PHY for management purposes
+ * @dev_flags: Device-specific flags used by the PHY driver.
+ * @irq: IRQ number of the PHY's interrupt (-1 if none)
+ * @phy_timer: The timer for handling the state machine
+ * @phylink: Pointer to phylink instance for this PHY
+ * @sfp_bus_attached: Flag indicating whether the SFP bus has been attached
+ * @sfp_bus: SFP bus attached to this PHY's fiber port
+ * @attached_dev: The attached enet driver's device instance ptr
+ * @adjust_link: Callback for the enet controller to respond to changes: in the
+ *               link state.
+ * @phy_link_change: Callback for phylink for notification of link change
+ * @macsec_ops: MACsec offloading ops.
  *
- * speed, duplex, pause, supported, advertising, lp_advertising,
- * and autoneg are used like in mii_if_info
+ * @speed: Current link speed
+ * @duplex: Current duplex
+ * @pause: Current pause
+ * @asym_pause: Current asymmetric pause
+ * @supported: Combined MAC/PHY supported linkmodes
+ * @advertising: Currently advertised linkmodes
+ * @adv_old: Saved advertised while power saving for WoL
+ * @lp_advertising: Current link partner advertised linkmodes
+ * @eee_broken_modes: Energy efficient ethernet modes which should be prohibited
+ * @autoneg: Flag autoneg being used
+ * @link: Current link state
+ * @autoneg_complete: Flag auto negotiation of the link has completed
+ * @mdix: Current crossover
+ * @mdix_ctrl: User setting of crossover
+ * @interrupts: Flag interrupts have been enabled
+ * @interface: enum phy_interface_t value
+ * @skb: Netlink message for cable diagnostics
+ * @nest: Netlink nest used for cable diagnostics
+ * @ehdr: nNtlink header for cable diagnostics
+ * @phy_led_triggers: Array of LED triggers
+ * @phy_num_led_triggers: Number of triggers in @phy_led_triggers
+ * @led_link_trigger: LED trigger for link up/down
+ * @last_triggered: last LED trigger for link speed
+ * @master_slave_set: User requested master/slave configuration
+ * @master_slave_get: Current master/slave advertisement
+ * @master_slave_state: Current master/slave configuration
+ * @mii_ts: Pointer to time stamper callbacks
+ * @lock:  Mutex for serialization access to PHY
+ * @state_queue: Work queue for state machine
+ * @shared: Pointer to private data shared by phys in one package
+ * @priv: Pointer to driver private data
  *
  * interrupts currently only supports enabled or disabled,
  * but could be changed in the future to support enabling
@@ -550,9 +655,18 @@ struct phy_device {
 #define to_phy_device(d) container_of(to_mdio_device(d), \
 				      struct phy_device, mdio)
 
-/* A structure containing possible configuration parameters
+/**
+ * struct phy_tdr_config - Configuration of a TDR raw test
+ *
+ * @first: Distance for first data collection point
+ * @last: Distance for last data collection point
+ * @step: Step between data collection points
+ * @pair: Bitmap of cable pairs to collect data for
+ *
+ * A structure containing possible configuration parameters
  * for a TDR cable test. The driver does not need to implement
  * all the parameters, but should report what is actually used.
+ * All distances are in centimeters.
  */
 struct phy_tdr_config {
 	u32 first;
@@ -562,18 +676,20 @@ struct phy_tdr_config {
 };
 #define PHY_PAIR_ALL -1
 
-/* struct phy_driver: Driver structure for a particular PHY type
+/**
+ * struct phy_driver - Driver structure for a particular PHY type
  *
- * driver_data: static driver data
- * phy_id: The result of reading the UID registers of this PHY
+ * @mdiodrv: Data common to all MDIO devices
+ * @phy_id: The result of reading the UID registers of this PHY
  *   type, and ANDing them with the phy_id_mask.  This driver
  *   only works for PHYs with IDs which match this field
- * name: The friendly name of this PHY type
- * phy_id_mask: Defines the important bits of the phy_id
- * features: A mandatory list of features (speed, duplex, etc)
+ * @name: The friendly name of this PHY type
+ * @phy_id_mask: Defines the important bits of the phy_id
+ * @features: A mandatory list of features (speed, duplex, etc)
  *   supported by this PHY
- * flags: A bitfield defining certain other features this PHY
+ * @flags: A bitfield defining certain other features this PHY
  *   supports (like interrupts)
+ * @driver_data: Static driver data
  *
  * All functions are optional. If config_aneg or read_status
  * are not implemented, the phy core uses the genphy versions.
@@ -592,151 +708,178 @@ struct phy_driver {
 	u32 flags;
 	const void *driver_data;
 
-	/*
-	 * Called to issue a PHY software reset
+	/**
+	 * @soft_reset: Called to issue a PHY software reset
 	 */
 	int (*soft_reset)(struct phy_device *phydev);
 
-	/*
-	 * Called to initialize the PHY,
+	/**
+	 * @config_init: Called to initialize the PHY,
 	 * including after a reset
 	 */
 	int (*config_init)(struct phy_device *phydev);
 
-	/*
-	 * Called during discovery.  Used to set
+	/**
+	 * @probe: Called during discovery.  Used to set
 	 * up device-specific structures, if any
 	 */
 	int (*probe)(struct phy_device *phydev);
 
-	/*
-	 * Probe the hardware to determine what abilities it has.
-	 * Should only set phydev->supported.
+	/**
+	 * @get_features: Probe the hardware to determine what
+	 * abilities it has.  Should only set phydev->supported.
 	 */
 	int (*get_features)(struct phy_device *phydev);
 
 	/* PHY Power Management */
+	/** @suspend: Suspend the hardware, saving state if needed */
 	int (*suspend)(struct phy_device *phydev);
+	/** @resume: Resume the hardware, restoring state if needed */
 	int (*resume)(struct phy_device *phydev);
 
-	/*
-	 * Configures the advertisement and resets
+	/**
+	 * @config_aneg: Configures the advertisement and resets
 	 * autonegotiation if phydev->autoneg is on,
 	 * forces the speed to the current settings in phydev
 	 * if phydev->autoneg is off
 	 */
 	int (*config_aneg)(struct phy_device *phydev);
 
-	/* Determines the auto negotiation result */
+	/** @aneg_done: Determines the auto negotiation result */
 	int (*aneg_done)(struct phy_device *phydev);
 
-	/* Determines the negotiated speed and duplex */
+	/** @read_status: Determines the negotiated speed and duplex */
 	int (*read_status)(struct phy_device *phydev);
 
-	/* Clears any pending interrupts */
+	/** @ack_interrupt: Clears any pending interrupts */
 	int (*ack_interrupt)(struct phy_device *phydev);
 
-	/* Enables or disables interrupts */
+	/** @config_intr: Enables or disables interrupts */
 	int (*config_intr)(struct phy_device *phydev);
 
-	/*
-	 * Checks if the PHY generated an interrupt.
+	/**
+	 * @did_interrupt: Checks if the PHY generated an interrupt.
 	 * For multi-PHY devices with shared PHY interrupt pin
 	 * Set interrupt bits have to be cleared.
 	 */
 	int (*did_interrupt)(struct phy_device *phydev);
 
-	/* Override default interrupt handling */
+	/** @handle_interrupt: Override default interrupt handling */
 	irqreturn_t (*handle_interrupt)(struct phy_device *phydev);
 
-	/* Clears up any memory if needed */
+	/** @remove: Clears up any memory if needed */
 	void (*remove)(struct phy_device *phydev);
 
-	/* Returns true if this is a suitable driver for the given
-	 * phydev.  If NULL, matching is based on phy_id and
-	 * phy_id_mask.
+	/**
+	 * @match_phy_device: Returns true if this is a suitable
+	 * driver for the given phydev.	 If NULL, matching is based on
+	 * phy_id and phy_id_mask.
 	 */
 	int (*match_phy_device)(struct phy_device *phydev);
 
-	/* Some devices (e.g. qnap TS-119P II) require PHY register changes to
-	 * enable Wake on LAN, so set_wol is provided to be called in the
-	 * ethernet driver's set_wol function. */
+	/**
+	 * @set_wol: Some devices (e.g. qnap TS-119P II) require PHY
+	 * register changes to enable Wake on LAN, so set_wol is
+	 * provided to be called in the ethernet driver's set_wol
+	 * function.
+	 */
 	int (*set_wol)(struct phy_device *dev, struct ethtool_wolinfo *wol);
 
-	/* See set_wol, but for checking whether Wake on LAN is enabled. */
+	/**
+	 * @get_wol: See set_wol, but for checking whether Wake on LAN
+	 * is enabled.
+	 */
 	void (*get_wol)(struct phy_device *dev, struct ethtool_wolinfo *wol);
 
-	/*
-	 * Called to inform a PHY device driver when the core is about to
-	 * change the link state. This callback is supposed to be used as
-	 * fixup hook for drivers that need to take action when the link
-	 * state changes. Drivers are by no means allowed to mess with the
+	/**
+	 * @link_change_notify: Called to inform a PHY device driver
+	 * when the core is about to change the link state. This
+	 * callback is supposed to be used as fixup hook for drivers
+	 * that need to take action when the link state
+	 * changes. Drivers are by no means allowed to mess with the
 	 * PHY device structure in their implementations.
 	 */
 	void (*link_change_notify)(struct phy_device *dev);
 
-	/*
-	 * Phy specific driver override for reading a MMD register.
-	 * This function is optional for PHY specific drivers.  When
-	 * not provided, the default MMD read function will be used
-	 * by phy_read_mmd(), which will use either a direct read for
-	 * Clause 45 PHYs or an indirect read for Clause 22 PHYs.
-	 *  devnum is the MMD device number within the PHY device,
-	 *  regnum is the register within the selected MMD device.
+	/**
+	 * @read_mmd: PHY specific driver override for reading a MMD
+	 * register.  This function is optional for PHY specific
+	 * drivers.  When not provided, the default MMD read function
+	 * will be used by phy_read_mmd(), which will use either a
+	 * direct read for Clause 45 PHYs or an indirect read for
+	 * Clause 22 PHYs.  devnum is the MMD device number within the
+	 * PHY device, regnum is the register within the selected MMD
+	 * device.
 	 */
 	int (*read_mmd)(struct phy_device *dev, int devnum, u16 regnum);
 
-	/*
-	 * Phy specific driver override for writing a MMD register.
-	 * This function is optional for PHY specific drivers.  When
-	 * not provided, the default MMD write function will be used
-	 * by phy_write_mmd(), which will use either a direct write for
-	 * Clause 45 PHYs, or an indirect write for Clause 22 PHYs.
-	 *  devnum is the MMD device number within the PHY device,
-	 *  regnum is the register within the selected MMD device.
-	 *  val is the value to be written.
+	/**
+	 * @write_mmd: PHY specific driver override for writing a MMD
+	 * register.  This function is optional for PHY specific
+	 * drivers.  When not provided, the default MMD write function
+	 * will be used by phy_write_mmd(), which will use either a
+	 * direct write for Clause 45 PHYs, or an indirect write for
+	 * Clause 22 PHYs.  devnum is the MMD device number within the
+	 * PHY device, regnum is the register within the selected MMD
+	 * device.  val is the value to be written.
 	 */
 	int (*write_mmd)(struct phy_device *dev, int devnum, u16 regnum,
 			 u16 val);
 
+	/** @read_page: Return the current PHY register page number */
 	int (*read_page)(struct phy_device *dev);
+	/** @write_page: Set the current PHY register page number */
 	int (*write_page)(struct phy_device *dev, int page);
 
-	/* Get the size and type of the eeprom contained within a plug-in
-	 * module */
+	/**
+	 * @module_info: Get the size and type of the eeprom contained
+	 * within a plug-in module
+	 */
 	int (*module_info)(struct phy_device *dev,
 			   struct ethtool_modinfo *modinfo);
 
-	/* Get the eeprom information from the plug-in module */
+	/**
+	 * @module_eeprom: Get the eeprom information from the plug-in
+	 * module
+	 */
 	int (*module_eeprom)(struct phy_device *dev,
 			     struct ethtool_eeprom *ee, u8 *data);
 
-	/* Start a cable test */
+	/** @cable_test_start: Start a cable test */
 	int (*cable_test_start)(struct phy_device *dev);
 
-	/* Start a raw TDR cable test */
+	/**  @cable_test_tdr_start: Start a raw TDR cable test */
 	int (*cable_test_tdr_start)(struct phy_device *dev,
 				    const struct phy_tdr_config *config);
 
-	/* Once per second, or on interrupt, request the status of the
-	 * test.
+	/**
+	 * @cable_test_get_status: Once per second, or on interrupt,
+	 * request the status of the test.
 	 */
 	int (*cable_test_get_status)(struct phy_device *dev, bool *finished);
 
-	/* Get statistics from the phy using ethtool */
+	/* Get statistics from the PHY using ethtool */
+	/** @get_sset_count: Number of statistic counters */
 	int (*get_sset_count)(struct phy_device *dev);
+	/** @get_strings: Names of the statistic counters */
 	void (*get_strings)(struct phy_device *dev, u8 *data);
+	/** @get_stats: Return the statistic counter values */
 	void (*get_stats)(struct phy_device *dev,
 			  struct ethtool_stats *stats, u64 *data);
 
 	/* Get and Set PHY tunables */
+	/** @get_tunable: Return the value of a tunable */
 	int (*get_tunable)(struct phy_device *dev,
 			   struct ethtool_tunable *tuna, void *data);
+	/** @set_tunable: Set the value of a tunable */
 	int (*set_tunable)(struct phy_device *dev,
 			    struct ethtool_tunable *tuna,
 			    const void *data);
+	/** @set_loopback: Set the loopback mood of the PHY */
 	int (*set_loopback)(struct phy_device *dev, bool enable);
+	/** @get_sqi: Get the signal quality indication */
 	int (*get_sqi)(struct phy_device *dev);
+	/** @get_sqi_max: Get the maximum signal quality indication */
 	int (*get_sqi_max)(struct phy_device *dev);
 };
 #define to_phy_driver(d) container_of(to_mdio_common_driver(d),		\
@@ -890,6 +1033,24 @@ static inline int __phy_modify_changed(struct phy_device *phydev, u32 regnum,
  */
 int phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum);
 
+/**
+ * phy_read_mmd_poll_timeout - Periodically poll a PHY register until a
+ *                             condition is met or a timeout occurs
+ *
+ * @phydev: The phy_device struct
+ * @devaddr: The MMD to read from
+ * @regnum: The register on the MMD to read
+ * @val: Variable to read the register into
+ * @cond: Break condition (usually involving @val)
+ * @sleep_us: Maximum time to sleep between reads in us (0
+ *            tight-loops).  Should be less than ~20ms since usleep_range
+ *            is used (see Documentation/timers/timers-howto.rst).
+ * @timeout_us: Timeout in us, 0 means never timeout
+ * @sleep_before_read: if it is true, sleep @sleep_us before read.
+ * Returns 0 on success and -ETIMEDOUT upon a timeout. In either
+ * case, the last read value at @args is stored in @val. Must not
+ * be called from atomic context if sleep_us or timeout_us are used.
+ */
 #define phy_read_mmd_poll_timeout(phydev, devaddr, regnum, val, cond, \
 				  sleep_us, timeout_us, sleep_before_read) \
 ({ \
@@ -1161,7 +1322,7 @@ static inline bool phy_is_internal(struct phy_device *phydev)
 /**
  * phy_interface_mode_is_rgmii - Convenience function for testing if a
  * PHY interface mode is RGMII (all variants)
- * @mode: the phy_interface_t enum
+ * @mode: the &phy_interface_t enum
  */
 static inline bool phy_interface_mode_is_rgmii(phy_interface_t mode)
 {
@@ -1170,11 +1331,11 @@ static inline bool phy_interface_mode_is_rgmii(phy_interface_t mode)
 };
 
 /**
- * phy_interface_mode_is_8023z() - does the phy interface mode use 802.3z
+ * phy_interface_mode_is_8023z() - does the PHY interface mode use 802.3z
  *   negotiation
  * @mode: one of &enum phy_interface_t
  *
- * Returns true if the phy interface mode uses the 16-bit negotiation
+ * Returns true if the PHY interface mode uses the 16-bit negotiation
  * word as defined in 802.3z. (See 802.3-2015 37.2.1 Config_Reg encoding)
  */
 static inline bool phy_interface_mode_is_8023z(phy_interface_t mode)
@@ -1193,7 +1354,7 @@ static inline bool phy_interface_is_rgmii(struct phy_device *phydev)
 	return phy_interface_mode_is_rgmii(phydev->interface);
 };
 
-/*
+/**
  * phy_is_pseudo_fixed_link - Convenience function for testing if this
  * PHY is the CPU port facing side of an Ethernet switch, or similar.
  * @phydev: the phy_device struct
@@ -1566,8 +1727,9 @@ static inline int mdiobus_register_board_info(const struct mdio_board_info *i,
 
 
 /**
- * module_phy_driver() - Helper macro for registering PHY drivers
+ * phy_module_driver() - Helper macro for registering PHY drivers
  * @__phy_drivers: array of PHY drivers to register
+ * @__count: Numbers of members in array
  *
  * Helper macro for PHY drivers which do not do anything special in module
  * init/exit. Each module may only use this macro once, and calling it
diff --git a/include/linux/platform_data/macb.h b/include/linux/platform_data/macb.h
deleted file mode 100644
index aa5b5562d6f7..000000000000
--- a/include/linux/platform_data/macb.h
+++ /dev/null
@@ -1,20 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- */
-#ifndef __MACB_PDATA_H__
-#define __MACB_PDATA_H__
-
-#include <linux/clk.h>
-
-/**
- * struct macb_platform_data - platform data for MACB Ethernet
- * @pclk:		platform clock
- * @hclk:		AHB clock
- */
-struct macb_platform_data {
-	struct clk	*pclk;
-	struct clk	*hclk;
-};
-
-#endif /* __MACB_PDATA_H__ */
diff --git a/include/linux/powercap.h b/include/linux/powercap.h
index 4537f57f9e42..3d557bbcd2c7 100644
--- a/include/linux/powercap.h
+++ b/include/linux/powercap.h
@@ -44,19 +44,18 @@ struct powercap_control_type_ops {
 };
 
 /**
- * struct powercap_control_type- Defines a powercap control_type
- * @name:		name of control_type
+ * struct powercap_control_type - Defines a powercap control_type
  * @dev:		device for this control_type
  * @idr:		idr to have unique id for its child
- * @root_node:		Root holding power zones for this control_type
+ * @nr_zones:		counter for number of zones of this type
  * @ops:		Pointer to callback struct
- * @node_lock:		mutex for control type
+ * @lock:		mutex for control type
  * @allocated:		This is possible that client owns the memory
  *			used by this structure. In this case
  *			this flag is set to false by framework to
  *			prevent deallocation during release process.
  *			Otherwise this flag is set to true.
- * @ctrl_inst:		link to the control_type list
+ * @node:		linked-list node
  *
  * Defines powercap control_type. This acts as a container for power
  * zones, which use same method to control power. E.g. RAPL, RAPL-PCI etc.
@@ -129,7 +128,7 @@ struct powercap_zone_ops {
  *			this flag is set to false by framework to
  *			prevent deallocation during release process.
  *			Otherwise this flag is set to true.
- * @constraint_ptr:	List of constraints for this zone.
+ * @constraints:	List of constraints for this zone.
  *
  * This defines a power zone instance. The fields of this structure are
  * private, and should not be used by client drivers.
diff --git a/include/linux/ptp_classify.h b/include/linux/ptp_classify.h
index 8437307cca8c..c6487b7ab026 100644
--- a/include/linux/ptp_classify.h
+++ b/include/linux/ptp_classify.h
@@ -134,5 +134,13 @@ static inline struct ptp_header *ptp_parse_header(struct sk_buff *skb,
 {
 	return NULL;
 }
+static inline u8 ptp_get_msgtype(const struct ptp_header *hdr,
+				 unsigned int type)
+{
+	/* The return is meaningless. The stub function would not be
+	 * executed since no available header from ptp_parse_header.
+	 */
+	return 0;
+}
 #endif
 #endif /* _PTP_CLASSIFY_H_ */
diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h
index 56fa55841d39..57fb295ea41a 100644
--- a/include/linux/qed/qed_if.h
+++ b/include/linux/qed/qed_if.h
@@ -624,6 +624,7 @@ struct qed_dev_info {
 #define QED_MFW_VERSION_3_OFFSET	24
 
 	u32		flash_size;
+	bool		b_arfs_capable;
 	bool		b_inter_pf_switch;
 	bool		tx_switching;
 	bool		rdma_supported;
diff --git a/include/linux/rcupdate_trace.h b/include/linux/rcupdate_trace.h
index aaaac8ac927c..3e7919fc5f34 100644
--- a/include/linux/rcupdate_trace.h
+++ b/include/linux/rcupdate_trace.h
@@ -50,6 +50,7 @@ static inline void rcu_read_lock_trace(void)
 	struct task_struct *t = current;
 
 	WRITE_ONCE(t->trc_reader_nesting, READ_ONCE(t->trc_reader_nesting) + 1);
+	barrier();
 	if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB) &&
 	    t->trc_reader_special.b.need_mb)
 		smp_mb(); // Pairs with update-side barriers
@@ -72,6 +73,9 @@ static inline void rcu_read_unlock_trace(void)
 
 	rcu_lock_release(&rcu_trace_lock_map);
 	nesting = READ_ONCE(t->trc_reader_nesting) - 1;
+	barrier(); // Critical section before disabling.
+	// Disable IPI-based setting of .need_qs.
+	WRITE_ONCE(t->trc_reader_nesting, INT_MIN);
 	if (likely(!READ_ONCE(t->trc_reader_special.s)) || nesting) {
 		WRITE_ONCE(t->trc_reader_nesting, nesting);
 		return;  // We assume shallow reader nesting.
diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h
index 01fc4d9c9c54..8a99279a579b 100644
--- a/include/linux/serial_core.h
+++ b/include/linux/serial_core.h
@@ -248,6 +248,7 @@ struct uart_port {
 
 	unsigned char		hub6;			/* this should be in the 8250 driver */
 	unsigned char		suspended;
+	unsigned char		console_reinit;
 	const char		*name;			/* port name */
 	struct attribute_group	*attr_group;		/* port specific attributes */
 	const struct attribute_group **tty_groups;	/* all attributes (serial core use only) */
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index ed9bea924dc3..42131e325e27 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2548,6 +2548,11 @@ static inline int skb_mac_header_was_set(const struct sk_buff *skb)
 	return skb->mac_header != (typeof(skb->mac_header))~0U;
 }
 
+static inline void skb_unset_mac_header(struct sk_buff *skb)
+{
+	skb->mac_header = (typeof(skb->mac_header))~0U;
+}
+
 static inline void skb_reset_mac_header(struct sk_buff *skb)
 {
 	skb->mac_header = skb->data - skb->head;
@@ -3223,8 +3228,9 @@ static inline int skb_padto(struct sk_buff *skb, unsigned int len)
  *	is untouched. Otherwise it is extended. Returns zero on
  *	success. The skb is freed on error if @free_on_error is true.
  */
-static inline int __skb_put_padto(struct sk_buff *skb, unsigned int len,
-				  bool free_on_error)
+static inline int __must_check __skb_put_padto(struct sk_buff *skb,
+					       unsigned int len,
+					       bool free_on_error)
 {
 	unsigned int size = skb->len;
 
@@ -3247,7 +3253,7 @@ static inline int __skb_put_padto(struct sk_buff *skb, unsigned int len,
  *	is untouched. Otherwise it is extended. Returns zero on
  *	success. The skb is freed on error.
  */
-static inline int skb_put_padto(struct sk_buff *skb, unsigned int len)
+static inline int __must_check skb_put_padto(struct sk_buff *skb, unsigned int len)
 {
 	return __skb_put_padto(skb, len, true);
 }
@@ -3567,6 +3573,9 @@ int skb_ensure_writable(struct sk_buff *skb, int write_len);
 int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci);
 int skb_vlan_pop(struct sk_buff *skb);
 int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci);
+int skb_eth_pop(struct sk_buff *skb);
+int skb_eth_push(struct sk_buff *skb, const unsigned char *dst,
+		 const unsigned char *src);
 int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto,
 		  int mac_len, bool ethernet);
 int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len,
diff --git a/include/linux/sock_diag.h b/include/linux/sock_diag.h
index 15fe980a27ea..0b9ecd8cf979 100644
--- a/include/linux/sock_diag.h
+++ b/include/linux/sock_diag.h
@@ -25,7 +25,19 @@ void sock_diag_unregister(const struct sock_diag_handler *h);
 void sock_diag_register_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh));
 void sock_diag_unregister_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh));
 
-u64 sock_gen_cookie(struct sock *sk);
+u64 __sock_gen_cookie(struct sock *sk);
+
+static inline u64 sock_gen_cookie(struct sock *sk)
+{
+	u64 cookie;
+
+	preempt_disable();
+	cookie = __sock_gen_cookie(sk);
+	preempt_enable();
+
+	return cookie;
+}
+
 int sock_diag_check_cookie(struct sock *sk, const __u32 *cookie);
 void sock_diag_save_cookie(struct sock *sk, __u32 *cookie);
 
diff --git a/include/linux/stackleak.h b/include/linux/stackleak.h
index 3d5c3271a9a8..a59db2f08e76 100644
--- a/include/linux/stackleak.h
+++ b/include/linux/stackleak.h
@@ -25,7 +25,7 @@ static inline void stackleak_task_init(struct task_struct *t)
 
 #ifdef CONFIG_STACKLEAK_RUNTIME_DISABLE
 int stack_erasing_sysctl(struct ctl_table *table, int write,
-			void __user *buffer, size_t *lenp, loff_t *ppos);
+			void *buffer, size_t *lenp, loff_t *ppos);
 #endif
 
 #else /* !CONFIG_GCC_PLUGIN_STACKLEAK */
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index bd964c31d333..628e28903b8b 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -198,5 +198,8 @@ struct plat_stmmacenet_data {
 	int mac_port_sel_speed;
 	bool en_tx_lpi_clockgating;
 	int has_xgmac;
+	bool vlan_fail_q_en;
+	u8 vlan_fail_q;
+	unsigned int eee_usecs_rate;
 };
 #endif
diff --git a/include/linux/wait.h b/include/linux/wait.h
index 898c890fc153..27fb99cfeb02 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -21,6 +21,7 @@ int default_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int
 #define WQ_FLAG_WOKEN		0x02
 #define WQ_FLAG_BOOKMARK	0x04
 #define WQ_FLAG_CUSTOM		0x08
+#define WQ_FLAG_DONE		0x10
 
 /*
  * A single wait-queue entry structure:
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 8caac20556b4..9873e1c8cd16 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -484,6 +484,9 @@ struct hci_dev {
 	enum suspended_state	suspend_state;
 	bool			scanning_paused;
 	bool			suspended;
+	u8			wake_reason;
+	bdaddr_t		wake_addr;
+	u8			wake_addr_type;
 
 	wait_queue_head_t	suspend_wait_q;
 	DECLARE_BITMAP(suspend_tasks, __SUSPEND_NUM_TASKS);
@@ -1750,6 +1753,9 @@ void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 void mgmt_remote_name(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 		      u8 addr_type, s8 rssi, u8 *name, u8 name_len);
 void mgmt_discovering(struct hci_dev *hdev, u8 discovering);
+void mgmt_suspending(struct hci_dev *hdev, u8 state);
+void mgmt_resuming(struct hci_dev *hdev, u8 reason, bdaddr_t *bdaddr,
+		   u8 addr_type);
 bool mgmt_powering_down(struct hci_dev *hdev);
 void mgmt_new_ltk(struct hci_dev *hdev, struct smp_ltk *key, bool persistent);
 void mgmt_new_irk(struct hci_dev *hdev, struct smp_irk *irk, bool persistent);
diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 8f1e6a7a2df8..1d1232917de7 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -665,6 +665,8 @@ struct l2cap_ops {
 	struct sk_buff		*(*alloc_skb) (struct l2cap_chan *chan,
 					       unsigned long hdr_len,
 					       unsigned long len, int nb);
+	int			(*filter) (struct l2cap_chan * chan,
+					   struct sk_buff *skb);
 };
 
 struct l2cap_conn {
diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h
index beae5c3980f0..6b55155e05e9 100644
--- a/include/net/bluetooth/mgmt.h
+++ b/include/net/bluetooth/mgmt.h
@@ -572,6 +572,8 @@ struct mgmt_rp_add_advertising {
 #define MGMT_ADV_FLAG_SEC_1M 		BIT(7)
 #define MGMT_ADV_FLAG_SEC_2M 		BIT(8)
 #define MGMT_ADV_FLAG_SEC_CODED 	BIT(9)
+#define MGMT_ADV_FLAG_CAN_SET_TX_POWER	BIT(10)
+#define MGMT_ADV_FLAG_HW_OFFLOAD	BIT(11)
 
 #define MGMT_ADV_FLAG_SEC_MASK	(MGMT_ADV_FLAG_SEC_1M | MGMT_ADV_FLAG_SEC_2M | \
 				 MGMT_ADV_FLAG_SEC_CODED)
@@ -840,6 +842,7 @@ struct mgmt_ev_device_connected {
 #define MGMT_DEV_DISCONN_LOCAL_HOST	0x02
 #define MGMT_DEV_DISCONN_REMOTE		0x03
 #define MGMT_DEV_DISCONN_AUTH_FAILURE	0x04
+#define MGMT_DEV_DISCONN_LOCAL_HOST_SUSPEND	0x05
 
 #define MGMT_EV_DEVICE_DISCONNECTED	0x000C
 struct mgmt_ev_device_disconnected {
@@ -1028,3 +1031,18 @@ struct mgmt_ev_adv_monitor_added {
 struct mgmt_ev_adv_monitor_removed {
 	__le16 monitor_handle;
 }  __packed;
+
+#define MGMT_EV_CONTROLLER_SUSPEND		0x002d
+struct mgmt_ev_controller_suspend {
+	__u8	suspend_state;
+} __packed;
+
+#define MGMT_EV_CONTROLLER_RESUME		0x002e
+struct mgmt_ev_controller_resume {
+	__u8	wake_reason;
+	struct mgmt_addr_info addr;
+} __packed;
+
+#define MGMT_WAKE_REASON_NON_BT_WAKE		0x0
+#define MGMT_WAKE_REASON_UNEXPECTED		0x1
+#define MGMT_WAKE_REASON_REMOTE_WAKE		0x2
diff --git a/include/net/bpf_sk_storage.h b/include/net/bpf_sk_storage.h
index 119f4c9c3a9c..3c516dd07caf 100644
--- a/include/net/bpf_sk_storage.h
+++ b/include/net/bpf_sk_storage.h
@@ -20,8 +20,6 @@ void bpf_sk_storage_free(struct sock *sk);
 
 extern const struct bpf_func_proto bpf_sk_storage_get_proto;
 extern const struct bpf_func_proto bpf_sk_storage_delete_proto;
-extern const struct bpf_func_proto sk_storage_get_btf_proto;
-extern const struct bpf_func_proto sk_storage_delete_btf_proto;
 
 struct bpf_local_storage_elem;
 struct bpf_sk_storage_diag;
diff --git a/include/net/caif/caif_spi.h b/include/net/caif/caif_spi.h
deleted file mode 100644
index a0bf4cbce71b..000000000000
--- a/include/net/caif/caif_spi.h
+++ /dev/null
@@ -1,155 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright (C) ST-Ericsson AB 2010
- * Author:	Daniel Martensson / Daniel.Martensson@stericsson.com
- */
-
-#ifndef CAIF_SPI_H_
-#define CAIF_SPI_H_
-
-#include <net/caif/caif_device.h>
-
-#define SPI_CMD_WR			0x00
-#define SPI_CMD_RD			0x01
-#define SPI_CMD_EOT			0x02
-#define SPI_CMD_IND			0x04
-
-#define SPI_DMA_BUF_LEN			8192
-
-#define WL_SZ				2	/* 16 bits. */
-#define SPI_CMD_SZ			4	/* 32 bits. */
-#define SPI_IND_SZ			4	/* 32 bits. */
-
-#define SPI_XFER			0
-#define SPI_SS_ON			1
-#define SPI_SS_OFF			2
-#define SPI_TERMINATE			3
-
-/* Minimum time between different levels is 50 microseconds. */
-#define MIN_TRANSITION_TIME_USEC	50
-
-/* Defines for calculating duration of SPI transfers for a particular
- * number of bytes.
- */
-#define SPI_MASTER_CLK_MHZ		13
-#define SPI_XFER_TIME_USEC(bytes, clk) (((bytes) * 8) / clk)
-
-/* Normally this should be aligned on the modem in order to benefit from full
- * duplex transfers. However a size of 8188 provokes errors when running with
- * the modem. These errors occur when packet sizes approaches 4 kB of data.
- */
-#define CAIF_MAX_SPI_FRAME 4092
-
-/* Maximum number of uplink CAIF frames that can reside in the same SPI frame.
- * This number should correspond with the modem setting. The application side
- * CAIF accepts any number of embedded downlink CAIF frames.
- */
-#define CAIF_MAX_SPI_PKTS 9
-
-/* Decides if SPI buffers should be prefilled with 0xFF pattern for easier
- * debugging. Both TX and RX buffers will be filled before the transfer.
- */
-#define CFSPI_DBG_PREFILL		0
-
-/* Structure describing a SPI transfer. */
-struct cfspi_xfer {
-	u16 tx_dma_len;
-	u16 rx_dma_len;
-	void *va_tx[2];
-	dma_addr_t pa_tx[2];
-	void *va_rx;
-	dma_addr_t pa_rx;
-};
-
-/* Structure implemented by the SPI interface. */
-struct cfspi_ifc {
-	void (*ss_cb) (bool assert, struct cfspi_ifc *ifc);
-	void (*xfer_done_cb) (struct cfspi_ifc *ifc);
-	void *priv;
-};
-
-/* Structure implemented by SPI clients. */
-struct cfspi_dev {
-	int (*init_xfer) (struct cfspi_xfer *xfer, struct cfspi_dev *dev);
-	void (*sig_xfer) (bool xfer, struct cfspi_dev *dev);
-	struct cfspi_ifc *ifc;
-	char *name;
-	u32 clk_mhz;
-	void *priv;
-};
-
-/* Enumeration describing the CAIF SPI state. */
-enum cfspi_state {
-	CFSPI_STATE_WAITING = 0,
-	CFSPI_STATE_AWAKE,
-	CFSPI_STATE_FETCH_PKT,
-	CFSPI_STATE_GET_NEXT,
-	CFSPI_STATE_INIT_XFER,
-	CFSPI_STATE_WAIT_ACTIVE,
-	CFSPI_STATE_SIG_ACTIVE,
-	CFSPI_STATE_WAIT_XFER_DONE,
-	CFSPI_STATE_XFER_DONE,
-	CFSPI_STATE_WAIT_INACTIVE,
-	CFSPI_STATE_SIG_INACTIVE,
-	CFSPI_STATE_DELIVER_PKT,
-	CFSPI_STATE_MAX,
-};
-
-/* Structure implemented by SPI physical interfaces. */
-struct cfspi {
-	struct caif_dev_common cfdev;
-	struct net_device *ndev;
-	struct platform_device *pdev;
-	struct sk_buff_head qhead;
-	struct sk_buff_head chead;
-	u16 cmd;
-	u16 tx_cpck_len;
-	u16 tx_npck_len;
-	u16 rx_cpck_len;
-	u16 rx_npck_len;
-	struct cfspi_ifc ifc;
-	struct cfspi_xfer xfer;
-	struct cfspi_dev *dev;
-	unsigned long state;
-	struct work_struct work;
-	struct workqueue_struct *wq;
-	struct list_head list;
-	int    flow_off_sent;
-	u32 qd_low_mark;
-	u32 qd_high_mark;
-	struct completion comp;
-	wait_queue_head_t wait;
-	spinlock_t lock;
-	bool flow_stop;
-	bool slave;
-	bool slave_talked;
-#ifdef CONFIG_DEBUG_FS
-	enum cfspi_state dbg_state;
-	u16 pcmd;
-	u16 tx_ppck_len;
-	u16 rx_ppck_len;
-	struct dentry *dbgfs_dir;
-	struct dentry *dbgfs_state;
-	struct dentry *dbgfs_frame;
-#endif				/* CONFIG_DEBUG_FS */
-};
-
-extern int spi_frm_align;
-extern int spi_up_head_align;
-extern int spi_up_tail_align;
-extern int spi_down_head_align;
-extern int spi_down_tail_align;
-extern struct platform_driver cfspi_spi_driver;
-
-void cfspi_dbg_state(struct cfspi *cfspi, int state);
-int cfspi_xmitfrm(struct cfspi *cfspi, u8 *buf, size_t len);
-int cfspi_xmitlen(struct cfspi *cfspi);
-int cfspi_rxfrm(struct cfspi *cfspi, u8 *buf, size_t len);
-int cfspi_spi_remove(struct platform_device *pdev);
-int cfspi_spi_probe(struct platform_device *pdev);
-int cfspi_xmitfrm(struct cfspi *cfspi, u8 *buf, size_t len);
-int cfspi_xmitlen(struct cfspi *cfspi);
-int cfspi_rxfrm(struct cfspi *cfspi, u8 *buf, size_t len);
-void cfspi_xfer(struct work_struct *work);
-
-#endif				/* CAIF_SPI_H_ */
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 10c2cc8f0efc..aee47f2b5709 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -269,13 +269,23 @@ struct ieee80211_rate {
  * struct ieee80211_he_obss_pd - AP settings for spatial reuse
  *
  * @enable: is the feature enabled.
+ * @sr_ctrl: The SR Control field of SRP element.
+ * @non_srg_max_offset: non-SRG maximum tx power offset
  * @min_offset: minimal tx power offset an associated station shall use
  * @max_offset: maximum tx power offset an associated station shall use
+ * @bss_color_bitmap: bitmap that indicates the BSS color values used by
+ *	members of the SRG
+ * @partial_bssid_bitmap: bitmap that indicates the partial BSSID values
+ *	used by members of the SRG
  */
 struct ieee80211_he_obss_pd {
 	bool enable;
+	u8 sr_ctrl;
+	u8 non_srg_max_offset;
 	u8 min_offset;
 	u8 max_offset;
+	u8 bss_color_bitmap[8];
+	u8 partial_bssid_bitmap[8];
 };
 
 /**
@@ -2096,6 +2106,27 @@ struct cfg80211_scan_info {
 };
 
 /**
+ * struct cfg80211_scan_6ghz_params - relevant for 6 GHz only
+ *
+ * @short_bssid: short ssid to scan for
+ * @bssid: bssid to scan for
+ * @channel_idx: idx of the channel in the channel array in the scan request
+ *	 which the above info relvant to
+ * @unsolicited_probe: the AP transmits unsolicited probe response every 20 TU
+ * @short_ssid_valid: short_ssid is valid and can be used
+ * @psc_no_listen: when set, and the channel is a PSC channel, no need to wait
+ *       20 TUs before starting to send probe requests.
+ */
+struct cfg80211_scan_6ghz_params {
+	u32 short_ssid;
+	u32 channel_idx;
+	u8 bssid[ETH_ALEN];
+	bool unsolicited_probe;
+	bool short_ssid_valid;
+	bool psc_no_listen;
+};
+
+/**
  * struct cfg80211_scan_request - scan request description
  *
  * @ssids: SSIDs to scan for (active scan only)
@@ -2122,6 +2153,10 @@ struct cfg80211_scan_info {
  * @mac_addr_mask: MAC address mask used with randomisation, bits that
  *	are 0 in the mask should be randomised, bits that are 1 should
  *	be taken from the @mac_addr
+ * @scan_6ghz: relevant for split scan request only,
+ *	true if this is the second scan request
+ * @n_6ghz_params: number of 6 GHz params
+ * @scan_6ghz_params: 6 GHz params
  * @bssid: BSSID to scan for (most commonly, the wildcard BSSID)
  */
 struct cfg80211_scan_request {
@@ -2149,6 +2184,9 @@ struct cfg80211_scan_request {
 	struct cfg80211_scan_info info;
 	bool notified;
 	bool no_cck;
+	bool scan_6ghz;
+	u32 n_6ghz_params;
+	struct cfg80211_scan_6ghz_params *scan_6ghz_params;
 
 	/* keep last */
 	struct ieee80211_channel *channels[];
@@ -2528,6 +2566,8 @@ enum cfg80211_assoc_req_flags {
  * @fils_nonces: FILS nonces (part of AAD) for protecting (Re)Association
  *	Request/Response frame or %NULL if FILS is not used. This field starts
  *	with 16 octets of STA Nonce followed by 16 octets of AP Nonce.
+ * @s1g_capa: S1G capability override
+ * @s1g_capa_mask: S1G capability override mask
  */
 struct cfg80211_assoc_request {
 	struct cfg80211_bss *bss;
@@ -2542,6 +2582,7 @@ struct cfg80211_assoc_request {
 	const u8 *fils_kek;
 	size_t fils_kek_len;
 	const u8 *fils_nonces;
+	struct ieee80211_s1g_cap s1g_capa, s1g_capa_mask;
 };
 
 /**
@@ -4217,6 +4258,8 @@ struct cfg80211_ops {
 /**
  * enum wiphy_flags - wiphy capability flags
  *
+ * @WIPHY_FLAG_SPLIT_SCAN_6GHZ: if set to true, the scan request will be split
+ *	 into two, first for legacy bands and second for UHB.
  * @WIPHY_FLAG_NETNS_OK: if not set, do not allow changing the netns of this
  *	wiphy at all
  * @WIPHY_FLAG_PS_ON_BY_DEFAULT: if set to true, powersave will be enabled
@@ -4260,7 +4303,7 @@ struct cfg80211_ops {
 enum wiphy_flags {
 	WIPHY_FLAG_SUPPORTS_EXT_KEK_KCK		= BIT(0),
 	/* use hole at 1 */
-	/* use hole at 2 */
+	WIPHY_FLAG_SPLIT_SCAN_6GHZ		= BIT(2),
 	WIPHY_FLAG_NETNS_OK			= BIT(3),
 	WIPHY_FLAG_PS_ON_BY_DEFAULT		= BIT(4),
 	WIPHY_FLAG_4ADDR_AP			= BIT(5),
diff --git a/include/net/devlink.h b/include/net/devlink.h
index 4883dbae7faf..89ede1ce3a3a 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -550,6 +550,24 @@ enum devlink_param_generic_id {
 /* Firmware bundle identifier */
 #define DEVLINK_INFO_VERSION_GENERIC_FW_BUNDLE_ID	"fw.bundle_id"
 
+/**
+ * struct devlink_flash_update_params - Flash Update parameters
+ * @file_name: the name of the flash firmware file to update from
+ * @component: the flash component to update
+ *
+ * With the exception of file_name, drivers must opt-in to parameters by
+ * setting the appropriate bit in the supported_flash_update_params field in
+ * their devlink_ops structure.
+ */
+struct devlink_flash_update_params {
+	const char *file_name;
+	const char *component;
+	u32 overwrite_mask;
+};
+
+#define DEVLINK_SUPPORT_FLASH_UPDATE_COMPONENT		BIT(0)
+#define DEVLINK_SUPPORT_FLASH_UPDATE_OVERWRITE_MASK	BIT(1)
+
 struct devlink_region;
 struct devlink_info_req;
 
@@ -607,6 +625,22 @@ struct devlink_health_reporter_ops {
 };
 
 /**
+ * struct devlink_trap_metadata - Packet trap metadata.
+ * @trap_name: Trap name.
+ * @trap_group_name: Trap group name.
+ * @input_dev: Input netdevice.
+ * @fa_cookie: Flow action user cookie.
+ * @trap_type: Trap type.
+ */
+struct devlink_trap_metadata {
+	const char *trap_name;
+	const char *trap_group_name;
+	struct net_device *input_dev;
+	const struct flow_action_cookie *fa_cookie;
+	enum devlink_trap_type trap_type;
+};
+
+/**
  * struct devlink_trap_policer - Immutable packet trap policer attributes.
  * @id: Policer identifier.
  * @init_rate: Initial rate in packets / sec.
@@ -750,6 +784,22 @@ enum devlink_trap_generic_id {
 	DEVLINK_TRAP_GENERIC_ID_FLOW_ACTION_SAMPLE,
 	DEVLINK_TRAP_GENERIC_ID_FLOW_ACTION_TRAP,
 	DEVLINK_TRAP_GENERIC_ID_EARLY_DROP,
+	DEVLINK_TRAP_GENERIC_ID_VXLAN_PARSING,
+	DEVLINK_TRAP_GENERIC_ID_LLC_SNAP_PARSING,
+	DEVLINK_TRAP_GENERIC_ID_VLAN_PARSING,
+	DEVLINK_TRAP_GENERIC_ID_PPPOE_PPP_PARSING,
+	DEVLINK_TRAP_GENERIC_ID_MPLS_PARSING,
+	DEVLINK_TRAP_GENERIC_ID_ARP_PARSING,
+	DEVLINK_TRAP_GENERIC_ID_IP_1_PARSING,
+	DEVLINK_TRAP_GENERIC_ID_IP_N_PARSING,
+	DEVLINK_TRAP_GENERIC_ID_GRE_PARSING,
+	DEVLINK_TRAP_GENERIC_ID_UDP_PARSING,
+	DEVLINK_TRAP_GENERIC_ID_TCP_PARSING,
+	DEVLINK_TRAP_GENERIC_ID_IPSEC_PARSING,
+	DEVLINK_TRAP_GENERIC_ID_SCTP_PARSING,
+	DEVLINK_TRAP_GENERIC_ID_DCCP_PARSING,
+	DEVLINK_TRAP_GENERIC_ID_GTP_PARSING,
+	DEVLINK_TRAP_GENERIC_ID_ESP_PARSING,
 
 	/* Add new generic trap IDs above */
 	__DEVLINK_TRAP_GENERIC_ID_MAX,
@@ -785,6 +835,7 @@ enum devlink_trap_group_generic_id {
 	DEVLINK_TRAP_GROUP_GENERIC_ID_PTP_GENERAL,
 	DEVLINK_TRAP_GROUP_GENERIC_ID_ACL_SAMPLE,
 	DEVLINK_TRAP_GROUP_GENERIC_ID_ACL_TRAP,
+	DEVLINK_TRAP_GROUP_GENERIC_ID_PARSER_ERROR_DROPS,
 
 	/* Add new generic trap group IDs above */
 	__DEVLINK_TRAP_GROUP_GENERIC_ID_MAX,
@@ -940,6 +991,39 @@ enum devlink_trap_group_generic_id {
 	"flow_action_trap"
 #define DEVLINK_TRAP_GENERIC_NAME_EARLY_DROP \
 	"early_drop"
+#define DEVLINK_TRAP_GENERIC_NAME_VXLAN_PARSING \
+	"vxlan_parsing"
+#define DEVLINK_TRAP_GENERIC_NAME_LLC_SNAP_PARSING \
+	"llc_snap_parsing"
+#define DEVLINK_TRAP_GENERIC_NAME_VLAN_PARSING \
+	"vlan_parsing"
+#define DEVLINK_TRAP_GENERIC_NAME_PPPOE_PPP_PARSING \
+	"pppoe_ppp_parsing"
+#define DEVLINK_TRAP_GENERIC_NAME_MPLS_PARSING \
+	"mpls_parsing"
+#define DEVLINK_TRAP_GENERIC_NAME_ARP_PARSING \
+	"arp_parsing"
+#define DEVLINK_TRAP_GENERIC_NAME_IP_1_PARSING \
+	"ip_1_parsing"
+#define DEVLINK_TRAP_GENERIC_NAME_IP_N_PARSING \
+	"ip_n_parsing"
+#define DEVLINK_TRAP_GENERIC_NAME_GRE_PARSING \
+	"gre_parsing"
+#define DEVLINK_TRAP_GENERIC_NAME_UDP_PARSING \
+	"udp_parsing"
+#define DEVLINK_TRAP_GENERIC_NAME_TCP_PARSING \
+	"tcp_parsing"
+#define DEVLINK_TRAP_GENERIC_NAME_IPSEC_PARSING \
+	"ipsec_parsing"
+#define DEVLINK_TRAP_GENERIC_NAME_SCTP_PARSING \
+	"sctp_parsing"
+#define DEVLINK_TRAP_GENERIC_NAME_DCCP_PARSING \
+	"dccp_parsing"
+#define DEVLINK_TRAP_GENERIC_NAME_GTP_PARSING \
+	"gtp_parsing"
+#define DEVLINK_TRAP_GENERIC_NAME_ESP_PARSING \
+	"esp_parsing"
+
 
 #define DEVLINK_TRAP_GROUP_GENERIC_NAME_L2_DROPS \
 	"l2_drops"
@@ -991,6 +1075,8 @@ enum devlink_trap_group_generic_id {
 	"acl_sample"
 #define DEVLINK_TRAP_GROUP_GENERIC_NAME_ACL_TRAP \
 	"acl_trap"
+#define DEVLINK_TRAP_GROUP_GENERIC_NAME_PARSER_ERROR_DROPS \
+	"parser_error_drops"
 
 #define DEVLINK_TRAP_GENERIC(_type, _init_action, _id, _group_id,	      \
 			     _metadata_cap)				      \
@@ -1037,6 +1123,12 @@ enum devlink_trap_group_generic_id {
 	}
 
 struct devlink_ops {
+	/**
+	 * @supported_flash_update_params:
+	 * mask of parameters supported by the driver's .flash_update
+	 * implemementation.
+	 */
+	u32 supported_flash_update_params;
 	int (*reload_down)(struct devlink *devlink, bool netns_change,
 			   struct netlink_ext_ack *extack);
 	int (*reload_up)(struct devlink *devlink,
@@ -1097,8 +1189,15 @@ struct devlink_ops {
 				      struct netlink_ext_ack *extack);
 	int (*info_get)(struct devlink *devlink, struct devlink_info_req *req,
 			struct netlink_ext_ack *extack);
-	int (*flash_update)(struct devlink *devlink, const char *file_name,
-			    const char *component,
+	/**
+	 * @flash_update: Device flash update function
+	 *
+	 * Used to perform a flash update for the device. The set of
+	 * parameters supported by the driver should be set in
+	 * supported_flash_update_params.
+	 */
+	int (*flash_update)(struct devlink *devlink,
+			    struct devlink_flash_update_params *params,
 			    struct netlink_ext_ack *extack);
 	/**
 	 * @trap_init: Trap initialization function.
@@ -1144,6 +1243,16 @@ struct devlink_ops {
 			      const struct devlink_trap_policer *policer,
 			      struct netlink_ext_ack *extack);
 	/**
+	 * @trap_group_action_set: Trap group action set function.
+	 *
+	 * If this callback is populated, it will take precedence over looping
+	 * over all traps in a group and calling .trap_action_set().
+	 */
+	int (*trap_group_action_set)(struct devlink *devlink,
+				     const struct devlink_trap_group *group,
+				     enum devlink_trap_action action,
+				     struct netlink_ext_ack *extack);
+	/**
 	 * @trap_policer_init: Trap policer initialization function.
 	 *
 	 * Should be used by device drivers to initialize the trap policer in
diff --git a/include/net/drop_monitor.h b/include/net/drop_monitor.h
deleted file mode 100644
index 3f5b6ddb3179..000000000000
--- a/include/net/drop_monitor.h
+++ /dev/null
@@ -1,36 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-
-#ifndef _NET_DROP_MONITOR_H_
-#define _NET_DROP_MONITOR_H_
-
-#include <linux/ktime.h>
-#include <linux/netdevice.h>
-#include <linux/skbuff.h>
-#include <net/flow_offload.h>
-
-/**
- * struct net_dm_hw_metadata - Hardware-supplied packet metadata.
- * @trap_group_name: Hardware trap group name.
- * @trap_name: Hardware trap name.
- * @input_dev: Input netdevice.
- * @fa_cookie: Flow action user cookie.
- */
-struct net_dm_hw_metadata {
-	const char *trap_group_name;
-	const char *trap_name;
-	struct net_device *input_dev;
-	const struct flow_action_cookie *fa_cookie;
-};
-
-#if IS_REACHABLE(CONFIG_NET_DROP_MONITOR)
-void net_dm_hw_report(struct sk_buff *skb,
-		      const struct net_dm_hw_metadata *hw_metadata);
-#else
-static inline void
-net_dm_hw_report(struct sk_buff *skb,
-		 const struct net_dm_hw_metadata *hw_metadata)
-{
-}
-#endif
-
-#endif /* _NET_DROP_MONITOR_H_ */
diff --git a/include/net/dsa.h b/include/net/dsa.h
index d16057c5987a..8b0696e08cac 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -74,8 +74,8 @@ struct dsa_device_ops {
 	struct sk_buff *(*xmit)(struct sk_buff *skb, struct net_device *dev);
 	struct sk_buff *(*rcv)(struct sk_buff *skb, struct net_device *dev,
 			       struct packet_type *pt);
-	int (*flow_dissect)(const struct sk_buff *skb, __be16 *proto,
-			    int *offset);
+	void (*flow_dissect)(const struct sk_buff *skb, __be16 *proto,
+			     int *offset);
 	/* Used to determine which traffic should match the DSA filter in
 	 * eth_type_trans, and which, if any, should bypass it and be processed
 	 * as regular on the master net device.
@@ -84,6 +84,13 @@ struct dsa_device_ops {
 	unsigned int overhead;
 	const char *name;
 	enum dsa_tag_protocol proto;
+	/* Some tagging protocols either mangle or shift the destination MAC
+	 * address, in which case the DSA master would drop packets on ingress
+	 * if what it understands out of the destination MAC address is not in
+	 * its RX filter.
+	 */
+	bool promisc_on_master;
+	bool tail_tag;
 };
 
 /* This structure defines the control interfaces that are overlayed by the
@@ -301,6 +308,14 @@ struct dsa_switch {
 	 */
 	bool			configure_vlan_while_not_filtering;
 
+	/* If the switch driver always programs the CPU port as egress tagged
+	 * despite the VLAN configuration indicating otherwise, then setting
+	 * @untag_bridge_pvid will force the DSA receive path to pop the bridge's
+	 * default_pvid VLAN tagged frames to offer a consistent behavior
+	 * between a vlan_filtering=0 and vlan_filtering=1 bridge device.
+	 */
+	bool			untag_bridge_pvid;
+
 	/* In case vlan_filtering_is_global is set, the VLAN awareness state
 	 * should be retrieved from here and not from the per-port settings.
 	 */
@@ -705,6 +720,32 @@ static inline bool dsa_can_decode(const struct sk_buff *skb,
 	return false;
 }
 
+/* All DSA tags that push the EtherType to the right (basically all except tail
+ * tags, which don't break dissection) can be treated the same from the
+ * perspective of the flow dissector.
+ *
+ * We need to return:
+ *  - offset: the (B - A) difference between:
+ *    A. the position of the real EtherType and
+ *    B. the current skb->data (aka ETH_HLEN bytes into the frame, aka 2 bytes
+ *       after the normal EtherType was supposed to be)
+ *    The offset in bytes is exactly equal to the tagger overhead (and half of
+ *    that, in __be16 shorts).
+ *
+ *  - proto: the value of the real EtherType.
+ */
+static inline void dsa_tag_generic_flow_dissect(const struct sk_buff *skb,
+						__be16 *proto, int *offset)
+{
+#if IS_ENABLED(CONFIG_NET_DSA)
+	const struct dsa_device_ops *ops = skb->dev->dsa_ptr->tag_ops;
+	int tag_len = ops->overhead;
+
+	*offset = tag_len;
+	*proto = ((__be16 *)skb->data)[(tag_len / 2) - 1];
+#endif
+}
+
 #if IS_ENABLED(CONFIG_NET_DSA)
 static inline int __dsa_netdevice_ops_check(struct net_device *dev)
 {
diff --git a/include/net/flow.h b/include/net/flow.h
index 929d3ca614d0..b2531df3f65f 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -116,6 +116,7 @@ static inline void flowi4_init_output(struct flowi4 *fl4, int oif,
 	fl4->saddr = saddr;
 	fl4->fl4_dport = dport;
 	fl4->fl4_sport = sport;
+	fl4->flowi4_multipath_hash = 0;
 }
 
 /* Reset some input parameters after previous lookup */
diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index b9eb92f3fe86..cb35625d001e 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -41,6 +41,8 @@ struct genl_info;
  *	(private)
  * @ops: the operations supported by this family
  * @n_ops: number of operations supported by this family
+ * @small_ops: the small-struct operations supported by this family
+ * @n_small_ops: number of small-struct operations supported by this family
  */
 struct genl_family {
 	int			id;		/* private */
@@ -48,8 +50,12 @@ struct genl_family {
 	char			name[GENL_NAMSIZ];
 	unsigned int		version;
 	unsigned int		maxattr;
-	bool			netnsok;
-	bool			parallel_ops;
+	unsigned int		mcgrp_offset;	/* private */
+	u8			netnsok:1;
+	u8			parallel_ops:1;
+	u8			n_ops;
+	u8			n_small_ops;
+	u8			n_mcgrps;
 	const struct nla_policy *policy;
 	int			(*pre_doit)(const struct genl_ops *ops,
 					    struct sk_buff *skb,
@@ -58,10 +64,8 @@ struct genl_family {
 					     struct sk_buff *skb,
 					     struct genl_info *info);
 	const struct genl_ops *	ops;
+	const struct genl_small_ops *small_ops;
 	const struct genl_multicast_group *mcgrps;
-	unsigned int		n_ops;
-	unsigned int		n_mcgrps;
-	unsigned int		mcgrp_offset;	/* private */
 	struct module		*module;
 };
 
@@ -108,28 +112,33 @@ enum genl_validate_flags {
 };
 
 /**
- * struct genl_info - info that is available during dumpit op call
- * @family: generic netlink family - for internal genl code usage
- * @ops: generic netlink ops - for internal genl code usage
- * @attrs: netlink attributes
+ * struct genl_small_ops - generic netlink operations (small version)
+ * @cmd: command identifier
+ * @internal_flags: flags used by the family
+ * @flags: flags
+ * @validate: validation flags from enum genl_validate_flags
+ * @doit: standard command callback
+ * @dumpit: callback for dumpers
+ *
+ * This is a cut-down version of struct genl_ops for users who don't need
+ * most of the ancillary infra and want to save space.
  */
-struct genl_dumpit_info {
-	const struct genl_family *family;
-	const struct genl_ops *ops;
-	struct nlattr **attrs;
+struct genl_small_ops {
+	int	(*doit)(struct sk_buff *skb, struct genl_info *info);
+	int	(*dumpit)(struct sk_buff *skb, struct netlink_callback *cb);
+	u8	cmd;
+	u8	internal_flags;
+	u8	flags;
+	u8	validate;
 };
 
-static inline const struct genl_dumpit_info *
-genl_dumpit_info(struct netlink_callback *cb)
-{
-	return cb->data;
-}
-
 /**
  * struct genl_ops - generic netlink operations
  * @cmd: command identifier
  * @internal_flags: flags used by the family
  * @flags: flags
+ * @maxattr: maximum number of attributes supported
+ * @policy: netlink policy (takes precedence over family policy)
  * @doit: standard command callback
  * @start: start callback for dumps
  * @dumpit: callback for dumpers
@@ -142,12 +151,32 @@ struct genl_ops {
 	int		       (*dumpit)(struct sk_buff *skb,
 					 struct netlink_callback *cb);
 	int		       (*done)(struct netlink_callback *cb);
+	const struct nla_policy *policy;
+	unsigned int		maxattr;
 	u8			cmd;
 	u8			internal_flags;
 	u8			flags;
 	u8			validate;
 };
 
+/**
+ * struct genl_info - info that is available during dumpit op call
+ * @family: generic netlink family - for internal genl code usage
+ * @ops: generic netlink ops - for internal genl code usage
+ * @attrs: netlink attributes
+ */
+struct genl_dumpit_info {
+	const struct genl_family *family;
+	struct genl_ops op;
+	struct nlattr **attrs;
+};
+
+static inline const struct genl_dumpit_info *
+genl_dumpit_info(struct netlink_callback *cb)
+{
+	return cb->data;
+}
+
 int genl_register_family(struct genl_family *family);
 int genl_unregister_family(const struct genl_family *family);
 void genl_notify(const struct genl_family *family, struct sk_buff *skb,
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index c738abeb3265..7338b3865a2a 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -96,7 +96,8 @@ struct inet_connection_sock {
 	void (*icsk_clean_acked)(struct sock *sk, u32 acked_seq);
 	struct hlist_node         icsk_listen_portaddr_node;
 	unsigned int		  (*icsk_sync_mss)(struct sock *sk, u32 pmtu);
-	__u8			  icsk_ca_state:6,
+	__u8			  icsk_ca_state:5,
+				  icsk_ca_initialized:1,
 				  icsk_ca_setsockopt:1,
 				  icsk_ca_dst_locked:1;
 	__u8			  icsk_retransmits;
@@ -109,7 +110,7 @@ struct inet_connection_sock {
 		__u8		  pending;	 /* ACK is pending			   */
 		__u8		  quick;	 /* Scheduled number of quick acks	   */
 		__u8		  pingpong;	 /* The session is interactive		   */
-		__u8		  blocked;	 /* Delayed ACK was blocked by socket lock */
+		__u8		  retry;	 /* Number of attempts			   */
 		__u32		  ato;		 /* Predicted tick of soft clock	   */
 		unsigned long	  timeout;	 /* Currently scheduled timeout		   */
 		__u32		  lrcvtime;	 /* timestamp of last received data packet */
@@ -197,7 +198,8 @@ static inline void inet_csk_clear_xmit_timer(struct sock *sk, const int what)
 		sk_stop_timer(sk, &icsk->icsk_retransmit_timer);
 #endif
 	} else if (what == ICSK_TIME_DACK) {
-		icsk->icsk_ack.blocked = icsk->icsk_ack.pending = 0;
+		icsk->icsk_ack.pending = 0;
+		icsk->icsk_ack.retry = 0;
 #ifdef INET_CSK_CLEAR_TIMERS
 		sk_stop_timer(sk, &icsk->icsk_delack_timer);
 #endif
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index e90089d104b0..4747d446179a 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -627,6 +627,7 @@ struct ieee80211_fils_discovery {
  * @fils_discovery: FILS discovery configuration
  * @unsol_bcast_probe_resp_interval: Unsolicited broadcast probe response
  *	interval.
+ * @s1g: BSS is S1G BSS (affects Association Request format).
  */
 struct ieee80211_bss_conf {
 	const u8 *bssid;
@@ -696,6 +697,7 @@ struct ieee80211_bss_conf {
 	struct cfg80211_he_bss_color he_bss_color;
 	struct ieee80211_fils_discovery fils_discovery;
 	u32 unsol_bcast_probe_resp_interval;
+	bool s1g;
 };
 
 /**
@@ -833,6 +835,8 @@ enum mac80211_tx_info_flags {
 
 #define IEEE80211_TX_CTL_STBC_SHIFT		23
 
+#define IEEE80211_TX_RC_S1G_MCS IEEE80211_TX_RC_VHT_MCS
+
 /**
  * enum mac80211_tx_control_flags - flags to describe transmit control
  *
@@ -5403,11 +5407,15 @@ void ieee80211_sched_scan_stopped(struct ieee80211_hw *hw);
  * @IEEE80211_IFACE_ITER_RESUME_ALL: During resume, iterate over all
  *	interfaces, even if they haven't been re-added to the driver yet.
  * @IEEE80211_IFACE_ITER_ACTIVE: Iterate only active interfaces (netdev is up).
+ * @IEEE80211_IFACE_SKIP_SDATA_NOT_IN_DRIVER: Skip any interfaces where SDATA
+ *	is not in the driver.  This may fix crashes during firmware recovery
+ *	for instance.
  */
 enum ieee80211_interface_iteration_flags {
 	IEEE80211_IFACE_ITER_NORMAL	= 0,
 	IEEE80211_IFACE_ITER_RESUME_ALL	= BIT(0),
 	IEEE80211_IFACE_ITER_ACTIVE	= BIT(1),
+	IEEE80211_IFACE_SKIP_SDATA_NOT_IN_DRIVER	= BIT(2),
 };
 
 /**
diff --git a/include/net/mptcp.h b/include/net/mptcp.h
index 3525d2822abe..753ba7e755d6 100644
--- a/include/net/mptcp.h
+++ b/include/net/mptcp.h
@@ -85,8 +85,7 @@ bool mptcp_synack_options(const struct request_sock *req, unsigned int *size,
 bool mptcp_established_options(struct sock *sk, struct sk_buff *skb,
 			       unsigned int *size, unsigned int remaining,
 			       struct mptcp_out_options *opts);
-void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb,
-			    struct tcp_options_received *opt_rx);
+void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb);
 
 void mptcp_write_options(__be32 *ptr, struct mptcp_out_options *opts);
 
@@ -185,8 +184,7 @@ static inline bool mptcp_established_options(struct sock *sk,
 }
 
 static inline void mptcp_incoming_options(struct sock *sk,
-					  struct sk_buff *skb,
-					  struct tcp_options_received *opt_rx)
+					  struct sk_buff *skb)
 {
 }
 
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 2ee5901bec7a..22bc07f4b043 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -230,7 +230,7 @@ extern struct list_head net_namespace_list;
 struct net *get_net_ns_by_pid(pid_t pid);
 struct net *get_net_ns_by_fd(int fd);
 
-u64 net_gen_cookie(struct net *net);
+u64 __net_gen_cookie(struct net *net);
 
 #ifdef CONFIG_SYSCTL
 void ipx_register_sysctl(void);
diff --git a/include/net/netlink.h b/include/net/netlink.h
index fdd317f8fde4..5a5ff97cc596 100644
--- a/include/net/netlink.h
+++ b/include/net/netlink.h
@@ -730,7 +730,6 @@ static inline int __nlmsg_parse(const struct nlmsghdr *nlh, int hdrlen,
  * @hdrlen: length of family specific header
  * @tb: destination array with maxtype+1 elements
  * @maxtype: maximum attribute type to be expected
- * @validate: validation strictness
  * @extack: extended ACK report struct
  *
  * See nla_parse()
@@ -828,7 +827,6 @@ static inline int nla_validate_deprecated(const struct nlattr *head, int len,
  * @len: length of attribute stream
  * @maxtype: maximum attribute type to be expected
  * @policy: validation policy
- * @validate: validation strictness
  * @extack: extended ACK report struct
  *
  * Validates all attributes in the specified attribute stream against the
@@ -1937,10 +1935,17 @@ void nla_get_range_unsigned(const struct nla_policy *pt,
 void nla_get_range_signed(const struct nla_policy *pt,
 			  struct netlink_range_validation_signed *range);
 
-int netlink_policy_dump_start(const struct nla_policy *policy,
-			      unsigned int maxtype,
-			      unsigned long *state);
-bool netlink_policy_dump_loop(unsigned long *state);
-int netlink_policy_dump_write(struct sk_buff *skb, unsigned long state);
+struct netlink_policy_dump_state;
+
+int netlink_policy_dump_add_policy(struct netlink_policy_dump_state **pstate,
+				   const struct nla_policy *policy,
+				   unsigned int maxtype);
+int netlink_policy_dump_get_policy_idx(struct netlink_policy_dump_state *state,
+				       const struct nla_policy *policy,
+				       unsigned int maxtype);
+bool netlink_policy_dump_loop(struct netlink_policy_dump_state *state);
+int netlink_policy_dump_write(struct sk_buff *skb,
+			      struct netlink_policy_dump_state *state);
+void netlink_policy_dump_free(struct netlink_policy_dump_state *state);
 
 #endif
diff --git a/include/net/netns/nftables.h b/include/net/netns/nftables.h
index a1a8d45adb42..6c0806bd8d1e 100644
--- a/include/net/netns/nftables.h
+++ b/include/net/netns/nftables.h
@@ -8,6 +8,7 @@ struct netns_nftables {
 	struct list_head	tables;
 	struct list_head	commit_list;
 	struct list_head	module_list;
+	struct list_head	notify_list;
 	struct mutex		commit_mutex;
 	unsigned int		base_seq;
 	u8			gencursor;
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index b33f1aefad09..0bdff38eb4bb 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -226,12 +226,14 @@ struct sctp_sock {
 		data_ready_signalled:1;
 
 	atomic_t pd_mode;
+
+	/* Fields after this point will be skipped on copies, like on accept
+	 * and peeloff operations
+	 */
+
 	/* Receive to here while partial delivery is in effect. */
 	struct sk_buff_head pd_lobby;
 
-	/* These must be the last fields, as they will skipped on copies,
-	 * like on accept and peeloff operations
-	 */
 	struct list_head auto_asconf_list;
 	int do_auto_asconf;
 };
diff --git a/include/net/smc.h b/include/net/smc.h
index 646feb4bc75f..e441aa97ad61 100644
--- a/include/net/smc.h
+++ b/include/net/smc.h
@@ -37,6 +37,8 @@ struct smcd_dmb {
 #define ISM_EVENT_GID	1
 #define ISM_EVENT_SWR	2
 
+#define ISM_RESERVED_VLANID	0x1FFF
+
 #define ISM_ERROR	0xFFFF
 
 struct smcd_event {
@@ -63,6 +65,8 @@ struct smcd_ops {
 	int (*move_data)(struct smcd_dev *dev, u64 dmb_tok, unsigned int idx,
 			 bool sf, unsigned int offset, void *data,
 			 unsigned int size);
+	void (*get_system_eid)(struct smcd_dev *dev, u8 **eid);
+	u16 (*get_chid)(struct smcd_dev *dev);
 };
 
 struct smcd_dev {
diff --git a/include/net/sock.h b/include/net/sock.h
index eaa5cac5e836..a5c6ae78df77 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2195,6 +2195,8 @@ void sk_reset_timer(struct sock *sk, struct timer_list *timer,
 
 void sk_stop_timer(struct sock *sk, struct timer_list *timer);
 
+void sk_stop_timer_sync(struct sock *sk, struct timer_list *timer);
+
 int __sk_queue_drop_skb(struct sock *sk, struct sk_buff_head *sk_queue,
 			struct sk_buff *skb, unsigned int flags,
 			void (*destructor)(struct sock *sk,
diff --git a/include/net/tc_act/tc_vlan.h b/include/net/tc_act/tc_vlan.h
index 4e2502408c31..f051046ba034 100644
--- a/include/net/tc_act/tc_vlan.h
+++ b/include/net/tc_act/tc_vlan.h
@@ -11,6 +11,8 @@
 
 struct tcf_vlan_params {
 	int               tcfv_action;
+	unsigned char     tcfv_push_dst[ETH_ALEN];
+	unsigned char     tcfv_push_src[ETH_ALEN];
 	u16               tcfv_push_vid;
 	__be16            tcfv_push_proto;
 	u8                tcfv_push_prio;
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 852f0d71dd40..3601dea931a6 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1104,7 +1104,7 @@ void tcp_get_available_congestion_control(char *buf, size_t len);
 void tcp_get_allowed_congestion_control(char *buf, size_t len);
 int tcp_set_allowed_congestion_control(char *allowed);
 int tcp_set_congestion_control(struct sock *sk, const char *name, bool load,
-			       bool reinit, bool cap_net_admin);
+			       bool cap_net_admin);
 u32 tcp_slow_start(struct tcp_sock *tp, u32 acked);
 void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w, u32 acked);
 
diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h
index 94bb7a882250..2ea453dac876 100644
--- a/include/net/udp_tunnel.h
+++ b/include/net/udp_tunnel.h
@@ -200,11 +200,27 @@ enum udp_tunnel_nic_info_flags {
 	UDP_TUNNEL_NIC_INFO_STATIC_IANA_VXLAN	= BIT(3),
 };
 
+struct udp_tunnel_nic;
+
+#define UDP_TUNNEL_NIC_MAX_SHARING_DEVICES	(U16_MAX / 2)
+
+struct udp_tunnel_nic_shared {
+	struct udp_tunnel_nic *udp_tunnel_nic_info;
+
+	struct list_head devices;
+};
+
+struct udp_tunnel_nic_shared_node {
+	struct net_device *dev;
+	struct list_head list;
+};
+
 /**
  * struct udp_tunnel_nic_info - driver UDP tunnel offload information
  * @set_port:	callback for adding a new port
  * @unset_port:	callback for removing a port
  * @sync_table:	callback for syncing the entire port table at once
+ * @shared:	reference to device global state (optional)
  * @flags:	device flags from enum udp_tunnel_nic_info_flags
  * @tables:	UDP port tables this device has
  * @tables.n_entries:		number of entries in this table
@@ -213,6 +229,12 @@ enum udp_tunnel_nic_info_flags {
  * Drivers are expected to provide either @set_port and @unset_port callbacks
  * or the @sync_table callback. Callbacks are invoked with rtnl lock held.
  *
+ * Devices which (misguidedly) share the UDP tunnel port table across multiple
+ * netdevs should allocate an instance of struct udp_tunnel_nic_shared and
+ * point @shared at it.
+ * There must never be more than %UDP_TUNNEL_NIC_MAX_SHARING_DEVICES devices
+ * sharing a table.
+ *
  * Known limitations:
  *  - UDP tunnel port notifications are fundamentally best-effort -
  *    it is likely the driver will both see skbs which use a UDP tunnel port,
@@ -234,6 +256,8 @@ struct udp_tunnel_nic_info {
 	/* all at once */
 	int (*sync_table)(struct net_device *dev, unsigned int table);
 
+	struct udp_tunnel_nic_shared *shared;
+
 	unsigned int flags;
 
 	struct udp_tunnel_nic_table_info {
diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index 3a41627cbdfe..08537aa14f7c 100644
--- a/include/net/vxlan.h
+++ b/include/net/vxlan.h
@@ -121,6 +121,9 @@ struct vxlanhdr_gbp {
 #define VXLAN_GBP_POLICY_APPLIED	(BIT(3) << 16)
 #define VXLAN_GBP_ID_MASK		(0xFFFF)
 
+#define VXLAN_GBP_MASK (VXLAN_GBP_DONT_LEARN | VXLAN_GBP_POLICY_APPLIED | \
+			VXLAN_GBP_ID_MASK)
+
 /*
  * VXLAN Generic Protocol Extension (VXLAN_F_GPE):
  * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 2737d24ec244..53618a31634b 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -2000,6 +2000,39 @@ static inline int xfrm_tunnel_check(struct sk_buff *skb, struct xfrm_state *x,
 	return 0;
 }
 
+extern const int xfrm_msg_min[XFRM_NR_MSGTYPES];
+extern const struct nla_policy xfrma_policy[XFRMA_MAX+1];
+
+struct xfrm_translator {
+	/* Allocate frag_list and put compat translation there */
+	int (*alloc_compat)(struct sk_buff *skb, const struct nlmsghdr *src);
+
+	/* Allocate nlmsg with 64-bit translaton of received 32-bit message */
+	struct nlmsghdr *(*rcv_msg_compat)(const struct nlmsghdr *nlh,
+			int maxtype, const struct nla_policy *policy,
+			struct netlink_ext_ack *extack);
+
+	/* Translate 32-bit user_policy from sockptr */
+	int (*xlate_user_policy_sockptr)(u8 **pdata32, int optlen);
+
+	struct module *owner;
+};
+
+#if IS_ENABLED(CONFIG_XFRM_USER_COMPAT)
+extern int xfrm_register_translator(struct xfrm_translator *xtr);
+extern int xfrm_unregister_translator(struct xfrm_translator *xtr);
+extern struct xfrm_translator *xfrm_get_translator(void);
+extern void xfrm_put_translator(struct xfrm_translator *xtr);
+#else
+static inline struct xfrm_translator *xfrm_get_translator(void)
+{
+	return NULL;
+}
+static inline void xfrm_put_translator(struct xfrm_translator *xtr)
+{
+}
+#endif
+
 #if IS_ENABLED(CONFIG_IPV6)
 static inline bool xfrm6_local_dontfrag(const struct sock *sk)
 {
diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h
index da369b12005f..46608494616f 100644
--- a/include/soc/mscc/ocelot.h
+++ b/include/soc/mscc/ocelot.h
@@ -101,6 +101,7 @@
 #define OCELOT_TAG_LEN			16
 #define OCELOT_SHORT_PREFIX_LEN		4
 #define OCELOT_LONG_PREFIX_LEN		16
+#define OCELOT_TOTAL_TAG_LEN	(OCELOT_SHORT_PREFIX_LEN + OCELOT_TAG_LEN)
 
 #define OCELOT_SPEED_2500		0
 #define OCELOT_SPEED_1000		1
@@ -122,6 +123,8 @@ enum ocelot_target {
 	QSYS,
 	REW,
 	SYS,
+	S0,
+	S1,
 	S2,
 	HSIO,
 	PTP,
@@ -392,13 +395,6 @@ enum ocelot_reg {
 	SYS_CM_DATA_RD,
 	SYS_CM_OP,
 	SYS_CM_DATA,
-	S2_CORE_UPDATE_CTRL = S2 << TARGET_OFFSET,
-	S2_CORE_MV_CFG,
-	S2_CACHE_ENTRY_DAT,
-	S2_CACHE_MASK_DAT,
-	S2_CACHE_ACTION_DAT,
-	S2_CACHE_CNT_DAT,
-	S2_CACHE_TG_DAT,
 	PTP_PIN_CFG = PTP << TARGET_OFFSET,
 	PTP_PIN_TOD_SEC_MSB,
 	PTP_PIN_TOD_SEC_LSB,
@@ -517,6 +513,29 @@ enum ocelot_regfield {
 	REGFIELD_MAX
 };
 
+enum {
+	/* VCAP_CORE_CFG */
+	VCAP_CORE_UPDATE_CTRL,
+	VCAP_CORE_MV_CFG,
+	/* VCAP_CORE_CACHE */
+	VCAP_CACHE_ENTRY_DAT,
+	VCAP_CACHE_MASK_DAT,
+	VCAP_CACHE_ACTION_DAT,
+	VCAP_CACHE_CNT_DAT,
+	VCAP_CACHE_TG_DAT,
+	/* VCAP_CONST */
+	VCAP_CONST_VCAP_VER,
+	VCAP_CONST_ENTRY_WIDTH,
+	VCAP_CONST_ENTRY_CNT,
+	VCAP_CONST_ENTRY_SWCNT,
+	VCAP_CONST_ENTRY_TG_WIDTH,
+	VCAP_CONST_ACTION_DEF_CNT,
+	VCAP_CONST_ACTION_WIDTH,
+	VCAP_CONST_CNT_WIDTH,
+	VCAP_CONST_CORE_CNT,
+	VCAP_CONST_IF_CNT,
+};
+
 enum ocelot_ptp_pins {
 	PTP_PIN_0,
 	PTP_PIN_1,
@@ -540,6 +559,8 @@ enum ocelot_tag_prefix {
 struct ocelot;
 
 struct ocelot_ops {
+	struct net_device *(*port_to_netdev)(struct ocelot *ocelot, int port);
+	int (*netdev_to_port)(struct net_device *dev);
 	int (*reset)(struct ocelot *ocelot);
 	u16 (*wm_enc)(u16 value);
 };
@@ -566,6 +587,7 @@ struct ocelot_port {
 	u8				ptp_cmd;
 	struct sk_buff_head		tx_skbs;
 	u8				ts_id;
+	spinlock_t			ts_id_lock;
 
 	phy_interface_t			phy_mode;
 
@@ -611,11 +633,9 @@ struct ocelot {
 
 	struct list_head		multicast;
 
-	struct ocelot_vcap_block	block;
-
-	const struct vcap_field		*vcap_is2_keys;
-	const struct vcap_field		*vcap_is2_actions;
-	const struct vcap_props		*vcap;
+	struct list_head		dummy_rules;
+	struct ocelot_vcap_block	block[3];
+	struct vcap_props		*vcap;
 
 	/* Workqueue to check statistics for overflow with its lock */
 	struct mutex			stats_lock;
@@ -659,6 +679,24 @@ struct ocelot_policer {
 #define ocelot_fields_write(ocelot, id, reg, val) regmap_fields_write((ocelot)->regfields[(reg)], (id), (val))
 #define ocelot_fields_read(ocelot, id, reg, val) regmap_fields_read((ocelot)->regfields[(reg)], (id), (val))
 
+#define ocelot_target_read_ix(ocelot, target, reg, gi, ri) \
+	__ocelot_target_read_ix(ocelot, target, reg, reg##_GSZ * (gi) + reg##_RSZ * (ri))
+#define ocelot_target_read_gix(ocelot, target, reg, gi) \
+	__ocelot_target_read_ix(ocelot, target, reg, reg##_GSZ * (gi))
+#define ocelot_target_read_rix(ocelot, target, reg, ri) \
+	__ocelot_target_read_ix(ocelot, target, reg, reg##_RSZ * (ri))
+#define ocelot_target_read(ocelot, target, reg) \
+	__ocelot_target_read_ix(ocelot, target, reg, 0)
+
+#define ocelot_target_write_ix(ocelot, target, val, reg, gi, ri) \
+	__ocelot_target_write_ix(ocelot, target, val, reg, reg##_GSZ * (gi) + reg##_RSZ * (ri))
+#define ocelot_target_write_gix(ocelot, target, val, reg, gi) \
+	__ocelot_target_write_ix(ocelot, target, val, reg, reg##_GSZ * (gi))
+#define ocelot_target_write_rix(ocelot, target, val, reg, ri) \
+	__ocelot_target_write_ix(ocelot, target, val, reg, reg##_RSZ * (ri))
+#define ocelot_target_write(ocelot, target, val, reg) \
+	__ocelot_target_write_ix(ocelot, target, val, reg, 0)
+
 /* I/O */
 u32 ocelot_port_readl(struct ocelot_port *port, u32 reg);
 void ocelot_port_writel(struct ocelot_port *port, u32 val, u32 reg);
@@ -666,17 +704,19 @@ u32 __ocelot_read_ix(struct ocelot *ocelot, u32 reg, u32 offset);
 void __ocelot_write_ix(struct ocelot *ocelot, u32 val, u32 reg, u32 offset);
 void __ocelot_rmw_ix(struct ocelot *ocelot, u32 val, u32 mask, u32 reg,
 		     u32 offset);
+u32 __ocelot_target_read_ix(struct ocelot *ocelot, enum ocelot_target target,
+			    u32 reg, u32 offset);
+void __ocelot_target_write_ix(struct ocelot *ocelot, enum ocelot_target target,
+			      u32 val, u32 reg, u32 offset);
 
 /* Hardware initialization */
 int ocelot_regfields_init(struct ocelot *ocelot,
 			  const struct reg_field *const regfields);
 struct regmap *ocelot_regmap_init(struct ocelot *ocelot, struct resource *res);
-void ocelot_configure_cpu(struct ocelot *ocelot, int npi,
-			  enum ocelot_tag_prefix injection,
-			  enum ocelot_tag_prefix extraction);
 int ocelot_init(struct ocelot *ocelot);
 void ocelot_deinit(struct ocelot *ocelot);
 void ocelot_init_port(struct ocelot *ocelot, int port);
+void ocelot_deinit_port(struct ocelot *ocelot, int port);
 
 /* DSA callbacks */
 void ocelot_port_enable(struct ocelot *ocelot, int port,
@@ -708,8 +748,8 @@ int ocelot_vlan_add(struct ocelot *ocelot, int port, u16 vid, bool pvid,
 int ocelot_vlan_del(struct ocelot *ocelot, int port, u16 vid);
 int ocelot_hwstamp_get(struct ocelot *ocelot, int port, struct ifreq *ifr);
 int ocelot_hwstamp_set(struct ocelot *ocelot, int port, struct ifreq *ifr);
-int ocelot_port_add_txtstamp_skb(struct ocelot_port *ocelot_port,
-				 struct sk_buff *skb);
+void ocelot_port_add_txtstamp_skb(struct ocelot *ocelot, int port,
+				  struct sk_buff *clone);
 void ocelot_get_txtstamp(struct ocelot *ocelot);
 void ocelot_port_set_maxlen(struct ocelot *ocelot, int port, size_t sdu);
 int ocelot_get_max_mtu(struct ocelot *ocelot, int port);
diff --git a/include/soc/mscc/ocelot_vcap.h b/include/soc/mscc/ocelot_vcap.h
index 5748373ab4d3..96300adf3648 100644
--- a/include/soc/mscc/ocelot_vcap.h
+++ b/include/soc/mscc/ocelot_vcap.h
@@ -6,17 +6,22 @@
 #ifndef _OCELOT_VCAP_H_
 #define _OCELOT_VCAP_H_
 
+#include <soc/mscc/ocelot.h>
+
 /* =================================================================
  *  VCAP Common
  * =================================================================
  */
 
 enum {
-	/* VCAP_IS1, */
+	VCAP_ES0,
+	VCAP_IS1,
 	VCAP_IS2,
-	/* VCAP_ES0, */
+	__VCAP_COUNT,
 };
 
+#define OCELOT_NUM_VCAP_BLOCKS		__VCAP_COUNT
+
 struct vcap_props {
 	u16 tg_width; /* Type-group width (in bits) */
 	u16 sw_count; /* Sub word count */
@@ -33,6 +38,11 @@ struct vcap_props {
 	} action_table[2];
 	u16 counter_words; /* Number of counter words */
 	u16 counter_width; /* Counter width (in bits) */
+
+	enum ocelot_target		target;
+
+	const struct vcap_field		*keys;
+	const struct vcap_field		*actions;
 };
 
 /* VCAP Type-Group values */
@@ -41,6 +51,61 @@ struct vcap_props {
 #define VCAP_TG_HALF 2 /* Half entry */
 #define VCAP_TG_QUARTER 3 /* Quarter entry */
 
+#define VCAP_CORE_UPDATE_CTRL_UPDATE_CMD(x)      (((x) << 22) & GENMASK(24, 22))
+#define VCAP_CORE_UPDATE_CTRL_UPDATE_CMD_M       GENMASK(24, 22)
+#define VCAP_CORE_UPDATE_CTRL_UPDATE_CMD_X(x)    (((x) & GENMASK(24, 22)) >> 22)
+#define VCAP_CORE_UPDATE_CTRL_UPDATE_ENTRY_DIS   BIT(21)
+#define VCAP_CORE_UPDATE_CTRL_UPDATE_ACTION_DIS  BIT(20)
+#define VCAP_CORE_UPDATE_CTRL_UPDATE_CNT_DIS     BIT(19)
+#define VCAP_CORE_UPDATE_CTRL_UPDATE_ADDR(x)     (((x) << 3) & GENMASK(18, 3))
+#define VCAP_CORE_UPDATE_CTRL_UPDATE_ADDR_M      GENMASK(18, 3)
+#define VCAP_CORE_UPDATE_CTRL_UPDATE_ADDR_X(x)   (((x) & GENMASK(18, 3)) >> 3)
+#define VCAP_CORE_UPDATE_CTRL_UPDATE_SHOT        BIT(2)
+#define VCAP_CORE_UPDATE_CTRL_CLEAR_CACHE        BIT(1)
+#define VCAP_CORE_UPDATE_CTRL_MV_TRAFFIC_IGN     BIT(0)
+
+#define VCAP_CORE_MV_CFG_MV_NUM_POS(x)           (((x) << 16) & GENMASK(31, 16))
+#define VCAP_CORE_MV_CFG_MV_NUM_POS_M            GENMASK(31, 16)
+#define VCAP_CORE_MV_CFG_MV_NUM_POS_X(x)         (((x) & GENMASK(31, 16)) >> 16)
+#define VCAP_CORE_MV_CFG_MV_SIZE(x)              ((x) & GENMASK(15, 0))
+#define VCAP_CORE_MV_CFG_MV_SIZE_M               GENMASK(15, 0)
+
+#define VCAP_CACHE_ENTRY_DAT_RSZ                 0x4
+
+#define VCAP_CACHE_MASK_DAT_RSZ                  0x4
+
+#define VCAP_CACHE_ACTION_DAT_RSZ                0x4
+
+#define VCAP_CACHE_CNT_DAT_RSZ                   0x4
+
+#define VCAP_STICKY_VCAP_ROW_DELETED_STICKY      BIT(0)
+
+#define TCAM_BIST_CTRL_TCAM_BIST                 BIT(1)
+#define TCAM_BIST_CTRL_TCAM_INIT                 BIT(0)
+
+#define TCAM_BIST_CFG_TCAM_BIST_SOE_ENA          BIT(8)
+#define TCAM_BIST_CFG_TCAM_HCG_DIS               BIT(7)
+#define TCAM_BIST_CFG_TCAM_CG_DIS                BIT(6)
+#define TCAM_BIST_CFG_TCAM_BIAS(x)               ((x) & GENMASK(5, 0))
+#define TCAM_BIST_CFG_TCAM_BIAS_M                GENMASK(5, 0)
+
+#define TCAM_BIST_STAT_BIST_RT_ERR               BIT(15)
+#define TCAM_BIST_STAT_BIST_PENC_ERR             BIT(14)
+#define TCAM_BIST_STAT_BIST_COMP_ERR             BIT(13)
+#define TCAM_BIST_STAT_BIST_ADDR_ERR             BIT(12)
+#define TCAM_BIST_STAT_BIST_BL1E_ERR             BIT(11)
+#define TCAM_BIST_STAT_BIST_BL1_ERR              BIT(10)
+#define TCAM_BIST_STAT_BIST_BL0E_ERR             BIT(9)
+#define TCAM_BIST_STAT_BIST_BL0_ERR              BIT(8)
+#define TCAM_BIST_STAT_BIST_PH1_ERR              BIT(7)
+#define TCAM_BIST_STAT_BIST_PH0_ERR              BIT(6)
+#define TCAM_BIST_STAT_BIST_PV1_ERR              BIT(5)
+#define TCAM_BIST_STAT_BIST_PV0_ERR              BIT(4)
+#define TCAM_BIST_STAT_BIST_RUN                  BIT(3)
+#define TCAM_BIST_STAT_BIST_ERR                  BIT(2)
+#define TCAM_BIST_STAT_BIST_BUSY                 BIT(1)
+#define TCAM_BIST_STAT_TCAM_RDY                  BIT(0)
+
 /* =================================================================
  *  VCAP IS2
  * =================================================================
@@ -202,4 +267,137 @@ enum vcap_is2_action_field {
 	VCAP_IS2_ACT_HIT_CNT,
 };
 
+/* =================================================================
+ *  VCAP IS1
+ * =================================================================
+ */
+
+/* IS1 half key types */
+#define IS1_TYPE_S1_NORMAL 0
+#define IS1_TYPE_S1_5TUPLE_IP4 1
+
+/* IS1 full key types */
+#define IS1_TYPE_S1_NORMAL_IP6 0
+#define IS1_TYPE_S1_7TUPLE 1
+#define IS2_TYPE_S1_5TUPLE_IP6 2
+
+enum {
+	IS1_ACTION_TYPE_NORMAL,
+	IS1_ACTION_TYPE_MAX,
+};
+
+enum vcap_is1_half_key_field {
+	VCAP_IS1_HK_TYPE,
+	VCAP_IS1_HK_LOOKUP,
+	VCAP_IS1_HK_IGR_PORT_MASK,
+	VCAP_IS1_HK_RSV,
+	VCAP_IS1_HK_OAM_Y1731,
+	VCAP_IS1_HK_L2_MC,
+	VCAP_IS1_HK_L2_BC,
+	VCAP_IS1_HK_IP_MC,
+	VCAP_IS1_HK_VLAN_TAGGED,
+	VCAP_IS1_HK_VLAN_DBL_TAGGED,
+	VCAP_IS1_HK_TPID,
+	VCAP_IS1_HK_VID,
+	VCAP_IS1_HK_DEI,
+	VCAP_IS1_HK_PCP,
+	/* Specific Fields for IS1 Half Key S1_NORMAL */
+	VCAP_IS1_HK_L2_SMAC,
+	VCAP_IS1_HK_ETYPE_LEN,
+	VCAP_IS1_HK_ETYPE,
+	VCAP_IS1_HK_IP_SNAP,
+	VCAP_IS1_HK_IP4,
+	VCAP_IS1_HK_L3_FRAGMENT,
+	VCAP_IS1_HK_L3_FRAG_OFS_GT0,
+	VCAP_IS1_HK_L3_OPTIONS,
+	VCAP_IS1_HK_L3_DSCP,
+	VCAP_IS1_HK_L3_IP4_SIP,
+	VCAP_IS1_HK_TCP_UDP,
+	VCAP_IS1_HK_TCP,
+	VCAP_IS1_HK_L4_SPORT,
+	VCAP_IS1_HK_L4_RNG,
+	/* Specific Fields for IS1 Half Key S1_5TUPLE_IP4 */
+	VCAP_IS1_HK_IP4_INNER_TPID,
+	VCAP_IS1_HK_IP4_INNER_VID,
+	VCAP_IS1_HK_IP4_INNER_DEI,
+	VCAP_IS1_HK_IP4_INNER_PCP,
+	VCAP_IS1_HK_IP4_IP4,
+	VCAP_IS1_HK_IP4_L3_FRAGMENT,
+	VCAP_IS1_HK_IP4_L3_FRAG_OFS_GT0,
+	VCAP_IS1_HK_IP4_L3_OPTIONS,
+	VCAP_IS1_HK_IP4_L3_DSCP,
+	VCAP_IS1_HK_IP4_L3_IP4_DIP,
+	VCAP_IS1_HK_IP4_L3_IP4_SIP,
+	VCAP_IS1_HK_IP4_L3_PROTO,
+	VCAP_IS1_HK_IP4_TCP_UDP,
+	VCAP_IS1_HK_IP4_TCP,
+	VCAP_IS1_HK_IP4_L4_RNG,
+	VCAP_IS1_HK_IP4_IP_PAYLOAD_S1_5TUPLE,
+};
+
+enum vcap_is1_action_field {
+	VCAP_IS1_ACT_DSCP_ENA,
+	VCAP_IS1_ACT_DSCP_VAL,
+	VCAP_IS1_ACT_QOS_ENA,
+	VCAP_IS1_ACT_QOS_VAL,
+	VCAP_IS1_ACT_DP_ENA,
+	VCAP_IS1_ACT_DP_VAL,
+	VCAP_IS1_ACT_PAG_OVERRIDE_MASK,
+	VCAP_IS1_ACT_PAG_VAL,
+	VCAP_IS1_ACT_RSV,
+	VCAP_IS1_ACT_VID_REPLACE_ENA,
+	VCAP_IS1_ACT_VID_ADD_VAL,
+	VCAP_IS1_ACT_FID_SEL,
+	VCAP_IS1_ACT_FID_VAL,
+	VCAP_IS1_ACT_PCP_DEI_ENA,
+	VCAP_IS1_ACT_PCP_VAL,
+	VCAP_IS1_ACT_DEI_VAL,
+	VCAP_IS1_ACT_VLAN_POP_CNT_ENA,
+	VCAP_IS1_ACT_VLAN_POP_CNT,
+	VCAP_IS1_ACT_CUSTOM_ACE_TYPE_ENA,
+	VCAP_IS1_ACT_HIT_STICKY,
+};
+
+/* =================================================================
+ *  VCAP ES0
+ * =================================================================
+ */
+
+enum {
+	ES0_ACTION_TYPE_NORMAL,
+	ES0_ACTION_TYPE_MAX,
+};
+
+enum vcap_es0_key_field {
+	VCAP_ES0_EGR_PORT,
+	VCAP_ES0_IGR_PORT,
+	VCAP_ES0_RSV,
+	VCAP_ES0_L2_MC,
+	VCAP_ES0_L2_BC,
+	VCAP_ES0_VID,
+	VCAP_ES0_DP,
+	VCAP_ES0_PCP,
+};
+
+enum vcap_es0_action_field {
+	VCAP_ES0_ACT_PUSH_OUTER_TAG,
+	VCAP_ES0_ACT_PUSH_INNER_TAG,
+	VCAP_ES0_ACT_TAG_A_TPID_SEL,
+	VCAP_ES0_ACT_TAG_A_VID_SEL,
+	VCAP_ES0_ACT_TAG_A_PCP_SEL,
+	VCAP_ES0_ACT_TAG_A_DEI_SEL,
+	VCAP_ES0_ACT_TAG_B_TPID_SEL,
+	VCAP_ES0_ACT_TAG_B_VID_SEL,
+	VCAP_ES0_ACT_TAG_B_PCP_SEL,
+	VCAP_ES0_ACT_TAG_B_DEI_SEL,
+	VCAP_ES0_ACT_VID_A_VAL,
+	VCAP_ES0_ACT_PCP_A_VAL,
+	VCAP_ES0_ACT_DEI_A_VAL,
+	VCAP_ES0_ACT_VID_B_VAL,
+	VCAP_ES0_ACT_PCP_B_VAL,
+	VCAP_ES0_ACT_DEI_B_VAL,
+	VCAP_ES0_ACT_RSV,
+	VCAP_ES0_ACT_HIT_STICKY,
+};
+
 #endif /* _OCELOT_VCAP_H_ */
diff --git a/include/soc/nps/common.h b/include/soc/nps/common.h
index 9b1d43d671a3..8c18dc6d3fde 100644
--- a/include/soc/nps/common.h
+++ b/include/soc/nps/common.h
@@ -45,6 +45,12 @@
 #define CTOP_INST_MOV2B_FLIP_R3_B1_B2_INST	0x5B60
 #define CTOP_INST_MOV2B_FLIP_R3_B1_B2_LIMM	0x00010422
 
+#ifndef AUX_IENABLE
+#define AUX_IENABLE				0x40c
+#endif
+
+#define CTOP_AUX_IACK				(0xFFFFF800 + 0x088)
+
 #ifndef __ASSEMBLY__
 
 /* In order to increase compilation test coverage */
diff --git a/include/sound/soc.h b/include/sound/soc.h
index 5e3919ffb00c..fc4fcac72cf7 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -1193,6 +1193,8 @@ struct snd_soc_pcm_runtime {
 	     ((i) < (rtd)->num_cpus + (rtd)->num_codecs) &&		\
 		     ((dai) = (rtd)->dais[i]);				\
 	     (i)++)
+#define for_each_rtd_dais_rollback(rtd, i, dai)		\
+	for (; (--(i) >= 0) && ((dai) = (rtd)->dais[i]);)
 
 void snd_soc_close_delayed_work(struct snd_soc_pcm_runtime *rtd);
 
@@ -1361,6 +1363,8 @@ void snd_soc_unregister_dai(struct snd_soc_dai *dai);
 
 struct snd_soc_dai *snd_soc_find_dai(
 	const struct snd_soc_dai_link_component *dlc);
+struct snd_soc_dai *snd_soc_find_dai_with_mutex(
+	const struct snd_soc_dai_link_component *dlc);
 
 #include <sound/soc-dai.h>
 
diff --git a/include/trace/events/devlink.h b/include/trace/events/devlink.h
index 6f60a78d9a7e..44d8e2981065 100644
--- a/include/trace/events/devlink.h
+++ b/include/trace/events/devlink.h
@@ -171,6 +171,43 @@ TRACE_EVENT(devlink_health_reporter_state_update,
 		  __entry->new_state)
 );
 
+/*
+ * Tracepoint for devlink packet trap:
+ */
+TRACE_EVENT(devlink_trap_report,
+	TP_PROTO(const struct devlink *devlink, struct sk_buff *skb,
+		 const struct devlink_trap_metadata *metadata),
+
+	TP_ARGS(devlink, skb, metadata),
+
+	TP_STRUCT__entry(
+		__string(bus_name, devlink->dev->bus->name)
+		__string(dev_name, dev_name(devlink->dev))
+		__string(driver_name, devlink->dev->driver->name)
+		__string(trap_name, metadata->trap_name)
+		__string(trap_group_name, metadata->trap_group_name)
+		__dynamic_array(char, input_dev_name, IFNAMSIZ)
+	),
+
+	TP_fast_assign(
+		struct net_device *input_dev = metadata->input_dev;
+
+		__assign_str(bus_name, devlink->dev->bus->name);
+		__assign_str(dev_name, dev_name(devlink->dev));
+		__assign_str(driver_name, devlink->dev->driver->name);
+		__assign_str(trap_name, metadata->trap_name);
+		__assign_str(trap_group_name, metadata->trap_group_name);
+		__assign_str(input_dev_name,
+			     (input_dev ? input_dev->name : "NULL"));
+	),
+
+	TP_printk("bus_name=%s dev_name=%s driver_name=%s trap_name=%s "
+		  "trap_group_name=%s input_dev_name=%s", __get_str(bus_name),
+		  __get_str(dev_name), __get_str(driver_name),
+		  __get_str(trap_name), __get_str(trap_group_name),
+		  __get_str(input_dev_name))
+);
+
 #endif /* _TRACE_DEVLINK_H */
 
 /* This part must be outside protection */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 8dda13880957..4f556cfcbfbe 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -124,6 +124,7 @@ enum bpf_cmd {
 	BPF_ENABLE_STATS,
 	BPF_ITER_CREATE,
 	BPF_LINK_DETACH,
+	BPF_PROG_BIND_MAP,
 };
 
 enum bpf_map_type {
@@ -413,6 +414,9 @@ enum {
 
 /* Enable memory-mapping BPF map */
 	BPF_F_MMAPABLE		= (1U << 10),
+
+/* Share perf_event among processes */
+	BPF_F_PRESERVE_ELEMS	= (1U << 11),
 };
 
 /* Flags for BPF_PROG_QUERY. */
@@ -423,6 +427,11 @@ enum {
  */
 #define BPF_F_QUERY_EFFECTIVE	(1U << 0)
 
+/* Flags for BPF_PROG_TEST_RUN */
+
+/* If set, run the test on the cpu specified by bpf_attr.test.cpu */
+#define BPF_F_TEST_RUN_ON_CPU	(1U << 0)
+
 /* type for BPF_ENABLE_STATS */
 enum bpf_stats_type {
 	/* enabled run_time_ns and run_cnt */
@@ -565,6 +574,8 @@ union bpf_attr {
 						 */
 		__aligned_u64	ctx_in;
 		__aligned_u64	ctx_out;
+		__u32		flags;
+		__u32		cpu;
 	} test;
 
 	struct { /* anonymous struct used by BPF_*_GET_*_ID */
@@ -631,8 +642,13 @@ union bpf_attr {
 		};
 		__u32		attach_type;	/* attach type */
 		__u32		flags;		/* extra flags */
-		__aligned_u64	iter_info;	/* extra bpf_iter_link_info */
-		__u32		iter_info_len;	/* iter_info length */
+		union {
+			__u32		target_btf_id;	/* btf_id of target to attach to */
+			struct {
+				__aligned_u64	iter_info;	/* extra bpf_iter_link_info */
+				__u32		iter_info_len;	/* iter_info length */
+			};
+		};
 	} link_create;
 
 	struct { /* struct used by BPF_LINK_UPDATE command */
@@ -658,6 +674,12 @@ union bpf_attr {
 		__u32		flags;
 	} iter_create;
 
+	struct { /* struct used by BPF_PROG_BIND_MAP command */
+		__u32		prog_fd;
+		__u32		map_fd;
+		__u32		flags;		/* extra flags */
+	} prog_bind_map;
+
 } __attribute__((aligned(8)));
 
 /* The description below is an attempt at providing documentation to eBPF
@@ -1447,8 +1469,8 @@ union bpf_attr {
  * 	Return
  * 		The return value depends on the result of the test, and can be:
  *
- * 		* 0, if the *skb* task belongs to the cgroup2.
- * 		* 1, if the *skb* task does not belong to the cgroup2.
+ *		* 0, if current task belongs to the cgroup2.
+ *		* 1, if current task does not belong to the cgroup2.
  * 		* A negative error code, if an error occurred.
  *
  * long bpf_skb_change_tail(struct sk_buff *skb, u32 len, u64 flags)
@@ -2505,7 +2527,7 @@ union bpf_attr {
  *		result is from *reuse*\ **->socks**\ [] using the hash of the
  *		tuple.
  *
- * long bpf_sk_release(struct bpf_sock *sock)
+ * long bpf_sk_release(void *sock)
  *	Description
  *		Release the reference held by *sock*. *sock* must be a
  *		non-**NULL** pointer that was returned from
@@ -2685,7 +2707,7 @@ union bpf_attr {
  *		result is from *reuse*\ **->socks**\ [] using the hash of the
  *		tuple.
  *
- * long bpf_tcp_check_syncookie(struct bpf_sock *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len)
+ * long bpf_tcp_check_syncookie(void *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len)
  * 	Description
  * 		Check whether *iph* and *th* contain a valid SYN cookie ACK for
  * 		the listening socket in *sk*.
@@ -2854,6 +2876,7 @@ union bpf_attr {
  *		0 on success.
  *
  *		**-ENOENT** if the bpf-local-storage cannot be found.
+ *		**-EINVAL** if sk is not a fullsock (e.g. a request_sock).
  *
  * long bpf_send_signal(u32 sig)
  *	Description
@@ -2870,7 +2893,7 @@ union bpf_attr {
  *
  *		**-EAGAIN** if bpf program can try again.
  *
- * s64 bpf_tcp_gen_syncookie(struct bpf_sock *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len)
+ * s64 bpf_tcp_gen_syncookie(void *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len)
  *	Description
  *		Try to issue a SYN cookie for the packet with corresponding
  *		IP/TCP headers, *iph* and *th*, on the listening socket in *sk*.
@@ -3099,7 +3122,7 @@ union bpf_attr {
  * 	Return
  * 		The id is returned or 0 in case the id could not be retrieved.
  *
- * long bpf_sk_assign(struct sk_buff *skb, struct bpf_sock *sk, u64 flags)
+ * long bpf_sk_assign(struct sk_buff *skb, void *sk, u64 flags)
  *	Description
  *		Helper is overloaded depending on BPF program type. This
  *		description applies to **BPF_PROG_TYPE_SCHED_CLS** and
@@ -3227,11 +3250,11 @@ union bpf_attr {
  *
  *		**-EOVERFLOW** if an overflow happened: The same object will be tried again.
  *
- * u64 bpf_sk_cgroup_id(struct bpf_sock *sk)
+ * u64 bpf_sk_cgroup_id(void *sk)
  *	Description
  *		Return the cgroup v2 id of the socket *sk*.
  *
- *		*sk* must be a non-**NULL** pointer to a full socket, e.g. one
+ *		*sk* must be a non-**NULL** pointer to a socket, e.g. one
  *		returned from **bpf_sk_lookup_xxx**\ (),
  *		**bpf_sk_fullsock**\ (), etc. The format of returned id is
  *		same as in **bpf_skb_cgroup_id**\ ().
@@ -3241,7 +3264,7 @@ union bpf_attr {
  *	Return
  *		The id is returned or 0 in case the id could not be retrieved.
  *
- * u64 bpf_sk_ancestor_cgroup_id(struct bpf_sock *sk, int ancestor_level)
+ * u64 bpf_sk_ancestor_cgroup_id(void *sk, int ancestor_level)
  *	Description
  *		Return id of cgroup v2 that is ancestor of cgroup associated
  *		with the *sk* at the *ancestor_level*.  The root cgroup is at
@@ -3349,38 +3372,38 @@ union bpf_attr {
  *	Description
  *		Dynamically cast a *sk* pointer to a *tcp6_sock* pointer.
  *	Return
- *		*sk* if casting is valid, or NULL otherwise.
+ *		*sk* if casting is valid, or **NULL** otherwise.
  *
  * struct tcp_sock *bpf_skc_to_tcp_sock(void *sk)
  *	Description
  *		Dynamically cast a *sk* pointer to a *tcp_sock* pointer.
  *	Return
- *		*sk* if casting is valid, or NULL otherwise.
+ *		*sk* if casting is valid, or **NULL** otherwise.
  *
  * struct tcp_timewait_sock *bpf_skc_to_tcp_timewait_sock(void *sk)
  * 	Description
  *		Dynamically cast a *sk* pointer to a *tcp_timewait_sock* pointer.
  *	Return
- *		*sk* if casting is valid, or NULL otherwise.
+ *		*sk* if casting is valid, or **NULL** otherwise.
  *
  * struct tcp_request_sock *bpf_skc_to_tcp_request_sock(void *sk)
  * 	Description
  *		Dynamically cast a *sk* pointer to a *tcp_request_sock* pointer.
  *	Return
- *		*sk* if casting is valid, or NULL otherwise.
+ *		*sk* if casting is valid, or **NULL** otherwise.
  *
  * struct udp6_sock *bpf_skc_to_udp6_sock(void *sk)
  * 	Description
  *		Dynamically cast a *sk* pointer to a *udp6_sock* pointer.
  *	Return
- *		*sk* if casting is valid, or NULL otherwise.
+ *		*sk* if casting is valid, or **NULL** otherwise.
  *
  * long bpf_get_task_stack(struct task_struct *task, void *buf, u32 size, u64 flags)
  *	Description
  *		Return a user or a kernel stack in bpf program provided buffer.
  *		To achieve this, the helper needs *task*, which is a valid
- *		pointer to struct task_struct. To store the stacktrace, the
- *		bpf program provides *buf* with	a nonnegative *size*.
+ *		pointer to **struct task_struct**. To store the stacktrace, the
+ *		bpf program provides *buf* with a nonnegative *size*.
  *
  *		The last argument, *flags*, holds the number of stack frames to
  *		skip (from 0 to 255), masked with
@@ -3410,12 +3433,12 @@ union bpf_attr {
  * long bpf_load_hdr_opt(struct bpf_sock_ops *skops, void *searchby_res, u32 len, u64 flags)
  *	Description
  *		Load header option.  Support reading a particular TCP header
- *		option for bpf program (BPF_PROG_TYPE_SOCK_OPS).
+ *		option for bpf program (**BPF_PROG_TYPE_SOCK_OPS**).
  *
  *		If *flags* is 0, it will search the option from the
- *		sock_ops->skb_data.  The comment in "struct bpf_sock_ops"
+ *		*skops*\ **->skb_data**.  The comment in **struct bpf_sock_ops**
  *		has details on what skb_data contains under different
- *		sock_ops->op.
+ *		*skops*\ **->op**.
  *
  *		The first byte of the *searchby_res* specifies the
  *		kind that it wants to search.
@@ -3435,7 +3458,7 @@ union bpf_attr {
  *		[ 254, 4, 0xeB, 0x9F, 0, 0, .... 0 ].
  *
  *		To search for the standard window scale option (3),
- *		the searchby_res should be [ 3, 0, 0, .... 0 ].
+ *		the *searchby_res* should be [ 3, 0, 0, .... 0 ].
  *		Note, kind-length must be 0 for regular option.
  *
  *		Searching for No-Op (0) and End-of-Option-List (1) are
@@ -3445,27 +3468,30 @@ union bpf_attr {
  *		of a header option.
  *
  *		Supported flags:
+ *
  *		* **BPF_LOAD_HDR_OPT_TCP_SYN** to search from the
  *		  saved_syn packet or the just-received syn packet.
  *
  *	Return
- *		>0 when found, the header option is copied to *searchby_res*.
- *		The return value is the total length copied.
+ *		> 0 when found, the header option is copied to *searchby_res*.
+ *		The return value is the total length copied. On failure, a
+ *		negative error code is returned:
  *
- *		**-EINVAL** If param is invalid
+ *		**-EINVAL** if a parameter is invalid.
  *
- *		**-ENOMSG** The option is not found
+ *		**-ENOMSG** if the option is not found.
  *
- *		**-ENOENT** No syn packet available when
- *			    **BPF_LOAD_HDR_OPT_TCP_SYN** is used
+ *		**-ENOENT** if no syn packet is available when
+ *		**BPF_LOAD_HDR_OPT_TCP_SYN** is used.
  *
- *		**-ENOSPC** Not enough space.  Only *len* number of
- *			    bytes are copied.
+ *		**-ENOSPC** if there is not enough space.  Only *len* number of
+ *		bytes are copied.
  *
- *		**-EFAULT** Cannot parse the header options in the packet
+ *		**-EFAULT** on failure to parse the header options in the
+ *		packet.
  *
- *		**-EPERM** This helper cannot be used under the
- *			   current sock_ops->op.
+ *		**-EPERM** if the helper cannot be used under the current
+ *		*skops*\ **->op**.
  *
  * long bpf_store_hdr_opt(struct bpf_sock_ops *skops, const void *from, u32 len, u64 flags)
  *	Description
@@ -3483,44 +3509,44 @@ union bpf_attr {
  *		by searching the same option in the outgoing skb.
  *
  *		This helper can only be called during
- *		BPF_SOCK_OPS_WRITE_HDR_OPT_CB.
+ *		**BPF_SOCK_OPS_WRITE_HDR_OPT_CB**.
  *
  *	Return
  *		0 on success, or negative error in case of failure:
  *
- *		**-EINVAL** If param is invalid
+ *		**-EINVAL** If param is invalid.
  *
- *		**-ENOSPC** Not enough space in the header.
- *			    Nothing has been written
+ *		**-ENOSPC** if there is not enough space in the header.
+ *		Nothing has been written
  *
- *		**-EEXIST** The option has already existed
+ *		**-EEXIST** if the option already exists.
  *
- *		**-EFAULT** Cannot parse the existing header options
+ *		**-EFAULT** on failrue to parse the existing header options.
  *
- *		**-EPERM** This helper cannot be used under the
- *			   current sock_ops->op.
+ *		**-EPERM** if the helper cannot be used under the current
+ *		*skops*\ **->op**.
  *
  * long bpf_reserve_hdr_opt(struct bpf_sock_ops *skops, u32 len, u64 flags)
  *	Description
  *		Reserve *len* bytes for the bpf header option.  The
- *		space will be used by bpf_store_hdr_opt() later in
- *		BPF_SOCK_OPS_WRITE_HDR_OPT_CB.
+ *		space will be used by **bpf_store_hdr_opt**\ () later in
+ *		**BPF_SOCK_OPS_WRITE_HDR_OPT_CB**.
  *
- *		If bpf_reserve_hdr_opt() is called multiple times,
+ *		If **bpf_reserve_hdr_opt**\ () is called multiple times,
  *		the total number of bytes will be reserved.
  *
  *		This helper can only be called during
- *		BPF_SOCK_OPS_HDR_OPT_LEN_CB.
+ *		**BPF_SOCK_OPS_HDR_OPT_LEN_CB**.
  *
  *	Return
  *		0 on success, or negative error in case of failure:
  *
- *		**-EINVAL** if param is invalid
+ *		**-EINVAL** if a parameter is invalid.
  *
- *		**-ENOSPC** Not enough space in the header.
+ *		**-ENOSPC** if there is not enough space in the header.
  *
- *		**-EPERM** This helper cannot be used under the
- *			   current sock_ops->op.
+ *		**-EPERM** if the helper cannot be used under the current
+ *		*skops*\ **->op**.
  *
  * void *bpf_inode_storage_get(struct bpf_map *map, void *inode, void *value, u64 flags)
  *	Description
@@ -3560,9 +3586,9 @@ union bpf_attr {
  *
  * long bpf_d_path(struct path *path, char *buf, u32 sz)
  *	Description
- *		Return full path for given 'struct path' object, which
- *		needs to be the kernel BTF 'path' object. The path is
- *		returned in the provided buffer 'buf' of size 'sz' and
+ *		Return full path for given **struct path** object, which
+ *		needs to be the kernel BTF *path* object. The path is
+ *		returned in the provided buffer *buf* of size *sz* and
  *		is zero terminated.
  *
  *	Return
@@ -3573,9 +3599,75 @@ union bpf_attr {
  * long bpf_copy_from_user(void *dst, u32 size, const void *user_ptr)
  * 	Description
  * 		Read *size* bytes from user space address *user_ptr* and store
- * 		the data in *dst*. This is a wrapper of copy_from_user().
+ * 		the data in *dst*. This is a wrapper of **copy_from_user**\ ().
  * 	Return
  * 		0 on success, or a negative error in case of failure.
+ *
+ * long bpf_snprintf_btf(char *str, u32 str_size, struct btf_ptr *ptr, u32 btf_ptr_size, u64 flags)
+ *	Description
+ *		Use BTF to store a string representation of *ptr*->ptr in *str*,
+ *		using *ptr*->type_id.  This value should specify the type
+ *		that *ptr*->ptr points to. LLVM __builtin_btf_type_id(type, 1)
+ *		can be used to look up vmlinux BTF type ids. Traversing the
+ *		data structure using BTF, the type information and values are
+ *		stored in the first *str_size* - 1 bytes of *str*.  Safe copy of
+ *		the pointer data is carried out to avoid kernel crashes during
+ *		operation.  Smaller types can use string space on the stack;
+ *		larger programs can use map data to store the string
+ *		representation.
+ *
+ *		The string can be subsequently shared with userspace via
+ *		bpf_perf_event_output() or ring buffer interfaces.
+ *		bpf_trace_printk() is to be avoided as it places too small
+ *		a limit on string size to be useful.
+ *
+ *		*flags* is a combination of
+ *
+ *		**BTF_F_COMPACT**
+ *			no formatting around type information
+ *		**BTF_F_NONAME**
+ *			no struct/union member names/types
+ *		**BTF_F_PTR_RAW**
+ *			show raw (unobfuscated) pointer values;
+ *			equivalent to printk specifier %px.
+ *		**BTF_F_ZERO**
+ *			show zero-valued struct/union members; they
+ *			are not displayed by default
+ *
+ *	Return
+ *		The number of bytes that were written (or would have been
+ *		written if output had to be truncated due to string size),
+ *		or a negative error in cases of failure.
+ *
+ * long bpf_seq_printf_btf(struct seq_file *m, struct btf_ptr *ptr, u32 ptr_size, u64 flags)
+ *	Description
+ *		Use BTF to write to seq_write a string representation of
+ *		*ptr*->ptr, using *ptr*->type_id as per bpf_snprintf_btf().
+ *		*flags* are identical to those used for bpf_snprintf_btf.
+ *	Return
+ *		0 on success or a negative error in case of failure.
+ *
+ * u64 bpf_skb_cgroup_classid(struct sk_buff *skb)
+ * 	Description
+ * 		See **bpf_get_cgroup_classid**\ () for the main description.
+ * 		This helper differs from **bpf_get_cgroup_classid**\ () in that
+ * 		the cgroup v1 net_cls class is retrieved only from the *skb*'s
+ * 		associated socket instead of the current process.
+ * 	Return
+ * 		The id is returned or 0 in case the id could not be retrieved.
+ *
+ * long bpf_redirect_neigh(u32 ifindex, u64 flags)
+ * 	Description
+ * 		Redirect the packet to another net device of index *ifindex*
+ * 		and fill in L2 addresses from neighboring subsystem. This helper
+ * 		is somewhat similar to **bpf_redirect**\ (), except that it
+ * 		fills in e.g. MAC addresses based on the L3 information from
+ * 		the packet. This helper is supported for IPv4 and IPv6 protocols.
+ * 		The *flags* argument is reserved and must be 0. The helper is
+ * 		currently only supported for tc BPF program types.
+ * 	Return
+ * 		The helper returns **TC_ACT_REDIRECT** on success or
+ * 		**TC_ACT_SHOT** on error.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3727,6 +3819,10 @@ union bpf_attr {
 	FN(inode_storage_delete),	\
 	FN(d_path),			\
 	FN(copy_from_user),		\
+	FN(snprintf_btf),		\
+	FN(seq_printf_btf),		\
+	FN(skb_cgroup_classid),		\
+	FN(redirect_neigh),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
@@ -4835,4 +4931,34 @@ struct bpf_sk_lookup {
 	__u32 local_port;	/* Host byte order */
 };
 
+/*
+ * struct btf_ptr is used for typed pointer representation; the
+ * type id is used to render the pointer data as the appropriate type
+ * via the bpf_snprintf_btf() helper described above.  A flags field -
+ * potentially to specify additional details about the BTF pointer
+ * (rather than its mode of display) - is included for future use.
+ * Display flags - BTF_F_* - are passed to bpf_snprintf_btf separately.
+ */
+struct btf_ptr {
+	void *ptr;
+	__u32 type_id;
+	__u32 flags;		/* BTF ptr flags; unused at present. */
+};
+
+/*
+ * Flags to control bpf_snprintf_btf() behaviour.
+ *     - BTF_F_COMPACT: no formatting around type information
+ *     - BTF_F_NONAME: no struct/union member names/types
+ *     - BTF_F_PTR_RAW: show raw (unobfuscated) pointer values;
+ *       equivalent to %px.
+ *     - BTF_F_ZERO: show zero-valued struct/union members; they
+ *       are not displayed by default
+ */
+enum {
+	BTF_F_COMPACT	=	(1ULL << 0),
+	BTF_F_NONAME	=	(1ULL << 1),
+	BTF_F_PTR_RAW	=	(1ULL << 2),
+	BTF_F_ZERO	=	(1ULL << 3),
+};
+
 #endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index a2ecc8b00611..ba467dc07852 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -13,6 +13,8 @@
 #ifndef _UAPI_LINUX_DEVLINK_H_
 #define _UAPI_LINUX_DEVLINK_H_
 
+#include <linux/const.h>
+
 #define DEVLINK_GENL_NAME "devlink"
 #define DEVLINK_GENL_VERSION 0x1
 #define DEVLINK_GENL_MCGRP_CONFIG_NAME "config"
@@ -230,6 +232,28 @@ enum {
 	DEVLINK_ATTR_STATS_MAX = __DEVLINK_ATTR_STATS_MAX - 1
 };
 
+/* Specify what sections of a flash component can be overwritten when
+ * performing an update. Overwriting of firmware binary sections is always
+ * implicitly assumed to be allowed.
+ *
+ * Each section must be documented in
+ * Documentation/networking/devlink/devlink-flash.rst
+ *
+ */
+enum {
+	DEVLINK_FLASH_OVERWRITE_SETTINGS_BIT,
+	DEVLINK_FLASH_OVERWRITE_IDENTIFIERS_BIT,
+
+	__DEVLINK_FLASH_OVERWRITE_MAX_BIT,
+	DEVLINK_FLASH_OVERWRITE_MAX_BIT = __DEVLINK_FLASH_OVERWRITE_MAX_BIT - 1
+};
+
+#define DEVLINK_FLASH_OVERWRITE_SETTINGS _BITUL(DEVLINK_FLASH_OVERWRITE_SETTINGS_BIT)
+#define DEVLINK_FLASH_OVERWRITE_IDENTIFIERS _BITUL(DEVLINK_FLASH_OVERWRITE_IDENTIFIERS_BIT)
+
+#define DEVLINK_SUPPORTED_FLASH_OVERWRITE_SECTIONS \
+	(_BITUL(__DEVLINK_FLASH_OVERWRITE_MAX_BIT) - 1)
+
 /**
  * enum devlink_trap_action - Packet trap action.
  * @DEVLINK_TRAP_ACTION_DROP: Packet is dropped by the device and a copy is not
@@ -464,6 +488,7 @@ enum devlink_attr {
 	DEVLINK_ATTR_PORT_CONTROLLER_NUMBER,	/* u32 */
 
 	DEVLINK_ATTR_FLASH_UPDATE_STATUS_TIMEOUT,	/* u64 */
+	DEVLINK_ATTR_FLASH_UPDATE_OVERWRITE_MASK,	/* bitfield32 */
 
 	/* add new attributes above here, update the policy in devlink.c */
 
diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h
index 9cee6df01a10..e2bf36e6964b 100644
--- a/include/uapi/linux/ethtool_netlink.h
+++ b/include/uapi/linux/ethtool_netlink.h
@@ -79,6 +79,7 @@ enum {
 	ETHTOOL_MSG_TSINFO_GET_REPLY,
 	ETHTOOL_MSG_CABLE_TEST_NTF,
 	ETHTOOL_MSG_CABLE_TEST_TDR_NTF,
+	ETHTOOL_MSG_TUNNEL_INFO_GET_REPLY,
 
 	/* add new constants above here */
 	__ETHTOOL_MSG_KERNEL_CNT,
diff --git a/include/uapi/linux/genetlink.h b/include/uapi/linux/genetlink.h
index 9c0636ec2286..d83f214b4134 100644
--- a/include/uapi/linux/genetlink.h
+++ b/include/uapi/linux/genetlink.h
@@ -64,6 +64,8 @@ enum {
 	CTRL_ATTR_OPS,
 	CTRL_ATTR_MCAST_GROUPS,
 	CTRL_ATTR_POLICY,
+	CTRL_ATTR_OP_POLICY,
+	CTRL_ATTR_OP,
 	__CTRL_ATTR_MAX,
 };
 
@@ -85,6 +87,15 @@ enum {
 	__CTRL_ATTR_MCAST_GRP_MAX,
 };
 
+enum {
+	CTRL_ATTR_POLICY_UNSPEC,
+	CTRL_ATTR_POLICY_DO,
+	CTRL_ATTR_POLICY_DUMP,
+
+	__CTRL_ATTR_POLICY_DUMP_MAX,
+	CTRL_ATTR_POLICY_DUMP_MAX = __CTRL_ATTR_POLICY_DUMP_MAX - 1
+};
+
 #define CTRL_ATTR_MCAST_GRP_MAX (__CTRL_ATTR_MCAST_GRP_MAX - 1)
 
 
diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h
index 75a2ac479247..4c687686aa8f 100644
--- a/include/uapi/linux/if_bridge.h
+++ b/include/uapi/linux/if_bridge.h
@@ -457,6 +457,8 @@ enum {
 	MDBA_MDB_EATTR_TIMER,
 	MDBA_MDB_EATTR_SRC_LIST,
 	MDBA_MDB_EATTR_GROUP_MODE,
+	MDBA_MDB_EATTR_SOURCE,
+	MDBA_MDB_EATTR_RTPROT,
 	__MDBA_MDB_EATTR_MAX
 };
 #define MDBA_MDB_EATTR_MAX (__MDBA_MDB_EATTR_MAX - 1)
@@ -516,6 +518,8 @@ struct br_mdb_entry {
 	__u8 state;
 #define MDB_FLAGS_OFFLOAD	(1 << 0)
 #define MDB_FLAGS_FAST_LEAVE	(1 << 1)
+#define MDB_FLAGS_STAR_EXCL	(1 << 2)
+#define MDB_FLAGS_BLOCKED	(1 << 3)
 	__u8 flags;
 	__u16 vid;
 	struct {
@@ -530,10 +534,23 @@ struct br_mdb_entry {
 enum {
 	MDBA_SET_ENTRY_UNSPEC,
 	MDBA_SET_ENTRY,
+	MDBA_SET_ENTRY_ATTRS,
 	__MDBA_SET_ENTRY_MAX,
 };
 #define MDBA_SET_ENTRY_MAX (__MDBA_SET_ENTRY_MAX - 1)
 
+/* [MDBA_SET_ENTRY_ATTRS] = {
+ *    [MDBE_ATTR_xxx]
+ *    ...
+ * }
+ */
+enum {
+	MDBE_ATTR_UNSPEC,
+	MDBE_ATTR_SOURCE,
+	__MDBE_ATTR_MAX,
+};
+#define MDBE_ATTR_MAX (__MDBE_ATTR_MAX - 1)
+
 /* Embedded inside LINK_XSTATS_TYPE_BRIDGE */
 enum {
 	BRIDGE_XSTATS_UNSPEC,
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index f6d86033c4fa..7d8eced6f459 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -790,9 +790,10 @@ struct kvm_ppc_resize_hpt {
 #define KVM_VM_PPC_HV 1
 #define KVM_VM_PPC_PR 2
 
-/* on MIPS, 0 forces trap & emulate, 1 forces VZ ASE */
-#define KVM_VM_MIPS_TE		0
+/* on MIPS, 0 indicates auto, 1 forces VZ ASE, 2 forces trap & emulate */
+#define KVM_VM_MIPS_AUTO	0
 #define KVM_VM_MIPS_VZ		1
+#define KVM_VM_MIPS_TE		2
 
 #define KVM_S390_SIE_PAGE_OFFSET 1
 
@@ -1035,6 +1036,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_LAST_CPU 184
 #define KVM_CAP_SMALLER_MAXPHYADDR 185
 #define KVM_CAP_S390_DIAG318 186
+#define KVM_CAP_STEAL_TIME 187
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
diff --git a/include/uapi/linux/l2tp.h b/include/uapi/linux/l2tp.h
index 88a0d32b8c07..30c80d5ba4bf 100644
--- a/include/uapi/linux/l2tp.h
+++ b/include/uapi/linux/l2tp.h
@@ -144,6 +144,7 @@ enum {
 	L2TP_ATTR_RX_OOS_PACKETS,	/* u64 */
 	L2TP_ATTR_RX_ERRORS,		/* u64 */
 	L2TP_ATTR_STATS_PAD,
+	L2TP_ATTR_RX_COOKIE_DISCARDS,	/* u64 */
 	__L2TP_ATTR_STATS_MAX,
 };
 
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index bdc90b8dfd24..47700a2b9af9 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -2521,6 +2521,12 @@ enum nl80211_commands {
  *	unsolicited broadcast probe response. It is a nested attribute, see
  *	&enum nl80211_unsol_bcast_probe_resp_attributes.
  *
+ * @NL80211_ATTR_S1G_CAPABILITY: S1G Capability information element (from
+ *	association request when used with NL80211_CMD_NEW_STATION)
+ * @NL80211_ATTR_S1G_CAPABILITY_MASK: S1G Capability Information element
+ *	override mask. Used with NL80211_ATTR_S1G_CAPABILITY in
+ *	NL80211_CMD_ASSOCIATE or NL80211_CMD_CONNECT.
+ *
  * @NUM_NL80211_ATTR: total number of nl80211_attrs available
  * @NL80211_ATTR_MAX: highest attribute number currently defined
  * @__NL80211_ATTR_AFTER_LAST: internal use
@@ -3007,6 +3013,9 @@ enum nl80211_attrs {
 
 	NL80211_ATTR_UNSOL_BCAST_PROBE_RESP,
 
+	NL80211_ATTR_S1G_CAPABILITY,
+	NL80211_ATTR_S1G_CAPABILITY_MASK,
+
 	/* add attributes here, update the policy in nl80211.c */
 
 	__NL80211_ATTR_AFTER_LAST,
@@ -4088,6 +4097,7 @@ enum nl80211_user_reg_hint_type {
  *	receiving frames destined to the local BSS
  * @NL80211_SURVEY_INFO_MAX: highest survey info attribute number
  *	currently defined
+ * @NL80211_SURVEY_INFO_FREQUENCY_OFFSET: center frequency offset in KHz
  * @__NL80211_SURVEY_INFO_AFTER_LAST: internal use
  */
 enum nl80211_survey_info {
@@ -4103,6 +4113,7 @@ enum nl80211_survey_info {
 	NL80211_SURVEY_INFO_TIME_SCAN,
 	NL80211_SURVEY_INFO_PAD,
 	NL80211_SURVEY_INFO_TIME_BSS_RX,
+	NL80211_SURVEY_INFO_FREQUENCY_OFFSET,
 
 	/* keep last */
 	__NL80211_SURVEY_INFO_AFTER_LAST,
@@ -6059,6 +6070,8 @@ enum nl80211_timeout_reason {
  * @NL80211_SCAN_FLAG_FREQ_KHZ: report scan results with
  *	%NL80211_ATTR_SCAN_FREQ_KHZ. This also means
  *	%NL80211_ATTR_SCAN_FREQUENCIES will not be included.
+ * @NL80211_SCAN_FLAG_COLOCATED_6GHZ: scan for colocated APs reported by
+ *	2.4/5 GHz APs
  */
 enum nl80211_scan_flags {
 	NL80211_SCAN_FLAG_LOW_PRIORITY				= 1<<0,
@@ -6075,6 +6088,7 @@ enum nl80211_scan_flags {
 	NL80211_SCAN_FLAG_RANDOM_SN				= 1<<11,
 	NL80211_SCAN_FLAG_MIN_PREQ_CONTENT			= 1<<12,
 	NL80211_SCAN_FLAG_FREQ_KHZ				= 1<<13,
+	NL80211_SCAN_FLAG_COLOCATED_6GHZ			= 1<<14,
 };
 
 /**
@@ -6977,6 +6991,13 @@ enum nl80211_peer_measurement_ftm_resp {
  *
  * @NL80211_HE_OBSS_PD_ATTR_MIN_OFFSET: the OBSS PD minimum tx power offset.
  * @NL80211_HE_OBSS_PD_ATTR_MAX_OFFSET: the OBSS PD maximum tx power offset.
+ * @NL80211_HE_OBSS_PD_ATTR_NON_SRG_MAX_OFFSET: the non-SRG OBSS PD maximum
+ *	tx power offset.
+ * @NL80211_HE_OBSS_PD_ATTR_BSS_COLOR_BITMAP: bitmap that indicates the BSS color
+ *	values used by members of the SRG.
+ * @NL80211_HE_OBSS_PD_ATTR_PARTIAL_BSSID_BITMAP: bitmap that indicates the partial
+ *	BSSID values used by members of the SRG.
+ * @NL80211_HE_OBSS_PD_ATTR_SR_CTRL: The SR Control field of SRP element.
  *
  * @__NL80211_HE_OBSS_PD_ATTR_LAST: Internal
  * @NL80211_HE_OBSS_PD_ATTR_MAX: highest OBSS PD attribute.
@@ -6986,6 +7007,10 @@ enum nl80211_obss_pd_attributes {
 
 	NL80211_HE_OBSS_PD_ATTR_MIN_OFFSET,
 	NL80211_HE_OBSS_PD_ATTR_MAX_OFFSET,
+	NL80211_HE_OBSS_PD_ATTR_NON_SRG_MAX_OFFSET,
+	NL80211_HE_OBSS_PD_ATTR_BSS_COLOR_BITMAP,
+	NL80211_HE_OBSS_PD_ATTR_PARTIAL_BSSID_BITMAP,
+	NL80211_HE_OBSS_PD_ATTR_SR_CTRL,
 
 	/* keep last */
 	__NL80211_HE_OBSS_PD_ATTR_LAST,
diff --git a/include/uapi/linux/tc_act/tc_mpls.h b/include/uapi/linux/tc_act/tc_mpls.h
index 9360e95273c7..9e4e8f52a779 100644
--- a/include/uapi/linux/tc_act/tc_mpls.h
+++ b/include/uapi/linux/tc_act/tc_mpls.h
@@ -10,6 +10,7 @@
 #define TCA_MPLS_ACT_PUSH	2
 #define TCA_MPLS_ACT_MODIFY	3
 #define TCA_MPLS_ACT_DEC_TTL	4
+#define TCA_MPLS_ACT_MAC_PUSH	5
 
 struct tc_mpls {
 	tc_gen;		/* generic TC action fields. */
diff --git a/include/uapi/linux/tc_act/tc_vlan.h b/include/uapi/linux/tc_act/tc_vlan.h
index 168995b54a70..5b306fe815cc 100644
--- a/include/uapi/linux/tc_act/tc_vlan.h
+++ b/include/uapi/linux/tc_act/tc_vlan.h
@@ -16,6 +16,8 @@
 #define TCA_VLAN_ACT_POP	1
 #define TCA_VLAN_ACT_PUSH	2
 #define TCA_VLAN_ACT_MODIFY	3
+#define TCA_VLAN_ACT_POP_ETH	4
+#define TCA_VLAN_ACT_PUSH_ETH	5
 
 struct tc_vlan {
 	tc_gen;
@@ -30,6 +32,8 @@ enum {
 	TCA_VLAN_PUSH_VLAN_PROTOCOL,
 	TCA_VLAN_PAD,
 	TCA_VLAN_PUSH_VLAN_PRIORITY,
+	TCA_VLAN_PUSH_ETH_DST,
+	TCA_VLAN_PUSH_ETH_SRC,
 	__TCA_VLAN_MAX,
 };
 #define TCA_VLAN_MAX (__TCA_VLAN_MAX - 1)
diff --git a/include/xen/balloon.h b/include/xen/balloon.h
index 6fb95aa19405..6dbdb0b3fd03 100644
--- a/include/xen/balloon.h
+++ b/include/xen/balloon.h
@@ -2,6 +2,8 @@
 /******************************************************************************
  * Xen balloon functionality
  */
+#ifndef _XEN_BALLOON_H
+#define _XEN_BALLOON_H
 
 #define RETRY_UNLIMITED	0
 
@@ -34,3 +36,5 @@ static inline void xen_balloon_init(void)
 {
 }
 #endif
+
+#endif	/* _XEN_BALLOON_H */
diff --git a/include/xen/xen.h b/include/xen/xen.h
index 19a72f591e2b..43efba045acc 100644
--- a/include/xen/xen.h
+++ b/include/xen/xen.h
@@ -52,4 +52,13 @@ bool xen_biovec_phys_mergeable(const struct bio_vec *vec1,
 extern u64 xen_saved_max_mem_size;
 #endif
 
+#ifdef CONFIG_XEN_UNPOPULATED_ALLOC
+int xen_alloc_unpopulated_pages(unsigned int nr_pages, struct page **pages);
+void xen_free_unpopulated_pages(unsigned int nr_pages, struct page **pages);
+#else
+#define xen_alloc_unpopulated_pages alloc_xenballooned_pages
+#define xen_free_unpopulated_pages free_xenballooned_pages
+#include <xen/balloon.h>
+#endif
+
 #endif	/* _XEN_XEN_H */
diff --git a/init/main.c b/init/main.c
index ae78fb68d231..e880b4ecb314 100644
--- a/init/main.c
+++ b/init/main.c
@@ -33,6 +33,7 @@
 #include <linux/nmi.h>
 #include <linux/percpu.h>
 #include <linux/kmod.h>
+#include <linux/kprobes.h>
 #include <linux/vmalloc.h>
 #include <linux/kernel_stat.h>
 #include <linux/start_kernel.h>
@@ -303,7 +304,7 @@ static void * __init get_boot_config_from_initrd(u32 *_size, u32 *_csum)
 
 #ifdef CONFIG_BOOT_CONFIG
 
-char xbc_namebuf[XBC_KEYLEN_MAX] __initdata;
+static char xbc_namebuf[XBC_KEYLEN_MAX] __initdata;
 
 #define rest(dst, end) ((end) > (dst) ? (end) - (dst) : 0)
 
@@ -1402,6 +1403,7 @@ static int __ref kernel_init(void *unused)
 	kernel_init_freeable();
 	/* need to finish all async __init code before freeing the memory */
 	async_synchronize_full();
+	kprobe_free_init_mem();
 	ftrace_free_init_mem();
 	free_initmem();
 	mark_readonly();
diff --git a/ipc/ipc_sysctl.c b/ipc/ipc_sysctl.c
index d1b8644bfb88..3f312bf2b116 100644
--- a/ipc/ipc_sysctl.c
+++ b/ipc/ipc_sysctl.c
@@ -85,7 +85,7 @@ static int proc_ipc_auto_msgmni(struct ctl_table *table, int write,
 }
 
 static int proc_ipc_sem_dointvec(struct ctl_table *table, int write,
-	void __user *buffer, size_t *lenp, loff_t *ppos)
+	void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int ret, semmni;
 	struct ipc_namespace *ns = current->nsproxy->ipc_ns;
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index e046fb7d17cd..bd777dd6f967 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -15,7 +15,8 @@
 #include "map_in_map.h"
 
 #define ARRAY_CREATE_FLAG_MASK \
-	(BPF_F_NUMA_NODE | BPF_F_MMAPABLE | BPF_F_ACCESS_MASK)
+	(BPF_F_NUMA_NODE | BPF_F_MMAPABLE | BPF_F_ACCESS_MASK | \
+	 BPF_F_PRESERVE_ELEMS)
 
 static void bpf_array_free_percpu(struct bpf_array *array)
 {
@@ -64,6 +65,10 @@ int array_map_alloc_check(union bpf_attr *attr)
 	    attr->map_flags & BPF_F_MMAPABLE)
 		return -EINVAL;
 
+	if (attr->map_type != BPF_MAP_TYPE_PERF_EVENT_ARRAY &&
+	    attr->map_flags & BPF_F_PRESERVE_ELEMS)
+		return -EINVAL;
+
 	if (attr->value_size > KMALLOC_MAX_SIZE)
 		/* if value_size is bigger, the user space won't be able to
 		 * access the elements.
@@ -898,6 +903,7 @@ static void prog_array_map_poke_run(struct bpf_map *map, u32 key,
 				    struct bpf_prog *old,
 				    struct bpf_prog *new)
 {
+	u8 *old_addr, *new_addr, *old_bypass_addr;
 	struct prog_poke_elem *elem;
 	struct bpf_array_aux *aux;
 
@@ -918,12 +924,13 @@ static void prog_array_map_poke_run(struct bpf_map *map, u32 key,
 			 *    there could be danger of use after free otherwise.
 			 * 2) Initially when we start tracking aux, the program
 			 *    is not JITed yet and also does not have a kallsyms
-			 *    entry. We skip these as poke->ip_stable is not
-			 *    active yet. The JIT will do the final fixup before
-			 *    setting it stable. The various poke->ip_stable are
-			 *    successively activated, so tail call updates can
-			 *    arrive from here while JIT is still finishing its
-			 *    final fixup for non-activated poke entries.
+			 *    entry. We skip these as poke->tailcall_target_stable
+			 *    is not active yet. The JIT will do the final fixup
+			 *    before setting it stable. The various
+			 *    poke->tailcall_target_stable are successively
+			 *    activated, so tail call updates can arrive from here
+			 *    while JIT is still finishing its final fixup for
+			 *    non-activated poke entries.
 			 * 3) On program teardown, the program's kallsym entry gets
 			 *    removed out of RCU callback, but we can only untrack
 			 *    from sleepable context, therefore bpf_arch_text_poke()
@@ -940,7 +947,7 @@ static void prog_array_map_poke_run(struct bpf_map *map, u32 key,
 			 * 5) Any other error happening below from bpf_arch_text_poke()
 			 *    is a unexpected bug.
 			 */
-			if (!READ_ONCE(poke->ip_stable))
+			if (!READ_ONCE(poke->tailcall_target_stable))
 				continue;
 			if (poke->reason != BPF_POKE_REASON_TAIL_CALL)
 				continue;
@@ -948,12 +955,39 @@ static void prog_array_map_poke_run(struct bpf_map *map, u32 key,
 			    poke->tail_call.key != key)
 				continue;
 
-			ret = bpf_arch_text_poke(poke->ip, BPF_MOD_JUMP,
-						 old ? (u8 *)old->bpf_func +
-						 poke->adj_off : NULL,
-						 new ? (u8 *)new->bpf_func +
-						 poke->adj_off : NULL);
-			BUG_ON(ret < 0 && ret != -EINVAL);
+			old_bypass_addr = old ? NULL : poke->bypass_addr;
+			old_addr = old ? (u8 *)old->bpf_func + poke->adj_off : NULL;
+			new_addr = new ? (u8 *)new->bpf_func + poke->adj_off : NULL;
+
+			if (new) {
+				ret = bpf_arch_text_poke(poke->tailcall_target,
+							 BPF_MOD_JUMP,
+							 old_addr, new_addr);
+				BUG_ON(ret < 0 && ret != -EINVAL);
+				if (!old) {
+					ret = bpf_arch_text_poke(poke->tailcall_bypass,
+								 BPF_MOD_JUMP,
+								 poke->bypass_addr,
+								 NULL);
+					BUG_ON(ret < 0 && ret != -EINVAL);
+				}
+			} else {
+				ret = bpf_arch_text_poke(poke->tailcall_bypass,
+							 BPF_MOD_JUMP,
+							 old_bypass_addr,
+							 poke->bypass_addr);
+				BUG_ON(ret < 0 && ret != -EINVAL);
+				/* let other CPUs finish the execution of program
+				 * so that it will not possible to expose them
+				 * to invalid nop, stack unwind, nop state
+				 */
+				if (!ret)
+					synchronize_rcu();
+				ret = bpf_arch_text_poke(poke->tailcall_target,
+							 BPF_MOD_JUMP,
+							 old_addr, NULL);
+				BUG_ON(ret < 0 && ret != -EINVAL);
+			}
 		}
 	}
 }
@@ -1105,6 +1139,9 @@ static void perf_event_fd_array_release(struct bpf_map *map,
 	struct bpf_event_entry *ee;
 	int i;
 
+	if (map->map_flags & BPF_F_PRESERVE_ELEMS)
+		return;
+
 	rcu_read_lock();
 	for (i = 0; i < array->map.max_entries; i++) {
 		ee = READ_ONCE(array->ptrs[i]);
@@ -1114,12 +1151,19 @@ static void perf_event_fd_array_release(struct bpf_map *map,
 	rcu_read_unlock();
 }
 
+static void perf_event_fd_array_map_free(struct bpf_map *map)
+{
+	if (map->map_flags & BPF_F_PRESERVE_ELEMS)
+		bpf_fd_array_map_clear(map);
+	fd_array_map_free(map);
+}
+
 static int perf_event_array_map_btf_id;
 const struct bpf_map_ops perf_event_array_map_ops = {
 	.map_meta_equal = bpf_map_meta_equal,
 	.map_alloc_check = fd_array_map_alloc_check,
 	.map_alloc = array_map_alloc,
-	.map_free = fd_array_map_free,
+	.map_free = perf_event_fd_array_map_free,
 	.map_get_next_key = array_map_get_next_key,
 	.map_lookup_elem = fd_array_map_lookup_elem,
 	.map_delete_elem = fd_array_map_delete_elem,
diff --git a/kernel/bpf/bpf_inode_storage.c b/kernel/bpf/bpf_inode_storage.c
index 75be02799c0f..6edff97ad594 100644
--- a/kernel/bpf/bpf_inode_storage.c
+++ b/kernel/bpf/bpf_inode_storage.c
@@ -249,9 +249,7 @@ const struct bpf_map_ops inode_storage_map_ops = {
 	.map_owner_storage_ptr = inode_storage_ptr,
 };
 
-BTF_ID_LIST(bpf_inode_storage_btf_ids)
-BTF_ID_UNUSED
-BTF_ID(struct, inode)
+BTF_ID_LIST_SINGLE(bpf_inode_storage_btf_ids, struct, inode)
 
 const struct bpf_func_proto bpf_inode_storage_get_proto = {
 	.func		= bpf_inode_storage_get,
@@ -259,9 +257,9 @@ const struct bpf_func_proto bpf_inode_storage_get_proto = {
 	.ret_type	= RET_PTR_TO_MAP_VALUE_OR_NULL,
 	.arg1_type	= ARG_CONST_MAP_PTR,
 	.arg2_type	= ARG_PTR_TO_BTF_ID,
+	.arg2_btf_id	= &bpf_inode_storage_btf_ids[0],
 	.arg3_type	= ARG_PTR_TO_MAP_VALUE_OR_NULL,
 	.arg4_type	= ARG_ANYTHING,
-	.btf_id		= bpf_inode_storage_btf_ids,
 };
 
 const struct bpf_func_proto bpf_inode_storage_delete_proto = {
@@ -270,5 +268,5 @@ const struct bpf_func_proto bpf_inode_storage_delete_proto = {
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_CONST_MAP_PTR,
 	.arg2_type	= ARG_PTR_TO_BTF_ID,
-	.btf_id		= bpf_inode_storage_btf_ids,
+	.arg2_btf_id	= &bpf_inode_storage_btf_ids[0],
 };
diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c
index 30833bbf3019..8f10e30ea0b0 100644
--- a/kernel/bpf/bpf_iter.c
+++ b/kernel/bpf/bpf_iter.c
@@ -88,8 +88,8 @@ static ssize_t bpf_seq_read(struct file *file, char __user *buf, size_t size,
 	mutex_lock(&seq->lock);
 
 	if (!seq->buf) {
-		seq->size = PAGE_SIZE;
-		seq->buf = kmalloc(seq->size, GFP_KERNEL);
+		seq->size = PAGE_SIZE << 3;
+		seq->buf = kvmalloc(seq->size, GFP_KERNEL);
 		if (!seq->buf) {
 			err = -ENOMEM;
 			goto done;
diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c
index ffa7d11fc2bd..5d3a7af9ba9b 100644
--- a/kernel/bpf/bpf_local_storage.c
+++ b/kernel/bpf/bpf_local_storage.c
@@ -159,7 +159,7 @@ void bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage,
 				   struct bpf_local_storage_elem *selem)
 {
 	RCU_INIT_POINTER(selem->local_storage, local_storage);
-	hlist_add_head(&selem->snode, &local_storage->list);
+	hlist_add_head_rcu(&selem->snode, &local_storage->list);
 }
 
 void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem)
diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c
index 9cd1428c7199..78ea8a7bd27f 100644
--- a/kernel/bpf/bpf_lsm.c
+++ b/kernel/bpf/bpf_lsm.c
@@ -56,9 +56,9 @@ bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_inode_storage_delete:
 		return &bpf_inode_storage_delete_proto;
 	case BPF_FUNC_sk_storage_get:
-		return &sk_storage_get_btf_proto;
+		return &bpf_sk_storage_get_proto;
 	case BPF_FUNC_sk_storage_delete:
-		return &sk_storage_delete_btf_proto;
+		return &bpf_sk_storage_delete_proto;
 	default:
 		return tracing_prog_func_proto(func_id, prog);
 	}
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index f9ac6935ab3c..4d0ee7839fdb 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -284,6 +284,91 @@ static const char *btf_type_str(const struct btf_type *t)
 	return btf_kind_str[BTF_INFO_KIND(t->info)];
 }
 
+/* Chunk size we use in safe copy of data to be shown. */
+#define BTF_SHOW_OBJ_SAFE_SIZE		32
+
+/*
+ * This is the maximum size of a base type value (equivalent to a
+ * 128-bit int); if we are at the end of our safe buffer and have
+ * less than 16 bytes space we can't be assured of being able
+ * to copy the next type safely, so in such cases we will initiate
+ * a new copy.
+ */
+#define BTF_SHOW_OBJ_BASE_TYPE_SIZE	16
+
+/* Type name size */
+#define BTF_SHOW_NAME_SIZE		80
+
+/*
+ * Common data to all BTF show operations. Private show functions can add
+ * their own data to a structure containing a struct btf_show and consult it
+ * in the show callback.  See btf_type_show() below.
+ *
+ * One challenge with showing nested data is we want to skip 0-valued
+ * data, but in order to figure out whether a nested object is all zeros
+ * we need to walk through it.  As a result, we need to make two passes
+ * when handling structs, unions and arrays; the first path simply looks
+ * for nonzero data, while the second actually does the display.  The first
+ * pass is signalled by show->state.depth_check being set, and if we
+ * encounter a non-zero value we set show->state.depth_to_show to
+ * the depth at which we encountered it.  When we have completed the
+ * first pass, we will know if anything needs to be displayed if
+ * depth_to_show > depth.  See btf_[struct,array]_show() for the
+ * implementation of this.
+ *
+ * Another problem is we want to ensure the data for display is safe to
+ * access.  To support this, the anonymous "struct {} obj" tracks the data
+ * object and our safe copy of it.  We copy portions of the data needed
+ * to the object "copy" buffer, but because its size is limited to
+ * BTF_SHOW_OBJ_COPY_LEN bytes, multiple copies may be required as we
+ * traverse larger objects for display.
+ *
+ * The various data type show functions all start with a call to
+ * btf_show_start_type() which returns a pointer to the safe copy
+ * of the data needed (or if BTF_SHOW_UNSAFE is specified, to the
+ * raw data itself).  btf_show_obj_safe() is responsible for
+ * using copy_from_kernel_nofault() to update the safe data if necessary
+ * as we traverse the object's data.  skbuff-like semantics are
+ * used:
+ *
+ * - obj.head points to the start of the toplevel object for display
+ * - obj.size is the size of the toplevel object
+ * - obj.data points to the current point in the original data at
+ *   which our safe data starts.  obj.data will advance as we copy
+ *   portions of the data.
+ *
+ * In most cases a single copy will suffice, but larger data structures
+ * such as "struct task_struct" will require many copies.  The logic in
+ * btf_show_obj_safe() handles the logic that determines if a new
+ * copy_from_kernel_nofault() is needed.
+ */
+struct btf_show {
+	u64 flags;
+	void *target;	/* target of show operation (seq file, buffer) */
+	void (*showfn)(struct btf_show *show, const char *fmt, va_list args);
+	const struct btf *btf;
+	/* below are used during iteration */
+	struct {
+		u8 depth;
+		u8 depth_to_show;
+		u8 depth_check;
+		u8 array_member:1,
+		   array_terminated:1;
+		u16 array_encoding;
+		u32 type_id;
+		int status;			/* non-zero for error */
+		const struct btf_type *type;
+		const struct btf_member *member;
+		char name[BTF_SHOW_NAME_SIZE];	/* space for member name/type */
+	} state;
+	struct {
+		u32 size;
+		void *head;
+		void *data;
+		u8 safe[BTF_SHOW_OBJ_SAFE_SIZE];
+	} obj;
+};
+
 struct btf_kind_operations {
 	s32 (*check_meta)(struct btf_verifier_env *env,
 			  const struct btf_type *t,
@@ -300,9 +385,9 @@ struct btf_kind_operations {
 				  const struct btf_type *member_type);
 	void (*log_details)(struct btf_verifier_env *env,
 			    const struct btf_type *t);
-	void (*seq_show)(const struct btf *btf, const struct btf_type *t,
+	void (*show)(const struct btf *btf, const struct btf_type *t,
 			 u32 type_id, void *data, u8 bits_offsets,
-			 struct seq_file *m);
+			 struct btf_show *show);
 };
 
 static const struct btf_kind_operations * const kind_ops[NR_BTF_KINDS];
@@ -679,6 +764,488 @@ bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s,
 	return true;
 }
 
+/* Similar to btf_type_skip_modifiers() but does not skip typedefs. */
+static const struct btf_type *btf_type_skip_qualifiers(const struct btf *btf,
+						       u32 id)
+{
+	const struct btf_type *t = btf_type_by_id(btf, id);
+
+	while (btf_type_is_modifier(t) &&
+	       BTF_INFO_KIND(t->info) != BTF_KIND_TYPEDEF) {
+		id = t->type;
+		t = btf_type_by_id(btf, t->type);
+	}
+
+	return t;
+}
+
+#define BTF_SHOW_MAX_ITER	10
+
+#define BTF_KIND_BIT(kind)	(1ULL << kind)
+
+/*
+ * Populate show->state.name with type name information.
+ * Format of type name is
+ *
+ * [.member_name = ] (type_name)
+ */
+static const char *btf_show_name(struct btf_show *show)
+{
+	/* BTF_MAX_ITER array suffixes "[]" */
+	const char *array_suffixes = "[][][][][][][][][][]";
+	const char *array_suffix = &array_suffixes[strlen(array_suffixes)];
+	/* BTF_MAX_ITER pointer suffixes "*" */
+	const char *ptr_suffixes = "**********";
+	const char *ptr_suffix = &ptr_suffixes[strlen(ptr_suffixes)];
+	const char *name = NULL, *prefix = "", *parens = "";
+	const struct btf_member *m = show->state.member;
+	const struct btf_type *t = show->state.type;
+	const struct btf_array *array;
+	u32 id = show->state.type_id;
+	const char *member = NULL;
+	bool show_member = false;
+	u64 kinds = 0;
+	int i;
+
+	show->state.name[0] = '\0';
+
+	/*
+	 * Don't show type name if we're showing an array member;
+	 * in that case we show the array type so don't need to repeat
+	 * ourselves for each member.
+	 */
+	if (show->state.array_member)
+		return "";
+
+	/* Retrieve member name, if any. */
+	if (m) {
+		member = btf_name_by_offset(show->btf, m->name_off);
+		show_member = strlen(member) > 0;
+		id = m->type;
+	}
+
+	/*
+	 * Start with type_id, as we have resolved the struct btf_type *
+	 * via btf_modifier_show() past the parent typedef to the child
+	 * struct, int etc it is defined as.  In such cases, the type_id
+	 * still represents the starting type while the struct btf_type *
+	 * in our show->state points at the resolved type of the typedef.
+	 */
+	t = btf_type_by_id(show->btf, id);
+	if (!t)
+		return "";
+
+	/*
+	 * The goal here is to build up the right number of pointer and
+	 * array suffixes while ensuring the type name for a typedef
+	 * is represented.  Along the way we accumulate a list of
+	 * BTF kinds we have encountered, since these will inform later
+	 * display; for example, pointer types will not require an
+	 * opening "{" for struct, we will just display the pointer value.
+	 *
+	 * We also want to accumulate the right number of pointer or array
+	 * indices in the format string while iterating until we get to
+	 * the typedef/pointee/array member target type.
+	 *
+	 * We start by pointing at the end of pointer and array suffix
+	 * strings; as we accumulate pointers and arrays we move the pointer
+	 * or array string backwards so it will show the expected number of
+	 * '*' or '[]' for the type.  BTF_SHOW_MAX_ITER of nesting of pointers
+	 * and/or arrays and typedefs are supported as a precaution.
+	 *
+	 * We also want to get typedef name while proceeding to resolve
+	 * type it points to so that we can add parentheses if it is a
+	 * "typedef struct" etc.
+	 */
+	for (i = 0; i < BTF_SHOW_MAX_ITER; i++) {
+
+		switch (BTF_INFO_KIND(t->info)) {
+		case BTF_KIND_TYPEDEF:
+			if (!name)
+				name = btf_name_by_offset(show->btf,
+							       t->name_off);
+			kinds |= BTF_KIND_BIT(BTF_KIND_TYPEDEF);
+			id = t->type;
+			break;
+		case BTF_KIND_ARRAY:
+			kinds |= BTF_KIND_BIT(BTF_KIND_ARRAY);
+			parens = "[";
+			if (!t)
+				return "";
+			array = btf_type_array(t);
+			if (array_suffix > array_suffixes)
+				array_suffix -= 2;
+			id = array->type;
+			break;
+		case BTF_KIND_PTR:
+			kinds |= BTF_KIND_BIT(BTF_KIND_PTR);
+			if (ptr_suffix > ptr_suffixes)
+				ptr_suffix -= 1;
+			id = t->type;
+			break;
+		default:
+			id = 0;
+			break;
+		}
+		if (!id)
+			break;
+		t = btf_type_skip_qualifiers(show->btf, id);
+	}
+	/* We may not be able to represent this type; bail to be safe */
+	if (i == BTF_SHOW_MAX_ITER)
+		return "";
+
+	if (!name)
+		name = btf_name_by_offset(show->btf, t->name_off);
+
+	switch (BTF_INFO_KIND(t->info)) {
+	case BTF_KIND_STRUCT:
+	case BTF_KIND_UNION:
+		prefix = BTF_INFO_KIND(t->info) == BTF_KIND_STRUCT ?
+			 "struct" : "union";
+		/* if it's an array of struct/union, parens is already set */
+		if (!(kinds & (BTF_KIND_BIT(BTF_KIND_ARRAY))))
+			parens = "{";
+		break;
+	case BTF_KIND_ENUM:
+		prefix = "enum";
+		break;
+	default:
+		break;
+	}
+
+	/* pointer does not require parens */
+	if (kinds & BTF_KIND_BIT(BTF_KIND_PTR))
+		parens = "";
+	/* typedef does not require struct/union/enum prefix */
+	if (kinds & BTF_KIND_BIT(BTF_KIND_TYPEDEF))
+		prefix = "";
+
+	if (!name)
+		name = "";
+
+	/* Even if we don't want type name info, we want parentheses etc */
+	if (show->flags & BTF_SHOW_NONAME)
+		snprintf(show->state.name, sizeof(show->state.name), "%s",
+			 parens);
+	else
+		snprintf(show->state.name, sizeof(show->state.name),
+			 "%s%s%s(%s%s%s%s%s%s)%s",
+			 /* first 3 strings comprise ".member = " */
+			 show_member ? "." : "",
+			 show_member ? member : "",
+			 show_member ? " = " : "",
+			 /* ...next is our prefix (struct, enum, etc) */
+			 prefix,
+			 strlen(prefix) > 0 && strlen(name) > 0 ? " " : "",
+			 /* ...this is the type name itself */
+			 name,
+			 /* ...suffixed by the appropriate '*', '[]' suffixes */
+			 strlen(ptr_suffix) > 0 ? " " : "", ptr_suffix,
+			 array_suffix, parens);
+
+	return show->state.name;
+}
+
+static const char *__btf_show_indent(struct btf_show *show)
+{
+	const char *indents = "                                ";
+	const char *indent = &indents[strlen(indents)];
+
+	if ((indent - show->state.depth) >= indents)
+		return indent - show->state.depth;
+	return indents;
+}
+
+static const char *btf_show_indent(struct btf_show *show)
+{
+	return show->flags & BTF_SHOW_COMPACT ? "" : __btf_show_indent(show);
+}
+
+static const char *btf_show_newline(struct btf_show *show)
+{
+	return show->flags & BTF_SHOW_COMPACT ? "" : "\n";
+}
+
+static const char *btf_show_delim(struct btf_show *show)
+{
+	if (show->state.depth == 0)
+		return "";
+
+	if ((show->flags & BTF_SHOW_COMPACT) && show->state.type &&
+		BTF_INFO_KIND(show->state.type->info) == BTF_KIND_UNION)
+		return "|";
+
+	return ",";
+}
+
+__printf(2, 3) static void btf_show(struct btf_show *show, const char *fmt, ...)
+{
+	va_list args;
+
+	if (!show->state.depth_check) {
+		va_start(args, fmt);
+		show->showfn(show, fmt, args);
+		va_end(args);
+	}
+}
+
+/* Macros are used here as btf_show_type_value[s]() prepends and appends
+ * format specifiers to the format specifier passed in; these do the work of
+ * adding indentation, delimiters etc while the caller simply has to specify
+ * the type value(s) in the format specifier + value(s).
+ */
+#define btf_show_type_value(show, fmt, value)				       \
+	do {								       \
+		if ((value) != 0 || (show->flags & BTF_SHOW_ZERO) ||	       \
+		    show->state.depth == 0) {				       \
+			btf_show(show, "%s%s" fmt "%s%s",		       \
+				 btf_show_indent(show),			       \
+				 btf_show_name(show),			       \
+				 value, btf_show_delim(show),		       \
+				 btf_show_newline(show));		       \
+			if (show->state.depth > show->state.depth_to_show)     \
+				show->state.depth_to_show = show->state.depth; \
+		}							       \
+	} while (0)
+
+#define btf_show_type_values(show, fmt, ...)				       \
+	do {								       \
+		btf_show(show, "%s%s" fmt "%s%s", btf_show_indent(show),       \
+			 btf_show_name(show),				       \
+			 __VA_ARGS__, btf_show_delim(show),		       \
+			 btf_show_newline(show));			       \
+		if (show->state.depth > show->state.depth_to_show)	       \
+			show->state.depth_to_show = show->state.depth;	       \
+	} while (0)
+
+/* How much is left to copy to safe buffer after @data? */
+static int btf_show_obj_size_left(struct btf_show *show, void *data)
+{
+	return show->obj.head + show->obj.size - data;
+}
+
+/* Is object pointed to by @data of @size already copied to our safe buffer? */
+static bool btf_show_obj_is_safe(struct btf_show *show, void *data, int size)
+{
+	return data >= show->obj.data &&
+	       (data + size) < (show->obj.data + BTF_SHOW_OBJ_SAFE_SIZE);
+}
+
+/*
+ * If object pointed to by @data of @size falls within our safe buffer, return
+ * the equivalent pointer to the same safe data.  Assumes
+ * copy_from_kernel_nofault() has already happened and our safe buffer is
+ * populated.
+ */
+static void *__btf_show_obj_safe(struct btf_show *show, void *data, int size)
+{
+	if (btf_show_obj_is_safe(show, data, size))
+		return show->obj.safe + (data - show->obj.data);
+	return NULL;
+}
+
+/*
+ * Return a safe-to-access version of data pointed to by @data.
+ * We do this by copying the relevant amount of information
+ * to the struct btf_show obj.safe buffer using copy_from_kernel_nofault().
+ *
+ * If BTF_SHOW_UNSAFE is specified, just return data as-is; no
+ * safe copy is needed.
+ *
+ * Otherwise we need to determine if we have the required amount
+ * of data (determined by the @data pointer and the size of the
+ * largest base type we can encounter (represented by
+ * BTF_SHOW_OBJ_BASE_TYPE_SIZE). Having that much data ensures
+ * that we will be able to print some of the current object,
+ * and if more is needed a copy will be triggered.
+ * Some objects such as structs will not fit into the buffer;
+ * in such cases additional copies when we iterate over their
+ * members may be needed.
+ *
+ * btf_show_obj_safe() is used to return a safe buffer for
+ * btf_show_start_type(); this ensures that as we recurse into
+ * nested types we always have safe data for the given type.
+ * This approach is somewhat wasteful; it's possible for example
+ * that when iterating over a large union we'll end up copying the
+ * same data repeatedly, but the goal is safety not performance.
+ * We use stack data as opposed to per-CPU buffers because the
+ * iteration over a type can take some time, and preemption handling
+ * would greatly complicate use of the safe buffer.
+ */
+static void *btf_show_obj_safe(struct btf_show *show,
+			       const struct btf_type *t,
+			       void *data)
+{
+	const struct btf_type *rt;
+	int size_left, size;
+	void *safe = NULL;
+
+	if (show->flags & BTF_SHOW_UNSAFE)
+		return data;
+
+	rt = btf_resolve_size(show->btf, t, &size);
+	if (IS_ERR(rt)) {
+		show->state.status = PTR_ERR(rt);
+		return NULL;
+	}
+
+	/*
+	 * Is this toplevel object? If so, set total object size and
+	 * initialize pointers.  Otherwise check if we still fall within
+	 * our safe object data.
+	 */
+	if (show->state.depth == 0) {
+		show->obj.size = size;
+		show->obj.head = data;
+	} else {
+		/*
+		 * If the size of the current object is > our remaining
+		 * safe buffer we _may_ need to do a new copy.  However
+		 * consider the case of a nested struct; it's size pushes
+		 * us over the safe buffer limit, but showing any individual
+		 * struct members does not.  In such cases, we don't need
+		 * to initiate a fresh copy yet; however we definitely need
+		 * at least BTF_SHOW_OBJ_BASE_TYPE_SIZE bytes left
+		 * in our buffer, regardless of the current object size.
+		 * The logic here is that as we resolve types we will
+		 * hit a base type at some point, and we need to be sure
+		 * the next chunk of data is safely available to display
+		 * that type info safely.  We cannot rely on the size of
+		 * the current object here because it may be much larger
+		 * than our current buffer (e.g. task_struct is 8k).
+		 * All we want to do here is ensure that we can print the
+		 * next basic type, which we can if either
+		 * - the current type size is within the safe buffer; or
+		 * - at least BTF_SHOW_OBJ_BASE_TYPE_SIZE bytes are left in
+		 *   the safe buffer.
+		 */
+		safe = __btf_show_obj_safe(show, data,
+					   min(size,
+					       BTF_SHOW_OBJ_BASE_TYPE_SIZE));
+	}
+
+	/*
+	 * We need a new copy to our safe object, either because we haven't
+	 * yet copied and are intializing safe data, or because the data
+	 * we want falls outside the boundaries of the safe object.
+	 */
+	if (!safe) {
+		size_left = btf_show_obj_size_left(show, data);
+		if (size_left > BTF_SHOW_OBJ_SAFE_SIZE)
+			size_left = BTF_SHOW_OBJ_SAFE_SIZE;
+		show->state.status = copy_from_kernel_nofault(show->obj.safe,
+							      data, size_left);
+		if (!show->state.status) {
+			show->obj.data = data;
+			safe = show->obj.safe;
+		}
+	}
+
+	return safe;
+}
+
+/*
+ * Set the type we are starting to show and return a safe data pointer
+ * to be used for showing the associated data.
+ */
+static void *btf_show_start_type(struct btf_show *show,
+				 const struct btf_type *t,
+				 u32 type_id, void *data)
+{
+	show->state.type = t;
+	show->state.type_id = type_id;
+	show->state.name[0] = '\0';
+
+	return btf_show_obj_safe(show, t, data);
+}
+
+static void btf_show_end_type(struct btf_show *show)
+{
+	show->state.type = NULL;
+	show->state.type_id = 0;
+	show->state.name[0] = '\0';
+}
+
+static void *btf_show_start_aggr_type(struct btf_show *show,
+				      const struct btf_type *t,
+				      u32 type_id, void *data)
+{
+	void *safe_data = btf_show_start_type(show, t, type_id, data);
+
+	if (!safe_data)
+		return safe_data;
+
+	btf_show(show, "%s%s%s", btf_show_indent(show),
+		 btf_show_name(show),
+		 btf_show_newline(show));
+	show->state.depth++;
+	return safe_data;
+}
+
+static void btf_show_end_aggr_type(struct btf_show *show,
+				   const char *suffix)
+{
+	show->state.depth--;
+	btf_show(show, "%s%s%s%s", btf_show_indent(show), suffix,
+		 btf_show_delim(show), btf_show_newline(show));
+	btf_show_end_type(show);
+}
+
+static void btf_show_start_member(struct btf_show *show,
+				  const struct btf_member *m)
+{
+	show->state.member = m;
+}
+
+static void btf_show_start_array_member(struct btf_show *show)
+{
+	show->state.array_member = 1;
+	btf_show_start_member(show, NULL);
+}
+
+static void btf_show_end_member(struct btf_show *show)
+{
+	show->state.member = NULL;
+}
+
+static void btf_show_end_array_member(struct btf_show *show)
+{
+	show->state.array_member = 0;
+	btf_show_end_member(show);
+}
+
+static void *btf_show_start_array_type(struct btf_show *show,
+				       const struct btf_type *t,
+				       u32 type_id,
+				       u16 array_encoding,
+				       void *data)
+{
+	show->state.array_encoding = array_encoding;
+	show->state.array_terminated = 0;
+	return btf_show_start_aggr_type(show, t, type_id, data);
+}
+
+static void btf_show_end_array_type(struct btf_show *show)
+{
+	show->state.array_encoding = 0;
+	show->state.array_terminated = 0;
+	btf_show_end_aggr_type(show, "]");
+}
+
+static void *btf_show_start_struct_type(struct btf_show *show,
+					const struct btf_type *t,
+					u32 type_id,
+					void *data)
+{
+	return btf_show_start_aggr_type(show, t, type_id, data);
+}
+
+static void btf_show_end_struct_type(struct btf_show *show)
+{
+	btf_show_end_aggr_type(show, "}");
+}
+
 __printf(2, 3) static void __btf_verifier_log(struct bpf_verifier_log *log,
 					      const char *fmt, ...)
 {
@@ -1268,11 +1835,11 @@ static int btf_df_resolve(struct btf_verifier_env *env,
 	return -EINVAL;
 }
 
-static void btf_df_seq_show(const struct btf *btf, const struct btf_type *t,
-			    u32 type_id, void *data, u8 bits_offsets,
-			    struct seq_file *m)
+static void btf_df_show(const struct btf *btf, const struct btf_type *t,
+			u32 type_id, void *data, u8 bits_offsets,
+			struct btf_show *show)
 {
-	seq_printf(m, "<unsupported kind:%u>", BTF_INFO_KIND(t->info));
+	btf_show(show, "<unsupported kind:%u>", BTF_INFO_KIND(t->info));
 }
 
 static int btf_int_check_member(struct btf_verifier_env *env,
@@ -1445,7 +2012,7 @@ static void btf_int_log(struct btf_verifier_env *env,
 			 btf_int_encoding_str(BTF_INT_ENCODING(int_data)));
 }
 
-static void btf_int128_print(struct seq_file *m, void *data)
+static void btf_int128_print(struct btf_show *show, void *data)
 {
 	/* data points to a __int128 number.
 	 * Suppose
@@ -1464,9 +2031,10 @@ static void btf_int128_print(struct seq_file *m, void *data)
 	lower_num = *(u64 *)data;
 #endif
 	if (upper_num == 0)
-		seq_printf(m, "0x%llx", lower_num);
+		btf_show_type_value(show, "0x%llx", lower_num);
 	else
-		seq_printf(m, "0x%llx%016llx", upper_num, lower_num);
+		btf_show_type_values(show, "0x%llx%016llx", upper_num,
+				     lower_num);
 }
 
 static void btf_int128_shift(u64 *print_num, u16 left_shift_bits,
@@ -1510,8 +2078,8 @@ static void btf_int128_shift(u64 *print_num, u16 left_shift_bits,
 #endif
 }
 
-static void btf_bitfield_seq_show(void *data, u8 bits_offset,
-				  u8 nr_bits, struct seq_file *m)
+static void btf_bitfield_show(void *data, u8 bits_offset,
+			      u8 nr_bits, struct btf_show *show)
 {
 	u16 left_shift_bits, right_shift_bits;
 	u8 nr_copy_bytes;
@@ -1531,14 +2099,14 @@ static void btf_bitfield_seq_show(void *data, u8 bits_offset,
 	right_shift_bits = BITS_PER_U128 - nr_bits;
 
 	btf_int128_shift(print_num, left_shift_bits, right_shift_bits);
-	btf_int128_print(m, print_num);
+	btf_int128_print(show, print_num);
 }
 
 
-static void btf_int_bits_seq_show(const struct btf *btf,
-				  const struct btf_type *t,
-				  void *data, u8 bits_offset,
-				  struct seq_file *m)
+static void btf_int_bits_show(const struct btf *btf,
+			      const struct btf_type *t,
+			      void *data, u8 bits_offset,
+			      struct btf_show *show)
 {
 	u32 int_data = btf_type_int(t);
 	u8 nr_bits = BTF_INT_BITS(int_data);
@@ -1551,55 +2119,77 @@ static void btf_int_bits_seq_show(const struct btf *btf,
 	total_bits_offset = bits_offset + BTF_INT_OFFSET(int_data);
 	data += BITS_ROUNDDOWN_BYTES(total_bits_offset);
 	bits_offset = BITS_PER_BYTE_MASKED(total_bits_offset);
-	btf_bitfield_seq_show(data, bits_offset, nr_bits, m);
+	btf_bitfield_show(data, bits_offset, nr_bits, show);
 }
 
-static void btf_int_seq_show(const struct btf *btf, const struct btf_type *t,
-			     u32 type_id, void *data, u8 bits_offset,
-			     struct seq_file *m)
+static void btf_int_show(const struct btf *btf, const struct btf_type *t,
+			 u32 type_id, void *data, u8 bits_offset,
+			 struct btf_show *show)
 {
 	u32 int_data = btf_type_int(t);
 	u8 encoding = BTF_INT_ENCODING(int_data);
 	bool sign = encoding & BTF_INT_SIGNED;
 	u8 nr_bits = BTF_INT_BITS(int_data);
+	void *safe_data;
+
+	safe_data = btf_show_start_type(show, t, type_id, data);
+	if (!safe_data)
+		return;
 
 	if (bits_offset || BTF_INT_OFFSET(int_data) ||
 	    BITS_PER_BYTE_MASKED(nr_bits)) {
-		btf_int_bits_seq_show(btf, t, data, bits_offset, m);
-		return;
+		btf_int_bits_show(btf, t, safe_data, bits_offset, show);
+		goto out;
 	}
 
 	switch (nr_bits) {
 	case 128:
-		btf_int128_print(m, data);
+		btf_int128_print(show, safe_data);
 		break;
 	case 64:
 		if (sign)
-			seq_printf(m, "%lld", *(s64 *)data);
+			btf_show_type_value(show, "%lld", *(s64 *)safe_data);
 		else
-			seq_printf(m, "%llu", *(u64 *)data);
+			btf_show_type_value(show, "%llu", *(u64 *)safe_data);
 		break;
 	case 32:
 		if (sign)
-			seq_printf(m, "%d", *(s32 *)data);
+			btf_show_type_value(show, "%d", *(s32 *)safe_data);
 		else
-			seq_printf(m, "%u", *(u32 *)data);
+			btf_show_type_value(show, "%u", *(u32 *)safe_data);
 		break;
 	case 16:
 		if (sign)
-			seq_printf(m, "%d", *(s16 *)data);
+			btf_show_type_value(show, "%d", *(s16 *)safe_data);
 		else
-			seq_printf(m, "%u", *(u16 *)data);
+			btf_show_type_value(show, "%u", *(u16 *)safe_data);
 		break;
 	case 8:
+		if (show->state.array_encoding == BTF_INT_CHAR) {
+			/* check for null terminator */
+			if (show->state.array_terminated)
+				break;
+			if (*(char *)data == '\0') {
+				show->state.array_terminated = 1;
+				break;
+			}
+			if (isprint(*(char *)data)) {
+				btf_show_type_value(show, "'%c'",
+						    *(char *)safe_data);
+				break;
+			}
+		}
 		if (sign)
-			seq_printf(m, "%d", *(s8 *)data);
+			btf_show_type_value(show, "%d", *(s8 *)safe_data);
 		else
-			seq_printf(m, "%u", *(u8 *)data);
+			btf_show_type_value(show, "%u", *(u8 *)safe_data);
 		break;
 	default:
-		btf_int_bits_seq_show(btf, t, data, bits_offset, m);
+		btf_int_bits_show(btf, t, safe_data, bits_offset, show);
+		break;
 	}
+out:
+	btf_show_end_type(show);
 }
 
 static const struct btf_kind_operations int_ops = {
@@ -1608,7 +2198,7 @@ static const struct btf_kind_operations int_ops = {
 	.check_member = btf_int_check_member,
 	.check_kflag_member = btf_int_check_kflag_member,
 	.log_details = btf_int_log,
-	.seq_show = btf_int_seq_show,
+	.show = btf_int_show,
 };
 
 static int btf_modifier_check_member(struct btf_verifier_env *env,
@@ -1872,34 +2462,44 @@ static int btf_ptr_resolve(struct btf_verifier_env *env,
 	return 0;
 }
 
-static void btf_modifier_seq_show(const struct btf *btf,
-				  const struct btf_type *t,
-				  u32 type_id, void *data,
-				  u8 bits_offset, struct seq_file *m)
+static void btf_modifier_show(const struct btf *btf,
+			      const struct btf_type *t,
+			      u32 type_id, void *data,
+			      u8 bits_offset, struct btf_show *show)
 {
 	if (btf->resolved_ids)
 		t = btf_type_id_resolve(btf, &type_id);
 	else
 		t = btf_type_skip_modifiers(btf, type_id, NULL);
 
-	btf_type_ops(t)->seq_show(btf, t, type_id, data, bits_offset, m);
+	btf_type_ops(t)->show(btf, t, type_id, data, bits_offset, show);
 }
 
-static void btf_var_seq_show(const struct btf *btf, const struct btf_type *t,
-			     u32 type_id, void *data, u8 bits_offset,
-			     struct seq_file *m)
+static void btf_var_show(const struct btf *btf, const struct btf_type *t,
+			 u32 type_id, void *data, u8 bits_offset,
+			 struct btf_show *show)
 {
 	t = btf_type_id_resolve(btf, &type_id);
 
-	btf_type_ops(t)->seq_show(btf, t, type_id, data, bits_offset, m);
+	btf_type_ops(t)->show(btf, t, type_id, data, bits_offset, show);
 }
 
-static void btf_ptr_seq_show(const struct btf *btf, const struct btf_type *t,
-			     u32 type_id, void *data, u8 bits_offset,
-			     struct seq_file *m)
+static void btf_ptr_show(const struct btf *btf, const struct btf_type *t,
+			 u32 type_id, void *data, u8 bits_offset,
+			 struct btf_show *show)
 {
-	/* It is a hashed value */
-	seq_printf(m, "%p", *(void **)data);
+	void *safe_data;
+
+	safe_data = btf_show_start_type(show, t, type_id, data);
+	if (!safe_data)
+		return;
+
+	/* It is a hashed value unless BTF_SHOW_PTR_RAW is specified */
+	if (show->flags & BTF_SHOW_PTR_RAW)
+		btf_show_type_value(show, "0x%px", *(void **)safe_data);
+	else
+		btf_show_type_value(show, "0x%p", *(void **)safe_data);
+	btf_show_end_type(show);
 }
 
 static void btf_ref_type_log(struct btf_verifier_env *env,
@@ -1914,7 +2514,7 @@ static struct btf_kind_operations modifier_ops = {
 	.check_member = btf_modifier_check_member,
 	.check_kflag_member = btf_modifier_check_kflag_member,
 	.log_details = btf_ref_type_log,
-	.seq_show = btf_modifier_seq_show,
+	.show = btf_modifier_show,
 };
 
 static struct btf_kind_operations ptr_ops = {
@@ -1923,7 +2523,7 @@ static struct btf_kind_operations ptr_ops = {
 	.check_member = btf_ptr_check_member,
 	.check_kflag_member = btf_generic_check_kflag_member,
 	.log_details = btf_ref_type_log,
-	.seq_show = btf_ptr_seq_show,
+	.show = btf_ptr_show,
 };
 
 static s32 btf_fwd_check_meta(struct btf_verifier_env *env,
@@ -1964,7 +2564,7 @@ static struct btf_kind_operations fwd_ops = {
 	.check_member = btf_df_check_member,
 	.check_kflag_member = btf_df_check_kflag_member,
 	.log_details = btf_fwd_type_log,
-	.seq_show = btf_df_seq_show,
+	.show = btf_df_show,
 };
 
 static int btf_array_check_member(struct btf_verifier_env *env,
@@ -2123,28 +2723,90 @@ static void btf_array_log(struct btf_verifier_env *env,
 			 array->type, array->index_type, array->nelems);
 }
 
-static void btf_array_seq_show(const struct btf *btf, const struct btf_type *t,
-			       u32 type_id, void *data, u8 bits_offset,
-			       struct seq_file *m)
+static void __btf_array_show(const struct btf *btf, const struct btf_type *t,
+			     u32 type_id, void *data, u8 bits_offset,
+			     struct btf_show *show)
 {
 	const struct btf_array *array = btf_type_array(t);
 	const struct btf_kind_operations *elem_ops;
 	const struct btf_type *elem_type;
-	u32 i, elem_size, elem_type_id;
+	u32 i, elem_size = 0, elem_type_id;
+	u16 encoding = 0;
 
 	elem_type_id = array->type;
-	elem_type = btf_type_id_size(btf, &elem_type_id, &elem_size);
+	elem_type = btf_type_skip_modifiers(btf, elem_type_id, NULL);
+	if (elem_type && btf_type_has_size(elem_type))
+		elem_size = elem_type->size;
+
+	if (elem_type && btf_type_is_int(elem_type)) {
+		u32 int_type = btf_type_int(elem_type);
+
+		encoding = BTF_INT_ENCODING(int_type);
+
+		/*
+		 * BTF_INT_CHAR encoding never seems to be set for
+		 * char arrays, so if size is 1 and element is
+		 * printable as a char, we'll do that.
+		 */
+		if (elem_size == 1)
+			encoding = BTF_INT_CHAR;
+	}
+
+	if (!btf_show_start_array_type(show, t, type_id, encoding, data))
+		return;
+
+	if (!elem_type)
+		goto out;
 	elem_ops = btf_type_ops(elem_type);
-	seq_puts(m, "[");
+
 	for (i = 0; i < array->nelems; i++) {
-		if (i)
-			seq_puts(m, ",");
 
-		elem_ops->seq_show(btf, elem_type, elem_type_id, data,
-				   bits_offset, m);
+		btf_show_start_array_member(show);
+
+		elem_ops->show(btf, elem_type, elem_type_id, data,
+			       bits_offset, show);
 		data += elem_size;
+
+		btf_show_end_array_member(show);
+
+		if (show->state.array_terminated)
+			break;
+	}
+out:
+	btf_show_end_array_type(show);
+}
+
+static void btf_array_show(const struct btf *btf, const struct btf_type *t,
+			   u32 type_id, void *data, u8 bits_offset,
+			   struct btf_show *show)
+{
+	const struct btf_member *m = show->state.member;
+
+	/*
+	 * First check if any members would be shown (are non-zero).
+	 * See comments above "struct btf_show" definition for more
+	 * details on how this works at a high-level.
+	 */
+	if (show->state.depth > 0 && !(show->flags & BTF_SHOW_ZERO)) {
+		if (!show->state.depth_check) {
+			show->state.depth_check = show->state.depth + 1;
+			show->state.depth_to_show = 0;
+		}
+		__btf_array_show(btf, t, type_id, data, bits_offset, show);
+		show->state.member = m;
+
+		if (show->state.depth_check != show->state.depth + 1)
+			return;
+		show->state.depth_check = 0;
+
+		if (show->state.depth_to_show <= show->state.depth)
+			return;
+		/*
+		 * Reaching here indicates we have recursed and found
+		 * non-zero array member(s).
+		 */
 	}
-	seq_puts(m, "]");
+	__btf_array_show(btf, t, type_id, data, bits_offset, show);
 }
 
 static struct btf_kind_operations array_ops = {
@@ -2153,7 +2815,7 @@ static struct btf_kind_operations array_ops = {
 	.check_member = btf_array_check_member,
 	.check_kflag_member = btf_generic_check_kflag_member,
 	.log_details = btf_array_log,
-	.seq_show = btf_array_seq_show,
+	.show = btf_array_show,
 };
 
 static int btf_struct_check_member(struct btf_verifier_env *env,
@@ -2376,15 +3038,18 @@ int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t)
 	return off;
 }
 
-static void btf_struct_seq_show(const struct btf *btf, const struct btf_type *t,
-				u32 type_id, void *data, u8 bits_offset,
-				struct seq_file *m)
+static void __btf_struct_show(const struct btf *btf, const struct btf_type *t,
+			      u32 type_id, void *data, u8 bits_offset,
+			      struct btf_show *show)
 {
-	const char *seq = BTF_INFO_KIND(t->info) == BTF_KIND_UNION ? "|" : ",";
 	const struct btf_member *member;
+	void *safe_data;
 	u32 i;
 
-	seq_puts(m, "{");
+	safe_data = btf_show_start_struct_type(show, t, type_id, data);
+	if (!safe_data)
+		return;
+
 	for_each_member(i, t, member) {
 		const struct btf_type *member_type = btf_type_by_id(btf,
 								member->type);
@@ -2393,23 +3058,65 @@ static void btf_struct_seq_show(const struct btf *btf, const struct btf_type *t,
 		u32 bytes_offset;
 		u8 bits8_offset;
 
-		if (i)
-			seq_puts(m, seq);
+		btf_show_start_member(show, member);
 
 		member_offset = btf_member_bit_offset(t, member);
 		bitfield_size = btf_member_bitfield_size(t, member);
 		bytes_offset = BITS_ROUNDDOWN_BYTES(member_offset);
 		bits8_offset = BITS_PER_BYTE_MASKED(member_offset);
 		if (bitfield_size) {
-			btf_bitfield_seq_show(data + bytes_offset, bits8_offset,
-					      bitfield_size, m);
+			safe_data = btf_show_start_type(show, member_type,
+							member->type,
+							data + bytes_offset);
+			if (safe_data)
+				btf_bitfield_show(safe_data,
+						  bits8_offset,
+						  bitfield_size, show);
+			btf_show_end_type(show);
 		} else {
 			ops = btf_type_ops(member_type);
-			ops->seq_show(btf, member_type, member->type,
-				      data + bytes_offset, bits8_offset, m);
+			ops->show(btf, member_type, member->type,
+				  data + bytes_offset, bits8_offset, show);
 		}
+
+		btf_show_end_member(show);
+	}
+
+	btf_show_end_struct_type(show);
+}
+
+static void btf_struct_show(const struct btf *btf, const struct btf_type *t,
+			    u32 type_id, void *data, u8 bits_offset,
+			    struct btf_show *show)
+{
+	const struct btf_member *m = show->state.member;
+
+	/*
+	 * First check if any members would be shown (are non-zero).
+	 * See comments above "struct btf_show" definition for more
+	 * details on how this works at a high-level.
+	 */
+	if (show->state.depth > 0 && !(show->flags & BTF_SHOW_ZERO)) {
+		if (!show->state.depth_check) {
+			show->state.depth_check = show->state.depth + 1;
+			show->state.depth_to_show = 0;
+		}
+		__btf_struct_show(btf, t, type_id, data, bits_offset, show);
+		/* Restore saved member data here */
+		show->state.member = m;
+		if (show->state.depth_check != show->state.depth + 1)
+			return;
+		show->state.depth_check = 0;
+
+		if (show->state.depth_to_show <= show->state.depth)
+			return;
+		/*
+		 * Reaching here indicates we have recursed and found
+		 * non-zero child values.
+		 */
 	}
-	seq_puts(m, "}");
+
+	__btf_struct_show(btf, t, type_id, data, bits_offset, show);
 }
 
 static struct btf_kind_operations struct_ops = {
@@ -2418,7 +3125,7 @@ static struct btf_kind_operations struct_ops = {
 	.check_member = btf_struct_check_member,
 	.check_kflag_member = btf_generic_check_kflag_member,
 	.log_details = btf_struct_log,
-	.seq_show = btf_struct_seq_show,
+	.show = btf_struct_show,
 };
 
 static int btf_enum_check_member(struct btf_verifier_env *env,
@@ -2549,24 +3256,35 @@ static void btf_enum_log(struct btf_verifier_env *env,
 	btf_verifier_log(env, "size=%u vlen=%u", t->size, btf_type_vlen(t));
 }
 
-static void btf_enum_seq_show(const struct btf *btf, const struct btf_type *t,
-			      u32 type_id, void *data, u8 bits_offset,
-			      struct seq_file *m)
+static void btf_enum_show(const struct btf *btf, const struct btf_type *t,
+			  u32 type_id, void *data, u8 bits_offset,
+			  struct btf_show *show)
 {
 	const struct btf_enum *enums = btf_type_enum(t);
 	u32 i, nr_enums = btf_type_vlen(t);
-	int v = *(int *)data;
+	void *safe_data;
+	int v;
+
+	safe_data = btf_show_start_type(show, t, type_id, data);
+	if (!safe_data)
+		return;
+
+	v = *(int *)safe_data;
 
 	for (i = 0; i < nr_enums; i++) {
-		if (v == enums[i].val) {
-			seq_printf(m, "%s",
-				   __btf_name_by_offset(btf,
-							enums[i].name_off));
-			return;
-		}
+		if (v != enums[i].val)
+			continue;
+
+		btf_show_type_value(show, "%s",
+				    __btf_name_by_offset(btf,
+							 enums[i].name_off));
+
+		btf_show_end_type(show);
+		return;
 	}
 
-	seq_printf(m, "%d", v);
+	btf_show_type_value(show, "%d", v);
+	btf_show_end_type(show);
 }
 
 static struct btf_kind_operations enum_ops = {
@@ -2575,7 +3293,7 @@ static struct btf_kind_operations enum_ops = {
 	.check_member = btf_enum_check_member,
 	.check_kflag_member = btf_enum_check_kflag_member,
 	.log_details = btf_enum_log,
-	.seq_show = btf_enum_seq_show,
+	.show = btf_enum_show,
 };
 
 static s32 btf_func_proto_check_meta(struct btf_verifier_env *env,
@@ -2662,7 +3380,7 @@ static struct btf_kind_operations func_proto_ops = {
 	.check_member = btf_df_check_member,
 	.check_kflag_member = btf_df_check_kflag_member,
 	.log_details = btf_func_proto_log,
-	.seq_show = btf_df_seq_show,
+	.show = btf_df_show,
 };
 
 static s32 btf_func_check_meta(struct btf_verifier_env *env,
@@ -2696,7 +3414,7 @@ static struct btf_kind_operations func_ops = {
 	.check_member = btf_df_check_member,
 	.check_kflag_member = btf_df_check_kflag_member,
 	.log_details = btf_ref_type_log,
-	.seq_show = btf_df_seq_show,
+	.show = btf_df_show,
 };
 
 static s32 btf_var_check_meta(struct btf_verifier_env *env,
@@ -2760,7 +3478,7 @@ static const struct btf_kind_operations var_ops = {
 	.check_member		= btf_df_check_member,
 	.check_kflag_member	= btf_df_check_kflag_member,
 	.log_details		= btf_var_log,
-	.seq_show		= btf_var_seq_show,
+	.show			= btf_var_show,
 };
 
 static s32 btf_datasec_check_meta(struct btf_verifier_env *env,
@@ -2886,24 +3604,28 @@ static void btf_datasec_log(struct btf_verifier_env *env,
 	btf_verifier_log(env, "size=%u vlen=%u", t->size, btf_type_vlen(t));
 }
 
-static void btf_datasec_seq_show(const struct btf *btf,
-				 const struct btf_type *t, u32 type_id,
-				 void *data, u8 bits_offset,
-				 struct seq_file *m)
+static void btf_datasec_show(const struct btf *btf,
+			     const struct btf_type *t, u32 type_id,
+			     void *data, u8 bits_offset,
+			     struct btf_show *show)
 {
 	const struct btf_var_secinfo *vsi;
 	const struct btf_type *var;
 	u32 i;
 
-	seq_printf(m, "section (\"%s\") = {", __btf_name_by_offset(btf, t->name_off));
+	if (!btf_show_start_type(show, t, type_id, data))
+		return;
+
+	btf_show_type_value(show, "section (\"%s\") = {",
+			    __btf_name_by_offset(btf, t->name_off));
 	for_each_vsi(i, t, vsi) {
 		var = btf_type_by_id(btf, vsi->type);
 		if (i)
-			seq_puts(m, ",");
-		btf_type_ops(var)->seq_show(btf, var, vsi->type,
-					    data + vsi->offset, bits_offset, m);
+			btf_show(show, ",");
+		btf_type_ops(var)->show(btf, var, vsi->type,
+					data + vsi->offset, bits_offset, show);
 	}
-	seq_puts(m, "}");
+	btf_show_end_type(show);
 }
 
 static const struct btf_kind_operations datasec_ops = {
@@ -2912,7 +3634,7 @@ static const struct btf_kind_operations datasec_ops = {
 	.check_member		= btf_df_check_member,
 	.check_kflag_member	= btf_df_check_kflag_member,
 	.log_details		= btf_datasec_log,
-	.seq_show		= btf_datasec_seq_show,
+	.show			= btf_datasec_show,
 };
 
 static int btf_func_proto_check(struct btf_verifier_env *env,
@@ -3706,7 +4428,7 @@ errout:
 
 struct btf *bpf_prog_get_target_btf(const struct bpf_prog *prog)
 {
-	struct bpf_prog *tgt_prog = prog->aux->linked_prog;
+	struct bpf_prog *tgt_prog = prog->aux->dst_prog;
 
 	if (tgt_prog) {
 		return tgt_prog->aux->btf;
@@ -3733,7 +4455,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 		    struct bpf_insn_access_aux *info)
 {
 	const struct btf_type *t = prog->aux->attach_func_proto;
-	struct bpf_prog *tgt_prog = prog->aux->linked_prog;
+	struct bpf_prog *tgt_prog = prog->aux->dst_prog;
 	struct btf *btf = bpf_prog_get_target_btf(prog);
 	const char *tname = prog->aux->attach_func_name;
 	struct bpf_verifier_log *log = info->log;
@@ -3860,7 +4582,14 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 
 	info->reg_type = PTR_TO_BTF_ID;
 	if (tgt_prog) {
-		ret = btf_translate_to_vmlinux(log, btf, t, tgt_prog->type, arg);
+		enum bpf_prog_type tgt_type;
+
+		if (tgt_prog->type == BPF_PROG_TYPE_EXT)
+			tgt_type = tgt_prog->aux->saved_dst_prog_type;
+		else
+			tgt_type = tgt_prog->type;
+
+		ret = btf_translate_to_vmlinux(log, btf, t, tgt_type, arg);
 		if (ret > 0) {
 			info->btf_id = ret;
 			return true;
@@ -4193,19 +4922,6 @@ again:
 	return true;
 }
 
-int btf_resolve_helper_id(struct bpf_verifier_log *log,
-			  const struct bpf_func_proto *fn, int arg)
-{
-	int id;
-
-	if (fn->arg_type[arg] != ARG_PTR_TO_BTF_ID || !btf_vmlinux)
-		return -EINVAL;
-	id = fn->btf_id[arg];
-	if (!id || id > btf_vmlinux->nr_types)
-		return -EINVAL;
-	return id;
-}
-
 static int __get_type_size(struct btf *btf, u32 btf_id,
 			   const struct btf_type **bad_type)
 {
@@ -4401,7 +5117,7 @@ static int btf_check_func_type_match(struct bpf_verifier_log *log,
 }
 
 /* Compare BTFs of given program with BTF of target program */
-int btf_check_type_match(struct bpf_verifier_env *env, struct bpf_prog *prog,
+int btf_check_type_match(struct bpf_verifier_log *log, const struct bpf_prog *prog,
 			 struct btf *btf2, const struct btf_type *t2)
 {
 	struct btf *btf1 = prog->aux->btf;
@@ -4409,7 +5125,7 @@ int btf_check_type_match(struct bpf_verifier_env *env, struct bpf_prog *prog,
 	u32 btf_id = 0;
 
 	if (!prog->aux->func_info) {
-		bpf_log(&env->log, "Program extension requires BTF\n");
+		bpf_log(log, "Program extension requires BTF\n");
 		return -EINVAL;
 	}
 
@@ -4421,7 +5137,7 @@ int btf_check_type_match(struct bpf_verifier_env *env, struct bpf_prog *prog,
 	if (!t1 || !btf_type_is_func(t1))
 		return -EFAULT;
 
-	return btf_check_func_type_match(&env->log, btf1, t1, btf2, t2);
+	return btf_check_func_type_match(log, btf1, t1, btf2, t2);
 }
 
 /* Compare BTF of a function with given bpf_reg_state.
@@ -4572,7 +5288,7 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
 		return -EFAULT;
 	}
 	if (prog_type == BPF_PROG_TYPE_EXT)
-		prog_type = prog->aux->linked_prog->type;
+		prog_type = prog->aux->dst_prog->type;
 
 	t = btf_type_by_id(btf, t->type);
 	if (!t || !btf_type_is_func_proto(t)) {
@@ -4619,12 +5335,93 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
 	return 0;
 }
 
+static void btf_type_show(const struct btf *btf, u32 type_id, void *obj,
+			  struct btf_show *show)
+{
+	const struct btf_type *t = btf_type_by_id(btf, type_id);
+
+	show->btf = btf;
+	memset(&show->state, 0, sizeof(show->state));
+	memset(&show->obj, 0, sizeof(show->obj));
+
+	btf_type_ops(t)->show(btf, t, type_id, obj, 0, show);
+}
+
+static void btf_seq_show(struct btf_show *show, const char *fmt,
+			 va_list args)
+{
+	seq_vprintf((struct seq_file *)show->target, fmt, args);
+}
+
+int btf_type_seq_show_flags(const struct btf *btf, u32 type_id,
+			    void *obj, struct seq_file *m, u64 flags)
+{
+	struct btf_show sseq;
+
+	sseq.target = m;
+	sseq.showfn = btf_seq_show;
+	sseq.flags = flags;
+
+	btf_type_show(btf, type_id, obj, &sseq);
+
+	return sseq.state.status;
+}
+
 void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj,
 		       struct seq_file *m)
 {
-	const struct btf_type *t = btf_type_by_id(btf, type_id);
+	(void) btf_type_seq_show_flags(btf, type_id, obj, m,
+				       BTF_SHOW_NONAME | BTF_SHOW_COMPACT |
+				       BTF_SHOW_ZERO | BTF_SHOW_UNSAFE);
+}
+
+struct btf_show_snprintf {
+	struct btf_show show;
+	int len_left;		/* space left in string */
+	int len;		/* length we would have written */
+};
+
+static void btf_snprintf_show(struct btf_show *show, const char *fmt,
+			      va_list args)
+{
+	struct btf_show_snprintf *ssnprintf = (struct btf_show_snprintf *)show;
+	int len;
+
+	len = vsnprintf(show->target, ssnprintf->len_left, fmt, args);
+
+	if (len < 0) {
+		ssnprintf->len_left = 0;
+		ssnprintf->len = len;
+	} else if (len > ssnprintf->len_left) {
+		/* no space, drive on to get length we would have written */
+		ssnprintf->len_left = 0;
+		ssnprintf->len += len;
+	} else {
+		ssnprintf->len_left -= len;
+		ssnprintf->len += len;
+		show->target += len;
+	}
+}
+
+int btf_type_snprintf_show(const struct btf *btf, u32 type_id, void *obj,
+			   char *buf, int len, u64 flags)
+{
+	struct btf_show_snprintf ssnprintf;
+
+	ssnprintf.show.target = buf;
+	ssnprintf.show.flags = flags;
+	ssnprintf.show.showfn = btf_snprintf_show;
+	ssnprintf.len_left = len;
+	ssnprintf.len = 0;
+
+	btf_type_show(btf, type_id, obj, (struct btf_show *)&ssnprintf);
+
+	/* If we encontered an error, return it. */
+	if (ssnprintf.show.state.status)
+		return ssnprintf.show.state.status;
 
-	btf_type_ops(t)->seq_show(btf, t, type_id, obj, 0, m);
+	/* Otherwise return length we would have written */
+	return ssnprintf.len;
 }
 
 #ifdef CONFIG_PROC_FS
@@ -4772,7 +5569,7 @@ static int btf_id_cmp_func(const void *a, const void *b)
 	return *pa - *pb;
 }
 
-bool btf_id_set_contains(struct btf_id_set *set, u32 id)
+bool btf_id_set_contains(const struct btf_id_set *set, u32 id)
 {
 	return bsearch(&id, set->ids, set->cnt, sizeof(u32), btf_id_cmp_func) != NULL;
 }
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index ed0b3578867c..cda674f1392f 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -98,6 +98,8 @@ struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flag
 	fp->jit_requested = ebpf_jit_enabled();
 
 	INIT_LIST_HEAD_RCU(&fp->aux->ksym.lnode);
+	mutex_init(&fp->aux->used_maps_mutex);
+	mutex_init(&fp->aux->dst_mutex);
 
 	return fp;
 }
@@ -253,6 +255,8 @@ struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size,
 void __bpf_prog_free(struct bpf_prog *fp)
 {
 	if (fp->aux) {
+		mutex_destroy(&fp->aux->used_maps_mutex);
+		mutex_destroy(&fp->aux->dst_mutex);
 		free_percpu(fp->aux->stats);
 		kfree(fp->aux->poke_tab);
 		kfree(fp->aux);
@@ -773,7 +777,8 @@ int bpf_jit_add_poke_descriptor(struct bpf_prog *prog,
 
 	if (size > poke_tab_max)
 		return -ENOSPC;
-	if (poke->ip || poke->ip_stable || poke->adj_off)
+	if (poke->tailcall_target || poke->tailcall_target_stable ||
+	    poke->tailcall_bypass || poke->adj_off || poke->bypass_addr)
 		return -EINVAL;
 
 	switch (poke->reason) {
@@ -1747,8 +1752,9 @@ bool bpf_prog_array_compatible(struct bpf_array *array,
 static int bpf_check_tail_call(const struct bpf_prog *fp)
 {
 	struct bpf_prog_aux *aux = fp->aux;
-	int i;
+	int i, ret = 0;
 
+	mutex_lock(&aux->used_maps_mutex);
 	for (i = 0; i < aux->used_map_cnt; i++) {
 		struct bpf_map *map = aux->used_maps[i];
 		struct bpf_array *array;
@@ -1757,11 +1763,15 @@ static int bpf_check_tail_call(const struct bpf_prog *fp)
 			continue;
 
 		array = container_of(map, struct bpf_array, map);
-		if (!bpf_prog_array_compatible(array, fp))
-			return -EINVAL;
+		if (!bpf_prog_array_compatible(array, fp)) {
+			ret = -EINVAL;
+			goto out;
+		}
 	}
 
-	return 0;
+out:
+	mutex_unlock(&aux->used_maps_mutex);
+	return ret;
 }
 
 static void bpf_prog_select_func(struct bpf_prog *fp)
@@ -2130,7 +2140,8 @@ static void bpf_prog_free_deferred(struct work_struct *work)
 	if (aux->prog->has_callchain_buf)
 		put_callchain_buffers();
 #endif
-	bpf_trampoline_put(aux->trampoline);
+	if (aux->dst_trampoline)
+		bpf_trampoline_put(aux->dst_trampoline);
 	for (i = 0; i < aux->func_cnt; i++)
 		bpf_jit_free(aux->func[i]);
 	if (aux->func_cnt) {
@@ -2146,8 +2157,8 @@ void bpf_prog_free(struct bpf_prog *fp)
 {
 	struct bpf_prog_aux *aux = fp->aux;
 
-	if (aux->linked_prog)
-		bpf_prog_put(aux->linked_prog);
+	if (aux->dst_prog)
+		bpf_prog_put(aux->dst_prog);
 	INIT_WORK(&aux->work, bpf_prog_free_deferred);
 	schedule_work(&aux->work);
 }
@@ -2208,6 +2219,8 @@ const struct bpf_func_proto bpf_get_current_cgroup_id_proto __weak;
 const struct bpf_func_proto bpf_get_current_ancestor_cgroup_id_proto __weak;
 const struct bpf_func_proto bpf_get_local_storage_proto __weak;
 const struct bpf_func_proto bpf_get_ns_current_pid_tgid_proto __weak;
+const struct bpf_func_proto bpf_snprintf_btf_proto __weak;
+const struct bpf_func_proto bpf_seq_printf_btf_proto __weak;
 
 const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void)
 {
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index 7e1a8ad0c32a..c61a23b564aa 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -155,8 +155,7 @@ static void cpu_map_kthread_stop(struct work_struct *work)
 	kthread_stop(rcpu->kthread);
 }
 
-static struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu,
-					 struct xdp_frame *xdpf,
+static struct sk_buff *cpu_map_build_skb(struct xdp_frame *xdpf,
 					 struct sk_buff *skb)
 {
 	unsigned int hard_start_headroom;
@@ -365,7 +364,7 @@ static int cpu_map_kthread_run(void *data)
 			struct sk_buff *skb = skbs[i];
 			int ret;
 
-			skb = cpu_map_build_skb(rcpu, xdpf, skb);
+			skb = cpu_map_build_skb(xdpf, skb);
 			if (!skb) {
 				xdp_return_frame(xdpf);
 				continue;
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index fe0e06284d33..3395cf140d22 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -1622,7 +1622,6 @@ struct bpf_iter_seq_hash_map_info {
 	struct bpf_map *map;
 	struct bpf_htab *htab;
 	void *percpu_value_buf; // non-zero means percpu hash
-	unsigned long flags;
 	u32 bucket_id;
 	u32 skip_elems;
 };
@@ -1632,7 +1631,6 @@ bpf_hash_map_seq_find_next(struct bpf_iter_seq_hash_map_info *info,
 			   struct htab_elem *prev_elem)
 {
 	const struct bpf_htab *htab = info->htab;
-	unsigned long flags = info->flags;
 	u32 skip_elems = info->skip_elems;
 	u32 bucket_id = info->bucket_id;
 	struct hlist_nulls_head *head;
@@ -1656,19 +1654,18 @@ bpf_hash_map_seq_find_next(struct bpf_iter_seq_hash_map_info *info,
 
 		/* not found, unlock and go to the next bucket */
 		b = &htab->buckets[bucket_id++];
-		htab_unlock_bucket(htab, b, flags);
+		rcu_read_unlock();
 		skip_elems = 0;
 	}
 
 	for (i = bucket_id; i < htab->n_buckets; i++) {
 		b = &htab->buckets[i];
-		flags = htab_lock_bucket(htab, b);
+		rcu_read_lock();
 
 		count = 0;
 		head = &b->head;
 		hlist_nulls_for_each_entry_rcu(elem, n, head, hash_node) {
 			if (count >= skip_elems) {
-				info->flags = flags;
 				info->bucket_id = i;
 				info->skip_elems = count;
 				return elem;
@@ -1676,7 +1673,7 @@ bpf_hash_map_seq_find_next(struct bpf_iter_seq_hash_map_info *info,
 			count++;
 		}
 
-		htab_unlock_bucket(htab, b, flags);
+		rcu_read_unlock();
 		skip_elems = 0;
 	}
 
@@ -1754,14 +1751,10 @@ static int bpf_hash_map_seq_show(struct seq_file *seq, void *v)
 
 static void bpf_hash_map_seq_stop(struct seq_file *seq, void *v)
 {
-	struct bpf_iter_seq_hash_map_info *info = seq->private;
-
 	if (!v)
 		(void)__bpf_hash_map_seq_show(seq, NULL);
 	else
-		htab_unlock_bucket(info->htab,
-				   &info->htab->buckets[info->bucket_id],
-				   info->flags);
+		rcu_read_unlock();
 }
 
 static int bpf_iter_init_hash_map(void *priv_data,
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 5cc7425ee476..e825441781ab 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -683,6 +683,10 @@ bpf_base_func_proto(enum bpf_func_id func_id)
 		if (!perfmon_capable())
 			return NULL;
 		return bpf_get_trace_printk_proto();
+	case BPF_FUNC_snprintf_btf:
+		if (!perfmon_capable())
+			return NULL;
+		return &bpf_snprintf_btf_proto;
 	case BPF_FUNC_jiffies64:
 		return &bpf_jiffies64_proto;
 	default:
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index b48a56f53495..dd4b7fd60ee7 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -227,10 +227,12 @@ static void *map_seq_next(struct seq_file *m, void *v, loff_t *pos)
 	else
 		prev_key = key;
 
+	rcu_read_lock();
 	if (map->ops->map_get_next_key(map, prev_key, key)) {
 		map_iter(m)->done = true;
-		return NULL;
+		key = NULL;
 	}
+	rcu_read_unlock();
 	return key;
 }
 
diff --git a/kernel/bpf/preload/.gitignore b/kernel/bpf/preload/.gitignore
new file mode 100644
index 000000000000..856a4c5ad0dd
--- /dev/null
+++ b/kernel/bpf/preload/.gitignore
@@ -0,0 +1,4 @@
+/FEATURE-DUMP.libbpf
+/bpf_helper_defs.h
+/feature
+/bpf_preload_umd
diff --git a/kernel/bpf/preload/Makefile b/kernel/bpf/preload/Makefile
index 12c7b62b9b6e..23ee310b6eb4 100644
--- a/kernel/bpf/preload/Makefile
+++ b/kernel/bpf/preload/Makefile
@@ -12,6 +12,8 @@ userccflags += -I $(srctree)/tools/include/ -I $(srctree)/tools/include/uapi \
 
 userprogs := bpf_preload_umd
 
+clean-files := $(userprogs) bpf_helper_defs.h FEATURE-DUMP.libbpf staticobjs/ feature/
+
 bpf_preload_umd-objs := iterators/iterators.o
 bpf_preload_umd-userldlibs := $(LIBBPF_A) -lelf -lz
 
diff --git a/kernel/bpf/preload/iterators/iterators.bpf.c b/kernel/bpf/preload/iterators/iterators.bpf.c
index 5ded550b2ed6..52aa7b38e8b8 100644
--- a/kernel/bpf/preload/iterators/iterators.bpf.c
+++ b/kernel/bpf/preload/iterators/iterators.bpf.c
@@ -42,7 +42,7 @@ struct bpf_prog_aux {
 	__u32 id;
 	char name[16];
 	const char *attach_func_name;
-	struct bpf_prog *linked_prog;
+	struct bpf_prog *dst_prog;
 	struct bpf_func_info *func_info;
 	struct btf *btf;
 };
@@ -108,7 +108,7 @@ int dump_bpf_prog(struct bpf_iter__bpf_prog *ctx)
 
 	BPF_SEQ_PRINTF(seq, "%4u %-16s %s %s\n", aux->id,
 		       get_name(aux->btf, aux->func_info[0].type_id, aux->name),
-		       aux->attach_func_name, aux->linked_prog->aux->name);
+		       aux->attach_func_name, aux->dst_prog->aux->name);
 	return 0;
 }
 char LICENSE[] SEC("license") = "GPL";
diff --git a/kernel/bpf/preload/iterators/iterators.skel.h b/kernel/bpf/preload/iterators/iterators.skel.h
index c3171357dc4f..cf9a6a94b3a4 100644
--- a/kernel/bpf/preload/iterators/iterators.skel.h
+++ b/kernel/bpf/preload/iterators/iterators.skel.h
@@ -47,7 +47,7 @@ iterators_bpf__open_opts(const struct bpf_object_open_opts *opts)
 {
 	struct iterators_bpf *obj;
 
-	obj = (typeof(obj))calloc(1, sizeof(*obj));
+	obj = (struct iterators_bpf *)calloc(1, sizeof(*obj));
 	if (!obj)
 		return NULL;
 	if (iterators_bpf__create_skeleton(obj))
@@ -105,7 +105,7 @@ iterators_bpf__create_skeleton(struct iterators_bpf *obj)
 {
 	struct bpf_object_skeleton *s;
 
-	s = (typeof(s))calloc(1, sizeof(*s));
+	s = (struct bpf_object_skeleton *)calloc(1, sizeof(*s));
 	if (!s)
 		return -1;
 	obj->skeleton = s;
@@ -117,7 +117,7 @@ iterators_bpf__create_skeleton(struct iterators_bpf *obj)
 	/* maps */
 	s->map_cnt = 1;
 	s->map_skel_sz = sizeof(*s->maps);
-	s->maps = (typeof(s->maps))calloc(s->map_cnt, s->map_skel_sz);
+	s->maps = (struct bpf_map_skeleton *)calloc(s->map_cnt, s->map_skel_sz);
 	if (!s->maps)
 		goto err;
 
@@ -128,7 +128,7 @@ iterators_bpf__create_skeleton(struct iterators_bpf *obj)
 	/* programs */
 	s->prog_cnt = 2;
 	s->prog_skel_sz = sizeof(*s->progs);
-	s->progs = (typeof(s->progs))calloc(s->prog_cnt, s->prog_skel_sz);
+	s->progs = (struct bpf_prog_skeleton *)calloc(s->prog_cnt, s->prog_skel_sz);
 	if (!s->progs)
 		goto err;
 
@@ -140,10 +140,10 @@ iterators_bpf__create_skeleton(struct iterators_bpf *obj)
 	s->progs[1].prog = &obj->progs.dump_bpf_prog;
 	s->progs[1].link = &obj->links.dump_bpf_prog;
 
-	s->data_sz = 7128;
+	s->data_sz = 7176;
 	s->data = (void *)"\
 \x7f\x45\x4c\x46\x02\x01\x01\0\0\0\0\0\0\0\0\0\x01\0\xf7\0\x01\0\0\0\0\0\0\0\0\
-\0\0\0\0\0\0\0\0\0\0\0\x18\x18\0\0\0\0\0\0\0\0\0\0\x40\0\0\0\0\0\x40\0\x0f\0\
+\0\0\0\0\0\0\0\0\0\0\0\x48\x18\0\0\0\0\0\0\0\0\0\0\x40\0\0\0\0\0\x40\0\x0f\0\
 \x0e\0\x79\x12\0\0\0\0\0\0\x79\x26\0\0\0\0\0\0\x79\x17\x08\0\0\0\0\0\x15\x07\
 \x1a\0\0\0\0\0\x79\x21\x10\0\0\0\0\0\x55\x01\x08\0\0\0\0\0\xbf\xa4\0\0\0\0\0\0\
 \x07\x04\0\0\xe8\xff\xff\xff\xbf\x61\0\0\0\0\0\0\x18\x02\0\0\0\0\0\0\0\0\0\0\0\
@@ -164,7 +164,7 @@ iterators_bpf__create_skeleton(struct iterators_bpf *obj)
 \x79\x86\0\0\0\0\0\0\xbf\xa1\0\0\0\0\0\0\x07\x01\0\0\xf8\xff\xff\xff\xb7\x02\0\
 \0\x08\0\0\0\x85\0\0\0\x71\0\0\0\xb7\x01\0\0\0\0\0\0\x79\xa3\xf8\xff\0\0\0\0\
 \x0f\x13\0\0\0\0\0\0\xbf\xa1\0\0\0\0\0\0\x07\x01\0\0\xf4\xff\xff\xff\xb7\x02\0\
-\0\x04\0\0\0\x85\0\0\0\x04\0\0\0\xb7\x03\0\0\x04\0\0\0\x61\xa1\xf4\xff\0\0\0\0\
+\0\x04\0\0\0\x85\0\0\0\x71\0\0\0\xb7\x03\0\0\x04\0\0\0\x61\xa1\xf4\xff\0\0\0\0\
 \x61\x82\x10\0\0\0\0\0\x3d\x21\x02\0\0\0\0\0\x0f\x16\0\0\0\0\0\0\xbf\x69\0\0\0\
 \0\0\0\x7b\x9a\xd8\xff\0\0\0\0\x79\x71\x18\0\0\0\0\0\x7b\x1a\xe0\xff\0\0\0\0\
 \x79\x71\x20\0\0\0\0\0\x79\x11\0\0\0\0\0\0\x0f\x31\0\0\0\0\0\0\x7b\x1a\xe8\xff\
@@ -176,230 +176,232 @@ iterators_bpf__create_skeleton(struct iterators_bpf *obj)
 \x73\x25\x36\x64\x0a\0\x20\x20\x69\x64\x20\x6e\x61\x6d\x65\x20\x20\x20\x20\x20\
 \x20\x20\x20\x20\x20\x20\x20\x20\x61\x74\x74\x61\x63\x68\x65\x64\x0a\0\x25\x34\
 \x75\x20\x25\x2d\x31\x36\x73\x20\x25\x73\x20\x25\x73\x0a\0\x47\x50\x4c\0\x9f\
-\xeb\x01\0\x18\0\0\0\0\0\0\0\x1c\x04\0\0\x1c\x04\0\0\0\x05\0\0\0\0\0\0\0\0\0\
+\xeb\x01\0\x18\0\0\0\0\0\0\0\x1c\x04\0\0\x1c\x04\0\0\x09\x05\0\0\0\0\0\0\0\0\0\
 \x02\x02\0\0\0\x01\0\0\0\x02\0\0\x04\x10\0\0\0\x13\0\0\0\x03\0\0\0\0\0\0\0\x18\
 \0\0\0\x04\0\0\0\x40\0\0\0\0\0\0\0\0\0\0\x02\x08\0\0\0\0\0\0\0\0\0\0\x02\x0d\0\
 \0\0\0\0\0\0\x01\0\0\x0d\x06\0\0\0\x1c\0\0\0\x01\0\0\0\x20\0\0\0\0\0\0\x01\x04\
-\0\0\0\x20\0\0\x01\x24\0\0\0\x01\0\0\x0c\x05\0\0\0\xa3\0\0\0\x03\0\0\x04\x18\0\
-\0\0\xb1\0\0\0\x09\0\0\0\0\0\0\0\xb5\0\0\0\x0b\0\0\0\x40\0\0\0\xc0\0\0\0\x0b\0\
-\0\0\x80\0\0\0\0\0\0\0\0\0\0\x02\x0a\0\0\0\xc8\0\0\0\0\0\0\x07\0\0\0\0\xd1\0\0\
-\0\0\0\0\x08\x0c\0\0\0\xd7\0\0\0\0\0\0\x01\x08\0\0\0\x40\0\0\0\x98\x01\0\0\x03\
-\0\0\x04\x18\0\0\0\xa0\x01\0\0\x0e\0\0\0\0\0\0\0\xa3\x01\0\0\x11\0\0\0\x20\0\0\
-\0\xa8\x01\0\0\x0e\0\0\0\xa0\0\0\0\xb4\x01\0\0\0\0\0\x08\x0f\0\0\0\xba\x01\0\0\
-\0\0\0\x01\x04\0\0\0\x20\0\0\0\xc7\x01\0\0\0\0\0\x01\x01\0\0\0\x08\0\0\x01\0\0\
-\0\0\0\0\0\x03\0\0\0\0\x10\0\0\0\x12\0\0\0\x10\0\0\0\xcc\x01\0\0\0\0\0\x01\x04\
-\0\0\0\x20\0\0\0\0\0\0\0\0\0\0\x02\x14\0\0\0\x30\x02\0\0\x02\0\0\x04\x10\0\0\0\
-\x13\0\0\0\x03\0\0\0\0\0\0\0\x43\x02\0\0\x15\0\0\0\x40\0\0\0\0\0\0\0\0\0\0\x02\
-\x18\0\0\0\0\0\0\0\x01\0\0\x0d\x06\0\0\0\x1c\0\0\0\x13\0\0\0\x48\x02\0\0\x01\0\
-\0\x0c\x16\0\0\0\x94\x02\0\0\x01\0\0\x04\x08\0\0\0\x9d\x02\0\0\x19\0\0\0\0\0\0\
-\0\0\0\0\0\0\0\0\x02\x1a\0\0\0\xee\x02\0\0\x06\0\0\x04\x38\0\0\0\xa0\x01\0\0\
-\x0e\0\0\0\0\0\0\0\xa3\x01\0\0\x11\0\0\0\x20\0\0\0\xfb\x02\0\0\x1b\0\0\0\xc0\0\
-\0\0\x0c\x03\0\0\x15\0\0\0\0\x01\0\0\x18\x03\0\0\x1d\0\0\0\x40\x01\0\0\x22\x03\
+\0\0\0\x20\0\0\x01\x24\0\0\0\x01\0\0\x0c\x05\0\0\0\xaf\0\0\0\x03\0\0\x04\x18\0\
+\0\0\xbd\0\0\0\x09\0\0\0\0\0\0\0\xc1\0\0\0\x0b\0\0\0\x40\0\0\0\xcc\0\0\0\x0b\0\
+\0\0\x80\0\0\0\0\0\0\0\0\0\0\x02\x0a\0\0\0\xd4\0\0\0\0\0\0\x07\0\0\0\0\xdd\0\0\
+\0\0\0\0\x08\x0c\0\0\0\xe3\0\0\0\0\0\0\x01\x08\0\0\0\x40\0\0\0\xa4\x01\0\0\x03\
+\0\0\x04\x18\0\0\0\xac\x01\0\0\x0e\0\0\0\0\0\0\0\xaf\x01\0\0\x11\0\0\0\x20\0\0\
+\0\xb4\x01\0\0\x0e\0\0\0\xa0\0\0\0\xc0\x01\0\0\0\0\0\x08\x0f\0\0\0\xc6\x01\0\0\
+\0\0\0\x01\x04\0\0\0\x20\0\0\0\xd3\x01\0\0\0\0\0\x01\x01\0\0\0\x08\0\0\x01\0\0\
+\0\0\0\0\0\x03\0\0\0\0\x10\0\0\0\x12\0\0\0\x10\0\0\0\xd8\x01\0\0\0\0\0\x01\x04\
+\0\0\0\x20\0\0\0\0\0\0\0\0\0\0\x02\x14\0\0\0\x3c\x02\0\0\x02\0\0\x04\x10\0\0\0\
+\x13\0\0\0\x03\0\0\0\0\0\0\0\x4f\x02\0\0\x15\0\0\0\x40\0\0\0\0\0\0\0\0\0\0\x02\
+\x18\0\0\0\0\0\0\0\x01\0\0\x0d\x06\0\0\0\x1c\0\0\0\x13\0\0\0\x54\x02\0\0\x01\0\
+\0\x0c\x16\0\0\0\xa0\x02\0\0\x01\0\0\x04\x08\0\0\0\xa9\x02\0\0\x19\0\0\0\0\0\0\
+\0\0\0\0\0\0\0\0\x02\x1a\0\0\0\xfa\x02\0\0\x06\0\0\x04\x38\0\0\0\xac\x01\0\0\
+\x0e\0\0\0\0\0\0\0\xaf\x01\0\0\x11\0\0\0\x20\0\0\0\x07\x03\0\0\x1b\0\0\0\xc0\0\
+\0\0\x18\x03\0\0\x15\0\0\0\0\x01\0\0\x21\x03\0\0\x1d\0\0\0\x40\x01\0\0\x2b\x03\
 \0\0\x1e\0\0\0\x80\x01\0\0\0\0\0\0\0\0\0\x02\x1c\0\0\0\0\0\0\0\0\0\0\x0a\x10\0\
-\0\0\0\0\0\0\0\0\0\x02\x1f\0\0\0\0\0\0\0\0\0\0\x02\x20\0\0\0\x6c\x03\0\0\x02\0\
-\0\x04\x08\0\0\0\x7a\x03\0\0\x0e\0\0\0\0\0\0\0\x83\x03\0\0\x0e\0\0\0\x20\0\0\0\
-\x22\x03\0\0\x03\0\0\x04\x18\0\0\0\x8d\x03\0\0\x1b\0\0\0\0\0\0\0\x95\x03\0\0\
-\x21\0\0\0\x40\0\0\0\x9b\x03\0\0\x23\0\0\0\x80\0\0\0\0\0\0\0\0\0\0\x02\x22\0\0\
-\0\0\0\0\0\0\0\0\x02\x24\0\0\0\x9f\x03\0\0\x01\0\0\x04\x04\0\0\0\xaa\x03\0\0\
-\x0e\0\0\0\0\0\0\0\x13\x04\0\0\x01\0\0\x04\x04\0\0\0\x1c\x04\0\0\x0e\0\0\0\0\0\
-\0\0\0\0\0\0\0\0\0\x03\0\0\0\0\x1c\0\0\0\x12\0\0\0\x23\0\0\0\x92\x04\0\0\0\0\0\
+\0\0\0\0\0\0\0\0\0\x02\x1f\0\0\0\0\0\0\0\0\0\0\x02\x20\0\0\0\x75\x03\0\0\x02\0\
+\0\x04\x08\0\0\0\x83\x03\0\0\x0e\0\0\0\0\0\0\0\x8c\x03\0\0\x0e\0\0\0\x20\0\0\0\
+\x2b\x03\0\0\x03\0\0\x04\x18\0\0\0\x96\x03\0\0\x1b\0\0\0\0\0\0\0\x9e\x03\0\0\
+\x21\0\0\0\x40\0\0\0\xa4\x03\0\0\x23\0\0\0\x80\0\0\0\0\0\0\0\0\0\0\x02\x22\0\0\
+\0\0\0\0\0\0\0\0\x02\x24\0\0\0\xa8\x03\0\0\x01\0\0\x04\x04\0\0\0\xb3\x03\0\0\
+\x0e\0\0\0\0\0\0\0\x1c\x04\0\0\x01\0\0\x04\x04\0\0\0\x25\x04\0\0\x0e\0\0\0\0\0\
+\0\0\0\0\0\0\0\0\0\x03\0\0\0\0\x1c\0\0\0\x12\0\0\0\x23\0\0\0\x9b\x04\0\0\0\0\0\
 \x0e\x25\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\0\0\0\0\x1c\0\0\0\x12\0\0\0\x0e\0\0\0\
-\xa6\x04\0\0\0\0\0\x0e\x27\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\0\0\0\0\x1c\0\0\0\
-\x12\0\0\0\x20\0\0\0\xbc\x04\0\0\0\0\0\x0e\x29\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\
-\0\0\0\0\x1c\0\0\0\x12\0\0\0\x11\0\0\0\xd1\x04\0\0\0\0\0\x0e\x2b\0\0\0\0\0\0\0\
-\0\0\0\0\0\0\0\x03\0\0\0\0\x10\0\0\0\x12\0\0\0\x04\0\0\0\xe8\x04\0\0\0\0\0\x0e\
-\x2d\0\0\0\x01\0\0\0\xf0\x04\0\0\x04\0\0\x0f\0\0\0\0\x26\0\0\0\0\0\0\0\x23\0\0\
+\xaf\x04\0\0\0\0\0\x0e\x27\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\0\0\0\0\x1c\0\0\0\
+\x12\0\0\0\x20\0\0\0\xc5\x04\0\0\0\0\0\x0e\x29\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\
+\0\0\0\0\x1c\0\0\0\x12\0\0\0\x11\0\0\0\xda\x04\0\0\0\0\0\x0e\x2b\0\0\0\0\0\0\0\
+\0\0\0\0\0\0\0\x03\0\0\0\0\x10\0\0\0\x12\0\0\0\x04\0\0\0\xf1\x04\0\0\0\0\0\x0e\
+\x2d\0\0\0\x01\0\0\0\xf9\x04\0\0\x04\0\0\x0f\0\0\0\0\x26\0\0\0\0\0\0\0\x23\0\0\
 \0\x28\0\0\0\x23\0\0\0\x0e\0\0\0\x2a\0\0\0\x31\0\0\0\x20\0\0\0\x2c\0\0\0\x51\0\
-\0\0\x11\0\0\0\xf8\x04\0\0\x01\0\0\x0f\0\0\0\0\x2e\0\0\0\0\0\0\0\x04\0\0\0\0\
+\0\0\x11\0\0\0\x01\x05\0\0\x01\0\0\x0f\0\0\0\0\x2e\0\0\0\0\0\0\0\x04\0\0\0\0\
 \x62\x70\x66\x5f\x69\x74\x65\x72\x5f\x5f\x62\x70\x66\x5f\x6d\x61\x70\0\x6d\x65\
 \x74\x61\0\x6d\x61\x70\0\x63\x74\x78\0\x69\x6e\x74\0\x64\x75\x6d\x70\x5f\x62\
 \x70\x66\x5f\x6d\x61\x70\0\x69\x74\x65\x72\x2f\x62\x70\x66\x5f\x6d\x61\x70\0\
-\x30\x3a\x30\0\x2f\x77\x2f\x6e\x65\x74\x2d\x6e\x65\x78\x74\x2f\x6b\x65\x72\x6e\
-\x65\x6c\x2f\x62\x70\x66\x2f\x70\x72\x65\x6c\x6f\x61\x64\x2f\x69\x74\x65\x72\
-\x61\x74\x6f\x72\x73\x2f\x69\x74\x65\x72\x61\x74\x6f\x72\x73\x2e\x62\x70\x66\
-\x2e\x63\0\x09\x73\x74\x72\x75\x63\x74\x20\x73\x65\x71\x5f\x66\x69\x6c\x65\x20\
-\x2a\x73\x65\x71\x20\x3d\x20\x63\x74\x78\x2d\x3e\x6d\x65\x74\x61\x2d\x3e\x73\
-\x65\x71\x3b\0\x62\x70\x66\x5f\x69\x74\x65\x72\x5f\x6d\x65\x74\x61\0\x73\x65\
-\x71\0\x73\x65\x73\x73\x69\x6f\x6e\x5f\x69\x64\0\x73\x65\x71\x5f\x6e\x75\x6d\0\
-\x73\x65\x71\x5f\x66\x69\x6c\x65\0\x5f\x5f\x75\x36\x34\0\x6c\x6f\x6e\x67\x20\
-\x6c\x6f\x6e\x67\x20\x75\x6e\x73\x69\x67\x6e\x65\x64\x20\x69\x6e\x74\0\x30\x3a\
-\x31\0\x09\x73\x74\x72\x75\x63\x74\x20\x62\x70\x66\x5f\x6d\x61\x70\x20\x2a\x6d\
-\x61\x70\x20\x3d\x20\x63\x74\x78\x2d\x3e\x6d\x61\x70\x3b\0\x09\x69\x66\x20\x28\
-\x21\x6d\x61\x70\x29\0\x30\x3a\x32\0\x09\x5f\x5f\x75\x36\x34\x20\x73\x65\x71\
-\x5f\x6e\x75\x6d\x20\x3d\x20\x63\x74\x78\x2d\x3e\x6d\x65\x74\x61\x2d\x3e\x73\
-\x65\x71\x5f\x6e\x75\x6d\x3b\0\x09\x69\x66\x20\x28\x73\x65\x71\x5f\x6e\x75\x6d\
-\x20\x3d\x3d\x20\x30\x29\0\x09\x09\x42\x50\x46\x5f\x53\x45\x51\x5f\x50\x52\x49\
-\x4e\x54\x46\x28\x73\x65\x71\x2c\x20\x22\x20\x20\x69\x64\x20\x6e\x61\x6d\x65\
-\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x6d\x61\x78\x5f\x65\x6e\
-\x74\x72\x69\x65\x73\x5c\x6e\x22\x29\x3b\0\x62\x70\x66\x5f\x6d\x61\x70\0\x69\
-\x64\0\x6e\x61\x6d\x65\0\x6d\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\x73\0\x5f\x5f\
-\x75\x33\x32\0\x75\x6e\x73\x69\x67\x6e\x65\x64\x20\x69\x6e\x74\0\x63\x68\x61\
-\x72\0\x5f\x5f\x41\x52\x52\x41\x59\x5f\x53\x49\x5a\x45\x5f\x54\x59\x50\x45\x5f\
-\x5f\0\x09\x42\x50\x46\x5f\x53\x45\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\x65\
-\x71\x2c\x20\x22\x25\x34\x75\x20\x25\x2d\x31\x36\x73\x25\x36\x64\x5c\x6e\x22\
-\x2c\x20\x6d\x61\x70\x2d\x3e\x69\x64\x2c\x20\x6d\x61\x70\x2d\x3e\x6e\x61\x6d\
-\x65\x2c\x20\x6d\x61\x70\x2d\x3e\x6d\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\x73\
-\x29\x3b\0\x7d\0\x62\x70\x66\x5f\x69\x74\x65\x72\x5f\x5f\x62\x70\x66\x5f\x70\
-\x72\x6f\x67\0\x70\x72\x6f\x67\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\
-\x6f\x67\0\x69\x74\x65\x72\x2f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x09\x73\x74\
-\x72\x75\x63\x74\x20\x62\x70\x66\x5f\x70\x72\x6f\x67\x20\x2a\x70\x72\x6f\x67\
-\x20\x3d\x20\x63\x74\x78\x2d\x3e\x70\x72\x6f\x67\x3b\0\x09\x69\x66\x20\x28\x21\
-\x70\x72\x6f\x67\x29\0\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x61\x75\x78\0\x09\x61\
-\x75\x78\x20\x3d\x20\x70\x72\x6f\x67\x2d\x3e\x61\x75\x78\x3b\0\x09\x09\x42\x50\
-\x46\x5f\x53\x45\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\x65\x71\x2c\x20\x22\
-\x20\x20\x69\x64\x20\x6e\x61\x6d\x65\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\
-\x20\x20\x20\x61\x74\x74\x61\x63\x68\x65\x64\x5c\x6e\x22\x29\x3b\0\x62\x70\x66\
-\x5f\x70\x72\x6f\x67\x5f\x61\x75\x78\0\x61\x74\x74\x61\x63\x68\x5f\x66\x75\x6e\
-\x63\x5f\x6e\x61\x6d\x65\0\x6c\x69\x6e\x6b\x65\x64\x5f\x70\x72\x6f\x67\0\x66\
-\x75\x6e\x63\x5f\x69\x6e\x66\x6f\0\x62\x74\x66\0\x09\x42\x50\x46\x5f\x53\x45\
-\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\x65\x71\x2c\x20\x22\x25\x34\x75\x20\
-\x25\x2d\x31\x36\x73\x20\x25\x73\x20\x25\x73\x5c\x6e\x22\x2c\x20\x61\x75\x78\
-\x2d\x3e\x69\x64\x2c\0\x30\x3a\x34\0\x30\x3a\x35\0\x09\x69\x66\x20\x28\x21\x62\
-\x74\x66\x29\0\x62\x70\x66\x5f\x66\x75\x6e\x63\x5f\x69\x6e\x66\x6f\0\x69\x6e\
-\x73\x6e\x5f\x6f\x66\x66\0\x74\x79\x70\x65\x5f\x69\x64\0\x30\0\x73\x74\x72\x69\
-\x6e\x67\x73\0\x74\x79\x70\x65\x73\0\x68\x64\x72\0\x62\x74\x66\x5f\x68\x65\x61\
-\x64\x65\x72\0\x73\x74\x72\x5f\x6c\x65\x6e\0\x09\x74\x79\x70\x65\x73\x20\x3d\
-\x20\x62\x74\x66\x2d\x3e\x74\x79\x70\x65\x73\x3b\0\x09\x62\x70\x66\x5f\x70\x72\
-\x6f\x62\x65\x5f\x72\x65\x61\x64\x5f\x6b\x65\x72\x6e\x65\x6c\x28\x26\x74\x2c\
-\x20\x73\x69\x7a\x65\x6f\x66\x28\x74\x29\x2c\x20\x74\x79\x70\x65\x73\x20\x2b\
-\x20\x62\x74\x66\x5f\x69\x64\x29\x3b\0\x09\x73\x74\x72\x20\x3d\x20\x62\x74\x66\
-\x2d\x3e\x73\x74\x72\x69\x6e\x67\x73\x3b\0\x62\x74\x66\x5f\x74\x79\x70\x65\0\
-\x6e\x61\x6d\x65\x5f\x6f\x66\x66\0\x09\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x20\x3d\
-\x20\x42\x50\x46\x5f\x43\x4f\x52\x45\x5f\x52\x45\x41\x44\x28\x74\x2c\x20\x6e\
-\x61\x6d\x65\x5f\x6f\x66\x66\x29\x3b\0\x30\x3a\x32\x3a\x30\0\x09\x69\x66\x20\
-\x28\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x20\x3e\x3d\x20\x62\x74\x66\x2d\x3e\x68\
-\x64\x72\x2e\x73\x74\x72\x5f\x6c\x65\x6e\x29\0\x09\x72\x65\x74\x75\x72\x6e\x20\
-\x73\x74\x72\x20\x2b\x20\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x3b\0\x30\x3a\x33\0\
-\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\x61\x70\x2e\x5f\x5f\x5f\x66\x6d\x74\0\
-\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\x61\x70\x2e\x5f\x5f\x5f\x66\x6d\x74\
-\x2e\x31\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\x2e\x5f\x5f\x5f\
-\x66\x6d\x74\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\x2e\x5f\x5f\
-\x5f\x66\x6d\x74\x2e\x32\0\x4c\x49\x43\x45\x4e\x53\x45\0\x2e\x72\x6f\x64\x61\
-\x74\x61\0\x6c\x69\x63\x65\x6e\x73\x65\0\x9f\xeb\x01\0\x20\0\0\0\0\0\0\0\x24\0\
-\0\0\x24\0\0\0\x44\x02\0\0\x68\x02\0\0\xa4\x01\0\0\x08\0\0\0\x31\0\0\0\x01\0\0\
-\0\0\0\0\0\x07\0\0\0\x56\x02\0\0\x01\0\0\0\0\0\0\0\x17\0\0\0\x10\0\0\0\x31\0\0\
-\0\x09\0\0\0\0\0\0\0\x42\0\0\0\x7b\0\0\0\x1e\x40\x01\0\x08\0\0\0\x42\0\0\0\x7b\
-\0\0\0\x24\x40\x01\0\x10\0\0\0\x42\0\0\0\xf2\0\0\0\x1d\x48\x01\0\x18\0\0\0\x42\
-\0\0\0\x13\x01\0\0\x06\x50\x01\0\x20\0\0\0\x42\0\0\0\x22\x01\0\0\x1d\x44\x01\0\
-\x28\0\0\0\x42\0\0\0\x47\x01\0\0\x06\x5c\x01\0\x38\0\0\0\x42\0\0\0\x5a\x01\0\0\
-\x03\x60\x01\0\x70\0\0\0\x42\0\0\0\xe0\x01\0\0\x02\x68\x01\0\xf0\0\0\0\x42\0\0\
-\0\x2e\x02\0\0\x01\x70\x01\0\x56\x02\0\0\x1a\0\0\0\0\0\0\0\x42\0\0\0\x7b\0\0\0\
-\x1e\x84\x01\0\x08\0\0\0\x42\0\0\0\x7b\0\0\0\x24\x84\x01\0\x10\0\0\0\x42\0\0\0\
-\x64\x02\0\0\x1f\x8c\x01\0\x18\0\0\0\x42\0\0\0\x88\x02\0\0\x06\x98\x01\0\x20\0\
-\0\0\x42\0\0\0\xa1\x02\0\0\x0e\xa4\x01\0\x28\0\0\0\x42\0\0\0\x22\x01\0\0\x1d\
-\x88\x01\0\x30\0\0\0\x42\0\0\0\x47\x01\0\0\x06\xa8\x01\0\x40\0\0\0\x42\0\0\0\
-\xb3\x02\0\0\x03\xac\x01\0\x80\0\0\0\x42\0\0\0\x26\x03\0\0\x02\xb4\x01\0\xb8\0\
-\0\0\x42\0\0\0\x61\x03\0\0\x06\x08\x01\0\xd0\0\0\0\x42\0\0\0\0\0\0\0\0\0\0\0\
-\xd8\0\0\0\x42\0\0\0\xb2\x03\0\0\x0f\x14\x01\0\xe0\0\0\0\x42\0\0\0\xc7\x03\0\0\
-\x2d\x18\x01\0\xf0\0\0\0\x42\0\0\0\xfe\x03\0\0\x0d\x10\x01\0\0\x01\0\0\x42\0\0\
-\0\0\0\0\0\0\0\0\0\x08\x01\0\0\x42\0\0\0\xc7\x03\0\0\x02\x18\x01\0\x20\x01\0\0\
-\x42\0\0\0\x25\x04\0\0\x0d\x1c\x01\0\x38\x01\0\0\x42\0\0\0\0\0\0\0\0\0\0\0\x40\
-\x01\0\0\x42\0\0\0\x25\x04\0\0\x0d\x1c\x01\0\x58\x01\0\0\x42\0\0\0\x25\x04\0\0\
-\x0d\x1c\x01\0\x60\x01\0\0\x42\0\0\0\x53\x04\0\0\x1b\x20\x01\0\x68\x01\0\0\x42\
-\0\0\0\x53\x04\0\0\x06\x20\x01\0\x70\x01\0\0\x42\0\0\0\x76\x04\0\0\x0d\x28\x01\
-\0\x78\x01\0\0\x42\0\0\0\0\0\0\0\0\0\0\0\x80\x01\0\0\x42\0\0\0\x26\x03\0\0\x02\
-\xb4\x01\0\xf8\x01\0\0\x42\0\0\0\x2e\x02\0\0\x01\xc4\x01\0\x10\0\0\0\x31\0\0\0\
-\x07\0\0\0\0\0\0\0\x02\0\0\0\x3e\0\0\0\0\0\0\0\x08\0\0\0\x08\0\0\0\x3e\0\0\0\0\
-\0\0\0\x10\0\0\0\x02\0\0\0\xee\0\0\0\0\0\0\0\x20\0\0\0\x08\0\0\0\x1e\x01\0\0\0\
-\0\0\0\x70\0\0\0\x0d\0\0\0\x3e\0\0\0\0\0\0\0\x80\0\0\0\x0d\0\0\0\xee\0\0\0\0\0\
-\0\0\xa0\0\0\0\x0d\0\0\0\x1e\x01\0\0\0\0\0\0\x56\x02\0\0\x12\0\0\0\0\0\0\0\x14\
-\0\0\0\x3e\0\0\0\0\0\0\0\x08\0\0\0\x08\0\0\0\x3e\0\0\0\0\0\0\0\x10\0\0\0\x14\0\
-\0\0\xee\0\0\0\0\0\0\0\x20\0\0\0\x18\0\0\0\x3e\0\0\0\0\0\0\0\x28\0\0\0\x08\0\0\
-\0\x1e\x01\0\0\0\0\0\0\x80\0\0\0\x1a\0\0\0\x3e\0\0\0\0\0\0\0\x90\0\0\0\x1a\0\0\
-\0\xee\0\0\0\0\0\0\0\xa8\0\0\0\x1a\0\0\0\x59\x03\0\0\0\0\0\0\xb0\0\0\0\x1a\0\0\
-\0\x5d\x03\0\0\0\0\0\0\xc0\0\0\0\x1f\0\0\0\x8b\x03\0\0\0\0\0\0\xd8\0\0\0\x20\0\
-\0\0\xee\0\0\0\0\0\0\0\xf0\0\0\0\x20\0\0\0\x3e\0\0\0\0\0\0\0\x18\x01\0\0\x24\0\
-\0\0\x3e\0\0\0\0\0\0\0\x50\x01\0\0\x1a\0\0\0\xee\0\0\0\0\0\0\0\x60\x01\0\0\x20\
-\0\0\0\x4d\x04\0\0\0\0\0\0\x88\x01\0\0\x1a\0\0\0\x1e\x01\0\0\0\0\0\0\x98\x01\0\
-\0\x1a\0\0\0\x8e\x04\0\0\0\0\0\0\xa0\x01\0\0\x18\0\0\0\x3e\0\0\0\0\0\0\0\0\0\0\
-\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xd6\0\0\0\0\0\x02\0\x70\0\0\0\0\
-\0\0\0\0\0\0\0\0\0\0\0\xc8\0\0\0\0\0\x02\0\xf0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
-\xcf\0\0\0\0\0\x03\0\x78\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xc1\0\0\0\0\0\x03\0\x80\
-\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xba\0\0\0\0\0\x03\0\xf8\x01\0\0\0\0\0\0\0\0\0\
-\0\0\0\0\0\x14\0\0\0\x01\0\x04\0\0\0\0\0\0\0\0\0\x23\0\0\0\0\0\0\0\xf4\0\0\0\
-\x01\0\x04\0\x23\0\0\0\0\0\0\0\x0e\0\0\0\0\0\0\0\x28\0\0\0\x01\0\x04\0\x31\0\0\
-\0\0\0\0\0\x20\0\0\0\0\0\0\0\xdd\0\0\0\x01\0\x04\0\x51\0\0\0\0\0\0\0\x11\0\0\0\
-\0\0\0\0\0\0\0\0\x03\0\x02\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\0\x03\
-\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\0\x04\0\0\0\0\0\0\0\0\0\0\0\0\0\
-\0\0\0\0\xb2\0\0\0\x11\0\x05\0\0\0\0\0\0\0\0\0\x04\0\0\0\0\0\0\0\x3d\0\0\0\x12\
-\0\x02\0\0\0\0\0\0\0\0\0\0\x01\0\0\0\0\0\0\x5b\0\0\0\x12\0\x03\0\0\0\0\0\0\0\0\
-\0\x08\x02\0\0\0\0\0\0\x48\0\0\0\0\0\0\0\x01\0\0\0\x0c\0\0\0\xc8\0\0\0\0\0\0\0\
-\x01\0\0\0\x0c\0\0\0\x50\0\0\0\0\0\0\0\x01\0\0\0\x0c\0\0\0\xd0\x01\0\0\0\0\0\0\
-\x01\0\0\0\x0c\0\0\0\xf0\x03\0\0\0\0\0\0\x0a\0\0\0\x0c\0\0\0\xfc\x03\0\0\0\0\0\
-\0\x0a\0\0\0\x0c\0\0\0\x08\x04\0\0\0\0\0\0\x0a\0\0\0\x0c\0\0\0\x14\x04\0\0\0\0\
-\0\0\x0a\0\0\0\x0c\0\0\0\x2c\x04\0\0\0\0\0\0\0\0\0\0\x0d\0\0\0\x2c\0\0\0\0\0\0\
-\0\0\0\0\0\x0a\0\0\0\x3c\0\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x50\0\0\0\0\0\0\0\0\0\
-\0\0\x0a\0\0\0\x60\0\0\0\0\0\0\0\0\0\0\0\x0a\0\0\0\x70\0\0\0\0\0\0\0\0\0\0\0\
-\x0a\0\0\0\x80\0\0\0\0\0\0\0\0\0\0\0\x0a\0\0\0\x90\0\0\0\0\0\0\0\0\0\0\0\x0a\0\
-\0\0\xa0\0\0\0\0\0\0\0\0\0\0\0\x0a\0\0\0\xb0\0\0\0\0\0\0\0\0\0\0\0\x0a\0\0\0\
-\xc0\0\0\0\0\0\0\0\0\0\0\0\x0a\0\0\0\xd0\0\0\0\0\0\0\0\0\0\0\0\x0a\0\0\0\xe8\0\
-\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\xf8\0\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x08\x01\0\0\
-\0\0\0\0\0\0\0\0\x0b\0\0\0\x18\x01\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x28\x01\0\0\0\
-\0\0\0\0\0\0\0\x0b\0\0\0\x38\x01\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x48\x01\0\0\0\0\
-\0\0\0\0\0\0\x0b\0\0\0\x58\x01\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x68\x01\0\0\0\0\0\
-\0\0\0\0\0\x0b\0\0\0\x78\x01\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x88\x01\0\0\0\0\0\0\
-\0\0\0\0\x0b\0\0\0\x98\x01\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\xa8\x01\0\0\0\0\0\0\0\
-\0\0\0\x0b\0\0\0\xb8\x01\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\xc8\x01\0\0\0\0\0\0\0\0\
-\0\0\x0b\0\0\0\xd8\x01\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\xe8\x01\0\0\0\0\0\0\0\0\0\
-\0\x0b\0\0\0\xf8\x01\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x08\x02\0\0\0\0\0\0\0\0\0\0\
-\x0b\0\0\0\x18\x02\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x28\x02\0\0\0\0\0\0\0\0\0\0\
-\x0b\0\0\0\x38\x02\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x48\x02\0\0\0\0\0\0\0\0\0\0\
-\x0b\0\0\0\x58\x02\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x68\x02\0\0\0\0\0\0\0\0\0\0\
-\x0b\0\0\0\x78\x02\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x94\x02\0\0\0\0\0\0\0\0\0\0\
-\x0a\0\0\0\xa4\x02\0\0\0\0\0\0\0\0\0\0\x0a\0\0\0\xb4\x02\0\0\0\0\0\0\0\0\0\0\
-\x0a\0\0\0\xc4\x02\0\0\0\0\0\0\0\0\0\0\x0a\0\0\0\xd4\x02\0\0\0\0\0\0\0\0\0\0\
-\x0a\0\0\0\xe4\x02\0\0\0\0\0\0\0\0\0\0\x0a\0\0\0\xf4\x02\0\0\0\0\0\0\0\0\0\0\
-\x0a\0\0\0\x0c\x03\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x1c\x03\0\0\0\0\0\0\0\0\0\0\
-\x0b\0\0\0\x2c\x03\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x3c\x03\0\0\0\0\0\0\0\0\0\0\
-\x0b\0\0\0\x4c\x03\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x5c\x03\0\0\0\0\0\0\0\0\0\0\
-\x0b\0\0\0\x6c\x03\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x7c\x03\0\0\0\0\0\0\0\0\0\0\
-\x0b\0\0\0\x8c\x03\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x9c\x03\0\0\0\0\0\0\0\0\0\0\
-\x0b\0\0\0\xac\x03\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\xbc\x03\0\0\0\0\0\0\0\0\0\0\
-\x0b\0\0\0\xcc\x03\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\xdc\x03\0\0\0\0\0\0\0\0\0\0\
-\x0b\0\0\0\xec\x03\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\xfc\x03\0\0\0\0\0\0\0\0\0\0\
-\x0b\0\0\0\x0c\x04\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x1c\x04\0\0\0\0\0\0\0\0\0\0\
-\x0b\0\0\0\x4e\x4f\x41\x42\x43\x44\x4d\0\x2e\x74\x65\x78\x74\0\x2e\x72\x65\x6c\
-\x2e\x42\x54\x46\x2e\x65\x78\x74\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\x61\
-\x70\x2e\x5f\x5f\x5f\x66\x6d\x74\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\
-\x6f\x67\x2e\x5f\x5f\x5f\x66\x6d\x74\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\
-\x61\x70\0\x2e\x72\x65\x6c\x69\x74\x65\x72\x2f\x62\x70\x66\x5f\x6d\x61\x70\0\
-\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x2e\x72\x65\x6c\x69\x74\
-\x65\x72\x2f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x2e\x6c\x6c\x76\x6d\x5f\x61\x64\
-\x64\x72\x73\x69\x67\0\x6c\x69\x63\x65\x6e\x73\x65\0\x2e\x73\x74\x72\x74\x61\
-\x62\0\x2e\x73\x79\x6d\x74\x61\x62\0\x2e\x72\x6f\x64\x61\x74\x61\0\x2e\x72\x65\
-\x6c\x2e\x42\x54\x46\0\x4c\x49\x43\x45\x4e\x53\x45\0\x4c\x42\x42\x31\x5f\x37\0\
-\x4c\x42\x42\x31\x5f\x36\0\x4c\x42\x42\x30\x5f\x34\0\x4c\x42\x42\x31\x5f\x33\0\
-\x4c\x42\x42\x30\x5f\x33\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\
-\x2e\x5f\x5f\x5f\x66\x6d\x74\x2e\x32\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\
-\x61\x70\x2e\x5f\x5f\x5f\x66\x6d\x74\x2e\x31\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
+\x30\x3a\x30\0\x2f\x68\x6f\x6d\x65\x2f\x61\x6c\x72\x75\x61\x2f\x62\x75\x69\x6c\
+\x64\x2f\x6c\x69\x6e\x75\x78\x2f\x6b\x65\x72\x6e\x65\x6c\x2f\x62\x70\x66\x2f\
+\x70\x72\x65\x6c\x6f\x61\x64\x2f\x69\x74\x65\x72\x61\x74\x6f\x72\x73\x2f\x69\
+\x74\x65\x72\x61\x74\x6f\x72\x73\x2e\x62\x70\x66\x2e\x63\0\x09\x73\x74\x72\x75\
+\x63\x74\x20\x73\x65\x71\x5f\x66\x69\x6c\x65\x20\x2a\x73\x65\x71\x20\x3d\x20\
+\x63\x74\x78\x2d\x3e\x6d\x65\x74\x61\x2d\x3e\x73\x65\x71\x3b\0\x62\x70\x66\x5f\
+\x69\x74\x65\x72\x5f\x6d\x65\x74\x61\0\x73\x65\x71\0\x73\x65\x73\x73\x69\x6f\
+\x6e\x5f\x69\x64\0\x73\x65\x71\x5f\x6e\x75\x6d\0\x73\x65\x71\x5f\x66\x69\x6c\
+\x65\0\x5f\x5f\x75\x36\x34\0\x6c\x6f\x6e\x67\x20\x6c\x6f\x6e\x67\x20\x75\x6e\
+\x73\x69\x67\x6e\x65\x64\x20\x69\x6e\x74\0\x30\x3a\x31\0\x09\x73\x74\x72\x75\
+\x63\x74\x20\x62\x70\x66\x5f\x6d\x61\x70\x20\x2a\x6d\x61\x70\x20\x3d\x20\x63\
+\x74\x78\x2d\x3e\x6d\x61\x70\x3b\0\x09\x69\x66\x20\x28\x21\x6d\x61\x70\x29\0\
+\x30\x3a\x32\0\x09\x5f\x5f\x75\x36\x34\x20\x73\x65\x71\x5f\x6e\x75\x6d\x20\x3d\
+\x20\x63\x74\x78\x2d\x3e\x6d\x65\x74\x61\x2d\x3e\x73\x65\x71\x5f\x6e\x75\x6d\
+\x3b\0\x09\x69\x66\x20\x28\x73\x65\x71\x5f\x6e\x75\x6d\x20\x3d\x3d\x20\x30\x29\
+\0\x09\x09\x42\x50\x46\x5f\x53\x45\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\x65\
+\x71\x2c\x20\x22\x20\x20\x69\x64\x20\x6e\x61\x6d\x65\x20\x20\x20\x20\x20\x20\
+\x20\x20\x20\x20\x20\x20\x20\x6d\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\x73\x5c\
+\x6e\x22\x29\x3b\0\x62\x70\x66\x5f\x6d\x61\x70\0\x69\x64\0\x6e\x61\x6d\x65\0\
+\x6d\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\x73\0\x5f\x5f\x75\x33\x32\0\x75\x6e\
+\x73\x69\x67\x6e\x65\x64\x20\x69\x6e\x74\0\x63\x68\x61\x72\0\x5f\x5f\x41\x52\
+\x52\x41\x59\x5f\x53\x49\x5a\x45\x5f\x54\x59\x50\x45\x5f\x5f\0\x09\x42\x50\x46\
+\x5f\x53\x45\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\x65\x71\x2c\x20\x22\x25\
+\x34\x75\x20\x25\x2d\x31\x36\x73\x25\x36\x64\x5c\x6e\x22\x2c\x20\x6d\x61\x70\
+\x2d\x3e\x69\x64\x2c\x20\x6d\x61\x70\x2d\x3e\x6e\x61\x6d\x65\x2c\x20\x6d\x61\
+\x70\x2d\x3e\x6d\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\x73\x29\x3b\0\x7d\0\x62\
+\x70\x66\x5f\x69\x74\x65\x72\x5f\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x70\x72\
+\x6f\x67\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x69\x74\x65\
+\x72\x2f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x09\x73\x74\x72\x75\x63\x74\x20\x62\
+\x70\x66\x5f\x70\x72\x6f\x67\x20\x2a\x70\x72\x6f\x67\x20\x3d\x20\x63\x74\x78\
+\x2d\x3e\x70\x72\x6f\x67\x3b\0\x09\x69\x66\x20\x28\x21\x70\x72\x6f\x67\x29\0\
+\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x61\x75\x78\0\x09\x61\x75\x78\x20\x3d\x20\
+\x70\x72\x6f\x67\x2d\x3e\x61\x75\x78\x3b\0\x09\x09\x42\x50\x46\x5f\x53\x45\x51\
+\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\x65\x71\x2c\x20\x22\x20\x20\x69\x64\x20\
+\x6e\x61\x6d\x65\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x61\x74\
+\x74\x61\x63\x68\x65\x64\x5c\x6e\x22\x29\x3b\0\x62\x70\x66\x5f\x70\x72\x6f\x67\
+\x5f\x61\x75\x78\0\x61\x74\x74\x61\x63\x68\x5f\x66\x75\x6e\x63\x5f\x6e\x61\x6d\
+\x65\0\x64\x73\x74\x5f\x70\x72\x6f\x67\0\x66\x75\x6e\x63\x5f\x69\x6e\x66\x6f\0\
+\x62\x74\x66\0\x09\x42\x50\x46\x5f\x53\x45\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\
+\x73\x65\x71\x2c\x20\x22\x25\x34\x75\x20\x25\x2d\x31\x36\x73\x20\x25\x73\x20\
+\x25\x73\x5c\x6e\x22\x2c\x20\x61\x75\x78\x2d\x3e\x69\x64\x2c\0\x30\x3a\x34\0\
+\x30\x3a\x35\0\x09\x69\x66\x20\x28\x21\x62\x74\x66\x29\0\x62\x70\x66\x5f\x66\
+\x75\x6e\x63\x5f\x69\x6e\x66\x6f\0\x69\x6e\x73\x6e\x5f\x6f\x66\x66\0\x74\x79\
+\x70\x65\x5f\x69\x64\0\x30\0\x73\x74\x72\x69\x6e\x67\x73\0\x74\x79\x70\x65\x73\
+\0\x68\x64\x72\0\x62\x74\x66\x5f\x68\x65\x61\x64\x65\x72\0\x73\x74\x72\x5f\x6c\
+\x65\x6e\0\x09\x74\x79\x70\x65\x73\x20\x3d\x20\x62\x74\x66\x2d\x3e\x74\x79\x70\
+\x65\x73\x3b\0\x09\x62\x70\x66\x5f\x70\x72\x6f\x62\x65\x5f\x72\x65\x61\x64\x5f\
+\x6b\x65\x72\x6e\x65\x6c\x28\x26\x74\x2c\x20\x73\x69\x7a\x65\x6f\x66\x28\x74\
+\x29\x2c\x20\x74\x79\x70\x65\x73\x20\x2b\x20\x62\x74\x66\x5f\x69\x64\x29\x3b\0\
+\x09\x73\x74\x72\x20\x3d\x20\x62\x74\x66\x2d\x3e\x73\x74\x72\x69\x6e\x67\x73\
+\x3b\0\x62\x74\x66\x5f\x74\x79\x70\x65\0\x6e\x61\x6d\x65\x5f\x6f\x66\x66\0\x09\
+\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x20\x3d\x20\x42\x50\x46\x5f\x43\x4f\x52\x45\
+\x5f\x52\x45\x41\x44\x28\x74\x2c\x20\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x29\x3b\0\
+\x30\x3a\x32\x3a\x30\0\x09\x69\x66\x20\x28\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x20\
+\x3e\x3d\x20\x62\x74\x66\x2d\x3e\x68\x64\x72\x2e\x73\x74\x72\x5f\x6c\x65\x6e\
+\x29\0\x09\x72\x65\x74\x75\x72\x6e\x20\x73\x74\x72\x20\x2b\x20\x6e\x61\x6d\x65\
+\x5f\x6f\x66\x66\x3b\0\x30\x3a\x33\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\
+\x61\x70\x2e\x5f\x5f\x5f\x66\x6d\x74\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\
+\x61\x70\x2e\x5f\x5f\x5f\x66\x6d\x74\x2e\x31\0\x64\x75\x6d\x70\x5f\x62\x70\x66\
+\x5f\x70\x72\x6f\x67\x2e\x5f\x5f\x5f\x66\x6d\x74\0\x64\x75\x6d\x70\x5f\x62\x70\
+\x66\x5f\x70\x72\x6f\x67\x2e\x5f\x5f\x5f\x66\x6d\x74\x2e\x32\0\x4c\x49\x43\x45\
+\x4e\x53\x45\0\x2e\x72\x6f\x64\x61\x74\x61\0\x6c\x69\x63\x65\x6e\x73\x65\0\x9f\
+\xeb\x01\0\x20\0\0\0\0\0\0\0\x24\0\0\0\x24\0\0\0\x44\x02\0\0\x68\x02\0\0\xa4\
+\x01\0\0\x08\0\0\0\x31\0\0\0\x01\0\0\0\0\0\0\0\x07\0\0\0\x62\x02\0\0\x01\0\0\0\
+\0\0\0\0\x17\0\0\0\x10\0\0\0\x31\0\0\0\x09\0\0\0\0\0\0\0\x42\0\0\0\x87\0\0\0\
+\x1e\x40\x01\0\x08\0\0\0\x42\0\0\0\x87\0\0\0\x24\x40\x01\0\x10\0\0\0\x42\0\0\0\
+\xfe\0\0\0\x1d\x48\x01\0\x18\0\0\0\x42\0\0\0\x1f\x01\0\0\x06\x50\x01\0\x20\0\0\
+\0\x42\0\0\0\x2e\x01\0\0\x1d\x44\x01\0\x28\0\0\0\x42\0\0\0\x53\x01\0\0\x06\x5c\
+\x01\0\x38\0\0\0\x42\0\0\0\x66\x01\0\0\x03\x60\x01\0\x70\0\0\0\x42\0\0\0\xec\
+\x01\0\0\x02\x68\x01\0\xf0\0\0\0\x42\0\0\0\x3a\x02\0\0\x01\x70\x01\0\x62\x02\0\
+\0\x1a\0\0\0\0\0\0\0\x42\0\0\0\x87\0\0\0\x1e\x84\x01\0\x08\0\0\0\x42\0\0\0\x87\
+\0\0\0\x24\x84\x01\0\x10\0\0\0\x42\0\0\0\x70\x02\0\0\x1f\x8c\x01\0\x18\0\0\0\
+\x42\0\0\0\x94\x02\0\0\x06\x98\x01\0\x20\0\0\0\x42\0\0\0\xad\x02\0\0\x0e\xa4\
+\x01\0\x28\0\0\0\x42\0\0\0\x2e\x01\0\0\x1d\x88\x01\0\x30\0\0\0\x42\0\0\0\x53\
+\x01\0\0\x06\xa8\x01\0\x40\0\0\0\x42\0\0\0\xbf\x02\0\0\x03\xac\x01\0\x80\0\0\0\
+\x42\0\0\0\x2f\x03\0\0\x02\xb4\x01\0\xb8\0\0\0\x42\0\0\0\x6a\x03\0\0\x06\x08\
+\x01\0\xd0\0\0\0\x42\0\0\0\0\0\0\0\0\0\0\0\xd8\0\0\0\x42\0\0\0\xbb\x03\0\0\x0f\
+\x14\x01\0\xe0\0\0\0\x42\0\0\0\xd0\x03\0\0\x2d\x18\x01\0\xf0\0\0\0\x42\0\0\0\
+\x07\x04\0\0\x0d\x10\x01\0\0\x01\0\0\x42\0\0\0\0\0\0\0\0\0\0\0\x08\x01\0\0\x42\
+\0\0\0\xd0\x03\0\0\x02\x18\x01\0\x20\x01\0\0\x42\0\0\0\x2e\x04\0\0\x0d\x1c\x01\
+\0\x38\x01\0\0\x42\0\0\0\0\0\0\0\0\0\0\0\x40\x01\0\0\x42\0\0\0\x2e\x04\0\0\x0d\
+\x1c\x01\0\x58\x01\0\0\x42\0\0\0\x2e\x04\0\0\x0d\x1c\x01\0\x60\x01\0\0\x42\0\0\
+\0\x5c\x04\0\0\x1b\x20\x01\0\x68\x01\0\0\x42\0\0\0\x5c\x04\0\0\x06\x20\x01\0\
+\x70\x01\0\0\x42\0\0\0\x7f\x04\0\0\x0d\x28\x01\0\x78\x01\0\0\x42\0\0\0\0\0\0\0\
+\0\0\0\0\x80\x01\0\0\x42\0\0\0\x2f\x03\0\0\x02\xb4\x01\0\xf8\x01\0\0\x42\0\0\0\
+\x3a\x02\0\0\x01\xc4\x01\0\x10\0\0\0\x31\0\0\0\x07\0\0\0\0\0\0\0\x02\0\0\0\x3e\
+\0\0\0\0\0\0\0\x08\0\0\0\x08\0\0\0\x3e\0\0\0\0\0\0\0\x10\0\0\0\x02\0\0\0\xfa\0\
+\0\0\0\0\0\0\x20\0\0\0\x08\0\0\0\x2a\x01\0\0\0\0\0\0\x70\0\0\0\x0d\0\0\0\x3e\0\
+\0\0\0\0\0\0\x80\0\0\0\x0d\0\0\0\xfa\0\0\0\0\0\0\0\xa0\0\0\0\x0d\0\0\0\x2a\x01\
+\0\0\0\0\0\0\x62\x02\0\0\x12\0\0\0\0\0\0\0\x14\0\0\0\x3e\0\0\0\0\0\0\0\x08\0\0\
+\0\x08\0\0\0\x3e\0\0\0\0\0\0\0\x10\0\0\0\x14\0\0\0\xfa\0\0\0\0\0\0\0\x20\0\0\0\
+\x18\0\0\0\x3e\0\0\0\0\0\0\0\x28\0\0\0\x08\0\0\0\x2a\x01\0\0\0\0\0\0\x80\0\0\0\
+\x1a\0\0\0\x3e\0\0\0\0\0\0\0\x90\0\0\0\x1a\0\0\0\xfa\0\0\0\0\0\0\0\xa8\0\0\0\
+\x1a\0\0\0\x62\x03\0\0\0\0\0\0\xb0\0\0\0\x1a\0\0\0\x66\x03\0\0\0\0\0\0\xc0\0\0\
+\0\x1f\0\0\0\x94\x03\0\0\0\0\0\0\xd8\0\0\0\x20\0\0\0\xfa\0\0\0\0\0\0\0\xf0\0\0\
+\0\x20\0\0\0\x3e\0\0\0\0\0\0\0\x18\x01\0\0\x24\0\0\0\x3e\0\0\0\0\0\0\0\x50\x01\
+\0\0\x1a\0\0\0\xfa\0\0\0\0\0\0\0\x60\x01\0\0\x20\0\0\0\x56\x04\0\0\0\0\0\0\x88\
+\x01\0\0\x1a\0\0\0\x2a\x01\0\0\0\0\0\0\x98\x01\0\0\x1a\0\0\0\x97\x04\0\0\0\0\0\
+\0\xa0\x01\0\0\x18\0\0\0\x3e\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
+\0\0\0\0\0\0\0\x91\0\0\0\x04\0\xf1\xff\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xe6\0\0\
+\0\0\0\x02\0\x70\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xd8\0\0\0\0\0\x02\0\xf0\0\0\0\0\
+\0\0\0\0\0\0\0\0\0\0\0\xdf\0\0\0\0\0\x03\0\x78\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
+\xd1\0\0\0\0\0\x03\0\x80\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xca\0\0\0\0\0\x03\0\
+\xf8\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x14\0\0\0\x01\0\x04\0\0\0\0\0\0\0\0\0\x23\
+\0\0\0\0\0\0\0\x04\x01\0\0\x01\0\x04\0\x23\0\0\0\0\0\0\0\x0e\0\0\0\0\0\0\0\x28\
+\0\0\0\x01\0\x04\0\x31\0\0\0\0\0\0\0\x20\0\0\0\0\0\0\0\xed\0\0\0\x01\0\x04\0\
+\x51\0\0\0\0\0\0\0\x11\0\0\0\0\0\0\0\0\0\0\0\x03\0\x02\0\0\0\0\0\0\0\0\0\0\0\0\
+\0\0\0\0\0\0\0\0\0\x03\0\x03\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\0\
+\x04\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xc2\0\0\0\x11\0\x05\0\0\0\0\0\0\0\0\0\
+\x04\0\0\0\0\0\0\0\x3d\0\0\0\x12\0\x02\0\0\0\0\0\0\0\0\0\0\x01\0\0\0\0\0\0\x5b\
+\0\0\0\x12\0\x03\0\0\0\0\0\0\0\0\0\x08\x02\0\0\0\0\0\0\x48\0\0\0\0\0\0\0\x01\0\
+\0\0\x0d\0\0\0\xc8\0\0\0\0\0\0\0\x01\0\0\0\x0d\0\0\0\x50\0\0\0\0\0\0\0\x01\0\0\
+\0\x0d\0\0\0\xd0\x01\0\0\0\0\0\0\x01\0\0\0\x0d\0\0\0\xf0\x03\0\0\0\0\0\0\x0a\0\
+\0\0\x0d\0\0\0\xfc\x03\0\0\0\0\0\0\x0a\0\0\0\x0d\0\0\0\x08\x04\0\0\0\0\0\0\x0a\
+\0\0\0\x0d\0\0\0\x14\x04\0\0\0\0\0\0\x0a\0\0\0\x0d\0\0\0\x2c\x04\0\0\0\0\0\0\0\
+\0\0\0\x0e\0\0\0\x2c\0\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x3c\0\0\0\0\0\0\0\0\0\0\0\
+\x0c\0\0\0\x50\0\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x60\0\0\0\0\0\0\0\0\0\0\0\x0b\0\
+\0\0\x70\0\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x80\0\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\
+\x90\0\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\xa0\0\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\xb0\0\
+\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\xc0\0\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\xd0\0\0\0\0\
+\0\0\0\0\0\0\0\x0b\0\0\0\xe8\0\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\xf8\0\0\0\0\0\0\0\
+\0\0\0\0\x0c\0\0\0\x08\x01\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x18\x01\0\0\0\0\0\0\0\
+\0\0\0\x0c\0\0\0\x28\x01\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x38\x01\0\0\0\0\0\0\0\0\
+\0\0\x0c\0\0\0\x48\x01\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x58\x01\0\0\0\0\0\0\0\0\0\
+\0\x0c\0\0\0\x68\x01\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x78\x01\0\0\0\0\0\0\0\0\0\0\
+\x0c\0\0\0\x88\x01\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x98\x01\0\0\0\0\0\0\0\0\0\0\
+\x0c\0\0\0\xa8\x01\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\xb8\x01\0\0\0\0\0\0\0\0\0\0\
+\x0c\0\0\0\xc8\x01\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\xd8\x01\0\0\0\0\0\0\0\0\0\0\
+\x0c\0\0\0\xe8\x01\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\xf8\x01\0\0\0\0\0\0\0\0\0\0\
+\x0c\0\0\0\x08\x02\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x18\x02\0\0\0\0\0\0\0\0\0\0\
+\x0c\0\0\0\x28\x02\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x38\x02\0\0\0\0\0\0\0\0\0\0\
+\x0c\0\0\0\x48\x02\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x58\x02\0\0\0\0\0\0\0\0\0\0\
+\x0c\0\0\0\x68\x02\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x78\x02\0\0\0\0\0\0\0\0\0\0\
+\x0c\0\0\0\x94\x02\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\xa4\x02\0\0\0\0\0\0\0\0\0\0\
+\x0b\0\0\0\xb4\x02\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\xc4\x02\0\0\0\0\0\0\0\0\0\0\
+\x0b\0\0\0\xd4\x02\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\xe4\x02\0\0\0\0\0\0\0\0\0\0\
+\x0b\0\0\0\xf4\x02\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x0c\x03\0\0\0\0\0\0\0\0\0\0\
+\x0c\0\0\0\x1c\x03\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x2c\x03\0\0\0\0\0\0\0\0\0\0\
+\x0c\0\0\0\x3c\x03\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x4c\x03\0\0\0\0\0\0\0\0\0\0\
+\x0c\0\0\0\x5c\x03\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x6c\x03\0\0\0\0\0\0\0\0\0\0\
+\x0c\0\0\0\x7c\x03\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x8c\x03\0\0\0\0\0\0\0\0\0\0\
+\x0c\0\0\0\x9c\x03\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\xac\x03\0\0\0\0\0\0\0\0\0\0\
+\x0c\0\0\0\xbc\x03\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\xcc\x03\0\0\0\0\0\0\0\0\0\0\
+\x0c\0\0\0\xdc\x03\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\xec\x03\0\0\0\0\0\0\0\0\0\0\
+\x0c\0\0\0\xfc\x03\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x0c\x04\0\0\0\0\0\0\0\0\0\0\
+\x0c\0\0\0\x1c\x04\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x4d\x4e\x40\x41\x42\x43\x4c\0\
+\x2e\x74\x65\x78\x74\0\x2e\x72\x65\x6c\x2e\x42\x54\x46\x2e\x65\x78\x74\0\x64\
+\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\x61\x70\x2e\x5f\x5f\x5f\x66\x6d\x74\0\x64\
+\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\x2e\x5f\x5f\x5f\x66\x6d\x74\0\
+\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\x61\x70\0\x2e\x72\x65\x6c\x69\x74\x65\
+\x72\x2f\x62\x70\x66\x5f\x6d\x61\x70\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\
+\x72\x6f\x67\0\x2e\x72\x65\x6c\x69\x74\x65\x72\x2f\x62\x70\x66\x5f\x70\x72\x6f\
+\x67\0\x2e\x6c\x6c\x76\x6d\x5f\x61\x64\x64\x72\x73\x69\x67\0\x6c\x69\x63\x65\
+\x6e\x73\x65\0\x69\x74\x65\x72\x61\x74\x6f\x72\x73\x2e\x62\x70\x66\x2e\x63\0\
+\x2e\x73\x74\x72\x74\x61\x62\0\x2e\x73\x79\x6d\x74\x61\x62\0\x2e\x72\x6f\x64\
+\x61\x74\x61\0\x2e\x72\x65\x6c\x2e\x42\x54\x46\0\x4c\x49\x43\x45\x4e\x53\x45\0\
+\x4c\x42\x42\x31\x5f\x37\0\x4c\x42\x42\x31\x5f\x36\0\x4c\x42\x42\x30\x5f\x34\0\
+\x4c\x42\x42\x31\x5f\x33\0\x4c\x42\x42\x30\x5f\x33\0\x64\x75\x6d\x70\x5f\x62\
+\x70\x66\x5f\x70\x72\x6f\x67\x2e\x5f\x5f\x5f\x66\x6d\x74\x2e\x32\0\x64\x75\x6d\
+\x70\x5f\x62\x70\x66\x5f\x6d\x61\x70\x2e\x5f\x5f\x5f\x66\x6d\x74\x2e\x31\0\0\0\
 \0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
-\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x01\0\0\0\x01\0\0\0\x06\0\0\0\0\0\0\0\0\0\0\0\
-\0\0\0\0\x40\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x04\0\0\0\0\0\0\0\0\
-\0\0\0\0\0\0\0\x4e\0\0\0\x01\0\0\0\x06\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x40\0\0\0\
-\0\0\0\0\0\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x08\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
-\x6d\0\0\0\x01\0\0\0\x06\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x40\x01\0\0\0\0\0\0\x08\
-\x02\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x08\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xa1\0\0\0\
-\x01\0\0\0\x02\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x48\x03\0\0\0\0\0\0\x62\0\0\0\0\0\
-\0\0\0\0\0\0\0\0\0\0\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x89\0\0\0\x01\0\0\0\x03\
-\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xaa\x03\0\0\0\0\0\0\x04\0\0\0\0\0\0\0\0\0\0\0\0\
-\0\0\0\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xad\0\0\0\x01\0\0\0\0\0\0\0\0\0\0\0\0\
-\0\0\0\0\0\0\0\xae\x03\0\0\0\0\0\0\x34\x09\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x01\0\0\
-\0\0\0\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
-\xe2\x0c\0\0\0\0\0\0\x2c\x04\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x01\0\0\0\0\0\0\0\0\0\
-\0\0\0\0\0\0\x99\0\0\0\x02\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x10\x11\0\0\0\
-\0\0\0\x80\x01\0\0\0\0\0\0\x0e\0\0\0\x0d\0\0\0\x08\0\0\0\0\0\0\0\x18\0\0\0\0\0\
-\0\0\x4a\0\0\0\x09\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x90\x12\0\0\0\0\0\0\
-\x20\0\0\0\0\0\0\0\x08\0\0\0\x02\0\0\0\x08\0\0\0\0\0\0\0\x10\0\0\0\0\0\0\0\x69\
-\0\0\0\x09\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xb0\x12\0\0\0\0\0\0\x20\0\0\0\
-\0\0\0\0\x08\0\0\0\x03\0\0\0\x08\0\0\0\0\0\0\0\x10\0\0\0\0\0\0\0\xa9\0\0\0\x09\
-\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xd0\x12\0\0\0\0\0\0\x50\0\0\0\0\0\0\0\
-\x08\0\0\0\x06\0\0\0\x08\0\0\0\0\0\0\0\x10\0\0\0\0\0\0\0\x07\0\0\0\x09\0\0\0\0\
-\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x20\x13\0\0\0\0\0\0\xe0\x03\0\0\0\0\0\0\x08\0\0\
-\0\x07\0\0\0\x08\0\0\0\0\0\0\0\x10\0\0\0\0\0\0\0\x7b\0\0\0\x03\x4c\xff\x6f\0\0\
-\0\x80\0\0\0\0\0\0\0\0\0\0\0\0\0\x17\0\0\0\0\0\0\x07\0\0\0\0\0\0\0\0\0\0\0\0\0\
-\0\0\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x91\0\0\0\x03\0\0\0\0\0\0\0\0\0\0\0\0\0\
-\0\0\0\0\0\0\x07\x17\0\0\0\0\0\0\x0a\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x01\0\0\0\
-\0\0\0\0\0\0\0\0\0\0\0\0";
+\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x01\0\0\0\x01\0\0\
+\0\x06\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x40\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
+\0\0\0\0\x04\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x4e\0\0\0\x01\0\0\0\x06\0\0\0\0\0\0\
+\0\0\0\0\0\0\0\0\0\x40\0\0\0\0\0\0\0\0\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x08\0\0\
+\0\0\0\0\0\0\0\0\0\0\0\0\0\x6d\0\0\0\x01\0\0\0\x06\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
+\0\x40\x01\0\0\0\0\0\0\x08\x02\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x08\0\0\0\0\0\0\0\0\
+\0\0\0\0\0\0\0\xb1\0\0\0\x01\0\0\0\x02\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x48\x03\0\
+\0\0\0\0\0\x62\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
+\x89\0\0\0\x01\0\0\0\x03\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xaa\x03\0\0\0\0\0\0\x04\
+\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xbd\0\0\0\x01\
+\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xae\x03\0\0\0\0\0\0\x3d\x09\0\0\0\0\0\0\
+\0\0\0\0\0\0\0\0\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x01\0\0\0\0\0\0\0\
+\0\0\0\0\0\0\0\0\0\0\0\0\xeb\x0c\0\0\0\0\0\0\x2c\x04\0\0\0\0\0\0\0\0\0\0\0\0\0\
+\0\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xa9\0\0\0\x02\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
+\0\0\0\0\0\x18\x11\0\0\0\0\0\0\x98\x01\0\0\0\0\0\0\x0e\0\0\0\x0e\0\0\0\x08\0\0\
+\0\0\0\0\0\x18\0\0\0\0\0\0\0\x4a\0\0\0\x09\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
+\0\xb0\x12\0\0\0\0\0\0\x20\0\0\0\0\0\0\0\x08\0\0\0\x02\0\0\0\x08\0\0\0\0\0\0\0\
+\x10\0\0\0\0\0\0\0\x69\0\0\0\x09\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xd0\x12\
+\0\0\0\0\0\0\x20\0\0\0\0\0\0\0\x08\0\0\0\x03\0\0\0\x08\0\0\0\0\0\0\0\x10\0\0\0\
+\0\0\0\0\xb9\0\0\0\x09\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xf0\x12\0\0\0\0\0\
+\0\x50\0\0\0\0\0\0\0\x08\0\0\0\x06\0\0\0\x08\0\0\0\0\0\0\0\x10\0\0\0\0\0\0\0\
+\x07\0\0\0\x09\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x40\x13\0\0\0\0\0\0\xe0\
+\x03\0\0\0\0\0\0\x08\0\0\0\x07\0\0\0\x08\0\0\0\0\0\0\0\x10\0\0\0\0\0\0\0\x7b\0\
+\0\0\x03\x4c\xff\x6f\0\0\0\x80\0\0\0\0\0\0\0\0\0\0\0\0\x20\x17\0\0\0\0\0\0\x07\
+\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xa1\0\0\0\x03\
+\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x27\x17\0\0\0\0\0\0\x1a\x01\0\0\0\0\0\0\
+\0\0\0\0\0\0\0\0\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0";
 
 	return 0;
 err:
diff --git a/kernel/bpf/reuseport_array.c b/kernel/bpf/reuseport_array.c
index 5a2ba1182493..a55cd542f2ce 100644
--- a/kernel/bpf/reuseport_array.c
+++ b/kernel/bpf/reuseport_array.c
@@ -191,7 +191,7 @@ int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, void *key,
 	rcu_read_lock();
 	sk = reuseport_array_lookup_elem(map, key);
 	if (sk) {
-		*(u64 *)value = sock_gen_cookie(sk);
+		*(u64 *)value = __sock_gen_cookie(sk);
 		err = 0;
 	} else {
 		err = -ENOENT;
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index a2fa006f430e..06065fa27124 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -665,18 +665,17 @@ BPF_CALL_4(bpf_get_task_stack, struct task_struct *, task, void *, buf,
 	return __bpf_get_stack(regs, task, NULL, buf, size, flags);
 }
 
-BTF_ID_LIST(bpf_get_task_stack_btf_ids)
-BTF_ID(struct, task_struct)
+BTF_ID_LIST_SINGLE(bpf_get_task_stack_btf_ids, struct, task_struct)
 
 const struct bpf_func_proto bpf_get_task_stack_proto = {
 	.func		= bpf_get_task_stack,
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_BTF_ID,
+	.arg1_btf_id	= &bpf_get_task_stack_btf_ids[0],
 	.arg2_type	= ARG_PTR_TO_UNINIT_MEM,
 	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
 	.arg4_type	= ARG_ANYTHING,
-	.btf_id		= bpf_get_task_stack_btf_ids,
 };
 
 BPF_CALL_4(bpf_get_stack_pe, struct bpf_perf_event_data_kern *, ctx,
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 178c147350f5..f1528c2a6927 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -4,6 +4,7 @@
 #include <linux/bpf.h>
 #include <linux/bpf_trace.h>
 #include <linux/bpf_lirc.h>
+#include <linux/bpf_verifier.h>
 #include <linux/btf.h>
 #include <linux/syscalls.h>
 #include <linux/slab.h>
@@ -2154,14 +2155,14 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 	prog->expected_attach_type = attr->expected_attach_type;
 	prog->aux->attach_btf_id = attr->attach_btf_id;
 	if (attr->attach_prog_fd) {
-		struct bpf_prog *tgt_prog;
+		struct bpf_prog *dst_prog;
 
-		tgt_prog = bpf_prog_get(attr->attach_prog_fd);
-		if (IS_ERR(tgt_prog)) {
-			err = PTR_ERR(tgt_prog);
+		dst_prog = bpf_prog_get(attr->attach_prog_fd);
+		if (IS_ERR(dst_prog)) {
+			err = PTR_ERR(dst_prog);
 			goto free_prog_nouncharge;
 		}
-		prog->aux->linked_prog = tgt_prog;
+		prog->aux->dst_prog = dst_prog;
 	}
 
 	prog->aux->offload_requested = !!attr->prog_ifindex;
@@ -2498,11 +2499,23 @@ struct bpf_link *bpf_link_get_from_fd(u32 ufd)
 struct bpf_tracing_link {
 	struct bpf_link link;
 	enum bpf_attach_type attach_type;
+	struct bpf_trampoline *trampoline;
+	struct bpf_prog *tgt_prog;
 };
 
 static void bpf_tracing_link_release(struct bpf_link *link)
 {
-	WARN_ON_ONCE(bpf_trampoline_unlink_prog(link->prog));
+	struct bpf_tracing_link *tr_link =
+		container_of(link, struct bpf_tracing_link, link);
+
+	WARN_ON_ONCE(bpf_trampoline_unlink_prog(link->prog,
+						tr_link->trampoline));
+
+	bpf_trampoline_put(tr_link->trampoline);
+
+	/* tgt_prog is NULL if target is a kernel function */
+	if (tr_link->tgt_prog)
+		bpf_prog_put(tr_link->tgt_prog);
 }
 
 static void bpf_tracing_link_dealloc(struct bpf_link *link)
@@ -2542,10 +2555,15 @@ static const struct bpf_link_ops bpf_tracing_link_lops = {
 	.fill_link_info = bpf_tracing_link_fill_link_info,
 };
 
-static int bpf_tracing_prog_attach(struct bpf_prog *prog)
+static int bpf_tracing_prog_attach(struct bpf_prog *prog,
+				   int tgt_prog_fd,
+				   u32 btf_id)
 {
 	struct bpf_link_primer link_primer;
+	struct bpf_prog *tgt_prog = NULL;
+	struct bpf_trampoline *tr = NULL;
 	struct bpf_tracing_link *link;
+	u64 key = 0;
 	int err;
 
 	switch (prog->type) {
@@ -2574,6 +2592,28 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog)
 		goto out_put_prog;
 	}
 
+	if (!!tgt_prog_fd != !!btf_id) {
+		err = -EINVAL;
+		goto out_put_prog;
+	}
+
+	if (tgt_prog_fd) {
+		/* For now we only allow new targets for BPF_PROG_TYPE_EXT */
+		if (prog->type != BPF_PROG_TYPE_EXT) {
+			err = -EINVAL;
+			goto out_put_prog;
+		}
+
+		tgt_prog = bpf_prog_get(tgt_prog_fd);
+		if (IS_ERR(tgt_prog)) {
+			err = PTR_ERR(tgt_prog);
+			tgt_prog = NULL;
+			goto out_put_prog;
+		}
+
+		key = bpf_trampoline_compute_key(tgt_prog, btf_id);
+	}
+
 	link = kzalloc(sizeof(*link), GFP_USER);
 	if (!link) {
 		err = -ENOMEM;
@@ -2583,20 +2623,100 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog)
 		      &bpf_tracing_link_lops, prog);
 	link->attach_type = prog->expected_attach_type;
 
-	err = bpf_link_prime(&link->link, &link_primer);
-	if (err) {
-		kfree(link);
-		goto out_put_prog;
+	mutex_lock(&prog->aux->dst_mutex);
+
+	/* There are a few possible cases here:
+	 *
+	 * - if prog->aux->dst_trampoline is set, the program was just loaded
+	 *   and not yet attached to anything, so we can use the values stored
+	 *   in prog->aux
+	 *
+	 * - if prog->aux->dst_trampoline is NULL, the program has already been
+         *   attached to a target and its initial target was cleared (below)
+	 *
+	 * - if tgt_prog != NULL, the caller specified tgt_prog_fd +
+	 *   target_btf_id using the link_create API.
+	 *
+	 * - if tgt_prog == NULL when this function was called using the old
+         *   raw_tracepoint_open API, and we need a target from prog->aux
+         *
+         * The combination of no saved target in prog->aux, and no target
+         * specified on load is illegal, and we reject that here.
+	 */
+	if (!prog->aux->dst_trampoline && !tgt_prog) {
+		err = -ENOENT;
+		goto out_unlock;
 	}
 
-	err = bpf_trampoline_link_prog(prog);
+	if (!prog->aux->dst_trampoline ||
+	    (key && key != prog->aux->dst_trampoline->key)) {
+		/* If there is no saved target, or the specified target is
+		 * different from the destination specified at load time, we
+		 * need a new trampoline and a check for compatibility
+		 */
+		struct bpf_attach_target_info tgt_info = {};
+
+		err = bpf_check_attach_target(NULL, prog, tgt_prog, btf_id,
+					      &tgt_info);
+		if (err)
+			goto out_unlock;
+
+		tr = bpf_trampoline_get(key, &tgt_info);
+		if (!tr) {
+			err = -ENOMEM;
+			goto out_unlock;
+		}
+	} else {
+		/* The caller didn't specify a target, or the target was the
+		 * same as the destination supplied during program load. This
+		 * means we can reuse the trampoline and reference from program
+		 * load time, and there is no need to allocate a new one. This
+		 * can only happen once for any program, as the saved values in
+		 * prog->aux are cleared below.
+		 */
+		tr = prog->aux->dst_trampoline;
+		tgt_prog = prog->aux->dst_prog;
+	}
+
+	err = bpf_link_prime(&link->link, &link_primer);
+	if (err)
+		goto out_unlock;
+
+	err = bpf_trampoline_link_prog(prog, tr);
 	if (err) {
 		bpf_link_cleanup(&link_primer);
-		goto out_put_prog;
+		link = NULL;
+		goto out_unlock;
 	}
 
+	link->tgt_prog = tgt_prog;
+	link->trampoline = tr;
+
+	/* Always clear the trampoline and target prog from prog->aux to make
+	 * sure the original attach destination is not kept alive after a
+	 * program is (re-)attached to another target.
+	 */
+	if (prog->aux->dst_prog &&
+	    (tgt_prog_fd || tr != prog->aux->dst_trampoline))
+		/* got extra prog ref from syscall, or attaching to different prog */
+		bpf_prog_put(prog->aux->dst_prog);
+	if (prog->aux->dst_trampoline && tr != prog->aux->dst_trampoline)
+		/* we allocated a new trampoline, so free the old one */
+		bpf_trampoline_put(prog->aux->dst_trampoline);
+
+	prog->aux->dst_prog = NULL;
+	prog->aux->dst_trampoline = NULL;
+	mutex_unlock(&prog->aux->dst_mutex);
+
 	return bpf_link_settle(&link_primer);
+out_unlock:
+	if (tr && tr != prog->aux->dst_trampoline)
+		bpf_trampoline_put(tr);
+	mutex_unlock(&prog->aux->dst_mutex);
+	kfree(link);
 out_put_prog:
+	if (tgt_prog_fd && tgt_prog)
+		bpf_prog_put(tgt_prog);
 	bpf_prog_put(prog);
 	return err;
 }
@@ -2710,7 +2830,7 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr)
 			tp_name = prog->aux->attach_func_name;
 			break;
 		}
-		return bpf_tracing_prog_attach(prog);
+		return bpf_tracing_prog_attach(prog, 0, 0);
 	case BPF_PROG_TYPE_RAW_TRACEPOINT:
 	case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE:
 		if (strncpy_from_user(buf,
@@ -2979,7 +3099,7 @@ static int bpf_prog_query(const union bpf_attr *attr,
 	}
 }
 
-#define BPF_PROG_TEST_RUN_LAST_FIELD test.ctx_out
+#define BPF_PROG_TEST_RUN_LAST_FIELD test.cpu
 
 static int bpf_prog_test_run(const union bpf_attr *attr,
 			     union bpf_attr __user *uattr)
@@ -3162,21 +3282,25 @@ static const struct bpf_map *bpf_map_from_imm(const struct bpf_prog *prog,
 	const struct bpf_map *map;
 	int i;
 
+	mutex_lock(&prog->aux->used_maps_mutex);
 	for (i = 0, *off = 0; i < prog->aux->used_map_cnt; i++) {
 		map = prog->aux->used_maps[i];
 		if (map == (void *)addr) {
 			*type = BPF_PSEUDO_MAP_FD;
-			return map;
+			goto out;
 		}
 		if (!map->ops->map_direct_value_meta)
 			continue;
 		if (!map->ops->map_direct_value_meta(map, addr, off)) {
 			*type = BPF_PSEUDO_MAP_VALUE;
-			return map;
+			goto out;
 		}
 	}
+	map = NULL;
 
-	return NULL;
+out:
+	mutex_unlock(&prog->aux->used_maps_mutex);
+	return map;
 }
 
 static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog,
@@ -3294,6 +3418,7 @@ static int bpf_prog_get_info_by_fd(struct file *file,
 	memcpy(info.tag, prog->tag, sizeof(prog->tag));
 	memcpy(info.name, prog->aux->name, sizeof(prog->aux->name));
 
+	mutex_lock(&prog->aux->used_maps_mutex);
 	ulen = info.nr_map_ids;
 	info.nr_map_ids = prog->aux->used_map_cnt;
 	ulen = min_t(u32, info.nr_map_ids, ulen);
@@ -3303,9 +3428,12 @@ static int bpf_prog_get_info_by_fd(struct file *file,
 
 		for (i = 0; i < ulen; i++)
 			if (put_user(prog->aux->used_maps[i]->id,
-				     &user_map_ids[i]))
+				     &user_map_ids[i])) {
+				mutex_unlock(&prog->aux->used_maps_mutex);
 				return -EFAULT;
+			}
 	}
+	mutex_unlock(&prog->aux->used_maps_mutex);
 
 	err = set_info_rec_size(&info);
 	if (err)
@@ -3886,10 +4014,15 @@ err_put:
 
 static int tracing_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
 {
-	if (attr->link_create.attach_type == BPF_TRACE_ITER &&
-	    prog->expected_attach_type == BPF_TRACE_ITER)
-		return bpf_iter_link_attach(attr, prog);
+	if (attr->link_create.attach_type != prog->expected_attach_type)
+		return -EINVAL;
 
+	if (prog->expected_attach_type == BPF_TRACE_ITER)
+		return bpf_iter_link_attach(attr, prog);
+	else if (prog->type == BPF_PROG_TYPE_EXT)
+		return bpf_tracing_prog_attach(prog,
+					       attr->link_create.target_fd,
+					       attr->link_create.target_btf_id);
 	return -EINVAL;
 }
 
@@ -3903,18 +4036,25 @@ static int link_create(union bpf_attr *attr)
 	if (CHECK_ATTR(BPF_LINK_CREATE))
 		return -EINVAL;
 
-	ptype = attach_type_to_prog_type(attr->link_create.attach_type);
-	if (ptype == BPF_PROG_TYPE_UNSPEC)
-		return -EINVAL;
-
-	prog = bpf_prog_get_type(attr->link_create.prog_fd, ptype);
+	prog = bpf_prog_get(attr->link_create.prog_fd);
 	if (IS_ERR(prog))
 		return PTR_ERR(prog);
 
 	ret = bpf_prog_attach_check_attach_type(prog,
 						attr->link_create.attach_type);
 	if (ret)
-		goto err_out;
+		goto out;
+
+	if (prog->type == BPF_PROG_TYPE_EXT) {
+		ret = tracing_bpf_link_attach(attr, prog);
+		goto out;
+	}
+
+	ptype = attach_type_to_prog_type(attr->link_create.attach_type);
+	if (ptype == BPF_PROG_TYPE_UNSPEC || ptype != prog->type) {
+		ret = -EINVAL;
+		goto out;
+	}
 
 	switch (ptype) {
 	case BPF_PROG_TYPE_CGROUP_SKB:
@@ -3942,7 +4082,7 @@ static int link_create(union bpf_attr *attr)
 		ret = -EINVAL;
 	}
 
-err_out:
+out:
 	if (ret < 0)
 		bpf_prog_put(prog);
 	return ret;
@@ -4153,6 +4293,66 @@ static int bpf_iter_create(union bpf_attr *attr)
 	return err;
 }
 
+#define BPF_PROG_BIND_MAP_LAST_FIELD prog_bind_map.flags
+
+static int bpf_prog_bind_map(union bpf_attr *attr)
+{
+	struct bpf_prog *prog;
+	struct bpf_map *map;
+	struct bpf_map **used_maps_old, **used_maps_new;
+	int i, ret = 0;
+
+	if (CHECK_ATTR(BPF_PROG_BIND_MAP))
+		return -EINVAL;
+
+	if (attr->prog_bind_map.flags)
+		return -EINVAL;
+
+	prog = bpf_prog_get(attr->prog_bind_map.prog_fd);
+	if (IS_ERR(prog))
+		return PTR_ERR(prog);
+
+	map = bpf_map_get(attr->prog_bind_map.map_fd);
+	if (IS_ERR(map)) {
+		ret = PTR_ERR(map);
+		goto out_prog_put;
+	}
+
+	mutex_lock(&prog->aux->used_maps_mutex);
+
+	used_maps_old = prog->aux->used_maps;
+
+	for (i = 0; i < prog->aux->used_map_cnt; i++)
+		if (used_maps_old[i] == map)
+			goto out_unlock;
+
+	used_maps_new = kmalloc_array(prog->aux->used_map_cnt + 1,
+				      sizeof(used_maps_new[0]),
+				      GFP_KERNEL);
+	if (!used_maps_new) {
+		ret = -ENOMEM;
+		goto out_unlock;
+	}
+
+	memcpy(used_maps_new, used_maps_old,
+	       sizeof(used_maps_old[0]) * prog->aux->used_map_cnt);
+	used_maps_new[prog->aux->used_map_cnt] = map;
+
+	prog->aux->used_map_cnt++;
+	prog->aux->used_maps = used_maps_new;
+
+	kfree(used_maps_old);
+
+out_unlock:
+	mutex_unlock(&prog->aux->used_maps_mutex);
+
+	if (ret)
+		bpf_map_put(map);
+out_prog_put:
+	bpf_prog_put(prog);
+	return ret;
+}
+
 SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size)
 {
 	union bpf_attr attr;
@@ -4286,6 +4486,9 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
 	case BPF_LINK_DETACH:
 		err = link_detach(&attr);
 		break;
+	case BPF_PROG_BIND_MAP:
+		err = bpf_prog_bind_map(&attr);
+		break;
 	default:
 		err = -EINVAL;
 		break;
diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c
index 99af4cea1102..5b6af30bfbcd 100644
--- a/kernel/bpf/task_iter.c
+++ b/kernel/bpf/task_iter.c
@@ -22,7 +22,8 @@ struct bpf_iter_seq_task_info {
 };
 
 static struct task_struct *task_seq_get_next(struct pid_namespace *ns,
-					     u32 *tid)
+					     u32 *tid,
+					     bool skip_if_dup_files)
 {
 	struct task_struct *task = NULL;
 	struct pid *pid;
@@ -36,6 +37,12 @@ retry:
 		if (!task) {
 			++*tid;
 			goto retry;
+		} else if (skip_if_dup_files && task->tgid != task->pid &&
+			   task->files == task->group_leader->files) {
+			put_task_struct(task);
+			task = NULL;
+			++*tid;
+			goto retry;
 		}
 	}
 	rcu_read_unlock();
@@ -48,7 +55,7 @@ static void *task_seq_start(struct seq_file *seq, loff_t *pos)
 	struct bpf_iter_seq_task_info *info = seq->private;
 	struct task_struct *task;
 
-	task = task_seq_get_next(info->common.ns, &info->tid);
+	task = task_seq_get_next(info->common.ns, &info->tid, false);
 	if (!task)
 		return NULL;
 
@@ -65,7 +72,7 @@ static void *task_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 	++*pos;
 	++info->tid;
 	put_task_struct((struct task_struct *)v);
-	task = task_seq_get_next(info->common.ns, &info->tid);
+	task = task_seq_get_next(info->common.ns, &info->tid, false);
 	if (!task)
 		return NULL;
 
@@ -148,7 +155,7 @@ again:
 		curr_files = *fstruct;
 		curr_fd = info->fd;
 	} else {
-		curr_task = task_seq_get_next(ns, &curr_tid);
+		curr_task = task_seq_get_next(ns, &curr_tid, true);
 		if (!curr_task)
 			return NULL;
 
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index 7dd523a7e32d..35c5887d82ff 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -65,7 +65,7 @@ static void bpf_trampoline_ksym_add(struct bpf_trampoline *tr)
 	bpf_image_ksym_add(tr->image, ksym);
 }
 
-struct bpf_trampoline *bpf_trampoline_lookup(u64 key)
+static struct bpf_trampoline *bpf_trampoline_lookup(u64 key)
 {
 	struct bpf_trampoline *tr;
 	struct hlist_head *head;
@@ -261,14 +261,12 @@ static enum bpf_tramp_prog_type bpf_attach_type_to_tramp(struct bpf_prog *prog)
 	}
 }
 
-int bpf_trampoline_link_prog(struct bpf_prog *prog)
+int bpf_trampoline_link_prog(struct bpf_prog *prog, struct bpf_trampoline *tr)
 {
 	enum bpf_tramp_prog_type kind;
-	struct bpf_trampoline *tr;
 	int err = 0;
 	int cnt;
 
-	tr = prog->aux->trampoline;
 	kind = bpf_attach_type_to_tramp(prog);
 	mutex_lock(&tr->mutex);
 	if (tr->extension_prog) {
@@ -301,7 +299,7 @@ int bpf_trampoline_link_prog(struct bpf_prog *prog)
 	}
 	hlist_add_head(&prog->aux->tramp_hlist, &tr->progs_hlist[kind]);
 	tr->progs_cnt[kind]++;
-	err = bpf_trampoline_update(prog->aux->trampoline);
+	err = bpf_trampoline_update(tr);
 	if (err) {
 		hlist_del(&prog->aux->tramp_hlist);
 		tr->progs_cnt[kind]--;
@@ -312,13 +310,11 @@ out:
 }
 
 /* bpf_trampoline_unlink_prog() should never fail. */
-int bpf_trampoline_unlink_prog(struct bpf_prog *prog)
+int bpf_trampoline_unlink_prog(struct bpf_prog *prog, struct bpf_trampoline *tr)
 {
 	enum bpf_tramp_prog_type kind;
-	struct bpf_trampoline *tr;
 	int err;
 
-	tr = prog->aux->trampoline;
 	kind = bpf_attach_type_to_tramp(prog);
 	mutex_lock(&tr->mutex);
 	if (kind == BPF_TRAMP_REPLACE) {
@@ -330,12 +326,32 @@ int bpf_trampoline_unlink_prog(struct bpf_prog *prog)
 	}
 	hlist_del(&prog->aux->tramp_hlist);
 	tr->progs_cnt[kind]--;
-	err = bpf_trampoline_update(prog->aux->trampoline);
+	err = bpf_trampoline_update(tr);
 out:
 	mutex_unlock(&tr->mutex);
 	return err;
 }
 
+struct bpf_trampoline *bpf_trampoline_get(u64 key,
+					  struct bpf_attach_target_info *tgt_info)
+{
+	struct bpf_trampoline *tr;
+
+	tr = bpf_trampoline_lookup(key);
+	if (!tr)
+		return NULL;
+
+	mutex_lock(&tr->mutex);
+	if (tr->func.addr)
+		goto out;
+
+	memcpy(&tr->func.model, &tgt_info->fmodel, sizeof(tgt_info->fmodel));
+	tr->func.addr = (void *)tgt_info->tgt_addr;
+out:
+	mutex_unlock(&tr->mutex);
+	return tr;
+}
+
 void bpf_trampoline_put(struct bpf_trampoline *tr)
 {
 	if (!tr)
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 86fdebb5ffd8..015a1c074b6b 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -238,7 +238,6 @@ struct bpf_call_arg_meta {
 	u64 msize_max_value;
 	int ref_obj_id;
 	int func_id;
-	u32 btf_id;
 };
 
 struct btf *btf_vmlinux;
@@ -436,6 +435,15 @@ static bool arg_type_may_be_refcounted(enum bpf_arg_type type)
 	return type == ARG_PTR_TO_SOCK_COMMON;
 }
 
+static bool arg_type_may_be_null(enum bpf_arg_type type)
+{
+	return type == ARG_PTR_TO_MAP_VALUE_OR_NULL ||
+	       type == ARG_PTR_TO_MEM_OR_NULL ||
+	       type == ARG_PTR_TO_CTX_OR_NULL ||
+	       type == ARG_PTR_TO_SOCKET_OR_NULL ||
+	       type == ARG_PTR_TO_ALLOC_MEM_OR_NULL;
+}
+
 /* Determine whether the function releases some resources allocated by another
  * function call. The first reference type argument will be assumed to be
  * released by release_reference().
@@ -478,7 +486,12 @@ static bool is_acquire_function(enum bpf_func_id func_id,
 static bool is_ptr_cast_function(enum bpf_func_id func_id)
 {
 	return func_id == BPF_FUNC_tcp_sock ||
-		func_id == BPF_FUNC_sk_fullsock;
+		func_id == BPF_FUNC_sk_fullsock ||
+		func_id == BPF_FUNC_skc_to_tcp_sock ||
+		func_id == BPF_FUNC_skc_to_tcp6_sock ||
+		func_id == BPF_FUNC_skc_to_udp6_sock ||
+		func_id == BPF_FUNC_skc_to_tcp_timewait_sock ||
+		func_id == BPF_FUNC_skc_to_tcp_request_sock;
 }
 
 /* string representation of 'enum bpf_reg_type' */
@@ -1490,6 +1503,13 @@ static int check_subprogs(struct bpf_verifier_env *env)
 	for (i = 0; i < insn_cnt; i++) {
 		u8 code = insn[i].code;
 
+		if (code == (BPF_JMP | BPF_CALL) &&
+		    insn[i].imm == BPF_FUNC_tail_call &&
+		    insn[i].src_reg != BPF_PSEUDO_CALL)
+			subprog[cur_subprog].has_tail_call = true;
+		if (BPF_CLASS(code) == BPF_LD &&
+		    (BPF_MODE(code) == BPF_ABS || BPF_MODE(code) == BPF_IND))
+			subprog[cur_subprog].has_ld_abs = true;
 		if (BPF_CLASS(code) != BPF_JMP && BPF_CLASS(code) != BPF_JMP32)
 			goto next;
 		if (BPF_OP(code) == BPF_EXIT || BPF_OP(code) == BPF_CALL)
@@ -2628,8 +2648,7 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno,
 
 static enum bpf_prog_type resolve_prog_type(struct bpf_prog *prog)
 {
-	return prog->aux->linked_prog ? prog->aux->linked_prog->type
-				      : prog->type;
+	return prog->aux->dst_prog ? prog->aux->dst_prog->type : prog->type;
 }
 
 static bool may_access_direct_pkt_data(struct bpf_verifier_env *env,
@@ -2979,10 +2998,37 @@ static int check_max_stack_depth(struct bpf_verifier_env *env)
 	int depth = 0, frame = 0, idx = 0, i = 0, subprog_end;
 	struct bpf_subprog_info *subprog = env->subprog_info;
 	struct bpf_insn *insn = env->prog->insnsi;
+	bool tail_call_reachable = false;
 	int ret_insn[MAX_CALL_FRAMES];
 	int ret_prog[MAX_CALL_FRAMES];
+	int j;
 
 process_func:
+	/* protect against potential stack overflow that might happen when
+	 * bpf2bpf calls get combined with tailcalls. Limit the caller's stack
+	 * depth for such case down to 256 so that the worst case scenario
+	 * would result in 8k stack size (32 which is tailcall limit * 256 =
+	 * 8k).
+	 *
+	 * To get the idea what might happen, see an example:
+	 * func1 -> sub rsp, 128
+	 *  subfunc1 -> sub rsp, 256
+	 *  tailcall1 -> add rsp, 256
+	 *   func2 -> sub rsp, 192 (total stack size = 128 + 192 = 320)
+	 *   subfunc2 -> sub rsp, 64
+	 *   subfunc22 -> sub rsp, 128
+	 *   tailcall2 -> add rsp, 128
+	 *    func3 -> sub rsp, 32 (total stack size 128 + 192 + 64 + 32 = 416)
+	 *
+	 * tailcall will unwind the current stack frame but it will not get rid
+	 * of caller's stack as shown on the example above.
+	 */
+	if (idx && subprog[idx].has_tail_call && depth >= 256) {
+		verbose(env,
+			"tail_calls are not allowed when call stack of previous frames is %d bytes. Too large\n",
+			depth);
+		return -EACCES;
+	}
 	/* round up to 32-bytes, since this is granularity
 	 * of interpreter stack size
 	 */
@@ -3011,6 +3057,10 @@ continue_func:
 				  i);
 			return -EFAULT;
 		}
+
+		if (subprog[idx].has_tail_call)
+			tail_call_reachable = true;
+
 		frame++;
 		if (frame >= MAX_CALL_FRAMES) {
 			verbose(env, "the call stack of %d frames is too deep !\n",
@@ -3019,6 +3069,15 @@ continue_func:
 		}
 		goto process_func;
 	}
+	/* if tail call got detected across bpf2bpf calls then mark each of the
+	 * currently present subprog frames as tail call reachable subprogs;
+	 * this info will be utilized by JIT so that we will be preserving the
+	 * tail call counter throughout bpf2bpf calls combined with tailcalls
+	 */
+	if (tail_call_reachable)
+		for (j = 0; j < frame; j++)
+			subprog[ret_prog[j]].tail_call_reachable = true;
+
 	/* end of for() loop means the last insn of the 'subprog'
 	 * was reached. Doesn't matter whether it was JA or EXIT
 	 */
@@ -3594,18 +3653,6 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno,
 	struct bpf_func_state *state = func(env, reg);
 	int err, min_off, max_off, i, j, slot, spi;
 
-	if (reg->type != PTR_TO_STACK) {
-		/* Allow zero-byte read from NULL, regardless of pointer type */
-		if (zero_size_allowed && access_size == 0 &&
-		    register_is_null(reg))
-			return 0;
-
-		verbose(env, "R%d type=%s expected=%s\n", regno,
-			reg_type_str[reg->type],
-			reg_type_str[PTR_TO_STACK]);
-		return -EACCES;
-	}
-
 	if (tnum_is_const(reg->var_off)) {
 		min_off = max_off = reg->var_off.value + reg->off;
 		err = __check_stack_boundary(env, regno, min_off, access_size,
@@ -3750,9 +3797,19 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno,
 					   access_size, zero_size_allowed,
 					   "rdwr",
 					   &env->prog->aux->max_rdwr_access);
-	default: /* scalar_value|ptr_to_stack or invalid ptr */
+	case PTR_TO_STACK:
 		return check_stack_boundary(env, regno, access_size,
 					    zero_size_allowed, meta);
+	default: /* scalar_value or invalid ptr */
+		/* Allow zero-byte read from NULL, regardless of pointer type */
+		if (zero_size_allowed && access_size == 0 &&
+		    register_is_null(reg))
+			return 0;
+
+		verbose(env, "R%d type=%s expected=%s\n", regno,
+			reg_type_str[reg->type],
+			reg_type_str[PTR_TO_STACK]);
+		return -EACCES;
 	}
 }
 
@@ -3784,10 +3841,6 @@ static int process_spin_lock(struct bpf_verifier_env *env, int regno,
 	struct bpf_map *map = reg->map_ptr;
 	u64 val = reg->var_off.value;
 
-	if (reg->type != PTR_TO_MAP_VALUE) {
-		verbose(env, "R%d is not a pointer to map_value\n", regno);
-		return -EINVAL;
-	}
 	if (!is_const) {
 		verbose(env,
 			"R%d doesn't have constant offset. bpf_spin_lock has to be at the constant offset\n",
@@ -3854,12 +3907,6 @@ static bool arg_type_is_mem_size(enum bpf_arg_type type)
 	       type == ARG_CONST_SIZE_OR_ZERO;
 }
 
-static bool arg_type_is_alloc_mem_ptr(enum bpf_arg_type type)
-{
-	return type == ARG_PTR_TO_ALLOC_MEM ||
-	       type == ARG_PTR_TO_ALLOC_MEM_OR_NULL;
-}
-
 static bool arg_type_is_alloc_size(enum bpf_arg_type type)
 {
 	return type == ARG_CONST_ALLOC_SIZE_OR_ZERO;
@@ -3895,7 +3942,7 @@ static int resolve_map_arg_type(struct bpf_verifier_env *env,
 	case BPF_MAP_TYPE_SOCKMAP:
 	case BPF_MAP_TYPE_SOCKHASH:
 		if (*arg_type == ARG_PTR_TO_MAP_VALUE) {
-			*arg_type = ARG_PTR_TO_SOCKET;
+			*arg_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON;
 		} else {
 			verbose(env, "invalid arg_type for sockmap/sockhash\n");
 			return -EINVAL;
@@ -3908,14 +3955,161 @@ static int resolve_map_arg_type(struct bpf_verifier_env *env,
 	return 0;
 }
 
+struct bpf_reg_types {
+	const enum bpf_reg_type types[10];
+	u32 *btf_id;
+};
+
+static const struct bpf_reg_types map_key_value_types = {
+	.types = {
+		PTR_TO_STACK,
+		PTR_TO_PACKET,
+		PTR_TO_PACKET_META,
+		PTR_TO_MAP_VALUE,
+	},
+};
+
+static const struct bpf_reg_types sock_types = {
+	.types = {
+		PTR_TO_SOCK_COMMON,
+		PTR_TO_SOCKET,
+		PTR_TO_TCP_SOCK,
+		PTR_TO_XDP_SOCK,
+	},
+};
+
+static const struct bpf_reg_types btf_id_sock_common_types = {
+	.types = {
+		PTR_TO_SOCK_COMMON,
+		PTR_TO_SOCKET,
+		PTR_TO_TCP_SOCK,
+		PTR_TO_XDP_SOCK,
+		PTR_TO_BTF_ID,
+	},
+	.btf_id = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON],
+};
+
+static const struct bpf_reg_types mem_types = {
+	.types = {
+		PTR_TO_STACK,
+		PTR_TO_PACKET,
+		PTR_TO_PACKET_META,
+		PTR_TO_MAP_VALUE,
+		PTR_TO_MEM,
+		PTR_TO_RDONLY_BUF,
+		PTR_TO_RDWR_BUF,
+	},
+};
+
+static const struct bpf_reg_types int_ptr_types = {
+	.types = {
+		PTR_TO_STACK,
+		PTR_TO_PACKET,
+		PTR_TO_PACKET_META,
+		PTR_TO_MAP_VALUE,
+	},
+};
+
+static const struct bpf_reg_types fullsock_types = { .types = { PTR_TO_SOCKET } };
+static const struct bpf_reg_types scalar_types = { .types = { SCALAR_VALUE } };
+static const struct bpf_reg_types context_types = { .types = { PTR_TO_CTX } };
+static const struct bpf_reg_types alloc_mem_types = { .types = { PTR_TO_MEM } };
+static const struct bpf_reg_types const_map_ptr_types = { .types = { CONST_PTR_TO_MAP } };
+static const struct bpf_reg_types btf_ptr_types = { .types = { PTR_TO_BTF_ID } };
+static const struct bpf_reg_types spin_lock_types = { .types = { PTR_TO_MAP_VALUE } };
+
+static const struct bpf_reg_types *compatible_reg_types[__BPF_ARG_TYPE_MAX] = {
+	[ARG_PTR_TO_MAP_KEY]		= &map_key_value_types,
+	[ARG_PTR_TO_MAP_VALUE]		= &map_key_value_types,
+	[ARG_PTR_TO_UNINIT_MAP_VALUE]	= &map_key_value_types,
+	[ARG_PTR_TO_MAP_VALUE_OR_NULL]	= &map_key_value_types,
+	[ARG_CONST_SIZE]		= &scalar_types,
+	[ARG_CONST_SIZE_OR_ZERO]	= &scalar_types,
+	[ARG_CONST_ALLOC_SIZE_OR_ZERO]	= &scalar_types,
+	[ARG_CONST_MAP_PTR]		= &const_map_ptr_types,
+	[ARG_PTR_TO_CTX]		= &context_types,
+	[ARG_PTR_TO_CTX_OR_NULL]	= &context_types,
+	[ARG_PTR_TO_SOCK_COMMON]	= &sock_types,
+	[ARG_PTR_TO_BTF_ID_SOCK_COMMON]	= &btf_id_sock_common_types,
+	[ARG_PTR_TO_SOCKET]		= &fullsock_types,
+	[ARG_PTR_TO_SOCKET_OR_NULL]	= &fullsock_types,
+	[ARG_PTR_TO_BTF_ID]		= &btf_ptr_types,
+	[ARG_PTR_TO_SPIN_LOCK]		= &spin_lock_types,
+	[ARG_PTR_TO_MEM]		= &mem_types,
+	[ARG_PTR_TO_MEM_OR_NULL]	= &mem_types,
+	[ARG_PTR_TO_UNINIT_MEM]		= &mem_types,
+	[ARG_PTR_TO_ALLOC_MEM]		= &alloc_mem_types,
+	[ARG_PTR_TO_ALLOC_MEM_OR_NULL]	= &alloc_mem_types,
+	[ARG_PTR_TO_INT]		= &int_ptr_types,
+	[ARG_PTR_TO_LONG]		= &int_ptr_types,
+};
+
+static int check_reg_type(struct bpf_verifier_env *env, u32 regno,
+			  enum bpf_arg_type arg_type,
+			  const u32 *arg_btf_id)
+{
+	struct bpf_reg_state *regs = cur_regs(env), *reg = &regs[regno];
+	enum bpf_reg_type expected, type = reg->type;
+	const struct bpf_reg_types *compatible;
+	int i, j;
+
+	compatible = compatible_reg_types[arg_type];
+	if (!compatible) {
+		verbose(env, "verifier internal error: unsupported arg type %d\n", arg_type);
+		return -EFAULT;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(compatible->types); i++) {
+		expected = compatible->types[i];
+		if (expected == NOT_INIT)
+			break;
+
+		if (type == expected)
+			goto found;
+	}
+
+	verbose(env, "R%d type=%s expected=", regno, reg_type_str[type]);
+	for (j = 0; j + 1 < i; j++)
+		verbose(env, "%s, ", reg_type_str[compatible->types[j]]);
+	verbose(env, "%s\n", reg_type_str[compatible->types[j]]);
+	return -EACCES;
+
+found:
+	if (type == PTR_TO_BTF_ID) {
+		if (!arg_btf_id) {
+			if (!compatible->btf_id) {
+				verbose(env, "verifier internal error: missing arg compatible BTF ID\n");
+				return -EFAULT;
+			}
+			arg_btf_id = compatible->btf_id;
+		}
+
+		if (!btf_struct_ids_match(&env->log, reg->off, reg->btf_id,
+					  *arg_btf_id)) {
+			verbose(env, "R%d is of type %s but %s is expected\n",
+				regno, kernel_type_name(reg->btf_id),
+				kernel_type_name(*arg_btf_id));
+			return -EACCES;
+		}
+
+		if (!tnum_is_const(reg->var_off) || reg->var_off.value) {
+			verbose(env, "R%d is a pointer to in-kernel struct with non-zero offset\n",
+				regno);
+			return -EACCES;
+		}
+	}
+
+	return 0;
+}
+
 static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
 			  struct bpf_call_arg_meta *meta,
 			  const struct bpf_func_proto *fn)
 {
 	u32 regno = BPF_REG_1 + arg;
 	struct bpf_reg_state *regs = cur_regs(env), *reg = &regs[regno];
-	enum bpf_reg_type expected_type, type = reg->type;
 	enum bpf_arg_type arg_type = fn->arg_type[arg];
+	enum bpf_reg_type type = reg->type;
 	int err = 0;
 
 	if (arg_type == ARG_DONTCARE)
@@ -3948,125 +4142,24 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
 			return err;
 	}
 
-	if (arg_type == ARG_PTR_TO_MAP_KEY ||
-	    arg_type == ARG_PTR_TO_MAP_VALUE ||
-	    arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE ||
-	    arg_type == ARG_PTR_TO_MAP_VALUE_OR_NULL) {
-		expected_type = PTR_TO_STACK;
-		if (register_is_null(reg) &&
-		    arg_type == ARG_PTR_TO_MAP_VALUE_OR_NULL)
-			/* final test in check_stack_boundary() */;
-		else if (!type_is_pkt_pointer(type) &&
-			 type != PTR_TO_MAP_VALUE &&
-			 type != expected_type)
-			goto err_type;
-	} else if (arg_type == ARG_CONST_SIZE ||
-		   arg_type == ARG_CONST_SIZE_OR_ZERO ||
-		   arg_type == ARG_CONST_ALLOC_SIZE_OR_ZERO) {
-		expected_type = SCALAR_VALUE;
-		if (type != expected_type)
-			goto err_type;
-	} else if (arg_type == ARG_CONST_MAP_PTR) {
-		expected_type = CONST_PTR_TO_MAP;
-		if (type != expected_type)
-			goto err_type;
-	} else if (arg_type == ARG_PTR_TO_CTX ||
-		   arg_type == ARG_PTR_TO_CTX_OR_NULL) {
-		expected_type = PTR_TO_CTX;
-		if (!(register_is_null(reg) &&
-		      arg_type == ARG_PTR_TO_CTX_OR_NULL)) {
-			if (type != expected_type)
-				goto err_type;
-			err = check_ctx_reg(env, reg, regno);
-			if (err < 0)
-				return err;
-		}
-	} else if (arg_type == ARG_PTR_TO_SOCK_COMMON) {
-		expected_type = PTR_TO_SOCK_COMMON;
-		/* Any sk pointer can be ARG_PTR_TO_SOCK_COMMON */
-		if (!type_is_sk_pointer(type))
-			goto err_type;
-		if (reg->ref_obj_id) {
-			if (meta->ref_obj_id) {
-				verbose(env, "verifier internal error: more than one arg with ref_obj_id R%d %u %u\n",
-					regno, reg->ref_obj_id,
-					meta->ref_obj_id);
-				return -EFAULT;
-			}
-			meta->ref_obj_id = reg->ref_obj_id;
-		}
-	} else if (arg_type == ARG_PTR_TO_SOCKET ||
-		   arg_type == ARG_PTR_TO_SOCKET_OR_NULL) {
-		expected_type = PTR_TO_SOCKET;
-		if (!(register_is_null(reg) &&
-		      arg_type == ARG_PTR_TO_SOCKET_OR_NULL)) {
-			if (type != expected_type)
-				goto err_type;
-		}
-	} else if (arg_type == ARG_PTR_TO_BTF_ID) {
-		bool ids_match = false;
-
-		expected_type = PTR_TO_BTF_ID;
-		if (type != expected_type)
-			goto err_type;
-		if (!fn->check_btf_id) {
-			if (reg->btf_id != meta->btf_id) {
-				ids_match = btf_struct_ids_match(&env->log, reg->off, reg->btf_id,
-								 meta->btf_id);
-				if (!ids_match) {
-					verbose(env, "Helper has type %s got %s in R%d\n",
-						kernel_type_name(meta->btf_id),
-						kernel_type_name(reg->btf_id), regno);
-					return -EACCES;
-				}
-			}
-		} else if (!fn->check_btf_id(reg->btf_id, arg)) {
-			verbose(env, "Helper does not support %s in R%d\n",
-				kernel_type_name(reg->btf_id), regno);
-
-			return -EACCES;
-		}
-		if ((reg->off && !ids_match) || !tnum_is_const(reg->var_off) || reg->var_off.value) {
-			verbose(env, "R%d is a pointer to in-kernel struct with non-zero offset\n",
-				regno);
-			return -EACCES;
-		}
-	} else if (arg_type == ARG_PTR_TO_SPIN_LOCK) {
-		if (meta->func_id == BPF_FUNC_spin_lock) {
-			if (process_spin_lock(env, regno, true))
-				return -EACCES;
-		} else if (meta->func_id == BPF_FUNC_spin_unlock) {
-			if (process_spin_lock(env, regno, false))
-				return -EACCES;
-		} else {
-			verbose(env, "verifier internal error\n");
-			return -EFAULT;
-		}
-	} else if (arg_type_is_mem_ptr(arg_type)) {
-		expected_type = PTR_TO_STACK;
-		/* One exception here. In case function allows for NULL to be
-		 * passed in as argument, it's a SCALAR_VALUE type. Final test
-		 * happens during stack boundary checking.
+	if (register_is_null(reg) && arg_type_may_be_null(arg_type))
+		/* A NULL register has a SCALAR_VALUE type, so skip
+		 * type checking.
 		 */
-		if (register_is_null(reg) &&
-		    (arg_type == ARG_PTR_TO_MEM_OR_NULL ||
-		     arg_type == ARG_PTR_TO_ALLOC_MEM_OR_NULL))
-			/* final test in check_stack_boundary() */;
-		else if (!type_is_pkt_pointer(type) &&
-			 type != PTR_TO_MAP_VALUE &&
-			 type != PTR_TO_MEM &&
-			 type != PTR_TO_RDONLY_BUF &&
-			 type != PTR_TO_RDWR_BUF &&
-			 type != expected_type)
-			goto err_type;
-		meta->raw_mode = arg_type == ARG_PTR_TO_UNINIT_MEM;
-	} else if (arg_type_is_alloc_mem_ptr(arg_type)) {
-		expected_type = PTR_TO_MEM;
-		if (register_is_null(reg) &&
-		    arg_type == ARG_PTR_TO_ALLOC_MEM_OR_NULL)
-			/* final test in check_stack_boundary() */;
-		else if (type != expected_type)
-			goto err_type;
+		goto skip_type_check;
+
+	err = check_reg_type(env, regno, arg_type, fn->arg_btf_id[arg]);
+	if (err)
+		return err;
+
+	if (type == PTR_TO_CTX) {
+		err = check_ctx_reg(env, reg, regno);
+		if (err < 0)
+			return err;
+	}
+
+skip_type_check:
+	if (reg->ref_obj_id) {
 		if (meta->ref_obj_id) {
 			verbose(env, "verifier internal error: more than one arg with ref_obj_id R%d %u %u\n",
 				regno, reg->ref_obj_id,
@@ -4074,15 +4167,6 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
 			return -EFAULT;
 		}
 		meta->ref_obj_id = reg->ref_obj_id;
-	} else if (arg_type_is_int_ptr(arg_type)) {
-		expected_type = PTR_TO_STACK;
-		if (!type_is_pkt_pointer(type) &&
-		    type != PTR_TO_MAP_VALUE &&
-		    type != expected_type)
-			goto err_type;
-	} else {
-		verbose(env, "unsupported arg_type %d\n", arg_type);
-		return -EFAULT;
 	}
 
 	if (arg_type == ARG_CONST_MAP_PTR) {
@@ -4121,6 +4205,22 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
 		err = check_helper_mem_access(env, regno,
 					      meta->map_ptr->value_size, false,
 					      meta);
+	} else if (arg_type == ARG_PTR_TO_SPIN_LOCK) {
+		if (meta->func_id == BPF_FUNC_spin_lock) {
+			if (process_spin_lock(env, regno, true))
+				return -EACCES;
+		} else if (meta->func_id == BPF_FUNC_spin_unlock) {
+			if (process_spin_lock(env, regno, false))
+				return -EACCES;
+		} else {
+			verbose(env, "verifier internal error\n");
+			return -EFAULT;
+		}
+	} else if (arg_type_is_mem_ptr(arg_type)) {
+		/* The access to this pointer is only checked when we hit the
+		 * next is_mem_size argument below.
+		 */
+		meta->raw_mode = (arg_type == ARG_PTR_TO_UNINIT_MEM);
 	} else if (arg_type_is_mem_size(arg_type)) {
 		bool zero_size_allowed = (arg_type == ARG_CONST_SIZE_OR_ZERO);
 
@@ -4186,10 +4286,6 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
 	}
 
 	return err;
-err_type:
-	verbose(env, "R%d type=%s expected=%s\n", regno,
-		reg_type_str[type], reg_type_str[expected_type]);
-	return -EACCES;
 }
 
 static bool may_update_sockmap(struct bpf_verifier_env *env, int func_id)
@@ -4224,6 +4320,11 @@ static bool may_update_sockmap(struct bpf_verifier_env *env, int func_id)
 	return false;
 }
 
+static bool allow_tail_call_in_subprogs(struct bpf_verifier_env *env)
+{
+	return env->prog->jit_requested && IS_ENABLED(CONFIG_X86_64);
+}
+
 static int check_map_func_compatibility(struct bpf_verifier_env *env,
 					struct bpf_map *map, int func_id)
 {
@@ -4339,8 +4440,8 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 	case BPF_FUNC_tail_call:
 		if (map->map_type != BPF_MAP_TYPE_PROG_ARRAY)
 			goto error;
-		if (env->subprog_cnt > 1) {
-			verbose(env, "tail_calls are not allowed in programs with bpf-to-bpf calls\n");
+		if (env->subprog_cnt > 1 && !allow_tail_call_in_subprogs(env)) {
+			verbose(env, "tail_calls are not allowed in non-JITed programs with bpf-to-bpf calls\n");
 			return -EINVAL;
 		}
 		break;
@@ -4495,10 +4596,26 @@ static bool check_refcount_ok(const struct bpf_func_proto *fn, int func_id)
 	return count <= 1;
 }
 
+static bool check_btf_id_ok(const struct bpf_func_proto *fn)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(fn->arg_type); i++) {
+		if (fn->arg_type[i] == ARG_PTR_TO_BTF_ID && !fn->arg_btf_id[i])
+			return false;
+
+		if (fn->arg_type[i] != ARG_PTR_TO_BTF_ID && fn->arg_btf_id[i])
+			return false;
+	}
+
+	return true;
+}
+
 static int check_func_proto(const struct bpf_func_proto *fn, int func_id)
 {
 	return check_raw_mode_ok(fn) &&
 	       check_arg_pair_ok(fn) &&
+	       check_btf_id_ok(fn) &&
 	       check_refcount_ok(fn, func_id) ? 0 : -EINVAL;
 }
 
@@ -4894,11 +5011,6 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
 	meta.func_id = func_id;
 	/* check args */
 	for (i = 0; i < 5; i++) {
-		if (!fn->check_btf_id) {
-			err = btf_resolve_helper_id(&env->log, fn, i);
-			if (err > 0)
-				meta.btf_id = err;
-		}
 		err = check_func_arg(env, i, &meta, fn);
 		if (err)
 			return err;
@@ -5317,6 +5429,10 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 			dst, reg_type_str[ptr_reg->type]);
 		return -EACCES;
 	case CONST_PTR_TO_MAP:
+		/* smin_val represents the known value */
+		if (known && smin_val == 0 && opcode == BPF_ADD)
+			break;
+		/* fall-through */
 	case PTR_TO_PACKET_END:
 	case PTR_TO_SOCKET:
 	case PTR_TO_SOCKET_OR_NULL:
@@ -5732,8 +5848,7 @@ static void scalar_min_max_and(struct bpf_reg_state *dst_reg,
 	u64 umax_val = src_reg->umax_value;
 
 	if (src_known && dst_known) {
-		__mark_reg_known(dst_reg, dst_reg->var_off.value &
-					  src_reg->var_off.value);
+		__mark_reg_known(dst_reg, dst_reg->var_off.value);
 		return;
 	}
 
@@ -5803,8 +5918,7 @@ static void scalar_min_max_or(struct bpf_reg_state *dst_reg,
 	u64 umin_val = src_reg->umin_value;
 
 	if (src_known && dst_known) {
-		__mark_reg_known(dst_reg, dst_reg->var_off.value |
-					  src_reg->var_off.value);
+		__mark_reg_known(dst_reg, dst_reg->var_off.value);
 		return;
 	}
 
@@ -7461,18 +7575,6 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
 		return -EINVAL;
 	}
 
-	if (env->subprog_cnt > 1) {
-		/* when program has LD_ABS insn JITs and interpreter assume
-		 * that r1 == ctx == skb which is not the case for callees
-		 * that can have arbitrary arguments. It's problematic
-		 * for main prog as well since JITs would need to analyze
-		 * all functions in order to make proper register save/restore
-		 * decisions in the main prog. Hence disallow LD_ABS with calls
-		 */
-		verbose(env, "BPF_LD_[ABS|IND] instructions cannot be mixed with bpf-to-bpf calls\n");
-		return -EINVAL;
-	}
-
 	if (insn->dst_reg != BPF_REG_0 || insn->off != 0 ||
 	    BPF_SIZE(insn->code) == BPF_DW ||
 	    (mode == BPF_ABS && insn->src_reg != BPF_REG_0)) {
@@ -7883,6 +7985,23 @@ err_free:
 	return ret;
 }
 
+static int check_abnormal_return(struct bpf_verifier_env *env)
+{
+	int i;
+
+	for (i = 1; i < env->subprog_cnt; i++) {
+		if (env->subprog_info[i].has_ld_abs) {
+			verbose(env, "LD_ABS is not allowed in subprogs without BTF\n");
+			return -EINVAL;
+		}
+		if (env->subprog_info[i].has_tail_call) {
+			verbose(env, "tail_call is not allowed in subprogs without BTF\n");
+			return -EINVAL;
+		}
+	}
+	return 0;
+}
+
 /* The minimum supported BTF func info size */
 #define MIN_BPF_FUNCINFO_SIZE	8
 #define MAX_FUNCINFO_REC_SIZE	252
@@ -7891,20 +8010,24 @@ static int check_btf_func(struct bpf_verifier_env *env,
 			  const union bpf_attr *attr,
 			  union bpf_attr __user *uattr)
 {
+	const struct btf_type *type, *func_proto, *ret_type;
 	u32 i, nfuncs, urec_size, min_size;
 	u32 krec_size = sizeof(struct bpf_func_info);
 	struct bpf_func_info *krecord;
 	struct bpf_func_info_aux *info_aux = NULL;
-	const struct btf_type *type;
 	struct bpf_prog *prog;
 	const struct btf *btf;
 	void __user *urecord;
 	u32 prev_offset = 0;
+	bool scalar_return;
 	int ret = -ENOMEM;
 
 	nfuncs = attr->func_info_cnt;
-	if (!nfuncs)
+	if (!nfuncs) {
+		if (check_abnormal_return(env))
+			return -EINVAL;
 		return 0;
+	}
 
 	if (nfuncs != env->subprog_cnt) {
 		verbose(env, "number of funcs in func_info doesn't match number of subprogs\n");
@@ -7952,25 +8075,23 @@ static int check_btf_func(struct bpf_verifier_env *env,
 		}
 
 		/* check insn_off */
+		ret = -EINVAL;
 		if (i == 0) {
 			if (krecord[i].insn_off) {
 				verbose(env,
 					"nonzero insn_off %u for the first func info record",
 					krecord[i].insn_off);
-				ret = -EINVAL;
 				goto err_free;
 			}
 		} else if (krecord[i].insn_off <= prev_offset) {
 			verbose(env,
 				"same or smaller insn offset (%u) than previous func info record (%u)",
 				krecord[i].insn_off, prev_offset);
-			ret = -EINVAL;
 			goto err_free;
 		}
 
 		if (env->subprog_info[i].start != krecord[i].insn_off) {
 			verbose(env, "func_info BTF section doesn't match subprog layout in BPF program\n");
-			ret = -EINVAL;
 			goto err_free;
 		}
 
@@ -7979,10 +8100,26 @@ static int check_btf_func(struct bpf_verifier_env *env,
 		if (!type || !btf_type_is_func(type)) {
 			verbose(env, "invalid type id %d in func info",
 				krecord[i].type_id);
-			ret = -EINVAL;
 			goto err_free;
 		}
 		info_aux[i].linkage = BTF_INFO_VLEN(type->info);
+
+		func_proto = btf_type_by_id(btf, type->type);
+		if (unlikely(!func_proto || !btf_type_is_func_proto(func_proto)))
+			/* btf_func_check() already verified it during BTF load */
+			goto err_free;
+		ret_type = btf_type_skip_modifiers(btf, func_proto->type, NULL);
+		scalar_return =
+			btf_type_is_small_int(ret_type) || btf_type_is_enum(ret_type);
+		if (i && !scalar_return && env->subprog_info[i].has_ld_abs) {
+			verbose(env, "LD_ABS is only allowed in functions that return 'int'.\n");
+			goto err_free;
+		}
+		if (i && !scalar_return && env->subprog_info[i].has_tail_call) {
+			verbose(env, "tail_call is only allowed in functions that return 'int'.\n");
+			goto err_free;
+		}
+
 		prev_offset = krecord[i].insn_off;
 		urecord += urec_size;
 	}
@@ -8143,8 +8280,11 @@ static int check_btf_info(struct bpf_verifier_env *env,
 	struct btf *btf;
 	int err;
 
-	if (!attr->func_info_cnt && !attr->line_info_cnt)
+	if (!attr->func_info_cnt && !attr->line_info_cnt) {
+		if (check_abnormal_return(env))
+			return -EINVAL;
 		return 0;
+	}
 
 	btf = btf_get_by_fd(attr->prog_btf_fd);
 	if (IS_ERR(btf))
@@ -9619,6 +9759,18 @@ static void adjust_subprog_starts(struct bpf_verifier_env *env, u32 off, u32 len
 	}
 }
 
+static void adjust_poke_descs(struct bpf_prog *prog, u32 len)
+{
+	struct bpf_jit_poke_descriptor *tab = prog->aux->poke_tab;
+	int i, sz = prog->aux->size_poke_tab;
+	struct bpf_jit_poke_descriptor *desc;
+
+	for (i = 0; i < sz; i++) {
+		desc = &tab[i];
+		desc->insn_idx += len - 1;
+	}
+}
+
 static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 off,
 					    const struct bpf_insn *patch, u32 len)
 {
@@ -9635,6 +9787,7 @@ static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 of
 	if (adjust_insn_aux_data(env, new_prog, off, len))
 		return NULL;
 	adjust_subprog_starts(env, off, len);
+	adjust_poke_descs(new_prog, len);
 	return new_prog;
 }
 
@@ -10165,6 +10318,7 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 {
 	struct bpf_prog *prog = env->prog, **func, *tmp;
 	int i, j, subprog_start, subprog_end = 0, len, subprog;
+	struct bpf_map *map_ptr;
 	struct bpf_insn *insn;
 	void *old_bpf_func;
 	int err, num_exentries;
@@ -10232,6 +10386,31 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 		func[i]->aux->btf = prog->aux->btf;
 		func[i]->aux->func_info = prog->aux->func_info;
 
+		for (j = 0; j < prog->aux->size_poke_tab; j++) {
+			u32 insn_idx = prog->aux->poke_tab[j].insn_idx;
+			int ret;
+
+			if (!(insn_idx >= subprog_start &&
+			      insn_idx <= subprog_end))
+				continue;
+
+			ret = bpf_jit_add_poke_descriptor(func[i],
+							  &prog->aux->poke_tab[j]);
+			if (ret < 0) {
+				verbose(env, "adding tail call poke descriptor failed\n");
+				goto out_free;
+			}
+
+			func[i]->insnsi[insn_idx - subprog_start].imm = ret + 1;
+
+			map_ptr = func[i]->aux->poke_tab[ret].tail_call.map;
+			ret = map_ptr->ops->map_poke_track(map_ptr, func[i]->aux);
+			if (ret < 0) {
+				verbose(env, "tracking tail call prog failed\n");
+				goto out_free;
+			}
+		}
+
 		/* Use bpf_prog_F_tag to indicate functions in stack traces.
 		 * Long term would need debug info to populate names
 		 */
@@ -10250,6 +10429,7 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 				num_exentries++;
 		}
 		func[i]->aux->num_exentries = num_exentries;
+		func[i]->aux->tail_call_reachable = env->subprog_info[i].tail_call_reachable;
 		func[i] = bpf_int_jit_compile(func[i]);
 		if (!func[i]->jited) {
 			err = -ENOTSUPP;
@@ -10257,6 +10437,19 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 		}
 		cond_resched();
 	}
+
+	/* Untrack main program's aux structs so that during map_poke_run()
+	 * we will not stumble upon the unfilled poke descriptors; each
+	 * of the main program's poke descs got distributed across subprogs
+	 * and got tracked onto map, so we are sure that none of them will
+	 * be missed after the operation below
+	 */
+	for (i = 0; i < prog->aux->size_poke_tab; i++) {
+		map_ptr = prog->aux->poke_tab[i].tail_call.map;
+
+		map_ptr->ops->map_poke_untrack(map_ptr, prog->aux);
+	}
+
 	/* at this point all bpf functions were successfully JITed
 	 * now populate all bpf_calls with correct addresses and
 	 * run last pass of JIT
@@ -10325,9 +10518,16 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 	bpf_prog_free_unused_jited_linfo(prog);
 	return 0;
 out_free:
-	for (i = 0; i < env->subprog_cnt; i++)
-		if (func[i])
-			bpf_jit_free(func[i]);
+	for (i = 0; i < env->subprog_cnt; i++) {
+		if (!func[i])
+			continue;
+
+		for (j = 0; j < func[i]->aux->size_poke_tab; j++) {
+			map_ptr = func[i]->aux->poke_tab[j].tail_call.map;
+			map_ptr->ops->map_poke_untrack(map_ptr, func[i]->aux);
+		}
+		bpf_jit_free(func[i]);
+	}
 	kfree(func);
 out_undo_insn:
 	/* cleanup main prog to be interpreted */
@@ -10361,6 +10561,13 @@ static int fixup_call_args(struct bpf_verifier_env *env)
 			return err;
 	}
 #ifndef CONFIG_BPF_JIT_ALWAYS_ON
+	if (env->subprog_cnt > 1 && env->prog->aux->tail_call_reachable) {
+		/* When JIT fails the progs with bpf2bpf calls and tail_calls
+		 * have to be rejected, since interpreter doesn't support them yet.
+		 */
+		verbose(env, "tail_calls are not allowed in non-JITed programs with bpf-to-bpf calls\n");
+		return -EINVAL;
+	}
 	for (i = 0; i < prog->len; i++, insn++) {
 		if (insn->code != (BPF_JMP | BPF_CALL) ||
 		    insn->src_reg != BPF_PSEUDO_CALL)
@@ -10524,8 +10731,9 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env)
 			 * the program array.
 			 */
 			prog->cb_access = 1;
-			env->prog->aux->stack_depth = MAX_BPF_STACK;
-			env->prog->aux->max_pkt_offset = MAX_PACKET_OFF;
+			if (!allow_tail_call_in_subprogs(env))
+				prog->aux->stack_depth = MAX_BPF_STACK;
+			prog->aux->max_pkt_offset = MAX_PACKET_OFF;
 
 			/* mark bpf_tail_call as different opcode to avoid
 			 * conditional branch in the interpeter for every normal
@@ -10545,6 +10753,7 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env)
 					.reason = BPF_POKE_REASON_TAIL_CALL,
 					.tail_call.map = BPF_MAP_PTR(aux->map_ptr_state),
 					.tail_call.key = bpf_map_key_immediate(aux),
+					.insn_idx = i + delta,
 				};
 
 				ret = bpf_jit_add_poke_descriptor(prog, &desc);
@@ -10993,11 +11202,10 @@ static int check_struct_ops_btf_id(struct bpf_verifier_env *env)
 }
 #define SECURITY_PREFIX "security_"
 
-static int check_attach_modify_return(struct bpf_prog *prog, unsigned long addr)
+static int check_attach_modify_return(unsigned long addr, const char *func_name)
 {
 	if (within_error_injection_list(addr) ||
-	    !strncmp(SECURITY_PREFIX, prog->aux->attach_func_name,
-		     sizeof(SECURITY_PREFIX) - 1))
+	    !strncmp(SECURITY_PREFIX, func_name, sizeof(SECURITY_PREFIX) - 1))
 		return 0;
 
 	return -EINVAL;
@@ -11034,55 +11242,39 @@ static int check_non_sleepable_error_inject(u32 btf_id)
 	return btf_id_set_contains(&btf_non_sleepable_error_inject, btf_id);
 }
 
-static int check_attach_btf_id(struct bpf_verifier_env *env)
+int bpf_check_attach_target(struct bpf_verifier_log *log,
+			    const struct bpf_prog *prog,
+			    const struct bpf_prog *tgt_prog,
+			    u32 btf_id,
+			    struct bpf_attach_target_info *tgt_info)
 {
-	struct bpf_prog *prog = env->prog;
 	bool prog_extension = prog->type == BPF_PROG_TYPE_EXT;
-	struct bpf_prog *tgt_prog = prog->aux->linked_prog;
-	u32 btf_id = prog->aux->attach_btf_id;
 	const char prefix[] = "btf_trace_";
-	struct btf_func_model fmodel;
 	int ret = 0, subprog = -1, i;
-	struct bpf_trampoline *tr;
 	const struct btf_type *t;
 	bool conservative = true;
 	const char *tname;
 	struct btf *btf;
-	long addr;
-	u64 key;
-
-	if (prog->aux->sleepable && prog->type != BPF_PROG_TYPE_TRACING &&
-	    prog->type != BPF_PROG_TYPE_LSM) {
-		verbose(env, "Only fentry/fexit/fmod_ret and lsm programs can be sleepable\n");
-		return -EINVAL;
-	}
-
-	if (prog->type == BPF_PROG_TYPE_STRUCT_OPS)
-		return check_struct_ops_btf_id(env);
-
-	if (prog->type != BPF_PROG_TYPE_TRACING &&
-	    prog->type != BPF_PROG_TYPE_LSM &&
-	    !prog_extension)
-		return 0;
+	long addr = 0;
 
 	if (!btf_id) {
-		verbose(env, "Tracing programs must provide btf_id\n");
+		bpf_log(log, "Tracing programs must provide btf_id\n");
 		return -EINVAL;
 	}
-	btf = bpf_prog_get_target_btf(prog);
+	btf = tgt_prog ? tgt_prog->aux->btf : btf_vmlinux;
 	if (!btf) {
-		verbose(env,
+		bpf_log(log,
 			"FENTRY/FEXIT program can only be attached to another program annotated with BTF\n");
 		return -EINVAL;
 	}
 	t = btf_type_by_id(btf, btf_id);
 	if (!t) {
-		verbose(env, "attach_btf_id %u is invalid\n", btf_id);
+		bpf_log(log, "attach_btf_id %u is invalid\n", btf_id);
 		return -EINVAL;
 	}
 	tname = btf_name_by_offset(btf, t->name_off);
 	if (!tname) {
-		verbose(env, "attach_btf_id %u doesn't have a name\n", btf_id);
+		bpf_log(log, "attach_btf_id %u doesn't have a name\n", btf_id);
 		return -EINVAL;
 	}
 	if (tgt_prog) {
@@ -11094,26 +11286,24 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 				break;
 			}
 		if (subprog == -1) {
-			verbose(env, "Subprog %s doesn't exist\n", tname);
+			bpf_log(log, "Subprog %s doesn't exist\n", tname);
 			return -EINVAL;
 		}
 		conservative = aux->func_info_aux[subprog].unreliable;
 		if (prog_extension) {
 			if (conservative) {
-				verbose(env,
+				bpf_log(log,
 					"Cannot replace static functions\n");
 				return -EINVAL;
 			}
 			if (!prog->jit_requested) {
-				verbose(env,
+				bpf_log(log,
 					"Extension programs should be JITed\n");
 				return -EINVAL;
 			}
-			env->ops = bpf_verifier_ops[tgt_prog->type];
-			prog->expected_attach_type = tgt_prog->expected_attach_type;
 		}
 		if (!tgt_prog->jited) {
-			verbose(env, "Can attach to only JITed progs\n");
+			bpf_log(log, "Can attach to only JITed progs\n");
 			return -EINVAL;
 		}
 		if (tgt_prog->type == prog->type) {
@@ -11121,7 +11311,7 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 			 * Cannot attach program extension to another extension.
 			 * It's ok to attach fentry/fexit to extension program.
 			 */
-			verbose(env, "Cannot recursively attach\n");
+			bpf_log(log, "Cannot recursively attach\n");
 			return -EINVAL;
 		}
 		if (tgt_prog->type == BPF_PROG_TYPE_TRACING &&
@@ -11143,32 +11333,30 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 			 * reasonable stack size. Hence extending fentry is not
 			 * allowed.
 			 */
-			verbose(env, "Cannot extend fentry/fexit\n");
+			bpf_log(log, "Cannot extend fentry/fexit\n");
 			return -EINVAL;
 		}
-		key = ((u64)aux->id) << 32 | btf_id;
 	} else {
 		if (prog_extension) {
-			verbose(env, "Cannot replace kernel functions\n");
+			bpf_log(log, "Cannot replace kernel functions\n");
 			return -EINVAL;
 		}
-		key = btf_id;
 	}
 
 	switch (prog->expected_attach_type) {
 	case BPF_TRACE_RAW_TP:
 		if (tgt_prog) {
-			verbose(env,
+			bpf_log(log,
 				"Only FENTRY/FEXIT progs are attachable to another BPF prog\n");
 			return -EINVAL;
 		}
 		if (!btf_type_is_typedef(t)) {
-			verbose(env, "attach_btf_id %u is not a typedef\n",
+			bpf_log(log, "attach_btf_id %u is not a typedef\n",
 				btf_id);
 			return -EINVAL;
 		}
 		if (strncmp(prefix, tname, sizeof(prefix) - 1)) {
-			verbose(env, "attach_btf_id %u points to wrong type name %s\n",
+			bpf_log(log, "attach_btf_id %u points to wrong type name %s\n",
 				btf_id, tname);
 			return -EINVAL;
 		}
@@ -11182,29 +11370,20 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 			/* should never happen in valid vmlinux build */
 			return -EINVAL;
 
-		/* remember two read only pointers that are valid for
-		 * the life time of the kernel
-		 */
-		prog->aux->attach_func_name = tname;
-		prog->aux->attach_func_proto = t;
-		prog->aux->attach_btf_trace = true;
-		return 0;
+		break;
 	case BPF_TRACE_ITER:
 		if (!btf_type_is_func(t)) {
-			verbose(env, "attach_btf_id %u is not a function\n",
+			bpf_log(log, "attach_btf_id %u is not a function\n",
 				btf_id);
 			return -EINVAL;
 		}
 		t = btf_type_by_id(btf, t->type);
 		if (!btf_type_is_func_proto(t))
 			return -EINVAL;
-		prog->aux->attach_func_name = tname;
-		prog->aux->attach_func_proto = t;
-		if (!bpf_iter_prog_supported(prog))
-			return -EINVAL;
-		ret = btf_distill_func_proto(&env->log, btf, t,
-					     tname, &fmodel);
-		return ret;
+		ret = btf_distill_func_proto(log, btf, t, tname, &tgt_info->fmodel);
+		if (ret)
+			return ret;
+		break;
 	default:
 		if (!prog_extension)
 			return -EINVAL;
@@ -11213,42 +11392,30 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 	case BPF_LSM_MAC:
 	case BPF_TRACE_FENTRY:
 	case BPF_TRACE_FEXIT:
-		prog->aux->attach_func_name = tname;
-		if (prog->type == BPF_PROG_TYPE_LSM) {
-			ret = bpf_lsm_verify_prog(&env->log, prog);
-			if (ret < 0)
-				return ret;
-		}
-
 		if (!btf_type_is_func(t)) {
-			verbose(env, "attach_btf_id %u is not a function\n",
+			bpf_log(log, "attach_btf_id %u is not a function\n",
 				btf_id);
 			return -EINVAL;
 		}
 		if (prog_extension &&
-		    btf_check_type_match(env, prog, btf, t))
+		    btf_check_type_match(log, prog, btf, t))
 			return -EINVAL;
 		t = btf_type_by_id(btf, t->type);
 		if (!btf_type_is_func_proto(t))
 			return -EINVAL;
-		tr = bpf_trampoline_lookup(key);
-		if (!tr)
-			return -ENOMEM;
-		/* t is either vmlinux type or another program's type */
-		prog->aux->attach_func_proto = t;
-		mutex_lock(&tr->mutex);
-		if (tr->func.addr) {
-			prog->aux->trampoline = tr;
-			goto out;
-		}
-		if (tgt_prog && conservative) {
-			prog->aux->attach_func_proto = NULL;
+
+		if ((prog->aux->saved_dst_prog_type || prog->aux->saved_dst_attach_type) &&
+		    (!tgt_prog || prog->aux->saved_dst_prog_type != tgt_prog->type ||
+		     prog->aux->saved_dst_attach_type != tgt_prog->expected_attach_type))
+			return -EINVAL;
+
+		if (tgt_prog && conservative)
 			t = NULL;
-		}
-		ret = btf_distill_func_proto(&env->log, btf, t,
-					     tname, &tr->func.model);
+
+		ret = btf_distill_func_proto(log, btf, t, tname, &tgt_info->fmodel);
 		if (ret < 0)
-			goto out;
+			return ret;
+
 		if (tgt_prog) {
 			if (subprog == 0)
 				addr = (long) tgt_prog->bpf_func;
@@ -11257,11 +11424,10 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 		} else {
 			addr = kallsyms_lookup_name(tname);
 			if (!addr) {
-				verbose(env,
+				bpf_log(log,
 					"The address of function %s cannot be found\n",
 					tname);
-				ret = -ENOENT;
-				goto out;
+				return -ENOENT;
 			}
 		}
 
@@ -11286,25 +11452,109 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 			default:
 				break;
 			}
-			if (ret)
-				verbose(env, "%s is not sleepable\n",
-					prog->aux->attach_func_name);
+			if (ret) {
+				bpf_log(log, "%s is not sleepable\n", tname);
+				return ret;
+			}
 		} else if (prog->expected_attach_type == BPF_MODIFY_RETURN) {
-			ret = check_attach_modify_return(prog, addr);
-			if (ret)
-				verbose(env, "%s() is not modifiable\n",
-					prog->aux->attach_func_name);
+			if (tgt_prog) {
+				bpf_log(log, "can't modify return codes of BPF programs\n");
+				return -EINVAL;
+			}
+			ret = check_attach_modify_return(addr, tname);
+			if (ret) {
+				bpf_log(log, "%s() is not modifiable\n", tname);
+				return ret;
+			}
 		}
-		if (ret)
-			goto out;
-		tr->func.addr = (void *)addr;
-		prog->aux->trampoline = tr;
-out:
-		mutex_unlock(&tr->mutex);
-		if (ret)
-			bpf_trampoline_put(tr);
+
+		break;
+	}
+	tgt_info->tgt_addr = addr;
+	tgt_info->tgt_name = tname;
+	tgt_info->tgt_type = t;
+	return 0;
+}
+
+static int check_attach_btf_id(struct bpf_verifier_env *env)
+{
+	struct bpf_prog *prog = env->prog;
+	struct bpf_prog *tgt_prog = prog->aux->dst_prog;
+	struct bpf_attach_target_info tgt_info = {};
+	u32 btf_id = prog->aux->attach_btf_id;
+	struct bpf_trampoline *tr;
+	int ret;
+	u64 key;
+
+	if (prog->aux->sleepable && prog->type != BPF_PROG_TYPE_TRACING &&
+	    prog->type != BPF_PROG_TYPE_LSM) {
+		verbose(env, "Only fentry/fexit/fmod_ret and lsm programs can be sleepable\n");
+		return -EINVAL;
+	}
+
+	if (prog->type == BPF_PROG_TYPE_STRUCT_OPS)
+		return check_struct_ops_btf_id(env);
+
+	if (prog->type != BPF_PROG_TYPE_TRACING &&
+	    prog->type != BPF_PROG_TYPE_LSM &&
+	    prog->type != BPF_PROG_TYPE_EXT)
+		return 0;
+
+	ret = bpf_check_attach_target(&env->log, prog, tgt_prog, btf_id, &tgt_info);
+	if (ret)
 		return ret;
+
+	if (tgt_prog && prog->type == BPF_PROG_TYPE_EXT) {
+		/* to make freplace equivalent to their targets, they need to
+		 * inherit env->ops and expected_attach_type for the rest of the
+		 * verification
+		 */
+		env->ops = bpf_verifier_ops[tgt_prog->type];
+		prog->expected_attach_type = tgt_prog->expected_attach_type;
+	}
+
+	/* store info about the attachment target that will be used later */
+	prog->aux->attach_func_proto = tgt_info.tgt_type;
+	prog->aux->attach_func_name = tgt_info.tgt_name;
+
+	if (tgt_prog) {
+		prog->aux->saved_dst_prog_type = tgt_prog->type;
+		prog->aux->saved_dst_attach_type = tgt_prog->expected_attach_type;
 	}
+
+	if (prog->expected_attach_type == BPF_TRACE_RAW_TP) {
+		prog->aux->attach_btf_trace = true;
+		return 0;
+	} else if (prog->expected_attach_type == BPF_TRACE_ITER) {
+		if (!bpf_iter_prog_supported(prog))
+			return -EINVAL;
+		return 0;
+	}
+
+	if (prog->type == BPF_PROG_TYPE_LSM) {
+		ret = bpf_lsm_verify_prog(&env->log, prog);
+		if (ret < 0)
+			return ret;
+	}
+
+	key = bpf_trampoline_compute_key(tgt_prog, btf_id);
+	tr = bpf_trampoline_get(key, &tgt_info);
+	if (!tr)
+		return -ENOMEM;
+
+	prog->aux->dst_trampoline = tr;
+	return 0;
+}
+
+struct btf *bpf_get_btf_vmlinux(void)
+{
+	if (!btf_vmlinux && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) {
+		mutex_lock(&bpf_verifier_lock);
+		if (!btf_vmlinux)
+			btf_vmlinux = btf_parse_vmlinux();
+		mutex_unlock(&bpf_verifier_lock);
+	}
+	return btf_vmlinux;
 }
 
 int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
@@ -11340,12 +11590,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
 	env->ops = bpf_verifier_ops[env->prog->type];
 	is_priv = bpf_capable();
 
-	if (!btf_vmlinux && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) {
-		mutex_lock(&bpf_verifier_lock);
-		if (!btf_vmlinux)
-			btf_vmlinux = btf_parse_vmlinux();
-		mutex_unlock(&bpf_verifier_lock);
-	}
+	bpf_get_btf_vmlinux();
 
 	/* grab the mutex to protect few globals used by verifier */
 	if (!is_priv)
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index fcae019158ca..6fdb6105e6d6 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -60,31 +60,56 @@ static long syscall_trace_enter(struct pt_regs *regs, long syscall,
 			return ret;
 	}
 
+	/* Either of the above might have changed the syscall number */
+	syscall = syscall_get_nr(current, regs);
+
 	if (unlikely(ti_work & _TIF_SYSCALL_TRACEPOINT))
 		trace_sys_enter(regs, syscall);
 
 	syscall_enter_audit(regs, syscall);
 
-	/* The above might have changed the syscall number */
-	return ret ? : syscall_get_nr(current, regs);
+	return ret ? : syscall;
 }
 
-noinstr long syscall_enter_from_user_mode(struct pt_regs *regs, long syscall)
+static __always_inline long
+__syscall_enter_from_user_work(struct pt_regs *regs, long syscall)
 {
 	unsigned long ti_work;
 
-	enter_from_user_mode(regs);
-	instrumentation_begin();
-
-	local_irq_enable();
 	ti_work = READ_ONCE(current_thread_info()->flags);
 	if (ti_work & SYSCALL_ENTER_WORK)
 		syscall = syscall_trace_enter(regs, syscall, ti_work);
-	instrumentation_end();
 
 	return syscall;
 }
 
+long syscall_enter_from_user_mode_work(struct pt_regs *regs, long syscall)
+{
+	return __syscall_enter_from_user_work(regs, syscall);
+}
+
+noinstr long syscall_enter_from_user_mode(struct pt_regs *regs, long syscall)
+{
+	long ret;
+
+	enter_from_user_mode(regs);
+
+	instrumentation_begin();
+	local_irq_enable();
+	ret = __syscall_enter_from_user_work(regs, syscall);
+	instrumentation_end();
+
+	return ret;
+}
+
+noinstr void syscall_enter_from_user_mode_prepare(struct pt_regs *regs)
+{
+	enter_from_user_mode(regs);
+	instrumentation_begin();
+	local_irq_enable();
+	instrumentation_end();
+}
+
 /**
  * exit_to_user_mode - Fixup state when exiting to user mode
  *
diff --git a/kernel/fork.c b/kernel/fork.c
index 4d32190861bd..49677d668de4 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -3014,7 +3014,7 @@ int unshare_files(struct files_struct **displaced)
 }
 
 int sysctl_max_threads(struct ctl_table *table, int write,
-		       void __user *buffer, size_t *lenp, loff_t *ppos)
+		       void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct ctl_table t;
 	int ret;
diff --git a/kernel/gcov/Kconfig b/kernel/gcov/Kconfig
index bb4b680e8455..3110c77230c7 100644
--- a/kernel/gcov/Kconfig
+++ b/kernel/gcov/Kconfig
@@ -4,7 +4,6 @@ menu "GCOV-based kernel profiling"
 config GCOV_KERNEL
 	bool "Enable gcov-based kernel profiling"
 	depends on DEBUG_FS
-	depends on !CC_IS_GCC || GCC_VERSION < 100000
 	select CONSTRUCTORS if !UML
 	default n
 	help
diff --git a/kernel/gcov/gcc_4_7.c b/kernel/gcov/gcc_4_7.c
index 908fdf5098c3..53c67c87f141 100644
--- a/kernel/gcov/gcc_4_7.c
+++ b/kernel/gcov/gcc_4_7.c
@@ -19,7 +19,9 @@
 #include <linux/vmalloc.h>
 #include "gcov.h"
 
-#if (__GNUC__ >= 7)
+#if (__GNUC__ >= 10)
+#define GCOV_COUNTERS			8
+#elif (__GNUC__ >= 7)
 #define GCOV_COUNTERS			9
 #elif (__GNUC__ > 5) || (__GNUC__ == 5 && __GNUC_MINOR__ >= 1)
 #define GCOV_COUNTERS			10
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 287b263c9cb9..e995541d277d 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -2140,6 +2140,9 @@ static void kill_kprobe(struct kprobe *p)
 
 	lockdep_assert_held(&kprobe_mutex);
 
+	if (WARN_ON_ONCE(kprobe_gone(p)))
+		return;
+
 	p->flags |= KPROBE_FLAG_GONE;
 	if (kprobe_aggrprobe(p)) {
 		/*
@@ -2159,9 +2162,10 @@ static void kill_kprobe(struct kprobe *p)
 
 	/*
 	 * The module is going away. We should disarm the kprobe which
-	 * is using ftrace.
+	 * is using ftrace, because ftrace framework is still available at
+	 * MODULE_STATE_GOING notification.
 	 */
-	if (kprobe_ftrace(p))
+	if (kprobe_ftrace(p) && !kprobe_disabled(p) && !kprobes_all_disarmed)
 		disarm_kprobe_ftrace(p);
 }
 
@@ -2419,7 +2423,10 @@ static int kprobes_module_callback(struct notifier_block *nb,
 	mutex_lock(&kprobe_mutex);
 	for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
 		head = &kprobe_table[i];
-		hlist_for_each_entry(p, head, hlist)
+		hlist_for_each_entry(p, head, hlist) {
+			if (kprobe_gone(p))
+				continue;
+
 			if (within_module_init((unsigned long)p->addr, mod) ||
 			    (checkcore &&
 			     within_module_core((unsigned long)p->addr, mod))) {
@@ -2436,6 +2443,7 @@ static int kprobes_module_callback(struct notifier_block *nb,
 				 */
 				kill_kprobe(p);
 			}
+		}
 	}
 	if (val == MODULE_STATE_GOING)
 		remove_module_kprobe_blacklist(mod);
@@ -2452,6 +2460,28 @@ static struct notifier_block kprobe_module_nb = {
 extern unsigned long __start_kprobe_blacklist[];
 extern unsigned long __stop_kprobe_blacklist[];
 
+void kprobe_free_init_mem(void)
+{
+	void *start = (void *)(&__init_begin);
+	void *end = (void *)(&__init_end);
+	struct hlist_head *head;
+	struct kprobe *p;
+	int i;
+
+	mutex_lock(&kprobe_mutex);
+
+	/* Kill all kprobes on initmem */
+	for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
+		head = &kprobe_table[i];
+		hlist_for_each_entry(p, head, hlist) {
+			if (start <= (void *)p->addr && (void *)p->addr < end)
+				kill_kprobe(p);
+		}
+	}
+
+	mutex_unlock(&kprobe_mutex);
+}
+
 static int __init init_kprobes(void)
 {
 	int i, err = 0;
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 54b74fabf40c..2facbbd146ec 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -3969,13 +3969,18 @@ static int separate_irq_context(struct task_struct *curr,
 static int mark_lock(struct task_struct *curr, struct held_lock *this,
 			     enum lock_usage_bit new_bit)
 {
-	unsigned int new_mask = 1 << new_bit, ret = 1;
+	unsigned int old_mask, new_mask, ret = 1;
 
 	if (new_bit >= LOCK_USAGE_STATES) {
 		DEBUG_LOCKS_WARN_ON(1);
 		return 0;
 	}
 
+	if (new_bit == LOCK_USED && this->read)
+		new_bit = LOCK_USED_READ;
+
+	new_mask = 1 << new_bit;
+
 	/*
 	 * If already set then do not dirty the cacheline,
 	 * nor do any checks:
@@ -3988,13 +3993,22 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this,
 	/*
 	 * Make sure we didn't race:
 	 */
-	if (unlikely(hlock_class(this)->usage_mask & new_mask)) {
-		graph_unlock();
-		return 1;
-	}
+	if (unlikely(hlock_class(this)->usage_mask & new_mask))
+		goto unlock;
 
+	old_mask = hlock_class(this)->usage_mask;
 	hlock_class(this)->usage_mask |= new_mask;
 
+	/*
+	 * Save one usage_traces[] entry and map both LOCK_USED and
+	 * LOCK_USED_READ onto the same entry.
+	 */
+	if (new_bit == LOCK_USED || new_bit == LOCK_USED_READ) {
+		if (old_mask & (LOCKF_USED | LOCKF_USED_READ))
+			goto unlock;
+		new_bit = LOCK_USED;
+	}
+
 	if (!(hlock_class(this)->usage_traces[new_bit] = save_trace()))
 		return 0;
 
@@ -4008,6 +4022,7 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this,
 			return 0;
 	}
 
+unlock:
 	graph_unlock();
 
 	/*
@@ -4942,12 +4957,20 @@ static void verify_lock_unused(struct lockdep_map *lock, struct held_lock *hlock
 {
 #ifdef CONFIG_PROVE_LOCKING
 	struct lock_class *class = look_up_lock_class(lock, subclass);
+	unsigned long mask = LOCKF_USED;
 
 	/* if it doesn't have a class (yet), it certainly hasn't been used yet */
 	if (!class)
 		return;
 
-	if (!(class->usage_mask & LOCK_USED))
+	/*
+	 * READ locks only conflict with USED, such that if we only ever use
+	 * READ locks, there is no deadlock possible -- RCU.
+	 */
+	if (!hlock->read)
+		mask |= LOCKF_USED_READ;
+
+	if (!(class->usage_mask & mask))
 		return;
 
 	hlock->class_idx = class - lock_classes;
diff --git a/kernel/locking/lockdep_internals.h b/kernel/locking/lockdep_internals.h
index baca699b94e9..b0be1560ed17 100644
--- a/kernel/locking/lockdep_internals.h
+++ b/kernel/locking/lockdep_internals.h
@@ -19,6 +19,7 @@ enum lock_usage_bit {
 #include "lockdep_states.h"
 #undef LOCKDEP_STATE
 	LOCK_USED,
+	LOCK_USED_READ,
 	LOCK_USAGE_STATES
 };
 
@@ -40,6 +41,7 @@ enum {
 #include "lockdep_states.h"
 #undef LOCKDEP_STATE
 	__LOCKF(USED)
+	__LOCKF(USED_READ)
 };
 
 #define LOCKDEP_STATE(__STATE)	LOCKF_ENABLED_##__STATE |
diff --git a/kernel/locking/percpu-rwsem.c b/kernel/locking/percpu-rwsem.c
index 8bbafe3e5203..70a32a576f3f 100644
--- a/kernel/locking/percpu-rwsem.c
+++ b/kernel/locking/percpu-rwsem.c
@@ -45,7 +45,7 @@ EXPORT_SYMBOL_GPL(percpu_free_rwsem);
 
 static bool __percpu_down_read_trylock(struct percpu_rw_semaphore *sem)
 {
-	__this_cpu_inc(*sem->read_count);
+	this_cpu_inc(*sem->read_count);
 
 	/*
 	 * Due to having preemption disabled the decrement happens on
@@ -71,7 +71,7 @@ static bool __percpu_down_read_trylock(struct percpu_rw_semaphore *sem)
 	if (likely(!atomic_read_acquire(&sem->block)))
 		return true;
 
-	__this_cpu_dec(*sem->read_count);
+	this_cpu_dec(*sem->read_count);
 
 	/* Prod writer to re-evaluate readers_active_check() */
 	rcuwait_wake_up(&sem->writer);
diff --git a/kernel/padata.c b/kernel/padata.c
index 16cb894dc272..d4d3ba6e1728 100644
--- a/kernel/padata.c
+++ b/kernel/padata.c
@@ -215,12 +215,13 @@ int padata_do_parallel(struct padata_shell *ps,
 	padata->pd = pd;
 	padata->cb_cpu = *cb_cpu;
 
-	rcu_read_unlock_bh();
-
 	spin_lock(&padata_works_lock);
 	padata->seq_nr = ++pd->seq_nr;
 	pw = padata_work_alloc();
 	spin_unlock(&padata_works_lock);
+
+	rcu_read_unlock_bh();
+
 	if (pw) {
 		padata_work_init(pw, padata_parallel_worker, padata, 0);
 		queue_work(pinst->parallel_wq, &pw->pw_work);
diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
index 835e2df8590a..d5d9f2d03e8a 100644
--- a/kernel/rcu/tasks.h
+++ b/kernel/rcu/tasks.h
@@ -28,6 +28,8 @@ typedef void (*postgp_func_t)(struct rcu_tasks *rtp);
  * @kthread_ptr: This flavor's grace-period/callback-invocation kthread.
  * @gp_func: This flavor's grace-period-wait function.
  * @gp_state: Grace period's most recent state transition (debugging).
+ * @gp_sleep: Per-grace-period sleep to prevent CPU-bound looping.
+ * @init_fract: Initial backoff sleep interval.
  * @gp_jiffies: Time of last @gp_state transition.
  * @gp_start: Most recent grace-period start in jiffies.
  * @n_gps: Number of grace periods completed since boot.
@@ -48,6 +50,8 @@ struct rcu_tasks {
 	struct wait_queue_head cbs_wq;
 	raw_spinlock_t cbs_lock;
 	int gp_state;
+	int gp_sleep;
+	int init_fract;
 	unsigned long gp_jiffies;
 	unsigned long gp_start;
 	unsigned long n_gps;
@@ -81,7 +85,7 @@ static struct rcu_tasks rt_name =					\
 DEFINE_STATIC_SRCU(tasks_rcu_exit_srcu);
 
 /* Avoid IPIing CPUs early in the grace period. */
-#define RCU_TASK_IPI_DELAY (HZ / 2)
+#define RCU_TASK_IPI_DELAY (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB) ? HZ / 2 : 0)
 static int rcu_task_ipi_delay __read_mostly = RCU_TASK_IPI_DELAY;
 module_param(rcu_task_ipi_delay, int, 0644);
 
@@ -231,7 +235,7 @@ static int __noreturn rcu_tasks_kthread(void *arg)
 			cond_resched();
 		}
 		/* Paranoid sleep to keep this from entering a tight loop */
-		schedule_timeout_idle(HZ/10);
+		schedule_timeout_idle(rtp->gp_sleep);
 
 		set_tasks_gp_state(rtp, RTGS_WAIT_CBS);
 	}
@@ -329,8 +333,10 @@ static void rcu_tasks_wait_gp(struct rcu_tasks *rtp)
 	 */
 	lastreport = jiffies;
 
-	/* Start off with HZ/10 wait and slowly back off to 1 HZ wait. */
-	fract = 10;
+	// Start off with initial wait and slowly back off to 1 HZ wait.
+	fract = rtp->init_fract;
+	if (fract > HZ)
+		fract = HZ;
 
 	for (;;) {
 		bool firstreport;
@@ -553,6 +559,8 @@ EXPORT_SYMBOL_GPL(rcu_barrier_tasks);
 
 static int __init rcu_spawn_tasks_kthread(void)
 {
+	rcu_tasks.gp_sleep = HZ / 10;
+	rcu_tasks.init_fract = 10;
 	rcu_tasks.pregp_func = rcu_tasks_pregp_step;
 	rcu_tasks.pertask_func = rcu_tasks_pertask;
 	rcu_tasks.postscan_func = rcu_tasks_postscan;
@@ -590,7 +598,7 @@ void exit_tasks_rcu_finish(void) __releases(&tasks_rcu_exit_srcu)
 }
 
 #else /* #ifdef CONFIG_TASKS_RCU */
-static void show_rcu_tasks_classic_gp_kthread(void) { }
+static inline void show_rcu_tasks_classic_gp_kthread(void) { }
 void exit_tasks_rcu_start(void) { }
 void exit_tasks_rcu_finish(void) { exit_tasks_rcu_finish_trace(current); }
 #endif /* #else #ifdef CONFIG_TASKS_RCU */
@@ -685,6 +693,7 @@ EXPORT_SYMBOL_GPL(rcu_barrier_tasks_rude);
 
 static int __init rcu_spawn_tasks_rude_kthread(void)
 {
+	rcu_tasks_rude.gp_sleep = HZ / 10;
 	rcu_spawn_tasks_kthread_generic(&rcu_tasks_rude);
 	return 0;
 }
@@ -745,9 +754,9 @@ static DEFINE_PER_CPU(bool, trc_ipi_to_cpu);
 
 // The number of detections of task quiescent state relying on
 // heavyweight readers executing explicit memory barriers.
-unsigned long n_heavy_reader_attempts;
-unsigned long n_heavy_reader_updates;
-unsigned long n_heavy_reader_ofl_updates;
+static unsigned long n_heavy_reader_attempts;
+static unsigned long n_heavy_reader_updates;
+static unsigned long n_heavy_reader_ofl_updates;
 
 void call_rcu_tasks_trace(struct rcu_head *rhp, rcu_callback_t func);
 DEFINE_RCU_TASKS(rcu_tasks_trace, rcu_tasks_wait_gp, call_rcu_tasks_trace,
@@ -821,6 +830,12 @@ static void trc_read_check_handler(void *t_in)
 		WRITE_ONCE(t->trc_reader_checked, true);
 		goto reset_ipi;
 	}
+	// If we are racing with an rcu_read_unlock_trace(), try again later.
+	if (unlikely(t->trc_reader_nesting < 0)) {
+		if (WARN_ON_ONCE(atomic_dec_and_test(&trc_n_readers_need_end)))
+			wake_up(&trc_wait);
+		goto reset_ipi;
+	}
 	WRITE_ONCE(t->trc_reader_checked, true);
 
 	// Get here if the task is in a read-side critical section.  Set
@@ -911,7 +926,8 @@ static void trc_wait_for_one_reader(struct task_struct *t,
 
 	// If currently running, send an IPI, either way, add to list.
 	trc_add_holdout(t, bhp);
-	if (task_curr(t) && time_after(jiffies, rcu_tasks_trace.gp_start + rcu_task_ipi_delay)) {
+	if (task_curr(t) &&
+	    time_after(jiffies + 1, rcu_tasks_trace.gp_start + rcu_task_ipi_delay)) {
 		// The task is currently running, so try IPIing it.
 		cpu = task_cpu(t);
 
@@ -1072,15 +1088,17 @@ static void rcu_tasks_trace_postgp(struct rcu_tasks *rtp)
 		if (ret)
 			break;  // Count reached zero.
 		// Stall warning time, so make a list of the offenders.
+		rcu_read_lock();
 		for_each_process_thread(g, t)
 			if (READ_ONCE(t->trc_reader_special.b.need_qs))
 				trc_add_holdout(t, &holdouts);
+		rcu_read_unlock();
 		firstreport = true;
-		list_for_each_entry_safe(t, g, &holdouts, trc_holdout_list)
-			if (READ_ONCE(t->trc_reader_special.b.need_qs)) {
+		list_for_each_entry_safe(t, g, &holdouts, trc_holdout_list) {
+			if (READ_ONCE(t->trc_reader_special.b.need_qs))
 				show_stalled_task_trace(t, &firstreport);
-				trc_del_holdout(t);
-			}
+			trc_del_holdout(t); // Release task_struct reference.
+		}
 		if (firstreport)
 			pr_err("INFO: rcu_tasks_trace detected stalls? (Counter/taskslist mismatch?)\n");
 		show_stalled_ipi_trace();
@@ -1163,6 +1181,17 @@ EXPORT_SYMBOL_GPL(rcu_barrier_tasks_trace);
 
 static int __init rcu_spawn_tasks_trace_kthread(void)
 {
+	if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB)) {
+		rcu_tasks_trace.gp_sleep = HZ / 10;
+		rcu_tasks_trace.init_fract = 10;
+	} else {
+		rcu_tasks_trace.gp_sleep = HZ / 200;
+		if (rcu_tasks_trace.gp_sleep <= 0)
+			rcu_tasks_trace.gp_sleep = 1;
+		rcu_tasks_trace.init_fract = HZ / 5;
+		if (rcu_tasks_trace.init_fract <= 0)
+			rcu_tasks_trace.init_fract = 1;
+	}
 	rcu_tasks_trace.pregp_func = rcu_tasks_trace_pregp_step;
 	rcu_tasks_trace.pertask_func = rcu_tasks_trace_pertask;
 	rcu_tasks_trace.postscan_func = rcu_tasks_trace_postscan;
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 3ee59ce0a323..676d4af62103 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -1109,13 +1109,18 @@ out:
 }
 
 #ifdef CONFIG_SECCOMP_FILTER
-static int seccomp_notify_release(struct inode *inode, struct file *file)
+static void seccomp_notify_free(struct seccomp_filter *filter)
+{
+	kfree(filter->notif);
+	filter->notif = NULL;
+}
+
+static void seccomp_notify_detach(struct seccomp_filter *filter)
 {
-	struct seccomp_filter *filter = file->private_data;
 	struct seccomp_knotif *knotif;
 
 	if (!filter)
-		return 0;
+		return;
 
 	mutex_lock(&filter->notify_lock);
 
@@ -1139,9 +1144,15 @@ static int seccomp_notify_release(struct inode *inode, struct file *file)
 		complete(&knotif->ready);
 	}
 
-	kfree(filter->notif);
-	filter->notif = NULL;
+	seccomp_notify_free(filter);
 	mutex_unlock(&filter->notify_lock);
+}
+
+static int seccomp_notify_release(struct inode *inode, struct file *file)
+{
+	struct seccomp_filter *filter = file->private_data;
+
+	seccomp_notify_detach(filter);
 	__put_seccomp_filter(filter);
 	return 0;
 }
@@ -1488,7 +1499,7 @@ static struct file *init_listener(struct seccomp_filter *filter)
 
 out_notif:
 	if (IS_ERR(ret))
-		kfree(filter->notif);
+		seccomp_notify_free(filter);
 out:
 	return ret;
 }
@@ -1581,6 +1592,7 @@ out_put_fd:
 			listener_f->private_data = NULL;
 			fput(listener_f);
 			put_unused_fd(listener);
+			seccomp_notify_detach(prepared);
 		} else {
 			fd_install(listener, listener_f);
 			ret = listener;
diff --git a/kernel/stackleak.c b/kernel/stackleak.c
index a8fc9ae1d03d..ce161a8e8d97 100644
--- a/kernel/stackleak.c
+++ b/kernel/stackleak.c
@@ -20,7 +20,7 @@
 static DEFINE_STATIC_KEY_FALSE(stack_erasing_bypass);
 
 int stack_erasing_sysctl(struct ctl_table *table, int write,
-			void __user *buffer, size_t *lenp, loff_t *ppos)
+			void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int ret = 0;
 	int state = !static_branch_unlikely(&stack_erasing_bypass);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 09e70ee2332e..afad085960b8 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -2912,6 +2912,14 @@ static struct ctl_table vm_table[] = {
 		.proc_handler	= percpu_pagelist_fraction_sysctl_handler,
 		.extra1		= SYSCTL_ZERO,
 	},
+	{
+		.procname	= "page_lock_unfairness",
+		.data		= &sysctl_page_lock_unfairness,
+		.maxlen		= sizeof(sysctl_page_lock_unfairness),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+	},
 #ifdef CONFIG_MMU
 	{
 		.procname	= "max_map_count",
diff --git a/kernel/taskstats.c b/kernel/taskstats.c
index e2ac0e37c4ae..a2802b6ff4bb 100644
--- a/kernel/taskstats.c
+++ b/kernel/taskstats.c
@@ -34,17 +34,13 @@ struct kmem_cache *taskstats_cache;
 
 static struct genl_family family;
 
-static const struct nla_policy taskstats_cmd_get_policy[TASKSTATS_CMD_ATTR_MAX+1] = {
+static const struct nla_policy taskstats_cmd_get_policy[] = {
 	[TASKSTATS_CMD_ATTR_PID]  = { .type = NLA_U32 },
 	[TASKSTATS_CMD_ATTR_TGID] = { .type = NLA_U32 },
 	[TASKSTATS_CMD_ATTR_REGISTER_CPUMASK] = { .type = NLA_STRING },
 	[TASKSTATS_CMD_ATTR_DEREGISTER_CPUMASK] = { .type = NLA_STRING },};
 
-/*
- * We have to use TASKSTATS_CMD_ATTR_MAX here, it is the maxattr in the family.
- * Make sure they are always aligned.
- */
-static const struct nla_policy cgroupstats_cmd_get_policy[TASKSTATS_CMD_ATTR_MAX+1] = {
+static const struct nla_policy cgroupstats_cmd_get_policy[] = {
 	[CGROUPSTATS_CMD_ATTR_FD] = { .type = NLA_U32 },
 };
 
@@ -649,47 +645,25 @@ static const struct genl_ops taskstats_ops[] = {
 		.cmd		= TASKSTATS_CMD_GET,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit		= taskstats_user_cmd,
-		/* policy enforced later */
-		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_HASPOL,
+		.policy		= taskstats_cmd_get_policy,
+		.maxattr	= ARRAY_SIZE(taskstats_cmd_get_policy) - 1,
+		.flags		= GENL_ADMIN_PERM,
 	},
 	{
 		.cmd		= CGROUPSTATS_CMD_GET,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit		= cgroupstats_user_cmd,
-		/* policy enforced later */
-		.flags		= GENL_CMD_CAP_HASPOL,
+		.policy		= cgroupstats_cmd_get_policy,
+		.maxattr	= ARRAY_SIZE(cgroupstats_cmd_get_policy) - 1,
 	},
 };
 
-static int taskstats_pre_doit(const struct genl_ops *ops, struct sk_buff *skb,
-			      struct genl_info *info)
-{
-	const struct nla_policy *policy = NULL;
-
-	switch (ops->cmd) {
-	case TASKSTATS_CMD_GET:
-		policy = taskstats_cmd_get_policy;
-		break;
-	case CGROUPSTATS_CMD_GET:
-		policy = cgroupstats_cmd_get_policy;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	return nlmsg_validate_deprecated(info->nlhdr, GENL_HDRLEN,
-					 TASKSTATS_CMD_ATTR_MAX, policy,
-					 info->extack);
-}
-
 static struct genl_family family __ro_after_init = {
 	.name		= TASKSTATS_GENL_NAME,
 	.version	= TASKSTATS_GENL_VERSION,
-	.maxattr	= TASKSTATS_CMD_ATTR_MAX,
 	.module		= THIS_MODULE,
 	.ops		= taskstats_ops,
 	.n_ops		= ARRAY_SIZE(taskstats_ops),
-	.pre_doit	= taskstats_pre_doit,
 };
 
 /* Needed early in initialization */
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index b2a5380eb187..e118a83439c3 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -7,6 +7,7 @@
 #include <linux/slab.h>
 #include <linux/bpf.h>
 #include <linux/bpf_perf_event.h>
+#include <linux/btf.h>
 #include <linux/filter.h>
 #include <linux/uaccess.h>
 #include <linux/ctype.h>
@@ -16,6 +17,9 @@
 #include <linux/error-injection.h>
 #include <linux/btf_ids.h>
 
+#include <uapi/linux/bpf.h>
+#include <uapi/linux/btf.h>
+
 #include <asm/tlb.h>
 
 #include "trace_probe.h"
@@ -67,6 +71,10 @@ static struct bpf_raw_event_map *bpf_get_raw_tracepoint_module(const char *name)
 u64 bpf_get_stackid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
 u64 bpf_get_stack(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
 
+static int bpf_btf_printf_prepare(struct btf_ptr *ptr, u32 btf_ptr_size,
+				  u64 flags, const struct btf **btf,
+				  s32 *btf_id);
+
 /**
  * trace_call_bpf - invoke BPF program
  * @call: tracepoint event
@@ -743,19 +751,18 @@ out:
 	return err;
 }
 
-BTF_ID_LIST(bpf_seq_printf_btf_ids)
-BTF_ID(struct, seq_file)
+BTF_ID_LIST_SINGLE(btf_seq_file_ids, struct, seq_file)
 
 static const struct bpf_func_proto bpf_seq_printf_proto = {
 	.func		= bpf_seq_printf,
 	.gpl_only	= true,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_BTF_ID,
+	.arg1_btf_id	= &btf_seq_file_ids[0],
 	.arg2_type	= ARG_PTR_TO_MEM,
 	.arg3_type	= ARG_CONST_SIZE,
 	.arg4_type      = ARG_PTR_TO_MEM_OR_NULL,
 	.arg5_type      = ARG_CONST_SIZE_OR_ZERO,
-	.btf_id		= bpf_seq_printf_btf_ids,
 };
 
 BPF_CALL_3(bpf_seq_write, struct seq_file *, m, const void *, data, u32, len)
@@ -763,17 +770,39 @@ BPF_CALL_3(bpf_seq_write, struct seq_file *, m, const void *, data, u32, len)
 	return seq_write(m, data, len) ? -EOVERFLOW : 0;
 }
 
-BTF_ID_LIST(bpf_seq_write_btf_ids)
-BTF_ID(struct, seq_file)
-
 static const struct bpf_func_proto bpf_seq_write_proto = {
 	.func		= bpf_seq_write,
 	.gpl_only	= true,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_BTF_ID,
+	.arg1_btf_id	= &btf_seq_file_ids[0],
 	.arg2_type	= ARG_PTR_TO_MEM,
 	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
-	.btf_id		= bpf_seq_write_btf_ids,
+};
+
+BPF_CALL_4(bpf_seq_printf_btf, struct seq_file *, m, struct btf_ptr *, ptr,
+	   u32, btf_ptr_size, u64, flags)
+{
+	const struct btf *btf;
+	s32 btf_id;
+	int ret;
+
+	ret = bpf_btf_printf_prepare(ptr, btf_ptr_size, flags, &btf, &btf_id);
+	if (ret)
+		return ret;
+
+	return btf_type_seq_show_flags(btf, btf_id, ptr->ptr, m, flags);
+}
+
+static const struct bpf_func_proto bpf_seq_printf_btf_proto = {
+	.func		= bpf_seq_printf_btf,
+	.gpl_only	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_BTF_ID,
+	.arg1_btf_id	= &btf_seq_file_ids[0],
+	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
+	.arg4_type	= ARG_ANYTHING,
 };
 
 static __always_inline int
@@ -1118,6 +1147,14 @@ BPF_CALL_3(bpf_d_path, struct path *, path, char *, buf, u32, sz)
 }
 
 BTF_SET_START(btf_allowlist_d_path)
+#ifdef CONFIG_SECURITY
+BTF_ID(func, security_file_permission)
+BTF_ID(func, security_inode_getattr)
+BTF_ID(func, security_file_open)
+#endif
+#ifdef CONFIG_SECURITY_PATH
+BTF_ID(func, security_path_truncate)
+#endif
 BTF_ID(func, vfs_truncate)
 BTF_ID(func, vfs_fallocate)
 BTF_ID(func, dentry_open)
@@ -1130,20 +1167,78 @@ static bool bpf_d_path_allowed(const struct bpf_prog *prog)
 	return btf_id_set_contains(&btf_allowlist_d_path, prog->aux->attach_btf_id);
 }
 
-BTF_ID_LIST(bpf_d_path_btf_ids)
-BTF_ID(struct, path)
+BTF_ID_LIST_SINGLE(bpf_d_path_btf_ids, struct, path)
 
 static const struct bpf_func_proto bpf_d_path_proto = {
 	.func		= bpf_d_path,
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_BTF_ID,
+	.arg1_btf_id	= &bpf_d_path_btf_ids[0],
 	.arg2_type	= ARG_PTR_TO_MEM,
 	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
-	.btf_id		= bpf_d_path_btf_ids,
 	.allowed	= bpf_d_path_allowed,
 };
 
+#define BTF_F_ALL	(BTF_F_COMPACT  | BTF_F_NONAME | \
+			 BTF_F_PTR_RAW | BTF_F_ZERO)
+
+static int bpf_btf_printf_prepare(struct btf_ptr *ptr, u32 btf_ptr_size,
+				  u64 flags, const struct btf **btf,
+				  s32 *btf_id)
+{
+	const struct btf_type *t;
+
+	if (unlikely(flags & ~(BTF_F_ALL)))
+		return -EINVAL;
+
+	if (btf_ptr_size != sizeof(struct btf_ptr))
+		return -EINVAL;
+
+	*btf = bpf_get_btf_vmlinux();
+
+	if (IS_ERR_OR_NULL(*btf))
+		return PTR_ERR(*btf);
+
+	if (ptr->type_id > 0)
+		*btf_id = ptr->type_id;
+	else
+		return -EINVAL;
+
+	if (*btf_id > 0)
+		t = btf_type_by_id(*btf, *btf_id);
+	if (*btf_id <= 0 || !t)
+		return -ENOENT;
+
+	return 0;
+}
+
+BPF_CALL_5(bpf_snprintf_btf, char *, str, u32, str_size, struct btf_ptr *, ptr,
+	   u32, btf_ptr_size, u64, flags)
+{
+	const struct btf *btf;
+	s32 btf_id;
+	int ret;
+
+	ret = bpf_btf_printf_prepare(ptr, btf_ptr_size, flags, &btf, &btf_id);
+	if (ret)
+		return ret;
+
+	return btf_type_snprintf_show(btf, btf_id, ptr->ptr, str, str_size,
+				      flags);
+}
+
+const struct bpf_func_proto bpf_snprintf_btf_proto = {
+	.func		= bpf_snprintf_btf,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_MEM,
+	.arg2_type	= ARG_CONST_SIZE,
+	.arg3_type	= ARG_PTR_TO_MEM,
+	.arg4_type	= ARG_CONST_SIZE,
+	.arg5_type	= ARG_ANYTHING,
+};
+
 const struct bpf_func_proto *
 bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
@@ -1230,6 +1325,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_get_task_stack_proto;
 	case BPF_FUNC_copy_from_user:
 		return prog->aux->sleepable ? &bpf_copy_from_user_proto : NULL;
+	case BPF_FUNC_snprintf_btf:
+		return &bpf_snprintf_btf_proto;
 	default:
 		return NULL;
 	}
@@ -1627,6 +1724,10 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return prog->expected_attach_type == BPF_TRACE_ITER ?
 		       &bpf_seq_write_proto :
 		       NULL;
+	case BPF_FUNC_seq_printf_btf:
+		return prog->expected_attach_type == BPF_TRACE_ITER ?
+		       &bpf_seq_printf_btf_proto :
+		       NULL;
 	case BPF_FUNC_d_path:
 		return &bpf_d_path_proto;
 	default:
@@ -1675,6 +1776,7 @@ const struct bpf_verifier_ops raw_tracepoint_verifier_ops = {
 };
 
 const struct bpf_prog_ops raw_tracepoint_prog_ops = {
+	.test_run = bpf_prog_test_run_raw_tp,
 };
 
 const struct bpf_verifier_ops tracing_verifier_ops = {
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 275441254bb5..603255f5f085 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -2782,6 +2782,7 @@ static void ftrace_remove_trampoline_from_kallsyms(struct ftrace_ops *ops)
 {
 	lockdep_assert_held(&ftrace_lock);
 	list_del_rcu(&ops->list);
+	synchronize_rcu();
 }
 
 /*
@@ -2862,6 +2863,8 @@ int ftrace_startup(struct ftrace_ops *ops, int command)
 		__unregister_ftrace_function(ops);
 		ftrace_start_up--;
 		ops->flags &= ~FTRACE_OPS_FL_ENABLED;
+		if (ops->flags & FTRACE_OPS_FL_DYNAMIC)
+			ftrace_trampoline_free(ops);
 		return ret;
 	}
 
@@ -7531,8 +7534,7 @@ static bool is_permanent_ops_registered(void)
 
 int
 ftrace_enable_sysctl(struct ctl_table *table, int write,
-		     void __user *buffer, size_t *lenp,
-		     loff_t *ppos)
+		     void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int ret = -ENODEV;
 
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index f40d850ebabc..2a7c26345e83 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3782,14 +3782,14 @@ unsigned long trace_total_entries(struct trace_array *tr)
 
 static void print_lat_help_header(struct seq_file *m)
 {
-	seq_puts(m, "#                  _------=> CPU#            \n"
-		    "#                 / _-----=> irqs-off        \n"
-		    "#                | / _----=> need-resched    \n"
-		    "#                || / _---=> hardirq/softirq \n"
-		    "#                ||| / _--=> preempt-depth   \n"
-		    "#                |||| /     delay            \n"
-		    "#  cmd     pid   ||||| time  |   caller      \n"
-		    "#     \\   /      |||||  \\    |   /         \n");
+	seq_puts(m, "#                    _------=> CPU#            \n"
+		    "#                   / _-----=> irqs-off        \n"
+		    "#                  | / _----=> need-resched    \n"
+		    "#                  || / _---=> hardirq/softirq \n"
+		    "#                  ||| / _--=> preempt-depth   \n"
+		    "#                  |||| /     delay            \n"
+		    "#  cmd     pid     ||||| time  |   caller      \n"
+		    "#     \\   /        |||||  \\    |   /         \n");
 }
 
 static void print_event_info(struct array_buffer *buf, struct seq_file *m)
@@ -3810,26 +3810,26 @@ static void print_func_help_header(struct array_buffer *buf, struct seq_file *m,
 
 	print_event_info(buf, m);
 
-	seq_printf(m, "#           TASK-PID   %s  CPU#   TIMESTAMP  FUNCTION\n", tgid ? "TGID     " : "");
-	seq_printf(m, "#              | |     %s    |       |         |\n",	 tgid ? "  |      " : "");
+	seq_printf(m, "#           TASK-PID    %s CPU#     TIMESTAMP  FUNCTION\n", tgid ? "   TGID   " : "");
+	seq_printf(m, "#              | |      %s   |         |         |\n",      tgid ? "     |    " : "");
 }
 
 static void print_func_help_header_irq(struct array_buffer *buf, struct seq_file *m,
 				       unsigned int flags)
 {
 	bool tgid = flags & TRACE_ITER_RECORD_TGID;
-	const char *space = "          ";
-	int prec = tgid ? 10 : 2;
+	const char *space = "            ";
+	int prec = tgid ? 12 : 2;
 
 	print_event_info(buf, m);
 
-	seq_printf(m, "#                          %.*s  _-----=> irqs-off\n", prec, space);
-	seq_printf(m, "#                          %.*s / _----=> need-resched\n", prec, space);
-	seq_printf(m, "#                          %.*s| / _---=> hardirq/softirq\n", prec, space);
-	seq_printf(m, "#                          %.*s|| / _--=> preempt-depth\n", prec, space);
-	seq_printf(m, "#                          %.*s||| /     delay\n", prec, space);
-	seq_printf(m, "#           TASK-PID %.*sCPU#  ||||    TIMESTAMP  FUNCTION\n", prec, "   TGID   ");
-	seq_printf(m, "#              | |   %.*s  |   ||||       |         |\n", prec, "     |    ");
+	seq_printf(m, "#                            %.*s  _-----=> irqs-off\n", prec, space);
+	seq_printf(m, "#                            %.*s / _----=> need-resched\n", prec, space);
+	seq_printf(m, "#                            %.*s| / _---=> hardirq/softirq\n", prec, space);
+	seq_printf(m, "#                            %.*s|| / _--=> preempt-depth\n", prec, space);
+	seq_printf(m, "#                            %.*s||| /     delay\n", prec, space);
+	seq_printf(m, "#           TASK-PID  %.*s CPU#  ||||   TIMESTAMP  FUNCTION\n", prec, "     TGID   ");
+	seq_printf(m, "#              | |    %.*s   |   ||||      |         |\n", prec, "       |    ");
 }
 
 void
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 0b933546142e..1b2ef6490229 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -3865,7 +3865,6 @@ static int parse_var_defs(struct hist_trigger_data *hist_data)
 
 			s = kstrdup(field_str, GFP_KERNEL);
 			if (!s) {
-				kfree(hist_data->attrs->var_defs.name[n_vars]);
 				ret = -ENOMEM;
 				goto free;
 			}
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 4d1893564912..000e9dc224c6 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -497,7 +497,7 @@ lat_print_generic(struct trace_seq *s, struct trace_entry *entry, int cpu)
 
 	trace_find_cmdline(entry->pid, comm);
 
-	trace_seq_printf(s, "%8.8s-%-5d %3d",
+	trace_seq_printf(s, "%8.8s-%-7d %3d",
 			 comm, entry->pid, cpu);
 
 	return trace_print_lat_fmt(s, entry);
@@ -588,15 +588,15 @@ int trace_print_context(struct trace_iterator *iter)
 
 	trace_find_cmdline(entry->pid, comm);
 
-	trace_seq_printf(s, "%16s-%-5d ", comm, entry->pid);
+	trace_seq_printf(s, "%16s-%-7d ", comm, entry->pid);
 
 	if (tr->trace_flags & TRACE_ITER_RECORD_TGID) {
 		unsigned int tgid = trace_find_tgid(entry->pid);
 
 		if (!tgid)
-			trace_seq_printf(s, "(-----) ");
+			trace_seq_printf(s, "(-------) ");
 		else
-			trace_seq_printf(s, "(%5d) ", tgid);
+			trace_seq_printf(s, "(%7d) ", tgid);
 	}
 
 	trace_seq_printf(s, "[%03d] ", iter->cpu);
@@ -636,7 +636,7 @@ int trace_print_lat_context(struct trace_iterator *iter)
 		trace_find_cmdline(entry->pid, comm);
 
 		trace_seq_printf(
-			s, "%16s %5d %3d %d %08x %08lx ",
+			s, "%16s %7d %3d %d %08x %08lx ",
 			comm, entry->pid, iter->cpu, entry->flags,
 			entry->preempt_count, iter->idx);
 	} else {
@@ -917,7 +917,7 @@ static enum print_line_t trace_ctxwake_print(struct trace_iterator *iter,
 	S = task_index_to_char(field->prev_state);
 	trace_find_cmdline(field->next_pid, comm);
 	trace_seq_printf(&iter->seq,
-			 " %5d:%3d:%c %s [%03d] %5d:%3d:%c %s\n",
+			 " %7d:%3d:%c %s [%03d] %7d:%3d:%c %s\n",
 			 field->prev_pid,
 			 field->prev_prio,
 			 S, delim,
diff --git a/kernel/trace/trace_preemptirq.c b/kernel/trace/trace_preemptirq.c
index f10073e62603..f4938040c228 100644
--- a/kernel/trace/trace_preemptirq.c
+++ b/kernel/trace/trace_preemptirq.c
@@ -102,14 +102,14 @@ NOKPROBE_SYMBOL(trace_hardirqs_on_caller);
 
 __visible void trace_hardirqs_off_caller(unsigned long caller_addr)
 {
+	lockdep_hardirqs_off(CALLER_ADDR0);
+
 	if (!this_cpu_read(tracing_irq_cpu)) {
 		this_cpu_write(tracing_irq_cpu, 1);
 		tracer_hardirqs_off(CALLER_ADDR0, caller_addr);
 		if (!in_nmi())
 			trace_irq_disable_rcuidle(CALLER_ADDR0, caller_addr);
 	}
-
-	lockdep_hardirqs_off(CALLER_ADDR0);
 }
 EXPORT_SYMBOL(trace_hardirqs_off_caller);
 NOKPROBE_SYMBOL(trace_hardirqs_off_caller);
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index e068c3c7189a..0c781f912f9f 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -520,8 +520,8 @@ config DEBUG_FS_ALLOW_NONE
 endchoice
 
 source "lib/Kconfig.kgdb"
-
 source "lib/Kconfig.ubsan"
+source "lib/Kconfig.kcsan"
 
 endmenu
 
@@ -1620,8 +1620,6 @@ config PROVIDE_OHCI1394_DMA_INIT
 
 source "samples/Kconfig"
 
-source "lib/Kconfig.kcsan"
-
 config ARCH_HAS_DEVMEM_IS_ALLOWED
 	bool
 
diff --git a/lib/dynamic_debug.c b/lib/dynamic_debug.c
index 1d012e597cc3..2d4dfd44b0fa 100644
--- a/lib/dynamic_debug.c
+++ b/lib/dynamic_debug.c
@@ -353,8 +353,7 @@ static int check_set(const char **dest, char *src, char *name)
 
 /*
  * Parse words[] as a ddebug query specification, which is a series
- * of (keyword, value) pairs or combined keyword=value terms,
- * chosen from these possibilities:
+ * of (keyword, value) pairs chosen from these possibilities:
  *
  * func <function-name>
  * file <full-pathname>
@@ -373,34 +372,22 @@ static int ddebug_parse_query(char *words[], int nwords,
 	unsigned int i;
 	int rc = 0;
 	char *fline;
-	char *keyword, *arg;
+
+	/* check we have an even number of words */
+	if (nwords % 2 != 0) {
+		pr_err("expecting pairs of match-spec <value>\n");
+		return -EINVAL;
+	}
 
 	if (modname)
 		/* support $modname.dyndbg=<multiple queries> */
 		query->module = modname;
 
-	for (i = 0; i < nwords; i++) {
-		/* accept keyword=arg */
-		vpr_info("%d w:%s\n", i, words[i]);
-
-		keyword = words[i];
-		arg = strchr(keyword, '=');
-		if (arg) {
-			*arg++ = '\0';
-		} else {
-			i++; /* next word is arg */
-			if (!(i < nwords)) {
-				pr_err("missing arg to keyword: %s\n", keyword);
-				return -EINVAL;
-			}
-			arg = words[i];
-		}
-		vpr_info("%d key:%s arg:%s\n", i, keyword, arg);
-
-		if (!strcmp(keyword, "func")) {
-			rc = check_set(&query->function, arg, "func");
-		} else if (!strcmp(keyword, "file")) {
-			if (check_set(&query->filename, arg, "file"))
+	for (i = 0; i < nwords; i += 2) {
+		if (!strcmp(words[i], "func")) {
+			rc = check_set(&query->function, words[i+1], "func");
+		} else if (!strcmp(words[i], "file")) {
+			if (check_set(&query->filename, words[i+1], "file"))
 				return -EINVAL;
 
 			/* tail :$info is function or line-range */
@@ -416,18 +403,18 @@ static int ddebug_parse_query(char *words[], int nwords,
 				if (parse_linerange(query, fline))
 					return -EINVAL;
 			}
-		} else if (!strcmp(keyword, "module")) {
-			rc = check_set(&query->module, arg, "module");
-		} else if (!strcmp(keyword, "format")) {
-			string_unescape_inplace(arg, UNESCAPE_SPACE |
+		} else if (!strcmp(words[i], "module")) {
+			rc = check_set(&query->module, words[i+1], "module");
+		} else if (!strcmp(words[i], "format")) {
+			string_unescape_inplace(words[i+1], UNESCAPE_SPACE |
 							    UNESCAPE_OCTAL |
 							    UNESCAPE_SPECIAL);
-			rc = check_set(&query->format, arg, "format");
-		} else if (!strcmp(keyword, "line")) {
-			if (parse_linerange(query, arg))
+			rc = check_set(&query->format, words[i+1], "format");
+		} else if (!strcmp(words[i], "line")) {
+			if (parse_linerange(query, words[i+1]))
 				return -EINVAL;
 		} else {
-			pr_err("unknown keyword \"%s\"\n", keyword);
+			pr_err("unknown keyword \"%s\"\n", words[i]);
 			return -EINVAL;
 		}
 		if (rc)
@@ -525,7 +512,7 @@ static int ddebug_exec_query(char *query_string, const char *modname)
    last error or number of matching callsites.  Module name is either
    in param (for boot arg) or perhaps in query string.
 */
-int ddebug_exec_queries(char *query, const char *modname)
+static int ddebug_exec_queries(char *query, const char *modname)
 {
 	char *split;
 	int i, errs = 0, exitcode = 0, rc, nfound = 0;
@@ -557,7 +544,30 @@ int ddebug_exec_queries(char *query, const char *modname)
 		return exitcode;
 	return nfound;
 }
-EXPORT_SYMBOL_GPL(ddebug_exec_queries);
+
+/**
+ * dynamic_debug_exec_queries - select and change dynamic-debug prints
+ * @query: query-string described in admin-guide/dynamic-debug-howto
+ * @modname: string containing module name, usually &module.mod_name
+ *
+ * This uses the >/proc/dynamic_debug/control reader, allowing module
+ * authors to modify their dynamic-debug callsites. The modname is
+ * canonically struct module.mod_name, but can also be null or a
+ * module-wildcard, for example: "drm*".
+ */
+int dynamic_debug_exec_queries(const char *query, const char *modname)
+{
+	int rc;
+	char *qry = kstrndup(query, PAGE_SIZE, GFP_KERNEL);
+
+	if (!query)
+		return -ENOMEM;
+
+	rc = ddebug_exec_queries(qry, modname);
+	kfree(qry);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(dynamic_debug_exec_queries);
 
 #define PREFIX_SIZE 64
 
@@ -947,7 +957,7 @@ int ddebug_add_module(struct _ddebug *tab, unsigned int n,
 	list_add(&dt->link, &ddebug_tables);
 	mutex_unlock(&ddebug_lock);
 
-	v2pr_info("%u debug prints in module %s\n", n, dt->mod_name);
+	v2pr_info("%3u debug prints in module %s\n", n, dt->mod_name);
 	return 0;
 }
 
diff --git a/lib/kobject.c b/lib/kobject.c
index 3afb939f2a1c..ea53b30cf483 100644
--- a/lib/kobject.c
+++ b/lib/kobject.c
@@ -604,9 +604,6 @@ static void __kobject_del(struct kobject *kobj)
 	struct kernfs_node *sd;
 	const struct kobj_type *ktype;
 
-	if (!kobj)
-		return;
-
 	sd = kobj->sd;
 	ktype = get_ktype(kobj);
 
@@ -637,8 +634,12 @@ static void __kobject_del(struct kobject *kobj)
  */
 void kobject_del(struct kobject *kobj)
 {
-	struct kobject *parent = kobj->parent;
+	struct kobject *parent;
+
+	if (!kobj)
+		return;
 
+	parent = kobj->parent;
 	__kobject_del(kobj);
 	kobject_put(parent);
 }
diff --git a/lib/test_firmware.c b/lib/test_firmware.c
index 9fee2b93a8d1..06c955057756 100644
--- a/lib/test_firmware.c
+++ b/lib/test_firmware.c
@@ -26,6 +26,8 @@
 #include <linux/vmalloc.h>
 #include <linux/efi_embedded_fw.h>
 
+MODULE_IMPORT_NS(TEST_FIRMWARE);
+
 #define TEST_FIRMWARE_NAME	"test-firmware.bin"
 #define TEST_FIRMWARE_NUM_REQS	4
 #define TEST_FIRMWARE_BUF_SIZE	SZ_1K
@@ -489,6 +491,9 @@ out:
 static DEVICE_ATTR_WO(trigger_request);
 
 #ifdef CONFIG_EFI_EMBEDDED_FIRMWARE
+extern struct list_head efi_embedded_fw_list;
+extern bool efi_embedded_fw_checked;
+
 static ssize_t trigger_request_platform_store(struct device *dev,
 					      struct device_attribute *attr,
 					      const char *buf, size_t count)
@@ -501,6 +506,7 @@ static ssize_t trigger_request_platform_store(struct device *dev,
 	};
 	struct efi_embedded_fw efi_embedded_fw;
 	const struct firmware *firmware = NULL;
+	bool saved_efi_embedded_fw_checked;
 	char *name;
 	int rc;
 
@@ -513,6 +519,8 @@ static ssize_t trigger_request_platform_store(struct device *dev,
 	efi_embedded_fw.data = (void *)test_data;
 	efi_embedded_fw.length = sizeof(test_data);
 	list_add(&efi_embedded_fw.list, &efi_embedded_fw_list);
+	saved_efi_embedded_fw_checked = efi_embedded_fw_checked;
+	efi_embedded_fw_checked = true;
 
 	pr_info("loading '%s'\n", name);
 	rc = firmware_request_platform(&firmware, name, dev);
@@ -530,6 +538,7 @@ static ssize_t trigger_request_platform_store(struct device *dev,
 	rc = count;
 
 out:
+	efi_embedded_fw_checked = saved_efi_embedded_fw_checked;
 	release_firmware(firmware);
 	list_del(&efi_embedded_fw.list);
 	kfree(name);
diff --git a/lib/test_rhashtable.c b/lib/test_rhashtable.c
index c5a6fef7b45d..76c607ee6db5 100644
--- a/lib/test_rhashtable.c
+++ b/lib/test_rhashtable.c
@@ -434,7 +434,7 @@ static int __init test_rhltable(unsigned int entries)
 		} else {
 			if (WARN(err != -ENOENT, "removed non-existent element, error %d not %d",
 				 err, -ENOENT))
-			continue;
+				continue;
 		}
 	}
 
diff --git a/mm/filemap.c b/mm/filemap.c
index 054d93a86f8a..8c8f2deee4e3 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -988,9 +988,43 @@ void __init pagecache_init(void)
 	page_writeback_init();
 }
 
+/*
+ * The page wait code treats the "wait->flags" somewhat unusually, because
+ * we have multiple different kinds of waits, not just the usual "exclusive"
+ * one.
+ *
+ * We have:
+ *
+ *  (a) no special bits set:
+ *
+ *	We're just waiting for the bit to be released, and when a waker
+ *	calls the wakeup function, we set WQ_FLAG_WOKEN and wake it up,
+ *	and remove it from the wait queue.
+ *
+ *	Simple and straightforward.
+ *
+ *  (b) WQ_FLAG_EXCLUSIVE:
+ *
+ *	The waiter is waiting to get the lock, and only one waiter should
+ *	be woken up to avoid any thundering herd behavior. We'll set the
+ *	WQ_FLAG_WOKEN bit, wake it up, and remove it from the wait queue.
+ *
+ *	This is the traditional exclusive wait.
+ *
+ *  (c) WQ_FLAG_EXCLUSIVE | WQ_FLAG_CUSTOM:
+ *
+ *	The waiter is waiting to get the bit, and additionally wants the
+ *	lock to be transferred to it for fair lock behavior. If the lock
+ *	cannot be taken, we stop walking the wait queue without waking
+ *	the waiter.
+ *
+ *	This is the "fair lock handoff" case, and in addition to setting
+ *	WQ_FLAG_WOKEN, we set WQ_FLAG_DONE to let the waiter easily see
+ *	that it now has the lock.
+ */
 static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync, void *arg)
 {
-	int ret;
+	unsigned int flags;
 	struct wait_page_key *key = arg;
 	struct wait_page_queue *wait_page
 		= container_of(wait, struct wait_page_queue, wait);
@@ -999,35 +1033,44 @@ static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync,
 		return 0;
 
 	/*
-	 * If it's an exclusive wait, we get the bit for it, and
-	 * stop walking if we can't.
-	 *
-	 * If it's a non-exclusive wait, then the fact that this
-	 * wake function was called means that the bit already
-	 * was cleared, and we don't care if somebody then
-	 * re-took it.
+	 * If it's a lock handoff wait, we get the bit for it, and
+	 * stop walking (and do not wake it up) if we can't.
 	 */
-	ret = 0;
-	if (wait->flags & WQ_FLAG_EXCLUSIVE) {
-		if (test_and_set_bit(key->bit_nr, &key->page->flags))
+	flags = wait->flags;
+	if (flags & WQ_FLAG_EXCLUSIVE) {
+		if (test_bit(key->bit_nr, &key->page->flags))
 			return -1;
-		ret = 1;
+		if (flags & WQ_FLAG_CUSTOM) {
+			if (test_and_set_bit(key->bit_nr, &key->page->flags))
+				return -1;
+			flags |= WQ_FLAG_DONE;
+		}
 	}
-	wait->flags |= WQ_FLAG_WOKEN;
 
+	/*
+	 * We are holding the wait-queue lock, but the waiter that
+	 * is waiting for this will be checking the flags without
+	 * any locking.
+	 *
+	 * So update the flags atomically, and wake up the waiter
+	 * afterwards to avoid any races. This store-release pairs
+	 * with the load-acquire in wait_on_page_bit_common().
+	 */
+	smp_store_release(&wait->flags, flags | WQ_FLAG_WOKEN);
 	wake_up_state(wait->private, mode);
 
 	/*
 	 * Ok, we have successfully done what we're waiting for,
 	 * and we can unconditionally remove the wait entry.
 	 *
-	 * Note that this has to be the absolute last thing we do,
-	 * since after list_del_init(&wait->entry) the wait entry
+	 * Note that this pairs with the "finish_wait()" in the
+	 * waiter, and has to be the absolute last thing we do.
+	 * After this list_del_init(&wait->entry) the wait entry
 	 * might be de-allocated and the process might even have
 	 * exited.
 	 */
 	list_del_init_careful(&wait->entry);
-	return ret;
+	return (flags & WQ_FLAG_EXCLUSIVE) != 0;
 }
 
 static void wake_up_page_bit(struct page *page, int bit_nr)
@@ -1107,8 +1150,8 @@ enum behavior {
 };
 
 /*
- * Attempt to check (or get) the page bit, and mark the
- * waiter woken if successful.
+ * Attempt to check (or get) the page bit, and mark us done
+ * if successful.
  */
 static inline bool trylock_page_bit_common(struct page *page, int bit_nr,
 					struct wait_queue_entry *wait)
@@ -1119,13 +1162,17 @@ static inline bool trylock_page_bit_common(struct page *page, int bit_nr,
 	} else if (test_bit(bit_nr, &page->flags))
 		return false;
 
-	wait->flags |= WQ_FLAG_WOKEN;
+	wait->flags |= WQ_FLAG_WOKEN | WQ_FLAG_DONE;
 	return true;
 }
 
+/* How many times do we accept lock stealing from under a waiter? */
+int sysctl_page_lock_unfairness = 5;
+
 static inline int wait_on_page_bit_common(wait_queue_head_t *q,
 	struct page *page, int bit_nr, int state, enum behavior behavior)
 {
+	int unfairness = sysctl_page_lock_unfairness;
 	struct wait_page_queue wait_page;
 	wait_queue_entry_t *wait = &wait_page.wait;
 	bool thrashing = false;
@@ -1143,11 +1190,18 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q,
 	}
 
 	init_wait(wait);
-	wait->flags = behavior == EXCLUSIVE ? WQ_FLAG_EXCLUSIVE : 0;
 	wait->func = wake_page_function;
 	wait_page.page = page;
 	wait_page.bit_nr = bit_nr;
 
+repeat:
+	wait->flags = 0;
+	if (behavior == EXCLUSIVE) {
+		wait->flags = WQ_FLAG_EXCLUSIVE;
+		if (--unfairness < 0)
+			wait->flags |= WQ_FLAG_CUSTOM;
+	}
+
 	/*
 	 * Do one last check whether we can get the
 	 * page bit synchronously.
@@ -1170,27 +1224,63 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q,
 
 	/*
 	 * From now on, all the logic will be based on
-	 * the WQ_FLAG_WOKEN flag, and the and the page
-	 * bit testing (and setting) will be - or has
-	 * already been - done by the wake function.
+	 * the WQ_FLAG_WOKEN and WQ_FLAG_DONE flag, to
+	 * see whether the page bit testing has already
+	 * been done by the wake function.
 	 *
 	 * We can drop our reference to the page.
 	 */
 	if (behavior == DROP)
 		put_page(page);
 
+	/*
+	 * Note that until the "finish_wait()", or until
+	 * we see the WQ_FLAG_WOKEN flag, we need to
+	 * be very careful with the 'wait->flags', because
+	 * we may race with a waker that sets them.
+	 */
 	for (;;) {
+		unsigned int flags;
+
 		set_current_state(state);
 
-		if (signal_pending_state(state, current))
+		/* Loop until we've been woken or interrupted */
+		flags = smp_load_acquire(&wait->flags);
+		if (!(flags & WQ_FLAG_WOKEN)) {
+			if (signal_pending_state(state, current))
+				break;
+
+			io_schedule();
+			continue;
+		}
+
+		/* If we were non-exclusive, we're done */
+		if (behavior != EXCLUSIVE)
 			break;
 
-		if (wait->flags & WQ_FLAG_WOKEN)
+		/* If the waker got the lock for us, we're done */
+		if (flags & WQ_FLAG_DONE)
 			break;
 
-		io_schedule();
+		/*
+		 * Otherwise, if we're getting the lock, we need to
+		 * try to get it ourselves.
+		 *
+		 * And if that fails, we'll have to retry this all.
+		 */
+		if (unlikely(test_and_set_bit(bit_nr, &page->flags)))
+			goto repeat;
+
+		wait->flags |= WQ_FLAG_DONE;
+		break;
 	}
 
+	/*
+	 * If a signal happened, this 'finish_wait()' may remove the last
+	 * waiter from the wait-queues, but the PageWaiters bit will remain
+	 * set. That's ok. The next wakeup will take care of it, and trying
+	 * to do it here would be difficult and prone to races.
+	 */
 	finish_wait(q, wait);
 
 	if (thrashing) {
@@ -1200,12 +1290,20 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q,
 	}
 
 	/*
-	 * A signal could leave PageWaiters set. Clearing it here if
-	 * !waitqueue_active would be possible (by open-coding finish_wait),
-	 * but still fail to catch it in the case of wait hash collision. We
-	 * already can fail to clear wait hash collision cases, so don't
-	 * bother with signals either.
+	 * NOTE! The wait->flags weren't stable until we've done the
+	 * 'finish_wait()', and we could have exited the loop above due
+	 * to a signal, and had a wakeup event happen after the signal
+	 * test but before the 'finish_wait()'.
+	 *
+	 * So only after the finish_wait() can we reliably determine
+	 * if we got woken up or not, so we can now figure out the final
+	 * return value based on that state without races.
+	 *
+	 * Also note that WQ_FLAG_WOKEN is sufficient for a non-exclusive
+	 * waiter, but an exclusive one requires WQ_FLAG_DONE.
 	 */
+	if (behavior == EXCLUSIVE)
+		return wait->flags & WQ_FLAG_DONE ? 0 : -EINTR;
 
 	return wait->flags & WQ_FLAG_WOKEN ? 0 : -EINTR;
 }
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 7ff29cc3d55c..faadc449cca5 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2022,7 +2022,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 		put_page(page);
 		add_mm_counter(mm, mm_counter_file(page), -HPAGE_PMD_NR);
 		return;
-	} else if (is_huge_zero_pmd(*pmd)) {
+	} else if (pmd_trans_huge(*pmd) && is_huge_zero_pmd(*pmd)) {
 		/*
 		 * FIXME: Do we want to invalidate secondary mmu by calling
 		 * mmu_notifier_invalidate_range() see comments below inside
@@ -2116,30 +2116,34 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 		pte = pte_offset_map(&_pmd, addr);
 		BUG_ON(!pte_none(*pte));
 		set_pte_at(mm, addr, pte, entry);
-		atomic_inc(&page[i]._mapcount);
-		pte_unmap(pte);
-	}
-
-	/*
-	 * Set PG_double_map before dropping compound_mapcount to avoid
-	 * false-negative page_mapped().
-	 */
-	if (compound_mapcount(page) > 1 && !TestSetPageDoubleMap(page)) {
-		for (i = 0; i < HPAGE_PMD_NR; i++)
+		if (!pmd_migration)
 			atomic_inc(&page[i]._mapcount);
+		pte_unmap(pte);
 	}
 
-	lock_page_memcg(page);
-	if (atomic_add_negative(-1, compound_mapcount_ptr(page))) {
-		/* Last compound_mapcount is gone. */
-		__dec_lruvec_page_state(page, NR_ANON_THPS);
-		if (TestClearPageDoubleMap(page)) {
-			/* No need in mapcount reference anymore */
+	if (!pmd_migration) {
+		/*
+		 * Set PG_double_map before dropping compound_mapcount to avoid
+		 * false-negative page_mapped().
+		 */
+		if (compound_mapcount(page) > 1 &&
+		    !TestSetPageDoubleMap(page)) {
 			for (i = 0; i < HPAGE_PMD_NR; i++)
-				atomic_dec(&page[i]._mapcount);
+				atomic_inc(&page[i]._mapcount);
+		}
+
+		lock_page_memcg(page);
+		if (atomic_add_negative(-1, compound_mapcount_ptr(page))) {
+			/* Last compound_mapcount is gone. */
+			__dec_lruvec_page_state(page, NR_ANON_THPS);
+			if (TestClearPageDoubleMap(page)) {
+				/* No need in mapcount reference anymore */
+				for (i = 0; i < HPAGE_PMD_NR; i++)
+					atomic_dec(&page[i]._mapcount);
+			}
 		}
+		unlock_page_memcg(page);
 	}
-	unlock_page_memcg(page);
 
 	smp_wmb(); /* make pte visible before pmd */
 	pmd_populate(mm, pmd, pgtable);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index a301c2d672bf..67fc6383995b 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1250,21 +1250,32 @@ static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask,
 		int nid, nodemask_t *nodemask)
 {
 	unsigned long nr_pages = 1UL << huge_page_order(h);
+	if (nid == NUMA_NO_NODE)
+		nid = numa_mem_id();
 
 #ifdef CONFIG_CMA
 	{
 		struct page *page;
 		int node;
 
-		for_each_node_mask(node, *nodemask) {
-			if (!hugetlb_cma[node])
-				continue;
-
-			page = cma_alloc(hugetlb_cma[node], nr_pages,
-					 huge_page_order(h), true);
+		if (hugetlb_cma[nid]) {
+			page = cma_alloc(hugetlb_cma[nid], nr_pages,
+					huge_page_order(h), true);
 			if (page)
 				return page;
 		}
+
+		if (!(gfp_mask & __GFP_THISNODE)) {
+			for_each_node_mask(node, *nodemask) {
+				if (node == nid || !hugetlb_cma[node])
+					continue;
+
+				page = cma_alloc(hugetlb_cma[node], nr_pages,
+						huge_page_order(h), true);
+				if (page)
+					return page;
+			}
+		}
 	}
 #endif
 
@@ -3454,6 +3465,22 @@ static unsigned int allowed_mems_nr(struct hstate *h)
 }
 
 #ifdef CONFIG_SYSCTL
+static int proc_hugetlb_doulongvec_minmax(struct ctl_table *table, int write,
+					  void *buffer, size_t *length,
+					  loff_t *ppos, unsigned long *out)
+{
+	struct ctl_table dup_table;
+
+	/*
+	 * In order to avoid races with __do_proc_doulongvec_minmax(), we
+	 * can duplicate the @table and alter the duplicate of it.
+	 */
+	dup_table = *table;
+	dup_table.data = out;
+
+	return proc_doulongvec_minmax(&dup_table, write, buffer, length, ppos);
+}
+
 static int hugetlb_sysctl_handler_common(bool obey_mempolicy,
 			 struct ctl_table *table, int write,
 			 void *buffer, size_t *length, loff_t *ppos)
@@ -3465,9 +3492,8 @@ static int hugetlb_sysctl_handler_common(bool obey_mempolicy,
 	if (!hugepages_supported())
 		return -EOPNOTSUPP;
 
-	table->data = &tmp;
-	table->maxlen = sizeof(unsigned long);
-	ret = proc_doulongvec_minmax(table, write, buffer, length, ppos);
+	ret = proc_hugetlb_doulongvec_minmax(table, write, buffer, length, ppos,
+					     &tmp);
 	if (ret)
 		goto out;
 
@@ -3510,9 +3536,8 @@ int hugetlb_overcommit_handler(struct ctl_table *table, int write,
 	if (write && hstate_is_gigantic(h))
 		return -EINVAL;
 
-	table->data = &tmp;
-	table->maxlen = sizeof(unsigned long);
-	ret = proc_doulongvec_minmax(table, write, buffer, length, ppos);
+	ret = proc_hugetlb_doulongvec_minmax(table, write, buffer, length, ppos,
+					     &tmp);
 	if (ret)
 		goto out;
 
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index e749e568e1ea..cfa0dba5fd3b 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1709,7 +1709,7 @@ static void collapse_file(struct mm_struct *mm,
 				xas_unlock_irq(&xas);
 				page_cache_sync_readahead(mapping, &file->f_ra,
 							  file, index,
-							  PAGE_SIZE);
+							  end - index);
 				/* drain pagevecs to help isolate_lru_page() */
 				lru_add_drain();
 				page = find_lock_page(mapping, index);
diff --git a/mm/ksm.c b/mm/ksm.c
index 235f55d01541..9afccc36dbd2 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -2586,6 +2586,10 @@ struct page *ksm_might_need_to_copy(struct page *page,
 		return page;		/* let do_swap_page report the error */
 
 	new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address);
+	if (new_page && mem_cgroup_charge(new_page, vma->vm_mm, GFP_KERNEL)) {
+		put_page(new_page);
+		new_page = NULL;
+	}
 	if (new_page) {
 		copy_user_highpage(new_page, page, address, vma);
 
diff --git a/mm/madvise.c b/mm/madvise.c
index dd1d43cf026d..d4aa5f776543 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -289,9 +289,9 @@ static long madvise_willneed(struct vm_area_struct *vma,
 	 */
 	*prev = NULL;	/* tell sys_madvise we drop mmap_lock */
 	get_file(file);
-	mmap_read_unlock(current->mm);
 	offset = (loff_t)(start - vma->vm_start)
 			+ ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
+	mmap_read_unlock(current->mm);
 	vfs_fadvise(file, offset, end - start, POSIX_FADV_WILLNEED);
 	fput(file);
 	mmap_read_lock(current->mm);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index b807952b4d43..cfa6cbad21d5 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -6774,6 +6774,9 @@ static void uncharge_batch(const struct uncharge_gather *ug)
 	__this_cpu_add(ug->memcg->vmstats_percpu->nr_page_events, ug->nr_pages);
 	memcg_check_events(ug->memcg, ug->dummy_page);
 	local_irq_restore(flags);
+
+	/* drop reference from uncharge_page */
+	css_put(&ug->memcg->css);
 }
 
 static void uncharge_page(struct page *page, struct uncharge_gather *ug)
@@ -6797,6 +6800,9 @@ static void uncharge_page(struct page *page, struct uncharge_gather *ug)
 			uncharge_gather_clear(ug);
 		}
 		ug->memcg = page->mem_cgroup;
+
+		/* pairs with css_put in uncharge_batch */
+		css_get(&ug->memcg->css);
 	}
 
 	nr_pages = compound_nr(page);
diff --git a/mm/memory.c b/mm/memory.c
index 148eafb8cbb1..469af373ae76 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -73,6 +73,7 @@
 #include <linux/numa.h>
 #include <linux/perf_event.h>
 #include <linux/ptrace.h>
+#include <linux/vmalloc.h>
 
 #include <trace/events/kmem.h>
 
@@ -83,6 +84,7 @@
 #include <asm/tlb.h>
 #include <asm/tlbflush.h>
 
+#include "pgalloc-track.h"
 #include "internal.h"
 
 #if defined(LAST_CPUPID_NOT_IN_PAGE_FLAGS) && !defined(CONFIG_COMPILE_TEST)
@@ -2206,7 +2208,8 @@ EXPORT_SYMBOL(vm_iomap_memory);
 
 static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd,
 				     unsigned long addr, unsigned long end,
-				     pte_fn_t fn, void *data, bool create)
+				     pte_fn_t fn, void *data, bool create,
+				     pgtbl_mod_mask *mask)
 {
 	pte_t *pte;
 	int err = 0;
@@ -2214,7 +2217,7 @@ static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd,
 
 	if (create) {
 		pte = (mm == &init_mm) ?
-			pte_alloc_kernel(pmd, addr) :
+			pte_alloc_kernel_track(pmd, addr, mask) :
 			pte_alloc_map_lock(mm, pmd, addr, &ptl);
 		if (!pte)
 			return -ENOMEM;
@@ -2235,6 +2238,7 @@ static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd,
 				break;
 		}
 	} while (addr += PAGE_SIZE, addr != end);
+	*mask |= PGTBL_PTE_MODIFIED;
 
 	arch_leave_lazy_mmu_mode();
 
@@ -2245,7 +2249,8 @@ static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd,
 
 static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud,
 				     unsigned long addr, unsigned long end,
-				     pte_fn_t fn, void *data, bool create)
+				     pte_fn_t fn, void *data, bool create,
+				     pgtbl_mod_mask *mask)
 {
 	pmd_t *pmd;
 	unsigned long next;
@@ -2254,7 +2259,7 @@ static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud,
 	BUG_ON(pud_huge(*pud));
 
 	if (create) {
-		pmd = pmd_alloc(mm, pud, addr);
+		pmd = pmd_alloc_track(mm, pud, addr, mask);
 		if (!pmd)
 			return -ENOMEM;
 	} else {
@@ -2264,7 +2269,7 @@ static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud,
 		next = pmd_addr_end(addr, end);
 		if (create || !pmd_none_or_clear_bad(pmd)) {
 			err = apply_to_pte_range(mm, pmd, addr, next, fn, data,
-						 create);
+						 create, mask);
 			if (err)
 				break;
 		}
@@ -2274,14 +2279,15 @@ static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud,
 
 static int apply_to_pud_range(struct mm_struct *mm, p4d_t *p4d,
 				     unsigned long addr, unsigned long end,
-				     pte_fn_t fn, void *data, bool create)
+				     pte_fn_t fn, void *data, bool create,
+				     pgtbl_mod_mask *mask)
 {
 	pud_t *pud;
 	unsigned long next;
 	int err = 0;
 
 	if (create) {
-		pud = pud_alloc(mm, p4d, addr);
+		pud = pud_alloc_track(mm, p4d, addr, mask);
 		if (!pud)
 			return -ENOMEM;
 	} else {
@@ -2291,7 +2297,7 @@ static int apply_to_pud_range(struct mm_struct *mm, p4d_t *p4d,
 		next = pud_addr_end(addr, end);
 		if (create || !pud_none_or_clear_bad(pud)) {
 			err = apply_to_pmd_range(mm, pud, addr, next, fn, data,
-						 create);
+						 create, mask);
 			if (err)
 				break;
 		}
@@ -2301,14 +2307,15 @@ static int apply_to_pud_range(struct mm_struct *mm, p4d_t *p4d,
 
 static int apply_to_p4d_range(struct mm_struct *mm, pgd_t *pgd,
 				     unsigned long addr, unsigned long end,
-				     pte_fn_t fn, void *data, bool create)
+				     pte_fn_t fn, void *data, bool create,
+				     pgtbl_mod_mask *mask)
 {
 	p4d_t *p4d;
 	unsigned long next;
 	int err = 0;
 
 	if (create) {
-		p4d = p4d_alloc(mm, pgd, addr);
+		p4d = p4d_alloc_track(mm, pgd, addr, mask);
 		if (!p4d)
 			return -ENOMEM;
 	} else {
@@ -2318,7 +2325,7 @@ static int apply_to_p4d_range(struct mm_struct *mm, pgd_t *pgd,
 		next = p4d_addr_end(addr, end);
 		if (create || !p4d_none_or_clear_bad(p4d)) {
 			err = apply_to_pud_range(mm, p4d, addr, next, fn, data,
-						 create);
+						 create, mask);
 			if (err)
 				break;
 		}
@@ -2331,8 +2338,9 @@ static int __apply_to_page_range(struct mm_struct *mm, unsigned long addr,
 				 void *data, bool create)
 {
 	pgd_t *pgd;
-	unsigned long next;
+	unsigned long start = addr, next;
 	unsigned long end = addr + size;
+	pgtbl_mod_mask mask = 0;
 	int err = 0;
 
 	if (WARN_ON(addr >= end))
@@ -2343,11 +2351,14 @@ static int __apply_to_page_range(struct mm_struct *mm, unsigned long addr,
 		next = pgd_addr_end(addr, end);
 		if (!create && pgd_none_or_clear_bad(pgd))
 			continue;
-		err = apply_to_p4d_range(mm, pgd, addr, next, fn, data, create);
+		err = apply_to_p4d_range(mm, pgd, addr, next, fn, data, create, &mask);
 		if (err)
 			break;
 	} while (pgd++, addr = next, addr != end);
 
+	if (mask & ARCH_PAGE_TABLE_SYNC_MASK)
+		arch_sync_kernel_mappings(start, start + size);
+
 	return err;
 }
 
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index e9d5ab5d3ca0..b11a269e2356 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1575,6 +1575,20 @@ static int __ref __offline_pages(unsigned long start_pfn,
 		/* check again */
 		ret = walk_system_ram_range(start_pfn, end_pfn - start_pfn,
 					    NULL, check_pages_isolated_cb);
+		/*
+		 * per-cpu pages are drained in start_isolate_page_range, but if
+		 * there are still pages that are not free, make sure that we
+		 * drain again, because when we isolated range we might
+		 * have raced with another thread that was adding pages to pcp
+		 * list.
+		 *
+		 * Forward progress should be still guaranteed because
+		 * pages on the pcp list can only belong to MOVABLE_ZONE
+		 * because has_unmovable_pages explicitly checks for
+		 * PageBuddy on freed pages on other zones.
+		 */
+		if (ret)
+			drain_all_pages(zone);
 	} while (ret);
 
 	/* Ok, all of our target is isolated.
diff --git a/mm/memremap.c b/mm/memremap.c
index 03e38b7a38f1..006dace60b1a 100644
--- a/mm/memremap.c
+++ b/mm/memremap.c
@@ -216,7 +216,7 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid)
 			return ERR_PTR(-EINVAL);
 		}
 		break;
-	case MEMORY_DEVICE_DEVDAX:
+	case MEMORY_DEVICE_GENERIC:
 		need_devmap_managed = false;
 		break;
 	case MEMORY_DEVICE_PCI_P2PDMA:
diff --git a/mm/migrate.c b/mm/migrate.c
index 34a842a8eb6a..aecb1433cf3c 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -246,13 +246,13 @@ static bool remove_migration_pte(struct page *page, struct vm_area_struct *vma,
 		else if (pte_swp_uffd_wp(*pvmw.pte))
 			pte = pte_mkuffd_wp(pte);
 
-		if (unlikely(is_zone_device_page(new))) {
-			if (is_device_private_page(new)) {
-				entry = make_device_private_entry(new, pte_write(pte));
-				pte = swp_entry_to_pte(entry);
-				if (pte_swp_uffd_wp(*pvmw.pte))
-					pte = pte_mkuffd_wp(pte);
-			}
+		if (unlikely(is_device_private_page(new))) {
+			entry = make_device_private_entry(new, pte_write(pte));
+			pte = swp_entry_to_pte(entry);
+			if (pte_swp_soft_dirty(*pvmw.pte))
+				pte = pte_swp_mksoft_dirty(pte);
+			if (pte_swp_uffd_wp(*pvmw.pte))
+				pte = pte_swp_mkuffd_wp(pte);
 		}
 
 #ifdef CONFIG_HUGETLB_PAGE
@@ -668,7 +668,8 @@ void migrate_page_states(struct page *newpage, struct page *page)
 
 	copy_page_owner(page, newpage);
 
-	mem_cgroup_migrate(page, newpage);
+	if (!PageHuge(page))
+		mem_cgroup_migrate(page, newpage);
 }
 EXPORT_SYMBOL(migrate_page_states);
 
@@ -2427,10 +2428,17 @@ again:
 			entry = make_migration_entry(page, mpfn &
 						     MIGRATE_PFN_WRITE);
 			swp_pte = swp_entry_to_pte(entry);
-			if (pte_soft_dirty(pte))
-				swp_pte = pte_swp_mksoft_dirty(swp_pte);
-			if (pte_uffd_wp(pte))
-				swp_pte = pte_swp_mkuffd_wp(swp_pte);
+			if (pte_present(pte)) {
+				if (pte_soft_dirty(pte))
+					swp_pte = pte_swp_mksoft_dirty(swp_pte);
+				if (pte_uffd_wp(pte))
+					swp_pte = pte_swp_mkuffd_wp(swp_pte);
+			} else {
+				if (pte_swp_soft_dirty(pte))
+					swp_pte = pte_swp_mksoft_dirty(swp_pte);
+				if (pte_swp_uffd_wp(pte))
+					swp_pte = pte_swp_mkuffd_wp(swp_pte);
+			}
 			set_pte_at(mm, addr, ptep, swp_pte);
 
 			/*
diff --git a/mm/mlock.c b/mm/mlock.c
index 93ca2bf30b4f..884b1216da6a 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -58,11 +58,14 @@ EXPORT_SYMBOL(can_do_mlock);
  */
 void clear_page_mlock(struct page *page)
 {
+	int nr_pages;
+
 	if (!TestClearPageMlocked(page))
 		return;
 
-	mod_zone_page_state(page_zone(page), NR_MLOCK, -thp_nr_pages(page));
-	count_vm_event(UNEVICTABLE_PGCLEARED);
+	nr_pages = thp_nr_pages(page);
+	mod_zone_page_state(page_zone(page), NR_MLOCK, -nr_pages);
+	count_vm_events(UNEVICTABLE_PGCLEARED, nr_pages);
 	/*
 	 * The previous TestClearPageMlocked() corresponds to the smp_mb()
 	 * in __pagevec_lru_add_fn().
@@ -76,7 +79,7 @@ void clear_page_mlock(struct page *page)
 		 * We lost the race. the page already moved to evictable list.
 		 */
 		if (PageUnevictable(page))
-			count_vm_event(UNEVICTABLE_PGSTRANDED);
+			count_vm_events(UNEVICTABLE_PGSTRANDED, nr_pages);
 	}
 }
 
@@ -93,9 +96,10 @@ void mlock_vma_page(struct page *page)
 	VM_BUG_ON_PAGE(PageCompound(page) && PageDoubleMap(page), page);
 
 	if (!TestSetPageMlocked(page)) {
-		mod_zone_page_state(page_zone(page), NR_MLOCK,
-				    thp_nr_pages(page));
-		count_vm_event(UNEVICTABLE_PGMLOCKED);
+		int nr_pages = thp_nr_pages(page);
+
+		mod_zone_page_state(page_zone(page), NR_MLOCK, nr_pages);
+		count_vm_events(UNEVICTABLE_PGMLOCKED, nr_pages);
 		if (!isolate_lru_page(page))
 			putback_lru_page(page);
 	}
@@ -138,7 +142,7 @@ static void __munlock_isolated_page(struct page *page)
 
 	/* Did try_to_unlock() succeed or punt? */
 	if (!PageMlocked(page))
-		count_vm_event(UNEVICTABLE_PGMUNLOCKED);
+		count_vm_events(UNEVICTABLE_PGMUNLOCKED, thp_nr_pages(page));
 
 	putback_lru_page(page);
 }
@@ -154,10 +158,12 @@ static void __munlock_isolated_page(struct page *page)
  */
 static void __munlock_isolation_failed(struct page *page)
 {
+	int nr_pages = thp_nr_pages(page);
+
 	if (PageUnevictable(page))
-		__count_vm_event(UNEVICTABLE_PGSTRANDED);
+		__count_vm_events(UNEVICTABLE_PGSTRANDED, nr_pages);
 	else
-		__count_vm_event(UNEVICTABLE_PGMUNLOCKED);
+		__count_vm_events(UNEVICTABLE_PGMUNLOCKED, nr_pages);
 }
 
 /**
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index 242c03121d73..63a3db10a8c0 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -170,6 +170,14 @@ __first_valid_page(unsigned long pfn, unsigned long nr_pages)
  * pageblocks we may have modified and return -EBUSY to caller. This
  * prevents two threads from simultaneously working on overlapping ranges.
  *
+ * Please note that there is no strong synchronization with the page allocator
+ * either. Pages might be freed while their page blocks are marked ISOLATED.
+ * In some cases pages might still end up on pcp lists and that would allow
+ * for their allocation even when they are in fact isolated already. Depending
+ * on how strong of a guarantee the caller needs drain_all_pages might be needed
+ * (e.g. __offline_pages will need to call it after check for isolated range for
+ * a next retry).
+ *
  * Return: the number of isolated pageblocks on success and -EBUSY if any part
  * of range cannot be isolated.
  */
diff --git a/mm/percpu.c b/mm/percpu.c
index f4709629e6de..1ed1a349eab8 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -1316,7 +1316,7 @@ static struct pcpu_chunk * __init pcpu_alloc_first_chunk(unsigned long tmp_addr,
 
 	/* allocate chunk */
 	alloc_size = sizeof(struct pcpu_chunk) +
-		BITS_TO_LONGS(region_size >> PAGE_SHIFT);
+		BITS_TO_LONGS(region_size >> PAGE_SHIFT) * sizeof(unsigned long);
 	chunk = memblock_alloc(alloc_size, SMP_CACHE_BYTES);
 	if (!chunk)
 		panic("%s: Failed to allocate %zu bytes\n", __func__,
diff --git a/mm/rmap.c b/mm/rmap.c
index 83cc459edc40..9425260774a1 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1511,9 +1511,14 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 			 */
 			entry = make_migration_entry(page, 0);
 			swp_pte = swp_entry_to_pte(entry);
-			if (pte_soft_dirty(pteval))
+
+			/*
+			 * pteval maps a zone device page and is therefore
+			 * a swap pte.
+			 */
+			if (pte_swp_soft_dirty(pteval))
 				swp_pte = pte_swp_mksoft_dirty(swp_pte);
-			if (pte_uffd_wp(pteval))
+			if (pte_swp_uffd_wp(pteval))
 				swp_pte = pte_swp_mkuffd_wp(swp_pte);
 			set_pte_at(mm, pvmw.address, pvmw.pte, swp_pte);
 			/*
diff --git a/mm/shmem.c b/mm/shmem.c
index 271548ca20f3..8e2b35ba93ad 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -279,11 +279,13 @@ static int shmem_reserve_inode(struct super_block *sb, ino_t *inop)
 
 	if (!(sb->s_flags & SB_KERNMOUNT)) {
 		spin_lock(&sbinfo->stat_lock);
-		if (!sbinfo->free_inodes) {
-			spin_unlock(&sbinfo->stat_lock);
-			return -ENOSPC;
+		if (sbinfo->max_inodes) {
+			if (!sbinfo->free_inodes) {
+				spin_unlock(&sbinfo->stat_lock);
+				return -ENOSPC;
+			}
+			sbinfo->free_inodes--;
 		}
-		sbinfo->free_inodes--;
 		if (inop) {
 			ino = sbinfo->next_ino++;
 			if (unlikely(is_zero_ino(ino)))
diff --git a/mm/slub.c b/mm/slub.c
index 68c02b2eecd9..d4177aecedf6 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -672,12 +672,12 @@ static void slab_fix(struct kmem_cache *s, char *fmt, ...)
 }
 
 static bool freelist_corrupted(struct kmem_cache *s, struct page *page,
-			       void *freelist, void *nextfree)
+			       void **freelist, void *nextfree)
 {
 	if ((s->flags & SLAB_CONSISTENCY_CHECKS) &&
-	    !check_valid_pointer(s, page, nextfree)) {
-		object_err(s, page, freelist, "Freechain corrupt");
-		freelist = NULL;
+	    !check_valid_pointer(s, page, nextfree) && freelist) {
+		object_err(s, page, *freelist, "Freechain corrupt");
+		*freelist = NULL;
 		slab_fix(s, "Isolate corrupted freechain");
 		return true;
 	}
@@ -1494,7 +1494,7 @@ static inline void dec_slabs_node(struct kmem_cache *s, int node,
 							int objects) {}
 
 static bool freelist_corrupted(struct kmem_cache *s, struct page *page,
-			       void *freelist, void *nextfree)
+			       void **freelist, void *nextfree)
 {
 	return false;
 }
@@ -2184,7 +2184,7 @@ static void deactivate_slab(struct kmem_cache *s, struct page *page,
 		 * 'freelist' is already corrupted.  So isolate all objects
 		 * starting at 'freelist'.
 		 */
-		if (freelist_corrupted(s, page, freelist, nextfree))
+		if (freelist_corrupted(s, page, &freelist, nextfree))
 			break;
 
 		do {
diff --git a/mm/swap.c b/mm/swap.c
index d16d65d9b4e0..e7bdf094f76a 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -494,14 +494,14 @@ void lru_cache_add_inactive_or_unevictable(struct page *page,
 
 	unevictable = (vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) == VM_LOCKED;
 	if (unlikely(unevictable) && !TestSetPageMlocked(page)) {
+		int nr_pages = thp_nr_pages(page);
 		/*
 		 * We use the irq-unsafe __mod_zone_page_stat because this
 		 * counter is not modified from interrupt context, and the pte
 		 * lock is held(spinlock), which implies preemption disabled.
 		 */
-		__mod_zone_page_state(page_zone(page), NR_MLOCK,
-				    thp_nr_pages(page));
-		count_vm_event(UNEVICTABLE_PGMLOCKED);
+		__mod_zone_page_state(page_zone(page), NR_MLOCK, nr_pages);
+		count_vm_events(UNEVICTABLE_PGMLOCKED, nr_pages);
 	}
 	lru_cache_add(page);
 }
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 99e1796eb833..466fc3144fff 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2615,6 +2615,14 @@ static void shrink_node_memcgs(pg_data_t *pgdat, struct scan_control *sc)
 		unsigned long reclaimed;
 		unsigned long scanned;
 
+		/*
+		 * This loop can become CPU-bound when target memcgs
+		 * aren't eligible for reclaim - either because they
+		 * don't have any reclaimable pages, or because their
+		 * memory is explicitly protected. Avoid soft lockups.
+		 */
+		cond_resched();
+
 		mem_cgroup_calculate_protection(target_memcg, memcg);
 
 		if (mem_cgroup_below_min(memcg)) {
@@ -4260,8 +4268,14 @@ void check_move_unevictable_pages(struct pagevec *pvec)
 	for (i = 0; i < pvec->nr; i++) {
 		struct page *page = pvec->pages[i];
 		struct pglist_data *pagepgdat = page_pgdat(page);
+		int nr_pages;
+
+		if (PageTransTail(page))
+			continue;
+
+		nr_pages = thp_nr_pages(page);
+		pgscanned += nr_pages;
 
-		pgscanned++;
 		if (pagepgdat != pgdat) {
 			if (pgdat)
 				spin_unlock_irq(&pgdat->lru_lock);
@@ -4280,7 +4294,7 @@ void check_move_unevictable_pages(struct pagevec *pvec)
 			ClearPageUnevictable(page);
 			del_page_from_lru_list(page, lruvec, LRU_UNEVICTABLE);
 			add_page_to_lru_list(page, lruvec, lru);
-			pgrescued++;
+			pgrescued += nr_pages;
 		}
 	}
 
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index d4bcfd8f95bf..f292e0267bb9 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -51,12 +51,16 @@ static int vlan_group_prealloc_vid(struct vlan_group *vg,
 				   __be16 vlan_proto, u16 vlan_id)
 {
 	struct net_device **array;
-	unsigned int pidx, vidx;
+	unsigned int vidx;
 	unsigned int size;
+	int pidx;
 
 	ASSERT_RTNL();
 
 	pidx  = vlan_proto_idx(vlan_proto);
+	if (pidx < 0)
+		return -EINVAL;
+
 	vidx  = vlan_id / VLAN_GROUP_ARRAY_PART_LEN;
 	array = vg->vlan_devices_arrays[pidx][vidx];
 	if (array != NULL)
diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h
index bb7ec1a3915d..953405362795 100644
--- a/net/8021q/vlan.h
+++ b/net/8021q/vlan.h
@@ -36,7 +36,7 @@ struct vlan_info {
 	struct rcu_head		rcu;
 };
 
-static inline unsigned int vlan_proto_idx(__be16 proto)
+static inline int vlan_proto_idx(__be16 proto)
 {
 	switch (proto) {
 	case htons(ETH_P_8021Q):
@@ -44,8 +44,8 @@ static inline unsigned int vlan_proto_idx(__be16 proto)
 	case htons(ETH_P_8021AD):
 		return VLAN_PROTO_8021AD;
 	default:
-		BUG();
-		return 0;
+		WARN(1, "invalid VLAN protocol: 0x%04x\n", ntohs(proto));
+		return -EINVAL;
 	}
 }
 
@@ -64,17 +64,24 @@ static inline struct net_device *vlan_group_get_device(struct vlan_group *vg,
 						       __be16 vlan_proto,
 						       u16 vlan_id)
 {
-	return __vlan_group_get_device(vg, vlan_proto_idx(vlan_proto), vlan_id);
+	int pidx = vlan_proto_idx(vlan_proto);
+
+	if (pidx < 0)
+		return NULL;
+
+	return __vlan_group_get_device(vg, pidx, vlan_id);
 }
 
 static inline void vlan_group_set_device(struct vlan_group *vg,
 					 __be16 vlan_proto, u16 vlan_id,
 					 struct net_device *dev)
 {
+	int pidx = vlan_proto_idx(vlan_proto);
 	struct net_device **array;
-	if (!vg)
+
+	if (!vg || pidx < 0)
 		return;
-	array = vg->vlan_devices_arrays[vlan_proto_idx(vlan_proto)]
+	array = vg->vlan_devices_arrays[pidx]
 				       [vlan_id / VLAN_GROUP_ARRAY_PART_LEN];
 	array[vlan_id % VLAN_GROUP_ARRAY_PART_LEN] = dev;
 }
diff --git a/net/Kconfig b/net/Kconfig
index 3831206977a1..d6567162c1cf 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -434,7 +434,6 @@ config NET_SOCK_MSG
 config NET_DEVLINK
 	bool
 	default n
-	imply NET_DROP_MONITOR
 
 config PAGE_POOL
 	bool
diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c
index ab6cec3c7586..ba0027d1f2df 100644
--- a/net/batman-adv/bridge_loop_avoidance.c
+++ b/net/batman-adv/bridge_loop_avoidance.c
@@ -25,6 +25,7 @@
 #include <linux/lockdep.h>
 #include <linux/netdevice.h>
 #include <linux/netlink.h>
+#include <linux/preempt.h>
 #include <linux/rculist.h>
 #include <linux/rcupdate.h>
 #include <linux/seq_file.h>
@@ -83,11 +84,12 @@ static inline u32 batadv_choose_claim(const void *data, u32 size)
  */
 static inline u32 batadv_choose_backbone_gw(const void *data, u32 size)
 {
-	const struct batadv_bla_claim *claim = (struct batadv_bla_claim *)data;
+	const struct batadv_bla_backbone_gw *gw;
 	u32 hash = 0;
 
-	hash = jhash(&claim->addr, sizeof(claim->addr), hash);
-	hash = jhash(&claim->vid, sizeof(claim->vid), hash);
+	gw = (struct batadv_bla_backbone_gw *)data;
+	hash = jhash(&gw->orig, sizeof(gw->orig), hash);
+	hash = jhash(&gw->vid, sizeof(gw->vid), hash);
 
 	return hash % size;
 }
@@ -1579,13 +1581,16 @@ int batadv_bla_init(struct batadv_priv *bat_priv)
 }
 
 /**
- * batadv_bla_check_bcast_duplist() - Check if a frame is in the broadcast dup.
+ * batadv_bla_check_duplist() - Check if a frame is in the broadcast dup.
  * @bat_priv: the bat priv with all the soft interface information
- * @skb: contains the bcast_packet to be checked
+ * @skb: contains the multicast packet to be checked
+ * @payload_ptr: pointer to position inside the head buffer of the skb
+ *  marking the start of the data to be CRC'ed
+ * @orig: originator mac address, NULL if unknown
  *
- * check if it is on our broadcast list. Another gateway might
- * have sent the same packet because it is connected to the same backbone,
- * so we have to remove this duplicate.
+ * Check if it is on our broadcast list. Another gateway might have sent the
+ * same packet because it is connected to the same backbone, so we have to
+ * remove this duplicate.
  *
  * This is performed by checking the CRC, which will tell us
  * with a good chance that it is the same packet. If it is furthermore
@@ -1594,19 +1599,17 @@ int batadv_bla_init(struct batadv_priv *bat_priv)
  *
  * Return: true if a packet is in the duplicate list, false otherwise.
  */
-bool batadv_bla_check_bcast_duplist(struct batadv_priv *bat_priv,
-				    struct sk_buff *skb)
+static bool batadv_bla_check_duplist(struct batadv_priv *bat_priv,
+				     struct sk_buff *skb, u8 *payload_ptr,
+				     const u8 *orig)
 {
-	int i, curr;
-	__be32 crc;
-	struct batadv_bcast_packet *bcast_packet;
 	struct batadv_bcast_duplist_entry *entry;
 	bool ret = false;
-
-	bcast_packet = (struct batadv_bcast_packet *)skb->data;
+	int i, curr;
+	__be32 crc;
 
 	/* calculate the crc ... */
-	crc = batadv_skb_crc32(skb, (u8 *)(bcast_packet + 1));
+	crc = batadv_skb_crc32(skb, payload_ptr);
 
 	spin_lock_bh(&bat_priv->bla.bcast_duplist_lock);
 
@@ -1625,8 +1628,21 @@ bool batadv_bla_check_bcast_duplist(struct batadv_priv *bat_priv,
 		if (entry->crc != crc)
 			continue;
 
-		if (batadv_compare_eth(entry->orig, bcast_packet->orig))
-			continue;
+		/* are the originators both known and not anonymous? */
+		if (orig && !is_zero_ether_addr(orig) &&
+		    !is_zero_ether_addr(entry->orig)) {
+			/* If known, check if the new frame came from
+			 * the same originator:
+			 * We are safe to take identical frames from the
+			 * same orig, if known, as multiplications in
+			 * the mesh are detected via the (orig, seqno) pair.
+			 * So we can be a bit more liberal here and allow
+			 * identical frames from the same orig which the source
+			 * host might have sent multiple times on purpose.
+			 */
+			if (batadv_compare_eth(entry->orig, orig))
+				continue;
+		}
 
 		/* this entry seems to match: same crc, not too old,
 		 * and from another gw. therefore return true to forbid it.
@@ -1642,7 +1658,14 @@ bool batadv_bla_check_bcast_duplist(struct batadv_priv *bat_priv,
 	entry = &bat_priv->bla.bcast_duplist[curr];
 	entry->crc = crc;
 	entry->entrytime = jiffies;
-	ether_addr_copy(entry->orig, bcast_packet->orig);
+
+	/* known originator */
+	if (orig)
+		ether_addr_copy(entry->orig, orig);
+	/* anonymous originator */
+	else
+		eth_zero_addr(entry->orig);
+
 	bat_priv->bla.bcast_duplist_curr = curr;
 
 out:
@@ -1652,6 +1675,48 @@ out:
 }
 
 /**
+ * batadv_bla_check_ucast_duplist() - Check if a frame is in the broadcast dup.
+ * @bat_priv: the bat priv with all the soft interface information
+ * @skb: contains the multicast packet to be checked, decapsulated from a
+ *  unicast_packet
+ *
+ * Check if it is on our broadcast list. Another gateway might have sent the
+ * same packet because it is connected to the same backbone, so we have to
+ * remove this duplicate.
+ *
+ * Return: true if a packet is in the duplicate list, false otherwise.
+ */
+static bool batadv_bla_check_ucast_duplist(struct batadv_priv *bat_priv,
+					   struct sk_buff *skb)
+{
+	return batadv_bla_check_duplist(bat_priv, skb, (u8 *)skb->data, NULL);
+}
+
+/**
+ * batadv_bla_check_bcast_duplist() - Check if a frame is in the broadcast dup.
+ * @bat_priv: the bat priv with all the soft interface information
+ * @skb: contains the bcast_packet to be checked
+ *
+ * Check if it is on our broadcast list. Another gateway might have sent the
+ * same packet because it is connected to the same backbone, so we have to
+ * remove this duplicate.
+ *
+ * Return: true if a packet is in the duplicate list, false otherwise.
+ */
+bool batadv_bla_check_bcast_duplist(struct batadv_priv *bat_priv,
+				    struct sk_buff *skb)
+{
+	struct batadv_bcast_packet *bcast_packet;
+	u8 *payload_ptr;
+
+	bcast_packet = (struct batadv_bcast_packet *)skb->data;
+	payload_ptr = (u8 *)(bcast_packet + 1);
+
+	return batadv_bla_check_duplist(bat_priv, skb, payload_ptr,
+					bcast_packet->orig);
+}
+
+/**
  * batadv_bla_is_backbone_gw_orig() - Check if the originator is a gateway for
  *  the VLAN identified by vid.
  * @bat_priv: the bat priv with all the soft interface information
@@ -1812,7 +1877,7 @@ batadv_bla_loopdetect_check(struct batadv_priv *bat_priv, struct sk_buff *skb,
  * @bat_priv: the bat priv with all the soft interface information
  * @skb: the frame to be checked
  * @vid: the VLAN ID of the frame
- * @is_bcast: the packet came in a broadcast packet type.
+ * @packet_type: the batman packet type this frame came in
  *
  * batadv_bla_rx avoidance checks if:
  *  * we have to race for a claim
@@ -1824,7 +1889,7 @@ batadv_bla_loopdetect_check(struct batadv_priv *bat_priv, struct sk_buff *skb,
  * further process the skb.
  */
 bool batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb,
-		   unsigned short vid, bool is_bcast)
+		   unsigned short vid, int packet_type)
 {
 	struct batadv_bla_backbone_gw *backbone_gw;
 	struct ethhdr *ethhdr;
@@ -1846,9 +1911,32 @@ bool batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb,
 		goto handled;
 
 	if (unlikely(atomic_read(&bat_priv->bla.num_requests)))
-		/* don't allow broadcasts while requests are in flight */
-		if (is_multicast_ether_addr(ethhdr->h_dest) && is_bcast)
-			goto handled;
+		/* don't allow multicast packets while requests are in flight */
+		if (is_multicast_ether_addr(ethhdr->h_dest))
+			/* Both broadcast flooding or multicast-via-unicasts
+			 * delivery might send to multiple backbone gateways
+			 * sharing the same LAN and therefore need to coordinate
+			 * which backbone gateway forwards into the LAN,
+			 * by claiming the payload source address.
+			 *
+			 * Broadcast flooding and multicast-via-unicasts
+			 * delivery use the following two batman packet types.
+			 * Note: explicitly exclude BATADV_UNICAST_4ADDR,
+			 * as the DHCP gateway feature will send explicitly
+			 * to only one BLA gateway, so the claiming process
+			 * should be avoided there.
+			 */
+			if (packet_type == BATADV_BCAST ||
+			    packet_type == BATADV_UNICAST)
+				goto handled;
+
+	/* potential duplicates from foreign BLA backbone gateways via
+	 * multicast-in-unicast packets
+	 */
+	if (is_multicast_ether_addr(ethhdr->h_dest) &&
+	    packet_type == BATADV_UNICAST &&
+	    batadv_bla_check_ucast_duplist(bat_priv, skb))
+		goto handled;
 
 	ether_addr_copy(search_claim.addr, ethhdr->h_source);
 	search_claim.vid = vid;
@@ -1883,13 +1971,14 @@ bool batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb,
 		goto allow;
 	}
 
-	/* if it is a broadcast ... */
-	if (is_multicast_ether_addr(ethhdr->h_dest) && is_bcast) {
+	/* if it is a multicast ... */
+	if (is_multicast_ether_addr(ethhdr->h_dest) &&
+	    (packet_type == BATADV_BCAST || packet_type == BATADV_UNICAST)) {
 		/* ... drop it. the responsible gateway is in charge.
 		 *
-		 * We need to check is_bcast because with the gateway
+		 * We need to check packet type because with the gateway
 		 * feature, broadcasts (like DHCP requests) may be sent
-		 * using a unicast packet type.
+		 * using a unicast 4 address packet type. See comment above.
 		 */
 		goto handled;
 	} else {
diff --git a/net/batman-adv/bridge_loop_avoidance.h b/net/batman-adv/bridge_loop_avoidance.h
index 41edb2c4a327..a81c41b636f9 100644
--- a/net/batman-adv/bridge_loop_avoidance.h
+++ b/net/batman-adv/bridge_loop_avoidance.h
@@ -35,7 +35,7 @@ static inline bool batadv_bla_is_loopdetect_mac(const uint8_t *mac)
 
 #ifdef CONFIG_BATMAN_ADV_BLA
 bool batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb,
-		   unsigned short vid, bool is_bcast);
+		   unsigned short vid, int packet_type);
 bool batadv_bla_tx(struct batadv_priv *bat_priv, struct sk_buff *skb,
 		   unsigned short vid);
 bool batadv_bla_is_backbone_gw(struct sk_buff *skb,
@@ -66,7 +66,7 @@ bool batadv_bla_check_claim(struct batadv_priv *bat_priv, u8 *addr,
 
 static inline bool batadv_bla_rx(struct batadv_priv *bat_priv,
 				 struct sk_buff *skb, unsigned short vid,
-				 bool is_bcast)
+				 int packet_type)
 {
 	return false;
 }
diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c
index 1622c3f5898f..9af99c39b9fd 100644
--- a/net/batman-adv/multicast.c
+++ b/net/batman-adv/multicast.c
@@ -51,6 +51,7 @@
 #include <uapi/linux/batadv_packet.h>
 #include <uapi/linux/batman_adv.h>
 
+#include "bridge_loop_avoidance.h"
 #include "hard-interface.h"
 #include "hash.h"
 #include "log.h"
@@ -220,7 +221,7 @@ static u8 batadv_mcast_mla_rtr_flags_bridge_get(struct batadv_priv *bat_priv,
 		 * address here, only IPv6 ones
 		 */
 		if (br_ip_entry->addr.proto == htons(ETH_P_IPV6) &&
-		    ipv6_addr_is_ll_all_routers(&br_ip_entry->addr.u.ip6))
+		    ipv6_addr_is_ll_all_routers(&br_ip_entry->addr.dst.ip6))
 			flags &= ~BATADV_MCAST_WANT_NO_RTR6;
 
 		list_del(&br_ip_entry->list);
@@ -561,10 +562,10 @@ out:
 static void batadv_mcast_mla_br_addr_cpy(char *dst, const struct br_ip *src)
 {
 	if (src->proto == htons(ETH_P_IP))
-		ip_eth_mc_map(src->u.ip4, dst);
+		ip_eth_mc_map(src->dst.ip4, dst);
 #if IS_ENABLED(CONFIG_IPV6)
 	else if (src->proto == htons(ETH_P_IPV6))
-		ipv6_eth_mc_map(&src->u.ip6, dst);
+		ipv6_eth_mc_map(&src->dst.ip6, dst);
 #endif
 	else
 		eth_zero_addr(dst);
@@ -608,11 +609,11 @@ static int batadv_mcast_mla_bridge_get(struct net_device *dev,
 				continue;
 
 			if (tvlv_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES &&
-			    ipv4_is_local_multicast(br_ip_entry->addr.u.ip4))
+			    ipv4_is_local_multicast(br_ip_entry->addr.dst.ip4))
 				continue;
 
 			if (!(tvlv_flags & BATADV_MCAST_WANT_NO_RTR4) &&
-			    !ipv4_is_local_multicast(br_ip_entry->addr.u.ip4))
+			    !ipv4_is_local_multicast(br_ip_entry->addr.dst.ip4))
 				continue;
 		}
 
@@ -622,11 +623,11 @@ static int batadv_mcast_mla_bridge_get(struct net_device *dev,
 				continue;
 
 			if (tvlv_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES &&
-			    ipv6_addr_is_ll_all_nodes(&br_ip_entry->addr.u.ip6))
+			    ipv6_addr_is_ll_all_nodes(&br_ip_entry->addr.dst.ip6))
 				continue;
 
 			if (!(tvlv_flags & BATADV_MCAST_WANT_NO_RTR6) &&
-			    IPV6_ADDR_MC_SCOPE(&br_ip_entry->addr.u.ip6) >
+			    IPV6_ADDR_MC_SCOPE(&br_ip_entry->addr.dst.ip6) >
 			    IPV6_ADDR_SCOPE_LINKLOCAL)
 				continue;
 		}
@@ -1435,6 +1436,35 @@ batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb,
 }
 
 /**
+ * batadv_mcast_forw_send_orig() - send a multicast packet to an originator
+ * @bat_priv: the bat priv with all the soft interface information
+ * @skb: the multicast packet to send
+ * @vid: the vlan identifier
+ * @orig_node: the originator to send the packet to
+ *
+ * Return: NET_XMIT_DROP in case of error or NET_XMIT_SUCCESS otherwise.
+ */
+int batadv_mcast_forw_send_orig(struct batadv_priv *bat_priv,
+				struct sk_buff *skb,
+				unsigned short vid,
+				struct batadv_orig_node *orig_node)
+{
+	/* Avoid sending multicast-in-unicast packets to other BLA
+	 * gateways - they already got the frame from the LAN side
+	 * we share with them.
+	 * TODO: Refactor to take BLA into account earlier, to avoid
+	 * reducing the mcast_fanout count.
+	 */
+	if (batadv_bla_is_backbone_gw_orig(bat_priv, orig_node->orig, vid)) {
+		dev_kfree_skb(skb);
+		return NET_XMIT_SUCCESS;
+	}
+
+	return batadv_send_skb_unicast(bat_priv, skb, BATADV_UNICAST, 0,
+				       orig_node, vid);
+}
+
+/**
  * batadv_mcast_forw_tt() - forwards a packet to multicast listeners
  * @bat_priv: the bat priv with all the soft interface information
  * @skb: the multicast packet to transmit
@@ -1471,8 +1501,8 @@ batadv_mcast_forw_tt(struct batadv_priv *bat_priv, struct sk_buff *skb,
 			break;
 		}
 
-		batadv_send_skb_unicast(bat_priv, newskb, BATADV_UNICAST, 0,
-					orig_entry->orig_node, vid);
+		batadv_mcast_forw_send_orig(bat_priv, newskb, vid,
+					    orig_entry->orig_node);
 	}
 	rcu_read_unlock();
 
@@ -1513,8 +1543,7 @@ batadv_mcast_forw_want_all_ipv4(struct batadv_priv *bat_priv,
 			break;
 		}
 
-		batadv_send_skb_unicast(bat_priv, newskb, BATADV_UNICAST, 0,
-					orig_node, vid);
+		batadv_mcast_forw_send_orig(bat_priv, newskb, vid, orig_node);
 	}
 	rcu_read_unlock();
 	return ret;
@@ -1551,8 +1580,7 @@ batadv_mcast_forw_want_all_ipv6(struct batadv_priv *bat_priv,
 			break;
 		}
 
-		batadv_send_skb_unicast(bat_priv, newskb, BATADV_UNICAST, 0,
-					orig_node, vid);
+		batadv_mcast_forw_send_orig(bat_priv, newskb, vid, orig_node);
 	}
 	rcu_read_unlock();
 	return ret;
@@ -1618,8 +1646,7 @@ batadv_mcast_forw_want_all_rtr4(struct batadv_priv *bat_priv,
 			break;
 		}
 
-		batadv_send_skb_unicast(bat_priv, newskb, BATADV_UNICAST, 0,
-					orig_node, vid);
+		batadv_mcast_forw_send_orig(bat_priv, newskb, vid, orig_node);
 	}
 	rcu_read_unlock();
 	return ret;
@@ -1656,8 +1683,7 @@ batadv_mcast_forw_want_all_rtr6(struct batadv_priv *bat_priv,
 			break;
 		}
 
-		batadv_send_skb_unicast(bat_priv, newskb, BATADV_UNICAST, 0,
-					orig_node, vid);
+		batadv_mcast_forw_send_orig(bat_priv, newskb, vid, orig_node);
 	}
 	rcu_read_unlock();
 	return ret;
diff --git a/net/batman-adv/multicast.h b/net/batman-adv/multicast.h
index ebf825991ecd..3e114bc5ca3b 100644
--- a/net/batman-adv/multicast.h
+++ b/net/batman-adv/multicast.h
@@ -46,6 +46,11 @@ enum batadv_forw_mode
 batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb,
 		       struct batadv_orig_node **mcast_single_orig);
 
+int batadv_mcast_forw_send_orig(struct batadv_priv *bat_priv,
+				struct sk_buff *skb,
+				unsigned short vid,
+				struct batadv_orig_node *orig_node);
+
 int batadv_mcast_forw_send(struct batadv_priv *bat_priv, struct sk_buff *skb,
 			   unsigned short vid);
 
@@ -72,6 +77,16 @@ batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb,
 }
 
 static inline int
+batadv_mcast_forw_send_orig(struct batadv_priv *bat_priv,
+			    struct sk_buff *skb,
+			    unsigned short vid,
+			    struct batadv_orig_node *orig_node)
+{
+	kfree_skb(skb);
+	return NET_XMIT_DROP;
+}
+
+static inline int
 batadv_mcast_forw_send(struct batadv_priv *bat_priv, struct sk_buff *skb,
 		       unsigned short vid)
 {
diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c
index dc193618a761..c7a55647b520 100644
--- a/net/batman-adv/netlink.c
+++ b/net/batman-adv/netlink.c
@@ -1350,7 +1350,7 @@ static void batadv_post_doit(const struct genl_ops *ops, struct sk_buff *skb,
 	}
 }
 
-static const struct genl_ops batadv_netlink_ops[] = {
+static const struct genl_small_ops batadv_netlink_ops[] = {
 	{
 		.cmd = BATADV_CMD_GET_MESH,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
@@ -1484,8 +1484,8 @@ struct genl_family batadv_netlink_family __ro_after_init = {
 	.pre_doit = batadv_pre_doit,
 	.post_doit = batadv_post_doit,
 	.module = THIS_MODULE,
-	.ops = batadv_netlink_ops,
-	.n_ops = ARRAY_SIZE(batadv_netlink_ops),
+	.small_ops = batadv_netlink_ops,
+	.n_small_ops = ARRAY_SIZE(batadv_netlink_ops),
 	.mcgrps = batadv_netlink_mcgrps,
 	.n_mcgrps = ARRAY_SIZE(batadv_netlink_mcgrps),
 };
diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c
index 27cdf5e4349a..9e5c71e406ff 100644
--- a/net/batman-adv/routing.c
+++ b/net/batman-adv/routing.c
@@ -826,6 +826,10 @@ static bool batadv_check_unicast_ttvn(struct batadv_priv *bat_priv,
 	vid = batadv_get_vid(skb, hdr_len);
 	ethhdr = (struct ethhdr *)(skb->data + hdr_len);
 
+	/* do not reroute multicast frames in a unicast header */
+	if (is_multicast_ether_addr(ethhdr->h_dest))
+		return true;
+
 	/* check if the destination client was served by this node and it is now
 	 * roaming. In this case, it means that the node has got a ROAM_ADV
 	 * message and that it knows the new destination in the mesh to re-route
diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index 9d3974ba11ed..82e7ca886605 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -364,9 +364,8 @@ send:
 				goto dropped;
 			ret = batadv_send_skb_via_gw(bat_priv, skb, vid);
 		} else if (mcast_single_orig) {
-			ret = batadv_send_skb_unicast(bat_priv, skb,
-						      BATADV_UNICAST, 0,
-						      mcast_single_orig, vid);
+			ret = batadv_mcast_forw_send_orig(bat_priv, skb, vid,
+							  mcast_single_orig);
 		} else if (forw_mode == BATADV_FORW_SOME) {
 			ret = batadv_mcast_forw_send(bat_priv, skb, vid);
 		} else {
@@ -425,10 +424,10 @@ void batadv_interface_rx(struct net_device *soft_iface,
 	struct vlan_ethhdr *vhdr;
 	struct ethhdr *ethhdr;
 	unsigned short vid;
-	bool is_bcast;
+	int packet_type;
 
 	batadv_bcast_packet = (struct batadv_bcast_packet *)skb->data;
-	is_bcast = (batadv_bcast_packet->packet_type == BATADV_BCAST);
+	packet_type = batadv_bcast_packet->packet_type;
 
 	skb_pull_rcsum(skb, hdr_size);
 	skb_reset_mac_header(skb);
@@ -471,7 +470,7 @@ void batadv_interface_rx(struct net_device *soft_iface,
 	/* Let the bridge loop avoidance check the packet. If will
 	 * not handle it, we can safely push it up.
 	 */
-	if (batadv_bla_rx(bat_priv, skb, vid, is_bcast))
+	if (batadv_bla_rx(bat_priv, skb, vid, packet_type))
 		goto out;
 
 	if (orig_node)
diff --git a/net/bluetooth/Kconfig b/net/bluetooth/Kconfig
index e2497d764e97..64e669acd42f 100644
--- a/net/bluetooth/Kconfig
+++ b/net/bluetooth/Kconfig
@@ -64,7 +64,6 @@ source "net/bluetooth/hidp/Kconfig"
 config BT_HS
 	bool "Bluetooth High Speed (HS) features"
 	depends on BT_BREDR
-	default y
 	help
 	  Bluetooth High Speed includes support for off-loading
 	  Bluetooth connections via 802.11 (wifi) physical layer
diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c
index 26526be579c7..da7fd7c8c2dc 100644
--- a/net/bluetooth/a2mp.c
+++ b/net/bluetooth/a2mp.c
@@ -226,6 +226,9 @@ static int a2mp_discover_rsp(struct amp_mgr *mgr, struct sk_buff *skb,
 			struct a2mp_info_req req;
 
 			found = true;
+
+			memset(&req, 0, sizeof(req));
+
 			req.id = cl->id;
 			a2mp_send(mgr, A2MP_GETINFO_REQ, __next_ident(mgr),
 				  sizeof(req), &req);
@@ -305,6 +308,8 @@ static int a2mp_getinfo_req(struct amp_mgr *mgr, struct sk_buff *skb,
 	if (!hdev || hdev->dev_type != HCI_AMP) {
 		struct a2mp_info_rsp rsp;
 
+		memset(&rsp, 0, sizeof(rsp));
+
 		rsp.id = req->id;
 		rsp.status = A2MP_STATUS_INVALID_CTRL_ID;
 
@@ -348,6 +353,8 @@ static int a2mp_getinfo_rsp(struct amp_mgr *mgr, struct sk_buff *skb,
 	if (!ctrl)
 		return -ENOMEM;
 
+	memset(&req, 0, sizeof(req));
+
 	req.id = rsp->id;
 	a2mp_send(mgr, A2MP_GETAMPASSOC_REQ, __next_ident(mgr), sizeof(req),
 		  &req);
@@ -376,6 +383,8 @@ static int a2mp_getampassoc_req(struct amp_mgr *mgr, struct sk_buff *skb,
 		struct a2mp_amp_assoc_rsp rsp;
 		rsp.id = req->id;
 
+		memset(&rsp, 0, sizeof(rsp));
+
 		if (tmp) {
 			rsp.status = A2MP_STATUS_COLLISION_OCCURED;
 			amp_mgr_put(tmp);
@@ -464,7 +473,6 @@ static int a2mp_createphyslink_req(struct amp_mgr *mgr, struct sk_buff *skb,
 				   struct a2mp_cmd *hdr)
 {
 	struct a2mp_physlink_req *req = (void *) skb->data;
-
 	struct a2mp_physlink_rsp rsp;
 	struct hci_dev *hdev;
 	struct hci_conn *hcon;
@@ -475,6 +483,8 @@ static int a2mp_createphyslink_req(struct amp_mgr *mgr, struct sk_buff *skb,
 
 	BT_DBG("local_id %d, remote_id %d", req->local_id, req->remote_id);
 
+	memset(&rsp, 0, sizeof(rsp));
+
 	rsp.local_id = req->remote_id;
 	rsp.remote_id = req->local_id;
 
@@ -553,6 +563,8 @@ static int a2mp_discphyslink_req(struct amp_mgr *mgr, struct sk_buff *skb,
 
 	BT_DBG("local_id %d remote_id %d", req->local_id, req->remote_id);
 
+	memset(&rsp, 0, sizeof(rsp));
+
 	rsp.local_id = req->remote_id;
 	rsp.remote_id = req->local_id;
 	rsp.status = A2MP_STATUS_SUCCESS;
@@ -675,6 +687,8 @@ static int a2mp_chan_recv_cb(struct l2cap_chan *chan, struct sk_buff *skb)
 	if (err) {
 		struct a2mp_cmd_rej rej;
 
+		memset(&rej, 0, sizeof(rej));
+
 		rej.reason = cpu_to_le16(0);
 		hdr = (void *) skb->data;
 
@@ -898,6 +912,8 @@ void a2mp_send_getinfo_rsp(struct hci_dev *hdev)
 
 	BT_DBG("%s mgr %p", hdev->name, mgr);
 
+	memset(&rsp, 0, sizeof(rsp));
+
 	rsp.id = hdev->id;
 	rsp.status = A2MP_STATUS_INVALID_CTRL_ID;
 
@@ -995,6 +1011,8 @@ void a2mp_send_create_phy_link_rsp(struct hci_dev *hdev, u8 status)
 	if (!mgr)
 		return;
 
+	memset(&rsp, 0, sizeof(rsp));
+
 	hs_hcon = hci_conn_hash_lookup_state(hdev, AMP_LINK, BT_CONNECT);
 	if (!hs_hcon) {
 		rsp.status = A2MP_STATUS_UNABLE_START_LINK_CREATION;
@@ -1027,6 +1045,8 @@ void a2mp_discover_amp(struct l2cap_chan *chan)
 
 	mgr->bredr_chan = chan;
 
+	memset(&req, 0, sizeof(req));
+
 	req.mtu = cpu_to_le16(L2CAP_A2MP_DEFAULT_MTU);
 	req.ext_feat = 0;
 	a2mp_send(mgr, A2MP_DISCOVER_REQ, 1, sizeof(req), &req);
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index b0209e35284a..502552d6e9af 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -2963,7 +2963,7 @@ int hci_add_adv_instance(struct hci_dev *hdev, u8 instance, u32 flags,
 		       sizeof(adv_instance->scan_rsp_data));
 	} else {
 		if (hdev->adv_instance_cnt >= hdev->le_num_of_adv_sets ||
-		    instance < 1 || instance > HCI_MAX_ADV_INSTANCES)
+		    instance < 1 || instance > hdev->le_num_of_adv_sets)
 			return -EOVERFLOW;
 
 		adv_instance = kzalloc(sizeof(*adv_instance), GFP_KERNEL);
@@ -3061,6 +3061,7 @@ static int free_adv_monitor(int id, void *ptr, void *data)
 
 	idr_remove(&hdev->adv_monitors_idr, monitor->handle);
 	hci_free_adv_monitor(monitor);
+	hdev->adv_monitors_cnt--;
 
 	return 0;
 }
@@ -3077,6 +3078,7 @@ int hci_remove_adv_monitor(struct hci_dev *hdev, u16 handle)
 
 		idr_remove(&hdev->adv_monitors_idr, monitor->handle);
 		hci_free_adv_monitor(monitor);
+		hdev->adv_monitors_cnt--;
 	} else {
 		/* Remove all monitors if handle is 0. */
 		idr_for_each(&hdev->adv_monitors_idr, &free_adv_monitor, hdev);
@@ -3442,6 +3444,16 @@ void hci_copy_identity_address(struct hci_dev *hdev, bdaddr_t *bdaddr,
 	}
 }
 
+static void hci_suspend_clear_tasks(struct hci_dev *hdev)
+{
+	int i;
+
+	for (i = 0; i < __SUSPEND_NUM_TASKS; i++)
+		clear_bit(i, hdev->suspend_tasks);
+
+	wake_up(&hdev->suspend_wait_q);
+}
+
 static int hci_suspend_wait_event(struct hci_dev *hdev)
 {
 #define WAKE_COND                                                              \
@@ -3487,12 +3499,24 @@ static int hci_change_suspend_state(struct hci_dev *hdev,
 	return hci_suspend_wait_event(hdev);
 }
 
+static void hci_clear_wake_reason(struct hci_dev *hdev)
+{
+	hci_dev_lock(hdev);
+
+	hdev->wake_reason = 0;
+	bacpy(&hdev->wake_addr, BDADDR_ANY);
+	hdev->wake_addr_type = 0;
+
+	hci_dev_unlock(hdev);
+}
+
 static int hci_suspend_notifier(struct notifier_block *nb, unsigned long action,
 				void *data)
 {
 	struct hci_dev *hdev =
 		container_of(nb, struct hci_dev, suspend_notifier);
 	int ret = 0;
+	u8 state = BT_RUNNING;
 
 	/* If powering down, wait for completion. */
 	if (mgmt_powering_down(hdev)) {
@@ -3513,15 +3537,27 @@ static int hci_suspend_notifier(struct notifier_block *nb, unsigned long action,
 		 *  - Second, program event filter/whitelist and enable scan
 		 */
 		ret = hci_change_suspend_state(hdev, BT_SUSPEND_DISCONNECT);
+		if (!ret)
+			state = BT_SUSPEND_DISCONNECT;
 
 		/* Only configure whitelist if disconnect succeeded and wake
 		 * isn't being prevented.
 		 */
-		if (!ret && !(hdev->prevent_wake && hdev->prevent_wake(hdev)))
+		if (!ret && !(hdev->prevent_wake && hdev->prevent_wake(hdev))) {
 			ret = hci_change_suspend_state(hdev,
 						BT_SUSPEND_CONFIGURE_WAKE);
+			if (!ret)
+				state = BT_SUSPEND_CONFIGURE_WAKE;
+		}
+
+		hci_clear_wake_reason(hdev);
+		mgmt_suspending(hdev, state);
+
 	} else if (action == PM_POST_SUSPEND) {
 		ret = hci_change_suspend_state(hdev, BT_RUNNING);
+
+		mgmt_resuming(hdev, hdev->wake_reason, &hdev->wake_addr,
+			      hdev->wake_addr_type);
 	}
 
 done:
@@ -3784,6 +3820,7 @@ void hci_unregister_dev(struct hci_dev *hdev)
 
 	cancel_work_sync(&hdev->power_on);
 
+	hci_suspend_clear_tasks(hdev);
 	unregister_pm_notifier(&hdev->suspend_notifier);
 	cancel_work_sync(&hdev->suspend_prepare);
 
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 4b7fc430793c..f04963914366 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -2569,7 +2569,6 @@ static void hci_inquiry_result_evt(struct hci_dev *hdev, struct sk_buff *skb)
 static void hci_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 {
 	struct hci_ev_conn_complete *ev = (void *) skb->data;
-	struct inquiry_entry *ie;
 	struct hci_conn *conn;
 
 	BT_DBG("%s", hdev->name);
@@ -2578,13 +2577,19 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 
 	conn = hci_conn_hash_lookup_ba(hdev, ev->link_type, &ev->bdaddr);
 	if (!conn) {
-		/* Connection may not exist if auto-connected. Check the inquiry
-		 * cache to see if we've already discovered this bdaddr before.
-		 * If found and link is an ACL type, create a connection class
+		/* Connection may not exist if auto-connected. Check the bredr
+		 * allowlist to see if this device is allowed to auto connect.
+		 * If link is an ACL type, create a connection class
 		 * automatically.
+		 *
+		 * Auto-connect will only occur if the event filter is
+		 * programmed with a given address. Right now, event filter is
+		 * only used during suspend.
 		 */
-		ie = hci_inquiry_cache_lookup(hdev, &ev->bdaddr);
-		if (ie && ev->link_type == ACL_LINK) {
+		if (ev->link_type == ACL_LINK &&
+		    hci_bdaddr_list_lookup_with_flags(&hdev->whitelist,
+						      &ev->bdaddr,
+						      BDADDR_BREDR)) {
 			conn = hci_conn_add(hdev, ev->link_type, &ev->bdaddr,
 					    HCI_ROLE_SLAVE);
 			if (!conn) {
@@ -6012,6 +6017,75 @@ static bool hci_get_cmd_complete(struct hci_dev *hdev, u16 opcode,
 	return true;
 }
 
+static void hci_store_wake_reason(struct hci_dev *hdev, u8 event,
+				  struct sk_buff *skb)
+{
+	struct hci_ev_le_advertising_info *adv;
+	struct hci_ev_le_direct_adv_info *direct_adv;
+	struct hci_ev_le_ext_adv_report *ext_adv;
+	const struct hci_ev_conn_complete *conn_complete = (void *)skb->data;
+	const struct hci_ev_conn_request *conn_request = (void *)skb->data;
+
+	hci_dev_lock(hdev);
+
+	/* If we are currently suspended and this is the first BT event seen,
+	 * save the wake reason associated with the event.
+	 */
+	if (!hdev->suspended || hdev->wake_reason)
+		goto unlock;
+
+	/* Default to remote wake. Values for wake_reason are documented in the
+	 * Bluez mgmt api docs.
+	 */
+	hdev->wake_reason = MGMT_WAKE_REASON_REMOTE_WAKE;
+
+	/* Once configured for remote wakeup, we should only wake up for
+	 * reconnections. It's useful to see which device is waking us up so
+	 * keep track of the bdaddr of the connection event that woke us up.
+	 */
+	if (event == HCI_EV_CONN_REQUEST) {
+		bacpy(&hdev->wake_addr, &conn_complete->bdaddr);
+		hdev->wake_addr_type = BDADDR_BREDR;
+	} else if (event == HCI_EV_CONN_COMPLETE) {
+		bacpy(&hdev->wake_addr, &conn_request->bdaddr);
+		hdev->wake_addr_type = BDADDR_BREDR;
+	} else if (event == HCI_EV_LE_META) {
+		struct hci_ev_le_meta *le_ev = (void *)skb->data;
+		u8 subevent = le_ev->subevent;
+		u8 *ptr = &skb->data[sizeof(*le_ev)];
+		u8 num_reports = *ptr;
+
+		if ((subevent == HCI_EV_LE_ADVERTISING_REPORT ||
+		     subevent == HCI_EV_LE_DIRECT_ADV_REPORT ||
+		     subevent == HCI_EV_LE_EXT_ADV_REPORT) &&
+		    num_reports) {
+			adv = (void *)(ptr + 1);
+			direct_adv = (void *)(ptr + 1);
+			ext_adv = (void *)(ptr + 1);
+
+			switch (subevent) {
+			case HCI_EV_LE_ADVERTISING_REPORT:
+				bacpy(&hdev->wake_addr, &adv->bdaddr);
+				hdev->wake_addr_type = adv->bdaddr_type;
+				break;
+			case HCI_EV_LE_DIRECT_ADV_REPORT:
+				bacpy(&hdev->wake_addr, &direct_adv->bdaddr);
+				hdev->wake_addr_type = direct_adv->bdaddr_type;
+				break;
+			case HCI_EV_LE_EXT_ADV_REPORT:
+				bacpy(&hdev->wake_addr, &ext_adv->bdaddr);
+				hdev->wake_addr_type = ext_adv->bdaddr_type;
+				break;
+			}
+		}
+	} else {
+		hdev->wake_reason = MGMT_WAKE_REASON_UNEXPECTED;
+	}
+
+unlock:
+	hci_dev_unlock(hdev);
+}
+
 void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb)
 {
 	struct hci_event_hdr *hdr = (void *) skb->data;
@@ -6045,6 +6119,9 @@ void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb)
 
 	skb_pull(skb, HCI_EVENT_HDR_SIZE);
 
+	/* Store wake reason if we're suspended */
+	hci_store_wake_reason(hdev, event, skb);
+
 	switch (event) {
 	case HCI_EV_INQUIRY_COMPLETE:
 		hci_inquiry_complete_evt(hdev, skb);
diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c
index e0269192f2e5..6f12bab4d2fa 100644
--- a/net/bluetooth/hci_request.c
+++ b/net/bluetooth/hci_request.c
@@ -1027,6 +1027,9 @@ void hci_req_add_le_passive_scan(struct hci_request *req)
 	} else if (hci_is_le_conn_scanning(hdev)) {
 		window = hdev->le_scan_window_connect;
 		interval = hdev->le_scan_int_connect;
+	} else if (hci_is_adv_monitoring(hdev)) {
+		window = hdev->le_scan_window_adv_monitor;
+		interval = hdev->le_scan_int_adv_monitor;
 	} else {
 		window = hdev->le_scan_window;
 		interval = hdev->le_scan_interval;
@@ -1111,6 +1114,53 @@ static void hci_req_config_le_suspend_scan(struct hci_request *req)
 	set_bit(SUSPEND_SCAN_ENABLE, req->hdev->suspend_tasks);
 }
 
+static void cancel_adv_timeout(struct hci_dev *hdev)
+{
+	if (hdev->adv_instance_timeout) {
+		hdev->adv_instance_timeout = 0;
+		cancel_delayed_work(&hdev->adv_instance_expire);
+	}
+}
+
+/* This function requires the caller holds hdev->lock */
+static void hci_suspend_adv_instances(struct hci_request *req)
+{
+	bt_dev_dbg(req->hdev, "Suspending advertising instances");
+
+	/* Call to disable any advertisements active on the controller.
+	 * This will succeed even if no advertisements are configured.
+	 */
+	__hci_req_disable_advertising(req);
+
+	/* If we are using software rotation, pause the loop */
+	if (!ext_adv_capable(req->hdev))
+		cancel_adv_timeout(req->hdev);
+}
+
+/* This function requires the caller holds hdev->lock */
+static void hci_resume_adv_instances(struct hci_request *req)
+{
+	struct adv_info *adv;
+
+	bt_dev_dbg(req->hdev, "Resuming advertising instances");
+
+	if (ext_adv_capable(req->hdev)) {
+		/* Call for each tracked instance to be re-enabled */
+		list_for_each_entry(adv, &req->hdev->adv_instances, list) {
+			__hci_req_enable_ext_advertising(req,
+							 adv->instance);
+		}
+
+	} else {
+		/* Schedule for most recent instance to be restarted and begin
+		 * the software rotation loop
+		 */
+		__hci_req_schedule_adv_instance(req,
+						req->hdev->cur_adv_instance,
+						true);
+	}
+}
+
 static void suspend_req_complete(struct hci_dev *hdev, u8 status, u16 opcode)
 {
 	bt_dev_dbg(hdev, "Request complete opcode=0x%x, status=0x%x", opcode,
@@ -1153,7 +1203,7 @@ void hci_req_prepare_suspend(struct hci_dev *hdev, enum suspended_state next)
 		hdev->discovery_paused = true;
 		hdev->discovery_old_state = old_state;
 
-		/* Stop advertising */
+		/* Stop directed advertising */
 		old_state = hci_dev_test_flag(hdev, HCI_ADVERTISING);
 		if (old_state) {
 			set_bit(SUSPEND_PAUSE_ADVERTISING, hdev->suspend_tasks);
@@ -1162,6 +1212,10 @@ void hci_req_prepare_suspend(struct hci_dev *hdev, enum suspended_state next)
 					   &hdev->discov_off, 0);
 		}
 
+		/* Pause other advertisements */
+		if (hdev->adv_instance_cnt)
+			hci_suspend_adv_instances(&req);
+
 		hdev->advertising_paused = true;
 		hdev->advertising_old_state = old_state;
 		/* Disable page scan */
@@ -1212,7 +1266,7 @@ void hci_req_prepare_suspend(struct hci_dev *hdev, enum suspended_state next)
 		/* Reset passive/background scanning to normal */
 		hci_req_config_le_suspend_scan(&req);
 
-		/* Unpause advertising */
+		/* Unpause directed advertising */
 		hdev->advertising_paused = false;
 		if (hdev->advertising_old_state) {
 			set_bit(SUSPEND_UNPAUSE_ADVERTISING,
@@ -1223,6 +1277,10 @@ void hci_req_prepare_suspend(struct hci_dev *hdev, enum suspended_state next)
 			hdev->advertising_old_state = 0;
 		}
 
+		/* Resume other advertisements */
+		if (hdev->adv_instance_cnt)
+			hci_resume_adv_instances(&req);
+
 		/* Unpause discovery */
 		hdev->discovery_paused = false;
 		if (hdev->discovery_old_state != DISCOVERY_STOPPED &&
@@ -1533,11 +1591,14 @@ void __hci_req_update_scan_rsp_data(struct hci_request *req, u8 instance)
 
 		memset(&cp, 0, sizeof(cp));
 
-		if (instance)
+		/* Extended scan response data doesn't allow a response to be
+		 * set if the instance isn't scannable.
+		 */
+		if (get_adv_instance_scan_rsp_len(hdev, instance))
 			len = create_instance_scan_rsp_data(hdev, instance,
 							    cp.data);
 		else
-			len = create_default_scan_rsp_data(hdev, cp.data);
+			len = 0;
 
 		if (hdev->scan_rsp_data_len == len &&
 		    !memcmp(cp.data, hdev->scan_rsp_data, len))
@@ -1824,7 +1885,13 @@ int hci_get_random_address(struct hci_dev *hdev, bool require_privacy,
 	if (use_rpa) {
 		int to;
 
-		*own_addr_type = ADDR_LE_DEV_RANDOM;
+		/* If Controller supports LL Privacy use own address type is
+		 * 0x03
+		 */
+		if (use_ll_privacy(hdev))
+			*own_addr_type = ADDR_LE_DEV_RANDOM_RESOLVED;
+		else
+			*own_addr_type = ADDR_LE_DEV_RANDOM;
 
 		if (adv_instance) {
 			if (!adv_instance->rpa_expired &&
@@ -2183,14 +2250,6 @@ int __hci_req_schedule_adv_instance(struct hci_request *req, u8 instance,
 	return 0;
 }
 
-static void cancel_adv_timeout(struct hci_dev *hdev)
-{
-	if (hdev->adv_instance_timeout) {
-		hdev->adv_instance_timeout = 0;
-		cancel_delayed_work(&hdev->adv_instance_expire);
-	}
-}
-
 /* For a single instance:
  * - force == true: The instance will be removed even when its remaining
  *   lifetime is not zero.
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index ade83e224567..1ab27b90ddcb 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -7301,9 +7301,10 @@ static int l2cap_data_rcv(struct l2cap_chan *chan, struct sk_buff *skb)
 		goto drop;
 	}
 
-	if ((chan->mode == L2CAP_MODE_ERTM ||
-	     chan->mode == L2CAP_MODE_STREAMING) && sk_filter(chan->data, skb))
-		goto drop;
+	if (chan->ops->filter) {
+		if (chan->ops->filter(chan, skb))
+			goto drop;
+	}
 
 	if (!control->sframe) {
 		int err;
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index e1a3e66b1754..f1b1edd0b697 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -1521,8 +1521,6 @@ static void l2cap_sock_teardown_cb(struct l2cap_chan *chan, int err)
 
 	parent = bt_sk(sk)->parent;
 
-	sock_set_flag(sk, SOCK_ZAPPED);
-
 	switch (chan->state) {
 	case BT_OPEN:
 	case BT_BOUND:
@@ -1549,8 +1547,11 @@ static void l2cap_sock_teardown_cb(struct l2cap_chan *chan, int err)
 
 		break;
 	}
-
 	release_sock(sk);
+
+	/* Only zap after cleanup to avoid use after free race */
+	sock_set_flag(sk, SOCK_ZAPPED);
+
 }
 
 static void l2cap_sock_state_change_cb(struct l2cap_chan *chan, int state,
@@ -1663,6 +1664,19 @@ static void l2cap_sock_suspend_cb(struct l2cap_chan *chan)
 	sk->sk_state_change(sk);
 }
 
+static int l2cap_sock_filter(struct l2cap_chan *chan, struct sk_buff *skb)
+{
+	struct sock *sk = chan->data;
+
+	switch (chan->mode) {
+	case L2CAP_MODE_ERTM:
+	case L2CAP_MODE_STREAMING:
+		return sk_filter(sk, skb);
+	}
+
+	return 0;
+}
+
 static const struct l2cap_ops l2cap_chan_ops = {
 	.name			= "L2CAP Socket Interface",
 	.new_connection		= l2cap_sock_new_connection_cb,
@@ -1678,6 +1692,7 @@ static const struct l2cap_ops l2cap_chan_ops = {
 	.get_sndtimeo		= l2cap_sock_get_sndtimeo_cb,
 	.get_peer_pid		= l2cap_sock_get_peer_pid_cb,
 	.alloc_skb		= l2cap_sock_alloc_skb_cb,
+	.filter			= l2cap_sock_filter,
 };
 
 static void l2cap_sock_destruct(struct sock *sk)
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 5bbe71002fb9..12d7b368b428 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -163,6 +163,8 @@ static const u16 mgmt_events[] = {
 	MGMT_EV_PHY_CONFIGURATION_CHANGED,
 	MGMT_EV_EXP_FEATURE_CHANGED,
 	MGMT_EV_DEVICE_FLAGS_CHANGED,
+	MGMT_EV_CONTROLLER_SUSPEND,
+	MGMT_EV_CONTROLLER_RESUME,
 };
 
 static const u16 mgmt_untrusted_commands[] = {
@@ -782,7 +784,8 @@ static u32 get_supported_settings(struct hci_dev *hdev)
 
 		if (lmp_ssp_capable(hdev)) {
 			settings |= MGMT_SETTING_SSP;
-			settings |= MGMT_SETTING_HS;
+			if (IS_ENABLED(CONFIG_BT_HS))
+				settings |= MGMT_SETTING_HS;
 		}
 
 		if (lmp_sc_capable(hdev))
@@ -1815,6 +1818,10 @@ static int set_hs(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
 
 	bt_dev_dbg(hdev, "sock %p", sk);
 
+	if (!IS_ENABLED(CONFIG_BT_HS))
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_HS,
+				       MGMT_STATUS_NOT_SUPPORTED);
+
 	status = mgmt_bredr_support(hdev);
 	if (status)
 		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_HS, status);
@@ -4157,7 +4164,7 @@ static int read_adv_mon_features(struct sock *sk, struct hci_dev *hdev,
 {
 	struct adv_monitor *monitor = NULL;
 	struct mgmt_rp_read_adv_monitor_features *rp = NULL;
-	int handle;
+	int handle, err;
 	size_t rp_size = 0;
 	__u32 supported = 0;
 	__u16 num_handles = 0;
@@ -4192,9 +4199,13 @@ static int read_adv_mon_features(struct sock *sk, struct hci_dev *hdev,
 	if (num_handles)
 		memcpy(&rp->handles, &handles, (num_handles * sizeof(u16)));
 
-	return mgmt_cmd_complete(sk, hdev->id,
-				 MGMT_OP_READ_ADV_MONITOR_FEATURES,
-				 MGMT_STATUS_SUCCESS, rp, rp_size);
+	err = mgmt_cmd_complete(sk, hdev->id,
+				MGMT_OP_READ_ADV_MONITOR_FEATURES,
+				MGMT_STATUS_SUCCESS, rp, rp_size);
+
+	kfree(rp);
+
+	return err;
 }
 
 static int add_adv_patterns_monitor(struct sock *sk, struct hci_dev *hdev,
@@ -7202,6 +7213,8 @@ static u32 get_supported_adv_flags(struct hci_dev *hdev)
 
 	if (ext_adv_capable(hdev)) {
 		flags |= MGMT_ADV_FLAG_SEC_1M;
+		flags |= MGMT_ADV_FLAG_HW_OFFLOAD;
+		flags |= MGMT_ADV_FLAG_CAN_SET_TX_POWER;
 
 		if (hdev->le_features[1] & HCI_LE_PHY_2M)
 			flags |= MGMT_ADV_FLAG_SEC_2M;
@@ -7250,7 +7263,7 @@ static int read_adv_features(struct sock *sk, struct hci_dev *hdev,
 	rp->supported_flags = cpu_to_le32(supported_flags);
 	rp->max_adv_data_len = HCI_MAX_AD_LENGTH;
 	rp->max_scan_rsp_len = HCI_MAX_AD_LENGTH;
-	rp->max_instances = HCI_MAX_ADV_INSTANCES;
+	rp->max_instances = hdev->le_num_of_adv_sets;
 	rp->num_instances = hdev->adv_instance_cnt;
 
 	instance = rp->instance;
@@ -7446,7 +7459,7 @@ static int add_advertising(struct sock *sk, struct hci_dev *hdev,
 		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_ADVERTISING,
 				       MGMT_STATUS_NOT_SUPPORTED);
 
-	if (cp->instance < 1 || cp->instance > HCI_MAX_ADV_INSTANCES)
+	if (cp->instance < 1 || cp->instance > hdev->le_num_of_adv_sets)
 		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_ADD_ADVERTISING,
 				       MGMT_STATUS_INVALID_PARAMS);
 
@@ -7699,7 +7712,7 @@ static int get_adv_size_info(struct sock *sk, struct hci_dev *hdev,
 		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_GET_ADV_SIZE_INFO,
 				       MGMT_STATUS_REJECTED);
 
-	if (cp->instance < 1 || cp->instance > HCI_MAX_ADV_INSTANCES)
+	if (cp->instance < 1 || cp->instance > hdev->le_num_of_adv_sets)
 		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_GET_ADV_SIZE_INFO,
 				       MGMT_STATUS_INVALID_PARAMS);
 
@@ -8262,6 +8275,10 @@ void mgmt_device_disconnected(struct hci_dev *hdev, bdaddr_t *bdaddr,
 	ev.addr.type = link_to_bdaddr(link_type, addr_type);
 	ev.reason = reason;
 
+	/* Report disconnects due to suspend */
+	if (hdev->suspended)
+		ev.reason = MGMT_DEV_DISCONN_LOCAL_HOST_SUSPEND;
+
 	mgmt_event(MGMT_EV_DEVICE_DISCONNECTED, hdev, &ev, sizeof(ev), sk);
 
 	if (sk)
@@ -8868,6 +8885,30 @@ void mgmt_discovering(struct hci_dev *hdev, u8 discovering)
 	mgmt_event(MGMT_EV_DISCOVERING, hdev, &ev, sizeof(ev), NULL);
 }
 
+void mgmt_suspending(struct hci_dev *hdev, u8 state)
+{
+	struct mgmt_ev_controller_suspend ev;
+
+	ev.suspend_state = state;
+	mgmt_event(MGMT_EV_CONTROLLER_SUSPEND, hdev, &ev, sizeof(ev), NULL);
+}
+
+void mgmt_resuming(struct hci_dev *hdev, u8 reason, bdaddr_t *bdaddr,
+		   u8 addr_type)
+{
+	struct mgmt_ev_controller_resume ev;
+
+	ev.wake_reason = reason;
+	if (bdaddr) {
+		bacpy(&ev.addr.bdaddr, bdaddr);
+		ev.addr.type = addr_type;
+	} else {
+		memset(&ev.addr, 0, sizeof(ev.addr));
+	}
+
+	mgmt_event(MGMT_EV_CONTROLLER_RESUME, hdev, &ev, sizeof(ev), NULL);
+}
+
 static struct hci_mgmt_chan chan = {
 	.channel	= HCI_CHANNEL_CONTROL,
 	.handler_count	= ARRAY_SIZE(mgmt_handlers),
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index dcf7f96ff417..79ffcdef0b7a 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -1001,6 +1001,12 @@ static int sco_sock_getsockopt(struct socket *sock, int level, int optname,
 			err = -EFAULT;
 		break;
 
+	case BT_SNDMTU:
+	case BT_RCVMTU:
+		if (put_user(sco_pi(sk)->conn->mtu, (u32 __user *)optval))
+			err = -EFAULT;
+		break;
+
 	default:
 		err = -ENOPROTOOPT;
 		break;
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index a66f211726e7..c1c30a9f76f3 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -11,6 +11,7 @@
 #include <net/sock.h>
 #include <net/tcp.h>
 #include <linux/error-injection.h>
+#include <linux/smp.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/bpf_test_run.h>
@@ -204,6 +205,9 @@ int bpf_prog_test_run_tracing(struct bpf_prog *prog,
 	int b = 2, err = -EFAULT;
 	u32 retval = 0;
 
+	if (kattr->test.flags || kattr->test.cpu)
+		return -EINVAL;
+
 	switch (prog->expected_attach_type) {
 	case BPF_TRACE_FENTRY:
 	case BPF_TRACE_FEXIT:
@@ -236,6 +240,84 @@ out:
 	return err;
 }
 
+struct bpf_raw_tp_test_run_info {
+	struct bpf_prog *prog;
+	void *ctx;
+	u32 retval;
+};
+
+static void
+__bpf_prog_test_run_raw_tp(void *data)
+{
+	struct bpf_raw_tp_test_run_info *info = data;
+
+	rcu_read_lock();
+	info->retval = BPF_PROG_RUN(info->prog, info->ctx);
+	rcu_read_unlock();
+}
+
+int bpf_prog_test_run_raw_tp(struct bpf_prog *prog,
+			     const union bpf_attr *kattr,
+			     union bpf_attr __user *uattr)
+{
+	void __user *ctx_in = u64_to_user_ptr(kattr->test.ctx_in);
+	__u32 ctx_size_in = kattr->test.ctx_size_in;
+	struct bpf_raw_tp_test_run_info info;
+	int cpu = kattr->test.cpu, err = 0;
+	int current_cpu;
+
+	/* doesn't support data_in/out, ctx_out, duration, or repeat */
+	if (kattr->test.data_in || kattr->test.data_out ||
+	    kattr->test.ctx_out || kattr->test.duration ||
+	    kattr->test.repeat)
+		return -EINVAL;
+
+	if (ctx_size_in < prog->aux->max_ctx_offset)
+		return -EINVAL;
+
+	if ((kattr->test.flags & BPF_F_TEST_RUN_ON_CPU) == 0 && cpu != 0)
+		return -EINVAL;
+
+	if (ctx_size_in) {
+		info.ctx = kzalloc(ctx_size_in, GFP_USER);
+		if (!info.ctx)
+			return -ENOMEM;
+		if (copy_from_user(info.ctx, ctx_in, ctx_size_in)) {
+			err = -EFAULT;
+			goto out;
+		}
+	} else {
+		info.ctx = NULL;
+	}
+
+	info.prog = prog;
+
+	current_cpu = get_cpu();
+	if ((kattr->test.flags & BPF_F_TEST_RUN_ON_CPU) == 0 ||
+	    cpu == current_cpu) {
+		__bpf_prog_test_run_raw_tp(&info);
+	} else if (cpu >= nr_cpu_ids || !cpu_online(cpu)) {
+		/* smp_call_function_single() also checks cpu_online()
+		 * after csd_lock(). However, since cpu is from user
+		 * space, let's do an extra quick check to filter out
+		 * invalid value before smp_call_function_single().
+		 */
+		err = -ENXIO;
+	} else {
+		err = smp_call_function_single(cpu, __bpf_prog_test_run_raw_tp,
+					       &info, 1);
+	}
+	put_cpu();
+
+	if (!err &&
+	    copy_to_user(&uattr->test.retval, &info.retval, sizeof(u32)))
+		err = -EFAULT;
+
+out:
+	kfree(info.ctx);
+	return err;
+}
+
 static void *bpf_ctx_init(const union bpf_attr *kattr, u32 max_size)
 {
 	void __user *data_in = u64_to_user_ptr(kattr->test.ctx_in);
@@ -410,6 +492,9 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 	void *data;
 	int ret;
 
+	if (kattr->test.flags || kattr->test.cpu)
+		return -EINVAL;
+
 	data = bpf_test_init(kattr, size, NET_SKB_PAD + NET_IP_ALIGN,
 			     SKB_DATA_ALIGN(sizeof(struct skb_shared_info)));
 	if (IS_ERR(data))
@@ -607,6 +692,9 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog,
 	if (prog->type != BPF_PROG_TYPE_FLOW_DISSECTOR)
 		return -EINVAL;
 
+	if (kattr->test.flags || kattr->test.cpu)
+		return -EINVAL;
+
 	if (size < ETH_HLEN)
 		return -EINVAL;
 
diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c
index 7629b63f6f30..e28ffadd1371 100644
--- a/net/bridge/br_forward.c
+++ b/net/bridge/br_forward.c
@@ -274,14 +274,23 @@ void br_multicast_flood(struct net_bridge_mdb_entry *mdst,
 	struct net_bridge *br = netdev_priv(dev);
 	struct net_bridge_port *prev = NULL;
 	struct net_bridge_port_group *p;
+	bool allow_mode_include = true;
 	struct hlist_node *rp;
 
 	rp = rcu_dereference(hlist_first_rcu(&br->router_list));
-	p = mdst ? rcu_dereference(mdst->ports) : NULL;
+	if (mdst) {
+		p = rcu_dereference(mdst->ports);
+		if (br_multicast_should_handle_mode(br, mdst->addr.proto) &&
+		    br_multicast_is_star_g(&mdst->addr))
+			allow_mode_include = false;
+	} else {
+		p = NULL;
+	}
+
 	while (p || rp) {
 		struct net_bridge_port *port, *lport, *rport;
 
-		lport = p ? p->port : NULL;
+		lport = p ? p->key.port : NULL;
 		rport = hlist_entry_safe(rp, struct net_bridge_port, rlist);
 
 		if ((unsigned long)lport > (unsigned long)rport) {
@@ -292,6 +301,10 @@ void br_multicast_flood(struct net_bridge_mdb_entry *mdst,
 						   local_orig);
 				goto delivered;
 			}
+			if ((!allow_mode_include &&
+			     p->filter_mode == MCAST_INCLUDE) ||
+			    (p->flags & MDB_PG_FLAGS_BLOCKED))
+				goto delivered;
 		} else {
 			port = rport;
 		}
diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c
index 00f1651a6aba..e15bab19a012 100644
--- a/net/bridge/br_mdb.c
+++ b/net/bridge/br_mdb.c
@@ -62,19 +62,33 @@ static void __mdb_entry_fill_flags(struct br_mdb_entry *e, unsigned char flags)
 		e->flags |= MDB_FLAGS_OFFLOAD;
 	if (flags & MDB_PG_FLAGS_FAST_LEAVE)
 		e->flags |= MDB_FLAGS_FAST_LEAVE;
+	if (flags & MDB_PG_FLAGS_STAR_EXCL)
+		e->flags |= MDB_FLAGS_STAR_EXCL;
+	if (flags & MDB_PG_FLAGS_BLOCKED)
+		e->flags |= MDB_FLAGS_BLOCKED;
 }
 
-static void __mdb_entry_to_br_ip(struct br_mdb_entry *entry, struct br_ip *ip)
+static void __mdb_entry_to_br_ip(struct br_mdb_entry *entry, struct br_ip *ip,
+				 struct nlattr **mdb_attrs)
 {
 	memset(ip, 0, sizeof(struct br_ip));
 	ip->vid = entry->vid;
 	ip->proto = entry->addr.proto;
-	if (ip->proto == htons(ETH_P_IP))
-		ip->u.ip4 = entry->addr.u.ip4;
+	switch (ip->proto) {
+	case htons(ETH_P_IP):
+		ip->dst.ip4 = entry->addr.u.ip4;
+		if (mdb_attrs && mdb_attrs[MDBE_ATTR_SOURCE])
+			ip->src.ip4 = nla_get_in_addr(mdb_attrs[MDBE_ATTR_SOURCE]);
+		break;
 #if IS_ENABLED(CONFIG_IPV6)
-	else
-		ip->u.ip6 = entry->addr.u.ip6;
+	case htons(ETH_P_IPV6):
+		ip->dst.ip6 = entry->addr.u.ip6;
+		if (mdb_attrs && mdb_attrs[MDBE_ATTR_SOURCE])
+			ip->src.ip6 = nla_get_in6_addr(mdb_attrs[MDBE_ATTR_SOURCE]);
+		break;
 #endif
+	}
+
 }
 
 static int __mdb_fill_srcs(struct sk_buff *skb,
@@ -91,14 +105,14 @@ static int __mdb_fill_srcs(struct sk_buff *skb,
 		return -EMSGSIZE;
 
 	hlist_for_each_entry_rcu(ent, &p->src_list, node,
-				 lockdep_is_held(&p->port->br->multicast_lock)) {
+				 lockdep_is_held(&p->key.port->br->multicast_lock)) {
 		nest_ent = nla_nest_start(skb, MDBA_MDB_SRCLIST_ENTRY);
 		if (!nest_ent)
 			goto out_cancel_err;
 		switch (ent->addr.proto) {
 		case htons(ETH_P_IP):
 			if (nla_put_in_addr(skb, MDBA_MDB_SRCATTR_ADDRESS,
-					    ent->addr.u.ip4)) {
+					    ent->addr.src.ip4)) {
 				nla_nest_cancel(skb, nest_ent);
 				goto out_cancel_err;
 			}
@@ -106,7 +120,7 @@ static int __mdb_fill_srcs(struct sk_buff *skb,
 #if IS_ENABLED(CONFIG_IPV6)
 		case htons(ETH_P_IPV6):
 			if (nla_put_in6_addr(skb, MDBA_MDB_SRCATTR_ADDRESS,
-					     &ent->addr.u.ip6)) {
+					     &ent->addr.src.ip6)) {
 				nla_nest_cancel(skb, nest_ent);
 				goto out_cancel_err;
 			}
@@ -146,7 +160,7 @@ static int __mdb_fill_info(struct sk_buff *skb,
 
 	memset(&e, 0, sizeof(e));
 	if (p) {
-		ifindex = p->port->dev->ifindex;
+		ifindex = p->key.port->dev->ifindex;
 		mtimer = &p->timer;
 		flags = p->flags;
 	} else {
@@ -158,10 +172,10 @@ static int __mdb_fill_info(struct sk_buff *skb,
 	e.ifindex = ifindex;
 	e.vid = mp->addr.vid;
 	if (mp->addr.proto == htons(ETH_P_IP))
-		e.addr.u.ip4 = mp->addr.u.ip4;
+		e.addr.u.ip4 = mp->addr.dst.ip4;
 #if IS_ENABLED(CONFIG_IPV6)
 	if (mp->addr.proto == htons(ETH_P_IPV6))
-		e.addr.u.ip6 = mp->addr.u.ip6;
+		e.addr.u.ip6 = mp->addr.dst.ip6;
 #endif
 	e.addr.proto = mp->addr.proto;
 	nest_ent = nla_nest_start_noflag(skb,
@@ -172,30 +186,47 @@ static int __mdb_fill_info(struct sk_buff *skb,
 	if (nla_put_nohdr(skb, sizeof(e), &e) ||
 	    nla_put_u32(skb,
 			MDBA_MDB_EATTR_TIMER,
-			br_timer_value(mtimer))) {
-		nla_nest_cancel(skb, nest_ent);
-		return -EMSGSIZE;
-	}
+			br_timer_value(mtimer)))
+		goto nest_err;
+
 	switch (mp->addr.proto) {
 	case htons(ETH_P_IP):
-		dump_srcs_mode = !!(p && mp->br->multicast_igmp_version == 3);
+		dump_srcs_mode = !!(mp->br->multicast_igmp_version == 3);
+		if (mp->addr.src.ip4) {
+			if (nla_put_in_addr(skb, MDBA_MDB_EATTR_SOURCE,
+					    mp->addr.src.ip4))
+				goto nest_err;
+			break;
+		}
 		break;
 #if IS_ENABLED(CONFIG_IPV6)
 	case htons(ETH_P_IPV6):
-		dump_srcs_mode = !!(p && mp->br->multicast_mld_version == 2);
+		dump_srcs_mode = !!(mp->br->multicast_mld_version == 2);
+		if (!ipv6_addr_any(&mp->addr.src.ip6)) {
+			if (nla_put_in6_addr(skb, MDBA_MDB_EATTR_SOURCE,
+					     &mp->addr.src.ip6))
+				goto nest_err;
+			break;
+		}
 		break;
 #endif
 	}
-	if (dump_srcs_mode &&
-	    (__mdb_fill_srcs(skb, p) ||
-	     nla_put_u8(skb, MDBA_MDB_EATTR_GROUP_MODE, p->filter_mode))) {
-		nla_nest_cancel(skb, nest_ent);
-		return -EMSGSIZE;
+	if (p) {
+		if (nla_put_u8(skb, MDBA_MDB_EATTR_RTPROT, p->rt_protocol))
+			goto nest_err;
+		if (dump_srcs_mode &&
+		    (__mdb_fill_srcs(skb, p) ||
+		     nla_put_u8(skb, MDBA_MDB_EATTR_GROUP_MODE,
+				p->filter_mode)))
+			goto nest_err;
 	}
-
 	nla_nest_end(skb, nest_ent);
 
 	return 0;
+
+nest_err:
+	nla_nest_cancel(skb, nest_ent);
+	return -EMSGSIZE;
 }
 
 static int br_mdb_fill_info(struct sk_buff *skb, struct netlink_callback *cb,
@@ -236,7 +267,7 @@ static int br_mdb_fill_info(struct sk_buff *skb, struct netlink_callback *cb,
 
 		for (pp = &mp->ports; (p = rcu_dereference(*pp)) != NULL;
 		      pp = &p->next) {
-			if (!p->port)
+			if (!p->key.port)
 				continue;
 			if (pidx < s_pidx)
 				goto skip_pg;
@@ -393,15 +424,24 @@ static size_t rtnl_mdb_nlmsg_size(struct net_bridge_port_group *pg)
 	if (!pg)
 		goto out;
 
-	switch (pg->addr.proto) {
+	/* MDBA_MDB_EATTR_RTPROT */
+	nlmsg_size += nla_total_size(sizeof(u8));
+
+	switch (pg->key.addr.proto) {
 	case htons(ETH_P_IP):
-		if (pg->port->br->multicast_igmp_version == 2)
+		/* MDBA_MDB_EATTR_SOURCE */
+		if (pg->key.addr.src.ip4)
+			nlmsg_size += nla_total_size(sizeof(__be32));
+		if (pg->key.port->br->multicast_igmp_version == 2)
 			goto out;
 		addr_size = sizeof(__be32);
 		break;
 #if IS_ENABLED(CONFIG_IPV6)
 	case htons(ETH_P_IPV6):
-		if (pg->port->br->multicast_mld_version == 1)
+		/* MDBA_MDB_EATTR_SOURCE */
+		if (!ipv6_addr_any(&pg->key.addr.src.ip6))
+			nlmsg_size += nla_total_size(sizeof(struct in6_addr));
+		if (pg->key.port->br->multicast_mld_version == 1)
 			goto out;
 		addr_size = sizeof(struct in6_addr);
 		break;
@@ -450,7 +490,7 @@ static void br_mdb_complete(struct net_device *dev, int err, void *priv)
 		goto out;
 	for (pp = &mp->ports; (p = mlock_dereference(*pp, br)) != NULL;
 	     pp = &p->next) {
-		if (p->port != port)
+		if (p->key.port != port)
 			continue;
 		p->flags |= MDB_PG_FLAGS_OFFLOAD;
 	}
@@ -474,10 +514,10 @@ static void br_mdb_switchdev_host_port(struct net_device *dev,
 	};
 
 	if (mp->addr.proto == htons(ETH_P_IP))
-		ip_eth_mc_map(mp->addr.u.ip4, mdb.addr);
+		ip_eth_mc_map(mp->addr.dst.ip4, mdb.addr);
 #if IS_ENABLED(CONFIG_IPV6)
 	else
-		ipv6_eth_mc_map(&mp->addr.u.ip6, mdb.addr);
+		ipv6_eth_mc_map(&mp->addr.dst.ip6, mdb.addr);
 #endif
 
 	mdb.obj.orig_dev = dev;
@@ -520,26 +560,26 @@ void br_mdb_notify(struct net_device *dev,
 
 	if (pg) {
 		if (mp->addr.proto == htons(ETH_P_IP))
-			ip_eth_mc_map(mp->addr.u.ip4, mdb.addr);
+			ip_eth_mc_map(mp->addr.dst.ip4, mdb.addr);
 #if IS_ENABLED(CONFIG_IPV6)
 		else
-			ipv6_eth_mc_map(&mp->addr.u.ip6, mdb.addr);
+			ipv6_eth_mc_map(&mp->addr.dst.ip6, mdb.addr);
 #endif
-		mdb.obj.orig_dev = pg->port->dev;
+		mdb.obj.orig_dev = pg->key.port->dev;
 		switch (type) {
 		case RTM_NEWMDB:
 			complete_info = kmalloc(sizeof(*complete_info), GFP_ATOMIC);
 			if (!complete_info)
 				break;
-			complete_info->port = pg->port;
+			complete_info->port = pg->key.port;
 			complete_info->ip = mp->addr;
 			mdb.obj.complete_priv = complete_info;
 			mdb.obj.complete = br_mdb_complete;
-			if (switchdev_port_obj_add(pg->port->dev, &mdb.obj, NULL))
+			if (switchdev_port_obj_add(pg->key.port->dev, &mdb.obj, NULL))
 				kfree(complete_info);
 			break;
 		case RTM_DELMDB:
-			switchdev_port_obj_del(pg->port->dev, &mdb.obj);
+			switchdev_port_obj_del(pg->key.port->dev, &mdb.obj);
 			break;
 		}
 	} else {
@@ -629,33 +669,94 @@ errout:
 	rtnl_set_sk_err(net, RTNLGRP_MDB, err);
 }
 
-static bool is_valid_mdb_entry(struct br_mdb_entry *entry)
+static bool is_valid_mdb_entry(struct br_mdb_entry *entry,
+			       struct netlink_ext_ack *extack)
 {
-	if (entry->ifindex == 0)
+	if (entry->ifindex == 0) {
+		NL_SET_ERR_MSG_MOD(extack, "Zero entry ifindex is not allowed");
 		return false;
+	}
 
 	if (entry->addr.proto == htons(ETH_P_IP)) {
-		if (!ipv4_is_multicast(entry->addr.u.ip4))
+		if (!ipv4_is_multicast(entry->addr.u.ip4)) {
+			NL_SET_ERR_MSG_MOD(extack, "IPv4 entry group address is not multicast");
 			return false;
-		if (ipv4_is_local_multicast(entry->addr.u.ip4))
+		}
+		if (ipv4_is_local_multicast(entry->addr.u.ip4)) {
+			NL_SET_ERR_MSG_MOD(extack, "IPv4 entry group address is local multicast");
 			return false;
+		}
 #if IS_ENABLED(CONFIG_IPV6)
 	} else if (entry->addr.proto == htons(ETH_P_IPV6)) {
-		if (ipv6_addr_is_ll_all_nodes(&entry->addr.u.ip6))
+		if (ipv6_addr_is_ll_all_nodes(&entry->addr.u.ip6)) {
+			NL_SET_ERR_MSG_MOD(extack, "IPv6 entry group address is link-local all nodes");
 			return false;
+		}
 #endif
-	} else
+	} else {
+		NL_SET_ERR_MSG_MOD(extack, "Unknown entry protocol");
 		return false;
-	if (entry->state != MDB_PERMANENT && entry->state != MDB_TEMPORARY)
+	}
+
+	if (entry->state != MDB_PERMANENT && entry->state != MDB_TEMPORARY) {
+		NL_SET_ERR_MSG_MOD(extack, "Unknown entry state");
 		return false;
-	if (entry->vid >= VLAN_VID_MASK)
+	}
+	if (entry->vid >= VLAN_VID_MASK) {
+		NL_SET_ERR_MSG_MOD(extack, "Invalid entry VLAN id");
 		return false;
+	}
+
+	return true;
+}
+
+static bool is_valid_mdb_source(struct nlattr *attr, __be16 proto,
+				struct netlink_ext_ack *extack)
+{
+	switch (proto) {
+	case htons(ETH_P_IP):
+		if (nla_len(attr) != sizeof(struct in_addr)) {
+			NL_SET_ERR_MSG_MOD(extack, "IPv4 invalid source address length");
+			return false;
+		}
+		if (ipv4_is_multicast(nla_get_in_addr(attr))) {
+			NL_SET_ERR_MSG_MOD(extack, "IPv4 multicast source address is not allowed");
+			return false;
+		}
+		break;
+#if IS_ENABLED(CONFIG_IPV6)
+	case htons(ETH_P_IPV6): {
+		struct in6_addr src;
+
+		if (nla_len(attr) != sizeof(struct in6_addr)) {
+			NL_SET_ERR_MSG_MOD(extack, "IPv6 invalid source address length");
+			return false;
+		}
+		src = nla_get_in6_addr(attr);
+		if (ipv6_addr_is_multicast(&src)) {
+			NL_SET_ERR_MSG_MOD(extack, "IPv6 multicast source address is not allowed");
+			return false;
+		}
+		break;
+	}
+#endif
+	default:
+		NL_SET_ERR_MSG_MOD(extack, "Invalid protocol used with source address");
+		return false;
+	}
 
 	return true;
 }
 
+static const struct nla_policy br_mdbe_attrs_pol[MDBE_ATTR_MAX + 1] = {
+	[MDBE_ATTR_SOURCE] = NLA_POLICY_RANGE(NLA_BINARY,
+					      sizeof(struct in_addr),
+					      sizeof(struct in6_addr)),
+};
+
 static int br_mdb_parse(struct sk_buff *skb, struct nlmsghdr *nlh,
-			struct net_device **pdev, struct br_mdb_entry **pentry)
+			struct net_device **pdev, struct br_mdb_entry **pentry,
+			struct nlattr **mdb_attrs, struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	struct br_mdb_entry *entry;
@@ -671,51 +772,86 @@ static int br_mdb_parse(struct sk_buff *skb, struct nlmsghdr *nlh,
 
 	bpm = nlmsg_data(nlh);
 	if (bpm->ifindex == 0) {
-		pr_info("PF_BRIDGE: br_mdb_parse() with invalid ifindex\n");
+		NL_SET_ERR_MSG_MOD(extack, "Invalid bridge ifindex");
 		return -EINVAL;
 	}
 
 	dev = __dev_get_by_index(net, bpm->ifindex);
 	if (dev == NULL) {
-		pr_info("PF_BRIDGE: br_mdb_parse() with unknown ifindex\n");
+		NL_SET_ERR_MSG_MOD(extack, "Bridge device doesn't exist");
 		return -ENODEV;
 	}
 
 	if (!(dev->priv_flags & IFF_EBRIDGE)) {
-		pr_info("PF_BRIDGE: br_mdb_parse() with non-bridge\n");
+		NL_SET_ERR_MSG_MOD(extack, "Device is not a bridge");
 		return -EOPNOTSUPP;
 	}
 
 	*pdev = dev;
 
-	if (!tb[MDBA_SET_ENTRY] ||
-	    nla_len(tb[MDBA_SET_ENTRY]) != sizeof(struct br_mdb_entry)) {
-		pr_info("PF_BRIDGE: br_mdb_parse() with invalid attr\n");
+	if (!tb[MDBA_SET_ENTRY]) {
+		NL_SET_ERR_MSG_MOD(extack, "Missing MDBA_SET_ENTRY attribute");
+		return -EINVAL;
+	}
+	if (nla_len(tb[MDBA_SET_ENTRY]) != sizeof(struct br_mdb_entry)) {
+		NL_SET_ERR_MSG_MOD(extack, "Invalid MDBA_SET_ENTRY attribute length");
 		return -EINVAL;
 	}
 
 	entry = nla_data(tb[MDBA_SET_ENTRY]);
-	if (!is_valid_mdb_entry(entry)) {
-		pr_info("PF_BRIDGE: br_mdb_parse() with invalid entry\n");
+	if (!is_valid_mdb_entry(entry, extack))
 		return -EINVAL;
+	*pentry = entry;
+
+	if (tb[MDBA_SET_ENTRY_ATTRS]) {
+		err = nla_parse_nested(mdb_attrs, MDBE_ATTR_MAX,
+				       tb[MDBA_SET_ENTRY_ATTRS],
+				       br_mdbe_attrs_pol, extack);
+		if (err)
+			return err;
+		if (mdb_attrs[MDBE_ATTR_SOURCE] &&
+		    !is_valid_mdb_source(mdb_attrs[MDBE_ATTR_SOURCE],
+					 entry->addr.proto, extack))
+			return -EINVAL;
+	} else {
+		memset(mdb_attrs, 0,
+		       sizeof(struct nlattr *) * (MDBE_ATTR_MAX + 1));
 	}
 
-	*pentry = entry;
 	return 0;
 }
 
 static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port,
-			    struct br_ip *group, struct br_mdb_entry *entry)
+			    struct br_mdb_entry *entry,
+			    struct nlattr **mdb_attrs,
+			    struct netlink_ext_ack *extack)
 {
-	struct net_bridge_mdb_entry *mp;
+	struct net_bridge_mdb_entry *mp, *star_mp;
 	struct net_bridge_port_group *p;
 	struct net_bridge_port_group __rcu **pp;
+	struct br_ip group, star_group;
 	unsigned long now = jiffies;
+	u8 filter_mode;
 	int err;
 
-	mp = br_mdb_ip_get(br, group);
+	__mdb_entry_to_br_ip(entry, &group, mdb_attrs);
+
+	/* host join errors which can happen before creating the group */
+	if (!port) {
+		/* don't allow any flags for host-joined groups */
+		if (entry->state) {
+			NL_SET_ERR_MSG_MOD(extack, "Flags are not allowed for host groups");
+			return -EINVAL;
+		}
+		if (!br_multicast_is_star_g(&group)) {
+			NL_SET_ERR_MSG_MOD(extack, "Groups with sources cannot be manually host joined");
+			return -EINVAL;
+		}
+	}
+
+	mp = br_mdb_ip_get(br, &group);
 	if (!mp) {
-		mp = br_multicast_new_group(br, group);
+		mp = br_multicast_new_group(br, &group);
 		err = PTR_ERR_OR_ZERO(mp);
 		if (err)
 			return err;
@@ -723,11 +859,10 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port,
 
 	/* host join */
 	if (!port) {
-		/* don't allow any flags for host-joined groups */
-		if (entry->state)
-			return -EINVAL;
-		if (mp->host_joined)
+		if (mp->host_joined) {
+			NL_SET_ERR_MSG_MOD(extack, "Group is already joined by host");
 			return -EEXIST;
+		}
 
 		br_multicast_host_join(mp, false);
 		br_mdb_notify(br->dev, mp, NULL, RTM_NEWMDB);
@@ -738,56 +873,69 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port,
 	for (pp = &mp->ports;
 	     (p = mlock_dereference(*pp, br)) != NULL;
 	     pp = &p->next) {
-		if (p->port == port)
+		if (p->key.port == port) {
+			NL_SET_ERR_MSG_MOD(extack, "Group is already joined by port");
 			return -EEXIST;
-		if ((unsigned long)p->port < (unsigned long)port)
+		}
+		if ((unsigned long)p->key.port < (unsigned long)port)
 			break;
 	}
 
-	p = br_multicast_new_port_group(port, group, *pp, entry->state, NULL,
-					MCAST_EXCLUDE);
-	if (unlikely(!p))
+	filter_mode = br_multicast_is_star_g(&group) ? MCAST_EXCLUDE :
+						       MCAST_INCLUDE;
+
+	p = br_multicast_new_port_group(port, &group, *pp, entry->state, NULL,
+					filter_mode, RTPROT_STATIC);
+	if (unlikely(!p)) {
+		NL_SET_ERR_MSG_MOD(extack, "Couldn't allocate new port group");
 		return -ENOMEM;
+	}
 	rcu_assign_pointer(*pp, p);
 	if (entry->state == MDB_TEMPORARY)
 		mod_timer(&p->timer, now + br->multicast_membership_interval);
 	br_mdb_notify(br->dev, mp, p, RTM_NEWMDB);
+	/* if we are adding a new EXCLUDE port group (*,G) it needs to be also
+	 * added to all S,G entries for proper replication, if we are adding
+	 * a new INCLUDE port (S,G) then all of *,G EXCLUDE ports need to be
+	 * added to it for proper replication
+	 */
+	if (br_multicast_should_handle_mode(br, group.proto)) {
+		switch (filter_mode) {
+		case MCAST_EXCLUDE:
+			br_multicast_star_g_handle_mode(p, MCAST_EXCLUDE);
+			break;
+		case MCAST_INCLUDE:
+			star_group = p->key.addr;
+			memset(&star_group.src, 0, sizeof(star_group.src));
+			star_mp = br_mdb_ip_get(br, &star_group);
+			if (star_mp)
+				br_multicast_sg_add_exclude_ports(star_mp, p);
+			break;
+		}
+	}
 
 	return 0;
 }
 
 static int __br_mdb_add(struct net *net, struct net_bridge *br,
-			struct br_mdb_entry *entry)
+			struct net_bridge_port *p,
+			struct br_mdb_entry *entry,
+			struct nlattr **mdb_attrs,
+			struct netlink_ext_ack *extack)
 {
-	struct br_ip ip;
-	struct net_device *dev;
-	struct net_bridge_port *p = NULL;
 	int ret;
 
-	if (!netif_running(br->dev) || !br_opt_get(br, BROPT_MULTICAST_ENABLED))
-		return -EINVAL;
-
-	if (entry->ifindex != br->dev->ifindex) {
-		dev = __dev_get_by_index(net, entry->ifindex);
-		if (!dev)
-			return -ENODEV;
-
-		p = br_port_get_rtnl(dev);
-		if (!p || p->br != br || p->state == BR_STATE_DISABLED)
-			return -EINVAL;
-	}
-
-	__mdb_entry_to_br_ip(entry, &ip);
-
 	spin_lock_bh(&br->multicast_lock);
-	ret = br_mdb_add_group(br, p, &ip, entry);
+	ret = br_mdb_add_group(br, p, entry, mdb_attrs, extack);
 	spin_unlock_bh(&br->multicast_lock);
+
 	return ret;
 }
 
 static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh,
 		      struct netlink_ext_ack *extack)
 {
+	struct nlattr *mdb_attrs[MDBE_ATTR_MAX + 1];
 	struct net *net = sock_net(skb->sk);
 	struct net_bridge_vlan_group *vg;
 	struct net_bridge_port *p = NULL;
@@ -797,20 +945,43 @@ static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh,
 	struct net_bridge *br;
 	int err;
 
-	err = br_mdb_parse(skb, nlh, &dev, &entry);
+	err = br_mdb_parse(skb, nlh, &dev, &entry, mdb_attrs, extack);
 	if (err < 0)
 		return err;
 
 	br = netdev_priv(dev);
 
+	if (!netif_running(br->dev)) {
+		NL_SET_ERR_MSG_MOD(extack, "Bridge device is not running");
+		return -EINVAL;
+	}
+
+	if (!br_opt_get(br, BROPT_MULTICAST_ENABLED)) {
+		NL_SET_ERR_MSG_MOD(extack, "Bridge's multicast processing is disabled");
+		return -EINVAL;
+	}
+
 	if (entry->ifindex != br->dev->ifindex) {
 		pdev = __dev_get_by_index(net, entry->ifindex);
-		if (!pdev)
+		if (!pdev) {
+			NL_SET_ERR_MSG_MOD(extack, "Port net device doesn't exist");
 			return -ENODEV;
+		}
 
 		p = br_port_get_rtnl(pdev);
-		if (!p || p->br != br || p->state == BR_STATE_DISABLED)
+		if (!p) {
+			NL_SET_ERR_MSG_MOD(extack, "Net device is not a bridge port");
+			return -EINVAL;
+		}
+
+		if (p->br != br) {
+			NL_SET_ERR_MSG_MOD(extack, "Port belongs to a different bridge device");
 			return -EINVAL;
+		}
+		if (p->state == BR_STATE_DISABLED) {
+			NL_SET_ERR_MSG_MOD(extack, "Port is in disabled state");
+			return -EINVAL;
+		}
 		vg = nbp_vlan_group(p);
 	} else {
 		vg = br_vlan_group(br);
@@ -822,18 +993,19 @@ static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (br_vlan_enabled(br->dev) && vg && entry->vid == 0) {
 		list_for_each_entry(v, &vg->vlan_list, vlist) {
 			entry->vid = v->vid;
-			err = __br_mdb_add(net, br, entry);
+			err = __br_mdb_add(net, br, p, entry, mdb_attrs, extack);
 			if (err)
 				break;
 		}
 	} else {
-		err = __br_mdb_add(net, br, entry);
+		err = __br_mdb_add(net, br, p, entry, mdb_attrs, extack);
 	}
 
 	return err;
 }
 
-static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry)
+static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry,
+			struct nlattr **mdb_attrs)
 {
 	struct net_bridge_mdb_entry *mp;
 	struct net_bridge_port_group *p;
@@ -844,7 +1016,7 @@ static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry)
 	if (!netif_running(br->dev) || !br_opt_get(br, BROPT_MULTICAST_ENABLED))
 		return -EINVAL;
 
-	__mdb_entry_to_br_ip(entry, &ip);
+	__mdb_entry_to_br_ip(entry, &ip, mdb_attrs);
 
 	spin_lock_bh(&br->multicast_lock);
 	mp = br_mdb_ip_get(br, &ip);
@@ -864,10 +1036,10 @@ static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry)
 	for (pp = &mp->ports;
 	     (p = mlock_dereference(*pp, br)) != NULL;
 	     pp = &p->next) {
-		if (!p->port || p->port->dev->ifindex != entry->ifindex)
+		if (!p->key.port || p->key.port->dev->ifindex != entry->ifindex)
 			continue;
 
-		if (p->port->state == BR_STATE_DISABLED)
+		if (p->key.port->state == BR_STATE_DISABLED)
 			goto unlock;
 
 		br_multicast_del_pg(mp, p, pp);
@@ -883,6 +1055,7 @@ unlock:
 static int br_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,
 		      struct netlink_ext_ack *extack)
 {
+	struct nlattr *mdb_attrs[MDBE_ATTR_MAX + 1];
 	struct net *net = sock_net(skb->sk);
 	struct net_bridge_vlan_group *vg;
 	struct net_bridge_port *p = NULL;
@@ -892,7 +1065,7 @@ static int br_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,
 	struct net_bridge *br;
 	int err;
 
-	err = br_mdb_parse(skb, nlh, &dev, &entry);
+	err = br_mdb_parse(skb, nlh, &dev, &entry, mdb_attrs, extack);
 	if (err < 0)
 		return err;
 
@@ -917,10 +1090,10 @@ static int br_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (br_vlan_enabled(br->dev) && vg && entry->vid == 0) {
 		list_for_each_entry(v, &vg->vlan_list, vlist) {
 			entry->vid = v->vid;
-			err = __br_mdb_del(br, entry);
+			err = __br_mdb_del(br, entry, mdb_attrs);
 		}
 	} else {
-		err = __br_mdb_del(br, entry);
+		err = __br_mdb_del(br, entry, mdb_attrs);
 	}
 
 	return err;
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index e77f1e27caf7..eae898c3cff7 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -41,6 +41,13 @@ static const struct rhashtable_params br_mdb_rht_params = {
 	.automatic_shrinking = true,
 };
 
+static const struct rhashtable_params br_sg_port_rht_params = {
+	.head_offset = offsetof(struct net_bridge_port_group, rhnode),
+	.key_offset = offsetof(struct net_bridge_port_group, key),
+	.key_len = sizeof(struct net_bridge_port_group_sg_key),
+	.automatic_shrinking = true,
+};
+
 static void br_multicast_start_querier(struct net_bridge *br,
 				       struct bridge_mcast_own_query *query);
 static void br_multicast_add_router(struct net_bridge *br,
@@ -59,6 +66,26 @@ static void br_ip6_multicast_leave_group(struct net_bridge *br,
 					 const struct in6_addr *group,
 					 __u16 vid, const unsigned char *src);
 #endif
+static struct net_bridge_port_group *
+__br_multicast_add_group(struct net_bridge *br,
+			 struct net_bridge_port *port,
+			 struct br_ip *group,
+			 const unsigned char *src,
+			 u8 filter_mode,
+			 bool igmpv2_mldv1,
+			 bool blocked);
+static void br_multicast_find_del_pg(struct net_bridge *br,
+				     struct net_bridge_port_group *pg);
+
+static struct net_bridge_port_group *
+br_sg_port_find(struct net_bridge *br,
+		struct net_bridge_port_group_sg_key *sg_p)
+{
+	lockdep_assert_held_once(&br->multicast_lock);
+
+	return rhashtable_lookup_fast(&br->sg_port_tbl, sg_p,
+				      br_sg_port_rht_params);
+}
 
 static struct net_bridge_mdb_entry *br_mdb_ip_get_rcu(struct net_bridge *br,
 						      struct br_ip *dst)
@@ -86,7 +113,7 @@ static struct net_bridge_mdb_entry *br_mdb_ip4_get(struct net_bridge *br,
 	struct br_ip br_dst;
 
 	memset(&br_dst, 0, sizeof(br_dst));
-	br_dst.u.ip4 = dst;
+	br_dst.dst.ip4 = dst;
 	br_dst.proto = htons(ETH_P_IP);
 	br_dst.vid = vid;
 
@@ -101,7 +128,7 @@ static struct net_bridge_mdb_entry *br_mdb_ip6_get(struct net_bridge *br,
 	struct br_ip br_dst;
 
 	memset(&br_dst, 0, sizeof(br_dst));
-	br_dst.u.ip6 = *dst;
+	br_dst.dst.ip6 = *dst;
 	br_dst.proto = htons(ETH_P_IPV6);
 	br_dst.vid = vid;
 
@@ -126,11 +153,29 @@ struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge *br,
 
 	switch (skb->protocol) {
 	case htons(ETH_P_IP):
-		ip.u.ip4 = ip_hdr(skb)->daddr;
+		ip.dst.ip4 = ip_hdr(skb)->daddr;
+		if (br->multicast_igmp_version == 3) {
+			struct net_bridge_mdb_entry *mdb;
+
+			ip.src.ip4 = ip_hdr(skb)->saddr;
+			mdb = br_mdb_ip_get_rcu(br, &ip);
+			if (mdb)
+				return mdb;
+			ip.src.ip4 = 0;
+		}
 		break;
 #if IS_ENABLED(CONFIG_IPV6)
 	case htons(ETH_P_IPV6):
-		ip.u.ip6 = ipv6_hdr(skb)->daddr;
+		ip.dst.ip6 = ipv6_hdr(skb)->daddr;
+		if (br->multicast_mld_version == 2) {
+			struct net_bridge_mdb_entry *mdb;
+
+			ip.src.ip6 = ipv6_hdr(skb)->saddr;
+			mdb = br_mdb_ip_get_rcu(br, &ip);
+			if (mdb)
+				return mdb;
+			memset(&ip.src.ip6, 0, sizeof(ip.src.ip6));
+		}
 		break;
 #endif
 	default:
@@ -140,6 +185,326 @@ struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge *br,
 	return br_mdb_ip_get_rcu(br, &ip);
 }
 
+static bool br_port_group_equal(struct net_bridge_port_group *p,
+				struct net_bridge_port *port,
+				const unsigned char *src)
+{
+	if (p->key.port != port)
+		return false;
+
+	if (!(port->flags & BR_MULTICAST_TO_UNICAST))
+		return true;
+
+	return ether_addr_equal(src, p->eth_addr);
+}
+
+static void __fwd_add_star_excl(struct net_bridge_port_group *pg,
+				struct br_ip *sg_ip)
+{
+	struct net_bridge_port_group_sg_key sg_key;
+	struct net_bridge *br = pg->key.port->br;
+	struct net_bridge_port_group *src_pg;
+
+	memset(&sg_key, 0, sizeof(sg_key));
+	sg_key.port = pg->key.port;
+	sg_key.addr = *sg_ip;
+	if (br_sg_port_find(br, &sg_key))
+		return;
+
+	src_pg = __br_multicast_add_group(br, pg->key.port, sg_ip, pg->eth_addr,
+					  MCAST_INCLUDE, false, false);
+	if (IS_ERR_OR_NULL(src_pg) ||
+	    src_pg->rt_protocol != RTPROT_KERNEL)
+		return;
+
+	src_pg->flags |= MDB_PG_FLAGS_STAR_EXCL;
+}
+
+static void __fwd_del_star_excl(struct net_bridge_port_group *pg,
+				struct br_ip *sg_ip)
+{
+	struct net_bridge_port_group_sg_key sg_key;
+	struct net_bridge *br = pg->key.port->br;
+	struct net_bridge_port_group *src_pg;
+
+	memset(&sg_key, 0, sizeof(sg_key));
+	sg_key.port = pg->key.port;
+	sg_key.addr = *sg_ip;
+	src_pg = br_sg_port_find(br, &sg_key);
+	if (!src_pg || !(src_pg->flags & MDB_PG_FLAGS_STAR_EXCL) ||
+	    src_pg->rt_protocol != RTPROT_KERNEL)
+		return;
+
+	br_multicast_find_del_pg(br, src_pg);
+}
+
+/* When a port group transitions to (or is added as) EXCLUDE we need to add it
+ * to all other ports' S,G entries which are not blocked by the current group
+ * for proper replication, the assumption is that any S,G blocked entries
+ * are already added so the S,G,port lookup should skip them.
+ * When a port group transitions from EXCLUDE -> INCLUDE mode or is being
+ * deleted we need to remove it from all ports' S,G entries where it was
+ * automatically installed before (i.e. where it's MDB_PG_FLAGS_STAR_EXCL).
+ */
+void br_multicast_star_g_handle_mode(struct net_bridge_port_group *pg,
+				     u8 filter_mode)
+{
+	struct net_bridge *br = pg->key.port->br;
+	struct net_bridge_port_group *pg_lst;
+	struct net_bridge_mdb_entry *mp;
+	struct br_ip sg_ip;
+
+	if (WARN_ON(!br_multicast_is_star_g(&pg->key.addr)))
+		return;
+
+	mp = br_mdb_ip_get(br, &pg->key.addr);
+	if (!mp)
+		return;
+
+	memset(&sg_ip, 0, sizeof(sg_ip));
+	sg_ip = pg->key.addr;
+	for (pg_lst = mlock_dereference(mp->ports, br);
+	     pg_lst;
+	     pg_lst = mlock_dereference(pg_lst->next, br)) {
+		struct net_bridge_group_src *src_ent;
+
+		if (pg_lst == pg)
+			continue;
+		hlist_for_each_entry(src_ent, &pg_lst->src_list, node) {
+			if (!(src_ent->flags & BR_SGRP_F_INSTALLED))
+				continue;
+			sg_ip.src = src_ent->addr.src;
+			switch (filter_mode) {
+			case MCAST_INCLUDE:
+				__fwd_del_star_excl(pg, &sg_ip);
+				break;
+			case MCAST_EXCLUDE:
+				__fwd_add_star_excl(pg, &sg_ip);
+				break;
+			}
+		}
+	}
+}
+
+/* called when adding a new S,G with host_joined == false by default */
+static void br_multicast_sg_host_state(struct net_bridge_mdb_entry *star_mp,
+				       struct net_bridge_port_group *sg)
+{
+	struct net_bridge_mdb_entry *sg_mp;
+
+	if (WARN_ON(!br_multicast_is_star_g(&star_mp->addr)))
+		return;
+	if (!star_mp->host_joined)
+		return;
+
+	sg_mp = br_mdb_ip_get(star_mp->br, &sg->key.addr);
+	if (!sg_mp)
+		return;
+	sg_mp->host_joined = true;
+}
+
+/* set the host_joined state of all of *,G's S,G entries */
+static void br_multicast_star_g_host_state(struct net_bridge_mdb_entry *star_mp)
+{
+	struct net_bridge *br = star_mp->br;
+	struct net_bridge_mdb_entry *sg_mp;
+	struct net_bridge_port_group *pg;
+	struct br_ip sg_ip;
+
+	if (WARN_ON(!br_multicast_is_star_g(&star_mp->addr)))
+		return;
+
+	memset(&sg_ip, 0, sizeof(sg_ip));
+	sg_ip = star_mp->addr;
+	for (pg = mlock_dereference(star_mp->ports, br);
+	     pg;
+	     pg = mlock_dereference(pg->next, br)) {
+		struct net_bridge_group_src *src_ent;
+
+		hlist_for_each_entry(src_ent, &pg->src_list, node) {
+			if (!(src_ent->flags & BR_SGRP_F_INSTALLED))
+				continue;
+			sg_ip.src = src_ent->addr.src;
+			sg_mp = br_mdb_ip_get(br, &sg_ip);
+			if (!sg_mp)
+				continue;
+			sg_mp->host_joined = star_mp->host_joined;
+		}
+	}
+}
+
+static void br_multicast_sg_del_exclude_ports(struct net_bridge_mdb_entry *sgmp)
+{
+	struct net_bridge_port_group __rcu **pp;
+	struct net_bridge_port_group *p;
+
+	/* *,G exclude ports are only added to S,G entries */
+	if (WARN_ON(br_multicast_is_star_g(&sgmp->addr)))
+		return;
+
+	/* we need the STAR_EXCLUDE ports if there are non-STAR_EXCLUDE ports
+	 * we should ignore perm entries since they're managed by user-space
+	 */
+	for (pp = &sgmp->ports;
+	     (p = mlock_dereference(*pp, sgmp->br)) != NULL;
+	     pp = &p->next)
+		if (!(p->flags & (MDB_PG_FLAGS_STAR_EXCL |
+				  MDB_PG_FLAGS_PERMANENT)))
+			return;
+
+	/* currently the host can only have joined the *,G which means
+	 * we treat it as EXCLUDE {}, so for an S,G it's considered a
+	 * STAR_EXCLUDE entry and we can safely leave it
+	 */
+	sgmp->host_joined = false;
+
+	for (pp = &sgmp->ports;
+	     (p = mlock_dereference(*pp, sgmp->br)) != NULL;) {
+		if (!(p->flags & MDB_PG_FLAGS_PERMANENT))
+			br_multicast_del_pg(sgmp, p, pp);
+		else
+			pp = &p->next;
+	}
+}
+
+void br_multicast_sg_add_exclude_ports(struct net_bridge_mdb_entry *star_mp,
+				       struct net_bridge_port_group *sg)
+{
+	struct net_bridge_port_group_sg_key sg_key;
+	struct net_bridge *br = star_mp->br;
+	struct net_bridge_port_group *pg;
+
+	if (WARN_ON(br_multicast_is_star_g(&sg->key.addr)))
+		return;
+	if (WARN_ON(!br_multicast_is_star_g(&star_mp->addr)))
+		return;
+
+	br_multicast_sg_host_state(star_mp, sg);
+	memset(&sg_key, 0, sizeof(sg_key));
+	sg_key.addr = sg->key.addr;
+	/* we need to add all exclude ports to the S,G */
+	for (pg = mlock_dereference(star_mp->ports, br);
+	     pg;
+	     pg = mlock_dereference(pg->next, br)) {
+		struct net_bridge_port_group *src_pg;
+
+		if (pg == sg || pg->filter_mode == MCAST_INCLUDE)
+			continue;
+
+		sg_key.port = pg->key.port;
+		if (br_sg_port_find(br, &sg_key))
+			continue;
+
+		src_pg = __br_multicast_add_group(br, pg->key.port,
+						  &sg->key.addr,
+						  sg->eth_addr,
+						  MCAST_INCLUDE, false, false);
+		if (IS_ERR_OR_NULL(src_pg) ||
+		    src_pg->rt_protocol != RTPROT_KERNEL)
+			continue;
+		src_pg->flags |= MDB_PG_FLAGS_STAR_EXCL;
+	}
+}
+
+static void br_multicast_fwd_src_add(struct net_bridge_group_src *src)
+{
+	struct net_bridge_mdb_entry *star_mp;
+	struct net_bridge_port_group *sg;
+	struct br_ip sg_ip;
+
+	if (src->flags & BR_SGRP_F_INSTALLED)
+		return;
+
+	memset(&sg_ip, 0, sizeof(sg_ip));
+	sg_ip = src->pg->key.addr;
+	sg_ip.src = src->addr.src;
+	sg = __br_multicast_add_group(src->br, src->pg->key.port, &sg_ip,
+				      src->pg->eth_addr, MCAST_INCLUDE, false,
+				      !timer_pending(&src->timer));
+	if (IS_ERR_OR_NULL(sg))
+		return;
+	src->flags |= BR_SGRP_F_INSTALLED;
+	sg->flags &= ~MDB_PG_FLAGS_STAR_EXCL;
+
+	/* if it was added by user-space as perm we can skip next steps */
+	if (sg->rt_protocol != RTPROT_KERNEL &&
+	    (sg->flags & MDB_PG_FLAGS_PERMANENT))
+		return;
+
+	/* the kernel is now responsible for removing this S,G */
+	del_timer(&sg->timer);
+	star_mp = br_mdb_ip_get(src->br, &src->pg->key.addr);
+	if (!star_mp)
+		return;
+
+	br_multicast_sg_add_exclude_ports(star_mp, sg);
+}
+
+static void br_multicast_fwd_src_remove(struct net_bridge_group_src *src)
+{
+	struct net_bridge_port_group *p, *pg = src->pg;
+	struct net_bridge_port_group __rcu **pp;
+	struct net_bridge_mdb_entry *mp;
+	struct br_ip sg_ip;
+
+	memset(&sg_ip, 0, sizeof(sg_ip));
+	sg_ip = pg->key.addr;
+	sg_ip.src = src->addr.src;
+
+	mp = br_mdb_ip_get(src->br, &sg_ip);
+	if (!mp)
+		return;
+
+	for (pp = &mp->ports;
+	     (p = mlock_dereference(*pp, src->br)) != NULL;
+	     pp = &p->next) {
+		if (!br_port_group_equal(p, pg->key.port, pg->eth_addr))
+			continue;
+
+		if (p->rt_protocol != RTPROT_KERNEL &&
+		    (p->flags & MDB_PG_FLAGS_PERMANENT))
+			break;
+
+		br_multicast_del_pg(mp, p, pp);
+		break;
+	}
+	src->flags &= ~BR_SGRP_F_INSTALLED;
+}
+
+/* install S,G and based on src's timer enable or disable forwarding */
+static void br_multicast_fwd_src_handle(struct net_bridge_group_src *src)
+{
+	struct net_bridge_port_group_sg_key sg_key;
+	struct net_bridge_port_group *sg;
+	u8 old_flags;
+
+	br_multicast_fwd_src_add(src);
+
+	memset(&sg_key, 0, sizeof(sg_key));
+	sg_key.addr = src->pg->key.addr;
+	sg_key.addr.src = src->addr.src;
+	sg_key.port = src->pg->key.port;
+
+	sg = br_sg_port_find(src->br, &sg_key);
+	if (!sg || (sg->flags & MDB_PG_FLAGS_PERMANENT))
+		return;
+
+	old_flags = sg->flags;
+	if (timer_pending(&src->timer))
+		sg->flags &= ~MDB_PG_FLAGS_BLOCKED;
+	else
+		sg->flags |= MDB_PG_FLAGS_BLOCKED;
+
+	if (old_flags != sg->flags) {
+		struct net_bridge_mdb_entry *sg_mp;
+
+		sg_mp = br_mdb_ip_get(src->br, &sg_key.addr);
+		if (!sg_mp)
+			return;
+		br_mdb_notify(src->br->dev, sg_mp, sg, RTM_NEWMDB);
+	}
+}
+
 static void br_multicast_destroy_mdb_entry(struct net_bridge_mcast_gc *gc)
 {
 	struct net_bridge_mdb_entry *mp;
@@ -169,7 +534,8 @@ static void br_multicast_group_expired(struct timer_list *t)
 	struct net_bridge *br = mp->br;
 
 	spin_lock(&br->multicast_lock);
-	if (!netif_running(br->dev) || timer_pending(&mp->timer))
+	if (hlist_unhashed(&mp->mdb_node) || !netif_running(br->dev) ||
+	    timer_pending(&mp->timer))
 		goto out;
 
 	br_multicast_host_leave(mp, true);
@@ -194,8 +560,9 @@ static void br_multicast_destroy_group_src(struct net_bridge_mcast_gc *gc)
 
 static void br_multicast_del_group_src(struct net_bridge_group_src *src)
 {
-	struct net_bridge *br = src->pg->port->br;
+	struct net_bridge *br = src->pg->key.port->br;
 
+	br_multicast_fwd_src_remove(src);
 	hlist_del_init_rcu(&src->node);
 	src->pg->src_ents--;
 	hlist_add_head(&src->mcast_gc.gc_node, &br->mcast_gc_list);
@@ -219,7 +586,7 @@ void br_multicast_del_pg(struct net_bridge_mdb_entry *mp,
 			 struct net_bridge_port_group *pg,
 			 struct net_bridge_port_group __rcu **pp)
 {
-	struct net_bridge *br = pg->port->br;
+	struct net_bridge *br = pg->key.port->br;
 	struct net_bridge_group_src *ent;
 	struct hlist_node *tmp;
 
@@ -228,6 +595,13 @@ void br_multicast_del_pg(struct net_bridge_mdb_entry *mp,
 	hlist_for_each_entry_safe(ent, tmp, &pg->src_list, node)
 		br_multicast_del_group_src(ent);
 	br_mdb_notify(br->dev, mp, pg, RTM_DELMDB);
+	if (!br_multicast_is_star_g(&mp->addr)) {
+		rhashtable_remove_fast(&br->sg_port_tbl, &pg->rhnode,
+				       br_sg_port_rht_params);
+		br_multicast_sg_del_exclude_ports(mp);
+	} else {
+		br_multicast_star_g_handle_mode(pg, MCAST_INCLUDE);
+	}
 	hlist_add_head(&pg->mcast_gc.gc_node, &br->mcast_gc_list);
 	queue_work(system_long_wq, &br->mcast_gc_work);
 
@@ -242,7 +616,7 @@ static void br_multicast_find_del_pg(struct net_bridge *br,
 	struct net_bridge_mdb_entry *mp;
 	struct net_bridge_port_group *p;
 
-	mp = br_mdb_ip_get(br, &pg->addr);
+	mp = br_mdb_ip_get(br, &pg->key.addr);
 	if (WARN_ON(!mp))
 		return;
 
@@ -263,7 +637,7 @@ static void br_multicast_port_group_expired(struct timer_list *t)
 {
 	struct net_bridge_port_group *pg = from_timer(pg, t, timer);
 	struct net_bridge_group_src *src_ent;
-	struct net_bridge *br = pg->port->br;
+	struct net_bridge *br = pg->key.port->br;
 	struct hlist_node *tmp;
 	bool changed;
 
@@ -284,7 +658,10 @@ static void br_multicast_port_group_expired(struct timer_list *t)
 	if (hlist_empty(&pg->src_list)) {
 		br_multicast_find_del_pg(br, pg);
 	} else if (changed) {
-		struct net_bridge_mdb_entry *mp = br_mdb_ip_get(br, &pg->addr);
+		struct net_bridge_mdb_entry *mp = br_mdb_ip_get(br, &pg->key.addr);
+
+		if (changed && br_multicast_is_star_g(&pg->key.addr))
+			br_multicast_star_g_handle_mode(pg, MCAST_INCLUDE);
 
 		if (WARN_ON(!mp))
 			goto out;
@@ -312,7 +689,7 @@ static struct sk_buff *br_ip4_multicast_alloc_query(struct net_bridge *br,
 						    u8 sflag, u8 *igmp_type,
 						    bool *need_rexmit)
 {
-	struct net_bridge_port *p = pg ? pg->port : NULL;
+	struct net_bridge_port *p = pg ? pg->key.port : NULL;
 	struct net_bridge_group_src *ent;
 	size_t pkt_size, igmp_hdr_size;
 	unsigned long now = jiffies;
@@ -423,7 +800,7 @@ static struct sk_buff *br_ip4_multicast_alloc_query(struct net_bridge *br,
 			if (over_lmqt == time_after(ent->timer.expires,
 						    lmqt) &&
 			    ent->src_query_rexmit_cnt > 0) {
-				ihv3->srcs[lmqt_srcs++] = ent->addr.u.ip4;
+				ihv3->srcs[lmqt_srcs++] = ent->addr.src.ip4;
 				ent->src_query_rexmit_cnt--;
 				if (need_rexmit && ent->src_query_rexmit_cnt)
 					*need_rexmit = true;
@@ -458,7 +835,7 @@ static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br,
 						    u8 sflag, u8 *igmp_type,
 						    bool *need_rexmit)
 {
-	struct net_bridge_port *p = pg ? pg->port : NULL;
+	struct net_bridge_port *p = pg ? pg->key.port : NULL;
 	struct net_bridge_group_src *ent;
 	size_t pkt_size, mld_hdr_size;
 	unsigned long now = jiffies;
@@ -584,7 +961,7 @@ static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br,
 			if (over_llqt == time_after(ent->timer.expires,
 						    llqt) &&
 			    ent->src_query_rexmit_cnt > 0) {
-				mld2q->mld2q_srcs[llqt_srcs++] = ent->addr.u.ip6;
+				mld2q->mld2q_srcs[llqt_srcs++] = ent->addr.src.ip6;
 				ent->src_query_rexmit_cnt--;
 				if (need_rexmit && ent->src_query_rexmit_cnt)
 					*need_rexmit = true;
@@ -625,9 +1002,9 @@ static struct sk_buff *br_multicast_alloc_query(struct net_bridge *br,
 
 	switch (group->proto) {
 	case htons(ETH_P_IP):
-		ip4_dst = ip_dst ? ip_dst->u.ip4 : htonl(INADDR_ALLHOSTS_GROUP);
+		ip4_dst = ip_dst ? ip_dst->dst.ip4 : htonl(INADDR_ALLHOSTS_GROUP);
 		return br_ip4_multicast_alloc_query(br, pg,
-						    ip4_dst, group->u.ip4,
+						    ip4_dst, group->dst.ip4,
 						    with_srcs, over_lmqt,
 						    sflag, igmp_type,
 						    need_rexmit);
@@ -636,13 +1013,13 @@ static struct sk_buff *br_multicast_alloc_query(struct net_bridge *br,
 		struct in6_addr ip6_dst;
 
 		if (ip_dst)
-			ip6_dst = ip_dst->u.ip6;
+			ip6_dst = ip_dst->dst.ip6;
 		else
 			ipv6_addr_set(&ip6_dst, htonl(0xff020000), 0, 0,
 				      htonl(1));
 
 		return br_ip6_multicast_alloc_query(br, pg,
-						    &ip6_dst, &group->u.ip6,
+						    &ip6_dst, &group->dst.ip6,
 						    with_srcs, over_lmqt,
 						    sflag, igmp_type,
 						    need_rexmit);
@@ -704,7 +1081,10 @@ static void br_multicast_group_src_expired(struct timer_list *t)
 		if (!hlist_empty(&pg->src_list))
 			goto out;
 		br_multicast_find_del_pg(br, pg);
+	} else {
+		br_multicast_fwd_src_handle(src);
 	}
+
 out:
 	spin_unlock(&br->multicast_lock);
 }
@@ -717,13 +1097,13 @@ br_multicast_find_group_src(struct net_bridge_port_group *pg, struct br_ip *ip)
 	switch (ip->proto) {
 	case htons(ETH_P_IP):
 		hlist_for_each_entry(ent, &pg->src_list, node)
-			if (ip->u.ip4 == ent->addr.u.ip4)
+			if (ip->src.ip4 == ent->addr.src.ip4)
 				return ent;
 		break;
 #if IS_ENABLED(CONFIG_IPV6)
 	case htons(ETH_P_IPV6):
 		hlist_for_each_entry(ent, &pg->src_list, node)
-			if (!ipv6_addr_cmp(&ent->addr.u.ip6, &ip->u.ip6))
+			if (!ipv6_addr_cmp(&ent->addr.src.ip6, &ip->src.ip6))
 				return ent;
 		break;
 #endif
@@ -742,14 +1122,14 @@ br_multicast_new_group_src(struct net_bridge_port_group *pg, struct br_ip *src_i
 
 	switch (src_ip->proto) {
 	case htons(ETH_P_IP):
-		if (ipv4_is_zeronet(src_ip->u.ip4) ||
-		    ipv4_is_multicast(src_ip->u.ip4))
+		if (ipv4_is_zeronet(src_ip->src.ip4) ||
+		    ipv4_is_multicast(src_ip->src.ip4))
 			return NULL;
 		break;
 #if IS_ENABLED(CONFIG_IPV6)
 	case htons(ETH_P_IPV6):
-		if (ipv6_addr_any(&src_ip->u.ip6) ||
-		    ipv6_addr_is_multicast(&src_ip->u.ip6))
+		if (ipv6_addr_any(&src_ip->src.ip6) ||
+		    ipv6_addr_is_multicast(&src_ip->src.ip6))
 			return NULL;
 		break;
 #endif
@@ -760,7 +1140,7 @@ br_multicast_new_group_src(struct net_bridge_port_group *pg, struct br_ip *src_i
 		return NULL;
 
 	grp_src->pg = pg;
-	grp_src->br = pg->port->br;
+	grp_src->br = pg->key.port->br;
 	grp_src->addr = *src_ip;
 	grp_src->mcast_gc.destroy = br_multicast_destroy_group_src;
 	timer_setup(&grp_src->timer, br_multicast_group_src_expired, 0);
@@ -777,7 +1157,8 @@ struct net_bridge_port_group *br_multicast_new_port_group(
 			struct net_bridge_port_group __rcu *next,
 			unsigned char flags,
 			const unsigned char *src,
-			u8 filter_mode)
+			u8 filter_mode,
+			u8 rt_protocol)
 {
 	struct net_bridge_port_group *p;
 
@@ -785,12 +1166,21 @@ struct net_bridge_port_group *br_multicast_new_port_group(
 	if (unlikely(!p))
 		return NULL;
 
-	p->addr = *group;
-	p->port = port;
+	p->key.addr = *group;
+	p->key.port = port;
 	p->flags = flags;
 	p->filter_mode = filter_mode;
+	p->rt_protocol = rt_protocol;
 	p->mcast_gc.destroy = br_multicast_destroy_port_group;
 	INIT_HLIST_HEAD(&p->src_list);
+
+	if (!br_multicast_is_star_g(group) &&
+	    rhashtable_lookup_insert_fast(&port->br->sg_port_tbl, &p->rhnode,
+					  br_sg_port_rht_params)) {
+		kfree(p);
+		return NULL;
+	}
+
 	rcu_assign_pointer(p->next, next);
 	timer_setup(&p->timer, br_multicast_port_group_expired, 0);
 	timer_setup(&p->rexmit_timer, br_multicast_port_group_rexmit, 0);
@@ -804,23 +1194,12 @@ struct net_bridge_port_group *br_multicast_new_port_group(
 	return p;
 }
 
-static bool br_port_group_equal(struct net_bridge_port_group *p,
-				struct net_bridge_port *port,
-				const unsigned char *src)
-{
-	if (p->port != port)
-		return false;
-
-	if (!(port->flags & BR_MULTICAST_TO_UNICAST))
-		return true;
-
-	return ether_addr_equal(src, p->eth_addr);
-}
-
 void br_multicast_host_join(struct net_bridge_mdb_entry *mp, bool notify)
 {
 	if (!mp->host_joined) {
 		mp->host_joined = true;
+		if (br_multicast_is_star_g(&mp->addr))
+			br_multicast_star_g_host_state(mp);
 		if (notify)
 			br_mdb_notify(mp->br->dev, mp, NULL, RTM_NEWMDB);
 	}
@@ -833,32 +1212,33 @@ void br_multicast_host_leave(struct net_bridge_mdb_entry *mp, bool notify)
 		return;
 
 	mp->host_joined = false;
+	if (br_multicast_is_star_g(&mp->addr))
+		br_multicast_star_g_host_state(mp);
 	if (notify)
 		br_mdb_notify(mp->br->dev, mp, NULL, RTM_DELMDB);
 }
 
-static int br_multicast_add_group(struct net_bridge *br,
-				  struct net_bridge_port *port,
-				  struct br_ip *group,
-				  const unsigned char *src,
-				  u8 filter_mode,
-				  bool igmpv2_mldv1)
+static struct net_bridge_port_group *
+__br_multicast_add_group(struct net_bridge *br,
+			 struct net_bridge_port *port,
+			 struct br_ip *group,
+			 const unsigned char *src,
+			 u8 filter_mode,
+			 bool igmpv2_mldv1,
+			 bool blocked)
 {
 	struct net_bridge_port_group __rcu **pp;
-	struct net_bridge_port_group *p;
+	struct net_bridge_port_group *p = NULL;
 	struct net_bridge_mdb_entry *mp;
 	unsigned long now = jiffies;
-	int err;
 
-	spin_lock(&br->multicast_lock);
 	if (!netif_running(br->dev) ||
 	    (port && port->state == BR_STATE_DISABLED))
 		goto out;
 
 	mp = br_multicast_new_group(br, group);
-	err = PTR_ERR(mp);
 	if (IS_ERR(mp))
-		goto err;
+		return ERR_PTR(PTR_ERR(mp));
 
 	if (!port) {
 		br_multicast_host_join(mp, true);
@@ -870,14 +1250,19 @@ static int br_multicast_add_group(struct net_bridge *br,
 	     pp = &p->next) {
 		if (br_port_group_equal(p, port, src))
 			goto found;
-		if ((unsigned long)p->port < (unsigned long)port)
+		if ((unsigned long)p->key.port < (unsigned long)port)
 			break;
 	}
 
-	p = br_multicast_new_port_group(port, group, *pp, 0, src, filter_mode);
-	if (unlikely(!p))
-		goto err;
+	p = br_multicast_new_port_group(port, group, *pp, 0, src, filter_mode,
+					RTPROT_KERNEL);
+	if (unlikely(!p)) {
+		p = ERR_PTR(-ENOMEM);
+		goto out;
+	}
 	rcu_assign_pointer(*pp, p);
+	if (blocked)
+		p->flags |= MDB_PG_FLAGS_BLOCKED;
 	br_mdb_notify(br->dev, mp, p, RTM_NEWMDB);
 
 found:
@@ -885,10 +1270,26 @@ found:
 		mod_timer(&p->timer, now + br->multicast_membership_interval);
 
 out:
-	err = 0;
+	return p;
+}
+
+static int br_multicast_add_group(struct net_bridge *br,
+				  struct net_bridge_port *port,
+				  struct br_ip *group,
+				  const unsigned char *src,
+				  u8 filter_mode,
+				  bool igmpv2_mldv1)
+{
+	struct net_bridge_port_group *pg;
+	int err;
 
-err:
+	spin_lock(&br->multicast_lock);
+	pg = __br_multicast_add_group(br, port, group, src, filter_mode,
+				      igmpv2_mldv1, false);
+	/* NULL is considered valid for host joined groups */
+	err = IS_ERR(pg) ? PTR_ERR(pg) : 0;
 	spin_unlock(&br->multicast_lock);
+
 	return err;
 }
 
@@ -906,7 +1307,7 @@ static int br_ip4_multicast_add_group(struct net_bridge *br,
 		return 0;
 
 	memset(&br_group, 0, sizeof(br_group));
-	br_group.u.ip4 = group;
+	br_group.dst.ip4 = group;
 	br_group.proto = htons(ETH_P_IP);
 	br_group.vid = vid;
 	filter_mode = igmpv2 ? MCAST_EXCLUDE : MCAST_INCLUDE;
@@ -930,7 +1331,7 @@ static int br_ip6_multicast_add_group(struct net_bridge *br,
 		return 0;
 
 	memset(&br_group, 0, sizeof(br_group));
-	br_group.u.ip6 = *group;
+	br_group.dst.ip6 = *group;
 	br_group.proto = htons(ETH_P_IPV6);
 	br_group.vid = vid;
 	filter_mode = mldv1 ? MCAST_EXCLUDE : MCAST_INCLUDE;
@@ -1019,10 +1420,10 @@ static void br_multicast_select_own_querier(struct net_bridge *br,
 					    struct sk_buff *skb)
 {
 	if (ip->proto == htons(ETH_P_IP))
-		br->ip4_querier.addr.u.ip4 = ip_hdr(skb)->saddr;
+		br->ip4_querier.addr.src.ip4 = ip_hdr(skb)->saddr;
 #if IS_ENABLED(CONFIG_IPV6)
 	else
-		br->ip6_querier.addr.u.ip6 = ipv6_hdr(skb)->saddr;
+		br->ip6_querier.addr.src.ip6 = ipv6_hdr(skb)->saddr;
 #endif
 }
 
@@ -1079,7 +1480,7 @@ static void br_multicast_send_query(struct net_bridge *br,
 	    !br_opt_get(br, BROPT_MULTICAST_QUERIER))
 		return;
 
-	memset(&br_group.u, 0, sizeof(br_group.u));
+	memset(&br_group.dst, 0, sizeof(br_group.dst));
 
 	if (port ? (own_query == &port->ip4_own_query) :
 		   (own_query == &br->ip4_own_query)) {
@@ -1145,7 +1546,7 @@ static void br_multicast_port_group_rexmit(struct timer_list *t)
 {
 	struct net_bridge_port_group *pg = from_timer(pg, t, rexmit_timer);
 	struct bridge_mcast_other_query *other_query = NULL;
-	struct net_bridge *br = pg->port->br;
+	struct net_bridge *br = pg->key.port->br;
 	bool need_rexmit = false;
 
 	spin_lock(&br->multicast_lock);
@@ -1154,7 +1555,7 @@ static void br_multicast_port_group_rexmit(struct timer_list *t)
 	    !br_opt_get(br, BROPT_MULTICAST_QUERIER))
 		goto out;
 
-	if (pg->addr.proto == htons(ETH_P_IP))
+	if (pg->key.addr.proto == htons(ETH_P_IP))
 		other_query = &br->ip4_other_query;
 #if IS_ENABLED(CONFIG_IPV6)
 	else
@@ -1166,11 +1567,11 @@ static void br_multicast_port_group_rexmit(struct timer_list *t)
 
 	if (pg->grp_query_rexmit_cnt) {
 		pg->grp_query_rexmit_cnt--;
-		__br_multicast_send_query(br, pg->port, pg, &pg->addr,
-					  &pg->addr, false, 1, NULL);
+		__br_multicast_send_query(br, pg->key.port, pg, &pg->key.addr,
+					  &pg->key.addr, false, 1, NULL);
 	}
-	__br_multicast_send_query(br, pg->port, pg, &pg->addr,
-				  &pg->addr, true, 0, &need_rexmit);
+	__br_multicast_send_query(br, pg->key.port, pg, &pg->key.addr,
+				  &pg->key.addr, true, 0, &need_rexmit);
 
 	if (pg->grp_query_rexmit_cnt || need_rexmit)
 		mod_timer(&pg->rexmit_timer, jiffies +
@@ -1301,10 +1702,17 @@ static int __grp_src_delete_marked(struct net_bridge_port_group *pg)
 	return deleted;
 }
 
+static void __grp_src_mod_timer(struct net_bridge_group_src *src,
+				unsigned long expires)
+{
+	mod_timer(&src->timer, expires);
+	br_multicast_fwd_src_handle(src);
+}
+
 static void __grp_src_query_marked_and_rexmit(struct net_bridge_port_group *pg)
 {
 	struct bridge_mcast_other_query *other_query = NULL;
-	struct net_bridge *br = pg->port->br;
+	struct net_bridge *br = pg->key.port->br;
 	u32 lmqc = br->multicast_last_member_count;
 	unsigned long lmqt, lmi, now = jiffies;
 	struct net_bridge_group_src *ent;
@@ -1313,7 +1721,7 @@ static void __grp_src_query_marked_and_rexmit(struct net_bridge_port_group *pg)
 	    !br_opt_get(br, BROPT_MULTICAST_ENABLED))
 		return;
 
-	if (pg->addr.proto == htons(ETH_P_IP))
+	if (pg->key.addr.proto == htons(ETH_P_IP))
 		other_query = &br->ip4_other_query;
 #if IS_ENABLED(CONFIG_IPV6)
 	else
@@ -1329,7 +1737,7 @@ static void __grp_src_query_marked_and_rexmit(struct net_bridge_port_group *pg)
 				    other_query &&
 				    !timer_pending(&other_query->timer))
 					ent->src_query_rexmit_cnt = lmqc;
-				mod_timer(&ent->timer, lmqt);
+				__grp_src_mod_timer(ent, lmqt);
 			}
 		}
 	}
@@ -1338,8 +1746,8 @@ static void __grp_src_query_marked_and_rexmit(struct net_bridge_port_group *pg)
 	    !other_query || timer_pending(&other_query->timer))
 		return;
 
-	__br_multicast_send_query(br, pg->port, pg, &pg->addr,
-				  &pg->addr, true, 1, NULL);
+	__br_multicast_send_query(br, pg->key.port, pg, &pg->key.addr,
+				  &pg->key.addr, true, 1, NULL);
 
 	lmi = now + br->multicast_last_member_interval;
 	if (!timer_pending(&pg->rexmit_timer) ||
@@ -1350,14 +1758,14 @@ static void __grp_src_query_marked_and_rexmit(struct net_bridge_port_group *pg)
 static void __grp_send_query_and_rexmit(struct net_bridge_port_group *pg)
 {
 	struct bridge_mcast_other_query *other_query = NULL;
-	struct net_bridge *br = pg->port->br;
+	struct net_bridge *br = pg->key.port->br;
 	unsigned long now = jiffies, lmi;
 
 	if (!netif_running(br->dev) ||
 	    !br_opt_get(br, BROPT_MULTICAST_ENABLED))
 		return;
 
-	if (pg->addr.proto == htons(ETH_P_IP))
+	if (pg->key.addr.proto == htons(ETH_P_IP))
 		other_query = &br->ip4_other_query;
 #if IS_ENABLED(CONFIG_IPV6)
 	else
@@ -1368,8 +1776,8 @@ static void __grp_send_query_and_rexmit(struct net_bridge_port_group *pg)
 	    other_query && !timer_pending(&other_query->timer)) {
 		lmi = now + br->multicast_last_member_interval;
 		pg->grp_query_rexmit_cnt = br->multicast_last_member_count - 1;
-		__br_multicast_send_query(br, pg->port, pg, &pg->addr,
-					  &pg->addr, false, 0, NULL);
+		__br_multicast_send_query(br, pg->key.port, pg, &pg->key.addr,
+					  &pg->key.addr, false, 0, NULL);
 		if (!timer_pending(&pg->rexmit_timer) ||
 		    time_after(pg->rexmit_timer.expires, lmi))
 			mod_timer(&pg->rexmit_timer, lmi);
@@ -1389,7 +1797,7 @@ static void __grp_send_query_and_rexmit(struct net_bridge_port_group *pg)
 static bool br_multicast_isinc_allow(struct net_bridge_port_group *pg,
 				     void *srcs, u32 nsrcs, size_t src_size)
 {
-	struct net_bridge *br = pg->port->br;
+	struct net_bridge *br = pg->key.port->br;
 	struct net_bridge_group_src *ent;
 	unsigned long now = jiffies;
 	bool changed = false;
@@ -1397,9 +1805,9 @@ static bool br_multicast_isinc_allow(struct net_bridge_port_group *pg,
 	u32 src_idx;
 
 	memset(&src_ip, 0, sizeof(src_ip));
-	src_ip.proto = pg->addr.proto;
+	src_ip.proto = pg->key.addr.proto;
 	for (src_idx = 0; src_idx < nsrcs; src_idx++) {
-		memcpy(&src_ip.u, srcs, src_size);
+		memcpy(&src_ip.src, srcs, src_size);
 		ent = br_multicast_find_group_src(pg, &src_ip);
 		if (!ent) {
 			ent = br_multicast_new_group_src(pg, &src_ip);
@@ -1408,7 +1816,7 @@ static bool br_multicast_isinc_allow(struct net_bridge_port_group *pg,
 		}
 
 		if (ent)
-			mod_timer(&ent->timer, now + br_multicast_gmi(br));
+			__grp_src_mod_timer(ent, now + br_multicast_gmi(br));
 		srcs += src_size;
 	}
 
@@ -1431,14 +1839,16 @@ static void __grp_src_isexc_incl(struct net_bridge_port_group *pg,
 		ent->flags |= BR_SGRP_F_DELETE;
 
 	memset(&src_ip, 0, sizeof(src_ip));
-	src_ip.proto = pg->addr.proto;
+	src_ip.proto = pg->key.addr.proto;
 	for (src_idx = 0; src_idx < nsrcs; src_idx++) {
-		memcpy(&src_ip.u, srcs, src_size);
+		memcpy(&src_ip.src, srcs, src_size);
 		ent = br_multicast_find_group_src(pg, &src_ip);
 		if (ent)
 			ent->flags &= ~BR_SGRP_F_DELETE;
 		else
-			br_multicast_new_group_src(pg, &src_ip);
+			ent = br_multicast_new_group_src(pg, &src_ip);
+		if (ent)
+			br_multicast_fwd_src_handle(ent);
 		srcs += src_size;
 	}
 
@@ -1454,7 +1864,7 @@ static void __grp_src_isexc_incl(struct net_bridge_port_group *pg,
 static bool __grp_src_isexc_excl(struct net_bridge_port_group *pg,
 				 void *srcs, u32 nsrcs, size_t src_size)
 {
-	struct net_bridge *br = pg->port->br;
+	struct net_bridge *br = pg->key.port->br;
 	struct net_bridge_group_src *ent;
 	unsigned long now = jiffies;
 	bool changed = false;
@@ -1465,17 +1875,17 @@ static bool __grp_src_isexc_excl(struct net_bridge_port_group *pg,
 		ent->flags |= BR_SGRP_F_DELETE;
 
 	memset(&src_ip, 0, sizeof(src_ip));
-	src_ip.proto = pg->addr.proto;
+	src_ip.proto = pg->key.addr.proto;
 	for (src_idx = 0; src_idx < nsrcs; src_idx++) {
-		memcpy(&src_ip.u, srcs, src_size);
+		memcpy(&src_ip.src, srcs, src_size);
 		ent = br_multicast_find_group_src(pg, &src_ip);
 		if (ent) {
 			ent->flags &= ~BR_SGRP_F_DELETE;
 		} else {
 			ent = br_multicast_new_group_src(pg, &src_ip);
 			if (ent) {
-				mod_timer(&ent->timer,
-					  now + br_multicast_gmi(br));
+				__grp_src_mod_timer(ent,
+						    now + br_multicast_gmi(br));
 				changed = true;
 			}
 		}
@@ -1491,12 +1901,13 @@ static bool __grp_src_isexc_excl(struct net_bridge_port_group *pg,
 static bool br_multicast_isexc(struct net_bridge_port_group *pg,
 			       void *srcs, u32 nsrcs, size_t src_size)
 {
-	struct net_bridge *br = pg->port->br;
+	struct net_bridge *br = pg->key.port->br;
 	bool changed = false;
 
 	switch (pg->filter_mode) {
 	case MCAST_INCLUDE:
 		__grp_src_isexc_incl(pg, srcs, nsrcs, src_size);
+		br_multicast_star_g_handle_mode(pg, MCAST_EXCLUDE);
 		changed = true;
 		break;
 	case MCAST_EXCLUDE:
@@ -1517,7 +1928,7 @@ static bool br_multicast_isexc(struct net_bridge_port_group *pg,
 static bool __grp_src_toin_incl(struct net_bridge_port_group *pg,
 				void *srcs, u32 nsrcs, size_t src_size)
 {
-	struct net_bridge *br = pg->port->br;
+	struct net_bridge *br = pg->key.port->br;
 	u32 src_idx, to_send = pg->src_ents;
 	struct net_bridge_group_src *ent;
 	unsigned long now = jiffies;
@@ -1528,9 +1939,9 @@ static bool __grp_src_toin_incl(struct net_bridge_port_group *pg,
 		ent->flags |= BR_SGRP_F_SEND;
 
 	memset(&src_ip, 0, sizeof(src_ip));
-	src_ip.proto = pg->addr.proto;
+	src_ip.proto = pg->key.addr.proto;
 	for (src_idx = 0; src_idx < nsrcs; src_idx++) {
-		memcpy(&src_ip.u, srcs, src_size);
+		memcpy(&src_ip.src, srcs, src_size);
 		ent = br_multicast_find_group_src(pg, &src_ip);
 		if (ent) {
 			ent->flags &= ~BR_SGRP_F_SEND;
@@ -1541,7 +1952,7 @@ static bool __grp_src_toin_incl(struct net_bridge_port_group *pg,
 				changed = true;
 		}
 		if (ent)
-			mod_timer(&ent->timer, now + br_multicast_gmi(br));
+			__grp_src_mod_timer(ent, now + br_multicast_gmi(br));
 		srcs += src_size;
 	}
 
@@ -1559,7 +1970,7 @@ static bool __grp_src_toin_incl(struct net_bridge_port_group *pg,
 static bool __grp_src_toin_excl(struct net_bridge_port_group *pg,
 				void *srcs, u32 nsrcs, size_t src_size)
 {
-	struct net_bridge *br = pg->port->br;
+	struct net_bridge *br = pg->key.port->br;
 	u32 src_idx, to_send = pg->src_ents;
 	struct net_bridge_group_src *ent;
 	unsigned long now = jiffies;
@@ -1571,9 +1982,9 @@ static bool __grp_src_toin_excl(struct net_bridge_port_group *pg,
 			ent->flags |= BR_SGRP_F_SEND;
 
 	memset(&src_ip, 0, sizeof(src_ip));
-	src_ip.proto = pg->addr.proto;
+	src_ip.proto = pg->key.addr.proto;
 	for (src_idx = 0; src_idx < nsrcs; src_idx++) {
-		memcpy(&src_ip.u, srcs, src_size);
+		memcpy(&src_ip.src, srcs, src_size);
 		ent = br_multicast_find_group_src(pg, &src_ip);
 		if (ent) {
 			if (timer_pending(&ent->timer)) {
@@ -1586,7 +1997,7 @@ static bool __grp_src_toin_excl(struct net_bridge_port_group *pg,
 				changed = true;
 		}
 		if (ent)
-			mod_timer(&ent->timer, now + br_multicast_gmi(br));
+			__grp_src_mod_timer(ent, now + br_multicast_gmi(br));
 		srcs += src_size;
 	}
 
@@ -1632,17 +2043,19 @@ static void __grp_src_toex_incl(struct net_bridge_port_group *pg,
 		ent->flags = (ent->flags & ~BR_SGRP_F_SEND) | BR_SGRP_F_DELETE;
 
 	memset(&src_ip, 0, sizeof(src_ip));
-	src_ip.proto = pg->addr.proto;
+	src_ip.proto = pg->key.addr.proto;
 	for (src_idx = 0; src_idx < nsrcs; src_idx++) {
-		memcpy(&src_ip.u, srcs, src_size);
+		memcpy(&src_ip.src, srcs, src_size);
 		ent = br_multicast_find_group_src(pg, &src_ip);
 		if (ent) {
 			ent->flags = (ent->flags & ~BR_SGRP_F_DELETE) |
 				     BR_SGRP_F_SEND;
 			to_send++;
 		} else {
-			br_multicast_new_group_src(pg, &src_ip);
+			ent = br_multicast_new_group_src(pg, &src_ip);
 		}
+		if (ent)
+			br_multicast_fwd_src_handle(ent);
 		srcs += src_size;
 	}
 
@@ -1670,16 +2083,16 @@ static bool __grp_src_toex_excl(struct net_bridge_port_group *pg,
 		ent->flags = (ent->flags & ~BR_SGRP_F_SEND) | BR_SGRP_F_DELETE;
 
 	memset(&src_ip, 0, sizeof(src_ip));
-	src_ip.proto = pg->addr.proto;
+	src_ip.proto = pg->key.addr.proto;
 	for (src_idx = 0; src_idx < nsrcs; src_idx++) {
-		memcpy(&src_ip.u, srcs, src_size);
+		memcpy(&src_ip.src, srcs, src_size);
 		ent = br_multicast_find_group_src(pg, &src_ip);
 		if (ent) {
 			ent->flags &= ~BR_SGRP_F_DELETE;
 		} else {
 			ent = br_multicast_new_group_src(pg, &src_ip);
 			if (ent) {
-				mod_timer(&ent->timer, pg->timer.expires);
+				__grp_src_mod_timer(ent, pg->timer.expires);
 				changed = true;
 			}
 		}
@@ -1701,12 +2114,13 @@ static bool __grp_src_toex_excl(struct net_bridge_port_group *pg,
 static bool br_multicast_toex(struct net_bridge_port_group *pg,
 			      void *srcs, u32 nsrcs, size_t src_size)
 {
-	struct net_bridge *br = pg->port->br;
+	struct net_bridge *br = pg->key.port->br;
 	bool changed = false;
 
 	switch (pg->filter_mode) {
 	case MCAST_INCLUDE:
 		__grp_src_toex_incl(pg, srcs, nsrcs, src_size);
+		br_multicast_star_g_handle_mode(pg, MCAST_EXCLUDE);
 		changed = true;
 		break;
 	case MCAST_EXCLUDE:
@@ -1734,9 +2148,9 @@ static void __grp_src_block_incl(struct net_bridge_port_group *pg,
 		ent->flags &= ~BR_SGRP_F_SEND;
 
 	memset(&src_ip, 0, sizeof(src_ip));
-	src_ip.proto = pg->addr.proto;
+	src_ip.proto = pg->key.addr.proto;
 	for (src_idx = 0; src_idx < nsrcs; src_idx++) {
-		memcpy(&src_ip.u, srcs, src_size);
+		memcpy(&src_ip.src, srcs, src_size);
 		ent = br_multicast_find_group_src(pg, &src_ip);
 		if (ent) {
 			ent->flags |= BR_SGRP_F_SEND;
@@ -1749,7 +2163,7 @@ static void __grp_src_block_incl(struct net_bridge_port_group *pg,
 		__grp_src_query_marked_and_rexmit(pg);
 
 	if (pg->filter_mode == MCAST_INCLUDE && hlist_empty(&pg->src_list))
-		br_multicast_find_del_pg(pg->port->br, pg);
+		br_multicast_find_del_pg(pg->key.port->br, pg);
 }
 
 /* State          Msg type      New state                Actions
@@ -1768,14 +2182,14 @@ static bool __grp_src_block_excl(struct net_bridge_port_group *pg,
 		ent->flags &= ~BR_SGRP_F_SEND;
 
 	memset(&src_ip, 0, sizeof(src_ip));
-	src_ip.proto = pg->addr.proto;
+	src_ip.proto = pg->key.addr.proto;
 	for (src_idx = 0; src_idx < nsrcs; src_idx++) {
-		memcpy(&src_ip.u, srcs, src_size);
+		memcpy(&src_ip.src, srcs, src_size);
 		ent = br_multicast_find_group_src(pg, &src_ip);
 		if (!ent) {
 			ent = br_multicast_new_group_src(pg, &src_ip);
 			if (ent) {
-				mod_timer(&ent->timer, pg->timer.expires);
+				__grp_src_mod_timer(ent, pg->timer.expires);
 				changed = true;
 			}
 		}
@@ -2071,16 +2485,16 @@ static bool br_ip4_multicast_select_querier(struct net_bridge *br,
 	    !timer_pending(&br->ip4_other_query.timer))
 		goto update;
 
-	if (!br->ip4_querier.addr.u.ip4)
+	if (!br->ip4_querier.addr.src.ip4)
 		goto update;
 
-	if (ntohl(saddr) <= ntohl(br->ip4_querier.addr.u.ip4))
+	if (ntohl(saddr) <= ntohl(br->ip4_querier.addr.src.ip4))
 		goto update;
 
 	return false;
 
 update:
-	br->ip4_querier.addr.u.ip4 = saddr;
+	br->ip4_querier.addr.src.ip4 = saddr;
 
 	/* update protected by general multicast_lock by caller */
 	rcu_assign_pointer(br->ip4_querier.port, port);
@@ -2097,13 +2511,13 @@ static bool br_ip6_multicast_select_querier(struct net_bridge *br,
 	    !timer_pending(&br->ip6_other_query.timer))
 		goto update;
 
-	if (ipv6_addr_cmp(saddr, &br->ip6_querier.addr.u.ip6) <= 0)
+	if (ipv6_addr_cmp(saddr, &br->ip6_querier.addr.src.ip6) <= 0)
 		goto update;
 
 	return false;
 
 update:
-	br->ip6_querier.addr.u.ip6 = *saddr;
+	br->ip6_querier.addr.src.ip6 = *saddr;
 
 	/* update protected by general multicast_lock by caller */
 	rcu_assign_pointer(br->ip6_querier.port, port);
@@ -2118,10 +2532,10 @@ static bool br_multicast_select_querier(struct net_bridge *br,
 {
 	switch (saddr->proto) {
 	case htons(ETH_P_IP):
-		return br_ip4_multicast_select_querier(br, port, saddr->u.ip4);
+		return br_ip4_multicast_select_querier(br, port, saddr->src.ip4);
 #if IS_ENABLED(CONFIG_IPV6)
 	case htons(ETH_P_IPV6):
-		return br_ip6_multicast_select_querier(br, port, &saddr->u.ip6);
+		return br_ip6_multicast_select_querier(br, port, &saddr->src.ip6);
 #endif
 	}
 
@@ -2263,7 +2677,7 @@ static void br_ip4_multicast_query(struct net_bridge *br,
 
 	if (!group) {
 		saddr.proto = htons(ETH_P_IP);
-		saddr.u.ip4 = iph->saddr;
+		saddr.src.ip4 = iph->saddr;
 
 		br_multicast_query_received(br, port, &br->ip4_other_query,
 					    &saddr, max_delay);
@@ -2351,7 +2765,7 @@ static int br_ip6_multicast_query(struct net_bridge *br,
 
 	if (is_general_query) {
 		saddr.proto = htons(ETH_P_IPV6);
-		saddr.u.ip6 = ipv6_hdr(skb)->saddr;
+		saddr.src.ip6 = ipv6_hdr(skb)->saddr;
 
 		br_multicast_query_received(br, port, &br->ip6_other_query,
 					    &saddr, max_delay);
@@ -2475,7 +2889,7 @@ br_multicast_leave_group(struct net_bridge *br,
 	for (p = mlock_dereference(mp->ports, br);
 	     p != NULL;
 	     p = mlock_dereference(p->next, br)) {
-		if (p->port != port)
+		if (p->key.port != port)
 			continue;
 
 		if (!hlist_unhashed(&p->mglist) &&
@@ -2506,7 +2920,7 @@ static void br_ip4_multicast_leave_group(struct net_bridge *br,
 	own_query = port ? &port->ip4_own_query : &br->ip4_own_query;
 
 	memset(&br_group, 0, sizeof(br_group));
-	br_group.u.ip4 = group;
+	br_group.dst.ip4 = group;
 	br_group.proto = htons(ETH_P_IP);
 	br_group.vid = vid;
 
@@ -2530,7 +2944,7 @@ static void br_ip6_multicast_leave_group(struct net_bridge *br,
 	own_query = port ? &port->ip6_own_query : &br->ip6_own_query;
 
 	memset(&br_group, 0, sizeof(br_group));
-	br_group.u.ip6 = *group;
+	br_group.dst.ip6 = *group;
 	br_group.proto = htons(ETH_P_IPV6);
 	br_group.vid = vid;
 
@@ -3235,7 +3649,7 @@ int br_multicast_list_adjacent(struct net_device *dev,
 			if (!entry)
 				goto unlock;
 
-			entry->addr = group->addr;
+			entry->addr = group->key.addr;
 			list_add(&entry->list, br_ip_list);
 			count++;
 		}
@@ -3492,10 +3906,23 @@ void br_multicast_get_stats(const struct net_bridge *br,
 
 int br_mdb_hash_init(struct net_bridge *br)
 {
-	return rhashtable_init(&br->mdb_hash_tbl, &br_mdb_rht_params);
+	int err;
+
+	err = rhashtable_init(&br->sg_port_tbl, &br_sg_port_rht_params);
+	if (err)
+		return err;
+
+	err = rhashtable_init(&br->mdb_hash_tbl, &br_mdb_rht_params);
+	if (err) {
+		rhashtable_destroy(&br->sg_port_tbl);
+		return err;
+	}
+
+	return 0;
 }
 
 void br_mdb_hash_fini(struct net_bridge *br)
 {
+	rhashtable_destroy(&br->sg_port_tbl);
 	rhashtable_destroy(&br->mdb_hash_tbl);
 }
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index a23d2bae56e1..345118e35c42 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -213,11 +213,14 @@ struct net_bridge_fdb_entry {
 #define MDB_PG_FLAGS_PERMANENT	BIT(0)
 #define MDB_PG_FLAGS_OFFLOAD	BIT(1)
 #define MDB_PG_FLAGS_FAST_LEAVE	BIT(2)
+#define MDB_PG_FLAGS_STAR_EXCL	BIT(3)
+#define MDB_PG_FLAGS_BLOCKED	BIT(4)
 
 #define PG_SRC_ENT_LIMIT	32
 
 #define BR_SGRP_F_DELETE	BIT(0)
 #define BR_SGRP_F_SEND		BIT(1)
+#define BR_SGRP_F_INSTALLED	BIT(2)
 
 struct net_bridge_mcast_gc {
 	struct hlist_node		gc_node;
@@ -238,14 +241,19 @@ struct net_bridge_group_src {
 	struct rcu_head			rcu;
 };
 
-struct net_bridge_port_group {
+struct net_bridge_port_group_sg_key {
 	struct net_bridge_port		*port;
-	struct net_bridge_port_group __rcu *next;
 	struct br_ip			addr;
+};
+
+struct net_bridge_port_group {
+	struct net_bridge_port_group __rcu *next;
+	struct net_bridge_port_group_sg_key key;
 	unsigned char			eth_addr[ETH_ALEN] __aligned(2);
 	unsigned char			flags;
 	unsigned char			filter_mode;
 	unsigned char			grp_query_rexmit_cnt;
+	unsigned char			rt_protocol;
 
 	struct hlist_head		src_list;
 	unsigned int			src_ents;
@@ -253,6 +261,7 @@ struct net_bridge_port_group {
 	struct timer_list		rexmit_timer;
 	struct hlist_node		mglist;
 
+	struct rhash_head		rhnode;
 	struct net_bridge_mcast_gc	mcast_gc;
 	struct rcu_head			rcu;
 };
@@ -440,6 +449,7 @@ struct net_bridge {
 	unsigned long			multicast_startup_query_interval;
 
 	struct rhashtable		mdb_hash_tbl;
+	struct rhashtable		sg_port_tbl;
 
 	struct hlist_head		mcast_gc_list;
 	struct hlist_head		mdb_list;
@@ -804,7 +814,7 @@ struct net_bridge_port_group *
 br_multicast_new_port_group(struct net_bridge_port *port, struct br_ip *group,
 			    struct net_bridge_port_group __rcu *next,
 			    unsigned char flags, const unsigned char *src,
-			    u8 filter_mode);
+			    u8 filter_mode, u8 rt_protocol);
 int br_mdb_hash_init(struct net_bridge *br);
 void br_mdb_hash_fini(struct net_bridge *br);
 void br_mdb_notify(struct net_device *dev, struct net_bridge_mdb_entry *mp,
@@ -825,6 +835,10 @@ void br_mdb_init(void);
 void br_mdb_uninit(void);
 void br_multicast_host_join(struct net_bridge_mdb_entry *mp, bool notify);
 void br_multicast_host_leave(struct net_bridge_mdb_entry *mp, bool notify);
+void br_multicast_star_g_handle_mode(struct net_bridge_port_group *pg,
+				     u8 filter_mode);
+void br_multicast_sg_add_exclude_ports(struct net_bridge_mdb_entry *star_mp,
+				       struct net_bridge_port_group *sg);
 
 #define mlock_dereference(X, br) \
 	rcu_dereference_protected(X, lockdep_is_held(&br->multicast_lock))
@@ -873,6 +887,35 @@ static inline bool br_multicast_querier_exists(struct net_bridge *br,
 	}
 }
 
+static inline bool br_multicast_is_star_g(const struct br_ip *ip)
+{
+	switch (ip->proto) {
+	case htons(ETH_P_IP):
+		return ipv4_is_zeronet(ip->src.ip4);
+#if IS_ENABLED(CONFIG_IPV6)
+	case htons(ETH_P_IPV6):
+		return ipv6_addr_any(&ip->src.ip6);
+#endif
+	default:
+		return false;
+	}
+}
+
+static inline bool br_multicast_should_handle_mode(const struct net_bridge *br,
+						   __be16 proto)
+{
+	switch (proto) {
+	case htons(ETH_P_IP):
+		return !!(br->multicast_igmp_version == 3);
+#if IS_ENABLED(CONFIG_IPV6)
+	case htons(ETH_P_IPV6):
+		return !!(br->multicast_mld_version == 2);
+#endif
+	default:
+		return false;
+	}
+}
+
 static inline int br_multicast_igmp_type(const struct sk_buff *skb)
 {
 	return BR_INPUT_SKB_CB(skb)->igmp;
diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c
index 199deb2adf60..002bbc93209d 100644
--- a/net/bridge/br_vlan.c
+++ b/net/bridge/br_vlan.c
@@ -1288,11 +1288,13 @@ void br_vlan_get_stats(const struct net_bridge_vlan *v,
 	}
 }
 
-static int __br_vlan_get_pvid(const struct net_device *dev,
-			      struct net_bridge_port *p, u16 *p_pvid)
+int br_vlan_get_pvid(const struct net_device *dev, u16 *p_pvid)
 {
 	struct net_bridge_vlan_group *vg;
+	struct net_bridge_port *p;
 
+	ASSERT_RTNL();
+	p = br_port_get_check_rtnl(dev);
 	if (p)
 		vg = nbp_vlan_group(p);
 	else if (netif_is_bridge_master(dev))
@@ -1303,18 +1305,23 @@ static int __br_vlan_get_pvid(const struct net_device *dev,
 	*p_pvid = br_get_pvid(vg);
 	return 0;
 }
-
-int br_vlan_get_pvid(const struct net_device *dev, u16 *p_pvid)
-{
-	ASSERT_RTNL();
-
-	return __br_vlan_get_pvid(dev, br_port_get_check_rtnl(dev), p_pvid);
-}
 EXPORT_SYMBOL_GPL(br_vlan_get_pvid);
 
 int br_vlan_get_pvid_rcu(const struct net_device *dev, u16 *p_pvid)
 {
-	return __br_vlan_get_pvid(dev, br_port_get_check_rcu(dev), p_pvid);
+	struct net_bridge_vlan_group *vg;
+	struct net_bridge_port *p;
+
+	p = br_port_get_check_rcu(dev);
+	if (p)
+		vg = nbp_vlan_group_rcu(p);
+	else if (netif_is_bridge_master(dev))
+		vg = br_vlan_group_rcu(netdev_priv(dev));
+	else
+		return -EINVAL;
+
+	*p_pvid = br_get_pvid(vg);
+	return 0;
 }
 EXPORT_SYMBOL_GPL(br_vlan_get_pvid_rcu);
 
diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c
index a0d1a3265b71..c907f0dc7f87 100644
--- a/net/core/bpf_sk_storage.c
+++ b/net/core/bpf_sk_storage.c
@@ -12,7 +12,6 @@
 #include <net/sock.h>
 #include <uapi/linux/sock_diag.h>
 #include <uapi/linux/btf.h>
-#include <linux/btf_ids.h>
 
 DEFINE_BPF_STORAGE_CACHE(sk_cache);
 
@@ -270,7 +269,7 @@ BPF_CALL_4(bpf_sk_storage_get, struct bpf_map *, map, struct sock *, sk,
 {
 	struct bpf_local_storage_data *sdata;
 
-	if (flags > BPF_SK_STORAGE_GET_F_CREATE)
+	if (!sk || !sk_fullsock(sk) || flags > BPF_SK_STORAGE_GET_F_CREATE)
 		return (unsigned long)NULL;
 
 	sdata = sk_storage_lookup(sk, map, true);
@@ -300,6 +299,9 @@ BPF_CALL_4(bpf_sk_storage_get, struct bpf_map *, map, struct sock *, sk,
 
 BPF_CALL_2(bpf_sk_storage_delete, struct bpf_map *, map, struct sock *, sk)
 {
+	if (!sk || !sk_fullsock(sk))
+		return -EINVAL;
+
 	if (refcount_inc_not_zero(&sk->sk_refcnt)) {
 		int err;
 
@@ -356,7 +358,7 @@ const struct bpf_func_proto bpf_sk_storage_get_proto = {
 	.gpl_only	= false,
 	.ret_type	= RET_PTR_TO_MAP_VALUE_OR_NULL,
 	.arg1_type	= ARG_CONST_MAP_PTR,
-	.arg2_type	= ARG_PTR_TO_SOCKET,
+	.arg2_type	= ARG_PTR_TO_BTF_ID_SOCK_COMMON,
 	.arg3_type	= ARG_PTR_TO_MAP_VALUE_OR_NULL,
 	.arg4_type	= ARG_ANYTHING,
 };
@@ -376,31 +378,7 @@ const struct bpf_func_proto bpf_sk_storage_delete_proto = {
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_CONST_MAP_PTR,
-	.arg2_type	= ARG_PTR_TO_SOCKET,
-};
-
-BTF_ID_LIST(sk_storage_btf_ids)
-BTF_ID_UNUSED
-BTF_ID(struct, sock)
-
-const struct bpf_func_proto sk_storage_get_btf_proto = {
-	.func		= bpf_sk_storage_get,
-	.gpl_only	= false,
-	.ret_type	= RET_PTR_TO_MAP_VALUE_OR_NULL,
-	.arg1_type	= ARG_CONST_MAP_PTR,
-	.arg2_type	= ARG_PTR_TO_BTF_ID,
-	.arg3_type	= ARG_PTR_TO_MAP_VALUE_OR_NULL,
-	.arg4_type	= ARG_ANYTHING,
-	.btf_id		= sk_storage_btf_ids,
-};
-
-const struct bpf_func_proto sk_storage_delete_btf_proto = {
-	.func		= bpf_sk_storage_delete,
-	.gpl_only	= false,
-	.ret_type	= RET_INTEGER,
-	.arg1_type	= ARG_CONST_MAP_PTR,
-	.arg2_type	= ARG_PTR_TO_BTF_ID,
-	.btf_id		= sk_storage_btf_ids,
+	.arg2_type	= ARG_PTR_TO_BTF_ID_SOCK_COMMON,
 };
 
 struct bpf_sk_storage_diag {
@@ -679,6 +657,7 @@ struct bpf_iter_seq_sk_storage_map_info {
 static struct bpf_local_storage_elem *
 bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info,
 				 struct bpf_local_storage_elem *prev_selem)
+	__acquires(RCU) __releases(RCU)
 {
 	struct bpf_local_storage *sk_storage;
 	struct bpf_local_storage_elem *selem;
@@ -697,16 +676,16 @@ bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info,
 	selem = prev_selem;
 	count = 0;
 	while (selem) {
-		selem = hlist_entry_safe(selem->map_node.next,
+		selem = hlist_entry_safe(rcu_dereference(hlist_next_rcu(&selem->map_node)),
 					 struct bpf_local_storage_elem, map_node);
 		if (!selem) {
 			/* not found, unlock and go to the next bucket */
 			b = &smap->buckets[bucket_id++];
-			raw_spin_unlock_bh(&b->lock);
+			rcu_read_unlock();
 			skip_elems = 0;
 			break;
 		}
-		sk_storage = rcu_dereference_raw(selem->local_storage);
+		sk_storage = rcu_dereference(selem->local_storage);
 		if (sk_storage) {
 			info->skip_elems = skip_elems + count;
 			return selem;
@@ -716,10 +695,10 @@ bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info,
 
 	for (i = bucket_id; i < (1U << smap->bucket_log); i++) {
 		b = &smap->buckets[i];
-		raw_spin_lock_bh(&b->lock);
+		rcu_read_lock();
 		count = 0;
-		hlist_for_each_entry(selem, &b->list, map_node) {
-			sk_storage = rcu_dereference_raw(selem->local_storage);
+		hlist_for_each_entry_rcu(selem, &b->list, map_node) {
+			sk_storage = rcu_dereference(selem->local_storage);
 			if (sk_storage && count >= skip_elems) {
 				info->bucket_id = i;
 				info->skip_elems = count;
@@ -727,7 +706,7 @@ bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info,
 			}
 			count++;
 		}
-		raw_spin_unlock_bh(&b->lock);
+		rcu_read_unlock();
 		skip_elems = 0;
 	}
 
@@ -786,7 +765,7 @@ static int __bpf_sk_storage_map_seq_show(struct seq_file *seq,
 		ctx.meta = &meta;
 		ctx.map = info->map;
 		if (selem) {
-			sk_storage = rcu_dereference_raw(selem->local_storage);
+			sk_storage = rcu_dereference(selem->local_storage);
 			ctx.sk = sk_storage->owner;
 			ctx.value = SDATA(selem)->data;
 		}
@@ -802,18 +781,12 @@ static int bpf_sk_storage_map_seq_show(struct seq_file *seq, void *v)
 }
 
 static void bpf_sk_storage_map_seq_stop(struct seq_file *seq, void *v)
+	__releases(RCU)
 {
-	struct bpf_iter_seq_sk_storage_map_info *info = seq->private;
-	struct bpf_local_storage_map *smap;
-	struct bpf_local_storage_map_bucket *b;
-
-	if (!v) {
+	if (!v)
 		(void)__bpf_sk_storage_map_seq_show(seq, v);
-	} else {
-		smap = (struct bpf_local_storage_map *)info->map;
-		b = &smap->buckets[info->bucket_id];
-		raw_spin_unlock_bh(&b->lock);
-	}
+	else
+		rcu_read_unlock();
 }
 
 static int bpf_iter_init_sk_storage_map(void *priv_data,
diff --git a/net/core/dev.c b/net/core/dev.c
index bd9c8510d86f..9d55bf5d1a65 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4841,6 +4841,21 @@ int netif_rx_ni(struct sk_buff *skb)
 }
 EXPORT_SYMBOL(netif_rx_ni);
 
+int netif_rx_any_context(struct sk_buff *skb)
+{
+	/*
+	 * If invoked from contexts which do not invoke bottom half
+	 * processing either at return from interrupt or when softrqs are
+	 * reenabled, use netif_rx_ni() which invokes bottomhalf processing
+	 * directly.
+	 */
+	if (in_interrupt())
+		return netif_rx(skb);
+	else
+		return netif_rx_ni(skb);
+}
+EXPORT_SYMBOL(netif_rx_any_context);
+
 static __latent_entropy void net_tx_action(struct softirq_action *h)
 {
 	struct softnet_data *sd = this_cpu_ptr(&softnet_data);
@@ -5442,15 +5457,20 @@ static int generic_xdp_install(struct net_device *dev, struct netdev_bpf *xdp)
 	if (new) {
 		u32 i;
 
+		mutex_lock(&new->aux->used_maps_mutex);
+
 		/* generic XDP does not work with DEVMAPs that can
 		 * have a bpf_prog installed on an entry
 		 */
 		for (i = 0; i < new->aux->used_map_cnt; i++) {
-			if (dev_map_can_have_prog(new->aux->used_maps[i]))
-				return -EINVAL;
-			if (cpu_map_prog_allowed(new->aux->used_maps[i]))
+			if (dev_map_can_have_prog(new->aux->used_maps[i]) ||
+			    cpu_map_prog_allowed(new->aux->used_maps[i])) {
+				mutex_unlock(&new->aux->used_maps_mutex);
 				return -EINVAL;
+			}
 		}
+
+		mutex_unlock(&new->aux->used_maps_mutex);
 	}
 
 	switch (xdp->command) {
@@ -8689,7 +8709,7 @@ int dev_get_port_parent_id(struct net_device *dev,
 		if (!first.id_len)
 			first = *ppid;
 		else if (memcmp(&first, ppid, sizeof(*ppid)))
-			return -ENODATA;
+			return -EOPNOTSUPP;
 	}
 
 	return err;
@@ -10016,6 +10036,8 @@ int netdev_refcnt_read(const struct net_device *dev)
 }
 EXPORT_SYMBOL(netdev_refcnt_read);
 
+#define WAIT_REFS_MIN_MSECS 1
+#define WAIT_REFS_MAX_MSECS 250
 /**
  * netdev_wait_allrefs - wait until all references are gone.
  * @dev: target net_device
@@ -10028,8 +10050,6 @@ EXPORT_SYMBOL(netdev_refcnt_read);
  * We can get stuck here if buggy protocols don't correctly
  * call dev_put.
  */
-#define WAIT_REFS_MIN_MSECS 1
-#define WAIT_REFS_MAX_MSECS 250
 static void netdev_wait_allrefs(struct net_device *dev)
 {
 	unsigned long rebroadcast_time, warning_time;
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 045468390480..0f3c8b2ec056 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -27,7 +27,6 @@
 #include <net/net_namespace.h>
 #include <net/sock.h>
 #include <net/devlink.h>
-#include <net/drop_monitor.h>
 #define CREATE_TRACE_POINTS
 #include <trace/events/devlink.h>
 
@@ -84,6 +83,7 @@ EXPORT_SYMBOL(devlink_dpipe_header_ipv6);
 
 EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_hwmsg);
 EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_hwerr);
+EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_trap_report);
 
 static const struct nla_policy devlink_function_nl_policy[DEVLINK_PORT_FUNCTION_ATTR_MAX + 1] = {
 	[DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR] = { .type = NLA_BINARY },
@@ -811,8 +811,6 @@ static int devlink_port_type_set(struct devlink *devlink,
 	int err;
 
 	if (devlink->ops->port_type_set) {
-		if (port_type == DEVLINK_PORT_TYPE_NOTSET)
-			return -EINVAL;
 		if (port_type == devlink_port->type)
 			return 0;
 		err = devlink->ops->port_type_set(devlink_port, port_type);
@@ -3149,22 +3147,45 @@ EXPORT_SYMBOL_GPL(devlink_flash_update_timeout_notify);
 static int devlink_nl_cmd_flash_update(struct sk_buff *skb,
 				       struct genl_info *info)
 {
+	struct nlattr *nla_component, *nla_overwrite_mask;
+	struct devlink_flash_update_params params = {};
 	struct devlink *devlink = info->user_ptr[0];
-	const char *file_name, *component;
-	struct nlattr *nla_component;
+	u32 supported_params;
 
 	if (!devlink->ops->flash_update)
 		return -EOPNOTSUPP;
 
 	if (!info->attrs[DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME])
 		return -EINVAL;
-	file_name = nla_data(info->attrs[DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME]);
+
+	supported_params = devlink->ops->supported_flash_update_params;
+
+	params.file_name = nla_data(info->attrs[DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME]);
 
 	nla_component = info->attrs[DEVLINK_ATTR_FLASH_UPDATE_COMPONENT];
-	component = nla_component ? nla_data(nla_component) : NULL;
+	if (nla_component) {
+		if (!(supported_params & DEVLINK_SUPPORT_FLASH_UPDATE_COMPONENT)) {
+			NL_SET_ERR_MSG_ATTR(info->extack, nla_component,
+					    "component update is not supported by this device");
+			return -EOPNOTSUPP;
+		}
+		params.component = nla_data(nla_component);
+	}
+
+	nla_overwrite_mask = info->attrs[DEVLINK_ATTR_FLASH_UPDATE_OVERWRITE_MASK];
+	if (nla_overwrite_mask) {
+		struct nla_bitfield32 sections;
 
-	return devlink->ops->flash_update(devlink, file_name, component,
-					  info->extack);
+		if (!(supported_params & DEVLINK_SUPPORT_FLASH_UPDATE_OVERWRITE_MASK)) {
+			NL_SET_ERR_MSG_ATTR(info->extack, nla_overwrite_mask,
+					    "overwrite settings are not supported by this device");
+			return -EOPNOTSUPP;
+		}
+		sections = nla_get_bitfield32(nla_overwrite_mask);
+		params.overwrite_mask = sections.value & sections.selector;
+	}
+
+	return devlink->ops->flash_update(devlink, &params, info->extack);
 }
 
 static const struct devlink_param devlink_param_generic[] = {
@@ -6699,6 +6720,24 @@ __devlink_trap_group_action_set(struct devlink *devlink,
 	struct devlink_trap_item *trap_item;
 	int err;
 
+	if (devlink->ops->trap_group_action_set) {
+		err = devlink->ops->trap_group_action_set(devlink, group_item->group,
+							  trap_action, extack);
+		if (err)
+			return err;
+
+		list_for_each_entry(trap_item, &devlink->trap_list, list) {
+			if (strcmp(trap_item->group_item->group->name, group_name))
+				continue;
+			if (trap_item->action != trap_action &&
+			    trap_item->trap->type != DEVLINK_TRAP_TYPE_DROP)
+				continue;
+			trap_item->action = trap_action;
+		}
+
+		return 0;
+	}
+
 	list_for_each_entry(trap_item, &devlink->trap_list, list) {
 		if (strcmp(trap_item->group_item->group->name, group_name))
 			continue;
@@ -7055,7 +7094,8 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
 	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING },
 	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING },
 	[DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32 },
-	[DEVLINK_ATTR_PORT_TYPE] = { .type = NLA_U16 },
+	[DEVLINK_ATTR_PORT_TYPE] = NLA_POLICY_RANGE(NLA_U16, DEVLINK_PORT_TYPE_AUTO,
+						    DEVLINK_PORT_TYPE_IB),
 	[DEVLINK_ATTR_PORT_SPLIT_COUNT] = { .type = NLA_U32 },
 	[DEVLINK_ATTR_SB_INDEX] = { .type = NLA_U32 },
 	[DEVLINK_ATTR_SB_POOL_INDEX] = { .type = NLA_U16 },
@@ -7064,7 +7104,8 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
 	[DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE] = { .type = NLA_U8 },
 	[DEVLINK_ATTR_SB_THRESHOLD] = { .type = NLA_U32 },
 	[DEVLINK_ATTR_SB_TC_INDEX] = { .type = NLA_U16 },
-	[DEVLINK_ATTR_ESWITCH_MODE] = { .type = NLA_U16 },
+	[DEVLINK_ATTR_ESWITCH_MODE] = NLA_POLICY_RANGE(NLA_U16, DEVLINK_ESWITCH_MODE_LEGACY,
+						       DEVLINK_ESWITCH_MODE_SWITCHDEV),
 	[DEVLINK_ATTR_ESWITCH_INLINE_MODE] = { .type = NLA_U8 },
 	[DEVLINK_ATTR_ESWITCH_ENCAP_MODE] = { .type = NLA_U8 },
 	[DEVLINK_ATTR_DPIPE_TABLE_NAME] = { .type = NLA_NUL_STRING },
@@ -7083,6 +7124,8 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
 	[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER] = { .type = NLA_U8 },
 	[DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME] = { .type = NLA_NUL_STRING },
 	[DEVLINK_ATTR_FLASH_UPDATE_COMPONENT] = { .type = NLA_NUL_STRING },
+	[DEVLINK_ATTR_FLASH_UPDATE_OVERWRITE_MASK] =
+		NLA_POLICY_BITFIELD32(DEVLINK_SUPPORTED_FLASH_OVERWRITE_SECTIONS),
 	[DEVLINK_ATTR_TRAP_NAME] = { .type = NLA_NUL_STRING },
 	[DEVLINK_ATTR_TRAP_ACTION] = { .type = NLA_U8 },
 	[DEVLINK_ATTR_TRAP_GROUP_NAME] = { .type = NLA_NUL_STRING },
@@ -7096,7 +7139,7 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
 	[DEVLINK_ATTR_PORT_FUNCTION] = { .type = NLA_NESTED },
 };
 
-static const struct genl_ops devlink_nl_ops[] = {
+static const struct genl_small_ops devlink_nl_ops[] = {
 	{
 		.cmd = DEVLINK_CMD_GET,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
@@ -7421,8 +7464,8 @@ static struct genl_family devlink_nl_family __ro_after_init = {
 	.pre_doit	= devlink_nl_pre_doit,
 	.post_doit	= devlink_nl_post_doit,
 	.module		= THIS_MODULE,
-	.ops		= devlink_nl_ops,
-	.n_ops		= ARRAY_SIZE(devlink_nl_ops),
+	.small_ops	= devlink_nl_ops,
+	.n_small_ops	= ARRAY_SIZE(devlink_nl_ops),
 	.mcgrps		= devlink_nl_mcgrps,
 	.n_mcgrps	= ARRAY_SIZE(devlink_nl_mcgrps),
 };
@@ -8900,6 +8943,22 @@ static const struct devlink_trap devlink_trap_generic[] = {
 	DEVLINK_TRAP(FLOW_ACTION_SAMPLE, CONTROL),
 	DEVLINK_TRAP(FLOW_ACTION_TRAP, CONTROL),
 	DEVLINK_TRAP(EARLY_DROP, DROP),
+	DEVLINK_TRAP(VXLAN_PARSING, DROP),
+	DEVLINK_TRAP(LLC_SNAP_PARSING, DROP),
+	DEVLINK_TRAP(VLAN_PARSING, DROP),
+	DEVLINK_TRAP(PPPOE_PPP_PARSING, DROP),
+	DEVLINK_TRAP(MPLS_PARSING, DROP),
+	DEVLINK_TRAP(ARP_PARSING, DROP),
+	DEVLINK_TRAP(IP_1_PARSING, DROP),
+	DEVLINK_TRAP(IP_N_PARSING, DROP),
+	DEVLINK_TRAP(GRE_PARSING, DROP),
+	DEVLINK_TRAP(UDP_PARSING, DROP),
+	DEVLINK_TRAP(TCP_PARSING, DROP),
+	DEVLINK_TRAP(IPSEC_PARSING, DROP),
+	DEVLINK_TRAP(SCTP_PARSING, DROP),
+	DEVLINK_TRAP(DCCP_PARSING, DROP),
+	DEVLINK_TRAP(GTP_PARSING, DROP),
+	DEVLINK_TRAP(ESP_PARSING, DROP),
 };
 
 #define DEVLINK_TRAP_GROUP(_id)						      \
@@ -8934,6 +8993,7 @@ static const struct devlink_trap_group devlink_trap_group_generic[] = {
 	DEVLINK_TRAP_GROUP(PTP_GENERAL),
 	DEVLINK_TRAP_GROUP(ACL_SAMPLE),
 	DEVLINK_TRAP_GROUP(ACL_TRAP),
+	DEVLINK_TRAP_GROUP(PARSER_ERROR_DROPS),
 };
 
 static int devlink_trap_generic_verify(const struct devlink_trap *trap)
@@ -9236,20 +9296,19 @@ devlink_trap_stats_update(struct devlink_stats __percpu *trap_stats,
 }
 
 static void
-devlink_trap_report_metadata_fill(struct net_dm_hw_metadata *hw_metadata,
-				  const struct devlink_trap_item *trap_item,
-				  struct devlink_port *in_devlink_port,
-				  const struct flow_action_cookie *fa_cookie)
+devlink_trap_report_metadata_set(struct devlink_trap_metadata *metadata,
+				 const struct devlink_trap_item *trap_item,
+				 struct devlink_port *in_devlink_port,
+				 const struct flow_action_cookie *fa_cookie)
 {
-	struct devlink_trap_group_item *group_item = trap_item->group_item;
-
-	hw_metadata->trap_group_name = group_item->group->name;
-	hw_metadata->trap_name = trap_item->trap->name;
-	hw_metadata->fa_cookie = fa_cookie;
+	metadata->trap_name = trap_item->trap->name;
+	metadata->trap_group_name = trap_item->group_item->group->name;
+	metadata->fa_cookie = fa_cookie;
+	metadata->trap_type = trap_item->trap->type;
 
 	spin_lock(&in_devlink_port->type_lock);
 	if (in_devlink_port->type == DEVLINK_PORT_TYPE_ETH)
-		hw_metadata->input_dev = in_devlink_port->type_dev;
+		metadata->input_dev = in_devlink_port->type_dev;
 	spin_unlock(&in_devlink_port->type_lock);
 }
 
@@ -9267,21 +9326,17 @@ void devlink_trap_report(struct devlink *devlink, struct sk_buff *skb,
 
 {
 	struct devlink_trap_item *trap_item = trap_ctx;
-	struct net_dm_hw_metadata hw_metadata = {};
 
 	devlink_trap_stats_update(trap_item->stats, skb->len);
 	devlink_trap_stats_update(trap_item->group_item->stats, skb->len);
 
-	/* Control packets were not dropped by the device or encountered an
-	 * exception during forwarding and therefore should not be reported to
-	 * the kernel's drop monitor.
-	 */
-	if (trap_item->trap->type == DEVLINK_TRAP_TYPE_CONTROL)
-		return;
+	if (trace_devlink_trap_report_enabled()) {
+		struct devlink_trap_metadata metadata = {};
 
-	devlink_trap_report_metadata_fill(&hw_metadata, trap_item,
-					  in_devlink_port, fa_cookie);
-	net_dm_hw_report(skb, &hw_metadata);
+		devlink_trap_report_metadata_set(&metadata, trap_item,
+						 in_devlink_port, fa_cookie);
+		trace_devlink_trap_report(devlink, skb, &metadata);
+	}
 }
 EXPORT_SYMBOL_GPL(devlink_trap_report);
 
@@ -9640,6 +9695,7 @@ out:
 
 int devlink_compat_flash_update(struct net_device *dev, const char *file_name)
 {
+	struct devlink_flash_update_params params = {};
 	struct devlink *devlink;
 	int ret;
 
@@ -9652,8 +9708,10 @@ int devlink_compat_flash_update(struct net_device *dev, const char *file_name)
 		goto out;
 	}
 
+	params.file_name = file_name;
+
 	mutex_lock(&devlink->lock);
-	ret = devlink->ops->flash_update(devlink, file_name, NULL, NULL);
+	ret = devlink->ops->flash_update(devlink, &params, NULL);
 	mutex_unlock(&devlink->lock);
 
 out:
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index 9704522b0872..571f191c06d9 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -26,13 +26,14 @@
 #include <linux/bitops.h>
 #include <linux/slab.h>
 #include <linux/module.h>
-#include <net/drop_monitor.h>
 #include <net/genetlink.h>
 #include <net/netevent.h>
 #include <net/flow_offload.h>
+#include <net/devlink.h>
 
 #include <trace/events/skb.h>
 #include <trace/events/napi.h>
+#include <trace/events/devlink.h>
 
 #include <asm/unaligned.h>
 
@@ -114,13 +115,14 @@ struct net_dm_alert_ops {
 				int work, int budget);
 	void (*work_item_func)(struct work_struct *work);
 	void (*hw_work_item_func)(struct work_struct *work);
-	void (*hw_probe)(struct sk_buff *skb,
-			 const struct net_dm_hw_metadata *hw_metadata);
+	void (*hw_trap_probe)(void *ignore, const struct devlink *devlink,
+			      struct sk_buff *skb,
+			      const struct devlink_trap_metadata *metadata);
 };
 
 struct net_dm_skb_cb {
 	union {
-		struct net_dm_hw_metadata *hw_metadata;
+		struct devlink_trap_metadata *hw_metadata;
 		void *pc;
 	};
 };
@@ -432,8 +434,9 @@ out:
 }
 
 static void
-net_dm_hw_summary_probe(struct sk_buff *skb,
-			const struct net_dm_hw_metadata *hw_metadata)
+net_dm_hw_trap_summary_probe(void *ignore, const struct devlink *devlink,
+			     struct sk_buff *skb,
+			     const struct devlink_trap_metadata *metadata)
 {
 	struct net_dm_hw_entries *hw_entries;
 	struct net_dm_hw_entry *hw_entry;
@@ -441,6 +444,9 @@ net_dm_hw_summary_probe(struct sk_buff *skb,
 	unsigned long flags;
 	int i;
 
+	if (metadata->trap_type == DEVLINK_TRAP_TYPE_CONTROL)
+		return;
+
 	hw_data = this_cpu_ptr(&dm_hw_cpu_data);
 	spin_lock_irqsave(&hw_data->lock, flags);
 	hw_entries = hw_data->hw_entries;
@@ -450,7 +456,7 @@ net_dm_hw_summary_probe(struct sk_buff *skb,
 
 	for (i = 0; i < hw_entries->num_entries; i++) {
 		hw_entry = &hw_entries->entries[i];
-		if (!strncmp(hw_entry->trap_name, hw_metadata->trap_name,
+		if (!strncmp(hw_entry->trap_name, metadata->trap_name,
 			     NET_DM_MAX_HW_TRAP_NAME_LEN - 1)) {
 			hw_entry->count++;
 			goto out;
@@ -460,7 +466,7 @@ net_dm_hw_summary_probe(struct sk_buff *skb,
 		goto out;
 
 	hw_entry = &hw_entries->entries[hw_entries->num_entries];
-	strlcpy(hw_entry->trap_name, hw_metadata->trap_name,
+	strlcpy(hw_entry->trap_name, metadata->trap_name,
 		NET_DM_MAX_HW_TRAP_NAME_LEN - 1);
 	hw_entry->count = 1;
 	hw_entries->num_entries++;
@@ -479,7 +485,7 @@ static const struct net_dm_alert_ops net_dm_alert_summary_ops = {
 	.napi_poll_probe	= trace_napi_poll_hit,
 	.work_item_func		= send_dm_alert,
 	.hw_work_item_func	= net_dm_hw_summary_work,
-	.hw_probe		= net_dm_hw_summary_probe,
+	.hw_trap_probe		= net_dm_hw_trap_summary_probe,
 };
 
 static void net_dm_packet_trace_kfree_skb_hit(void *ignore,
@@ -705,7 +711,7 @@ static void net_dm_packet_work(struct work_struct *work)
 }
 
 static size_t
-net_dm_flow_action_cookie_size(const struct net_dm_hw_metadata *hw_metadata)
+net_dm_flow_action_cookie_size(const struct devlink_trap_metadata *hw_metadata)
 {
 	return hw_metadata->fa_cookie ?
 	       nla_total_size(hw_metadata->fa_cookie->cookie_len) : 0;
@@ -713,7 +719,7 @@ net_dm_flow_action_cookie_size(const struct net_dm_hw_metadata *hw_metadata)
 
 static size_t
 net_dm_hw_packet_report_size(size_t payload_len,
-			     const struct net_dm_hw_metadata *hw_metadata)
+			     const struct devlink_trap_metadata *hw_metadata)
 {
 	size_t size;
 
@@ -743,7 +749,7 @@ net_dm_hw_packet_report_size(size_t payload_len,
 static int net_dm_hw_packet_report_fill(struct sk_buff *msg,
 					struct sk_buff *skb, size_t payload_len)
 {
-	struct net_dm_hw_metadata *hw_metadata;
+	struct devlink_trap_metadata *hw_metadata;
 	struct nlattr *attr;
 	void *hdr;
 
@@ -810,56 +816,56 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
-static struct net_dm_hw_metadata *
-net_dm_hw_metadata_clone(const struct net_dm_hw_metadata *hw_metadata)
+static struct devlink_trap_metadata *
+net_dm_hw_metadata_copy(const struct devlink_trap_metadata *metadata)
 {
 	const struct flow_action_cookie *fa_cookie;
-	struct net_dm_hw_metadata *n_hw_metadata;
+	struct devlink_trap_metadata *hw_metadata;
 	const char *trap_group_name;
 	const char *trap_name;
 
-	n_hw_metadata = kzalloc(sizeof(*hw_metadata), GFP_ATOMIC);
-	if (!n_hw_metadata)
+	hw_metadata = kzalloc(sizeof(*hw_metadata), GFP_ATOMIC);
+	if (!hw_metadata)
 		return NULL;
 
-	trap_group_name = kstrdup(hw_metadata->trap_group_name, GFP_ATOMIC);
+	trap_group_name = kstrdup(metadata->trap_group_name, GFP_ATOMIC);
 	if (!trap_group_name)
 		goto free_hw_metadata;
-	n_hw_metadata->trap_group_name = trap_group_name;
+	hw_metadata->trap_group_name = trap_group_name;
 
-	trap_name = kstrdup(hw_metadata->trap_name, GFP_ATOMIC);
+	trap_name = kstrdup(metadata->trap_name, GFP_ATOMIC);
 	if (!trap_name)
 		goto free_trap_group;
-	n_hw_metadata->trap_name = trap_name;
+	hw_metadata->trap_name = trap_name;
 
-	if (hw_metadata->fa_cookie) {
+	if (metadata->fa_cookie) {
 		size_t cookie_size = sizeof(*fa_cookie) +
-				     hw_metadata->fa_cookie->cookie_len;
+				     metadata->fa_cookie->cookie_len;
 
-		fa_cookie = kmemdup(hw_metadata->fa_cookie, cookie_size,
+		fa_cookie = kmemdup(metadata->fa_cookie, cookie_size,
 				    GFP_ATOMIC);
 		if (!fa_cookie)
 			goto free_trap_name;
-		n_hw_metadata->fa_cookie = fa_cookie;
+		hw_metadata->fa_cookie = fa_cookie;
 	}
 
-	n_hw_metadata->input_dev = hw_metadata->input_dev;
-	if (n_hw_metadata->input_dev)
-		dev_hold(n_hw_metadata->input_dev);
+	hw_metadata->input_dev = metadata->input_dev;
+	if (hw_metadata->input_dev)
+		dev_hold(hw_metadata->input_dev);
 
-	return n_hw_metadata;
+	return hw_metadata;
 
 free_trap_name:
 	kfree(trap_name);
 free_trap_group:
 	kfree(trap_group_name);
 free_hw_metadata:
-	kfree(n_hw_metadata);
+	kfree(hw_metadata);
 	return NULL;
 }
 
 static void
-net_dm_hw_metadata_free(const struct net_dm_hw_metadata *hw_metadata)
+net_dm_hw_metadata_free(const struct devlink_trap_metadata *hw_metadata)
 {
 	if (hw_metadata->input_dev)
 		dev_put(hw_metadata->input_dev);
@@ -871,7 +877,7 @@ net_dm_hw_metadata_free(const struct net_dm_hw_metadata *hw_metadata)
 
 static void net_dm_hw_packet_report(struct sk_buff *skb)
 {
-	struct net_dm_hw_metadata *hw_metadata;
+	struct devlink_trap_metadata *hw_metadata;
 	struct sk_buff *msg;
 	size_t payload_len;
 	int rc;
@@ -924,15 +930,19 @@ static void net_dm_hw_packet_work(struct work_struct *work)
 }
 
 static void
-net_dm_hw_packet_probe(struct sk_buff *skb,
-		       const struct net_dm_hw_metadata *hw_metadata)
+net_dm_hw_trap_packet_probe(void *ignore, const struct devlink *devlink,
+			    struct sk_buff *skb,
+			    const struct devlink_trap_metadata *metadata)
 {
-	struct net_dm_hw_metadata *n_hw_metadata;
+	struct devlink_trap_metadata *n_hw_metadata;
 	ktime_t tstamp = ktime_get_real();
 	struct per_cpu_dm_data *hw_data;
 	struct sk_buff *nskb;
 	unsigned long flags;
 
+	if (metadata->trap_type == DEVLINK_TRAP_TYPE_CONTROL)
+		return;
+
 	if (!skb_mac_header_was_set(skb))
 		return;
 
@@ -940,7 +950,7 @@ net_dm_hw_packet_probe(struct sk_buff *skb,
 	if (!nskb)
 		return;
 
-	n_hw_metadata = net_dm_hw_metadata_clone(hw_metadata);
+	n_hw_metadata = net_dm_hw_metadata_copy(metadata);
 	if (!n_hw_metadata)
 		goto free;
 
@@ -975,7 +985,7 @@ static const struct net_dm_alert_ops net_dm_alert_packet_ops = {
 	.napi_poll_probe	= net_dm_packet_trace_napi_poll_hit,
 	.work_item_func		= net_dm_packet_work,
 	.hw_work_item_func	= net_dm_hw_packet_work,
-	.hw_probe		= net_dm_hw_packet_probe,
+	.hw_trap_probe		= net_dm_hw_trap_packet_probe,
 };
 
 static const struct net_dm_alert_ops *net_dm_alert_ops_arr[] = {
@@ -983,25 +993,32 @@ static const struct net_dm_alert_ops *net_dm_alert_ops_arr[] = {
 	[NET_DM_ALERT_MODE_PACKET]	= &net_dm_alert_packet_ops,
 };
 
-void net_dm_hw_report(struct sk_buff *skb,
-		      const struct net_dm_hw_metadata *hw_metadata)
+#if IS_ENABLED(CONFIG_NET_DEVLINK)
+static int net_dm_hw_probe_register(const struct net_dm_alert_ops *ops)
 {
-	rcu_read_lock();
-
-	if (!monitor_hw)
-		goto out;
+	return register_trace_devlink_trap_report(ops->hw_trap_probe, NULL);
+}
 
-	net_dm_alert_ops_arr[net_dm_alert_mode]->hw_probe(skb, hw_metadata);
+static void net_dm_hw_probe_unregister(const struct net_dm_alert_ops *ops)
+{
+	unregister_trace_devlink_trap_report(ops->hw_trap_probe, NULL);
+	tracepoint_synchronize_unregister();
+}
+#else
+static int net_dm_hw_probe_register(const struct net_dm_alert_ops *ops)
+{
+	return -EOPNOTSUPP;
+}
 
-out:
-	rcu_read_unlock();
+static void net_dm_hw_probe_unregister(const struct net_dm_alert_ops *ops)
+{
 }
-EXPORT_SYMBOL_GPL(net_dm_hw_report);
+#endif
 
 static int net_dm_hw_monitor_start(struct netlink_ext_ack *extack)
 {
 	const struct net_dm_alert_ops *ops;
-	int cpu;
+	int cpu, rc;
 
 	if (monitor_hw) {
 		NL_SET_ERR_MSG_MOD(extack, "Hardware monitoring already enabled");
@@ -1025,13 +1042,24 @@ static int net_dm_hw_monitor_start(struct netlink_ext_ack *extack)
 		kfree(hw_entries);
 	}
 
+	rc = net_dm_hw_probe_register(ops);
+	if (rc) {
+		NL_SET_ERR_MSG_MOD(extack, "Failed to connect probe to devlink_trap_probe() tracepoint");
+		goto err_module_put;
+	}
+
 	monitor_hw = true;
 
 	return 0;
+
+err_module_put:
+	module_put(THIS_MODULE);
+	return rc;
 }
 
 static void net_dm_hw_monitor_stop(struct netlink_ext_ack *extack)
 {
+	const struct net_dm_alert_ops *ops;
 	int cpu;
 
 	if (!monitor_hw) {
@@ -1039,12 +1067,11 @@ static void net_dm_hw_monitor_stop(struct netlink_ext_ack *extack)
 		return;
 	}
 
+	ops = net_dm_alert_ops_arr[net_dm_alert_mode];
+
 	monitor_hw = false;
 
-	/* After this call returns we are guaranteed that no CPU is processing
-	 * any hardware drops.
-	 */
-	synchronize_rcu();
+	net_dm_hw_probe_unregister(ops);
 
 	for_each_possible_cpu(cpu) {
 		struct per_cpu_dm_data *hw_data = &per_cpu(dm_hw_cpu_data, cpu);
@@ -1053,7 +1080,7 @@ static void net_dm_hw_monitor_stop(struct netlink_ext_ack *extack)
 		del_timer_sync(&hw_data->send_timer);
 		cancel_work_sync(&hw_data->dm_alert_work);
 		while ((skb = __skb_dequeue(&hw_data->drop_queue))) {
-			struct net_dm_hw_metadata *hw_metadata;
+			struct devlink_trap_metadata *hw_metadata;
 
 			hw_metadata = NET_DM_SKB_CB(skb)->hw_metadata;
 			net_dm_hw_metadata_free(hw_metadata);
@@ -1548,7 +1575,7 @@ static const struct nla_policy net_dm_nl_policy[NET_DM_ATTR_MAX + 1] = {
 	[NET_DM_ATTR_HW_DROPS]	= {. type = NLA_FLAG },
 };
 
-static const struct genl_ops dropmon_ops[] = {
+static const struct genl_small_ops dropmon_ops[] = {
 	{
 		.cmd = NET_DM_CMD_CONFIG,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
@@ -1598,8 +1625,8 @@ static struct genl_family net_drop_monitor_family __ro_after_init = {
 	.pre_doit	= net_dm_nl_pre_doit,
 	.post_doit	= net_dm_nl_post_doit,
 	.module		= THIS_MODULE,
-	.ops		= dropmon_ops,
-	.n_ops		= ARRAY_SIZE(dropmon_ops),
+	.small_ops	= dropmon_ops,
+	.n_small_ops	= ARRAY_SIZE(dropmon_ops),
 	.mcgrps		= dropmon_mcgrps,
 	.n_mcgrps	= ARRAY_SIZE(dropmon_mcgrps),
 };
diff --git a/net/core/dst.c b/net/core/dst.c
index d6b6ced0d451..0c01bd8d9d81 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -144,7 +144,7 @@ static void dst_destroy_rcu(struct rcu_head *head)
 
 /* Operations to mark dst as DEAD and clean up the net device referenced
  * by dst:
- * 1. put the dst under loopback interface and discard all tx/rx packets
+ * 1. put the dst under blackhole interface and discard all tx/rx packets
  *    on this route.
  * 2. release the net_device
  * This function should be called when removing routes from the fib tree
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 51678a528f85..7bcfb16854cb 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -16,7 +16,7 @@
 #include <net/ip_tunnels.h>
 #include <linux/indirect_call_wrapper.h>
 
-#ifdef CONFIG_IPV6_MULTIPLE_TABLES
+#if defined(CONFIG_IPV6) && defined(CONFIG_IPV6_MULTIPLE_TABLES)
 #ifdef CONFIG_IP_MULTIPLE_TABLES
 #define INDIRECT_CALL_MT(f, f2, f1, ...) \
 	INDIRECT_CALL_INET(f, f2, f1, __VA_ARGS__)
diff --git a/net/core/filter.c b/net/core/filter.c
index 2ad9c0ef1946..3fb6adad1957 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -77,6 +77,9 @@
 #include <net/transp_v6.h>
 #include <linux/btf_ids.h>
 
+static const struct bpf_func_proto *
+bpf_sk_base_func_proto(enum bpf_func_id func_id);
+
 int copy_bpf_fprog_from_user(struct sock_fprog *dst, sockptr_t src, int len)
 {
 	if (in_compat_syscall()) {
@@ -2160,13 +2163,233 @@ static int __bpf_redirect(struct sk_buff *skb, struct net_device *dev,
 		return __bpf_redirect_no_mac(skb, dev, flags);
 }
 
+#if IS_ENABLED(CONFIG_IPV6)
+static int bpf_out_neigh_v6(struct net *net, struct sk_buff *skb)
+{
+	struct dst_entry *dst = skb_dst(skb);
+	struct net_device *dev = dst->dev;
+	u32 hh_len = LL_RESERVED_SPACE(dev);
+	const struct in6_addr *nexthop;
+	struct neighbour *neigh;
+
+	if (dev_xmit_recursion()) {
+		net_crit_ratelimited("bpf: recursion limit reached on datapath, buggy bpf program?\n");
+		goto out_drop;
+	}
+
+	skb->dev = dev;
+	skb->tstamp = 0;
+
+	if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) {
+		struct sk_buff *skb2;
+
+		skb2 = skb_realloc_headroom(skb, hh_len);
+		if (unlikely(!skb2)) {
+			kfree_skb(skb);
+			return -ENOMEM;
+		}
+		if (skb->sk)
+			skb_set_owner_w(skb2, skb->sk);
+		consume_skb(skb);
+		skb = skb2;
+	}
+
+	rcu_read_lock_bh();
+	nexthop = rt6_nexthop(container_of(dst, struct rt6_info, dst),
+			      &ipv6_hdr(skb)->daddr);
+	neigh = ip_neigh_gw6(dev, nexthop);
+	if (likely(!IS_ERR(neigh))) {
+		int ret;
+
+		sock_confirm_neigh(skb, neigh);
+		dev_xmit_recursion_inc();
+		ret = neigh_output(neigh, skb, false);
+		dev_xmit_recursion_dec();
+		rcu_read_unlock_bh();
+		return ret;
+	}
+	rcu_read_unlock_bh();
+	IP6_INC_STATS(dev_net(dst->dev),
+		      ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
+out_drop:
+	kfree_skb(skb);
+	return -ENETDOWN;
+}
+
+static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev)
+{
+	const struct ipv6hdr *ip6h = ipv6_hdr(skb);
+	struct net *net = dev_net(dev);
+	int err, ret = NET_XMIT_DROP;
+	struct dst_entry *dst;
+	struct flowi6 fl6 = {
+		.flowi6_flags	= FLOWI_FLAG_ANYSRC,
+		.flowi6_mark	= skb->mark,
+		.flowlabel	= ip6_flowinfo(ip6h),
+		.flowi6_oif	= dev->ifindex,
+		.flowi6_proto	= ip6h->nexthdr,
+		.daddr		= ip6h->daddr,
+		.saddr		= ip6h->saddr,
+	};
+
+	dst = ipv6_stub->ipv6_dst_lookup_flow(net, NULL, &fl6, NULL);
+	if (IS_ERR(dst))
+		goto out_drop;
+
+	skb_dst_set(skb, dst);
+
+	err = bpf_out_neigh_v6(net, skb);
+	if (unlikely(net_xmit_eval(err)))
+		dev->stats.tx_errors++;
+	else
+		ret = NET_XMIT_SUCCESS;
+	goto out_xmit;
+out_drop:
+	dev->stats.tx_errors++;
+	kfree_skb(skb);
+out_xmit:
+	return ret;
+}
+#else
+static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev)
+{
+	kfree_skb(skb);
+	return NET_XMIT_DROP;
+}
+#endif /* CONFIG_IPV6 */
+
+#if IS_ENABLED(CONFIG_INET)
+static int bpf_out_neigh_v4(struct net *net, struct sk_buff *skb)
+{
+	struct dst_entry *dst = skb_dst(skb);
+	struct rtable *rt = container_of(dst, struct rtable, dst);
+	struct net_device *dev = dst->dev;
+	u32 hh_len = LL_RESERVED_SPACE(dev);
+	struct neighbour *neigh;
+	bool is_v6gw = false;
+
+	if (dev_xmit_recursion()) {
+		net_crit_ratelimited("bpf: recursion limit reached on datapath, buggy bpf program?\n");
+		goto out_drop;
+	}
+
+	skb->dev = dev;
+	skb->tstamp = 0;
+
+	if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) {
+		struct sk_buff *skb2;
+
+		skb2 = skb_realloc_headroom(skb, hh_len);
+		if (unlikely(!skb2)) {
+			kfree_skb(skb);
+			return -ENOMEM;
+		}
+		if (skb->sk)
+			skb_set_owner_w(skb2, skb->sk);
+		consume_skb(skb);
+		skb = skb2;
+	}
+
+	rcu_read_lock_bh();
+	neigh = ip_neigh_for_gw(rt, skb, &is_v6gw);
+	if (likely(!IS_ERR(neigh))) {
+		int ret;
+
+		sock_confirm_neigh(skb, neigh);
+		dev_xmit_recursion_inc();
+		ret = neigh_output(neigh, skb, is_v6gw);
+		dev_xmit_recursion_dec();
+		rcu_read_unlock_bh();
+		return ret;
+	}
+	rcu_read_unlock_bh();
+out_drop:
+	kfree_skb(skb);
+	return -ENETDOWN;
+}
+
+static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev)
+{
+	const struct iphdr *ip4h = ip_hdr(skb);
+	struct net *net = dev_net(dev);
+	int err, ret = NET_XMIT_DROP;
+	struct rtable *rt;
+	struct flowi4 fl4 = {
+		.flowi4_flags	= FLOWI_FLAG_ANYSRC,
+		.flowi4_mark	= skb->mark,
+		.flowi4_tos	= RT_TOS(ip4h->tos),
+		.flowi4_oif	= dev->ifindex,
+		.flowi4_proto	= ip4h->protocol,
+		.daddr		= ip4h->daddr,
+		.saddr		= ip4h->saddr,
+	};
+
+	rt = ip_route_output_flow(net, &fl4, NULL);
+	if (IS_ERR(rt))
+		goto out_drop;
+	if (rt->rt_type != RTN_UNICAST && rt->rt_type != RTN_LOCAL) {
+		ip_rt_put(rt);
+		goto out_drop;
+	}
+
+	skb_dst_set(skb, &rt->dst);
+
+	err = bpf_out_neigh_v4(net, skb);
+	if (unlikely(net_xmit_eval(err)))
+		dev->stats.tx_errors++;
+	else
+		ret = NET_XMIT_SUCCESS;
+	goto out_xmit;
+out_drop:
+	dev->stats.tx_errors++;
+	kfree_skb(skb);
+out_xmit:
+	return ret;
+}
+#else
+static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev)
+{
+	kfree_skb(skb);
+	return NET_XMIT_DROP;
+}
+#endif /* CONFIG_INET */
+
+static int __bpf_redirect_neigh(struct sk_buff *skb, struct net_device *dev)
+{
+	struct ethhdr *ethh = eth_hdr(skb);
+
+	if (unlikely(skb->mac_header >= skb->network_header))
+		goto out;
+	bpf_push_mac_rcsum(skb);
+	if (is_multicast_ether_addr(ethh->h_dest))
+		goto out;
+
+	skb_pull(skb, sizeof(*ethh));
+	skb_unset_mac_header(skb);
+	skb_reset_network_header(skb);
+
+	if (skb->protocol == htons(ETH_P_IP))
+		return __bpf_redirect_neigh_v4(skb, dev);
+	else if (skb->protocol == htons(ETH_P_IPV6))
+		return __bpf_redirect_neigh_v6(skb, dev);
+out:
+	kfree_skb(skb);
+	return -ENOTSUPP;
+}
+
+/* Internal, non-exposed redirect flags. */
+enum {
+	BPF_F_NEIGH = (1ULL << 1),
+#define BPF_F_REDIRECT_INTERNAL	(BPF_F_NEIGH)
+};
+
 BPF_CALL_3(bpf_clone_redirect, struct sk_buff *, skb, u32, ifindex, u64, flags)
 {
 	struct net_device *dev;
 	struct sk_buff *clone;
 	int ret;
 
-	if (unlikely(flags & ~(BPF_F_INGRESS)))
+	if (unlikely(flags & (~(BPF_F_INGRESS) | BPF_F_REDIRECT_INTERNAL)))
 		return -EINVAL;
 
 	dev = dev_get_by_index_rcu(dev_net(skb->dev), ifindex);
@@ -2203,23 +2426,11 @@ static const struct bpf_func_proto bpf_clone_redirect_proto = {
 DEFINE_PER_CPU(struct bpf_redirect_info, bpf_redirect_info);
 EXPORT_PER_CPU_SYMBOL_GPL(bpf_redirect_info);
 
-BPF_CALL_2(bpf_redirect, u32, ifindex, u64, flags)
-{
-	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
-
-	if (unlikely(flags & ~(BPF_F_INGRESS)))
-		return TC_ACT_SHOT;
-
-	ri->flags = flags;
-	ri->tgt_index = ifindex;
-
-	return TC_ACT_REDIRECT;
-}
-
 int skb_do_redirect(struct sk_buff *skb)
 {
 	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
 	struct net_device *dev;
+	u32 flags = ri->flags;
 
 	dev = dev_get_by_index_rcu(dev_net(skb->dev), ri->tgt_index);
 	ri->tgt_index = 0;
@@ -2228,7 +2439,22 @@ int skb_do_redirect(struct sk_buff *skb)
 		return -EINVAL;
 	}
 
-	return __bpf_redirect(skb, dev, ri->flags);
+	return flags & BPF_F_NEIGH ?
+	       __bpf_redirect_neigh(skb, dev) :
+	       __bpf_redirect(skb, dev, flags);
+}
+
+BPF_CALL_2(bpf_redirect, u32, ifindex, u64, flags)
+{
+	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+
+	if (unlikely(flags & (~(BPF_F_INGRESS) | BPF_F_REDIRECT_INTERNAL)))
+		return TC_ACT_SHOT;
+
+	ri->flags = flags;
+	ri->tgt_index = ifindex;
+
+	return TC_ACT_REDIRECT;
 }
 
 static const struct bpf_func_proto bpf_redirect_proto = {
@@ -2239,6 +2465,27 @@ static const struct bpf_func_proto bpf_redirect_proto = {
 	.arg2_type      = ARG_ANYTHING,
 };
 
+BPF_CALL_2(bpf_redirect_neigh, u32, ifindex, u64, flags)
+{
+	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+
+	if (unlikely(flags))
+		return TC_ACT_SHOT;
+
+	ri->flags = BPF_F_NEIGH;
+	ri->tgt_index = ifindex;
+
+	return TC_ACT_REDIRECT;
+}
+
+static const struct bpf_func_proto bpf_redirect_neigh_proto = {
+	.func		= bpf_redirect_neigh,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_ANYTHING,
+	.arg2_type	= ARG_ANYTHING,
+};
+
 BPF_CALL_2(bpf_msg_apply_bytes, struct sk_msg *, msg, u32, bytes)
 {
 	msg->apply_bytes = bytes;
@@ -2704,6 +2951,23 @@ static const struct bpf_func_proto bpf_get_cgroup_classid_curr_proto = {
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
 };
+
+BPF_CALL_1(bpf_skb_cgroup_classid, const struct sk_buff *, skb)
+{
+	struct sock *sk = skb_to_full_sk(skb);
+
+	if (!sk || !sk_fullsock(sk))
+		return 0;
+
+	return sock_cgroup_classid(&sk->sk_cgrp_data);
+}
+
+static const struct bpf_func_proto bpf_skb_cgroup_classid_proto = {
+	.func		= bpf_skb_cgroup_classid,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+};
 #endif
 
 BPF_CALL_1(bpf_get_cgroup_classid, const struct sk_buff *, skb)
@@ -3803,19 +4067,18 @@ static const struct bpf_func_proto bpf_skb_event_output_proto = {
 	.arg5_type	= ARG_CONST_SIZE_OR_ZERO,
 };
 
-BTF_ID_LIST(bpf_skb_output_btf_ids)
-BTF_ID(struct, sk_buff)
+BTF_ID_LIST_SINGLE(bpf_skb_output_btf_ids, struct, sk_buff)
 
 const struct bpf_func_proto bpf_skb_output_proto = {
 	.func		= bpf_skb_event_output,
 	.gpl_only	= true,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_BTF_ID,
+	.arg1_btf_id	= &bpf_skb_output_btf_ids[0],
 	.arg2_type	= ARG_CONST_MAP_PTR,
 	.arg3_type	= ARG_ANYTHING,
 	.arg4_type	= ARG_PTR_TO_MEM,
 	.arg5_type	= ARG_CONST_SIZE_OR_ZERO,
-	.btf_id		= bpf_skb_output_btf_ids,
 };
 
 static unsigned short bpf_tunnel_key_af(u64 flags)
@@ -4086,18 +4349,17 @@ static inline u64 __bpf_sk_cgroup_id(struct sock *sk)
 {
 	struct cgroup *cgrp;
 
+	sk = sk_to_full_sk(sk);
+	if (!sk || !sk_fullsock(sk))
+		return 0;
+
 	cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
 	return cgroup_id(cgrp);
 }
 
 BPF_CALL_1(bpf_skb_cgroup_id, const struct sk_buff *, skb)
 {
-	struct sock *sk = skb_to_full_sk(skb);
-
-	if (!sk || !sk_fullsock(sk))
-		return 0;
-
-	return __bpf_sk_cgroup_id(sk);
+	return __bpf_sk_cgroup_id(skb->sk);
 }
 
 static const struct bpf_func_proto bpf_skb_cgroup_id_proto = {
@@ -4113,6 +4375,10 @@ static inline u64 __bpf_sk_ancestor_cgroup_id(struct sock *sk,
 	struct cgroup *ancestor;
 	struct cgroup *cgrp;
 
+	sk = sk_to_full_sk(sk);
+	if (!sk || !sk_fullsock(sk))
+		return 0;
+
 	cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
 	ancestor = cgroup_ancestor(cgrp, ancestor_level);
 	if (!ancestor)
@@ -4124,12 +4390,7 @@ static inline u64 __bpf_sk_ancestor_cgroup_id(struct sock *sk,
 BPF_CALL_2(bpf_skb_ancestor_cgroup_id, const struct sk_buff *, skb, int,
 	   ancestor_level)
 {
-	struct sock *sk = skb_to_full_sk(skb);
-
-	if (!sk || !sk_fullsock(sk))
-		return 0;
-
-	return __bpf_sk_ancestor_cgroup_id(sk, ancestor_level);
+	return __bpf_sk_ancestor_cgroup_id(skb->sk, ancestor_level);
 }
 
 static const struct bpf_func_proto bpf_skb_ancestor_cgroup_id_proto = {
@@ -4149,7 +4410,7 @@ static const struct bpf_func_proto bpf_sk_cgroup_id_proto = {
 	.func           = bpf_sk_cgroup_id,
 	.gpl_only       = false,
 	.ret_type       = RET_INTEGER,
-	.arg1_type      = ARG_PTR_TO_SOCKET,
+	.arg1_type      = ARG_PTR_TO_BTF_ID_SOCK_COMMON,
 };
 
 BPF_CALL_2(bpf_sk_ancestor_cgroup_id, struct sock *, sk, int, ancestor_level)
@@ -4161,7 +4422,7 @@ static const struct bpf_func_proto bpf_sk_ancestor_cgroup_id_proto = {
 	.func           = bpf_sk_ancestor_cgroup_id,
 	.gpl_only       = false,
 	.ret_type       = RET_INTEGER,
-	.arg1_type      = ARG_PTR_TO_SOCKET,
+	.arg1_type      = ARG_PTR_TO_BTF_ID_SOCK_COMMON,
 	.arg2_type      = ARG_ANYTHING,
 };
 #endif
@@ -4199,24 +4460,23 @@ static const struct bpf_func_proto bpf_xdp_event_output_proto = {
 	.arg5_type	= ARG_CONST_SIZE_OR_ZERO,
 };
 
-BTF_ID_LIST(bpf_xdp_output_btf_ids)
-BTF_ID(struct, xdp_buff)
+BTF_ID_LIST_SINGLE(bpf_xdp_output_btf_ids, struct, xdp_buff)
 
 const struct bpf_func_proto bpf_xdp_output_proto = {
 	.func		= bpf_xdp_event_output,
 	.gpl_only	= true,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_BTF_ID,
+	.arg1_btf_id	= &bpf_xdp_output_btf_ids[0],
 	.arg2_type	= ARG_CONST_MAP_PTR,
 	.arg3_type	= ARG_ANYTHING,
 	.arg4_type	= ARG_PTR_TO_MEM,
 	.arg5_type	= ARG_CONST_SIZE_OR_ZERO,
-	.btf_id		= bpf_xdp_output_btf_ids,
 };
 
 BPF_CALL_1(bpf_get_socket_cookie, struct sk_buff *, skb)
 {
-	return skb->sk ? sock_gen_cookie(skb->sk) : 0;
+	return skb->sk ? __sock_gen_cookie(skb->sk) : 0;
 }
 
 static const struct bpf_func_proto bpf_get_socket_cookie_proto = {
@@ -4228,7 +4488,7 @@ static const struct bpf_func_proto bpf_get_socket_cookie_proto = {
 
 BPF_CALL_1(bpf_get_socket_cookie_sock_addr, struct bpf_sock_addr_kern *, ctx)
 {
-	return sock_gen_cookie(ctx->sk);
+	return __sock_gen_cookie(ctx->sk);
 }
 
 static const struct bpf_func_proto bpf_get_socket_cookie_sock_addr_proto = {
@@ -4240,7 +4500,7 @@ static const struct bpf_func_proto bpf_get_socket_cookie_sock_addr_proto = {
 
 BPF_CALL_1(bpf_get_socket_cookie_sock, struct sock *, ctx)
 {
-	return sock_gen_cookie(ctx);
+	return __sock_gen_cookie(ctx);
 }
 
 static const struct bpf_func_proto bpf_get_socket_cookie_sock_proto = {
@@ -4252,7 +4512,7 @@ static const struct bpf_func_proto bpf_get_socket_cookie_sock_proto = {
 
 BPF_CALL_1(bpf_get_socket_cookie_sock_ops, struct bpf_sock_ops_kern *, ctx)
 {
-	return sock_gen_cookie(ctx->sk);
+	return __sock_gen_cookie(ctx->sk);
 }
 
 static const struct bpf_func_proto bpf_get_socket_cookie_sock_ops_proto = {
@@ -4265,7 +4525,7 @@ static const struct bpf_func_proto bpf_get_socket_cookie_sock_ops_proto = {
 static u64 __bpf_get_netns_cookie(struct sock *sk)
 {
 #ifdef CONFIG_NET_NS
-	return net_gen_cookie(sk ? sk->sk_net.net : &init_net);
+	return __net_gen_cookie(sk ? sk->sk_net.net : &init_net);
 #else
 	return 0;
 #endif
@@ -4313,10 +4573,8 @@ static const struct bpf_func_proto bpf_get_socket_uid_proto = {
 	.arg1_type      = ARG_PTR_TO_CTX,
 };
 
-#define SOCKOPT_CC_REINIT (1 << 0)
-
 static int _bpf_setsockopt(struct sock *sk, int level, int optname,
-			   char *optval, int optlen, u32 flags)
+			   char *optval, int optlen)
 {
 	char devname[IFNAMSIZ];
 	int val, valbool;
@@ -4449,13 +4707,11 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname,
 		   sk->sk_prot->setsockopt == tcp_setsockopt) {
 		if (optname == TCP_CONGESTION) {
 			char name[TCP_CA_NAME_MAX];
-			bool reinit = flags & SOCKOPT_CC_REINIT;
 
 			strncpy(name, optval, min_t(long, optlen,
 						    TCP_CA_NAME_MAX-1));
 			name[TCP_CA_NAME_MAX-1] = 0;
-			ret = tcp_set_congestion_control(sk, name, false,
-							 reinit, true);
+			ret = tcp_set_congestion_control(sk, name, false, true);
 		} else {
 			struct inet_connection_sock *icsk = inet_csk(sk);
 			struct tcp_sock *tp = tcp_sk(sk);
@@ -4615,9 +4871,7 @@ err_clear:
 BPF_CALL_5(bpf_sock_addr_setsockopt, struct bpf_sock_addr_kern *, ctx,
 	   int, level, int, optname, char *, optval, int, optlen)
 {
-	u32 flags = 0;
-	return _bpf_setsockopt(ctx->sk, level, optname, optval, optlen,
-			       flags);
+	return _bpf_setsockopt(ctx->sk, level, optname, optval, optlen);
 }
 
 static const struct bpf_func_proto bpf_sock_addr_setsockopt_proto = {
@@ -4651,11 +4905,7 @@ static const struct bpf_func_proto bpf_sock_addr_getsockopt_proto = {
 BPF_CALL_5(bpf_sock_ops_setsockopt, struct bpf_sock_ops_kern *, bpf_sock,
 	   int, level, int, optname, char *, optval, int, optlen)
 {
-	u32 flags = 0;
-	if (bpf_sock->op > BPF_SOCK_OPS_NEEDS_ECN)
-		flags |= SOCKOPT_CC_REINIT;
-	return _bpf_setsockopt(bpf_sock->sk, level, optname, optval, optlen,
-			       flags);
+	return _bpf_setsockopt(bpf_sock->sk, level, optname, optval, optlen);
 }
 
 static const struct bpf_func_proto bpf_sock_ops_setsockopt_proto = {
@@ -4943,6 +5193,7 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 	fl4.saddr = params->ipv4_src;
 	fl4.fl4_sport = params->sport;
 	fl4.fl4_dport = params->dport;
+	fl4.flowi4_multipath_hash = 0;
 
 	if (flags & BPF_FIB_LOOKUP_DIRECT) {
 		u32 tbid = l3mdev_fib_table_rcu(dev) ? : RT_TABLE_MAIN;
@@ -5705,7 +5956,7 @@ static const struct bpf_func_proto bpf_sk_lookup_udp_proto = {
 
 BPF_CALL_1(bpf_sk_release, struct sock *, sk)
 {
-	if (sk_is_refcounted(sk))
+	if (sk && sk_is_refcounted(sk))
 		sock_gen_put(sk);
 	return 0;
 }
@@ -5714,7 +5965,7 @@ static const struct bpf_func_proto bpf_sk_release_proto = {
 	.func		= bpf_sk_release,
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
-	.arg1_type	= ARG_PTR_TO_SOCK_COMMON,
+	.arg1_type	= ARG_PTR_TO_BTF_ID_SOCK_COMMON,
 };
 
 BPF_CALL_5(bpf_xdp_sk_lookup_udp, struct xdp_buff *, ctx,
@@ -6096,7 +6347,7 @@ BPF_CALL_5(bpf_tcp_check_syncookie, struct sock *, sk, void *, iph, u32, iph_len
 	u32 cookie;
 	int ret;
 
-	if (unlikely(th_len < sizeof(*th)))
+	if (unlikely(!sk || th_len < sizeof(*th)))
 		return -EINVAL;
 
 	/* sk_listener() allows TCP_NEW_SYN_RECV, which makes no sense here. */
@@ -6149,7 +6400,7 @@ static const struct bpf_func_proto bpf_tcp_check_syncookie_proto = {
 	.gpl_only	= true,
 	.pkt_access	= true,
 	.ret_type	= RET_INTEGER,
-	.arg1_type	= ARG_PTR_TO_SOCK_COMMON,
+	.arg1_type	= ARG_PTR_TO_BTF_ID_SOCK_COMMON,
 	.arg2_type	= ARG_PTR_TO_MEM,
 	.arg3_type	= ARG_CONST_SIZE,
 	.arg4_type	= ARG_PTR_TO_MEM,
@@ -6163,7 +6414,7 @@ BPF_CALL_5(bpf_tcp_gen_syncookie, struct sock *, sk, void *, iph, u32, iph_len,
 	u32 cookie;
 	u16 mss;
 
-	if (unlikely(th_len < sizeof(*th) || th_len != th->doff * 4))
+	if (unlikely(!sk || th_len < sizeof(*th) || th_len != th->doff * 4))
 		return -EINVAL;
 
 	if (sk->sk_protocol != IPPROTO_TCP || sk->sk_state != TCP_LISTEN)
@@ -6218,7 +6469,7 @@ static const struct bpf_func_proto bpf_tcp_gen_syncookie_proto = {
 	.gpl_only	= true, /* __cookie_v*_init_sequence() is GPL */
 	.pkt_access	= true,
 	.ret_type	= RET_INTEGER,
-	.arg1_type	= ARG_PTR_TO_SOCK_COMMON,
+	.arg1_type	= ARG_PTR_TO_BTF_ID_SOCK_COMMON,
 	.arg2_type	= ARG_PTR_TO_MEM,
 	.arg3_type	= ARG_CONST_SIZE,
 	.arg4_type	= ARG_PTR_TO_MEM,
@@ -6227,7 +6478,7 @@ static const struct bpf_func_proto bpf_tcp_gen_syncookie_proto = {
 
 BPF_CALL_3(bpf_sk_assign, struct sk_buff *, skb, struct sock *, sk, u64, flags)
 {
-	if (flags != 0)
+	if (!sk || flags != 0)
 		return -EINVAL;
 	if (!skb_at_tc_ingress(skb))
 		return -EOPNOTSUPP;
@@ -6251,7 +6502,7 @@ static const struct bpf_func_proto bpf_sk_assign_proto = {
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
 	.arg1_type      = ARG_PTR_TO_CTX,
-	.arg2_type      = ARG_PTR_TO_SOCK_COMMON,
+	.arg2_type      = ARG_PTR_TO_BTF_ID_SOCK_COMMON,
 	.arg3_type	= ARG_ANYTHING,
 };
 
@@ -6631,7 +6882,7 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 			return NULL;
 		}
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -6650,7 +6901,7 @@ sk_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_perf_event_output:
 		return &bpf_skb_event_output_proto;
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -6752,6 +7003,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return bpf_get_skb_set_tunnel_proto(func_id);
 	case BPF_FUNC_redirect:
 		return &bpf_redirect_proto;
+	case BPF_FUNC_redirect_neigh:
+		return &bpf_redirect_neigh_proto;
 	case BPF_FUNC_get_route_realm:
 		return &bpf_get_route_realm_proto;
 	case BPF_FUNC_get_hash_recalc:
@@ -6782,6 +7035,10 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_skb_get_xfrm_state:
 		return &bpf_skb_get_xfrm_state_proto;
 #endif
+#ifdef CONFIG_CGROUP_NET_CLASSID
+	case BPF_FUNC_skb_cgroup_classid:
+		return &bpf_skb_cgroup_classid_proto;
+#endif
 #ifdef CONFIG_SOCK_CGROUP_DATA
 	case BPF_FUNC_skb_cgroup_id:
 		return &bpf_skb_cgroup_id_proto;
@@ -6811,7 +7068,7 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_sk_assign_proto;
 #endif
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -6852,7 +7109,7 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_tcp_gen_syncookie_proto;
 #endif
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -6894,7 +7151,7 @@ sock_ops_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_tcp_sock_proto;
 #endif /* CONFIG_INET */
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -6940,7 +7197,7 @@ sk_msg_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_get_cgroup_classid_curr_proto;
 #endif
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -6982,7 +7239,7 @@ sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_skc_lookup_tcp_proto;
 #endif
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -6993,7 +7250,7 @@ flow_dissector_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_skb_load_bytes:
 		return &bpf_flow_dissector_load_bytes_proto;
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -7020,7 +7277,7 @@ lwt_out_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_skb_under_cgroup:
 		return &bpf_skb_under_cgroup_proto;
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -7405,8 +7662,6 @@ static int bpf_gen_ld_abs(const struct bpf_insn *orig,
 	bool indirect = BPF_MODE(orig->code) == BPF_IND;
 	struct bpf_insn *insn = insn_buf;
 
-	/* We're guaranteed here that CTX is in R6. */
-	*insn++ = BPF_MOV64_REG(BPF_REG_1, BPF_REG_CTX);
 	if (!indirect) {
 		*insn++ = BPF_MOV64_IMM(BPF_REG_2, orig->imm);
 	} else {
@@ -7414,6 +7669,8 @@ static int bpf_gen_ld_abs(const struct bpf_insn *orig,
 		if (orig->imm)
 			*insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, orig->imm);
 	}
+	/* We're guaranteed here that CTX is in R6. */
+	*insn++ = BPF_MOV64_REG(BPF_REG_1, BPF_REG_CTX);
 
 	switch (BPF_SIZE(orig->code)) {
 	case BPF_B:
@@ -9757,7 +10014,7 @@ sk_lookup_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_sk_release:
 		return &bpf_sk_release_proto;
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -9907,24 +10164,13 @@ BTF_SOCK_TYPE_xxx
 u32 btf_sock_ids[MAX_BTF_SOCK_TYPE];
 #endif
 
-static bool check_arg_btf_id(u32 btf_id, u32 arg)
-{
-	int i;
-
-	/* only one argument, no need to check arg */
-	for (i = 0; i < MAX_BTF_SOCK_TYPE; i++)
-		if (btf_sock_ids[i] == btf_id)
-			return true;
-	return false;
-}
-
 BPF_CALL_1(bpf_skc_to_tcp6_sock, struct sock *, sk)
 {
 	/* tcp6_sock type is not generated in dwarf and hence btf,
 	 * trigger an explicit type generation here.
 	 */
 	BTF_TYPE_EMIT(struct tcp6_sock);
-	if (sk_fullsock(sk) && sk->sk_protocol == IPPROTO_TCP &&
+	if (sk && sk_fullsock(sk) && sk->sk_protocol == IPPROTO_TCP &&
 	    sk->sk_family == AF_INET6)
 		return (unsigned long)sk;
 
@@ -9935,14 +10181,13 @@ const struct bpf_func_proto bpf_skc_to_tcp6_sock_proto = {
 	.func			= bpf_skc_to_tcp6_sock,
 	.gpl_only		= false,
 	.ret_type		= RET_PTR_TO_BTF_ID_OR_NULL,
-	.arg1_type		= ARG_PTR_TO_BTF_ID,
-	.check_btf_id		= check_arg_btf_id,
+	.arg1_type		= ARG_PTR_TO_BTF_ID_SOCK_COMMON,
 	.ret_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_TCP6],
 };
 
 BPF_CALL_1(bpf_skc_to_tcp_sock, struct sock *, sk)
 {
-	if (sk_fullsock(sk) && sk->sk_protocol == IPPROTO_TCP)
+	if (sk && sk_fullsock(sk) && sk->sk_protocol == IPPROTO_TCP)
 		return (unsigned long)sk;
 
 	return (unsigned long)NULL;
@@ -9952,20 +10197,19 @@ const struct bpf_func_proto bpf_skc_to_tcp_sock_proto = {
 	.func			= bpf_skc_to_tcp_sock,
 	.gpl_only		= false,
 	.ret_type		= RET_PTR_TO_BTF_ID_OR_NULL,
-	.arg1_type		= ARG_PTR_TO_BTF_ID,
-	.check_btf_id		= check_arg_btf_id,
+	.arg1_type		= ARG_PTR_TO_BTF_ID_SOCK_COMMON,
 	.ret_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_TCP],
 };
 
 BPF_CALL_1(bpf_skc_to_tcp_timewait_sock, struct sock *, sk)
 {
 #ifdef CONFIG_INET
-	if (sk->sk_prot == &tcp_prot && sk->sk_state == TCP_TIME_WAIT)
+	if (sk && sk->sk_prot == &tcp_prot && sk->sk_state == TCP_TIME_WAIT)
 		return (unsigned long)sk;
 #endif
 
 #if IS_BUILTIN(CONFIG_IPV6)
-	if (sk->sk_prot == &tcpv6_prot && sk->sk_state == TCP_TIME_WAIT)
+	if (sk && sk->sk_prot == &tcpv6_prot && sk->sk_state == TCP_TIME_WAIT)
 		return (unsigned long)sk;
 #endif
 
@@ -9976,20 +10220,19 @@ const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto = {
 	.func			= bpf_skc_to_tcp_timewait_sock,
 	.gpl_only		= false,
 	.ret_type		= RET_PTR_TO_BTF_ID_OR_NULL,
-	.arg1_type		= ARG_PTR_TO_BTF_ID,
-	.check_btf_id		= check_arg_btf_id,
+	.arg1_type		= ARG_PTR_TO_BTF_ID_SOCK_COMMON,
 	.ret_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_TCP_TW],
 };
 
 BPF_CALL_1(bpf_skc_to_tcp_request_sock, struct sock *, sk)
 {
 #ifdef CONFIG_INET
-	if (sk->sk_prot == &tcp_prot  && sk->sk_state == TCP_NEW_SYN_RECV)
+	if (sk && sk->sk_prot == &tcp_prot && sk->sk_state == TCP_NEW_SYN_RECV)
 		return (unsigned long)sk;
 #endif
 
 #if IS_BUILTIN(CONFIG_IPV6)
-	if (sk->sk_prot == &tcpv6_prot && sk->sk_state == TCP_NEW_SYN_RECV)
+	if (sk && sk->sk_prot == &tcpv6_prot && sk->sk_state == TCP_NEW_SYN_RECV)
 		return (unsigned long)sk;
 #endif
 
@@ -10000,8 +10243,7 @@ const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto = {
 	.func			= bpf_skc_to_tcp_request_sock,
 	.gpl_only		= false,
 	.ret_type		= RET_PTR_TO_BTF_ID_OR_NULL,
-	.arg1_type		= ARG_PTR_TO_BTF_ID,
-	.check_btf_id		= check_arg_btf_id,
+	.arg1_type		= ARG_PTR_TO_BTF_ID_SOCK_COMMON,
 	.ret_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_TCP_REQ],
 };
 
@@ -10011,7 +10253,7 @@ BPF_CALL_1(bpf_skc_to_udp6_sock, struct sock *, sk)
 	 * trigger an explicit type generation here.
 	 */
 	BTF_TYPE_EMIT(struct udp6_sock);
-	if (sk_fullsock(sk) && sk->sk_protocol == IPPROTO_UDP &&
+	if (sk && sk_fullsock(sk) && sk->sk_protocol == IPPROTO_UDP &&
 	    sk->sk_type == SOCK_DGRAM && sk->sk_family == AF_INET6)
 		return (unsigned long)sk;
 
@@ -10022,7 +10264,37 @@ const struct bpf_func_proto bpf_skc_to_udp6_sock_proto = {
 	.func			= bpf_skc_to_udp6_sock,
 	.gpl_only		= false,
 	.ret_type		= RET_PTR_TO_BTF_ID_OR_NULL,
-	.arg1_type		= ARG_PTR_TO_BTF_ID,
-	.check_btf_id		= check_arg_btf_id,
+	.arg1_type		= ARG_PTR_TO_BTF_ID_SOCK_COMMON,
 	.ret_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_UDP6],
 };
+
+static const struct bpf_func_proto *
+bpf_sk_base_func_proto(enum bpf_func_id func_id)
+{
+	const struct bpf_func_proto *func;
+
+	switch (func_id) {
+	case BPF_FUNC_skc_to_tcp6_sock:
+		func = &bpf_skc_to_tcp6_sock_proto;
+		break;
+	case BPF_FUNC_skc_to_tcp_sock:
+		func = &bpf_skc_to_tcp_sock_proto;
+		break;
+	case BPF_FUNC_skc_to_tcp_timewait_sock:
+		func = &bpf_skc_to_tcp_timewait_sock_proto;
+		break;
+	case BPF_FUNC_skc_to_tcp_request_sock:
+		func = &bpf_skc_to_tcp_request_sock_proto;
+		break;
+	case BPF_FUNC_skc_to_udp6_sock:
+		func = &bpf_skc_to_udp6_sock_proto;
+		break;
+	default:
+		return bpf_base_func_proto(func_id);
+	}
+
+	if (!perfmon_capable())
+		return NULL;
+
+	return func;
+}
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 29806eb765cf..e21950a2c897 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -932,8 +932,14 @@ bool __skb_flow_dissect(const struct net *net,
 			int offset = 0;
 
 			ops = skb->dev->dsa_ptr->tag_ops;
-			if (ops->flow_dissect &&
-			    !ops->flow_dissect(skb, &proto, &offset)) {
+			/* Tail taggers don't break flow dissection */
+			if (!ops->tail_tag) {
+				if (ops->flow_dissect)
+					ops->flow_dissect(skb, &proto, &offset);
+				else
+					dsa_tag_generic_flow_dissect(skb,
+								     &proto,
+								     &offset);
 				hlen -= offset;
 				nhoff += offset;
 			}
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index efec66fa78b7..94fff0700bdd 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -1158,8 +1158,8 @@ static ssize_t traffic_class_show(struct netdev_queue *queue,
 	 * belongs to the root device it will be reported with just the
 	 * traffic class, so just "0" for TC 0 for example.
 	 */
-	return dev->num_tc < 0 ? sprintf(buf, "%u%d\n", tc, dev->num_tc) :
-				 sprintf(buf, "%u\n", tc);
+	return dev->num_tc < 0 ? sprintf(buf, "%d%d\n", tc, dev->num_tc) :
+				 sprintf(buf, "%d\n", tc);
 }
 
 #ifdef CONFIG_XPS
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index dcd61aca343e..dbc66b896287 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -19,6 +19,7 @@
 #include <linux/net_namespace.h>
 #include <linux/sched/task.h>
 #include <linux/uidgid.h>
+#include <linux/cookie.h>
 
 #include <net/sock.h>
 #include <net/netlink.h>
@@ -69,16 +70,16 @@ EXPORT_SYMBOL_GPL(pernet_ops_rwsem);
 
 static unsigned int max_gen_ptrs = INITIAL_NET_GEN_PTRS;
 
-static atomic64_t cookie_gen;
+DEFINE_COOKIE(net_cookie);
 
-u64 net_gen_cookie(struct net *net)
+u64 __net_gen_cookie(struct net *net)
 {
 	while (1) {
 		u64 res = atomic64_read(&net->net_cookie);
 
 		if (res)
 			return res;
-		res = atomic64_inc_return(&cookie_gen);
+		res = gen_cookie_next(&net_cookie);
 		atomic64_cmpxchg(&net->net_cookie, 0, res);
 	}
 }
@@ -251,10 +252,10 @@ int peernet2id_alloc(struct net *net, struct net *peer, gfp_t gfp)
 	if (refcount_read(&net->count) == 0)
 		return NETNSA_NSID_NOT_ASSIGNED;
 
-	spin_lock(&net->nsid_lock);
+	spin_lock_bh(&net->nsid_lock);
 	id = __peernet2id(net, peer);
 	if (id >= 0) {
-		spin_unlock(&net->nsid_lock);
+		spin_unlock_bh(&net->nsid_lock);
 		return id;
 	}
 
@@ -264,12 +265,12 @@ int peernet2id_alloc(struct net *net, struct net *peer, gfp_t gfp)
 	 * just been idr_remove()'d from there in cleanup_net().
 	 */
 	if (!maybe_get_net(peer)) {
-		spin_unlock(&net->nsid_lock);
+		spin_unlock_bh(&net->nsid_lock);
 		return NETNSA_NSID_NOT_ASSIGNED;
 	}
 
 	id = alloc_netid(net, peer, -1);
-	spin_unlock(&net->nsid_lock);
+	spin_unlock_bh(&net->nsid_lock);
 
 	put_net(peer);
 	if (id < 0)
@@ -534,20 +535,20 @@ static void unhash_nsid(struct net *net, struct net *last)
 	for_each_net(tmp) {
 		int id;
 
-		spin_lock(&tmp->nsid_lock);
+		spin_lock_bh(&tmp->nsid_lock);
 		id = __peernet2id(tmp, net);
 		if (id >= 0)
 			idr_remove(&tmp->netns_ids, id);
-		spin_unlock(&tmp->nsid_lock);
+		spin_unlock_bh(&tmp->nsid_lock);
 		if (id >= 0)
 			rtnl_net_notifyid(tmp, RTM_DELNSID, id, 0, NULL,
 					  GFP_KERNEL);
 		if (tmp == last)
 			break;
 	}
-	spin_lock(&net->nsid_lock);
+	spin_lock_bh(&net->nsid_lock);
 	idr_destroy(&net->netns_ids);
-	spin_unlock(&net->nsid_lock);
+	spin_unlock_bh(&net->nsid_lock);
 }
 
 static LLIST_HEAD(cleanup_list);
@@ -760,9 +761,9 @@ static int rtnl_net_newid(struct sk_buff *skb, struct nlmsghdr *nlh,
 		return PTR_ERR(peer);
 	}
 
-	spin_lock(&net->nsid_lock);
+	spin_lock_bh(&net->nsid_lock);
 	if (__peernet2id(net, peer) >= 0) {
-		spin_unlock(&net->nsid_lock);
+		spin_unlock_bh(&net->nsid_lock);
 		err = -EEXIST;
 		NL_SET_BAD_ATTR(extack, nla);
 		NL_SET_ERR_MSG(extack,
@@ -771,7 +772,7 @@ static int rtnl_net_newid(struct sk_buff *skb, struct nlmsghdr *nlh,
 	}
 
 	err = alloc_netid(net, peer, nsid);
-	spin_unlock(&net->nsid_lock);
+	spin_unlock_bh(&net->nsid_lock);
 	if (err >= 0) {
 		rtnl_net_notifyid(net, RTM_NEWNSID, err, NETLINK_CB(skb).portid,
 				  nlh, GFP_KERNEL);
@@ -1101,7 +1102,10 @@ static int __init net_ns_init(void)
 		panic("Could not allocate generic netns");
 
 	rcu_assign_pointer(init_net.gen, ng);
-	net_gen_cookie(&init_net);
+
+	preempt_disable();
+	__net_gen_cookie(&init_net);
+	preempt_enable();
 
 	down_write(&pernet_ops_rwsem);
 	if (setup_net(&init_net, &init_user_ns))
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 44fdbb9c6e53..105978604ffd 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -922,7 +922,7 @@ static ssize_t pktgen_if_write(struct file *file,
 			pkt_dev->min_pkt_size = value;
 			pkt_dev->cur_pkt_size = value;
 		}
-		sprintf(pg_result, "OK: min_pkt_size=%u",
+		sprintf(pg_result, "OK: min_pkt_size=%d",
 			pkt_dev->min_pkt_size);
 		return count;
 	}
@@ -939,7 +939,7 @@ static ssize_t pktgen_if_write(struct file *file,
 			pkt_dev->max_pkt_size = value;
 			pkt_dev->cur_pkt_size = value;
 		}
-		sprintf(pg_result, "OK: max_pkt_size=%u",
+		sprintf(pg_result, "OK: max_pkt_size=%d",
 			pkt_dev->max_pkt_size);
 		return count;
 	}
@@ -959,7 +959,7 @@ static ssize_t pktgen_if_write(struct file *file,
 			pkt_dev->max_pkt_size = value;
 			pkt_dev->cur_pkt_size = value;
 		}
-		sprintf(pg_result, "OK: pkt_size=%u", pkt_dev->min_pkt_size);
+		sprintf(pg_result, "OK: pkt_size=%d", pkt_dev->min_pkt_size);
 		return count;
 	}
 
@@ -981,7 +981,7 @@ static ssize_t pktgen_if_write(struct file *file,
 
 		i += len;
 		pkt_dev->nfrags = value;
-		sprintf(pg_result, "OK: frags=%u", pkt_dev->nfrags);
+		sprintf(pg_result, "OK: frags=%d", pkt_dev->nfrags);
 		return count;
 	}
 	if (!strcmp(name, "delay")) {
@@ -1146,7 +1146,7 @@ static ssize_t pktgen_if_write(struct file *file,
 		     (!(pkt_dev->odev->priv_flags & IFF_TX_SKB_SHARING)))))
 			return -ENOTSUPP;
 		pkt_dev->burst = value < 1 ? 1 : value;
-		sprintf(pg_result, "OK: burst=%d", pkt_dev->burst);
+		sprintf(pg_result, "OK: burst=%u", pkt_dev->burst);
 		return count;
 	}
 	if (!strcmp(name, "node")) {
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index e0774471f56d..75b043accddb 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5558,6 +5558,73 @@ int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci)
 }
 EXPORT_SYMBOL(skb_vlan_push);
 
+/**
+ * skb_eth_pop() - Drop the Ethernet header at the head of a packet
+ *
+ * @skb: Socket buffer to modify
+ *
+ * Drop the Ethernet header of @skb.
+ *
+ * Expects that skb->data points to the mac header and that no VLAN tags are
+ * present.
+ *
+ * Returns 0 on success, -errno otherwise.
+ */
+int skb_eth_pop(struct sk_buff *skb)
+{
+	if (!pskb_may_pull(skb, ETH_HLEN) || skb_vlan_tagged(skb) ||
+	    skb_network_offset(skb) < ETH_HLEN)
+		return -EPROTO;
+
+	skb_pull_rcsum(skb, ETH_HLEN);
+	skb_reset_mac_header(skb);
+	skb_reset_mac_len(skb);
+
+	return 0;
+}
+EXPORT_SYMBOL(skb_eth_pop);
+
+/**
+ * skb_eth_push() - Add a new Ethernet header at the head of a packet
+ *
+ * @skb: Socket buffer to modify
+ * @dst: Destination MAC address of the new header
+ * @src: Source MAC address of the new header
+ *
+ * Prepend @skb with a new Ethernet header.
+ *
+ * Expects that skb->data points to the mac header, which must be empty.
+ *
+ * Returns 0 on success, -errno otherwise.
+ */
+int skb_eth_push(struct sk_buff *skb, const unsigned char *dst,
+		 const unsigned char *src)
+{
+	struct ethhdr *eth;
+	int err;
+
+	if (skb_network_offset(skb) || skb_vlan_tag_present(skb))
+		return -EPROTO;
+
+	err = skb_cow_head(skb, sizeof(*eth));
+	if (err < 0)
+		return err;
+
+	skb_push(skb, sizeof(*eth));
+	skb_reset_mac_header(skb);
+	skb_reset_mac_len(skb);
+
+	eth = eth_hdr(skb);
+	ether_addr_copy(eth->h_dest, dst);
+	ether_addr_copy(eth->h_source, src);
+	eth->h_proto = skb->protocol;
+
+	skb_postpush_rcsum(skb, eth, sizeof(*eth));
+
+	return 0;
+}
+EXPORT_SYMBOL(skb_eth_push);
+
 /* Update the ethertype of hdr and the skb csum value if required. */
 static void skb_mod_eth_type(struct sk_buff *skb, struct ethhdr *hdr,
 			     __be16 ethertype)
diff --git a/net/core/sock.c b/net/core/sock.c
index ba9e7d91e2ef..d9a537e6876a 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2947,6 +2947,13 @@ void sk_stop_timer(struct sock *sk, struct timer_list* timer)
 }
 EXPORT_SYMBOL(sk_stop_timer);
 
+void sk_stop_timer_sync(struct sock *sk, struct timer_list *timer)
+{
+	if (del_timer_sync(timer))
+		__sock_put(sk);
+}
+EXPORT_SYMBOL(sk_stop_timer_sync);
+
 void sock_init_data(struct socket *sock, struct sock *sk)
 {
 	sk_init_common(sk);
diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c
index c13ffbd33d8d..c9c45b935f99 100644
--- a/net/core/sock_diag.c
+++ b/net/core/sock_diag.c
@@ -11,7 +11,7 @@
 #include <linux/tcp.h>
 #include <linux/workqueue.h>
 #include <linux/nospec.h>
-
+#include <linux/cookie.h>
 #include <linux/inet_diag.h>
 #include <linux/sock_diag.h>
 
@@ -19,16 +19,17 @@ static const struct sock_diag_handler *sock_diag_handlers[AF_MAX];
 static int (*inet_rcv_compat)(struct sk_buff *skb, struct nlmsghdr *nlh);
 static DEFINE_MUTEX(sock_diag_table_mutex);
 static struct workqueue_struct *broadcast_wq;
-static atomic64_t cookie_gen;
 
-u64 sock_gen_cookie(struct sock *sk)
+DEFINE_COOKIE(sock_cookie);
+
+u64 __sock_gen_cookie(struct sock *sk)
 {
 	while (1) {
 		u64 res = atomic64_read(&sk->sk_cookie);
 
 		if (res)
 			return res;
-		res = atomic64_inc_return(&cookie_gen);
+		res = gen_cookie_next(&sock_cookie);
 		atomic64_cmpxchg(&sk->sk_cookie, 0, res);
 	}
 }
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 078386d7d9a2..e83a80e8f13b 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -2,6 +2,7 @@
 /* Copyright (c) 2017 - 2018 Covalent IO, Inc. http://covalent.io */
 
 #include <linux/bpf.h>
+#include <linux/btf_ids.h>
 #include <linux/filter.h>
 #include <linux/errno.h>
 #include <linux/file.h>
@@ -382,7 +383,7 @@ static void *sock_map_lookup(struct bpf_map *map, void *key)
 	struct sock *sk;
 
 	sk = __sock_map_lookup_elem(map, *(u32 *)key);
-	if (!sk || !sk_fullsock(sk))
+	if (!sk)
 		return NULL;
 	if (sk_is_refcounted(sk) && !refcount_inc_not_zero(&sk->sk_refcnt))
 		return NULL;
@@ -400,7 +401,7 @@ static void *sock_map_lookup_sys(struct bpf_map *map, void *key)
 	if (!sk)
 		return ERR_PTR(-ENOENT);
 
-	sock_gen_cookie(sk);
+	__sock_gen_cookie(sk);
 	return &sk->sk_cookie;
 }
 
@@ -609,6 +610,9 @@ static int sock_map_update_elem(struct bpf_map *map, void *key,
 	struct sock *sk = (struct sock *)value;
 	int ret;
 
+	if (unlikely(!sk || !sk_fullsock(sk)))
+		return -EINVAL;
+
 	if (!sock_map_sk_is_suitable(sk))
 		return -EOPNOTSUPP;
 
@@ -703,6 +707,109 @@ const struct bpf_func_proto bpf_msg_redirect_map_proto = {
 	.arg4_type      = ARG_ANYTHING,
 };
 
+struct sock_map_seq_info {
+	struct bpf_map *map;
+	struct sock *sk;
+	u32 index;
+};
+
+struct bpf_iter__sockmap {
+	__bpf_md_ptr(struct bpf_iter_meta *, meta);
+	__bpf_md_ptr(struct bpf_map *, map);
+	__bpf_md_ptr(void *, key);
+	__bpf_md_ptr(struct sock *, sk);
+};
+
+DEFINE_BPF_ITER_FUNC(sockmap, struct bpf_iter_meta *meta,
+		     struct bpf_map *map, void *key,
+		     struct sock *sk)
+
+static void *sock_map_seq_lookup_elem(struct sock_map_seq_info *info)
+{
+	if (unlikely(info->index >= info->map->max_entries))
+		return NULL;
+
+	info->sk = __sock_map_lookup_elem(info->map, info->index);
+
+	/* can't return sk directly, since that might be NULL */
+	return info;
+}
+
+static void *sock_map_seq_start(struct seq_file *seq, loff_t *pos)
+{
+	struct sock_map_seq_info *info = seq->private;
+
+	if (*pos == 0)
+		++*pos;
+
+	/* pairs with sock_map_seq_stop */
+	rcu_read_lock();
+	return sock_map_seq_lookup_elem(info);
+}
+
+static void *sock_map_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	struct sock_map_seq_info *info = seq->private;
+
+	++*pos;
+	++info->index;
+
+	return sock_map_seq_lookup_elem(info);
+}
+
+static int sock_map_seq_show(struct seq_file *seq, void *v)
+{
+	struct sock_map_seq_info *info = seq->private;
+	struct bpf_iter__sockmap ctx = {};
+	struct bpf_iter_meta meta;
+	struct bpf_prog *prog;
+
+	meta.seq = seq;
+	prog = bpf_iter_get_info(&meta, !v);
+	if (!prog)
+		return 0;
+
+	ctx.meta = &meta;
+	ctx.map = info->map;
+	if (v) {
+		ctx.key = &info->index;
+		ctx.sk = info->sk;
+	}
+
+	return bpf_iter_run_prog(prog, &ctx);
+}
+
+static void sock_map_seq_stop(struct seq_file *seq, void *v)
+{
+	if (!v)
+		(void)sock_map_seq_show(seq, NULL);
+
+	/* pairs with sock_map_seq_start */
+	rcu_read_unlock();
+}
+
+static const struct seq_operations sock_map_seq_ops = {
+	.start	= sock_map_seq_start,
+	.next	= sock_map_seq_next,
+	.stop	= sock_map_seq_stop,
+	.show	= sock_map_seq_show,
+};
+
+static int sock_map_init_seq_private(void *priv_data,
+				     struct bpf_iter_aux_info *aux)
+{
+	struct sock_map_seq_info *info = priv_data;
+
+	info->map = aux->map;
+	return 0;
+}
+
+static const struct bpf_iter_seq_info sock_map_iter_seq_info = {
+	.seq_ops		= &sock_map_seq_ops,
+	.init_seq_private	= sock_map_init_seq_private,
+	.seq_priv_size		= sizeof(struct sock_map_seq_info),
+};
+
 static int sock_map_btf_id;
 const struct bpf_map_ops sock_map_ops = {
 	.map_meta_equal		= bpf_map_meta_equal,
@@ -717,6 +824,7 @@ const struct bpf_map_ops sock_map_ops = {
 	.map_check_btf		= map_check_no_btf,
 	.map_btf_name		= "bpf_stab",
 	.map_btf_id		= &sock_map_btf_id,
+	.iter_seq_info		= &sock_map_iter_seq_info,
 };
 
 struct bpf_shtab_elem {
@@ -953,7 +1061,7 @@ static int sock_hash_get_next_key(struct bpf_map *map, void *key,
 	if (!elem)
 		goto find_first_elem;
 
-	elem_next = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(&elem->node)),
+	elem_next = hlist_entry_safe(rcu_dereference(hlist_next_rcu(&elem->node)),
 				     struct bpf_shtab_elem, node);
 	if (elem_next) {
 		memcpy(key_next, elem_next->key, key_size);
@@ -965,7 +1073,7 @@ static int sock_hash_get_next_key(struct bpf_map *map, void *key,
 find_first_elem:
 	for (; i < htab->buckets_num; i++) {
 		head = &sock_hash_select_bucket(htab, i)->head;
-		elem_next = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)),
+		elem_next = hlist_entry_safe(rcu_dereference(hlist_first_rcu(head)),
 					     struct bpf_shtab_elem, node);
 		if (elem_next) {
 			memcpy(key_next, elem_next->key, key_size);
@@ -1101,7 +1209,7 @@ static void *sock_hash_lookup_sys(struct bpf_map *map, void *key)
 	if (!sk)
 		return ERR_PTR(-ENOENT);
 
-	sock_gen_cookie(sk);
+	__sock_gen_cookie(sk);
 	return &sk->sk_cookie;
 }
 
@@ -1110,7 +1218,7 @@ static void *sock_hash_lookup(struct bpf_map *map, void *key)
 	struct sock *sk;
 
 	sk = __sock_hash_lookup_elem(map, key);
-	if (!sk || !sk_fullsock(sk))
+	if (!sk)
 		return NULL;
 	if (sk_is_refcounted(sk) && !refcount_inc_not_zero(&sk->sk_refcnt))
 		return NULL;
@@ -1199,6 +1307,117 @@ const struct bpf_func_proto bpf_msg_redirect_hash_proto = {
 	.arg4_type      = ARG_ANYTHING,
 };
 
+struct sock_hash_seq_info {
+	struct bpf_map *map;
+	struct bpf_shtab *htab;
+	u32 bucket_id;
+};
+
+static void *sock_hash_seq_find_next(struct sock_hash_seq_info *info,
+				     struct bpf_shtab_elem *prev_elem)
+{
+	const struct bpf_shtab *htab = info->htab;
+	struct bpf_shtab_bucket *bucket;
+	struct bpf_shtab_elem *elem;
+	struct hlist_node *node;
+
+	/* try to find next elem in the same bucket */
+	if (prev_elem) {
+		node = rcu_dereference(hlist_next_rcu(&prev_elem->node));
+		elem = hlist_entry_safe(node, struct bpf_shtab_elem, node);
+		if (elem)
+			return elem;
+
+		/* no more elements, continue in the next bucket */
+		info->bucket_id++;
+	}
+
+	for (; info->bucket_id < htab->buckets_num; info->bucket_id++) {
+		bucket = &htab->buckets[info->bucket_id];
+		node = rcu_dereference(hlist_first_rcu(&bucket->head));
+		elem = hlist_entry_safe(node, struct bpf_shtab_elem, node);
+		if (elem)
+			return elem;
+	}
+
+	return NULL;
+}
+
+static void *sock_hash_seq_start(struct seq_file *seq, loff_t *pos)
+{
+	struct sock_hash_seq_info *info = seq->private;
+
+	if (*pos == 0)
+		++*pos;
+
+	/* pairs with sock_hash_seq_stop */
+	rcu_read_lock();
+	return sock_hash_seq_find_next(info, NULL);
+}
+
+static void *sock_hash_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	struct sock_hash_seq_info *info = seq->private;
+
+	++*pos;
+	return sock_hash_seq_find_next(info, v);
+}
+
+static int sock_hash_seq_show(struct seq_file *seq, void *v)
+{
+	struct sock_hash_seq_info *info = seq->private;
+	struct bpf_iter__sockmap ctx = {};
+	struct bpf_shtab_elem *elem = v;
+	struct bpf_iter_meta meta;
+	struct bpf_prog *prog;
+
+	meta.seq = seq;
+	prog = bpf_iter_get_info(&meta, !elem);
+	if (!prog)
+		return 0;
+
+	ctx.meta = &meta;
+	ctx.map = info->map;
+	if (elem) {
+		ctx.key = elem->key;
+		ctx.sk = elem->sk;
+	}
+
+	return bpf_iter_run_prog(prog, &ctx);
+}
+
+static void sock_hash_seq_stop(struct seq_file *seq, void *v)
+{
+	if (!v)
+		(void)sock_hash_seq_show(seq, NULL);
+
+	/* pairs with sock_hash_seq_start */
+	rcu_read_unlock();
+}
+
+static const struct seq_operations sock_hash_seq_ops = {
+	.start	= sock_hash_seq_start,
+	.next	= sock_hash_seq_next,
+	.stop	= sock_hash_seq_stop,
+	.show	= sock_hash_seq_show,
+};
+
+static int sock_hash_init_seq_private(void *priv_data,
+				     struct bpf_iter_aux_info *aux)
+{
+	struct sock_hash_seq_info *info = priv_data;
+
+	info->map = aux->map;
+	info->htab = container_of(aux->map, struct bpf_shtab, map);
+	return 0;
+}
+
+static const struct bpf_iter_seq_info sock_hash_iter_seq_info = {
+	.seq_ops		= &sock_hash_seq_ops,
+	.init_seq_private	= sock_hash_init_seq_private,
+	.seq_priv_size		= sizeof(struct sock_hash_seq_info),
+};
+
 static int sock_hash_map_btf_id;
 const struct bpf_map_ops sock_hash_ops = {
 	.map_meta_equal		= bpf_map_meta_equal,
@@ -1213,6 +1432,7 @@ const struct bpf_map_ops sock_hash_ops = {
 	.map_check_btf		= map_check_no_btf,
 	.map_btf_name		= "bpf_shtab",
 	.map_btf_id		= &sock_hash_map_btf_id,
+	.iter_seq_info		= &sock_hash_iter_seq_info,
 };
 
 static struct sk_psock_progs *sock_map_progs(struct bpf_map *map)
@@ -1323,3 +1543,62 @@ void sock_map_close(struct sock *sk, long timeout)
 	release_sock(sk);
 	saved_close(sk, timeout);
 }
+
+static int sock_map_iter_attach_target(struct bpf_prog *prog,
+				       union bpf_iter_link_info *linfo,
+				       struct bpf_iter_aux_info *aux)
+{
+	struct bpf_map *map;
+	int err = -EINVAL;
+
+	if (!linfo->map.map_fd)
+		return -EBADF;
+
+	map = bpf_map_get_with_uref(linfo->map.map_fd);
+	if (IS_ERR(map))
+		return PTR_ERR(map);
+
+	if (map->map_type != BPF_MAP_TYPE_SOCKMAP &&
+	    map->map_type != BPF_MAP_TYPE_SOCKHASH)
+		goto put_map;
+
+	if (prog->aux->max_rdonly_access > map->key_size) {
+		err = -EACCES;
+		goto put_map;
+	}
+
+	aux->map = map;
+	return 0;
+
+put_map:
+	bpf_map_put_with_uref(map);
+	return err;
+}
+
+static void sock_map_iter_detach_target(struct bpf_iter_aux_info *aux)
+{
+	bpf_map_put_with_uref(aux->map);
+}
+
+static struct bpf_iter_reg sock_map_iter_reg = {
+	.target			= "sockmap",
+	.attach_target		= sock_map_iter_attach_target,
+	.detach_target		= sock_map_iter_detach_target,
+	.show_fdinfo		= bpf_iter_map_show_fdinfo,
+	.fill_link_info		= bpf_iter_map_fill_link_info,
+	.ctx_arg_info_size	= 2,
+	.ctx_arg_info		= {
+		{ offsetof(struct bpf_iter__sockmap, key),
+		  PTR_TO_RDONLY_BUF_OR_NULL },
+		{ offsetof(struct bpf_iter__sockmap, sk),
+		  PTR_TO_BTF_ID_OR_NULL },
+	},
+};
+
+static int __init bpf_sockmap_iter_init(void)
+{
+	sock_map_iter_reg.ctx_arg_info[1].btf_id =
+		btf_sock_ids[BTF_SOCK_TYPE_SOCK];
+	return bpf_iter_reg_target(&sock_map_iter_reg);
+}
+late_initcall(bpf_sockmap_iter_init);
diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c
index 84dde5a2066e..16014ad19406 100644
--- a/net/dcb/dcbnl.c
+++ b/net/dcb/dcbnl.c
@@ -1426,6 +1426,7 @@ static int dcbnl_ieee_set(struct net_device *netdev, struct nlmsghdr *nlh,
 {
 	const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops;
 	struct nlattr *ieee[DCB_ATTR_IEEE_MAX + 1];
+	int prio;
 	int err;
 
 	if (!ops)
@@ -1475,6 +1476,13 @@ static int dcbnl_ieee_set(struct net_device *netdev, struct nlmsghdr *nlh,
 		struct dcbnl_buffer *buffer =
 			nla_data(ieee[DCB_ATTR_DCB_BUFFER]);
 
+		for (prio = 0; prio < ARRAY_SIZE(buffer->prio2buffer); prio++) {
+			if (buffer->prio2buffer[prio] >= DCBX_MAX_BUFFERS) {
+				err = -EINVAL;
+				goto err;
+			}
+		}
+
 		err = ops->dcbnl_setbuffer(netdev, buffer);
 		if (err)
 			goto err;
diff --git a/net/dccp/timer.c b/net/dccp/timer.c
index 927c796d7682..a934d2932373 100644
--- a/net/dccp/timer.c
+++ b/net/dccp/timer.c
@@ -176,7 +176,6 @@ static void dccp_delack_timer(struct timer_list *t)
 	bh_lock_sock(sk);
 	if (sock_owned_by_user(sk)) {
 		/* Try again later. */
-		icsk->icsk_ack.blocked = 1;
 		__NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOCKED);
 		sk_reset_timer(sk, &icsk->icsk_delack_timer,
 			       jiffies + TCP_DELACK_MIN);
diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index 5c18c0214aac..dec4ab59b7c4 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -225,6 +225,15 @@ static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev,
 	skb->pkt_type = PACKET_HOST;
 	skb->protocol = eth_type_trans(skb, skb->dev);
 
+	if (unlikely(cpu_dp->ds->untag_bridge_pvid)) {
+		nskb = dsa_untag_bridge_pvid(skb);
+		if (!nskb) {
+			kfree_skb(skb);
+			return 0;
+		}
+		skb = nskb;
+	}
+
 	s = this_cpu_ptr(p->stats64);
 	u64_stats_update_begin(&s->syncp);
 	s->rx_packets++;
diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h
index 2da656d984ef..12998bf04e55 100644
--- a/net/dsa/dsa_priv.h
+++ b/net/dsa/dsa_priv.h
@@ -7,6 +7,7 @@
 #ifndef __DSA_PRIV_H
 #define __DSA_PRIV_H
 
+#include <linux/if_bridge.h>
 #include <linux/phy.h>
 #include <linux/netdevice.h>
 #include <linux/netpoll.h>
@@ -194,6 +195,65 @@ dsa_slave_to_master(const struct net_device *dev)
 	return dp->cpu_dp->master;
 }
 
+/* If under a bridge with vlan_filtering=0, make sure to send pvid-tagged
+ * frames as untagged, since the bridge will not untag them.
+ */
+static inline struct sk_buff *dsa_untag_bridge_pvid(struct sk_buff *skb)
+{
+	struct dsa_port *dp = dsa_slave_to_port(skb->dev);
+	struct net_device *br = dp->bridge_dev;
+	struct net_device *dev = skb->dev;
+	struct net_device *upper_dev;
+	u16 vid, pvid, proto;
+	int err;
+
+	if (!br || br_vlan_enabled(br))
+		return skb;
+
+	err = br_vlan_get_proto(br, &proto);
+	if (err)
+		return skb;
+
+	/* Move VLAN tag from data to hwaccel */
+	if (!skb_vlan_tag_present(skb) && skb->protocol == htons(proto)) {
+		skb = skb_vlan_untag(skb);
+		if (!skb)
+			return NULL;
+	}
+
+	if (!skb_vlan_tag_present(skb))
+		return skb;
+
+	vid = skb_vlan_tag_get_id(skb);
+
+	/* We already run under an RCU read-side critical section since
+	 * we are called from netif_receive_skb_list_internal().
+	 */
+	err = br_vlan_get_pvid_rcu(dev, &pvid);
+	if (err)
+		return skb;
+
+	if (vid != pvid)
+		return skb;
+
+	/* The sad part about attempting to untag from DSA is that we
+	 * don't know, unless we check, if the skb will end up in
+	 * the bridge's data path - br_allowed_ingress() - or not.
+	 * For example, there might be an 8021q upper for the
+	 * default_pvid of the bridge, which will steal VLAN-tagged traffic
+	 * from the bridge's data path. This is a configuration that DSA
+	 * supports because vlan_filtering is 0. In that case, we should
+	 * definitely keep the tag, to make sure it keeps working.
+	 */
+	upper_dev = __vlan_find_dev_deep_rcu(br, htons(proto), vid);
+	if (upper_dev)
+		return skb;
+
+	__vlan_hwaccel_clear_tag(skb);
+
+	return skb;
+}
+
 /* switch.c */
 int dsa_switch_register_notifier(struct dsa_switch *ds);
 void dsa_switch_unregister_notifier(struct dsa_switch *ds);
diff --git a/net/dsa/master.c b/net/dsa/master.c
index 61615ebc70e9..c91de041a91d 100644
--- a/net/dsa/master.c
+++ b/net/dsa/master.c
@@ -259,6 +259,18 @@ static void dsa_netdev_ops_set(struct net_device *dev,
 	dev->dsa_ptr->netdev_ops = ops;
 }
 
+static void dsa_master_set_promiscuity(struct net_device *dev, int inc)
+{
+	const struct dsa_device_ops *ops = dev->dsa_ptr->tag_ops;
+
+	if (!ops->promisc_on_master)
+		return;
+
+	rtnl_lock();
+	dev_set_promiscuity(dev, inc);
+	rtnl_unlock();
+}
+
 static ssize_t tagging_show(struct device *d, struct device_attribute *attr,
 			    char *buf)
 {
@@ -314,9 +326,12 @@ int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp)
 	dev->dsa_ptr = cpu_dp;
 	lockdep_set_class(&dev->addr_list_lock,
 			  &dsa_master_addr_list_lock_key);
+
+	dsa_master_set_promiscuity(dev, 1);
+
 	ret = dsa_master_ethtool_setup(dev);
 	if (ret)
-		return ret;
+		goto out_err_reset_promisc;
 
 	dsa_netdev_ops_set(dev, &dsa_netdev_ops);
 
@@ -329,6 +344,8 @@ int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp)
 out_err_ndo_teardown:
 	dsa_netdev_ops_set(dev, NULL);
 	dsa_master_ethtool_teardown(dev);
+out_err_reset_promisc:
+	dsa_master_set_promiscuity(dev, -1);
 	return ret;
 }
 
@@ -338,6 +355,7 @@ void dsa_master_teardown(struct net_device *dev)
 	dsa_netdev_ops_set(dev, NULL);
 	dsa_master_ethtool_teardown(dev);
 	dsa_master_reset_mtu(dev);
+	dsa_master_set_promiscuity(dev, -1);
 
 	dev->dsa_ptr = NULL;
 
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 2d52bfba110a..e7c1d62fde99 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -1854,15 +1854,27 @@ int dsa_slave_create(struct dsa_port *port)
 
 	dsa_slave_notify(slave_dev, DSA_PORT_REGISTER);
 
-	ret = register_netdev(slave_dev);
+	rtnl_lock();
+
+	ret = register_netdevice(slave_dev);
 	if (ret) {
 		netdev_err(master, "error %d registering interface %s\n",
 			   ret, slave_dev->name);
+		rtnl_unlock();
 		goto out_phy;
 	}
 
+	ret = netdev_upper_dev_link(master, slave_dev, NULL);
+
+	rtnl_unlock();
+
+	if (ret)
+		goto out_unregister;
+
 	return 0;
 
+out_unregister:
+	unregister_netdev(slave_dev);
 out_phy:
 	rtnl_lock();
 	phylink_disconnect_phy(p->dp->pl);
@@ -1879,16 +1891,18 @@ out_free:
 
 void dsa_slave_destroy(struct net_device *slave_dev)
 {
+	struct net_device *master = dsa_slave_to_master(slave_dev);
 	struct dsa_port *dp = dsa_slave_to_port(slave_dev);
 	struct dsa_slave_priv *p = netdev_priv(slave_dev);
 
 	netif_carrier_off(slave_dev);
 	rtnl_lock();
+	netdev_upper_dev_unlink(master, slave_dev);
+	unregister_netdevice(slave_dev);
 	phylink_disconnect_phy(dp->pl);
 	rtnl_unlock();
 
 	dsa_slave_notify(slave_dev, DSA_PORT_UNREGISTER);
-	unregister_netdev(slave_dev);
 	phylink_destroy(dp->pl);
 	gro_cells_destroy(&p->gcells);
 	free_percpu(p->stats64);
diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c
index cc8512b5f9e2..ad72dff8d524 100644
--- a/net/dsa/tag_brcm.c
+++ b/net/dsa/tag_brcm.c
@@ -107,6 +107,18 @@ static struct sk_buff *brcm_tag_xmit_ll(struct sk_buff *skb,
 	return skb;
 }
 
+/* Frames with this tag have one of these two layouts:
+ * -----------------------------------
+ * | MAC DA | MAC SA | 4b tag | Type | DSA_TAG_PROTO_BRCM
+ * -----------------------------------
+ * -----------------------------------
+ * | 4b tag | MAC DA | MAC SA | Type | DSA_TAG_PROTO_BRCM_PREPEND
+ * -----------------------------------
+ * In both cases, at receive time, skb->data points 2 bytes before the actual
+ * Ethernet type field and we have an offset of 4bytes between where skb->data
+ * and where the payload starts. So the same low-level receive function can be
+ * used.
+ */
 static struct sk_buff *brcm_tag_rcv_ll(struct sk_buff *skb,
 				       struct net_device *dev,
 				       struct packet_type *pt,
@@ -144,27 +156,6 @@ static struct sk_buff *brcm_tag_rcv_ll(struct sk_buff *skb,
 
 	return skb;
 }
-
-static int brcm_tag_flow_dissect(const struct sk_buff *skb, __be16 *proto,
-				 int *offset)
-{
-	/* We have been called on the DSA master network device after
-	 * eth_type_trans() which pulled the Ethernet header already.
-	 * Frames have one of these two layouts:
-	 * -----------------------------------
-	 * | MAC DA | MAC SA | 4b tag | Type | DSA_TAG_PROTO_BRCM
-	 * -----------------------------------
-	 * -----------------------------------
-	 * | 4b tag | MAC DA | MAC SA | Type | DSA_TAG_PROTO_BRCM_PREPEND
-	 * -----------------------------------
-	 * skb->data points 2 bytes before the actual Ethernet type field and
-	 * we have an offset of 4bytes between where skb->data and where the
-	 * payload starts.
-	 */
-	*offset = BRCM_TAG_LEN;
-	*proto = ((__be16 *)skb->data)[1];
-	return 0;
-}
 #endif
 
 #if IS_ENABLED(CONFIG_NET_DSA_TAG_BRCM)
@@ -200,7 +191,6 @@ static const struct dsa_device_ops brcm_netdev_ops = {
 	.xmit	= brcm_tag_xmit,
 	.rcv	= brcm_tag_rcv,
 	.overhead = BRCM_TAG_LEN,
-	.flow_dissect = brcm_tag_flow_dissect,
 };
 
 DSA_TAG_DRIVER(brcm_netdev_ops);
@@ -229,7 +219,6 @@ static const struct dsa_device_ops brcm_prepend_netdev_ops = {
 	.xmit	= brcm_tag_xmit_prepend,
 	.rcv	= brcm_tag_rcv_prepend,
 	.overhead = BRCM_TAG_LEN,
-	.flow_dissect = brcm_tag_flow_dissect,
 };
 
 DSA_TAG_DRIVER(brcm_prepend_netdev_ops);
diff --git a/net/dsa/tag_dsa.c b/net/dsa/tag_dsa.c
index 7ddec9794477..0b756fae68a5 100644
--- a/net/dsa/tag_dsa.c
+++ b/net/dsa/tag_dsa.c
@@ -142,20 +142,11 @@ static struct sk_buff *dsa_rcv(struct sk_buff *skb, struct net_device *dev,
 	return skb;
 }
 
-static int dsa_tag_flow_dissect(const struct sk_buff *skb, __be16 *proto,
-				int *offset)
-{
-	*offset = 4;
-	*proto = ((__be16 *)skb->data)[1];
-	return 0;
-}
-
 static const struct dsa_device_ops dsa_netdev_ops = {
 	.name	= "dsa",
 	.proto	= DSA_TAG_PROTO_DSA,
 	.xmit	= dsa_xmit,
 	.rcv	= dsa_rcv,
-	.flow_dissect   = dsa_tag_flow_dissect,
 	.overhead = DSA_HLEN,
 };
 
diff --git a/net/dsa/tag_edsa.c b/net/dsa/tag_edsa.c
index d6200ff98200..120614240319 100644
--- a/net/dsa/tag_edsa.c
+++ b/net/dsa/tag_edsa.c
@@ -192,20 +192,11 @@ static struct sk_buff *edsa_rcv(struct sk_buff *skb, struct net_device *dev,
 	return skb;
 }
 
-static int edsa_tag_flow_dissect(const struct sk_buff *skb, __be16 *proto,
-				 int *offset)
-{
-	*offset = 8;
-	*proto = ((__be16 *)skb->data)[3];
-	return 0;
-}
-
 static const struct dsa_device_ops edsa_netdev_ops = {
 	.name	= "edsa",
 	.proto	= DSA_TAG_PROTO_EDSA,
 	.xmit	= edsa_xmit,
 	.rcv	= edsa_rcv,
-	.flow_dissect   = edsa_tag_flow_dissect,
 	.overhead = EDSA_HLEN,
 };
 
diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c
index bd1a3158d79a..945a9bd5ba35 100644
--- a/net/dsa/tag_ksz.c
+++ b/net/dsa/tag_ksz.c
@@ -237,6 +237,7 @@ static const struct dsa_device_ops ksz9893_netdev_ops = {
 	.xmit	= ksz9893_xmit,
 	.rcv	= ksz9477_rcv,
 	.overhead = KSZ_INGRESS_TAG_LEN,
+	.tail_tag = true,
 };
 
 DSA_TAG_DRIVER(ksz9893_netdev_ops);
diff --git a/net/dsa/tag_mtk.c b/net/dsa/tag_mtk.c
index f602fc758d68..4cdd9cf428fb 100644
--- a/net/dsa/tag_mtk.c
+++ b/net/dsa/tag_mtk.c
@@ -105,21 +105,11 @@ static struct sk_buff *mtk_tag_rcv(struct sk_buff *skb, struct net_device *dev,
 	return skb;
 }
 
-static int mtk_tag_flow_dissect(const struct sk_buff *skb, __be16 *proto,
-				int *offset)
-{
-	*offset = 4;
-	*proto = ((__be16 *)skb->data)[1];
-
-	return 0;
-}
-
 static const struct dsa_device_ops mtk_netdev_ops = {
 	.name		= "mtk",
 	.proto		= DSA_TAG_PROTO_MTK,
 	.xmit		= mtk_tag_xmit,
 	.rcv		= mtk_tag_rcv,
-	.flow_dissect	= mtk_tag_flow_dissect,
 	.overhead	= MTK_HDR_LEN,
 };
 
diff --git a/net/dsa/tag_ocelot.c b/net/dsa/tag_ocelot.c
index 42f327c06dca..ec16badb7812 100644
--- a/net/dsa/tag_ocelot.c
+++ b/net/dsa/tag_ocelot.c
@@ -137,13 +137,16 @@ static struct sk_buff *ocelot_xmit(struct sk_buff *skb,
 				   struct net_device *netdev)
 {
 	struct dsa_port *dp = dsa_slave_to_port(netdev);
+	struct sk_buff *clone = DSA_SKB_CB(skb)->clone;
 	struct dsa_switch *ds = dp->ds;
 	struct ocelot *ocelot = ds->priv;
 	struct ocelot_port *ocelot_port;
+	u8 *prefix, *injection;
 	u64 qos_class, rew_op;
-	u8 *injection;
+	int err;
 
-	if (unlikely(skb_cow_head(skb, OCELOT_TAG_LEN) < 0)) {
+	err = skb_cow_head(skb, OCELOT_TOTAL_TAG_LEN);
+	if (unlikely(err < 0)) {
 		netdev_err(netdev, "Cannot make room for tag.\n");
 		return NULL;
 	}
@@ -152,19 +155,24 @@ static struct sk_buff *ocelot_xmit(struct sk_buff *skb,
 
 	injection = skb_push(skb, OCELOT_TAG_LEN);
 
-	memcpy(injection, ocelot_port->xmit_template, OCELOT_TAG_LEN);
+	prefix = skb_push(skb, OCELOT_SHORT_PREFIX_LEN);
+
+	memcpy(prefix, ocelot_port->xmit_template, OCELOT_TOTAL_TAG_LEN);
+
 	/* Fix up the fields which are not statically determined
 	 * in the template
 	 */
 	qos_class = skb->priority;
 	packing(injection, &qos_class, 19,  17, OCELOT_TAG_LEN, PACK, 0);
 
-	if (ocelot->ptp && (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) {
+	/* TX timestamping was requested */
+	if (clone) {
 		rew_op = ocelot_port->ptp_cmd;
-		if (ocelot_port->ptp_cmd == IFH_REW_OP_TWO_STEP_PTP) {
-			rew_op |= (ocelot_port->ts_id  % 4) << 3;
-			ocelot_port->ts_id++;
-		}
+		/* Retrieve timestamp ID populated inside skb->cb[0] of the
+		 * clone by ocelot_port_add_txtstamp_skb
+		 */
+		if (ocelot_port->ptp_cmd == IFH_REW_OP_TWO_STEP_PTP)
+			rew_op |= clone->cb[0] << 3;
 
 		packing(injection, &rew_op, 125, 117, OCELOT_TAG_LEN, PACK, 0);
 	}
@@ -184,11 +192,11 @@ static struct sk_buff *ocelot_rcv(struct sk_buff *skb,
 	 * so it points to the beginning of the frame.
 	 */
 	skb_push(skb, ETH_HLEN);
-	/* We don't care about the long prefix, it is just for easy entrance
+	/* We don't care about the short prefix, it is just for easy entrance
 	 * into the DSA master's RX filter. Discard it now by moving it into
 	 * the headroom.
 	 */
-	skb_pull(skb, OCELOT_LONG_PREFIX_LEN);
+	skb_pull(skb, OCELOT_SHORT_PREFIX_LEN);
 	/* And skb->data now points to the extraction frame header.
 	 * Keep a pointer to it.
 	 */
@@ -202,7 +210,7 @@ static struct sk_buff *ocelot_rcv(struct sk_buff *skb,
 	skb_pull(skb, ETH_HLEN);
 
 	/* Remove from inet csum the extraction header */
-	skb_postpull_rcsum(skb, start, OCELOT_LONG_PREFIX_LEN + OCELOT_TAG_LEN);
+	skb_postpull_rcsum(skb, start, OCELOT_TOTAL_TAG_LEN);
 
 	packing(extraction, &src_port,  46, 43, OCELOT_TAG_LEN, UNPACK, 0);
 	packing(extraction, &qos_class, 19, 17, OCELOT_TAG_LEN, UNPACK, 0);
@@ -228,7 +236,8 @@ static const struct dsa_device_ops ocelot_netdev_ops = {
 	.proto			= DSA_TAG_PROTO_OCELOT,
 	.xmit			= ocelot_xmit,
 	.rcv			= ocelot_rcv,
-	.overhead		= OCELOT_TAG_LEN + OCELOT_LONG_PREFIX_LEN,
+	.overhead		= OCELOT_TOTAL_TAG_LEN,
+	.promisc_on_master	= true,
 };
 
 MODULE_LICENSE("GPL v2");
diff --git a/net/dsa/tag_qca.c b/net/dsa/tag_qca.c
index 7066f5e697d7..1b9e8507112b 100644
--- a/net/dsa/tag_qca.c
+++ b/net/dsa/tag_qca.c
@@ -89,21 +89,11 @@ static struct sk_buff *qca_tag_rcv(struct sk_buff *skb, struct net_device *dev,
 	return skb;
 }
 
-static int qca_tag_flow_dissect(const struct sk_buff *skb, __be16 *proto,
-                                int *offset)
-{
-	*offset = QCA_HDR_LEN;
-	*proto = ((__be16 *)skb->data)[0];
-
-	return 0;
-}
-
 static const struct dsa_device_ops qca_netdev_ops = {
 	.name	= "qca",
 	.proto	= DSA_TAG_PROTO_QCA,
 	.xmit	= qca_tag_xmit,
 	.rcv	= qca_tag_rcv,
-	.flow_dissect = qca_tag_flow_dissect,
 	.overhead = QCA_HDR_LEN,
 };
 
diff --git a/net/dsa/tag_rtl4_a.c b/net/dsa/tag_rtl4_a.c
index 7b63010fa87b..2646abe5a69e 100644
--- a/net/dsa/tag_rtl4_a.c
+++ b/net/dsa/tag_rtl4_a.c
@@ -106,22 +106,11 @@ static struct sk_buff *rtl4a_tag_rcv(struct sk_buff *skb,
 	return skb;
 }
 
-static int rtl4a_tag_flow_dissect(const struct sk_buff *skb, __be16 *proto,
-				  int *offset)
-{
-	*offset = RTL4_A_HDR_LEN;
-	/* Skip past the tag and fetch the encapsulated Ethertype */
-	*proto = ((__be16 *)skb->data)[1];
-
-	return 0;
-}
-
 static const struct dsa_device_ops rtl4a_netdev_ops = {
 	.name	= "rtl4a",
 	.proto	= DSA_TAG_PROTO_RTL4_A,
 	.xmit	= rtl4a_tag_xmit,
 	.rcv	= rtl4a_tag_rcv,
-	.flow_dissect = rtl4a_tag_flow_dissect,
 	.overhead = RTL4_A_HDR_LEN,
 };
 module_dsa_tag_driver(rtl4a_netdev_ops);
diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c
index 3710f9daa46d..50496013cdb7 100644
--- a/net/dsa/tag_sja1105.c
+++ b/net/dsa/tag_sja1105.c
@@ -346,6 +346,16 @@ static struct sk_buff *sja1105_rcv(struct sk_buff *skb,
 					      is_meta);
 }
 
+static void sja1105_flow_dissect(const struct sk_buff *skb, __be16 *proto,
+				 int *offset)
+{
+	/* No tag added for management frames, all ok */
+	if (unlikely(sja1105_is_link_local(skb)))
+		return;
+
+	dsa_tag_generic_flow_dissect(skb, proto, offset);
+}
+
 static const struct dsa_device_ops sja1105_netdev_ops = {
 	.name = "sja1105",
 	.proto = DSA_TAG_PROTO_SJA1105,
@@ -353,6 +363,8 @@ static const struct dsa_device_ops sja1105_netdev_ops = {
 	.rcv = sja1105_rcv,
 	.filter = sja1105_filter,
 	.overhead = VLAN_HLEN,
+	.flow_dissect = sja1105_flow_dissect,
+	.promisc_on_master = true,
 };
 
 MODULE_LICENSE("GPL v2");
diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c
index 4f8ab62f0208..3a1cc24a4f0a 100644
--- a/net/dsa/tag_trailer.c
+++ b/net/dsa/tag_trailer.c
@@ -83,6 +83,7 @@ static const struct dsa_device_ops trailer_netdev_ops = {
 	.xmit	= trailer_xmit,
 	.rcv	= trailer_rcv,
 	.overhead = 4,
+	.tail_tag = true,
 };
 
 MODULE_LICENSE("GPL");
diff --git a/net/ethtool/tunnels.c b/net/ethtool/tunnels.c
index 84f23289475b..d93bf2da0f34 100644
--- a/net/ethtool/tunnels.c
+++ b/net/ethtool/tunnels.c
@@ -200,7 +200,7 @@ int ethnl_tunnel_info_doit(struct sk_buff *skb, struct genl_info *info)
 	reply_len = ret + ethnl_reply_header_size();
 
 	rskb = ethnl_reply_init(reply_len, req_info.dev,
-				ETHTOOL_MSG_TUNNEL_INFO_GET,
+				ETHTOOL_MSG_TUNNEL_INFO_GET_REPLY,
 				ETHTOOL_A_TUNNEL_INFO_HEADER,
 				info, &reply_payload);
 	if (!rskb) {
@@ -273,7 +273,7 @@ int ethnl_tunnel_info_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 				goto cont;
 
 			ehdr = ethnl_dump_put(skb, cb,
-					      ETHTOOL_MSG_TUNNEL_INFO_GET);
+					      ETHTOOL_MSG_TUNNEL_INFO_GET_REPLY);
 			if (!ehdr) {
 				ret = -EMSGSIZE;
 				goto out;
diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c
index 06c3cd988760..f3c8f91dbe2c 100644
--- a/net/hsr/hsr_netlink.c
+++ b/net/hsr/hsr_netlink.c
@@ -76,7 +76,7 @@ static int hsr_newlink(struct net *src_net, struct net_device *dev,
 		proto = nla_get_u8(data[IFLA_HSR_PROTOCOL]);
 
 	if (proto >= HSR_PROTOCOL_MAX) {
-		NL_SET_ERR_MSG_MOD(extack, "Unsupported protocol\n");
+		NL_SET_ERR_MSG_MOD(extack, "Unsupported protocol");
 		return -EINVAL;
 	}
 
@@ -84,14 +84,14 @@ static int hsr_newlink(struct net *src_net, struct net_device *dev,
 		proto_version = HSR_V0;
 	} else {
 		if (proto == HSR_PROTOCOL_PRP) {
-			NL_SET_ERR_MSG_MOD(extack, "PRP version unsupported\n");
+			NL_SET_ERR_MSG_MOD(extack, "PRP version unsupported");
 			return -EINVAL;
 		}
 
 		proto_version = nla_get_u8(data[IFLA_HSR_VERSION]);
 		if (proto_version > HSR_V1) {
 			NL_SET_ERR_MSG_MOD(extack,
-					   "Only HSR version 0/1 supported\n");
+					   "Only HSR version 0/1 supported");
 			return -EINVAL;
 		}
 	}
@@ -493,7 +493,7 @@ fail:
 	return res;
 }
 
-static const struct genl_ops hsr_ops[] = {
+static const struct genl_small_ops hsr_ops[] = {
 	{
 		.cmd = HSR_C_GET_NODE_STATUS,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
@@ -518,8 +518,8 @@ static struct genl_family hsr_genl_family __ro_after_init = {
 	.policy = hsr_genl_policy,
 	.netnsok = true,
 	.module = THIS_MODULE,
-	.ops = hsr_ops,
-	.n_ops = ARRAY_SIZE(hsr_ops),
+	.small_ops = hsr_ops,
+	.n_small_ops = ARRAY_SIZE(hsr_ops),
 	.mcgrps = hsr_mcgrps,
 	.n_mcgrps = ARRAY_SIZE(hsr_mcgrps),
 };
diff --git a/net/ieee802154/netlink.c b/net/ieee802154/netlink.c
index 7fe3b6b6c495..b07abc38b4b3 100644
--- a/net/ieee802154/netlink.c
+++ b/net/ieee802154/netlink.c
@@ -81,7 +81,7 @@ int ieee802154_nl_reply(struct sk_buff *msg, struct genl_info *info)
 	return genlmsg_reply(msg, info);
 }
 
-static const struct genl_ops ieee802154_ops[] = {
+static const struct genl_small_ops ieee802154_ops[] = {
 	/* see nl-phy.c */
 	IEEE802154_DUMP(IEEE802154_LIST_PHY, ieee802154_list_phy,
 			ieee802154_dump_phy),
@@ -130,8 +130,8 @@ struct genl_family nl802154_family __ro_after_init = {
 	.maxattr	= IEEE802154_ATTR_MAX,
 	.policy		= ieee802154_policy,
 	.module		= THIS_MODULE,
-	.ops		= ieee802154_ops,
-	.n_ops		= ARRAY_SIZE(ieee802154_ops),
+	.small_ops	= ieee802154_ops,
+	.n_small_ops	= ARRAY_SIZE(ieee802154_ops),
 	.mcgrps		= ieee802154_mcgrps,
 	.n_mcgrps	= ARRAY_SIZE(ieee802154_mcgrps),
 };
diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c
index e3939f76b024..618954f82764 100644
--- a/net/ipv4/bpf_tcp_ca.c
+++ b/net/ipv4/bpf_tcp_ca.c
@@ -28,27 +28,6 @@ static u32 unsupported_ops[] = {
 static const struct btf_type *tcp_sock_type;
 static u32 tcp_sock_id, sock_id;
 
-static int btf_sk_storage_get_ids[5];
-static struct bpf_func_proto btf_sk_storage_get_proto __read_mostly;
-
-static int btf_sk_storage_delete_ids[5];
-static struct bpf_func_proto btf_sk_storage_delete_proto __read_mostly;
-
-static void convert_sk_func_proto(struct bpf_func_proto *to, int *to_btf_ids,
-				  const struct bpf_func_proto *from)
-{
-	int i;
-
-	*to = *from;
-	to->btf_id = to_btf_ids;
-	for (i = 0; i < ARRAY_SIZE(to->arg_type); i++) {
-		if (to->arg_type[i] == ARG_PTR_TO_SOCKET) {
-			to->arg_type[i] = ARG_PTR_TO_BTF_ID;
-			to->btf_id[i] = tcp_sock_id;
-		}
-	}
-}
-
 static int bpf_tcp_ca_init(struct btf *btf)
 {
 	s32 type_id;
@@ -64,13 +43,6 @@ static int bpf_tcp_ca_init(struct btf *btf)
 	tcp_sock_id = type_id;
 	tcp_sock_type = btf_type_by_id(btf, tcp_sock_id);
 
-	convert_sk_func_proto(&btf_sk_storage_get_proto,
-			      btf_sk_storage_get_ids,
-			      &bpf_sk_storage_get_proto);
-	convert_sk_func_proto(&btf_sk_storage_delete_proto,
-			      btf_sk_storage_delete_ids,
-			      &bpf_sk_storage_delete_proto);
-
 	return 0;
 }
 
@@ -185,8 +157,8 @@ static const struct bpf_func_proto bpf_tcp_send_ack_proto = {
 	/* In case we want to report error later */
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_BTF_ID,
+	.arg1_btf_id	= &tcp_sock_id,
 	.arg2_type	= ARG_ANYTHING,
-	.btf_id		= &tcp_sock_id,
 };
 
 static const struct bpf_func_proto *
@@ -197,9 +169,9 @@ bpf_tcp_ca_get_func_proto(enum bpf_func_id func_id,
 	case BPF_FUNC_tcp_send_ack:
 		return &bpf_tcp_send_ack_proto;
 	case BPF_FUNC_sk_storage_get:
-		return &btf_sk_storage_get_proto;
+		return &bpf_sk_storage_get_proto;
 	case BPF_FUNC_sk_storage_delete:
-		return &btf_sk_storage_delete_proto;
+		return &bpf_sk_storage_delete_proto;
 	default:
 		return bpf_base_func_proto(func_id);
 	}
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 41079490a118..86a23e4a6a50 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -362,6 +362,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
 	fl4.flowi4_tun_key.tun_id = 0;
 	fl4.flowi4_flags = 0;
 	fl4.flowi4_uid = sock_net_uid(net, NULL);
+	fl4.flowi4_multipath_hash = 0;
 
 	no_addr = idev->ifa_list == NULL;
 
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index 5308cfa3de62..e5f69b0bf3df 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -911,7 +911,7 @@ static int fou_nl_dump(struct sk_buff *skb, struct netlink_callback *cb)
 	return skb->len;
 }
 
-static const struct genl_ops fou_nl_ops[] = {
+static const struct genl_small_ops fou_nl_ops[] = {
 	{
 		.cmd = FOU_CMD_ADD,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
@@ -940,8 +940,8 @@ static struct genl_family fou_nl_family __ro_after_init = {
 	.policy = fou_nl_policy,
 	.netnsok	= true,
 	.module		= THIS_MODULE,
-	.ops		= fou_nl_ops,
-	.n_ops		= ARRAY_SIZE(fou_nl_ops),
+	.small_ops	= fou_nl_ops,
+	.n_small_ops	= ARRAY_SIZE(fou_nl_ops),
 };
 
 size_t fou_encap_hlen(struct ip_tunnel_encap *e)
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index b457dd2d6c75..4148f5f78f31 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -564,7 +564,7 @@ void inet_csk_clear_xmit_timers(struct sock *sk)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 
-	icsk->icsk_pending = icsk->icsk_ack.pending = icsk->icsk_ack.blocked = 0;
+	icsk->icsk_pending = icsk->icsk_ack.pending = 0;
 
 	sk_stop_timer(sk, &icsk->icsk_retransmit_timer);
 	sk_stop_timer(sk, &icsk->icsk_delack_timer);
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 93816d47e55a..366a4507b5a3 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -203,8 +203,8 @@ errout:
 }
 EXPORT_SYMBOL_GPL(inet_diag_msg_attrs_fill);
 
-static void inet_diag_parse_attrs(const struct nlmsghdr *nlh, int hdrlen,
-				  struct nlattr **req_nlas)
+static int inet_diag_parse_attrs(const struct nlmsghdr *nlh, int hdrlen,
+				 struct nlattr **req_nlas)
 {
 	struct nlattr *nla;
 	int remaining;
@@ -212,9 +212,13 @@ static void inet_diag_parse_attrs(const struct nlmsghdr *nlh, int hdrlen,
 	nlmsg_for_each_attr(nla, nlh, hdrlen, remaining) {
 		int type = nla_type(nla);
 
+		if (type == INET_DIAG_REQ_PROTOCOL && nla_len(nla) != sizeof(u32))
+			return -EINVAL;
+
 		if (type < __INET_DIAG_REQ_MAX)
 			req_nlas[type] = nla;
 	}
+	return 0;
 }
 
 static int inet_diag_get_protocol(const struct inet_diag_req_v2 *req,
@@ -591,7 +595,10 @@ static int inet_diag_cmd_exact(int cmd, struct sk_buff *in_skb,
 	int err, protocol;
 
 	memset(&dump_data, 0, sizeof(dump_data));
-	inet_diag_parse_attrs(nlh, hdrlen, dump_data.req_nlas);
+	err = inet_diag_parse_attrs(nlh, hdrlen, dump_data.req_nlas);
+	if (err)
+		return err;
+
 	protocol = inet_diag_get_protocol(req, &dump_data);
 
 	handler = inet_diag_lock_handler(protocol);
@@ -1197,8 +1204,11 @@ static int __inet_diag_dump_start(struct netlink_callback *cb, int hdrlen)
 	if (!cb_data)
 		return -ENOMEM;
 
-	inet_diag_parse_attrs(nlh, hdrlen, cb_data->req_nlas);
-
+	err = inet_diag_parse_attrs(nlh, hdrlen, cb_data->req_nlas);
+	if (err) {
+		kfree(cb_data);
+		return err;
+	}
 	nla = cb_data->inet_diag_nla_bc;
 	if (nla) {
 		err = inet_diag_bc_audit(nla, skb);
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 5fb536ff51f0..8b200252c655 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -74,6 +74,7 @@
 #include <net/icmp.h>
 #include <net/checksum.h>
 #include <net/inetpeer.h>
+#include <net/inet_ecn.h>
 #include <net/lwtunnel.h>
 #include <linux/bpf-cgroup.h>
 #include <linux/igmp.h>
@@ -1704,7 +1705,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
 	if (IS_ERR(rt))
 		return;
 
-	inet_sk(sk)->tos = arg->tos;
+	inet_sk(sk)->tos = arg->tos & ~INET_ECN_MASK;
 
 	sk->sk_protocol = ip_hdr(skb)->protocol;
 	sk->sk_bound_dev_if = arg->bound_dev_if;
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index 75c6013ff9a4..b2ea1a8c5fd6 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -554,6 +554,7 @@ static int ip_tun_parse_opts_vxlan(struct nlattr *attr,
 
 		attr = tb[LWTUNNEL_IP_OPT_VXLAN_GBP];
 		md->gbp = nla_get_u32(attr);
+		md->gbp &= VXLAN_GBP_MASK;
 		info->key.tun_flags |= TUNNEL_VXLAN_OPT;
 	}
 
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 2c05b863ae43..d15a78b26dfa 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -786,8 +786,10 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow
 			neigh_event_send(n, NULL);
 		} else {
 			if (fib_lookup(net, fl4, &res, 0) == 0) {
-				struct fib_nh_common *nhc = FIB_RES_NHC(res);
+				struct fib_nh_common *nhc;
 
+				fib_select_path(net, &res, fl4, skb);
+				nhc = FIB_RES_NHC(res);
 				update_or_create_fnhe(nhc, fl4->daddr, new_gw,
 						0, false,
 						jiffies + ip_rt_gc_timeout);
@@ -1013,6 +1015,7 @@ out:	kfree_skb(skb);
 static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
 {
 	struct dst_entry *dst = &rt->dst;
+	struct net *net = dev_net(dst->dev);
 	struct fib_result res;
 	bool lock = false;
 	u32 old_mtu;
@@ -1034,9 +1037,11 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
 		return;
 
 	rcu_read_lock();
-	if (fib_lookup(dev_net(dst->dev), fl4, &res, 0) == 0) {
-		struct fib_nh_common *nhc = FIB_RES_NHC(res);
+	if (fib_lookup(net, fl4, &res, 0) == 0) {
+		struct fib_nh_common *nhc;
 
+		fib_select_path(net, &res, fl4, NULL);
+		nhc = FIB_RES_NHC(res);
 		update_or_create_fnhe(nhc, fl4->daddr, 0, mtu, lock,
 				      jiffies + ip_rt_mtu_expires);
 	}
@@ -2148,6 +2153,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	fl4.daddr = daddr;
 	fl4.saddr = saddr;
 	fl4.flowi4_uid = sock_net_uid(net, NULL);
+	fl4.flowi4_multipath_hash = 0;
 
 	if (fib4_rules_early_flow_dissect(net, skb, &fl4, &_flkeys)) {
 		flkeys = &_flkeys;
@@ -2668,8 +2674,6 @@ struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *fl4,
 	fib_select_path(net, res, fl4, skb);
 
 	dev_out = FIB_RES_DEV(*res);
-	fl4->flowi4_oif = dev_out->ifindex;
-
 
 make_route:
 	rth = __mkroute_output(res, fl4, orig_oif, dev_out, flags);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 65057744fac8..ed2805564424 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1538,10 +1538,8 @@ void tcp_cleanup_rbuf(struct sock *sk, int copied)
 
 	if (inet_csk_ack_scheduled(sk)) {
 		const struct inet_connection_sock *icsk = inet_csk(sk);
-		   /* Delayed ACKs frequently hit locked sockets during bulk
-		    * receive. */
-		if (icsk->icsk_ack.blocked ||
-		    /* Once-per-two-segments ACK was not sent by tcp_input.c */
+
+		if (/* Once-per-two-segments ACK was not sent by tcp_input.c */
 		    tp->rcv_nxt - tp->rcv_wup > icsk->icsk_ack.rcv_mss ||
 		    /*
 		     * If this read emptied read buffer, we send ACK, if
@@ -2696,6 +2694,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 	if (icsk->icsk_ca_ops->release)
 		icsk->icsk_ca_ops->release(sk);
 	memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
+	icsk->icsk_ca_initialized = 0;
 	tcp_set_ca_state(sk, TCP_CA_Open);
 	tp->is_sack_reneg = 0;
 	tcp_clear_retrans(tp);
@@ -3047,7 +3046,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, int optname,
 		name[val] = 0;
 
 		lock_sock(sk);
-		err = tcp_set_congestion_control(sk, name, true, true,
+		err = tcp_set_congestion_control(sk, name, true,
 						 ns_capable(sock_net(sk)->user_ns,
 							    CAP_NET_ADMIN));
 		release_sock(sk);
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index 62878cf26d9c..db47ac24d057 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -176,7 +176,7 @@ void tcp_assign_congestion_control(struct sock *sk)
 
 void tcp_init_congestion_control(struct sock *sk)
 {
-	const struct inet_connection_sock *icsk = inet_csk(sk);
+	struct inet_connection_sock *icsk = inet_csk(sk);
 
 	tcp_sk(sk)->prior_ssthresh = 0;
 	if (icsk->icsk_ca_ops->init)
@@ -185,6 +185,7 @@ void tcp_init_congestion_control(struct sock *sk)
 		INET_ECN_xmit(sk);
 	else
 		INET_ECN_dontxmit(sk);
+	icsk->icsk_ca_initialized = 1;
 }
 
 static void tcp_reinit_congestion_control(struct sock *sk,
@@ -340,7 +341,7 @@ out:
  * already initialized.
  */
 int tcp_set_congestion_control(struct sock *sk, const char *name, bool load,
-			       bool reinit, bool cap_net_admin)
+			       bool cap_net_admin)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	const struct tcp_congestion_ops *ca;
@@ -361,28 +362,14 @@ int tcp_set_congestion_control(struct sock *sk, const char *name, bool load,
 		goto out;
 	}
 
-	if (!ca) {
+	if (!ca)
 		err = -ENOENT;
-	} else if (!load) {
-		const struct tcp_congestion_ops *old_ca = icsk->icsk_ca_ops;
-
-		if (bpf_try_module_get(ca, ca->owner)) {
-			if (reinit) {
-				tcp_reinit_congestion_control(sk, ca);
-			} else {
-				icsk->icsk_ca_ops = ca;
-				bpf_module_put(old_ca, old_ca->owner);
-			}
-		} else {
-			err = -EBUSY;
-		}
-	} else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) || cap_net_admin)) {
+	else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) || cap_net_admin))
 		err = -EPERM;
-	} else if (!bpf_try_module_get(ca, ca->owner)) {
+	else if (!bpf_try_module_get(ca, ca->owner))
 		err = -EBUSY;
-	} else {
+	else
 		tcp_reinit_congestion_control(sk, ca);
-	}
  out:
 	rcu_read_unlock();
 	return err;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 50834e7f958e..20f89078fa8d 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1006,7 +1006,11 @@ static void tcp_check_sack_reordering(struct sock *sk, const u32 low_seq,
 		      ts ? LINUX_MIB_TCPTSREORDER : LINUX_MIB_TCPSACKREORDER);
 }
 
-/* This must be called before lost_out is incremented */
+ /* This must be called before lost_out or retrans_out are updated
+  * on a new loss, because we want to know if all skbs previously
+  * known to be lost have already been retransmitted, indicating
+  * that this newly lost skb is our next skb to retransmit.
+  */
 static void tcp_verify_retransmit_hint(struct tcp_sock *tp, struct sk_buff *skb)
 {
 	if ((!tp->retransmit_skb_hint && tp->retrans_out >= tp->lost_out) ||
@@ -1016,41 +1020,36 @@ static void tcp_verify_retransmit_hint(struct tcp_sock *tp, struct sk_buff *skb)
 		tp->retransmit_skb_hint = skb;
 }
 
-/* Sum the number of packets on the wire we have marked as lost.
- * There are two cases we care about here:
- * a) Packet hasn't been marked lost (nor retransmitted),
- *    and this is the first loss.
- * b) Packet has been marked both lost and retransmitted,
- *    and this means we think it was lost again.
+/* Sum the number of packets on the wire we have marked as lost, and
+ * notify the congestion control module that the given skb was marked lost.
  */
-static void tcp_sum_lost(struct tcp_sock *tp, struct sk_buff *skb)
+static void tcp_notify_skb_loss_event(struct tcp_sock *tp, const struct sk_buff *skb)
 {
-	__u8 sacked = TCP_SKB_CB(skb)->sacked;
-
-	if (!(sacked & TCPCB_LOST) ||
-	    ((sacked & TCPCB_LOST) && (sacked & TCPCB_SACKED_RETRANS)))
-		tp->lost += tcp_skb_pcount(skb);
+	tp->lost += tcp_skb_pcount(skb);
 }
 
-static void tcp_skb_mark_lost(struct tcp_sock *tp, struct sk_buff *skb)
+void tcp_mark_skb_lost(struct sock *sk, struct sk_buff *skb)
 {
-	if (!(TCP_SKB_CB(skb)->sacked & (TCPCB_LOST|TCPCB_SACKED_ACKED))) {
-		tcp_verify_retransmit_hint(tp, skb);
+	__u8 sacked = TCP_SKB_CB(skb)->sacked;
+	struct tcp_sock *tp = tcp_sk(sk);
 
-		tp->lost_out += tcp_skb_pcount(skb);
-		tcp_sum_lost(tp, skb);
-		TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
-	}
-}
+	if (sacked & TCPCB_SACKED_ACKED)
+		return;
 
-void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp, struct sk_buff *skb)
-{
 	tcp_verify_retransmit_hint(tp, skb);
-
-	tcp_sum_lost(tp, skb);
-	if (!(TCP_SKB_CB(skb)->sacked & (TCPCB_LOST|TCPCB_SACKED_ACKED))) {
+	if (sacked & TCPCB_LOST) {
+		if (sacked & TCPCB_SACKED_RETRANS) {
+			/* Account for retransmits that are lost again */
+			TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS;
+			tp->retrans_out -= tcp_skb_pcount(skb);
+			NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPLOSTRETRANSMIT,
+				      tcp_skb_pcount(skb));
+			tcp_notify_skb_loss_event(tp, skb);
+		}
+	} else {
 		tp->lost_out += tcp_skb_pcount(skb);
 		TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
+		tcp_notify_skb_loss_event(tp, skb);
 	}
 }
 
@@ -2308,7 +2307,8 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head)
 		if (cnt > packets)
 			break;
 
-		tcp_skb_mark_lost(tp, skb);
+		if (!(TCP_SKB_CB(skb)->sacked & TCPCB_LOST))
+			tcp_mark_skb_lost(sk, skb);
 
 		if (mark_head)
 			break;
@@ -2674,14 +2674,8 @@ void tcp_simple_retransmit(struct sock *sk)
 	unsigned int mss = tcp_current_mss(sk);
 
 	skb_rbtree_walk(skb, &sk->tcp_rtx_queue) {
-		if (tcp_skb_seglen(skb) > mss &&
-		    !(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) {
-			if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) {
-				TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS;
-				tp->retrans_out -= tcp_skb_pcount(skb);
-			}
-			tcp_skb_mark_lost_uncond_verify(tp, skb);
-		}
+		if (tcp_skb_seglen(skb) > mss)
+			tcp_mark_skb_lost(sk, skb);
 	}
 
 	tcp_clear_retrans_hints_partial(tp);
@@ -4908,7 +4902,7 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
 	int eaten;
 
 	if (sk_is_mptcp(sk))
-		mptcp_incoming_options(sk, skb, &tp->rx_opt);
+		mptcp_incoming_options(sk, skb);
 
 	if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq) {
 		__kfree_skb(skb);
@@ -5885,8 +5879,10 @@ void tcp_init_transfer(struct sock *sk, int bpf_op, struct sk_buff *skb)
 		tp->snd_cwnd = tcp_init_cwnd(tp, __sk_dst_get(sk));
 	tp->snd_cwnd_stamp = tcp_jiffies32;
 
+	icsk->icsk_ca_initialized = 0;
 	bpf_skops_established(sk, bpf_op, skb);
-	tcp_init_congestion_control(sk);
+	if (!icsk->icsk_ca_initialized)
+		tcp_init_congestion_control(sk);
 	tcp_init_buffer_space(sk);
 }
 
@@ -6487,7 +6483,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 	case TCP_LAST_ACK:
 		if (!before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) {
 			if (sk_is_mptcp(sk))
-				mptcp_incoming_options(sk, skb, &tp->rx_opt);
+				mptcp_incoming_options(sk, skb);
 			break;
 		}
 		fallthrough;
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index 279db8822439..6b27c481fe18 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -943,7 +943,7 @@ static int tcp_metrics_nl_cmd_del(struct sk_buff *skb, struct genl_info *info)
 	return 0;
 }
 
-static const struct genl_ops tcp_metrics_nl_ops[] = {
+static const struct genl_small_ops tcp_metrics_nl_ops[] = {
 	{
 		.cmd = TCP_METRICS_CMD_GET,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
@@ -966,8 +966,8 @@ static struct genl_family tcp_metrics_nl_family __ro_after_init = {
 	.policy = tcp_metrics_nl_policy,
 	.netnsok	= true,
 	.module		= THIS_MODULE,
-	.ops		= tcp_metrics_nl_ops,
-	.n_ops		= ARRAY_SIZE(tcp_metrics_nl_ops),
+	.small_ops	= tcp_metrics_nl_ops,
+	.n_small_ops	= ARRAY_SIZE(tcp_metrics_nl_ops),
 };
 
 static unsigned int tcpmhash_entries;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 386978dcd318..bf48cd73e967 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3911,11 +3911,8 @@ void tcp_send_delayed_ack(struct sock *sk)
 
 	/* Use new timeout only if there wasn't a older one earlier. */
 	if (icsk->icsk_ack.pending & ICSK_ACK_TIMER) {
-		/* If delack timer was blocked or is about to expire,
-		 * send ACK now.
-		 */
-		if (icsk->icsk_ack.blocked ||
-		    time_before_eq(icsk->icsk_ack.timeout, jiffies + (ato >> 2))) {
+		/* If delack timer is about to expire, send ACK now. */
+		if (time_before_eq(icsk->icsk_ack.timeout, jiffies + (ato >> 2))) {
 			tcp_send_ack(sk);
 			return;
 		}
@@ -3944,10 +3941,15 @@ void __tcp_send_ack(struct sock *sk, u32 rcv_nxt)
 	buff = alloc_skb(MAX_TCP_HEADER,
 			 sk_gfp_mask(sk, GFP_ATOMIC | __GFP_NOWARN));
 	if (unlikely(!buff)) {
+		struct inet_connection_sock *icsk = inet_csk(sk);
+		unsigned long delay;
+
+		delay = TCP_DELACK_MAX << icsk->icsk_ack.retry;
+		if (delay < TCP_RTO_MAX)
+			icsk->icsk_ack.retry++;
 		inet_csk_schedule_ack(sk);
-		inet_csk(sk)->icsk_ack.ato = TCP_ATO_MIN;
-		inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
-					  TCP_DELACK_MAX, TCP_RTO_MAX);
+		icsk->icsk_ack.ato = TCP_ATO_MIN;
+		inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK, delay, TCP_RTO_MAX);
 		return;
 	}
 
diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c
index fdb715bdd2d1..f65a3ddd0d58 100644
--- a/net/ipv4/tcp_recovery.c
+++ b/net/ipv4/tcp_recovery.c
@@ -2,20 +2,6 @@
 #include <linux/tcp.h>
 #include <net/tcp.h>
 
-void tcp_mark_skb_lost(struct sock *sk, struct sk_buff *skb)
-{
-	struct tcp_sock *tp = tcp_sk(sk);
-
-	tcp_skb_mark_lost_uncond_verify(tp, skb);
-	if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) {
-		/* Account for retransmits that are lost again */
-		TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS;
-		tp->retrans_out -= tcp_skb_pcount(skb);
-		NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPLOSTRETRANSMIT,
-			      tcp_skb_pcount(skb));
-	}
-}
-
 static bool tcp_rack_sent_after(u64 t1, u64 t2, u32 seq1, u32 seq2)
 {
 	return t1 > t2 || (t1 == t2 && after(seq1, seq2));
@@ -246,6 +232,6 @@ void tcp_newreno_mark_lost(struct sock *sk, bool snd_una_advanced)
 			tcp_fragment(sk, TCP_FRAG_IN_RTX_QUEUE, skb,
 				     mss, mss, GFP_ATOMIC);
 
-		tcp_skb_mark_lost_uncond_verify(tp, skb);
+		tcp_mark_skb_lost(sk, skb);
 	}
 }
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 0c08c420fbc2..6c62b9ea1320 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -331,7 +331,6 @@ static void tcp_delack_timer(struct timer_list *t)
 	if (!sock_owned_by_user(sk)) {
 		tcp_delack_timer_handler(sk);
 	} else {
-		icsk->icsk_ack.blocked = 1;
 		__NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOCKED);
 		/* deleguate our work to tcp_release_cb() */
 		if (!test_and_set_bit(TCP_DELACK_TIMER_DEFERRED, &sk->sk_tsq_flags))
diff --git a/net/ipv4/udp_tunnel_nic.c b/net/ipv4/udp_tunnel_nic.c
index 69962165c0e8..0d122edc368d 100644
--- a/net/ipv4/udp_tunnel_nic.c
+++ b/net/ipv4/udp_tunnel_nic.c
@@ -19,8 +19,9 @@ enum udp_tunnel_nic_table_entry_flags {
 struct udp_tunnel_nic_table_entry {
 	__be16 port;
 	u8 type;
-	u8 use_cnt;
 	u8 flags;
+	u16 use_cnt;
+#define UDP_TUNNEL_NIC_USE_CNT_MAX	U16_MAX
 	u8 hw_priv;
 };
 
@@ -370,6 +371,8 @@ udp_tunnel_nic_entry_adj(struct udp_tunnel_nic *utn,
 	bool dodgy = entry->flags & UDP_TUNNEL_NIC_ENTRY_OP_FAIL;
 	unsigned int from, to;
 
+	WARN_ON(entry->use_cnt + (u32)use_cnt_adj > U16_MAX);
+
 	/* If not going from used to unused or vice versa - all done.
 	 * For dodgy entries make sure we try to sync again (queue the entry).
 	 */
@@ -675,6 +678,7 @@ static void
 udp_tunnel_nic_replay(struct net_device *dev, struct udp_tunnel_nic *utn)
 {
 	const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info;
+	struct udp_tunnel_nic_shared_node *node;
 	unsigned int i, j;
 
 	/* Freeze all the ports we are already tracking so that the replay
@@ -686,7 +690,12 @@ udp_tunnel_nic_replay(struct net_device *dev, struct udp_tunnel_nic *utn)
 	utn->missed = 0;
 	utn->need_replay = 0;
 
-	udp_tunnel_get_rx_info(dev);
+	if (!info->shared) {
+		udp_tunnel_get_rx_info(dev);
+	} else {
+		list_for_each_entry(node, &info->shared->devices, list)
+			udp_tunnel_get_rx_info(node->dev);
+	}
 
 	for (i = 0; i < utn->n_tables; i++)
 		for (j = 0; j < info->tables[i].n_entries; j++)
@@ -742,20 +751,39 @@ err_free_utn:
 	return NULL;
 }
 
+static void udp_tunnel_nic_free(struct udp_tunnel_nic *utn)
+{
+	unsigned int i;
+
+	for (i = 0; i < utn->n_tables; i++)
+		kfree(utn->entries[i]);
+	kfree(utn->entries);
+	kfree(utn);
+}
+
 static int udp_tunnel_nic_register(struct net_device *dev)
 {
 	const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info;
+	struct udp_tunnel_nic_shared_node *node = NULL;
 	struct udp_tunnel_nic *utn;
 	unsigned int n_tables, i;
 
 	BUILD_BUG_ON(sizeof(utn->missed) * BITS_PER_BYTE <
 		     UDP_TUNNEL_NIC_MAX_TABLES);
+	/* Expect use count of at most 2 (IPv4, IPv6) per device */
+	BUILD_BUG_ON(UDP_TUNNEL_NIC_USE_CNT_MAX <
+		     UDP_TUNNEL_NIC_MAX_SHARING_DEVICES * 2);
 
+	/* Check that the driver info is sane */
 	if (WARN_ON(!info->set_port != !info->unset_port) ||
 	    WARN_ON(!info->set_port == !info->sync_table) ||
 	    WARN_ON(!info->tables[0].n_entries))
 		return -EINVAL;
 
+	if (WARN_ON(info->shared &&
+		    info->flags & UDP_TUNNEL_NIC_INFO_OPEN_ONLY))
+		return -EINVAL;
+
 	n_tables = 1;
 	for (i = 1; i < UDP_TUNNEL_NIC_MAX_TABLES; i++) {
 		if (!info->tables[i].n_entries)
@@ -766,9 +794,33 @@ static int udp_tunnel_nic_register(struct net_device *dev)
 			return -EINVAL;
 	}
 
-	utn = udp_tunnel_nic_alloc(info, n_tables);
-	if (!utn)
-		return -ENOMEM;
+	/* Create UDP tunnel state structures */
+	if (info->shared) {
+		node = kzalloc(sizeof(*node), GFP_KERNEL);
+		if (!node)
+			return -ENOMEM;
+
+		node->dev = dev;
+	}
+
+	if (info->shared && info->shared->udp_tunnel_nic_info) {
+		utn = info->shared->udp_tunnel_nic_info;
+	} else {
+		utn = udp_tunnel_nic_alloc(info, n_tables);
+		if (!utn) {
+			kfree(node);
+			return -ENOMEM;
+		}
+	}
+
+	if (info->shared) {
+		if (!info->shared->udp_tunnel_nic_info) {
+			INIT_LIST_HEAD(&info->shared->devices);
+			info->shared->udp_tunnel_nic_info = utn;
+		}
+
+		list_add_tail(&node->list, &info->shared->devices);
+	}
 
 	utn->dev = dev;
 	dev_hold(dev);
@@ -783,7 +835,33 @@ static int udp_tunnel_nic_register(struct net_device *dev)
 static void
 udp_tunnel_nic_unregister(struct net_device *dev, struct udp_tunnel_nic *utn)
 {
-	unsigned int i;
+	const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info;
+
+	/* For a shared table remove this dev from the list of sharing devices
+	 * and if there are other devices just detach.
+	 */
+	if (info->shared) {
+		struct udp_tunnel_nic_shared_node *node, *first;
+
+		list_for_each_entry(node, &info->shared->devices, list)
+			if (node->dev == dev)
+				break;
+		if (node->dev != dev)
+			return;
+
+		list_del(&node->list);
+		kfree(node);
+
+		first = list_first_entry_or_null(&info->shared->devices,
+						 typeof(*first), list);
+		if (first) {
+			udp_tunnel_drop_rx_info(dev);
+			utn->dev = first->dev;
+			goto release_dev;
+		}
+
+		info->shared->udp_tunnel_nic_info = NULL;
+	}
 
 	/* Flush before we check work, so we don't waste time adding entries
 	 * from the work which we will boot immediately.
@@ -796,10 +874,8 @@ udp_tunnel_nic_unregister(struct net_device *dev, struct udp_tunnel_nic *utn)
 	if (utn->work_pending)
 		return;
 
-	for (i = 0; i < utn->n_tables; i++)
-		kfree(utn->entries[i]);
-	kfree(utn->entries);
-	kfree(utn);
+	udp_tunnel_nic_free(utn);
+release_dev:
 	dev->udp_tunnel_nic = NULL;
 	dev_put(dev);
 }
diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig
index 76bff79d6fed..747f56e0c636 100644
--- a/net/ipv6/Kconfig
+++ b/net/ipv6/Kconfig
@@ -303,6 +303,7 @@ config IPV6_SEG6_LWTUNNEL
 config IPV6_SEG6_HMAC
 	bool "IPv6: Segment Routing HMAC support"
 	depends on IPV6
+	select CRYPTO
 	select CRYPTO_HMAC
 	select CRYPTO_SHA1
 	select CRYPTO_SHA256
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 44d68ed70f24..141c0a4c569a 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -1997,14 +1997,19 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn,
 /* Need to own table->tb6_lock */
 int fib6_del(struct fib6_info *rt, struct nl_info *info)
 {
-	struct fib6_node *fn = rcu_dereference_protected(rt->fib6_node,
-				    lockdep_is_held(&rt->fib6_table->tb6_lock));
-	struct fib6_table *table = rt->fib6_table;
 	struct net *net = info->nl_net;
 	struct fib6_info __rcu **rtp;
 	struct fib6_info __rcu **rtp_next;
+	struct fib6_table *table;
+	struct fib6_node *fn;
+
+	if (rt == net->ipv6.fib6_null_entry)
+		return -ENOENT;
 
-	if (!fn || rt == net->ipv6.fib6_null_entry)
+	table = rt->fib6_table;
+	fn = rcu_dereference_protected(rt->fib6_node,
+				       lockdep_is_held(&table->tb6_lock));
+	if (!fn)
 		return -ENOENT;
 
 	WARN_ON(!(fn->fn_flags & RTN_RTINFO));
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 3a57fb9ce049..931b186d2e48 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -707,6 +707,17 @@ static int prepare_ip6gre_xmit_ipv6(struct sk_buff *skb,
 	return 0;
 }
 
+static struct ip_tunnel_info *skb_tunnel_info_txcheck(struct sk_buff *skb)
+{
+	struct ip_tunnel_info *tun_info;
+
+	tun_info = skb_tunnel_info(skb);
+	if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX)))
+		return ERR_PTR(-EINVAL);
+
+	return tun_info;
+}
+
 static netdev_tx_t __gre6_xmit(struct sk_buff *skb,
 			       struct net_device *dev, __u8 dsfield,
 			       struct flowi6 *fl6, int encap_limit,
@@ -734,10 +745,9 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb,
 		const struct ip_tunnel_key *key;
 		__be16 flags;
 
-		tun_info = skb_tunnel_info(skb);
-		if (unlikely(!tun_info ||
-			     !(tun_info->mode & IP_TUNNEL_INFO_TX) ||
-			     ip_tunnel_info_af(tun_info) != AF_INET6))
+		tun_info = skb_tunnel_info_txcheck(skb);
+		if (IS_ERR(tun_info) ||
+		    unlikely(ip_tunnel_info_af(tun_info) != AF_INET6))
 			return -EINVAL;
 
 		key = &tun_info->key;
@@ -908,7 +918,8 @@ static netdev_tx_t ip6gre_tunnel_xmit(struct sk_buff *skb,
 	return NETDEV_TX_OK;
 
 tx_err:
-	stats->tx_errors++;
+	if (!t->parms.collect_md || !IS_ERR(skb_tunnel_info_txcheck(skb)))
+		stats->tx_errors++;
 	stats->tx_dropped++;
 	kfree_skb(skb);
 	return NETDEV_TX_OK;
@@ -917,6 +928,7 @@ tx_err:
 static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
 					 struct net_device *dev)
 {
+	struct ip_tunnel_info *tun_info = NULL;
 	struct ip6_tnl *t = netdev_priv(dev);
 	struct dst_entry *dst = skb_dst(skb);
 	struct net_device_stats *stats;
@@ -964,15 +976,13 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
 	 * for native mode, call prepare_ip6gre_xmit_{ipv4,ipv6}.
 	 */
 	if (t->parms.collect_md) {
-		struct ip_tunnel_info *tun_info;
 		const struct ip_tunnel_key *key;
 		struct erspan_metadata *md;
 		__be32 tun_id;
 
-		tun_info = skb_tunnel_info(skb);
-		if (unlikely(!tun_info ||
-			     !(tun_info->mode & IP_TUNNEL_INFO_TX) ||
-			     ip_tunnel_info_af(tun_info) != AF_INET6))
+		tun_info = skb_tunnel_info_txcheck(skb);
+		if (IS_ERR(tun_info) ||
+		    unlikely(ip_tunnel_info_af(tun_info) != AF_INET6))
 			goto tx_err;
 
 		key = &tun_info->key;
@@ -1065,7 +1075,8 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
 
 tx_err:
 	stats = &t->dev->stats;
-	stats->tx_errors++;
+	if (!IS_ERR(tun_info))
+		stats->tx_errors++;
 	stats->tx_dropped++;
 	kfree_skb(skb);
 	return NETDEV_TX_OK;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index e8ee20720fe0..bde6d48a9942 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -4202,7 +4202,7 @@ static struct fib6_info *rt6_add_route_info(struct net *net,
 		.fc_nlinfo.nl_net = net,
 	};
 
-	cfg.fc_table = l3mdev_fib_table(dev) ? : RT6_TABLE_INFO,
+	cfg.fc_table = l3mdev_fib_table(dev) ? : RT6_TABLE_INFO;
 	cfg.fc_dst = *prefix;
 	cfg.fc_gateway = *gwaddr;
 
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index a95af62acb52..d80572074667 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -588,11 +588,11 @@ static int iucv_sock_bind(struct socket *sock, struct sockaddr *addr,
 			  int addr_len)
 {
 	struct sockaddr_iucv *sa = (struct sockaddr_iucv *) addr;
+	char uid[sizeof(sa->siucv_user_id)];
 	struct sock *sk = sock->sk;
 	struct iucv_sock *iucv;
 	int err = 0;
 	struct net_device *dev;
-	char uid[9];
 
 	/* Verify the input sockaddr */
 	if (addr_len < sizeof(struct sockaddr_iucv) ||
diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c
index cd2e468852e7..349c6ac3313f 100644
--- a/net/iucv/iucv.c
+++ b/net/iucv/iucv.c
@@ -1116,10 +1116,9 @@ int __iucv_message_receive(struct iucv_path *path, struct iucv_message *msg,
 	if (msg->flags & IUCV_IPRMDATA)
 		return iucv_message_receive_iprmdata(path, msg, flags,
 						     buffer, size, residual);
-	 if (cpumask_empty(&iucv_buffer_cpumask)) {
-		rc = -EIO;
-		goto out;
-	}
+	if (cpumask_empty(&iucv_buffer_cpumask))
+		return -EIO;
+
 	parm = iucv_param[smp_processor_id()];
 	memset(parm, 0, sizeof(union iucv_param));
 	parm->db.ipbfadr1 = (u32)(addr_t) buffer;
@@ -1135,7 +1134,6 @@ int __iucv_message_receive(struct iucv_path *path, struct iucv_message *msg,
 		if (residual)
 			*residual = parm->db.ipbfln1f;
 	}
-out:
 	return rc;
 }
 EXPORT_SYMBOL(__iucv_message_receive);
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index 83c015f7f20d..83956c9ee1fc 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -420,6 +420,9 @@ static int l2tp_nl_tunnel_send(struct sk_buff *skb, u32 portid, u32 seq, int fla
 	    nla_put_u64_64bit(skb, L2TP_ATTR_RX_SEQ_DISCARDS,
 			      atomic_long_read(&tunnel->stats.rx_seq_discards),
 			      L2TP_ATTR_STATS_PAD) ||
+	    nla_put_u64_64bit(skb, L2TP_ATTR_RX_COOKIE_DISCARDS,
+			      atomic_long_read(&tunnel->stats.rx_cookie_discards),
+			      L2TP_ATTR_STATS_PAD) ||
 	    nla_put_u64_64bit(skb, L2TP_ATTR_RX_OOS_PACKETS,
 			      atomic_long_read(&tunnel->stats.rx_oos_packets),
 			      L2TP_ATTR_STATS_PAD) ||
@@ -760,6 +763,9 @@ static int l2tp_nl_session_send(struct sk_buff *skb, u32 portid, u32 seq, int fl
 	    nla_put_u64_64bit(skb, L2TP_ATTR_RX_SEQ_DISCARDS,
 			      atomic_long_read(&session->stats.rx_seq_discards),
 			      L2TP_ATTR_STATS_PAD) ||
+	    nla_put_u64_64bit(skb, L2TP_ATTR_RX_COOKIE_DISCARDS,
+			      atomic_long_read(&session->stats.rx_cookie_discards),
+			      L2TP_ATTR_STATS_PAD) ||
 	    nla_put_u64_64bit(skb, L2TP_ATTR_RX_OOS_PACKETS,
 			      atomic_long_read(&session->stats.rx_oos_packets),
 			      L2TP_ATTR_STATS_PAD) ||
@@ -908,7 +914,7 @@ static const struct nla_policy l2tp_nl_policy[L2TP_ATTR_MAX + 1] = {
 	},
 };
 
-static const struct genl_ops l2tp_nl_ops[] = {
+static const struct genl_small_ops l2tp_nl_ops[] = {
 	{
 		.cmd = L2TP_CMD_NOOP,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
@@ -975,8 +981,8 @@ static struct genl_family l2tp_nl_family __ro_after_init = {
 	.policy = l2tp_nl_policy,
 	.netnsok	= true,
 	.module		= THIS_MODULE,
-	.ops		= l2tp_nl_ops,
-	.n_ops		= ARRAY_SIZE(l2tp_nl_ops),
+	.small_ops	= l2tp_nl_ops,
+	.n_small_ops	= ARRAY_SIZE(l2tp_nl_ops),
 	.mcgrps		= l2tp_multicast_group,
 	.n_mcgrps	= ARRAY_SIZE(l2tp_multicast_group),
 };
diff --git a/net/mac80211/airtime.c b/net/mac80211/airtime.c
index 314973033d03..26d2f8ba7029 100644
--- a/net/mac80211/airtime.c
+++ b/net/mac80211/airtime.c
@@ -560,7 +560,9 @@ static int ieee80211_fill_rx_status(struct ieee80211_rx_status *stat,
 	if (rate->idx < 0 || !rate->count)
 		return -1;
 
-	if (rate->flags & IEEE80211_TX_RC_80_MHZ_WIDTH)
+	if (rate->flags & IEEE80211_TX_RC_160_MHZ_WIDTH)
+		stat->bw = RATE_INFO_BW_160;
+	else if (rate->flags & IEEE80211_TX_RC_80_MHZ_WIDTH)
 		stat->bw = RATE_INFO_BW_80;
 	else if (rate->flags & IEEE80211_TX_RC_40_MHZ_WIDTH)
 		stat->bw = RATE_INFO_BW_40;
@@ -668,20 +670,26 @@ u32 ieee80211_calc_expected_tx_airtime(struct ieee80211_hw *hw,
 		 * This will not be very accurate, but much better than simply
 		 * assuming un-aggregated tx in all cases.
 		 */
-		if (duration > 400) /* <= VHT20 MCS2 1S */
+		if (duration > 400 * 1024) /* <= VHT20 MCS2 1S */
 			agg_shift = 1;
-		else if (duration > 250) /* <= VHT20 MCS3 1S or MCS1 2S */
+		else if (duration > 250 * 1024) /* <= VHT20 MCS3 1S or MCS1 2S */
 			agg_shift = 2;
-		else if (duration > 150) /* <= VHT20 MCS5 1S or MCS3 2S */
+		else if (duration > 150 * 1024) /* <= VHT20 MCS5 1S or MCS2 2S */
 			agg_shift = 3;
-		else
+		else if (duration > 70 * 1024) /* <= VHT20 MCS5 2S */
 			agg_shift = 4;
+		else if (stat.encoding != RX_ENC_HE ||
+			 duration > 20 * 1024) /* <= HE40 MCS6 2S */
+			agg_shift = 5;
+		else
+			agg_shift = 6;
 
 		duration *= len;
 		duration /= AVG_PKT_SIZE;
 		duration /= 1024;
+		duration += (overhead >> agg_shift);
 
-		return duration + (overhead >> agg_shift);
+		return max_t(u32, duration, 4);
 	}
 
 	if (!conf)
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 8d75a4045d6e..da70f174d629 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -1124,6 +1124,8 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev,
 	       sizeof(struct ieee80211_he_obss_pd));
 	memcpy(&sdata->vif.bss_conf.he_bss_color, &params->he_bss_color,
 	       sizeof(struct ieee80211_he_bss_color));
+	sdata->vif.bss_conf.s1g = params->chandef.chan->band ==
+				  NL80211_BAND_S1GHZ;
 
 	sdata->vif.bss_conf.ssid_len = params->ssid_len;
 	if (params->ssid_len)
diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c
index bdc0f29dc6cd..8f48aff74c7b 100644
--- a/net/mac80211/chan.c
+++ b/net/mac80211/chan.c
@@ -536,7 +536,14 @@ static void ieee80211_del_chanctx(struct ieee80211_local *local,
 
 	if (!local->use_chanctx) {
 		struct cfg80211_chan_def *chandef = &local->_oper_chandef;
-		chandef->width = NL80211_CHAN_WIDTH_20_NOHT;
+		/* S1G doesn't have 20MHz, so get the correct width for the
+		 * current channel.
+		 */
+		if (chandef->chan->band == NL80211_BAND_S1GHZ)
+			chandef->width =
+				ieee80211_s1g_channel_width(chandef->chan);
+		else
+			chandef->width = NL80211_CHAN_WIDTH_20_NOHT;
 		chandef->center_freq1 = chandef->chan->center_freq;
 		chandef->freq1_offset = chandef->chan->freq_offset;
 		chandef->center_freq2 = 0;
diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c
index c0963969a465..1f552f374e97 100644
--- a/net/mac80211/ibss.c
+++ b/net/mac80211/ibss.c
@@ -1037,7 +1037,8 @@ static void ieee80211_update_sta_info(struct ieee80211_sub_if_data *sdata,
 	}
 
 	if (sta && !sta->sta.wme &&
-	    elems->wmm_info && local->hw.queues >= IEEE80211_NUM_ACS) {
+	    (elems->wmm_info || elems->s1g_capab) &&
+	    local->hw.queues >= IEEE80211_NUM_ACS) {
 		sta->sta.wme = true;
 		ieee80211_check_fast_xmit(sta);
 	}
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index ecd9229012bf..c3e3578574a6 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -544,6 +544,8 @@ struct ieee80211_if_managed {
 	struct ieee80211_ht_cap ht_capa_mask; /* Valid parts of ht_capa */
 	struct ieee80211_vht_cap vht_capa; /* configured VHT overrides */
 	struct ieee80211_vht_cap vht_capa_mask; /* Valid parts of vht_capa */
+	struct ieee80211_s1g_cap s1g_capa; /* configured S1G overrides */
+	struct ieee80211_s1g_cap s1g_capa_mask; /* valid s1g_capa bits */
 
 	/* TDLS support */
 	u8 tdls_peer[ETH_ALEN] __aligned(2);
@@ -1376,7 +1378,6 @@ struct ieee80211_local {
 				*/
 
 	bool pspolling;
-	bool offchannel_ps_enabled;
 	/*
 	 * PS can only be enabled when we have exactly one managed
 	 * interface (and monitors) in PS, this then points there.
@@ -1534,6 +1535,10 @@ struct ieee802_11_elems {
 	u8 dtim_count;
 	u8 dtim_period;
 	const struct ieee80211_addba_ext_ie *addba_ext_ie;
+	const struct ieee80211_s1g_cap *s1g_capab;
+	const struct ieee80211_s1g_oper_ie *s1g_oper;
+	const struct ieee80211_s1g_bcn_compat_ie *s1g_bcn_compat;
+	const struct ieee80211_aid_response_ie *aid_resp;
 
 	/* length of them, respectively */
 	u8 ext_capab_len;
@@ -1652,6 +1657,8 @@ int ieee80211_set_arp_filter(struct ieee80211_sub_if_data *sdata);
 void ieee80211_sta_work(struct ieee80211_sub_if_data *sdata);
 void ieee80211_sta_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata,
 				  struct sk_buff *skb);
+void ieee80211_sta_rx_queued_ext(struct ieee80211_sub_if_data *sdata,
+				 struct sk_buff *skb);
 void ieee80211_sta_reset_beacon_monitor(struct ieee80211_sub_if_data *sdata);
 void ieee80211_sta_reset_conn_monitor(struct ieee80211_sub_if_data *sdata);
 void ieee80211_mgd_stop(struct ieee80211_sub_if_data *sdata);
@@ -2204,6 +2211,11 @@ int ieee80211_add_ext_srates_ie(struct ieee80211_sub_if_data *sdata,
 				struct sk_buff *skb, bool need_basic,
 				enum nl80211_band band);
 u8 *ieee80211_add_wmm_info_ie(u8 *buf, u8 qosinfo);
+void ieee80211_add_s1g_capab_ie(struct ieee80211_sub_if_data *sdata,
+				struct ieee80211_sta_s1g_cap *caps,
+				struct sk_buff *skb);
+void ieee80211_add_aid_request_ie(struct ieee80211_sub_if_data *sdata,
+				  struct sk_buff *skb);
 
 /* channel management */
 bool ieee80211_chandef_ht_oper(const struct ieee80211_ht_operation *ht_oper,
@@ -2215,6 +2227,8 @@ bool ieee80211_chandef_vht_oper(struct ieee80211_hw *hw, u32 vht_cap_info,
 bool ieee80211_chandef_he_6ghz_oper(struct ieee80211_sub_if_data *sdata,
 				    const struct ieee80211_he_operation *he_oper,
 				    struct cfg80211_chan_def *chandef);
+bool ieee80211_chandef_s1g_oper(const struct ieee80211_s1g_oper_ie *oper,
+				struct cfg80211_chan_def *chandef);
 u32 ieee80211_chandef_downgrade(struct cfg80211_chan_def *c);
 
 int __must_check
@@ -2293,6 +2307,9 @@ void ieee80211_tdls_chsw_work(struct work_struct *wk);
 void ieee80211_tdls_handle_disconnect(struct ieee80211_sub_if_data *sdata,
 				      const u8 *peer, u16 reason);
 const char *ieee80211_get_reason_code_string(u16 reason_code);
+u16 ieee80211_encode_usf(int val);
+u8 *ieee80211_get_bssid(struct ieee80211_hdr *hdr, size_t len,
+			enum nl80211_iftype type);
 
 extern const struct ethtool_ops ieee80211_ethtool_ops;
 
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 7ac9af66f545..240862a74a0f 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -1433,6 +1433,11 @@ static void ieee80211_iface_work(struct work_struct *work)
 				WARN_ON(1);
 				break;
 			}
+		} else if (ieee80211_is_ext(mgmt->frame_control)) {
+			if (sdata->vif.type == NL80211_IFTYPE_STATION)
+				ieee80211_sta_rx_queued_ext(sdata, skb);
+			else
+				WARN_ON(1);
 		} else if (ieee80211_is_data_qos(mgmt->frame_control)) {
 			struct ieee80211_hdr *hdr = (void *)mgmt;
 			/*
diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c
index 15f2fc658f70..aca26df7587d 100644
--- a/net/mac80211/mesh_plink.c
+++ b/net/mac80211/mesh_plink.c
@@ -144,6 +144,7 @@ out:
 
 /**
  * mesh_set_ht_prot_mode - set correct HT protection mode
+ * @sdata: the (mesh) interface to handle
  *
  * Section 9.23.3.5 of IEEE 80211-2012 describes the protection rules for HT
  * mesh STA in a MBSS. Three HT protection modes are supported for now, non-HT
diff --git a/net/mac80211/mesh_ps.c b/net/mac80211/mesh_ps.c
index 76d19c09d26e..204830a55240 100644
--- a/net/mac80211/mesh_ps.c
+++ b/net/mac80211/mesh_ps.c
@@ -12,6 +12,7 @@
 
 /**
  * mps_qos_null_get - create pre-addressed QoS Null frame for mesh powersave
+ * @sta: the station to get the frame for
  */
 static struct sk_buff *mps_qos_null_get(struct sta_info *sta)
 {
@@ -44,6 +45,7 @@ static struct sk_buff *mps_qos_null_get(struct sta_info *sta)
 
 /**
  * mps_qos_null_tx - send a QoS Null to indicate link-specific power mode
+ * @sta: the station to send to
  */
 static void mps_qos_null_tx(struct sta_info *sta)
 {
@@ -400,6 +402,8 @@ static void mpsp_trigger_send(struct sta_info *sta, bool rspi, bool eosp)
 
 /**
  * mpsp_qos_null_append - append QoS Null frame to MPSP skb queue if needed
+ * @sta: the station to handle
+ * @frames: the frame list to append to
  *
  * To properly end a mesh MPSP the last transmitted frame has to set the EOSP
  * flag in the QoS Control field. In case the current tailing frame is not a
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 50a9b9025725..e9a8e8e94ee6 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -149,6 +149,7 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata,
 			     const struct ieee80211_ht_operation *ht_oper,
 			     const struct ieee80211_vht_operation *vht_oper,
 			     const struct ieee80211_he_operation *he_oper,
+			     const struct ieee80211_s1g_oper_ie *s1g_oper,
 			     struct cfg80211_chan_def *chandef, bool tracking)
 {
 	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
@@ -171,6 +172,18 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata,
 			ret = 0;
 		vht_chandef = *chandef;
 		goto out;
+	} else if (sband->band == NL80211_BAND_S1GHZ) {
+		if (!ieee80211_chandef_s1g_oper(s1g_oper, chandef)) {
+			sdata_info(sdata,
+				   "Missing S1G Operation Element? Trying operating == primary\n");
+			chandef->width = ieee80211_s1g_channel_width(channel);
+		}
+
+		ret = IEEE80211_STA_DISABLE_HT | IEEE80211_STA_DISABLE_40MHZ |
+		      IEEE80211_STA_DISABLE_VHT |
+		      IEEE80211_STA_DISABLE_80P80MHZ |
+		      IEEE80211_STA_DISABLE_160MHZ;
+		goto out;
 	}
 
 	memcpy(&sta_ht_cap, &sband->ht_cap, sizeof(sta_ht_cap));
@@ -347,6 +360,7 @@ static int ieee80211_config_bw(struct ieee80211_sub_if_data *sdata,
 			       const struct ieee80211_ht_operation *ht_oper,
 			       const struct ieee80211_vht_operation *vht_oper,
 			       const struct ieee80211_he_operation *he_oper,
+			       const struct ieee80211_s1g_oper_ie *s1g_oper,
 			       const u8 *bssid, u32 *changed)
 {
 	struct ieee80211_local *local = sdata->local;
@@ -393,7 +407,7 @@ static int ieee80211_config_bw(struct ieee80211_sub_if_data *sdata,
 	/* calculate new channel (type) based on HT/VHT/HE operation IEs */
 	flags = ieee80211_determine_chantype(sdata, sband, chan, vht_cap_info,
 					     ht_oper, vht_oper, he_oper,
-					     &chandef, true);
+					     s1g_oper, &chandef, true);
 
 	/*
 	 * Downgrade the new channel if we associated with restricted
@@ -696,6 +710,7 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata)
 	struct ieee80211_chanctx_conf *chanctx_conf;
 	struct ieee80211_channel *chan;
 	u32 rates = 0;
+	__le16 listen_int;
 	struct element *ext_capa = NULL;
 
 	/* we know it's writable, cast away the const */
@@ -784,13 +799,15 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata)
 	memcpy(mgmt->sa, sdata->vif.addr, ETH_ALEN);
 	memcpy(mgmt->bssid, assoc_data->bss->bssid, ETH_ALEN);
 
+	listen_int = cpu_to_le16(sband->band == NL80211_BAND_S1GHZ ?
+			ieee80211_encode_usf(local->hw.conf.listen_interval) :
+			local->hw.conf.listen_interval);
 	if (!is_zero_ether_addr(assoc_data->prev_bssid)) {
 		skb_put(skb, 10);
 		mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT |
 						  IEEE80211_STYPE_REASSOC_REQ);
 		mgmt->u.reassoc_req.capab_info = cpu_to_le16(capab);
-		mgmt->u.reassoc_req.listen_interval =
-				cpu_to_le16(local->hw.conf.listen_interval);
+		mgmt->u.reassoc_req.listen_interval = listen_int;
 		memcpy(mgmt->u.reassoc_req.current_ap, assoc_data->prev_bssid,
 		       ETH_ALEN);
 	} else {
@@ -798,8 +815,7 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata)
 		mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT |
 						  IEEE80211_STYPE_ASSOC_REQ);
 		mgmt->u.assoc_req.capab_info = cpu_to_le16(capab);
-		mgmt->u.assoc_req.listen_interval =
-				cpu_to_le16(local->hw.conf.listen_interval);
+		mgmt->u.assoc_req.listen_interval = listen_int;
 	}
 
 	/* SSID */
@@ -809,6 +825,9 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata)
 	*pos++ = assoc_data->ssid_len;
 	memcpy(pos, assoc_data->ssid, assoc_data->ssid_len);
 
+	if (sband->band == NL80211_BAND_S1GHZ)
+		goto skip_rates;
+
 	/* add all rates which were marked to be used above */
 	supp_rates_len = rates_len;
 	if (supp_rates_len > 8)
@@ -844,6 +863,7 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata)
 		}
 	}
 
+skip_rates:
 	if (capab & WLAN_CAPABILITY_SPECTRUM_MGMT ||
 	    capab & WLAN_CAPABILITY_RADIO_MEASURE) {
 		pos = skb_put(skb, 4);
@@ -1018,6 +1038,11 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata)
 		pos = ieee80211_add_wmm_info_ie(skb_put(skb, 9), qos_info);
 	}
 
+	if (sband->band == NL80211_BAND_S1GHZ) {
+		ieee80211_add_aid_request_ie(sdata, skb);
+		ieee80211_add_s1g_capab_ie(sdata, &sband->s1g_cap, skb);
+	}
+
 	/* add any remaining custom (i.e. vendor specific here) IEs */
 	if (assoc_data->ie_len) {
 		noffset = assoc_data->ie_len;
@@ -1597,6 +1622,9 @@ static u32 ieee80211_handle_pwr_constr(struct ieee80211_sub_if_data *sdata,
 	int new_ap_level;
 	__le16 capab = mgmt->u.probe_resp.capab_info;
 
+	if (ieee80211_is_s1g_beacon(mgmt->frame_control))
+		return 0;	/* TODO */
+
 	if (country_ie &&
 	    (capab & cpu_to_le16(WLAN_CAPABILITY_SPECTRUM_MGMT) ||
 	     capab & cpu_to_le16(WLAN_CAPABILITY_RADIO_MEASURE))) {
@@ -2508,7 +2536,9 @@ void ieee80211_sta_tx_notify(struct ieee80211_sub_if_data *sdata,
 	    !sdata->u.mgd.probe_send_count)
 		return;
 
-	if (!ack)
+	if (ack)
+		sdata->u.mgd.probe_send_count = 0;
+	else
 		sdata->u.mgd.nullfunc_failed = true;
 	ieee80211_queue_work(&sdata->local->hw, &sdata->work);
 }
@@ -3242,14 +3272,26 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata,
 	const struct cfg80211_bss_ies *bss_ies = NULL;
 	struct ieee80211_mgd_assoc_data *assoc_data = ifmgd->assoc_data;
 	bool is_6ghz = cbss->channel->band == NL80211_BAND_6GHZ;
+	bool is_s1g = cbss->channel->band == NL80211_BAND_S1GHZ;
 	u32 changed = 0;
+	u8 *pos;
 	int err;
 	bool ret;
 
 	/* AssocResp and ReassocResp have identical structure */
 
+	pos = mgmt->u.assoc_resp.variable;
 	aid = le16_to_cpu(mgmt->u.assoc_resp.aid);
+	if (is_s1g) {
+		pos = (u8 *) mgmt->u.s1g_assoc_resp.variable;
+		aid = 0; /* TODO */
+	}
 	capab_info = le16_to_cpu(mgmt->u.assoc_resp.capab_info);
+	ieee802_11_parse_elems(pos, len - (pos - (u8 *)mgmt), false, elems,
+			       mgmt->bssid, assoc_data->bss->bssid);
+
+	if (elems->aid_resp)
+		aid = le16_to_cpu(elems->aid_resp->aid);
 
 	/*
 	 * The 5 MSB of the AID field are reserved
@@ -3266,7 +3308,7 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata,
 		ifmgd->broken_ap = true;
 	}
 
-	if (!elems->supp_rates) {
+	if (!is_s1g && !elems->supp_rates) {
 		sdata_info(sdata, "no SuppRates element in AssocResp\n");
 		return false;
 	}
@@ -3508,7 +3550,8 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata,
 		sta->sta.mfp = false;
 	}
 
-	sta->sta.wme = elems->wmm_param && local->hw.queues >= IEEE80211_NUM_ACS;
+	sta->sta.wme = (elems->wmm_param || elems->s1g_capab) &&
+		       local->hw.queues >= IEEE80211_NUM_ACS;
 
 	err = sta_info_move_state(sta, IEEE80211_STA_ASSOC);
 	if (!err && !(ifmgd->flags & IEEE80211_STA_CONTROL_PORT))
@@ -3603,7 +3646,7 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata,
 	int ac, uapsd_queues = -1;
 	u8 *pos;
 	bool reassoc;
-	struct cfg80211_bss *bss;
+	struct cfg80211_bss *cbss;
 	struct ieee80211_event event = {
 		.type = MLME_EVENT,
 		.u.mlme.data = ASSOC_EVENT,
@@ -3613,9 +3656,12 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata,
 
 	if (!assoc_data)
 		return;
+
 	if (!ether_addr_equal(assoc_data->bss->bssid, mgmt->bssid))
 		return;
 
+	cbss = assoc_data->bss;
+
 	/*
 	 * AssocResp and ReassocResp have identical structure, so process both
 	 * of them in this function.
@@ -3627,7 +3673,12 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata,
 	reassoc = ieee80211_is_reassoc_resp(mgmt->frame_control);
 	capab_info = le16_to_cpu(mgmt->u.assoc_resp.capab_info);
 	status_code = le16_to_cpu(mgmt->u.assoc_resp.status_code);
+	pos = mgmt->u.assoc_resp.variable;
 	aid = le16_to_cpu(mgmt->u.assoc_resp.aid);
+	if (cbss->channel->band == NL80211_BAND_S1GHZ) {
+		pos = (u8 *) mgmt->u.s1g_assoc_resp.variable;
+		aid = 0; /* TODO */
+	}
 
 	sdata_info(sdata,
 		   "RX %sssocResp from %pM (capab=0x%x status=%d aid=%d)\n",
@@ -3638,7 +3689,6 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata,
 	    fils_decrypt_assoc_resp(sdata, (u8 *)mgmt, &len, assoc_data) < 0)
 		return;
 
-	pos = mgmt->u.assoc_resp.variable;
 	ieee802_11_parse_elems(pos, len - (pos - (u8 *)mgmt), false, &elems,
 			       mgmt->bssid, assoc_data->bss->bssid);
 
@@ -3658,8 +3708,6 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata,
 		return;
 	}
 
-	bss = assoc_data->bss;
-
 	if (status_code != WLAN_STATUS_SUCCESS) {
 		sdata_info(sdata, "%pM denied association (code=%d)\n",
 			   mgmt->sa, status_code);
@@ -3668,10 +3716,10 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata,
 		event.u.mlme.reason = status_code;
 		drv_event_callback(sdata->local, sdata, &event);
 	} else {
-		if (!ieee80211_assoc_success(sdata, bss, mgmt, len, &elems)) {
+		if (!ieee80211_assoc_success(sdata, cbss, mgmt, len, &elems)) {
 			/* oops -- internal error -- send timeout for now */
 			ieee80211_destroy_assoc_data(sdata, false, false);
-			cfg80211_assoc_timeout(sdata->dev, bss);
+			cfg80211_assoc_timeout(sdata->dev, cbss);
 			return;
 		}
 		event.u.mlme.status = MLME_SUCCESS;
@@ -3692,7 +3740,7 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata,
 				uapsd_queues |= ieee80211_ac_to_qos_mask[ac];
 	}
 
-	cfg80211_rx_assoc_resp(sdata->dev, bss, (u8 *)mgmt, len, uapsd_queues,
+	cfg80211_rx_assoc_resp(sdata->dev, cbss, (u8 *)mgmt, len, uapsd_queues,
 			       ifmgd->assoc_req_ies, ifmgd->assoc_req_ies_len);
 }
 
@@ -3891,11 +3939,12 @@ static bool ieee80211_rx_our_beacon(const u8 *tx_bssid,
 }
 
 static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata,
-				     struct ieee80211_mgmt *mgmt, size_t len,
+				     struct ieee80211_hdr *hdr, size_t len,
 				     struct ieee80211_rx_status *rx_status)
 {
 	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
 	struct ieee80211_bss_conf *bss_conf = &sdata->vif.bss_conf;
+	struct ieee80211_mgmt *mgmt = (void *) hdr;
 	size_t baselen;
 	struct ieee802_11_elems elems;
 	struct ieee80211_local *local = sdata->local;
@@ -3905,14 +3954,24 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata,
 	u32 changed = 0;
 	bool erp_valid;
 	u8 erp_value = 0;
-	u32 ncrc;
-	u8 *bssid;
+	u32 ncrc = 0;
+	u8 *bssid, *variable = mgmt->u.beacon.variable;
 	u8 deauth_buf[IEEE80211_DEAUTH_FRAME_LEN];
 
 	sdata_assert_lock(sdata);
 
 	/* Process beacon from the current BSS */
-	baselen = (u8 *) mgmt->u.beacon.variable - (u8 *) mgmt;
+	bssid = ieee80211_get_bssid(hdr, len, sdata->vif.type);
+	if (ieee80211_is_s1g_beacon(mgmt->frame_control)) {
+		struct ieee80211_ext *ext = (void *) mgmt;
+
+		if (ieee80211_is_s1g_short_beacon(ext->frame_control))
+			variable = ext->u.s1g_short_beacon.variable;
+		else
+			variable = ext->u.s1g_beacon.variable;
+	}
+
+	baselen = (u8 *) variable - (u8 *) mgmt;
 	if (baselen > len)
 		return;
 
@@ -3932,10 +3991,10 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata,
 	rcu_read_unlock();
 
 	if (ifmgd->assoc_data && ifmgd->assoc_data->need_beacon &&
-	    ieee80211_rx_our_beacon(mgmt->bssid, ifmgd->assoc_data->bss)) {
-		ieee802_11_parse_elems(mgmt->u.beacon.variable,
+	    ieee80211_rx_our_beacon(bssid, ifmgd->assoc_data->bss)) {
+		ieee802_11_parse_elems(variable,
 				       len - baselen, false, &elems,
-				       mgmt->bssid,
+				       bssid,
 				       ifmgd->assoc_data->bss->bssid);
 
 		ieee80211_rx_bss_info(sdata, mgmt, len, rx_status);
@@ -3968,7 +4027,7 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata,
 	}
 
 	if (!ifmgd->associated ||
-	    !ieee80211_rx_our_beacon(mgmt->bssid,  ifmgd->associated))
+	    !ieee80211_rx_our_beacon(bssid,  ifmgd->associated))
 		return;
 	bssid = ifmgd->associated->bssid;
 
@@ -3988,8 +4047,14 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata,
 	 */
 	ieee80211_sta_reset_beacon_monitor(sdata);
 
-	ncrc = crc32_be(0, (void *)&mgmt->u.beacon.beacon_int, 4);
-	ncrc = ieee802_11_parse_elems_crc(mgmt->u.beacon.variable,
+	/* TODO: CRC urrently not calculated on S1G Beacon Compatibility
+	 * element (which carries the beacon interval). Don't forget to add a
+	 * bit to care_about_ies[] above if mac80211 is interested in a
+	 * changing S1G element.
+	 */
+	if (!ieee80211_is_s1g_beacon(hdr->frame_control))
+		ncrc = crc32_be(0, (void *)&mgmt->u.beacon.beacon_int, 4);
+	ncrc = ieee802_11_parse_elems_crc(variable,
 					  len - baselen, false, &elems,
 					  care_about_ies, ncrc,
 					  mgmt->bssid, bssid);
@@ -4023,7 +4088,7 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata,
 		struct ieee80211_p2p_noa_attr noa = {};
 		int ret;
 
-		ret = cfg80211_get_p2p_attr(mgmt->u.beacon.variable,
+		ret = cfg80211_get_p2p_attr(variable,
 					    len - baselen,
 					    IEEE80211_P2P_ATTR_ABSENCE_NOTICE,
 					    (u8 *) &noa, sizeof(noa));
@@ -4059,7 +4124,8 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata,
 	 * the driver will use them. The synchronized view is currently
 	 * guaranteed only in certain callbacks.
 	 */
-	if (ieee80211_hw_check(&local->hw, TIMING_BEACON_ONLY)) {
+	if (ieee80211_hw_check(&local->hw, TIMING_BEACON_ONLY) &&
+	    !ieee80211_is_s1g_beacon(hdr->frame_control)) {
 		sdata->vif.bss_conf.sync_tsf =
 			le64_to_cpu(mgmt->u.beacon.timestamp);
 		sdata->vif.bss_conf.sync_device_ts =
@@ -4067,7 +4133,8 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata,
 		sdata->vif.bss_conf.sync_dtim_count = elems.dtim_count;
 	}
 
-	if (ncrc == ifmgd->beacon_crc && ifmgd->beacon_crc_valid)
+	if ((ncrc == ifmgd->beacon_crc && ifmgd->beacon_crc_valid) ||
+	    ieee80211_is_s1g_short_beacon(mgmt->frame_control))
 		return;
 	ifmgd->beacon_crc = ncrc;
 	ifmgd->beacon_crc_valid = true;
@@ -4108,9 +4175,11 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata,
 	} else {
 		erp_valid = false;
 	}
-	changed |= ieee80211_handle_bss_capability(sdata,
-			le16_to_cpu(mgmt->u.beacon.capab_info),
-			erp_valid, erp_value);
+
+	if (!ieee80211_is_s1g_beacon(hdr->frame_control))
+		changed |= ieee80211_handle_bss_capability(sdata,
+				le16_to_cpu(mgmt->u.beacon.capab_info),
+				erp_valid, erp_value);
 
 	mutex_lock(&local->sta_mtx);
 	sta = sta_info_get(sdata, bssid);
@@ -4120,7 +4189,7 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata,
 	if (ieee80211_config_bw(sdata, sta, elems.ht_cap_elem,
 				elems.vht_cap_elem, elems.ht_operation,
 				elems.vht_operation, elems.he_operation,
-				bssid, &changed)) {
+				elems.s1g_oper, bssid, &changed)) {
 		mutex_unlock(&local->sta_mtx);
 		sdata_info(sdata,
 			   "failed to follow AP %pM bandwidth change, disconnect\n",
@@ -4148,6 +4217,26 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata,
 	ieee80211_bss_info_change_notify(sdata, changed);
 }
 
+void ieee80211_sta_rx_queued_ext(struct ieee80211_sub_if_data *sdata,
+				 struct sk_buff *skb)
+{
+	struct ieee80211_rx_status *rx_status;
+	struct ieee80211_hdr *hdr;
+	u16 fc;
+
+	rx_status = (struct ieee80211_rx_status *) skb->cb;
+	hdr = (struct ieee80211_hdr *) skb->data;
+	fc = le16_to_cpu(hdr->frame_control);
+
+	sdata_lock(sdata);
+	switch (fc & IEEE80211_FCTL_STYPE) {
+	case IEEE80211_STYPE_S1G_BEACON:
+		ieee80211_rx_mgmt_beacon(sdata, hdr, skb->len, rx_status);
+		break;
+	}
+	sdata_unlock(sdata);
+}
+
 void ieee80211_sta_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata,
 				  struct sk_buff *skb)
 {
@@ -4165,7 +4254,8 @@ void ieee80211_sta_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata,
 
 	switch (fc & IEEE80211_FCTL_STYPE) {
 	case IEEE80211_STYPE_BEACON:
-		ieee80211_rx_mgmt_beacon(sdata, mgmt, skb->len, rx_status);
+		ieee80211_rx_mgmt_beacon(sdata, (void *)mgmt,
+					 skb->len, rx_status);
 		break;
 	case IEEE80211_STYPE_PROBE_RESP:
 		ieee80211_rx_mgmt_probe_resp(sdata, skb);
@@ -4852,9 +4942,11 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata,
 	const struct ieee80211_ht_operation *ht_oper = NULL;
 	const struct ieee80211_vht_operation *vht_oper = NULL;
 	const struct ieee80211_he_operation *he_oper = NULL;
+	const struct ieee80211_s1g_oper_ie *s1g_oper = NULL;
 	struct ieee80211_supported_band *sband;
 	struct cfg80211_chan_def chandef;
 	bool is_6ghz = cbss->channel->band == NL80211_BAND_6GHZ;
+	bool is_5ghz = cbss->channel->band == NL80211_BAND_5GHZ;
 	struct ieee80211_bss *bss = (void *)cbss->priv;
 	int ret;
 	u32 i;
@@ -4873,7 +4965,7 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata,
 		ifmgd->flags |= IEEE80211_STA_DISABLE_HE;
 	}
 
-	if (!sband->vht_cap.vht_supported && !is_6ghz) {
+	if (!sband->vht_cap.vht_supported && is_5ghz) {
 		ifmgd->flags |= IEEE80211_STA_DISABLE_VHT;
 		ifmgd->flags |= IEEE80211_STA_DISABLE_HE;
 	}
@@ -4954,10 +5046,23 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata,
 	if (!have_80mhz)
 		ifmgd->flags |= IEEE80211_STA_DISABLE_VHT;
 
+	if (sband->band == NL80211_BAND_S1GHZ) {
+		const u8 *s1g_oper_ie;
+
+		s1g_oper_ie = ieee80211_bss_get_ie(cbss,
+						   WLAN_EID_S1G_OPERATION);
+		if (s1g_oper_ie && s1g_oper_ie[1] >= sizeof(*s1g_oper))
+			s1g_oper = (void *)(s1g_oper_ie + 2);
+		else
+			sdata_info(sdata,
+				   "AP missing S1G operation element?\n");
+	}
+
 	ifmgd->flags |= ieee80211_determine_chantype(sdata, sband,
 						     cbss->channel,
 						     bss->vht_cap_info,
 						     ht_oper, vht_oper, he_oper,
+						     s1g_oper,
 						     &chandef, false);
 
 	sdata->needed_rx_chains = min(ieee80211_ht_vht_rx_chains(sdata, cbss),
@@ -5084,6 +5189,10 @@ static int ieee80211_prep_connection(struct ieee80211_sub_if_data *sdata,
 		const struct cfg80211_bss_ies *ies;
 		int shift = ieee80211_vif_get_shift(&sdata->vif);
 
+		/* TODO: S1G Basic Rate Set is expressed elsewhere */
+		if (cbss->channel->band == NL80211_BAND_S1GHZ)
+			goto skip_rates;
+
 		ieee80211_get_rates(sband, bss->supp_rates,
 				    bss->supp_rates_len,
 				    &rates, &basic_rates,
@@ -5128,6 +5237,7 @@ static int ieee80211_prep_connection(struct ieee80211_sub_if_data *sdata,
 		else
 			sdata->flags &= ~IEEE80211_SDATA_OPERATING_GMODE;
 
+skip_rates:
 		memcpy(ifmgd->bssid, cbss->bssid, ETH_ALEN);
 
 		/* set timing information */
@@ -5455,6 +5565,10 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata,
 	memcpy(&ifmgd->vht_capa_mask, &req->vht_capa_mask,
 	       sizeof(ifmgd->vht_capa_mask));
 
+	memcpy(&ifmgd->s1g_capa, &req->s1g_capa, sizeof(ifmgd->s1g_capa));
+	memcpy(&ifmgd->s1g_capa_mask, &req->s1g_capa_mask,
+	       sizeof(ifmgd->s1g_capa_mask));
+
 	if (req->ie && req->ie_len) {
 		memcpy(assoc_data->ie, req->ie, req->ie_len);
 		assoc_data->ie_len = req->ie_len;
diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c
index 1ac7b8c374c9..853c9a369d72 100644
--- a/net/mac80211/offchannel.c
+++ b/net/mac80211/offchannel.c
@@ -26,8 +26,7 @@ static void ieee80211_offchannel_ps_enable(struct ieee80211_sub_if_data *sdata)
 {
 	struct ieee80211_local *local = sdata->local;
 	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
-
-	local->offchannel_ps_enabled = false;
+	bool offchannel_ps_enabled = false;
 
 	/* FIXME: what to do when local->pspolling is true? */
 
@@ -38,12 +37,12 @@ static void ieee80211_offchannel_ps_enable(struct ieee80211_sub_if_data *sdata)
 	cancel_work_sync(&local->dynamic_ps_enable_work);
 
 	if (local->hw.conf.flags & IEEE80211_CONF_PS) {
-		local->offchannel_ps_enabled = true;
+		offchannel_ps_enabled = true;
 		local->hw.conf.flags &= ~IEEE80211_CONF_PS;
 		ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_PS);
 	}
 
-	if (!local->offchannel_ps_enabled ||
+	if (!offchannel_ps_enabled ||
 	    !ieee80211_hw_check(&local->hw, PS_NULLFUNC_STACK))
 		/*
 		 * If power save was enabled, no need to send a nullfunc
@@ -58,38 +57,19 @@ static void ieee80211_offchannel_ps_enable(struct ieee80211_sub_if_data *sdata)
 		ieee80211_send_nullfunc(local, sdata, true);
 }
 
-/* inform AP that we are awake again, unless power save is enabled */
+/* inform AP that we are awake again */
 static void ieee80211_offchannel_ps_disable(struct ieee80211_sub_if_data *sdata)
 {
 	struct ieee80211_local *local = sdata->local;
 
 	if (!local->ps_sdata)
 		ieee80211_send_nullfunc(local, sdata, false);
-	else if (local->offchannel_ps_enabled) {
-		/*
-		 * In !IEEE80211_HW_PS_NULLFUNC_STACK case the hardware
-		 * will send a nullfunc frame with the powersave bit set
-		 * even though the AP already knows that we are sleeping.
-		 * This could be avoided by sending a null frame with power
-		 * save bit disabled before enabling the power save, but
-		 * this doesn't gain anything.
-		 *
-		 * When IEEE80211_HW_PS_NULLFUNC_STACK is enabled, no need
-		 * to send a nullfunc frame because AP already knows that
-		 * we are sleeping, let's just enable power save mode in
-		 * hardware.
-		 */
-		/* TODO:  Only set hardware if CONF_PS changed?
-		 * TODO:  Should we set offchannel_ps_enabled to false?
-		 */
-		local->hw.conf.flags |= IEEE80211_CONF_PS;
-		ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_PS);
-	} else if (local->hw.conf.dynamic_ps_timeout > 0) {
+	else if (local->hw.conf.dynamic_ps_timeout > 0) {
 		/*
-		 * If IEEE80211_CONF_PS was not set and the dynamic_ps_timer
-		 * had been running before leaving the operating channel,
-		 * restart the timer now and send a nullfunc frame to inform
-		 * the AP that we are awake.
+		 * the dynamic_ps_timer had been running before leaving the
+		 * operating channel, restart the timer now and send a nullfunc
+		 * frame to inform the AP that we are awake so that AP sends
+		 * the buffered packets (if any).
 		 */
 		ieee80211_send_nullfunc(local, sdata, false);
 		mod_timer(&local->dynamic_ps_timer, jiffies +
diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c
index b051f125d3af..0cba7fed28cf 100644
--- a/net/mac80211/rate.c
+++ b/net/mac80211/rate.c
@@ -51,6 +51,12 @@ void rate_control_rate_init(struct sta_info *sta)
 
 	sband = local->hw.wiphy->bands[chanctx_conf->def.chan->band];
 
+	/* TODO: check for minstrel_s1g ? */
+	if (sband->band == NL80211_BAND_S1GHZ) {
+		rcu_read_unlock();
+		return;
+	}
+
 	spin_lock_bh(&sta->rate_ctrl_lock);
 	ref->ops->rate_init(ref->priv, sband, &chanctx_conf->def, ista,
 			    priv_sta);
@@ -266,10 +272,15 @@ void ieee80211_check_rate_mask(struct ieee80211_sub_if_data *sdata)
 	if (WARN_ON(!sdata->vif.bss_conf.chandef.chan))
 		return;
 
+	band = sdata->vif.bss_conf.chandef.chan->band;
+	if (band == NL80211_BAND_S1GHZ) {
+		/* TODO */
+		return;
+	}
+
 	if (WARN_ON_ONCE(!basic_rates))
 		return;
 
-	band = sdata->vif.bss_conf.chandef.chan->band;
 	user_mask = sdata->rc_rateidx_mask[band];
 	sband = local->hw.wiphy->bands[band];
 
@@ -296,21 +307,29 @@ static bool rc_no_data_or_no_ack_use_min(struct ieee80211_tx_rate_control *txrc)
 		!ieee80211_is_data(fc);
 }
 
-static void rc_send_low_basicrate(s8 *idx, u32 basic_rates,
+static void rc_send_low_basicrate(struct ieee80211_tx_rate *rate,
+				  u32 basic_rates,
 				  struct ieee80211_supported_band *sband)
 {
 	u8 i;
 
+	if (sband->band == NL80211_BAND_S1GHZ) {
+		/* TODO */
+		rate->flags |= IEEE80211_TX_RC_S1G_MCS;
+		rate->idx = 0;
+		return;
+	}
+
 	if (basic_rates == 0)
 		return; /* assume basic rates unknown and accept rate */
-	if (*idx < 0)
+	if (rate->idx < 0)
 		return;
-	if (basic_rates & (1 << *idx))
+	if (basic_rates & (1 << rate->idx))
 		return; /* selected rate is a basic rate */
 
-	for (i = *idx + 1; i <= sband->n_bitrates; i++) {
+	for (i = rate->idx + 1; i <= sband->n_bitrates; i++) {
 		if (basic_rates & (1 << i)) {
-			*idx = i;
+			rate->idx = i;
 			return;
 		}
 	}
@@ -328,6 +347,12 @@ static void __rate_control_send_low(struct ieee80211_hw *hw,
 	u32 rate_flags =
 		ieee80211_chandef_rate_flags(&hw->conf.chandef);
 
+	if (sband->band == NL80211_BAND_S1GHZ) {
+		info->control.rates[0].flags |= IEEE80211_TX_RC_S1G_MCS;
+		info->control.rates[0].idx = 0;
+		return;
+	}
+
 	if ((sband->band == NL80211_BAND_2GHZ) &&
 	    (info->flags & IEEE80211_TX_CTL_NO_CCK_RATE))
 		rate_flags |= IEEE80211_RATE_ERP_G;
@@ -388,7 +413,7 @@ static bool rate_control_send_low(struct ieee80211_sta *pubsta,
 		}
 
 		if (use_basicrate)
-			rc_send_low_basicrate(&info->control.rates[0].idx,
+			rc_send_low_basicrate(&info->control.rates[0],
 					      txrc->bss_conf->basic_rates,
 					      sband);
 
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index b04d6e01a346..1e2e5a406d58 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -42,51 +42,6 @@ static inline void ieee80211_rx_stats(struct net_device *dev, u32 len)
 	u64_stats_update_end(&tstats->syncp);
 }
 
-static u8 *ieee80211_get_bssid(struct ieee80211_hdr *hdr, size_t len,
-			       enum nl80211_iftype type)
-{
-	__le16 fc = hdr->frame_control;
-
-	if (ieee80211_is_data(fc)) {
-		if (len < 24) /* drop incorrect hdr len (data) */
-			return NULL;
-
-		if (ieee80211_has_a4(fc))
-			return NULL;
-		if (ieee80211_has_tods(fc))
-			return hdr->addr1;
-		if (ieee80211_has_fromds(fc))
-			return hdr->addr2;
-
-		return hdr->addr3;
-	}
-
-	if (ieee80211_is_mgmt(fc)) {
-		if (len < 24) /* drop incorrect hdr len (mgmt) */
-			return NULL;
-		return hdr->addr3;
-	}
-
-	if (ieee80211_is_ctl(fc)) {
-		if (ieee80211_is_pspoll(fc))
-			return hdr->addr1;
-
-		if (ieee80211_is_back_req(fc)) {
-			switch (type) {
-			case NL80211_IFTYPE_STATION:
-				return hdr->addr2;
-			case NL80211_IFTYPE_AP:
-			case NL80211_IFTYPE_AP_VLAN:
-				return hdr->addr1;
-			default:
-				break; /* fall through to the return */
-			}
-		}
-	}
-
-	return NULL;
-}
-
 /*
  * monitor mode reception
  *
@@ -451,7 +406,8 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local,
 	else if (status->bw == RATE_INFO_BW_5)
 		channel_flags |= IEEE80211_CHAN_QUARTER;
 
-	if (status->band == NL80211_BAND_5GHZ)
+	if (status->band == NL80211_BAND_5GHZ ||
+	    status->band == NL80211_BAND_6GHZ)
 		channel_flags |= IEEE80211_CHAN_OFDM | IEEE80211_CHAN_5GHZ;
 	else if (status->encoding != RX_ENC_LEGACY)
 		channel_flags |= IEEE80211_CHAN_DYN | IEEE80211_CHAN_2GHZ;
@@ -1801,7 +1757,8 @@ ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx)
 		}
 	} else if (rx->sdata->vif.type == NL80211_IFTYPE_OCB) {
 		sta->rx_stats.last_rx = jiffies;
-	} else if (!is_multicast_ether_addr(hdr->addr1)) {
+	} else if (!ieee80211_is_s1g_beacon(hdr->frame_control) &&
+		   is_multicast_ether_addr(hdr->addr1)) {
 		/*
 		 * Mesh beacons will update last_rx when if they are found to
 		 * match the current local configuration when processed.
@@ -1836,6 +1793,9 @@ ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx)
 		}
 	}
 
+	if (ieee80211_is_s1g_beacon(hdr->frame_control))
+		return RX_CONTINUE;
+
 	/*
 	 * Change STA power saving mode only at the end of a frame
 	 * exchange sequence, and only for a data or management
@@ -1946,6 +1906,9 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx)
 	__le16 fc;
 	const struct ieee80211_cipher_scheme *cs = NULL;
 
+	if (ieee80211_is_ext(hdr->frame_control))
+		return RX_CONTINUE;
+
 	/*
 	 * Key selection 101
 	 *
@@ -2254,7 +2217,7 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx)
 	hdr = (struct ieee80211_hdr *)rx->skb->data;
 	fc = hdr->frame_control;
 
-	if (ieee80211_is_ctl(fc))
+	if (ieee80211_is_ctl(fc) || ieee80211_is_ext(fc))
 		return RX_CONTINUE;
 
 	sc = le16_to_cpu(hdr->seq_ctrl);
@@ -3128,6 +3091,9 @@ ieee80211_rx_h_mgmt_check(struct ieee80211_rx_data *rx)
 	struct ieee80211_mgmt *mgmt = (struct ieee80211_mgmt *) rx->skb->data;
 	struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(rx->skb);
 
+	if (ieee80211_is_s1g_beacon(mgmt->frame_control))
+		return RX_CONTINUE;
+
 	/*
 	 * From here on, look only at management frames.
 	 * Data and control frames are already handled,
@@ -3595,6 +3561,27 @@ ieee80211_rx_h_action_return(struct ieee80211_rx_data *rx)
 }
 
 static ieee80211_rx_result debug_noinline
+ieee80211_rx_h_ext(struct ieee80211_rx_data *rx)
+{
+	struct ieee80211_sub_if_data *sdata = rx->sdata;
+	struct ieee80211_hdr *hdr = (void *)rx->skb->data;
+
+	if (!ieee80211_is_ext(hdr->frame_control))
+		return RX_CONTINUE;
+
+	if (sdata->vif.type != NL80211_IFTYPE_STATION)
+		return RX_DROP_MONITOR;
+
+	/* for now only beacons are ext, so queue them */
+	skb_queue_tail(&sdata->skb_queue, rx->skb);
+	ieee80211_queue_work(&rx->local->hw, &sdata->work);
+	if (rx->sta)
+		rx->sta->rx_stats.packets++;
+
+	return RX_QUEUED;
+}
+
+static ieee80211_rx_result debug_noinline
 ieee80211_rx_h_mgmt(struct ieee80211_rx_data *rx)
 {
 	struct ieee80211_sub_if_data *sdata = rx->sdata;
@@ -3813,6 +3800,7 @@ static void ieee80211_rx_handlers(struct ieee80211_rx_data *rx,
 		CALL_RXH(ieee80211_rx_h_userspace_mgmt);
 		CALL_RXH(ieee80211_rx_h_action_post_userspace);
 		CALL_RXH(ieee80211_rx_h_action_return);
+		CALL_RXH(ieee80211_rx_h_ext);
 		CALL_RXH(ieee80211_rx_h_mgmt);
 
  rxh_next:
@@ -3979,7 +3967,8 @@ static bool ieee80211_accept_frame(struct ieee80211_rx_data *rx)
 	struct ieee80211_hdr *hdr = (void *)skb->data;
 	struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb);
 	u8 *bssid = ieee80211_get_bssid(hdr, skb->len, sdata->vif.type);
-	bool multicast = is_multicast_ether_addr(hdr->addr1);
+	bool multicast = is_multicast_ether_addr(hdr->addr1) ||
+			 ieee80211_is_s1g_beacon(hdr->frame_control);
 
 	switch (sdata->vif.type) {
 	case NL80211_IFTYPE_STATION:
@@ -4577,7 +4566,8 @@ static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw,
 	ieee80211_verify_alignment(&rx);
 
 	if (unlikely(ieee80211_is_probe_resp(hdr->frame_control) ||
-		     ieee80211_is_beacon(hdr->frame_control)))
+		     ieee80211_is_beacon(hdr->frame_control) ||
+		     ieee80211_is_s1g_beacon(hdr->frame_control)))
 		ieee80211_scan_rx(local, skb);
 
 	if (ieee80211_is_data(fc)) {
diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c
index 5ac2785cdc7b..d4cc9ac2d703 100644
--- a/net/mac80211/scan.c
+++ b/net/mac80211/scan.c
@@ -9,7 +9,7 @@
  * Copyright 2007, Michael Wu <flamingice@sourmilk.net>
  * Copyright 2013-2015  Intel Mobile Communications GmbH
  * Copyright 2016-2017  Intel Deutschland GmbH
- * Copyright (C) 2018-2019 Intel Corporation
+ * Copyright (C) 2018-2020 Intel Corporation
  */
 
 #include <linux/if_arp.h>
@@ -146,7 +146,8 @@ ieee80211_bss_info_update(struct ieee80211_local *local,
 			  struct ieee80211_mgmt *mgmt, size_t len,
 			  struct ieee80211_channel *channel)
 {
-	bool beacon = ieee80211_is_beacon(mgmt->frame_control);
+	bool beacon = ieee80211_is_beacon(mgmt->frame_control) ||
+		      ieee80211_is_s1g_beacon(mgmt->frame_control);
 	struct cfg80211_bss *cbss, *non_tx_cbss;
 	struct ieee80211_bss *bss, *non_tx_bss;
 	struct cfg80211_inform_bss bss_meta = {
@@ -195,6 +196,11 @@ ieee80211_bss_info_update(struct ieee80211_local *local,
 		elements = mgmt->u.probe_resp.variable;
 		baselen = offsetof(struct ieee80211_mgmt,
 				   u.probe_resp.variable);
+	} else if (ieee80211_is_s1g_beacon(mgmt->frame_control)) {
+		struct ieee80211_ext *ext = (void *) mgmt;
+
+		baselen = offsetof(struct ieee80211_ext, u.s1g_beacon.variable);
+		elements = ext->u.s1g_beacon.variable;
 	} else {
 		baselen = offsetof(struct ieee80211_mgmt, u.beacon.variable);
 		elements = mgmt->u.beacon.variable;
@@ -246,9 +252,12 @@ void ieee80211_scan_rx(struct ieee80211_local *local, struct sk_buff *skb)
 	struct ieee80211_bss *bss;
 	struct ieee80211_channel *channel;
 
-	if (skb->len < 24 ||
-	    (!ieee80211_is_probe_resp(mgmt->frame_control) &&
-	     !ieee80211_is_beacon(mgmt->frame_control)))
+	if (ieee80211_is_s1g_beacon(mgmt->frame_control)) {
+		if (skb->len < 15)
+			return;
+	} else if (skb->len < 24 ||
+		 (!ieee80211_is_probe_resp(mgmt->frame_control) &&
+		  !ieee80211_is_beacon(mgmt->frame_control)))
 		return;
 
 	sdata1 = rcu_dereference(local->scan_sdata);
@@ -712,6 +721,10 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata,
 			req->duration_mandatory;
 
 		local->hw_scan_band = 0;
+		local->hw_scan_req->req.n_6ghz_params = req->n_6ghz_params;
+		local->hw_scan_req->req.scan_6ghz_params =
+			req->scan_6ghz_params;
+		local->hw_scan_req->req.scan_6ghz = req->scan_6ghz;
 
 		/*
 		 * After allocating local->hw_scan_req, we must
@@ -905,6 +918,17 @@ static void ieee80211_scan_state_set_channel(struct ieee80211_local *local,
 	local->scan_chandef.center_freq1 = chan->center_freq;
 	local->scan_chandef.freq1_offset = chan->freq_offset;
 	local->scan_chandef.center_freq2 = 0;
+
+	/* For scanning on the S1G band, ignore scan_width (which is constant
+	 * across all channels) for now since channel width is specific to each
+	 * channel. Detect the required channel width here and likely revisit
+	 * later. Maybe scan_width could be used to build the channel scan list?
+	 */
+	if (chan->band == NL80211_BAND_S1GHZ) {
+		local->scan_chandef.width = ieee80211_s1g_channel_width(chan);
+		goto set_channel;
+	}
+
 	switch (scan_req->scan_width) {
 	case NL80211_BSS_CHAN_WIDTH_5:
 		local->scan_chandef.width = NL80211_CHAN_WIDTH_5;
@@ -925,8 +949,14 @@ static void ieee80211_scan_state_set_channel(struct ieee80211_local *local,
 		else
 			local->scan_chandef.width = NL80211_CHAN_WIDTH_20_NOHT;
 		break;
+	case NL80211_BSS_CHAN_WIDTH_1:
+	case NL80211_BSS_CHAN_WIDTH_2:
+		/* shouldn't get here, S1G handled above */
+		WARN_ON(1);
+		break;
 	}
 
+set_channel:
 	if (ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_CHANNEL))
 		skip = 1;
 
@@ -1124,7 +1154,8 @@ int ieee80211_request_ibss_scan(struct ieee80211_sub_if_data *sdata,
 		int max_n;
 
 		for (band = 0; band < NUM_NL80211_BANDS; band++) {
-			if (!local->hw.wiphy->bands[band])
+			if (!local->hw.wiphy->bands[band] ||
+			    band == NL80211_BAND_6GHZ)
 				continue;
 
 			max_n = local->hw.wiphy->bands[band]->n_channels;
diff --git a/net/mac80211/status.c b/net/mac80211/status.c
index 7fe5bececfd9..6feb45135020 100644
--- a/net/mac80211/status.c
+++ b/net/mac80211/status.c
@@ -982,10 +982,6 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw,
 		if (!(info->flags & IEEE80211_TX_CTL_INJECTED) && acked)
 			ieee80211_frame_acked(sta, skb);
 
-		if ((sta->sdata->vif.type == NL80211_IFTYPE_STATION) &&
-		    ieee80211_hw_check(&local->hw, REPORTS_TX_ACK_STATUS))
-			ieee80211_sta_tx_notify(sta->sdata, (void *) skb->data,
-						acked, info->status.tx_time);
 	}
 
 	/* SNMP counters
@@ -1120,11 +1116,18 @@ void ieee80211_tx_status_ext(struct ieee80211_hw *hw,
 	noack_success = !!(info->flags & IEEE80211_TX_STAT_NOACK_TRANSMITTED);
 
 	if (pubsta) {
+		struct ieee80211_sub_if_data *sdata = sta->sdata;
+
 		if (!acked && !noack_success)
 			sta->status_stats.retry_failed++;
 		sta->status_stats.retry_count += retry_count;
 
 		if (ieee80211_hw_check(&local->hw, REPORTS_TX_ACK_STATUS)) {
+			if (sdata->vif.type == NL80211_IFTYPE_STATION &&
+			    skb && !(info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP))
+				ieee80211_sta_tx_notify(sdata, (void *) skb->data,
+							acked, info->status.tx_time);
+
 			if (acked) {
 				sta->status_stats.last_ack = jiffies;
 
@@ -1134,6 +1137,11 @@ void ieee80211_tx_status_ext(struct ieee80211_hw *hw,
 				/* Track when last packet was ACKed */
 				sta->status_stats.last_pkt_time = jiffies;
 
+				/* Reset connection monitor */
+				if (sdata->vif.type == NL80211_IFTYPE_STATION &&
+				    unlikely(sdata->u.mgd.probe_send_count > 0))
+					sdata->u.mgd.probe_send_count = 0;
+
 				if (info->status.is_valid_ack_signal) {
 					sta->status_stats.last_ack_signal =
 							 (s8)info->status.ack_signal;
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index adc83d830691..8ba10a48ded4 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -82,6 +82,10 @@ static __le16 ieee80211_duration(struct ieee80211_tx_data *tx,
 
 	erp = txrate->flags & IEEE80211_RATE_ERP_G;
 
+	/* device is expected to do this */
+	if (sband->band == NL80211_BAND_S1GHZ)
+		return 0;
+
 	/*
 	 * data and mgmt (except PS Poll):
 	 * - during CFP: 32768
@@ -2473,7 +2477,9 @@ static u16 ieee80211_store_ack_skb(struct ieee80211_local *local,
  * @sdata: virtual interface to build the header for
  * @skb: the skb to build the header in
  * @info_flags: skb flags to set
+ * @sta: the station pointer
  * @ctrl_flags: info control flags to set
+ * @cookie: cookie pointer to fill (if not %NULL)
  *
  * This function takes the skb with 802.3 header and reformats the header to
  * the appropriate IEEE 802.11 header based on which interface the packet is
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index c8504ffc71a1..49342060490f 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -45,6 +45,58 @@ struct ieee80211_hw *wiphy_to_ieee80211_hw(struct wiphy *wiphy)
 }
 EXPORT_SYMBOL(wiphy_to_ieee80211_hw);
 
+u8 *ieee80211_get_bssid(struct ieee80211_hdr *hdr, size_t len,
+			enum nl80211_iftype type)
+{
+	__le16 fc = hdr->frame_control;
+
+	if (ieee80211_is_data(fc)) {
+		if (len < 24) /* drop incorrect hdr len (data) */
+			return NULL;
+
+		if (ieee80211_has_a4(fc))
+			return NULL;
+		if (ieee80211_has_tods(fc))
+			return hdr->addr1;
+		if (ieee80211_has_fromds(fc))
+			return hdr->addr2;
+
+		return hdr->addr3;
+	}
+
+	if (ieee80211_is_s1g_beacon(fc)) {
+		struct ieee80211_ext *ext = (void *) hdr;
+
+		return ext->u.s1g_beacon.sa;
+	}
+
+	if (ieee80211_is_mgmt(fc)) {
+		if (len < 24) /* drop incorrect hdr len (mgmt) */
+			return NULL;
+		return hdr->addr3;
+	}
+
+	if (ieee80211_is_ctl(fc)) {
+		if (ieee80211_is_pspoll(fc))
+			return hdr->addr1;
+
+		if (ieee80211_is_back_req(fc)) {
+			switch (type) {
+			case NL80211_IFTYPE_STATION:
+				return hdr->addr2;
+			case NL80211_IFTYPE_AP:
+			case NL80211_IFTYPE_AP_VLAN:
+				return hdr->addr1;
+			default:
+				break; /* fall through to the return */
+			}
+		}
+	}
+
+	return NULL;
+}
+EXPORT_SYMBOL(ieee80211_get_bssid);
+
 void ieee80211_tx_set_protected(struct ieee80211_tx_data *tx)
 {
 	struct sk_buff *skb;
@@ -733,6 +785,9 @@ static void __iterate_interfaces(struct ieee80211_local *local,
 		if (!(iter_flags & IEEE80211_IFACE_ITER_RESUME_ALL) &&
 		    active_only && !(sdata->flags & IEEE80211_SDATA_IN_DRIVER))
 			continue;
+		if ((iter_flags & IEEE80211_IFACE_SKIP_SDATA_NOT_IN_DRIVER) &&
+		    !(sdata->flags & IEEE80211_SDATA_IN_DRIVER))
+			continue;
 		if (ieee80211_sdata_running(sdata) || !active_only)
 			iterator(data, sdata->vif.addr,
 				 &sdata->vif);
@@ -1003,6 +1058,11 @@ _ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action,
 		case WLAN_EID_LINK_ID:
 		case WLAN_EID_BSS_MAX_IDLE_PERIOD:
 		case WLAN_EID_RSNX:
+		case WLAN_EID_S1G_BCN_COMPAT:
+		case WLAN_EID_S1G_CAPABILITIES:
+		case WLAN_EID_S1G_OPERATION:
+		case WLAN_EID_AID_RESPONSE:
+		case WLAN_EID_S1G_SHORT_BCN_INTERVAL:
 		/*
 		 * not listing WLAN_EID_CHANNEL_SWITCH_WRAPPER -- it seems possible
 		 * that if the content gets bigger it might be needed more than once
@@ -1288,6 +1348,30 @@ _ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action,
 								&crc : NULL,
 							  elem, elems);
 			break;
+		case WLAN_EID_S1G_CAPABILITIES:
+			if (elen == sizeof(*elems->s1g_capab))
+				elems->s1g_capab = (void *)pos;
+			else
+				elem_parse_failed = true;
+			break;
+		case WLAN_EID_S1G_OPERATION:
+			if (elen == sizeof(*elems->s1g_oper))
+				elems->s1g_oper = (void *)pos;
+			else
+				elem_parse_failed = true;
+			break;
+		case WLAN_EID_S1G_BCN_COMPAT:
+			if (elen == sizeof(*elems->s1g_bcn_compat))
+				elems->s1g_bcn_compat = (void *)pos;
+			else
+				elem_parse_failed = true;
+			break;
+		case WLAN_EID_AID_RESPONSE:
+			if (elen == sizeof(struct ieee80211_aid_response_ie))
+				elems->aid_resp = (void *)pos;
+			else
+				elem_parse_failed = true;
+			break;
 		default:
 			break;
 		}
@@ -3353,9 +3437,10 @@ bool ieee80211_chandef_he_6ghz_oper(struct ieee80211_sub_if_data *sdata,
 		he_chandef.center_freq1 =
 			ieee80211_channel_to_frequency(he_6ghz_oper->ccfs0,
 						       NL80211_BAND_6GHZ);
-		he_chandef.center_freq2 =
-			ieee80211_channel_to_frequency(he_6ghz_oper->ccfs1,
-						       NL80211_BAND_6GHZ);
+		if (support_80_80 || support_160)
+			he_chandef.center_freq2 =
+				ieee80211_channel_to_frequency(he_6ghz_oper->ccfs1,
+							       NL80211_BAND_6GHZ);
 	}
 
 	if (!cfg80211_chandef_valid(&he_chandef)) {
@@ -3370,6 +3455,42 @@ bool ieee80211_chandef_he_6ghz_oper(struct ieee80211_sub_if_data *sdata,
 
 	*chandef = he_chandef;
 
+	return false;
+}
+
+bool ieee80211_chandef_s1g_oper(const struct ieee80211_s1g_oper_ie *oper,
+				struct cfg80211_chan_def *chandef)
+{
+	u32 oper_freq;
+
+	if (!oper)
+		return false;
+
+	switch (FIELD_GET(S1G_OPER_CH_WIDTH_OPER, oper->ch_width)) {
+	case IEEE80211_S1G_CHANWIDTH_1MHZ:
+		chandef->width = NL80211_CHAN_WIDTH_1;
+		break;
+	case IEEE80211_S1G_CHANWIDTH_2MHZ:
+		chandef->width = NL80211_CHAN_WIDTH_2;
+		break;
+	case IEEE80211_S1G_CHANWIDTH_4MHZ:
+		chandef->width = NL80211_CHAN_WIDTH_4;
+		break;
+	case IEEE80211_S1G_CHANWIDTH_8MHZ:
+		chandef->width = NL80211_CHAN_WIDTH_8;
+		break;
+	case IEEE80211_S1G_CHANWIDTH_16MHZ:
+		chandef->width = NL80211_CHAN_WIDTH_16;
+		break;
+	default:
+		return false;
+	}
+
+	oper_freq = ieee80211_channel_to_freq_khz(oper->oper_ch,
+						  NL80211_BAND_S1GHZ);
+	chandef->center_freq1 = KHZ_TO_MHZ(oper_freq);
+	chandef->freq1_offset = oper_freq % 1000;
+
 	return true;
 }
 
@@ -4276,6 +4397,58 @@ int ieee80211_max_num_channels(struct ieee80211_local *local)
 	return max_num_different_channels;
 }
 
+void ieee80211_add_s1g_capab_ie(struct ieee80211_sub_if_data *sdata,
+				struct ieee80211_sta_s1g_cap *caps,
+				struct sk_buff *skb)
+{
+	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
+	struct ieee80211_s1g_cap s1g_capab;
+	u8 *pos;
+	int i;
+
+	if (WARN_ON(sdata->vif.type != NL80211_IFTYPE_STATION))
+		return;
+
+	if (!caps->s1g)
+		return;
+
+	memcpy(s1g_capab.capab_info, caps->cap, sizeof(caps->cap));
+	memcpy(s1g_capab.supp_mcs_nss, caps->nss_mcs, sizeof(caps->nss_mcs));
+
+	/* override the capability info */
+	for (i = 0; i < sizeof(ifmgd->s1g_capa.capab_info); i++) {
+		u8 mask = ifmgd->s1g_capa_mask.capab_info[i];
+
+		s1g_capab.capab_info[i] &= ~mask;
+		s1g_capab.capab_info[i] |= ifmgd->s1g_capa.capab_info[i] & mask;
+	}
+
+	/* then MCS and NSS set */
+	for (i = 0; i < sizeof(ifmgd->s1g_capa.supp_mcs_nss); i++) {
+		u8 mask = ifmgd->s1g_capa_mask.supp_mcs_nss[i];
+
+		s1g_capab.supp_mcs_nss[i] &= ~mask;
+		s1g_capab.supp_mcs_nss[i] |=
+			ifmgd->s1g_capa.supp_mcs_nss[i] & mask;
+	}
+
+	pos = skb_put(skb, 2 + sizeof(s1g_capab));
+	*pos++ = WLAN_EID_S1G_CAPABILITIES;
+	*pos++ = sizeof(s1g_capab);
+
+	memcpy(pos, &s1g_capab, sizeof(s1g_capab));
+}
+
+void ieee80211_add_aid_request_ie(struct ieee80211_sub_if_data *sdata,
+				  struct sk_buff *skb)
+{
+	u8 *pos = skb_put(skb, 3);
+
+	*pos++ = WLAN_EID_AID_REQUEST;
+	*pos++ = 1;
+	*pos++ = 0;
+}
+
 u8 *ieee80211_add_wmm_info_ie(u8 *buf, u8 qosinfo)
 {
 	*buf++ = WLAN_EID_VENDOR_SPECIFIC;
@@ -4318,3 +4491,24 @@ const u8 ieee80211_ac_to_qos_mask[IEEE80211_NUM_ACS] = {
 	IEEE80211_WMM_IE_STA_QOSINFO_AC_BE,
 	IEEE80211_WMM_IE_STA_QOSINFO_AC_BK
 };
+
+u16 ieee80211_encode_usf(int listen_interval)
+{
+	static const int listen_int_usf[] = { 1, 10, 1000, 10000 };
+	u16 ui, usf = 0;
+
+	/* find greatest USF */
+	while (usf < IEEE80211_MAX_USF) {
+		if (listen_interval % listen_int_usf[usf + 1])
+			break;
+		usf += 1;
+	}
+	ui = listen_interval / listen_int_usf[usf];
+
+	/* error if there is a remainder. Should've been checked by user */
+	WARN_ON_ONCE(ui > IEEE80211_MAX_UI);
+	listen_interval = FIELD_PREP(LISTEN_INT_USF, usf) |
+			  FIELD_PREP(LISTEN_INT_UI, ui);
+
+	return (u16) listen_interval;
+}
diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c
index 7e601d067d53..fb0e3a657d2d 100644
--- a/net/mac80211/vht.c
+++ b/net/mac80211/vht.c
@@ -168,10 +168,7 @@ ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata,
 	/* take some capabilities as-is */
 	cap_info = le32_to_cpu(vht_cap_ie->vht_cap_info);
 	vht_cap->cap = cap_info;
-	vht_cap->cap &= IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_3895 |
-			IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_7991 |
-			IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_11454 |
-			IEEE80211_VHT_CAP_RXLDPC |
+	vht_cap->cap &= IEEE80211_VHT_CAP_RXLDPC |
 			IEEE80211_VHT_CAP_VHT_TXOP_PS |
 			IEEE80211_VHT_CAP_HTC_VHT |
 			IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_MASK |
@@ -180,6 +177,9 @@ ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata,
 			IEEE80211_VHT_CAP_RX_ANTENNA_PATTERN |
 			IEEE80211_VHT_CAP_TX_ANTENNA_PATTERN;
 
+	vht_cap->cap |= min_t(u32, cap_info & IEEE80211_VHT_CAP_MAX_MPDU_MASK,
+			      own_cap.cap & IEEE80211_VHT_CAP_MAX_MPDU_MASK);
+
 	/* and some based on our own capabilities */
 	switch (own_cap.cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK) {
 	case IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ:
diff --git a/net/mac802154/tx.c b/net/mac802154/tx.c
index ab52811523e9..c829e4a75325 100644
--- a/net/mac802154/tx.c
+++ b/net/mac802154/tx.c
@@ -34,11 +34,11 @@ void ieee802154_xmit_worker(struct work_struct *work)
 	if (res)
 		goto err_tx;
 
-	ieee802154_xmit_complete(&local->hw, skb, false);
-
 	dev->stats.tx_packets++;
 	dev->stats.tx_bytes += skb->len;
 
+	ieee802154_xmit_complete(&local->hw, skb, false);
+
 	return;
 
 err_tx:
@@ -78,6 +78,8 @@ ieee802154_tx(struct ieee802154_local *local, struct sk_buff *skb)
 
 	/* async is priority, otherwise sync is fallback */
 	if (local->ops->xmit_async) {
+		unsigned int len = skb->len;
+
 		ret = drv_xmit_async(local, skb);
 		if (ret) {
 			ieee802154_wake_queue(&local->hw);
@@ -85,7 +87,7 @@ ieee802154_tx(struct ieee802154_local *local, struct sk_buff *skb)
 		}
 
 		dev->stats.tx_packets++;
-		dev->stats.tx_bytes += skb->len;
+		dev->stats.tx_bytes += len;
 	} else {
 		local->tx_skb = skb;
 		queue_work(local->workqueue, &local->tx_work);
diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c
index 056986c7a228..84d119436b22 100644
--- a/net/mptcp/mib.c
+++ b/net/mptcp/mib.c
@@ -27,6 +27,10 @@ static const struct snmp_mib mptcp_snmp_list[] = {
 	SNMP_MIB_ITEM("OFOMerge", MPTCP_MIB_OFOMERGE),
 	SNMP_MIB_ITEM("NoDSSInWindow", MPTCP_MIB_NODSSWINDOW),
 	SNMP_MIB_ITEM("DuplicateData", MPTCP_MIB_DUPDATA),
+	SNMP_MIB_ITEM("AddAddr", MPTCP_MIB_ADDADDR),
+	SNMP_MIB_ITEM("EchoAdd", MPTCP_MIB_ECHOADD),
+	SNMP_MIB_ITEM("RmAddr", MPTCP_MIB_RMADDR),
+	SNMP_MIB_ITEM("RmSubflow", MPTCP_MIB_RMSUBFLOW),
 	SNMP_MIB_SENTINEL
 };
 
diff --git a/net/mptcp/mib.h b/net/mptcp/mib.h
index 937a177729f1..47bcecce1106 100644
--- a/net/mptcp/mib.h
+++ b/net/mptcp/mib.h
@@ -20,6 +20,10 @@ enum linux_mptcp_mib_field {
 	MPTCP_MIB_OFOMERGE,		/* Segments merged in OoO queue */
 	MPTCP_MIB_NODSSWINDOW,		/* Segments not in MPTCP windows */
 	MPTCP_MIB_DUPDATA,		/* Segments discarded due to duplicate DSS */
+	MPTCP_MIB_ADDADDR,		/* Received ADD_ADDR with echo-flag=0 */
+	MPTCP_MIB_ECHOADD,		/* Received ADD_ADDR with echo-flag=1 */
+	MPTCP_MIB_RMADDR,		/* Received RM_ADDR */
+	MPTCP_MIB_RMSUBFLOW,		/* Remove a subflow */
 	__MPTCP_MIB_MAX
 };
 
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index 7fa822b55c34..03794f89efeb 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -11,6 +11,7 @@
 #include <net/tcp.h>
 #include <net/mptcp.h>
 #include "protocol.h"
+#include "mib.h"
 
 static bool mptcp_cap_flag_sha256(u8 flags)
 {
@@ -242,7 +243,7 @@ static void mptcp_parse_option(const struct sk_buff *skb,
 		mp_opt->add_addr = 1;
 		mp_opt->port = 0;
 		mp_opt->addr_id = *ptr++;
-		pr_debug("ADD_ADDR: id=%d", mp_opt->addr_id);
+		pr_debug("ADD_ADDR: id=%d, echo=%d", mp_opt->addr_id, mp_opt->echo);
 		if (mp_opt->family == MPTCP_ADDR_IPVERSION_4) {
 			memcpy((u8 *)&mp_opt->addr.s_addr, (u8 *)ptr, 4);
 			ptr += 4;
@@ -571,21 +572,22 @@ static u64 add_addr6_generate_hmac(u64 key1, u64 key2, u8 addr_id,
 }
 #endif
 
-static bool mptcp_established_options_addr(struct sock *sk,
-					   unsigned int *size,
-					   unsigned int remaining,
-					   struct mptcp_out_options *opts)
+static bool mptcp_established_options_add_addr(struct sock *sk,
+					       unsigned int *size,
+					       unsigned int remaining,
+					       struct mptcp_out_options *opts)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
 	struct mptcp_sock *msk = mptcp_sk(subflow->conn);
 	struct mptcp_addr_info saddr;
+	bool echo;
 	int len;
 
-	if (!mptcp_pm_should_signal(msk) ||
-	    !(mptcp_pm_addr_signal(msk, remaining, &saddr)))
+	if (!mptcp_pm_should_add_signal(msk) ||
+	    !(mptcp_pm_add_addr_signal(msk, remaining, &saddr, &echo)))
 		return false;
 
-	len = mptcp_add_addr_len(saddr.family);
+	len = mptcp_add_addr_len(saddr.family, echo);
 	if (remaining < len)
 		return false;
 
@@ -594,22 +596,51 @@ static bool mptcp_established_options_addr(struct sock *sk,
 	if (saddr.family == AF_INET) {
 		opts->suboptions |= OPTION_MPTCP_ADD_ADDR;
 		opts->addr = saddr.addr;
-		opts->ahmac = add_addr_generate_hmac(msk->local_key,
-						     msk->remote_key,
-						     opts->addr_id,
-						     &opts->addr);
+		if (!echo) {
+			opts->ahmac = add_addr_generate_hmac(msk->local_key,
+							     msk->remote_key,
+							     opts->addr_id,
+							     &opts->addr);
+		}
 	}
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
 	else if (saddr.family == AF_INET6) {
 		opts->suboptions |= OPTION_MPTCP_ADD_ADDR6;
 		opts->addr6 = saddr.addr6;
-		opts->ahmac = add_addr6_generate_hmac(msk->local_key,
-						      msk->remote_key,
-						      opts->addr_id,
-						      &opts->addr6);
+		if (!echo) {
+			opts->ahmac = add_addr6_generate_hmac(msk->local_key,
+							      msk->remote_key,
+							      opts->addr_id,
+							      &opts->addr6);
+		}
 	}
 #endif
-	pr_debug("addr_id=%d, ahmac=%llu", opts->addr_id, opts->ahmac);
+	pr_debug("addr_id=%d, ahmac=%llu, echo=%d", opts->addr_id, opts->ahmac, echo);
+
+	return true;
+}
+
+static bool mptcp_established_options_rm_addr(struct sock *sk,
+					      unsigned int *size,
+					      unsigned int remaining,
+					      struct mptcp_out_options *opts)
+{
+	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
+	struct mptcp_sock *msk = mptcp_sk(subflow->conn);
+	u8 rm_id;
+
+	if (!mptcp_pm_should_rm_signal(msk) ||
+	    !(mptcp_pm_rm_addr_signal(msk, remaining, &rm_id)))
+		return false;
+
+	if (remaining < TCPOLEN_MPTCP_RM_ADDR_BASE)
+		return false;
+
+	*size = TCPOLEN_MPTCP_RM_ADDR_BASE;
+	opts->suboptions |= OPTION_MPTCP_RM_ADDR;
+	opts->rm_id = rm_id;
+
+	pr_debug("rm_id=%d", opts->rm_id);
 
 	return true;
 }
@@ -640,7 +671,11 @@ bool mptcp_established_options(struct sock *sk, struct sk_buff *skb,
 
 	*size += opt_size;
 	remaining -= opt_size;
-	if (mptcp_established_options_addr(sk, &opt_size, remaining, opts)) {
+	if (mptcp_established_options_add_addr(sk, &opt_size, remaining, opts)) {
+		*size += opt_size;
+		remaining -= opt_size;
+		ret = true;
+	} else if (mptcp_established_options_rm_addr(sk, &opt_size, remaining, opts)) {
 		*size += opt_size;
 		remaining -= opt_size;
 		ret = true;
@@ -824,8 +859,7 @@ static bool add_addr_hmac_valid(struct mptcp_sock *msk,
 	return hmac == mp_opt->ahmac;
 }
 
-void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb,
-			    struct tcp_options_received *opt_rx)
+void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
 	struct mptcp_sock *msk = mptcp_sk(subflow->conn);
@@ -854,11 +888,21 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb,
 			addr.addr6 = mp_opt.addr6;
 		}
 #endif
-		if (!mp_opt.echo)
+		if (!mp_opt.echo) {
 			mptcp_pm_add_addr_received(msk, &addr);
+			MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ADDADDR);
+		} else {
+			mptcp_pm_del_add_timer(msk, &addr);
+			MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ECHOADD);
+		}
 		mp_opt.add_addr = 0;
 	}
 
+	if (mp_opt.rm_addr) {
+		mptcp_pm_rm_addr_received(msk, mp_opt.rm_id);
+		mp_opt.rm_addr = 0;
+	}
+
 	if (!mp_opt.dss)
 		return;
 
diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index a8ad20559aaa..e19e1525ecbb 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -13,23 +13,34 @@
 /* path manager command handlers */
 
 int mptcp_pm_announce_addr(struct mptcp_sock *msk,
-			   const struct mptcp_addr_info *addr)
+			   const struct mptcp_addr_info *addr,
+			   bool echo)
 {
 	pr_debug("msk=%p, local_id=%d", msk, addr->id);
 
 	msk->pm.local = *addr;
-	WRITE_ONCE(msk->pm.addr_signal, true);
+	WRITE_ONCE(msk->pm.add_addr_echo, echo);
+	WRITE_ONCE(msk->pm.add_addr_signal, true);
 	return 0;
 }
 
 int mptcp_pm_remove_addr(struct mptcp_sock *msk, u8 local_id)
 {
-	return -ENOTSUPP;
+	pr_debug("msk=%p, local_id=%d", msk, local_id);
+
+	msk->pm.rm_id = local_id;
+	WRITE_ONCE(msk->pm.rm_addr_signal, true);
+	return 0;
 }
 
-int mptcp_pm_remove_subflow(struct mptcp_sock *msk, u8 remote_id)
+int mptcp_pm_remove_subflow(struct mptcp_sock *msk, u8 local_id)
 {
-	return -ENOTSUPP;
+	pr_debug("msk=%p, local_id=%d", msk, local_id);
+
+	spin_lock_bh(&msk->pm.lock);
+	mptcp_pm_nl_rm_subflow_received(msk, local_id);
+	spin_unlock_bh(&msk->pm.lock);
+	return 0;
 }
 
 /* path manager event handlers */
@@ -46,7 +57,7 @@ void mptcp_pm_new_connection(struct mptcp_sock *msk, int server_side)
 bool mptcp_pm_allow_new_subflow(struct mptcp_sock *msk)
 {
 	struct mptcp_pm_data *pm = &msk->pm;
-	int ret;
+	int ret = 0;
 
 	pr_debug("msk=%p subflows=%d max=%d allow=%d", msk, pm->subflows,
 		 pm->subflows_max, READ_ONCE(pm->accept_subflow));
@@ -56,9 +67,11 @@ bool mptcp_pm_allow_new_subflow(struct mptcp_sock *msk)
 		return false;
 
 	spin_lock_bh(&pm->lock);
-	ret = pm->subflows < pm->subflows_max;
-	if (ret && ++pm->subflows == pm->subflows_max)
-		WRITE_ONCE(pm->accept_subflow, false);
+	if (READ_ONCE(pm->accept_subflow)) {
+		ret = pm->subflows < pm->subflows_max;
+		if (ret && ++pm->subflows == pm->subflows_max)
+			WRITE_ONCE(pm->accept_subflow, false);
+	}
 	spin_unlock_bh(&pm->lock);
 
 	return ret;
@@ -135,38 +148,71 @@ void mptcp_pm_add_addr_received(struct mptcp_sock *msk,
 	pr_debug("msk=%p remote_id=%d accept=%d", msk, addr->id,
 		 READ_ONCE(pm->accept_addr));
 
-	/* avoid acquiring the lock if there is no room for fouther addresses */
-	if (!READ_ONCE(pm->accept_addr))
-		return;
-
 	spin_lock_bh(&pm->lock);
 
-	/* be sure there is something to signal re-checking under PM lock */
-	if (READ_ONCE(pm->accept_addr) &&
-	    mptcp_pm_schedule_work(msk, MPTCP_PM_ADD_ADDR_RECEIVED))
+	if (!READ_ONCE(pm->accept_addr))
+		mptcp_pm_announce_addr(msk, addr, true);
+	else if (mptcp_pm_schedule_work(msk, MPTCP_PM_ADD_ADDR_RECEIVED))
 		pm->remote = *addr;
 
 	spin_unlock_bh(&pm->lock);
 }
 
+void mptcp_pm_rm_addr_received(struct mptcp_sock *msk, u8 rm_id)
+{
+	struct mptcp_pm_data *pm = &msk->pm;
+
+	pr_debug("msk=%p remote_id=%d", msk, rm_id);
+
+	spin_lock_bh(&pm->lock);
+	mptcp_pm_schedule_work(msk, MPTCP_PM_RM_ADDR_RECEIVED);
+	pm->rm_id = rm_id;
+	spin_unlock_bh(&pm->lock);
+}
+
 /* path manager helpers */
 
-bool mptcp_pm_addr_signal(struct mptcp_sock *msk, unsigned int remaining,
-			  struct mptcp_addr_info *saddr)
+bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, unsigned int remaining,
+			      struct mptcp_addr_info *saddr, bool *echo)
 {
 	int ret = false;
 
 	spin_lock_bh(&msk->pm.lock);
 
 	/* double check after the lock is acquired */
-	if (!mptcp_pm_should_signal(msk))
+	if (!mptcp_pm_should_add_signal(msk))
 		goto out_unlock;
 
-	if (remaining < mptcp_add_addr_len(msk->pm.local.family))
+	*echo = READ_ONCE(msk->pm.add_addr_echo);
+
+	if (remaining < mptcp_add_addr_len(msk->pm.local.family, *echo))
 		goto out_unlock;
 
 	*saddr = msk->pm.local;
-	WRITE_ONCE(msk->pm.addr_signal, false);
+	WRITE_ONCE(msk->pm.add_addr_signal, false);
+	ret = true;
+
+out_unlock:
+	spin_unlock_bh(&msk->pm.lock);
+	return ret;
+}
+
+bool mptcp_pm_rm_addr_signal(struct mptcp_sock *msk, unsigned int remaining,
+			     u8 *rm_id)
+{
+	int ret = false;
+
+	spin_lock_bh(&msk->pm.lock);
+
+	/* double check after the lock is acquired */
+	if (!mptcp_pm_should_rm_signal(msk))
+		goto out_unlock;
+
+	if (remaining < TCPOLEN_MPTCP_RM_ADDR_BASE)
+		goto out_unlock;
+
+	*rm_id = msk->pm.rm_id;
+	WRITE_ONCE(msk->pm.rm_addr_signal, false);
 	ret = true;
 
 out_unlock:
@@ -185,13 +231,17 @@ void mptcp_pm_data_init(struct mptcp_sock *msk)
 	msk->pm.add_addr_accepted = 0;
 	msk->pm.local_addr_used = 0;
 	msk->pm.subflows = 0;
+	msk->pm.rm_id = 0;
 	WRITE_ONCE(msk->pm.work_pending, false);
-	WRITE_ONCE(msk->pm.addr_signal, false);
+	WRITE_ONCE(msk->pm.add_addr_signal, false);
+	WRITE_ONCE(msk->pm.rm_addr_signal, false);
 	WRITE_ONCE(msk->pm.accept_addr, false);
 	WRITE_ONCE(msk->pm.accept_subflow, false);
+	WRITE_ONCE(msk->pm.add_addr_echo, false);
 	msk->pm.status = 0;
 
 	spin_lock_init(&msk->pm.lock);
+	INIT_LIST_HEAD(&msk->pm.anno_list);
 
 	mptcp_pm_nl_data_init(msk);
 }
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 6947f4fee6b9..9f9cd41b7733 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -15,6 +15,7 @@
 #include <uapi/linux/mptcp.h>
 
 #include "protocol.h"
+#include "mib.h"
 
 /* forward declaration */
 static struct genl_family mptcp_genl_family;
@@ -27,6 +28,14 @@ struct mptcp_pm_addr_entry {
 	struct rcu_head		rcu;
 };
 
+struct mptcp_pm_add_entry {
+	struct list_head	list;
+	struct mptcp_addr_info	addr;
+	struct timer_list	add_timer;
+	struct mptcp_sock	*sock;
+	u8			retrans_times;
+};
+
 struct pm_nl_pernet {
 	/* protects pernet updates */
 	spinlock_t		lock;
@@ -40,6 +49,7 @@ struct pm_nl_pernet {
 };
 
 #define MPTCP_PM_ADDR_MAX	8
+#define ADD_ADDR_RETRANS_MAX	3
 
 static bool addresses_equal(const struct mptcp_addr_info *a,
 			    struct mptcp_addr_info *b, bool use_port)
@@ -64,6 +74,16 @@ static bool addresses_equal(const struct mptcp_addr_info *a,
 	return a->port == b->port;
 }
 
+static bool address_zero(const struct mptcp_addr_info *addr)
+{
+	struct mptcp_addr_info zero;
+
+	memset(&zero, 0, sizeof(zero));
+	zero.family = addr->family;
+
+	return addresses_equal(addr, &zero, false);
+}
+
 static void local_address(const struct sock_common *skc,
 			  struct mptcp_addr_info *addr)
 {
@@ -167,11 +187,126 @@ static void check_work_pending(struct mptcp_sock *msk)
 		WRITE_ONCE(msk->pm.work_pending, false);
 }
 
+static struct mptcp_pm_add_entry *
+lookup_anno_list_by_saddr(struct mptcp_sock *msk,
+			  struct mptcp_addr_info *addr)
+{
+	struct mptcp_pm_add_entry *entry;
+
+	list_for_each_entry(entry, &msk->pm.anno_list, list) {
+		if (addresses_equal(&entry->addr, addr, false))
+			return entry;
+	}
+
+	return NULL;
+}
+
+static void mptcp_pm_add_timer(struct timer_list *timer)
+{
+	struct mptcp_pm_add_entry *entry = from_timer(entry, timer, add_timer);
+	struct mptcp_sock *msk = entry->sock;
+	struct sock *sk = (struct sock *)msk;
+
+	pr_debug("msk=%p", msk);
+
+	if (!msk)
+		return;
+
+	if (inet_sk_state_load(sk) == TCP_CLOSE)
+		return;
+
+	if (!entry->addr.id)
+		return;
+
+	if (mptcp_pm_should_add_signal(msk)) {
+		sk_reset_timer(sk, timer, jiffies + TCP_RTO_MAX / 8);
+		goto out;
+	}
+
+	spin_lock_bh(&msk->pm.lock);
+
+	if (!mptcp_pm_should_add_signal(msk)) {
+		pr_debug("retransmit ADD_ADDR id=%d", entry->addr.id);
+		mptcp_pm_announce_addr(msk, &entry->addr, false);
+		entry->retrans_times++;
+	}
+
+	if (entry->retrans_times < ADD_ADDR_RETRANS_MAX)
+		sk_reset_timer(sk, timer, jiffies + TCP_RTO_MAX);
+
+	spin_unlock_bh(&msk->pm.lock);
+
+out:
+	__sock_put(sk);
+}
+
+struct mptcp_pm_add_entry *
+mptcp_pm_del_add_timer(struct mptcp_sock *msk,
+		       struct mptcp_addr_info *addr)
+{
+	struct mptcp_pm_add_entry *entry;
+	struct sock *sk = (struct sock *)msk;
+
+	spin_lock_bh(&msk->pm.lock);
+	entry = lookup_anno_list_by_saddr(msk, addr);
+	if (entry)
+		entry->retrans_times = ADD_ADDR_RETRANS_MAX;
+	spin_unlock_bh(&msk->pm.lock);
+
+	if (entry)
+		sk_stop_timer_sync(sk, &entry->add_timer);
+
+	return entry;
+}
+
+static bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk,
+				     struct mptcp_pm_addr_entry *entry)
+{
+	struct mptcp_pm_add_entry *add_entry = NULL;
+	struct sock *sk = (struct sock *)msk;
+
+	if (lookup_anno_list_by_saddr(msk, &entry->addr))
+		return false;
+
+	add_entry = kmalloc(sizeof(*add_entry), GFP_ATOMIC);
+	if (!add_entry)
+		return false;
+
+	list_add(&add_entry->list, &msk->pm.anno_list);
+
+	add_entry->addr = entry->addr;
+	add_entry->sock = msk;
+	add_entry->retrans_times = 0;
+
+	timer_setup(&add_entry->add_timer, mptcp_pm_add_timer, 0);
+	sk_reset_timer(sk, &add_entry->add_timer, jiffies + TCP_RTO_MAX);
+
+	return true;
+}
+
+void mptcp_pm_free_anno_list(struct mptcp_sock *msk)
+{
+	struct mptcp_pm_add_entry *entry, *tmp;
+	struct sock *sk = (struct sock *)msk;
+	LIST_HEAD(free_list);
+
+	pr_debug("msk=%p", msk);
+
+	spin_lock_bh(&msk->pm.lock);
+	list_splice_init(&msk->pm.anno_list, &free_list);
+	spin_unlock_bh(&msk->pm.lock);
+
+	list_for_each_entry_safe(entry, tmp, &free_list, list) {
+		sk_stop_timer_sync(sk, &entry->add_timer);
+		kfree(entry);
+	}
+}
+
 static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
 {
+	struct mptcp_addr_info remote = { 0 };
 	struct sock *sk = (struct sock *)msk;
 	struct mptcp_pm_addr_entry *local;
-	struct mptcp_addr_info remote;
 	struct pm_nl_pernet *pernet;
 
 	pernet = net_generic(sock_net((struct sock *)msk), pm_nl_pernet_id);
@@ -187,8 +322,10 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
 					      msk->pm.add_addr_signaled);
 
 		if (local) {
-			msk->pm.add_addr_signaled++;
-			mptcp_pm_announce_addr(msk, &local->addr);
+			if (mptcp_pm_alloc_anno_list(msk, local)) {
+				msk->pm.add_addr_signaled++;
+				mptcp_pm_announce_addr(msk, &local->addr, false);
+			}
 		} else {
 			/* pick failed, avoid fourther attempts later */
 			msk->pm.local_addr_used = msk->pm.add_addr_signal_max;
@@ -256,6 +393,79 @@ void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk)
 	spin_unlock_bh(&msk->pm.lock);
 	__mptcp_subflow_connect((struct sock *)msk, &local, &remote);
 	spin_lock_bh(&msk->pm.lock);
+
+	mptcp_pm_announce_addr(msk, &remote, true);
+}
+
+void mptcp_pm_nl_rm_addr_received(struct mptcp_sock *msk)
+{
+	struct mptcp_subflow_context *subflow, *tmp;
+	struct sock *sk = (struct sock *)msk;
+
+	pr_debug("address rm_id %d", msk->pm.rm_id);
+
+	if (!msk->pm.rm_id)
+		return;
+
+	if (list_empty(&msk->conn_list))
+		return;
+
+	list_for_each_entry_safe(subflow, tmp, &msk->conn_list, node) {
+		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+		int how = RCV_SHUTDOWN | SEND_SHUTDOWN;
+		long timeout = 0;
+
+		if (msk->pm.rm_id != subflow->remote_id)
+			continue;
+
+		spin_unlock_bh(&msk->pm.lock);
+		mptcp_subflow_shutdown(sk, ssk, how);
+		__mptcp_close_ssk(sk, ssk, subflow, timeout);
+		spin_lock_bh(&msk->pm.lock);
+
+		msk->pm.add_addr_accepted--;
+		msk->pm.subflows--;
+		WRITE_ONCE(msk->pm.accept_addr, true);
+
+		__MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RMADDR);
+
+		break;
+	}
+}
+
+void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk, u8 rm_id)
+{
+	struct mptcp_subflow_context *subflow, *tmp;
+	struct sock *sk = (struct sock *)msk;
+
+	pr_debug("subflow rm_id %d", rm_id);
+
+	if (!rm_id)
+		return;
+
+	if (list_empty(&msk->conn_list))
+		return;
+
+	list_for_each_entry_safe(subflow, tmp, &msk->conn_list, node) {
+		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+		int how = RCV_SHUTDOWN | SEND_SHUTDOWN;
+		long timeout = 0;
+
+		if (rm_id != subflow->local_id)
+			continue;
+
+		spin_unlock_bh(&msk->pm.lock);
+		mptcp_subflow_shutdown(sk, ssk, how);
+		__mptcp_close_ssk(sk, ssk, subflow, timeout);
+		spin_lock_bh(&msk->pm.lock);
+
+		msk->pm.local_addr_used--;
+		msk->pm.subflows--;
+
+		__MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RMSUBFLOW);
+
+		break;
+	}
 }
 
 static bool address_use_port(struct mptcp_pm_addr_entry *entry)
@@ -320,10 +530,13 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc)
 	 * addr
 	 */
 	local_address((struct sock_common *)msk, &msk_local);
-	local_address((struct sock_common *)msk, &skc_local);
+	local_address((struct sock_common *)skc, &skc_local);
 	if (addresses_equal(&msk_local, &skc_local, false))
 		return 0;
 
+	if (address_zero(&skc_local))
+		return 0;
+
 	pernet = net_generic(sock_net((struct sock *)msk), pm_nl_pernet_id);
 
 	rcu_read_lock();
@@ -338,7 +551,7 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc)
 		return ret;
 
 	/* address not found, add to local list */
-	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
+	entry = kmalloc(sizeof(*entry), GFP_ATOMIC);
 	if (!entry)
 		return -ENOMEM;
 
@@ -518,6 +731,68 @@ __lookup_addr_by_id(struct pm_nl_pernet *pernet, unsigned int id)
 	return NULL;
 }
 
+static bool remove_anno_list_by_saddr(struct mptcp_sock *msk,
+				      struct mptcp_addr_info *addr)
+{
+	struct mptcp_pm_add_entry *entry;
+
+	entry = mptcp_pm_del_add_timer(msk, addr);
+	if (entry) {
+		list_del(&entry->list);
+		kfree(entry);
+		return true;
+	}
+
+	return false;
+}
+
+static bool mptcp_pm_remove_anno_addr(struct mptcp_sock *msk,
+				      struct mptcp_addr_info *addr,
+				      bool force)
+{
+	bool ret;
+
+	ret = remove_anno_list_by_saddr(msk, addr);
+	if (ret || force) {
+		spin_lock_bh(&msk->pm.lock);
+		mptcp_pm_remove_addr(msk, addr->id);
+		spin_unlock_bh(&msk->pm.lock);
+	}
+	return ret;
+}
+
+static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net,
+						   struct mptcp_addr_info *addr)
+{
+	struct mptcp_sock *msk;
+	long s_slot = 0, s_num = 0;
+
+	pr_debug("remove_id=%d", addr->id);
+
+	while ((msk = mptcp_token_iter_next(net, &s_slot, &s_num)) != NULL) {
+		struct sock *sk = (struct sock *)msk;
+		bool remove_subflow;
+
+		if (list_empty(&msk->conn_list)) {
+			mptcp_pm_remove_anno_addr(msk, addr, false);
+			goto next;
+		}
+
+		lock_sock(sk);
+		remove_subflow = lookup_subflow_by_saddr(&msk->conn_list, addr);
+		mptcp_pm_remove_anno_addr(msk, addr, remove_subflow);
+		if (remove_subflow)
+			mptcp_pm_remove_subflow(msk, addr->id);
+		release_sock(sk);
+
+next:
+		sock_put(sk);
+		cond_resched();
+	}
+
+	return 0;
+}
+
 static int mptcp_nl_cmd_del_addr(struct sk_buff *skb, struct genl_info *info)
 {
 	struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR];
@@ -533,8 +808,8 @@ static int mptcp_nl_cmd_del_addr(struct sk_buff *skb, struct genl_info *info)
 	entry = __lookup_addr_by_id(pernet, addr.addr.id);
 	if (!entry) {
 		GENL_SET_ERR_MSG(info, "address not found");
-		ret = -EINVAL;
-		goto out;
+		spin_unlock_bh(&pernet->lock);
+		return -EINVAL;
 	}
 	if (entry->addr.flags & MPTCP_PM_ADDR_FLAG_SIGNAL)
 		pernet->add_addr_signal_max--;
@@ -543,9 +818,11 @@ static int mptcp_nl_cmd_del_addr(struct sk_buff *skb, struct genl_info *info)
 
 	pernet->addrs--;
 	list_del_rcu(&entry->list);
-	kfree_rcu(entry, rcu);
-out:
 	spin_unlock_bh(&pernet->lock);
+
+	mptcp_nl_remove_subflow_and_signal_addr(sock_net(skb->sk), &entry->addr);
+	kfree_rcu(entry, rcu);
+
 	return ret;
 }
 
@@ -777,7 +1054,7 @@ fail:
 	return -EMSGSIZE;
 }
 
-static struct genl_ops mptcp_pm_ops[] = {
+static struct genl_small_ops mptcp_pm_ops[] = {
 	{
 		.cmd    = MPTCP_PM_CMD_ADD_ADDR,
 		.doit   = mptcp_nl_cmd_add_addr,
@@ -816,8 +1093,8 @@ static struct genl_family mptcp_genl_family __ro_after_init = {
 	.policy		= mptcp_pm_policy,
 	.netnsok	= true,
 	.module		= THIS_MODULE,
-	.ops		= mptcp_pm_ops,
-	.n_ops		= ARRAY_SIZE(mptcp_pm_ops),
+	.small_ops	= mptcp_pm_ops,
+	.n_small_ops	= ARRAY_SIZE(mptcp_pm_ops),
 	.mcgrps		= mptcp_pm_mcgrps,
 	.n_mcgrps	= ARRAY_SIZE(mptcp_pm_mcgrps),
 };
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 386cd4e60250..34c037731f35 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1652,9 +1652,9 @@ static struct sock *mptcp_subflow_get_retrans(const struct mptcp_sock *msk)
  * so we need to use tcp_close() after detaching them from the mptcp
  * parent socket.
  */
-static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
-			      struct mptcp_subflow_context *subflow,
-			      long timeout)
+void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
+		       struct mptcp_subflow_context *subflow,
+		       long timeout)
 {
 	struct socket *sock = READ_ONCE(ssk->sk_socket);
 
@@ -1685,6 +1685,10 @@ static void pm_work(struct mptcp_sock *msk)
 		pm->status &= ~BIT(MPTCP_PM_ADD_ADDR_RECEIVED);
 		mptcp_pm_nl_add_addr_received(msk);
 	}
+	if (pm->status & BIT(MPTCP_PM_RM_ADDR_RECEIVED)) {
+		pm->status &= ~BIT(MPTCP_PM_RM_ADDR_RECEIVED);
+		mptcp_pm_nl_rm_addr_received(msk);
+	}
 	if (pm->status & BIT(MPTCP_PM_ESTABLISHED)) {
 		pm->status &= ~BIT(MPTCP_PM_ESTABLISHED);
 		mptcp_pm_nl_fully_established(msk);
@@ -1806,16 +1810,16 @@ static int mptcp_init_sock(struct sock *sk)
 	struct net *net = sock_net(sk);
 	int ret;
 
+	ret = __mptcp_init_sock(sk);
+	if (ret)
+		return ret;
+
 	if (!mptcp_is_enabled(net))
 		return -ENOPROTOOPT;
 
 	if (unlikely(!net->mib.mptcp_statistics) && !mptcp_mib_alloc(net))
 		return -ENOMEM;
 
-	ret = __mptcp_init_sock(sk);
-	if (ret)
-		return ret;
-
 	ret = __mptcp_socket_create(mptcp_sk(sk));
 	if (ret)
 		return ret;
@@ -1846,7 +1850,7 @@ static void mptcp_cancel_work(struct sock *sk)
 		sock_put(sk);
 }
 
-static void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how)
+void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how)
 {
 	lock_sock(ssk);
 
@@ -2124,15 +2128,21 @@ static struct sock *mptcp_accept(struct sock *sk, int flags, int *err,
 	return newsk;
 }
 
+void mptcp_destroy_common(struct mptcp_sock *msk)
+{
+	skb_rbtree_purge(&msk->out_of_order_queue);
+	mptcp_token_destroy(msk);
+	mptcp_pm_free_anno_list(msk);
+}
+
 static void mptcp_destroy(struct sock *sk)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
 
-	skb_rbtree_purge(&msk->out_of_order_queue);
-	mptcp_token_destroy(msk);
 	if (msk->cached_ext)
 		__skb_ext_put(msk->cached_ext);
 
+	mptcp_destroy_common(msk);
 	sk_sockets_allocated_dec(sk);
 }
 
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 493bd2c13bc6..6eef4db9ee5c 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -152,6 +152,7 @@ struct mptcp_addr_info {
 
 enum mptcp_pm_status {
 	MPTCP_PM_ADD_ADDR_RECEIVED,
+	MPTCP_PM_RM_ADDR_RECEIVED,
 	MPTCP_PM_ESTABLISHED,
 	MPTCP_PM_SUBFLOW_ESTABLISHED,
 };
@@ -159,14 +160,17 @@ enum mptcp_pm_status {
 struct mptcp_pm_data {
 	struct mptcp_addr_info local;
 	struct mptcp_addr_info remote;
+	struct list_head anno_list;
 
 	spinlock_t	lock;		/*protects the whole PM data */
 
-	bool		addr_signal;
+	bool		add_addr_signal;
+	bool		rm_addr_signal;
 	bool		server_side;
 	bool		work_pending;
 	bool		accept_addr;
 	bool		accept_subflow;
+	bool		add_addr_echo;
 	u8		add_addr_signaled;
 	u8		add_addr_accepted;
 	u8		local_addr_used;
@@ -176,6 +180,7 @@ struct mptcp_pm_data {
 	u8		local_addr_max;
 	u8		subflows_max;
 	u8		status;
+	u8		rm_id;
 };
 
 struct mptcp_data_frag {
@@ -360,6 +365,10 @@ void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow,
 				     struct mptcp_options_received *mp_opt);
 bool mptcp_subflow_data_available(struct sock *sk);
 void __init mptcp_subflow_init(void);
+void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how);
+void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
+		       struct mptcp_subflow_context *subflow,
+		       long timeout);
 
 /* called with sk socket lock held */
 int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
@@ -399,6 +408,7 @@ bool mptcp_finish_join(struct sock *sk);
 void mptcp_data_acked(struct sock *sk);
 void mptcp_subflow_eof(struct sock *sk);
 bool mptcp_update_rcv_data_fin(struct mptcp_sock *msk, u64 data_fin_seq);
+void mptcp_destroy_common(struct mptcp_sock *msk);
 
 void __init mptcp_token_init(void);
 static inline void mptcp_token_init_request(struct request_sock *req)
@@ -432,26 +442,40 @@ void mptcp_pm_subflow_established(struct mptcp_sock *msk,
 void mptcp_pm_subflow_closed(struct mptcp_sock *msk, u8 id);
 void mptcp_pm_add_addr_received(struct mptcp_sock *msk,
 				const struct mptcp_addr_info *addr);
+void mptcp_pm_rm_addr_received(struct mptcp_sock *msk, u8 rm_id);
+void mptcp_pm_free_anno_list(struct mptcp_sock *msk);
+struct mptcp_pm_add_entry *
+mptcp_pm_del_add_timer(struct mptcp_sock *msk,
+		       struct mptcp_addr_info *addr);
 
 int mptcp_pm_announce_addr(struct mptcp_sock *msk,
-			   const struct mptcp_addr_info *addr);
+			   const struct mptcp_addr_info *addr,
+			   bool echo);
 int mptcp_pm_remove_addr(struct mptcp_sock *msk, u8 local_id);
-int mptcp_pm_remove_subflow(struct mptcp_sock *msk, u8 remote_id);
+int mptcp_pm_remove_subflow(struct mptcp_sock *msk, u8 local_id);
 
-static inline bool mptcp_pm_should_signal(struct mptcp_sock *msk)
+static inline bool mptcp_pm_should_add_signal(struct mptcp_sock *msk)
 {
-	return READ_ONCE(msk->pm.addr_signal);
+	return READ_ONCE(msk->pm.add_addr_signal);
 }
 
-static inline unsigned int mptcp_add_addr_len(int family)
+static inline bool mptcp_pm_should_rm_signal(struct mptcp_sock *msk)
+{
+	return READ_ONCE(msk->pm.rm_addr_signal);
+}
+
+static inline unsigned int mptcp_add_addr_len(int family, bool echo)
 {
 	if (family == AF_INET)
-		return TCPOLEN_MPTCP_ADD_ADDR;
-	return TCPOLEN_MPTCP_ADD_ADDR6;
+		return echo ? TCPOLEN_MPTCP_ADD_ADDR_BASE
+			    : TCPOLEN_MPTCP_ADD_ADDR;
+	return echo ? TCPOLEN_MPTCP_ADD_ADDR6_BASE : TCPOLEN_MPTCP_ADD_ADDR6;
 }
 
-bool mptcp_pm_addr_signal(struct mptcp_sock *msk, unsigned int remaining,
-			  struct mptcp_addr_info *saddr);
+bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, unsigned int remaining,
+			      struct mptcp_addr_info *saddr, bool *echo);
+bool mptcp_pm_rm_addr_signal(struct mptcp_sock *msk, unsigned int remaining,
+			     u8 *rm_id);
 int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc);
 
 void __init mptcp_pm_nl_init(void);
@@ -459,6 +483,8 @@ void mptcp_pm_nl_data_init(struct mptcp_sock *msk);
 void mptcp_pm_nl_fully_established(struct mptcp_sock *msk);
 void mptcp_pm_nl_subflow_established(struct mptcp_sock *msk);
 void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk);
+void mptcp_pm_nl_rm_addr_received(struct mptcp_sock *msk);
+void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk, u8 rm_id);
 int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc);
 
 static inline struct mptcp_ext *mptcp_get_ext(struct sk_buff *skb)
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 34d6230df017..ac2b19993f1a 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -435,8 +435,7 @@ static void mptcp_sock_destruct(struct sock *sk)
 		sock_orphan(sk);
 	}
 
-	skb_rbtree_purge(&mptcp_sk(sk)->out_of_order_queue);
-	mptcp_token_destroy(mptcp_sk(sk));
+	mptcp_destroy_common(mptcp_sk(sk));
 	inet_sock_destruct(sk);
 }
 
@@ -1044,6 +1043,7 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
 	struct mptcp_sock *msk = mptcp_sk(sk);
 	struct mptcp_subflow_context *subflow;
 	struct sockaddr_storage addr;
+	int remote_id = remote->id;
 	int local_id = loc->id;
 	struct socket *sf;
 	struct sock *ssk;
@@ -1088,10 +1088,11 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
 		goto failed;
 
 	mptcp_crypto_key_sha(subflow->remote_key, &remote_token, NULL);
-	pr_debug("msk=%p remote_token=%u local_id=%d", msk, remote_token,
-		 local_id);
+	pr_debug("msk=%p remote_token=%u local_id=%d remote_id=%d", msk,
+		 remote_token, local_id, remote_id);
 	subflow->remote_token = remote_token;
 	subflow->local_id = local_id;
+	subflow->remote_id = remote_id;
 	subflow->request_join = 1;
 	subflow->request_bkup = !!(loc->flags & MPTCP_PM_ADDR_FLAG_BACKUP);
 	mptcp_info2sockaddr(remote, &addr);
@@ -1328,6 +1329,7 @@ static void subflow_ulp_clone(const struct request_sock *req,
 		new_ctx->fully_established = 1;
 		new_ctx->backup = subflow_req->backup;
 		new_ctx->local_id = subflow_req->local_id;
+		new_ctx->remote_id = subflow_req->remote_id;
 		new_ctx->token = subflow_req->token;
 		new_ctx->thmac = subflow_req->thmac;
 	}
diff --git a/net/ncsi/ncsi-netlink.c b/net/ncsi/ncsi-netlink.c
index 8b386d766e7d..adddc7707aa4 100644
--- a/net/ncsi/ncsi-netlink.c
+++ b/net/ncsi/ncsi-netlink.c
@@ -716,7 +716,7 @@ static int ncsi_set_channel_mask_nl(struct sk_buff *msg,
 	return 0;
 }
 
-static const struct genl_ops ncsi_ops[] = {
+static const struct genl_small_ops ncsi_ops[] = {
 	{
 		.cmd = NCSI_CMD_PKG_INFO,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
@@ -762,8 +762,8 @@ static struct genl_family ncsi_genl_family __ro_after_init = {
 	.maxattr = NCSI_ATTR_MAX,
 	.policy = ncsi_genl_policy,
 	.module = THIS_MODULE,
-	.ops = ncsi_ops,
-	.n_ops = ARRAY_SIZE(ncsi_ops),
+	.small_ops = ncsi_ops,
+	.n_small_ops = ARRAY_SIZE(ncsi_ops),
 };
 
 int ncsi_init_netlink(struct net_device *dev)
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 8dbfd84322a8..e279ded4e306 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -3893,7 +3893,7 @@ out:
 }
 
 
-static const struct genl_ops ip_vs_genl_ops[] = {
+static const struct genl_small_ops ip_vs_genl_ops[] = {
 	{
 		.cmd	= IPVS_CMD_NEW_SERVICE,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
@@ -4001,8 +4001,8 @@ static struct genl_family ip_vs_genl_family __ro_after_init = {
 	.policy = ip_vs_cmd_policy,
 	.netnsok        = true,         /* Make ipvsadm to work on netns */
 	.module		= THIS_MODULE,
-	.ops		= ip_vs_genl_ops,
-	.n_ops		= ARRAY_SIZE(ip_vs_genl_ops),
+	.small_ops	= ip_vs_genl_ops,
+	.n_small_ops	= ARRAY_SIZE(ip_vs_genl_ops),
 };
 
 static int __init ip_vs_genl_register(void)
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 89d99f6dfd0a..3d0fd33be018 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -851,7 +851,6 @@ static int ctnetlink_done(struct netlink_callback *cb)
 }
 
 struct ctnetlink_filter {
-	u_int32_t cta_flags;
 	u8 family;
 
 	u_int32_t orig_flags;
@@ -906,10 +905,6 @@ static int ctnetlink_parse_tuple_filter(const struct nlattr * const cda[],
 					 struct nf_conntrack_zone *zone,
 					 u_int32_t flags);
 
-/* applied on filters */
-#define CTA_FILTER_F_CTA_MARK			(1 << 0)
-#define CTA_FILTER_F_CTA_MARK_MASK		(1 << 1)
-
 static struct ctnetlink_filter *
 ctnetlink_alloc_filter(const struct nlattr * const cda[], u8 family)
 {
@@ -930,14 +925,10 @@ ctnetlink_alloc_filter(const struct nlattr * const cda[], u8 family)
 #ifdef CONFIG_NF_CONNTRACK_MARK
 	if (cda[CTA_MARK]) {
 		filter->mark.val = ntohl(nla_get_be32(cda[CTA_MARK]));
-		filter->cta_flags |= CTA_FILTER_FLAG(CTA_MARK);
-
-		if (cda[CTA_MARK_MASK]) {
+		if (cda[CTA_MARK_MASK])
 			filter->mark.mask = ntohl(nla_get_be32(cda[CTA_MARK_MASK]));
-			filter->cta_flags |= CTA_FILTER_FLAG(CTA_MARK_MASK);
-		} else {
+		else
 			filter->mark.mask = 0xffffffff;
-		}
 	} else if (cda[CTA_MARK_MASK]) {
 		err = -EINVAL;
 		goto err_filter;
@@ -1117,11 +1108,7 @@ static int ctnetlink_filter_match(struct nf_conn *ct, void *data)
 	}
 
 #ifdef CONFIG_NF_CONNTRACK_MARK
-	if ((filter->cta_flags & CTA_FILTER_FLAG(CTA_MARK_MASK)) &&
-	    (ct->mark & filter->mark.mask) != filter->mark.val)
-		goto ignore_entry;
-	else if ((filter->cta_flags & CTA_FILTER_FLAG(CTA_MARK)) &&
-		 ct->mark != filter->mark.val)
+	if ((ct->mark & filter->mark.mask) != filter->mark.val)
 		goto ignore_entry;
 #endif
 
@@ -1404,7 +1391,8 @@ ctnetlink_parse_tuple_filter(const struct nlattr * const cda[],
 	if (err < 0)
 		return err;
 
-
+	if (l3num != NFPROTO_IPV4 && l3num != NFPROTO_IPV6)
+		return -EOPNOTSUPP;
 	tuple->src.l3num = l3num;
 
 	if (flags & CTA_FILTER_FLAG(CTA_IP_DST) ||
diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c
index 95f79980348c..47e9319d2cf3 100644
--- a/net/netfilter/nf_conntrack_proto.c
+++ b/net/netfilter/nf_conntrack_proto.c
@@ -565,6 +565,7 @@ static int nf_ct_netns_inet_get(struct net *net)
 	int err;
 
 	err = nf_ct_netns_do_get(net, NFPROTO_IPV4);
+#if IS_ENABLED(CONFIG_IPV6)
 	if (err < 0)
 		goto err1;
 	err = nf_ct_netns_do_get(net, NFPROTO_IPV6);
@@ -575,6 +576,7 @@ static int nf_ct_netns_inet_get(struct net *net)
 err2:
 	nf_ct_netns_put(net, NFPROTO_IPV4);
 err1:
+#endif
 	return err;
 }
 
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 3cfff31e4818..ae2c04d411b1 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -691,6 +691,18 @@ nla_put_failure:
 	return -1;
 }
 
+struct nftnl_skb_parms {
+	bool report;
+};
+#define NFT_CB(skb)	(*(struct nftnl_skb_parms*)&((skb)->cb))
+
+static void nft_notify_enqueue(struct sk_buff *skb, bool report,
+			       struct list_head *notify_list)
+{
+	NFT_CB(skb).report = report;
+	list_add_tail(&skb->list, notify_list);
+}
+
 static void nf_tables_table_notify(const struct nft_ctx *ctx, int event)
 {
 	struct sk_buff *skb;
@@ -722,8 +734,7 @@ static void nf_tables_table_notify(const struct nft_ctx *ctx, int event)
 		goto err;
 	}
 
-	nfnetlink_send(skb, ctx->net, ctx->portid, NFNLGRP_NFTABLES,
-		       ctx->report, GFP_KERNEL);
+	nft_notify_enqueue(skb, ctx->report, &ctx->net->nft.notify_list);
 	return;
 err:
 	nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES, -ENOBUFS);
@@ -1492,8 +1503,7 @@ static void nf_tables_chain_notify(const struct nft_ctx *ctx, int event)
 		goto err;
 	}
 
-	nfnetlink_send(skb, ctx->net, ctx->portid, NFNLGRP_NFTABLES,
-		       ctx->report, GFP_KERNEL);
+	nft_notify_enqueue(skb, ctx->report, &ctx->net->nft.notify_list);
 	return;
 err:
 	nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES, -ENOBUFS);
@@ -2842,8 +2852,7 @@ static void nf_tables_rule_notify(const struct nft_ctx *ctx,
 		goto err;
 	}
 
-	nfnetlink_send(skb, ctx->net, ctx->portid, NFNLGRP_NFTABLES,
-		       ctx->report, GFP_KERNEL);
+	nft_notify_enqueue(skb, ctx->report, &ctx->net->nft.notify_list);
 	return;
 err:
 	nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES, -ENOBUFS);
@@ -3872,8 +3881,7 @@ static void nf_tables_set_notify(const struct nft_ctx *ctx,
 		goto err;
 	}
 
-	nfnetlink_send(skb, ctx->net, portid, NFNLGRP_NFTABLES, ctx->report,
-		       gfp_flags);
+	nft_notify_enqueue(skb, ctx->report, &ctx->net->nft.notify_list);
 	return;
 err:
 	nfnetlink_set_err(ctx->net, portid, NFNLGRP_NFTABLES, -ENOBUFS);
@@ -4994,8 +5002,7 @@ static void nf_tables_setelem_notify(const struct nft_ctx *ctx,
 		goto err;
 	}
 
-	nfnetlink_send(skb, net, portid, NFNLGRP_NFTABLES, ctx->report,
-		       GFP_KERNEL);
+	nft_notify_enqueue(skb, ctx->report, &ctx->net->nft.notify_list);
 	return;
 err:
 	nfnetlink_set_err(net, portid, NFNLGRP_NFTABLES, -ENOBUFS);
@@ -6327,7 +6334,7 @@ void nft_obj_notify(struct net *net, const struct nft_table *table,
 		goto err;
 	}
 
-	nfnetlink_send(skb, net, portid, NFNLGRP_NFTABLES, report, gfp);
+	nft_notify_enqueue(skb, report, &net->nft.notify_list);
 	return;
 err:
 	nfnetlink_set_err(net, portid, NFNLGRP_NFTABLES, -ENOBUFS);
@@ -7137,8 +7144,7 @@ static void nf_tables_flowtable_notify(struct nft_ctx *ctx,
 		goto err;
 	}
 
-	nfnetlink_send(skb, ctx->net, ctx->portid, NFNLGRP_NFTABLES,
-		       ctx->report, GFP_KERNEL);
+	nft_notify_enqueue(skb, ctx->report, &ctx->net->nft.notify_list);
 	return;
 err:
 	nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES, -ENOBUFS);
@@ -7747,6 +7753,41 @@ static void nf_tables_commit_release(struct net *net)
 	mutex_unlock(&net->nft.commit_mutex);
 }
 
+static void nft_commit_notify(struct net *net, u32 portid)
+{
+	struct sk_buff *batch_skb = NULL, *nskb, *skb;
+	unsigned char *data;
+	int len;
+
+	list_for_each_entry_safe(skb, nskb, &net->nft.notify_list, list) {
+		if (!batch_skb) {
+new_batch:
+			batch_skb = skb;
+			len = NLMSG_GOODSIZE - skb->len;
+			list_del(&skb->list);
+			continue;
+		}
+		len -= skb->len;
+		if (len > 0 && NFT_CB(skb).report == NFT_CB(batch_skb).report) {
+			data = skb_put(batch_skb, skb->len);
+			memcpy(data, skb->data, skb->len);
+			list_del(&skb->list);
+			kfree_skb(skb);
+			continue;
+		}
+		nfnetlink_send(batch_skb, net, portid, NFNLGRP_NFTABLES,
+			       NFT_CB(batch_skb).report, GFP_KERNEL);
+		goto new_batch;
+	}
+
+	if (batch_skb) {
+		nfnetlink_send(batch_skb, net, portid, NFNLGRP_NFTABLES,
+			       NFT_CB(batch_skb).report, GFP_KERNEL);
+	}
+
+	WARN_ON_ONCE(!list_empty(&net->nft.notify_list));
+}
+
 static int nf_tables_commit(struct net *net, struct sk_buff *skb)
 {
 	struct nft_trans *trans, *next;
@@ -7949,6 +7990,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
 		}
 	}
 
+	nft_commit_notify(net, NETLINK_CB(skb).portid);
 	nf_tables_gen_notify(net, skb, NFT_MSG_NEWGEN);
 	nf_tables_commit_release(net);
 
@@ -8773,6 +8815,7 @@ static int __net_init nf_tables_init_net(struct net *net)
 	INIT_LIST_HEAD(&net->nft.tables);
 	INIT_LIST_HEAD(&net->nft.commit_list);
 	INIT_LIST_HEAD(&net->nft.module_list);
+	INIT_LIST_HEAD(&net->nft.notify_list);
 	mutex_init(&net->nft.commit_mutex);
 	net->nft.base_seq = 1;
 	net->nft.validate_state = NFT_VALIDATE_SKIP;
@@ -8789,6 +8832,7 @@ static void __net_exit nf_tables_exit_net(struct net *net)
 	mutex_unlock(&net->nft.commit_mutex);
 	WARN_ON_ONCE(!list_empty(&net->nft.tables));
 	WARN_ON_ONCE(!list_empty(&net->nft.module_list));
+	WARN_ON_ONCE(!list_empty(&net->nft.notify_list));
 }
 
 static struct pernet_operations nf_tables_net_ops = {
diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c
index 7bc6537f3ccb..b37bd02448d8 100644
--- a/net/netfilter/nft_meta.c
+++ b/net/netfilter/nft_meta.c
@@ -147,11 +147,11 @@ nft_meta_get_eval_skugid(enum nft_meta_keys key,
 
 	switch (key) {
 	case NFT_META_SKUID:
-		*dest = from_kuid_munged(&init_user_ns,
+		*dest = from_kuid_munged(sock_net(sk)->user_ns,
 					 sock->file->f_cred->fsuid);
 		break;
 	case NFT_META_SKGID:
-		*dest =	from_kgid_munged(&init_user_ns,
+		*dest =	from_kgid_munged(sock_net(sk)->user_ns,
 					 sock->file->f_cred->fsgid);
 		break;
 	default:
diff --git a/net/netlabel/netlabel_calipso.c b/net/netlabel/netlabel_calipso.c
index 1a98247ab148..4e62f2ad3575 100644
--- a/net/netlabel/netlabel_calipso.c
+++ b/net/netlabel/netlabel_calipso.c
@@ -304,7 +304,7 @@ static int netlbl_calipso_remove(struct sk_buff *skb, struct genl_info *info)
 /* NetLabel Generic NETLINK Command Definitions
  */
 
-static const struct genl_ops netlbl_calipso_ops[] = {
+static const struct genl_small_ops netlbl_calipso_ops[] = {
 	{
 	.cmd = NLBL_CALIPSO_C_ADD,
 	.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
@@ -342,8 +342,8 @@ static struct genl_family netlbl_calipso_gnl_family __ro_after_init = {
 	.maxattr = NLBL_CALIPSO_A_MAX,
 	.policy = calipso_genl_policy,
 	.module = THIS_MODULE,
-	.ops = netlbl_calipso_ops,
-	.n_ops = ARRAY_SIZE(netlbl_calipso_ops),
+	.small_ops = netlbl_calipso_ops,
+	.n_small_ops = ARRAY_SIZE(netlbl_calipso_ops),
 };
 
 /* NetLabel Generic NETLINK Protocol Functions
diff --git a/net/netlabel/netlabel_cipso_v4.c b/net/netlabel/netlabel_cipso_v4.c
index 0f16080b87cb..726dda95934c 100644
--- a/net/netlabel/netlabel_cipso_v4.c
+++ b/net/netlabel/netlabel_cipso_v4.c
@@ -724,7 +724,7 @@ static int netlbl_cipsov4_remove(struct sk_buff *skb, struct genl_info *info)
  * NetLabel Generic NETLINK Command Definitions
  */
 
-static const struct genl_ops netlbl_cipsov4_ops[] = {
+static const struct genl_small_ops netlbl_cipsov4_ops[] = {
 	{
 	.cmd = NLBL_CIPSOV4_C_ADD,
 	.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
@@ -762,8 +762,8 @@ static struct genl_family netlbl_cipsov4_gnl_family __ro_after_init = {
 	.maxattr = NLBL_CIPSOV4_A_MAX,
 	.policy = netlbl_cipsov4_genl_policy,
 	.module = THIS_MODULE,
-	.ops = netlbl_cipsov4_ops,
-	.n_ops = ARRAY_SIZE(netlbl_cipsov4_ops),
+	.small_ops = netlbl_cipsov4_ops,
+	.n_small_ops = ARRAY_SIZE(netlbl_cipsov4_ops),
 };
 
 /*
diff --git a/net/netlabel/netlabel_mgmt.c b/net/netlabel/netlabel_mgmt.c
index e7a25fbfaf8b..eb1d66d20afb 100644
--- a/net/netlabel/netlabel_mgmt.c
+++ b/net/netlabel/netlabel_mgmt.c
@@ -757,7 +757,7 @@ version_failure:
  * NetLabel Generic NETLINK Command Definitions
  */
 
-static const struct genl_ops netlbl_mgmt_genl_ops[] = {
+static const struct genl_small_ops netlbl_mgmt_genl_ops[] = {
 	{
 	.cmd = NLBL_MGMT_C_ADD,
 	.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
@@ -823,8 +823,8 @@ static struct genl_family netlbl_mgmt_gnl_family __ro_after_init = {
 	.maxattr = NLBL_MGMT_A_MAX,
 	.policy = netlbl_mgmt_genl_policy,
 	.module = THIS_MODULE,
-	.ops = netlbl_mgmt_genl_ops,
-	.n_ops = ARRAY_SIZE(netlbl_mgmt_genl_ops),
+	.small_ops = netlbl_mgmt_genl_ops,
+	.n_small_ops = ARRAY_SIZE(netlbl_mgmt_genl_ops),
 };
 
 /*
diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c
index 77bb1bb22c3b..2e8e3f7b2111 100644
--- a/net/netlabel/netlabel_unlabeled.c
+++ b/net/netlabel/netlabel_unlabeled.c
@@ -1301,7 +1301,7 @@ unlabel_staticlistdef_return:
  * NetLabel Generic NETLINK Command Definitions
  */
 
-static const struct genl_ops netlbl_unlabel_genl_ops[] = {
+static const struct genl_small_ops netlbl_unlabel_genl_ops[] = {
 	{
 	.cmd = NLBL_UNLABEL_C_STATICADD,
 	.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
@@ -1367,8 +1367,8 @@ static struct genl_family netlbl_unlabel_gnl_family __ro_after_init = {
 	.maxattr = NLBL_UNLABEL_A_MAX,
 	.policy = netlbl_unlabel_genl_policy,
 	.module = THIS_MODULE,
-	.ops = netlbl_unlabel_genl_ops,
-	.n_ops = ARRAY_SIZE(netlbl_unlabel_genl_ops),
+	.small_ops = netlbl_unlabel_genl_ops,
+	.n_small_ops = ARRAY_SIZE(netlbl_unlabel_genl_ops),
 };
 
 /*
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 4ec4c0f72f61..df675a8e1918 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2186,13 +2186,35 @@ EXPORT_SYMBOL(__nlmsg_put);
  * It would be better to create kernel thread.
  */
 
+static int netlink_dump_done(struct netlink_sock *nlk, struct sk_buff *skb,
+			     struct netlink_callback *cb,
+			     struct netlink_ext_ack *extack)
+{
+	struct nlmsghdr *nlh;
+
+	nlh = nlmsg_put_answer(skb, cb, NLMSG_DONE, sizeof(nlk->dump_done_errno),
+			       NLM_F_MULTI | cb->answer_flags);
+	if (WARN_ON(!nlh))
+		return -ENOBUFS;
+
+	nl_dump_check_consistent(cb, nlh);
+	memcpy(nlmsg_data(nlh), &nlk->dump_done_errno, sizeof(nlk->dump_done_errno));
+
+	if (extack->_msg && nlk->flags & NETLINK_F_EXT_ACK) {
+		nlh->nlmsg_flags |= NLM_F_ACK_TLVS;
+		if (!nla_put_string(skb, NLMSGERR_ATTR_MSG, extack->_msg))
+			nlmsg_end(skb, nlh);
+	}
+
+	return 0;
+}
+
 static int netlink_dump(struct sock *sk)
 {
 	struct netlink_sock *nlk = nlk_sk(sk);
 	struct netlink_ext_ack extack = {};
 	struct netlink_callback *cb;
 	struct sk_buff *skb = NULL;
-	struct nlmsghdr *nlh;
 	struct module *module;
 	int err = -ENOBUFS;
 	int alloc_min_size;
@@ -2258,22 +2280,19 @@ static int netlink_dump(struct sock *sk)
 		return 0;
 	}
 
-	nlh = nlmsg_put_answer(skb, cb, NLMSG_DONE,
-			       sizeof(nlk->dump_done_errno),
-			       NLM_F_MULTI | cb->answer_flags);
-	if (WARN_ON(!nlh))
+	if (netlink_dump_done(nlk, skb, cb, &extack))
 		goto errout_skb;
 
-	nl_dump_check_consistent(cb, nlh);
-
-	memcpy(nlmsg_data(nlh), &nlk->dump_done_errno,
-	       sizeof(nlk->dump_done_errno));
-
-	if (extack._msg && nlk->flags & NETLINK_F_EXT_ACK) {
-		nlh->nlmsg_flags |= NLM_F_ACK_TLVS;
-		if (!nla_put_string(skb, NLMSGERR_ATTR_MSG, extack._msg))
-			nlmsg_end(skb, nlh);
+#ifdef CONFIG_COMPAT_NETLINK_MESSAGES
+	/* frag_list skb's data is used for compat tasks
+	 * and the regular skb's data for normal (non-compat) tasks.
+	 * See netlink_recvmsg().
+	 */
+	if (unlikely(skb_shinfo(skb)->frag_list)) {
+		if (netlink_dump_done(nlk, skb_shinfo(skb)->frag_list, cb, &extack))
+			goto errout_skb;
 	}
+#endif
 
 	if (sk_filter(sk, skb))
 		kfree_skb(skb);
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index 3a718e327515..c992424e4d63 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -107,16 +107,83 @@ static const struct genl_family *genl_family_find_byname(char *name)
 	return NULL;
 }
 
-static const struct genl_ops *genl_get_cmd(u8 cmd,
-					   const struct genl_family *family)
+static int genl_get_cmd_cnt(const struct genl_family *family)
+{
+	return family->n_ops + family->n_small_ops;
+}
+
+static void genl_op_from_full(const struct genl_family *family,
+			      unsigned int i, struct genl_ops *op)
+{
+	*op = family->ops[i];
+
+	if (!op->maxattr)
+		op->maxattr = family->maxattr;
+	if (!op->policy)
+		op->policy = family->policy;
+}
+
+static int genl_get_cmd_full(u32 cmd, const struct genl_family *family,
+			     struct genl_ops *op)
 {
 	int i;
 
 	for (i = 0; i < family->n_ops; i++)
-		if (family->ops[i].cmd == cmd)
-			return &family->ops[i];
+		if (family->ops[i].cmd == cmd) {
+			genl_op_from_full(family, i, op);
+			return 0;
+		}
 
-	return NULL;
+	return -ENOENT;
+}
+
+static void genl_op_from_small(const struct genl_family *family,
+			       unsigned int i, struct genl_ops *op)
+{
+	memset(op, 0, sizeof(*op));
+	op->doit	= family->small_ops[i].doit;
+	op->dumpit	= family->small_ops[i].dumpit;
+	op->cmd		= family->small_ops[i].cmd;
+	op->internal_flags = family->small_ops[i].internal_flags;
+	op->flags	= family->small_ops[i].flags;
+	op->validate	= family->small_ops[i].validate;
+
+	op->maxattr = family->maxattr;
+	op->policy = family->policy;
+}
+
+static int genl_get_cmd_small(u32 cmd, const struct genl_family *family,
+			      struct genl_ops *op)
+{
+	int i;
+
+	for (i = 0; i < family->n_small_ops; i++)
+		if (family->small_ops[i].cmd == cmd) {
+			genl_op_from_small(family, i, op);
+			return 0;
+		}
+
+	return -ENOENT;
+}
+
+static int genl_get_cmd(u32 cmd, const struct genl_family *family,
+			struct genl_ops *op)
+{
+	if (!genl_get_cmd_full(cmd, family, op))
+		return 0;
+	return genl_get_cmd_small(cmd, family, op);
+}
+
+static void genl_get_cmd_by_index(unsigned int i,
+				  const struct genl_family *family,
+				  struct genl_ops *op)
+{
+	if (i < family->n_ops)
+		genl_op_from_full(family, i, op);
+	else if (i < family->n_ops + family->n_small_ops)
+		genl_op_from_small(family, i - family->n_ops, op);
+	else
+		WARN_ON_ONCE(1);
 }
 
 static int genl_allocate_reserve_groups(int n_groups, int *first_id)
@@ -286,22 +353,25 @@ static void genl_unregister_mc_groups(const struct genl_family *family)
 
 static int genl_validate_ops(const struct genl_family *family)
 {
-	const struct genl_ops *ops = family->ops;
-	unsigned int n_ops = family->n_ops;
 	int i, j;
 
-	if (WARN_ON(n_ops && !ops))
+	if (WARN_ON(family->n_ops && !family->ops) ||
+	    WARN_ON(family->n_small_ops && !family->small_ops))
 		return -EINVAL;
 
-	if (!n_ops)
-		return 0;
+	for (i = 0; i < genl_get_cmd_cnt(family); i++) {
+		struct genl_ops op;
 
-	for (i = 0; i < n_ops; i++) {
-		if (ops[i].dumpit == NULL && ops[i].doit == NULL)
+		genl_get_cmd_by_index(i, family, &op);
+		if (op.dumpit == NULL && op.doit == NULL)
 			return -EINVAL;
-		for (j = i + 1; j < n_ops; j++)
-			if (ops[i].cmd == ops[j].cmd)
+		for (j = i + 1; j < genl_get_cmd_cnt(family); j++) {
+			struct genl_ops op2;
+
+			genl_get_cmd_by_index(j, family, &op2);
+			if (op.cmd == op2.cmd)
 				return -EINVAL;
+		}
 	}
 
 	return 0;
@@ -467,16 +537,16 @@ genl_family_rcv_msg_attrs_parse(const struct genl_family *family,
 	struct nlattr **attrbuf;
 	int err;
 
-	if (!family->maxattr)
+	if (!ops->maxattr)
 		return NULL;
 
-	attrbuf = kmalloc_array(family->maxattr + 1,
+	attrbuf = kmalloc_array(ops->maxattr + 1,
 				sizeof(struct nlattr *), GFP_KERNEL);
 	if (!attrbuf)
 		return ERR_PTR(-ENOMEM);
 
-	err = __nlmsg_parse(nlh, hdrlen, attrbuf, family->maxattr,
-			    family->policy, validate, extack);
+	err = __nlmsg_parse(nlh, hdrlen, attrbuf, ops->maxattr, ops->policy,
+			    validate, extack);
 	if (err) {
 		kfree(attrbuf);
 		return ERR_PTR(err);
@@ -524,7 +594,7 @@ no_attrs:
 		return -ENOMEM;
 	}
 	info->family = ctx->family;
-	info->ops = ops;
+	info->op = *ops;
 	info->attrs = attrs;
 
 	cb->data = info;
@@ -546,7 +616,7 @@ no_attrs:
 
 static int genl_lock_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 {
-	const struct genl_ops *ops = genl_dumpit_info(cb)->ops;
+	const struct genl_ops *ops = &genl_dumpit_info(cb)->op;
 	int rc;
 
 	genl_lock();
@@ -558,7 +628,7 @@ static int genl_lock_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 static int genl_lock_done(struct netlink_callback *cb)
 {
 	const struct genl_dumpit_info *info = genl_dumpit_info(cb);
-	const struct genl_ops *ops = info->ops;
+	const struct genl_ops *ops = &info->op;
 	int rc = 0;
 
 	if (ops->done) {
@@ -574,7 +644,7 @@ static int genl_lock_done(struct netlink_callback *cb)
 static int genl_parallel_done(struct netlink_callback *cb)
 {
 	const struct genl_dumpit_info *info = genl_dumpit_info(cb);
-	const struct genl_ops *ops = info->ops;
+	const struct genl_ops *ops = &info->op;
 	int rc = 0;
 
 	if (ops->done)
@@ -682,9 +752,9 @@ static int genl_family_rcv_msg(const struct genl_family *family,
 			       struct nlmsghdr *nlh,
 			       struct netlink_ext_ack *extack)
 {
-	const struct genl_ops *ops;
 	struct net *net = sock_net(skb->sk);
 	struct genlmsghdr *hdr = nlmsg_data(nlh);
+	struct genl_ops op;
 	int hdrlen;
 
 	/* this family doesn't exist in this netns */
@@ -695,24 +765,23 @@ static int genl_family_rcv_msg(const struct genl_family *family,
 	if (nlh->nlmsg_len < nlmsg_msg_size(hdrlen))
 		return -EINVAL;
 
-	ops = genl_get_cmd(hdr->cmd, family);
-	if (ops == NULL)
+	if (genl_get_cmd(hdr->cmd, family, &op))
 		return -EOPNOTSUPP;
 
-	if ((ops->flags & GENL_ADMIN_PERM) &&
+	if ((op.flags & GENL_ADMIN_PERM) &&
 	    !netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
-	if ((ops->flags & GENL_UNS_ADMIN_PERM) &&
+	if ((op.flags & GENL_UNS_ADMIN_PERM) &&
 	    !netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN))
 		return -EPERM;
 
 	if ((nlh->nlmsg_flags & NLM_F_DUMP) == NLM_F_DUMP)
 		return genl_family_rcv_msg_dumpit(family, skb, nlh, extack,
-						  ops, hdrlen, net);
+						  &op, hdrlen, net);
 	else
 		return genl_family_rcv_msg_doit(family, skb, nlh, extack,
-						ops, hdrlen, net);
+						&op, hdrlen, net);
 }
 
 static int genl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
@@ -765,7 +834,7 @@ static int ctrl_fill_info(const struct genl_family *family, u32 portid, u32 seq,
 	    nla_put_u32(skb, CTRL_ATTR_MAXATTR, family->maxattr))
 		goto nla_put_failure;
 
-	if (family->n_ops) {
+	if (genl_get_cmd_cnt(family)) {
 		struct nlattr *nla_ops;
 		int i;
 
@@ -773,23 +842,25 @@ static int ctrl_fill_info(const struct genl_family *family, u32 portid, u32 seq,
 		if (nla_ops == NULL)
 			goto nla_put_failure;
 
-		for (i = 0; i < family->n_ops; i++) {
+		for (i = 0; i < genl_get_cmd_cnt(family); i++) {
 			struct nlattr *nest;
-			const struct genl_ops *ops = &family->ops[i];
-			u32 op_flags = ops->flags;
+			struct genl_ops op;
+			u32 op_flags;
 
-			if (ops->dumpit)
+			genl_get_cmd_by_index(i, family, &op);
+			op_flags = op.flags;
+			if (op.dumpit)
 				op_flags |= GENL_CMD_CAP_DUMP;
-			if (ops->doit)
+			if (op.doit)
 				op_flags |= GENL_CMD_CAP_DO;
-			if (family->policy)
+			if (op.policy)
 				op_flags |= GENL_CMD_CAP_HASPOL;
 
 			nest = nla_nest_start_noflag(skb, i + 1);
 			if (nest == NULL)
 				goto nla_put_failure;
 
-			if (nla_put_u32(skb, CTRL_ATTR_OP_ID, ops->cmd) ||
+			if (nla_put_u32(skb, CTRL_ATTR_OP_ID, op.cmd) ||
 			    nla_put_u32(skb, CTRL_ATTR_OP_FLAGS, op_flags))
 				goto nla_put_failure;
 
@@ -945,7 +1016,7 @@ ctrl_build_mcgrp_msg(const struct genl_family *family,
 	return skb;
 }
 
-static const struct nla_policy ctrl_policy[CTRL_ATTR_MAX+1] = {
+static const struct nla_policy ctrl_policy_family[] = {
 	[CTRL_ATTR_FAMILY_ID]	= { .type = NLA_U16 },
 	[CTRL_ATTR_FAMILY_NAME]	= { .type = NLA_NUL_STRING,
 				    .len = GENL_NAMSIZ - 1 },
@@ -1039,90 +1110,237 @@ static int genl_ctrl_event(int event, const struct genl_family *family,
 	return 0;
 }
 
-static int ctrl_dumppolicy(struct sk_buff *skb, struct netlink_callback *cb)
-{
+struct ctrl_dump_policy_ctx {
+	struct netlink_policy_dump_state *state;
 	const struct genl_family *rt;
-	unsigned int fam_id = cb->args[0];
-	int err;
+	unsigned int opidx;
+	u32 op;
+	u16 fam_id;
+	u8 policies:1,
+	   single_op:1;
+};
 
-	if (!fam_id) {
-		struct nlattr *tb[CTRL_ATTR_MAX + 1];
+static const struct nla_policy ctrl_policy_policy[] = {
+	[CTRL_ATTR_FAMILY_ID]	= { .type = NLA_U16 },
+	[CTRL_ATTR_FAMILY_NAME]	= { .type = NLA_NUL_STRING,
+				    .len = GENL_NAMSIZ - 1 },
+	[CTRL_ATTR_OP]		= { .type = NLA_U32 },
+};
 
-		err = genlmsg_parse(cb->nlh, &genl_ctrl, tb,
-				    genl_ctrl.maxattr,
-				    genl_ctrl.policy, cb->extack);
-		if (err)
-			return err;
+static int ctrl_dumppolicy_start(struct netlink_callback *cb)
+{
+	const struct genl_dumpit_info *info = genl_dumpit_info(cb);
+	struct ctrl_dump_policy_ctx *ctx = (void *)cb->ctx;
+	struct nlattr **tb = info->attrs;
+	const struct genl_family *rt;
+	struct genl_ops op;
+	int err, i;
 
-		if (!tb[CTRL_ATTR_FAMILY_ID] && !tb[CTRL_ATTR_FAMILY_NAME])
-			return -EINVAL;
+	BUILD_BUG_ON(sizeof(*ctx) > sizeof(cb->ctx));
 
-		if (tb[CTRL_ATTR_FAMILY_ID]) {
-			fam_id = nla_get_u16(tb[CTRL_ATTR_FAMILY_ID]);
-		} else {
-			rt = genl_family_find_byname(
-				nla_data(tb[CTRL_ATTR_FAMILY_NAME]));
-			if (!rt)
-				return -ENOENT;
-			fam_id = rt->id;
-		}
+	if (!tb[CTRL_ATTR_FAMILY_ID] && !tb[CTRL_ATTR_FAMILY_NAME])
+		return -EINVAL;
+
+	if (tb[CTRL_ATTR_FAMILY_ID]) {
+		ctx->fam_id = nla_get_u16(tb[CTRL_ATTR_FAMILY_ID]);
+	} else {
+		rt = genl_family_find_byname(
+			nla_data(tb[CTRL_ATTR_FAMILY_NAME]));
+		if (!rt)
+			return -ENOENT;
+		ctx->fam_id = rt->id;
 	}
 
-	rt = genl_family_find_byid(fam_id);
+	rt = genl_family_find_byid(ctx->fam_id);
 	if (!rt)
 		return -ENOENT;
 
-	if (!rt->policy)
+	ctx->rt = rt;
+
+	if (tb[CTRL_ATTR_OP]) {
+		ctx->single_op = true;
+		ctx->op = nla_get_u32(tb[CTRL_ATTR_OP]);
+
+		err = genl_get_cmd(ctx->op, rt, &op);
+		if (err) {
+			NL_SET_BAD_ATTR(cb->extack, tb[CTRL_ATTR_OP]);
+			return err;
+		}
+
+		if (!op.policy)
+			return -ENODATA;
+
+		return netlink_policy_dump_add_policy(&ctx->state, op.policy,
+						      op.maxattr);
+	}
+
+	for (i = 0; i < genl_get_cmd_cnt(rt); i++) {
+		genl_get_cmd_by_index(i, rt, &op);
+
+		if (op.policy) {
+			err = netlink_policy_dump_add_policy(&ctx->state,
+							     op.policy,
+							     op.maxattr);
+			if (err)
+				return err;
+		}
+	}
+
+	if (!ctx->state)
 		return -ENODATA;
+	return 0;
+}
 
-	err = netlink_policy_dump_start(rt->policy, rt->maxattr, &cb->args[1]);
-	if (err)
-		return err;
+static void *ctrl_dumppolicy_prep(struct sk_buff *skb,
+				  struct netlink_callback *cb)
+{
+	struct ctrl_dump_policy_ctx *ctx = (void *)cb->ctx;
+	void *hdr;
+
+	hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid,
+			  cb->nlh->nlmsg_seq, &genl_ctrl,
+			  NLM_F_MULTI, CTRL_CMD_GETPOLICY);
+	if (!hdr)
+		return NULL;
+
+	if (nla_put_u16(skb, CTRL_ATTR_FAMILY_ID, ctx->fam_id))
+		return NULL;
+
+	return hdr;
+}
+
+static int ctrl_dumppolicy_put_op(struct sk_buff *skb,
+				  struct netlink_callback *cb,
+			          struct genl_ops *op)
+{
+	struct ctrl_dump_policy_ctx *ctx = (void *)cb->ctx;
+	struct nlattr *nest_pol, *nest_op;
+	void *hdr;
+	int idx;
+
+	/* skip if we have nothing to show */
+	if (!op->policy)
+		return 0;
+	if (!op->doit &&
+	    (!op->dumpit || op->validate & GENL_DONT_VALIDATE_DUMP))
+		return 0;
+
+	hdr = ctrl_dumppolicy_prep(skb, cb);
+	if (!hdr)
+		return -ENOBUFS;
+
+	nest_pol = nla_nest_start(skb, CTRL_ATTR_OP_POLICY);
+	if (!nest_pol)
+		goto err;
+
+	nest_op = nla_nest_start(skb, op->cmd);
+	if (!nest_op)
+		goto err;
+
+	/* for now both do/dump are always the same */
+	idx = netlink_policy_dump_get_policy_idx(ctx->state,
+						 op->policy,
+						 op->maxattr);
+
+	if (op->doit && nla_put_u32(skb, CTRL_ATTR_POLICY_DO, idx))
+		goto err;
+
+	if (op->dumpit && !(op->validate & GENL_DONT_VALIDATE_DUMP) &&
+	    nla_put_u32(skb, CTRL_ATTR_POLICY_DUMP, idx))
+		goto err;
+
+	nla_nest_end(skb, nest_op);
+	nla_nest_end(skb, nest_pol);
+	genlmsg_end(skb, hdr);
+
+	return 0;
+err:
+	genlmsg_cancel(skb, hdr);
+	return -ENOBUFS;
+}
+
+static int ctrl_dumppolicy(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct ctrl_dump_policy_ctx *ctx = (void *)cb->ctx;
+	void *hdr;
+
+	if (!ctx->policies) {
+		while (ctx->opidx < genl_get_cmd_cnt(ctx->rt)) {
+			struct genl_ops op;
+
+			if (ctx->single_op) {
+				int err;
+
+				err = genl_get_cmd(ctx->op, ctx->rt, &op);
+				if (WARN_ON(err))
+					return skb->len;
+
+				/* break out of the loop after this one */
+				ctx->opidx = genl_get_cmd_cnt(ctx->rt);
+			} else {
+				genl_get_cmd_by_index(ctx->opidx, ctx->rt, &op);
+			}
+
+			if (ctrl_dumppolicy_put_op(skb, cb, &op))
+				return skb->len;
+
+			ctx->opidx++;
+		}
+
+		/* completed with the per-op policy index list */
+		ctx->policies = true;
+	}
 
-	while (netlink_policy_dump_loop(&cb->args[1])) {
-		void *hdr;
+	while (netlink_policy_dump_loop(ctx->state)) {
 		struct nlattr *nest;
 
-		hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid,
-				  cb->nlh->nlmsg_seq, &genl_ctrl,
-				  NLM_F_MULTI, CTRL_CMD_GETPOLICY);
+		hdr = ctrl_dumppolicy_prep(skb, cb);
 		if (!hdr)
 			goto nla_put_failure;
 
-		if (nla_put_u16(skb, CTRL_ATTR_FAMILY_ID, rt->id))
-			goto nla_put_failure;
-
 		nest = nla_nest_start(skb, CTRL_ATTR_POLICY);
 		if (!nest)
 			goto nla_put_failure;
 
-		if (netlink_policy_dump_write(skb, cb->args[1]))
+		if (netlink_policy_dump_write(skb, ctx->state))
 			goto nla_put_failure;
 
 		nla_nest_end(skb, nest);
 
 		genlmsg_end(skb, hdr);
-		continue;
-
-nla_put_failure:
-		genlmsg_cancel(skb, hdr);
-		break;
 	}
 
-	cb->args[0] = fam_id;
 	return skb->len;
+
+nla_put_failure:
+	genlmsg_cancel(skb, hdr);
+	return skb->len;
+}
+
+static int ctrl_dumppolicy_done(struct netlink_callback *cb)
+{
+	struct ctrl_dump_policy_ctx *ctx = (void *)cb->ctx;
+
+	netlink_policy_dump_free(ctx->state);
+	return 0;
 }
 
 static const struct genl_ops genl_ctrl_ops[] = {
 	{
 		.cmd		= CTRL_CMD_GETFAMILY,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.policy		= ctrl_policy_family,
+		.maxattr	= ARRAY_SIZE(ctrl_policy_family) - 1,
 		.doit		= ctrl_getfamily,
 		.dumpit		= ctrl_dumpfamily,
 	},
 	{
 		.cmd		= CTRL_CMD_GETPOLICY,
+		.policy		= ctrl_policy_policy,
+		.maxattr	= ARRAY_SIZE(ctrl_policy_policy) - 1,
+		.start		= ctrl_dumppolicy_start,
 		.dumpit		= ctrl_dumppolicy,
+		.done		= ctrl_dumppolicy_done,
 	},
 };
 
@@ -1139,8 +1357,6 @@ static struct genl_family genl_ctrl __ro_after_init = {
 	.id = GENL_ID_CTRL,
 	.name = "nlctrl",
 	.version = 0x2,
-	.maxattr = CTRL_ATTR_MAX,
-	.policy = ctrl_policy,
 	.netnsok = true,
 };
 
diff --git a/net/netlink/policy.c b/net/netlink/policy.c
index 62f977fa645a..cf23c0151721 100644
--- a/net/netlink/policy.c
+++ b/net/netlink/policy.c
@@ -14,7 +14,7 @@
 
 #define INITIAL_POLICIES_ALLOC	10
 
-struct nl_policy_dump {
+struct netlink_policy_dump_state {
 	unsigned int policy_idx;
 	unsigned int attr_idx;
 	unsigned int n_alloc;
@@ -24,18 +24,19 @@ struct nl_policy_dump {
 	} policies[];
 };
 
-static int add_policy(struct nl_policy_dump **statep,
+static int add_policy(struct netlink_policy_dump_state **statep,
 		      const struct nla_policy *policy,
 		      unsigned int maxtype)
 {
-	struct nl_policy_dump *state = *statep;
+	struct netlink_policy_dump_state *state = *statep;
 	unsigned int n_alloc, i;
 
 	if (!policy || !maxtype)
 		return 0;
 
 	for (i = 0; i < state->n_alloc; i++) {
-		if (state->policies[i].policy == policy)
+		if (state->policies[i].policy == policy &&
+		    state->policies[i].maxtype == maxtype)
 			return 0;
 
 		if (!state->policies[i].policy) {
@@ -62,43 +63,85 @@ static int add_policy(struct nl_policy_dump **statep,
 	return 0;
 }
 
-static unsigned int get_policy_idx(struct nl_policy_dump *state,
-				   const struct nla_policy *policy)
+/**
+ * netlink_policy_dump_get_policy_idx - retrieve policy index
+ * @state: the policy dump state
+ * @policy: the policy to find
+ * @maxtype: the policy's maxattr
+ *
+ * Returns: the index of the given policy in the dump state
+ *
+ * Call this to find a policy index when you've added multiple and e.g.
+ * need to tell userspace which command has which policy (by index).
+ *
+ * Note: this will WARN and return 0 if the policy isn't found, which
+ *	 means it wasn't added in the first place, which would be an
+ *	 internal consistency bug.
+ */
+int netlink_policy_dump_get_policy_idx(struct netlink_policy_dump_state *state,
+				       const struct nla_policy *policy,
+				       unsigned int maxtype)
 {
 	unsigned int i;
 
+	if (WARN_ON(!policy || !maxtype))
+                return 0;
+
 	for (i = 0; i < state->n_alloc; i++) {
-		if (state->policies[i].policy == policy)
+		if (state->policies[i].policy == policy &&
+		    state->policies[i].maxtype == maxtype)
 			return i;
 	}
 
-	WARN_ON_ONCE(1);
-	return -1;
+	WARN_ON(1);
+	return 0;
 }
 
-int netlink_policy_dump_start(const struct nla_policy *policy,
-			      unsigned int maxtype,
-                              unsigned long *_state)
+static struct netlink_policy_dump_state *alloc_state(void)
 {
-	struct nl_policy_dump *state;
+	struct netlink_policy_dump_state *state;
+
+	state = kzalloc(struct_size(state, policies, INITIAL_POLICIES_ALLOC),
+			GFP_KERNEL);
+	if (!state)
+		return ERR_PTR(-ENOMEM);
+	state->n_alloc = INITIAL_POLICIES_ALLOC;
+
+	return state;
+}
+
+/**
+ * netlink_policy_dump_add_policy - add a policy to the dump
+ * @pstate: state to add to, may be reallocated, must be %NULL the first time
+ * @policy: the new policy to add to the dump
+ * @maxtype: the new policy's max attr type
+ *
+ * Returns: 0 on success, a negative error code otherwise.
+ *
+ * Call this to allocate a policy dump state, and to add policies to it. This
+ * should be called from the dump start() callback.
+ *
+ * Note: on failures, any previously allocated state is freed.
+ */
+int netlink_policy_dump_add_policy(struct netlink_policy_dump_state **pstate,
+				   const struct nla_policy *policy,
+				   unsigned int maxtype)
+{
+	struct netlink_policy_dump_state *state = *pstate;
 	unsigned int policy_idx;
 	int err;
 
-	/* also returns 0 if "*_state" is our ERR_PTR() end marker */
-	if (*_state)
-		return 0;
+	if (!state) {
+		state = alloc_state();
+		if (IS_ERR(state))
+			return PTR_ERR(state);
+	}
 
 	/*
 	 * walk the policies and nested ones first, and build
 	 * a linear list of them.
 	 */
 
-	state = kzalloc(struct_size(state, policies, INITIAL_POLICIES_ALLOC),
-			GFP_KERNEL);
-	if (!state)
-		return -ENOMEM;
-	state->n_alloc = INITIAL_POLICIES_ALLOC;
-
 	err = add_policy(&state, policy, maxtype);
 	if (err)
 		return err;
@@ -129,37 +172,40 @@ int netlink_policy_dump_start(const struct nla_policy *policy,
 		}
 	}
 
-	*_state = (unsigned long)state;
-
+	*pstate = state;
 	return 0;
 }
 
-static bool netlink_policy_dump_finished(struct nl_policy_dump *state)
+static bool
+netlink_policy_dump_finished(struct netlink_policy_dump_state *state)
 {
 	return state->policy_idx >= state->n_alloc ||
 	       !state->policies[state->policy_idx].policy;
 }
 
-bool netlink_policy_dump_loop(unsigned long *_state)
+/**
+ * netlink_policy_dump_loop - dumping loop indicator
+ * @state: the policy dump state
+ *
+ * Returns: %true if the dump continues, %false otherwise
+ *
+ * Note: this frees the dump state when finishing
+ */
+bool netlink_policy_dump_loop(struct netlink_policy_dump_state *state)
 {
-	struct nl_policy_dump *state = (void *)*_state;
-
-	if (IS_ERR(state))
-		return false;
-
-	if (netlink_policy_dump_finished(state)) {
-		kfree(state);
-		/* store end marker instead of freed state */
-		*_state = (unsigned long)ERR_PTR(-ENOENT);
-		return false;
-	}
-
-	return true;
+	return !netlink_policy_dump_finished(state);
 }
 
-int netlink_policy_dump_write(struct sk_buff *skb, unsigned long _state)
+/**
+ * netlink_policy_dump_write - write current policy dump attributes
+ * @skb: the message skb to write to
+ * @state: the policy dump state
+ *
+ * Returns: 0 on success, an error code otherwise
+ */
+int netlink_policy_dump_write(struct sk_buff *skb,
+			      struct netlink_policy_dump_state *state)
 {
-	struct nl_policy_dump *state = (void *)_state;
 	const struct nla_policy *pt;
 	struct nlattr *policy, *attr;
 	enum netlink_attribute_type type;
@@ -194,7 +240,9 @@ send_attribute:
 			type = NL_ATTR_TYPE_NESTED_ARRAY;
 		if (pt->nested_policy && pt->len &&
 		    (nla_put_u32(skb, NL_POLICY_TYPE_ATTR_POLICY_IDX,
-				 get_policy_idx(state, pt->nested_policy)) ||
+				 netlink_policy_dump_get_policy_idx(state,
+								    pt->nested_policy,
+								    pt->len)) ||
 		     nla_put_u32(skb, NL_POLICY_TYPE_ATTR_POLICY_MAXTYPE,
 				 pt->len)))
 			goto nla_put_failure;
@@ -316,3 +364,14 @@ nla_put_failure:
 	nla_nest_cancel(skb, policy);
 	return -ENOBUFS;
 }
+
+/**
+ * netlink_policy_dump_free - free policy dump state
+ * @state: the policy dump state to free
+ *
+ * Call this from the done() method to ensure dump state is freed.
+ */
+void netlink_policy_dump_free(struct netlink_policy_dump_state *state)
+{
+	kfree(state);
+}
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 855f2c155956..b87bfc82f44f 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -277,9 +277,11 @@ static int set_eth_addr(struct sk_buff *skb, struct sw_flow_key *flow_key,
  */
 static int pop_eth(struct sk_buff *skb, struct sw_flow_key *key)
 {
-	skb_pull_rcsum(skb, ETH_HLEN);
-	skb_reset_mac_header(skb);
-	skb_reset_mac_len(skb);
+	int err;
+
+	err = skb_eth_pop(skb);
+	if (err)
+		return err;
 
 	/* safe right before invalidate_flow_key */
 	key->mac_proto = MAC_PROTO_NONE;
@@ -290,22 +292,12 @@ static int pop_eth(struct sk_buff *skb, struct sw_flow_key *key)
 static int push_eth(struct sk_buff *skb, struct sw_flow_key *key,
 		    const struct ovs_action_push_eth *ethh)
 {
-	struct ethhdr *hdr;
-
-	/* Add the new Ethernet header */
-	if (skb_cow_head(skb, ETH_HLEN) < 0)
-		return -ENOMEM;
-
-	skb_push(skb, ETH_HLEN);
-	skb_reset_mac_header(skb);
-	skb_reset_mac_len(skb);
-
-	hdr = eth_hdr(skb);
-	ether_addr_copy(hdr->h_source, ethh->addresses.eth_src);
-	ether_addr_copy(hdr->h_dest, ethh->addresses.eth_dst);
-	hdr->h_proto = skb->protocol;
+	int err;
 
-	skb_postpush_rcsum(skb, hdr, ETH_HLEN);
+	err = skb_eth_push(skb, ethh->addresses.eth_dst,
+			   ethh->addresses.eth_src);
+	if (err)
+		return err;
 
 	/* safe right before invalidate_flow_key */
 	key->mac_proto = MAC_PROTO_ETHERNET;
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index e86b9601f5b1..18af10b7ef0e 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -2231,7 +2231,7 @@ exit_err:
 	return err;
 }
 
-static struct genl_ops ct_limit_genl_ops[] = {
+static struct genl_small_ops ct_limit_genl_ops[] = {
 	{ .cmd = OVS_CT_LIMIT_CMD_SET,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN
@@ -2263,8 +2263,8 @@ struct genl_family dp_ct_limit_genl_family __ro_after_init = {
 	.policy = ct_limit_policy,
 	.netnsok = true,
 	.parallel_ops = true,
-	.ops = ct_limit_genl_ops,
-	.n_ops = ARRAY_SIZE(ct_limit_genl_ops),
+	.small_ops = ct_limit_genl_ops,
+	.n_small_ops = ARRAY_SIZE(ct_limit_genl_ops),
 	.mcgrps = &ovs_ct_limit_multicast_group,
 	.n_mcgrps = 1,
 	.module = THIS_MODULE,
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 00df39b736ed..832f898edb6a 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -652,7 +652,7 @@ static const struct nla_policy packet_policy[OVS_PACKET_ATTR_MAX + 1] = {
 	[OVS_PACKET_ATTR_HASH] = { .type = NLA_U64 },
 };
 
-static const struct genl_ops dp_packet_genl_ops[] = {
+static const struct genl_small_ops dp_packet_genl_ops[] = {
 	{ .cmd = OVS_PACKET_CMD_EXECUTE,
 	  .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 	  .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
@@ -668,8 +668,8 @@ static struct genl_family dp_packet_genl_family __ro_after_init = {
 	.policy = packet_policy,
 	.netnsok = true,
 	.parallel_ops = true,
-	.ops = dp_packet_genl_ops,
-	.n_ops = ARRAY_SIZE(dp_packet_genl_ops),
+	.small_ops = dp_packet_genl_ops,
+	.n_small_ops = ARRAY_SIZE(dp_packet_genl_ops),
 	.module = THIS_MODULE,
 };
 
@@ -1453,7 +1453,7 @@ static const struct nla_policy flow_policy[OVS_FLOW_ATTR_MAX + 1] = {
 	[OVS_FLOW_ATTR_UFID_FLAGS] = { .type = NLA_U32 },
 };
 
-static const struct genl_ops dp_flow_genl_ops[] = {
+static const struct genl_small_ops dp_flow_genl_ops[] = {
 	{ .cmd = OVS_FLOW_CMD_NEW,
 	  .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 	  .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
@@ -1485,8 +1485,8 @@ static struct genl_family dp_flow_genl_family __ro_after_init = {
 	.policy = flow_policy,
 	.netnsok = true,
 	.parallel_ops = true,
-	.ops = dp_flow_genl_ops,
-	.n_ops = ARRAY_SIZE(dp_flow_genl_ops),
+	.small_ops = dp_flow_genl_ops,
+	.n_small_ops = ARRAY_SIZE(dp_flow_genl_ops),
 	.mcgrps = &ovs_dp_flow_multicast_group,
 	.n_mcgrps = 1,
 	.module = THIS_MODULE,
@@ -1918,7 +1918,7 @@ static const struct nla_policy datapath_policy[OVS_DP_ATTR_MAX + 1] = {
 		PCPU_MIN_UNIT_SIZE / sizeof(struct mask_cache_entry)),
 };
 
-static const struct genl_ops dp_datapath_genl_ops[] = {
+static const struct genl_small_ops dp_datapath_genl_ops[] = {
 	{ .cmd = OVS_DP_CMD_NEW,
 	  .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 	  .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
@@ -1950,8 +1950,8 @@ static struct genl_family dp_datapath_genl_family __ro_after_init = {
 	.policy = datapath_policy,
 	.netnsok = true,
 	.parallel_ops = true,
-	.ops = dp_datapath_genl_ops,
-	.n_ops = ARRAY_SIZE(dp_datapath_genl_ops),
+	.small_ops = dp_datapath_genl_ops,
+	.n_small_ops = ARRAY_SIZE(dp_datapath_genl_ops),
 	.mcgrps = &ovs_dp_datapath_multicast_group,
 	.n_mcgrps = 1,
 	.module = THIS_MODULE,
@@ -2401,7 +2401,7 @@ static const struct nla_policy vport_policy[OVS_VPORT_ATTR_MAX + 1] = {
 	[OVS_VPORT_ATTR_NETNSID] = { .type = NLA_S32 },
 };
 
-static const struct genl_ops dp_vport_genl_ops[] = {
+static const struct genl_small_ops dp_vport_genl_ops[] = {
 	{ .cmd = OVS_VPORT_CMD_NEW,
 	  .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 	  .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
@@ -2433,8 +2433,8 @@ struct genl_family dp_vport_genl_family __ro_after_init = {
 	.policy = vport_policy,
 	.netnsok = true,
 	.parallel_ops = true,
-	.ops = dp_vport_genl_ops,
-	.n_ops = ARRAY_SIZE(dp_vport_genl_ops),
+	.small_ops = dp_vport_genl_ops,
+	.n_small_ops = ARRAY_SIZE(dp_vport_genl_ops),
 	.mcgrps = &ovs_dp_vport_multicast_group,
 	.n_mcgrps = 1,
 	.module = THIS_MODULE,
diff --git a/net/openvswitch/meter.c b/net/openvswitch/meter.c
index 3d3d8e094546..50541e874726 100644
--- a/net/openvswitch/meter.c
+++ b/net/openvswitch/meter.c
@@ -672,7 +672,7 @@ bool ovs_meter_execute(struct datapath *dp, struct sk_buff *skb,
 	return false;
 }
 
-static struct genl_ops dp_meter_genl_ops[] = {
+static struct genl_small_ops dp_meter_genl_ops[] = {
 	{ .cmd = OVS_METER_CMD_FEATURES,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags = 0,		  /* OK for unprivileged users. */
@@ -711,8 +711,8 @@ struct genl_family dp_meter_genl_family __ro_after_init = {
 	.policy = meter_policy,
 	.netnsok = true,
 	.parallel_ops = true,
-	.ops = dp_meter_genl_ops,
-	.n_ops = ARRAY_SIZE(dp_meter_genl_ops),
+	.small_ops = dp_meter_genl_ops,
+	.n_small_ops = ARRAY_SIZE(dp_meter_genl_ops),
 	.mcgrps = &ovs_meter_multicast_group,
 	.n_mcgrps = 1,
 	.module = THIS_MODULE,
diff --git a/net/psample/psample.c b/net/psample/psample.c
index a042261a45c5..33e238c965bd 100644
--- a/net/psample/psample.c
+++ b/net/psample/psample.c
@@ -96,7 +96,7 @@ static int psample_nl_cmd_get_group_dumpit(struct sk_buff *msg,
 	return msg->len;
 }
 
-static const struct genl_ops psample_nl_ops[] = {
+static const struct genl_small_ops psample_nl_ops[] = {
 	{
 		.cmd = PSAMPLE_CMD_GET_GROUP,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
@@ -112,8 +112,8 @@ static struct genl_family psample_nl_family __ro_after_init = {
 	.netnsok	= true,
 	.module		= THIS_MODULE,
 	.mcgrps		= psample_nl_mcgrps,
-	.ops		= psample_nl_ops,
-	.n_ops		= ARRAY_SIZE(psample_nl_ops),
+	.small_ops	= psample_nl_ops,
+	.n_small_ops	= ARRAY_SIZE(psample_nl_ops),
 	.n_mcgrps	= ARRAY_SIZE(psample_nl_mcgrps),
 };
 
diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c
index 90c558f89d46..957aa9263ba4 100644
--- a/net/qrtr/qrtr.c
+++ b/net/qrtr/qrtr.c
@@ -332,8 +332,7 @@ static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb,
 {
 	struct qrtr_hdr_v1 *hdr;
 	size_t len = skb->len;
-	int rc = -ENODEV;
-	int confirm_rx;
+	int rc, confirm_rx;
 
 	confirm_rx = qrtr_tx_wait(node, to->sq_node, to->sq_port, type);
 	if (confirm_rx < 0) {
@@ -357,15 +356,17 @@ static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb,
 	hdr->size = cpu_to_le32(len);
 	hdr->confirm_rx = !!confirm_rx;
 
-	skb_put_padto(skb, ALIGN(len, 4) + sizeof(*hdr));
-
-	mutex_lock(&node->ep_lock);
-	if (node->ep)
-		rc = node->ep->xmit(node->ep, skb);
-	else
-		kfree_skb(skb);
-	mutex_unlock(&node->ep_lock);
+	rc = skb_put_padto(skb, ALIGN(len, 4) + sizeof(*hdr));
 
+	if (!rc) {
+		mutex_lock(&node->ep_lock);
+		rc = -ENODEV;
+		if (node->ep)
+			rc = node->ep->xmit(node->ep, skb);
+		else
+			kfree_skb(skb);
+		mutex_unlock(&node->ep_lock);
+	}
 	/* Need to ensure that a subsequent message carries the otherwise lost
 	 * confirm_rx flag if we dropped this one */
 	if (rc && confirm_rx)
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index c1fcd85719d6..5c568757643b 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -436,6 +436,25 @@ static void tcf_ife_cleanup(struct tc_action *a)
 		kfree_rcu(p, rcu);
 }
 
+static int load_metalist(struct nlattr **tb, bool rtnl_held)
+{
+	int i;
+
+	for (i = 1; i < max_metacnt; i++) {
+		if (tb[i]) {
+			void *val = nla_data(tb[i]);
+			int len = nla_len(tb[i]);
+			int rc;
+
+			rc = load_metaops_and_vet(i, val, len, rtnl_held);
+			if (rc != 0)
+				return rc;
+		}
+	}
+
+	return 0;
+}
+
 static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb,
 			     bool exists, bool rtnl_held)
 {
@@ -449,10 +468,6 @@ static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb,
 			val = nla_data(tb[i]);
 			len = nla_len(tb[i]);
 
-			rc = load_metaops_and_vet(i, val, len, rtnl_held);
-			if (rc != 0)
-				return rc;
-
 			rc = add_metainfo(ife, i, val, len, exists);
 			if (rc)
 				return rc;
@@ -509,6 +524,21 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 	if (!p)
 		return -ENOMEM;
 
+	if (tb[TCA_IFE_METALST]) {
+		err = nla_parse_nested_deprecated(tb2, IFE_META_MAX,
+						  tb[TCA_IFE_METALST], NULL,
+						  NULL);
+		if (err) {
+			kfree(p);
+			return err;
+		}
+		err = load_metalist(tb2, rtnl_held);
+		if (err) {
+			kfree(p);
+			return err;
+		}
+	}
+
 	index = parm->index;
 	err = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (err < 0) {
@@ -570,15 +600,9 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 	}
 
 	if (tb[TCA_IFE_METALST]) {
-		err = nla_parse_nested_deprecated(tb2, IFE_META_MAX,
-						  tb[TCA_IFE_METALST], NULL,
-						  NULL);
-		if (err)
-			goto metadata_parse_err;
 		err = populate_metalist(ife, tb2, exists, rtnl_held);
 		if (err)
 			goto metadata_parse_err;
-
 	} else {
 		/* if no passed metadata allow list or passed allow-all
 		 * then here we process by adding as many supported metadatum
diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c
index 8118e2640979..bb6b715636db 100644
--- a/net/sched/act_mpls.c
+++ b/net/sched/act_mpls.c
@@ -87,6 +87,23 @@ static int tcf_mpls_act(struct sk_buff *skb, const struct tc_action *a,
 				  skb->dev && skb->dev->type == ARPHRD_ETHER))
 			goto drop;
 		break;
+	case TCA_MPLS_ACT_MAC_PUSH:
+		if (skb_vlan_tag_present(skb)) {
+			if (__vlan_insert_inner_tag(skb, skb->vlan_proto,
+						    skb_vlan_tag_get(skb),
+						    ETH_HLEN) < 0)
+				goto drop;
+
+			skb->protocol = skb->vlan_proto;
+			__vlan_hwaccel_clear_tag(skb);
+		}
+
+		new_lse = tcf_mpls_get_lse(NULL, p, mac_len ||
+					   !eth_p_mpls(skb->protocol));
+
+		if (skb_mpls_push(skb, new_lse, p->tcfm_proto, 0, false))
+			goto drop;
+		break;
 	case TCA_MPLS_ACT_MODIFY:
 		new_lse = tcf_mpls_get_lse(mpls_hdr(skb), p, false);
 		if (skb_mpls_update_lse(skb, new_lse))
@@ -188,6 +205,7 @@ static int tcf_mpls_init(struct net *net, struct nlattr *nla,
 		}
 		break;
 	case TCA_MPLS_ACT_PUSH:
+	case TCA_MPLS_ACT_MAC_PUSH:
 		if (!tb[TCA_MPLS_LABEL]) {
 			NL_SET_ERR_MSG_MOD(extack, "Label is required for MPLS push");
 			return -EINVAL;
diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index 536c4bc31be6..37f1e10f35e0 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -156,6 +156,7 @@ tunnel_key_copy_vxlan_opt(const struct nlattr *nla, void *dst, int dst_len,
 		struct vxlan_metadata *md = dst;
 
 		md->gbp = nla_get_u32(tb[TCA_TUNNEL_KEY_ENC_OPT_VXLAN_GBP]);
+		md->gbp &= VXLAN_GBP_MASK;
 	}
 
 	return sizeof(struct vxlan_metadata);
diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index a5ff9f68ab02..8758bd2a78fa 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -77,6 +77,16 @@ static int tcf_vlan_act(struct sk_buff *skb, const struct tc_action *a,
 		/* put updated tci as hwaccel tag */
 		__vlan_hwaccel_put_tag(skb, p->tcfv_push_proto, tci);
 		break;
+	case TCA_VLAN_ACT_POP_ETH:
+		err = skb_eth_pop(skb);
+		if (err)
+			goto drop;
+		break;
+	case TCA_VLAN_ACT_PUSH_ETH:
+		err = skb_eth_push(skb, p->tcfv_push_dst, p->tcfv_push_src);
+		if (err)
+			goto drop;
+		break;
 	default:
 		BUG();
 	}
@@ -93,10 +103,13 @@ drop:
 }
 
 static const struct nla_policy vlan_policy[TCA_VLAN_MAX + 1] = {
+	[TCA_VLAN_UNSPEC]		= { .strict_start_type = TCA_VLAN_PUSH_ETH_DST },
 	[TCA_VLAN_PARMS]		= { .len = sizeof(struct tc_vlan) },
 	[TCA_VLAN_PUSH_VLAN_ID]		= { .type = NLA_U16 },
 	[TCA_VLAN_PUSH_VLAN_PROTOCOL]	= { .type = NLA_U16 },
 	[TCA_VLAN_PUSH_VLAN_PRIORITY]	= { .type = NLA_U8 },
+	[TCA_VLAN_PUSH_ETH_DST]		= NLA_POLICY_ETH_ADDR,
+	[TCA_VLAN_PUSH_ETH_SRC]		= NLA_POLICY_ETH_ADDR,
 };
 
 static int tcf_vlan_init(struct net *net, struct nlattr *nla,
@@ -179,6 +192,17 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
 		if (tb[TCA_VLAN_PUSH_VLAN_PRIORITY])
 			push_prio = nla_get_u8(tb[TCA_VLAN_PUSH_VLAN_PRIORITY]);
 		break;
+	case TCA_VLAN_ACT_POP_ETH:
+		break;
+	case TCA_VLAN_ACT_PUSH_ETH:
+		if (!tb[TCA_VLAN_PUSH_ETH_DST] || !tb[TCA_VLAN_PUSH_ETH_SRC]) {
+			if (exists)
+				tcf_idr_release(*a, bind);
+			else
+				tcf_idr_cleanup(tn, index);
+			return -EINVAL;
+		}
+		break;
 	default:
 		if (exists)
 			tcf_idr_release(*a, bind);
@@ -219,6 +243,13 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
 	p->tcfv_push_prio = push_prio;
 	p->tcfv_push_proto = push_proto;
 
+	if (action == TCA_VLAN_ACT_PUSH_ETH) {
+		nla_memcpy(&p->tcfv_push_dst, tb[TCA_VLAN_PUSH_ETH_DST],
+			   ETH_ALEN);
+		nla_memcpy(&p->tcfv_push_src, tb[TCA_VLAN_PUSH_ETH_SRC],
+			   ETH_ALEN);
+	}
+
 	spin_lock_bh(&v->tcf_lock);
 	goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
 	p = rcu_replace_pointer(v->vlan_p, p, lockdep_is_held(&v->tcf_lock));
@@ -279,6 +310,15 @@ static int tcf_vlan_dump(struct sk_buff *skb, struct tc_action *a,
 					      p->tcfv_push_prio))))
 		goto nla_put_failure;
 
+	if (p->tcfv_action == TCA_VLAN_ACT_PUSH_ETH) {
+		if (nla_put(skb, TCA_VLAN_PUSH_ETH_DST, ETH_ALEN,
+			    p->tcfv_push_dst))
+			goto nla_put_failure;
+		if (nla_put(skb, TCA_VLAN_PUSH_ETH_SRC, ETH_ALEN,
+			    p->tcfv_push_src))
+			goto nla_put_failure;
+	}
+
 	tcf_tm_dump(&t, &v->tcf_tm);
 	if (nla_put_64bit(skb, TCA_VLAN_TM, sizeof(t), &t, TCA_VLAN_PAD))
 		goto nla_put_failure;
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index a4f7ef1de7e7..fed18fd2c50b 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -1175,8 +1175,10 @@ static int fl_set_vxlan_opt(const struct nlattr *nla, struct fl_flow_key *key,
 		return -EINVAL;
 	}
 
-	if (tb[TCA_FLOWER_KEY_ENC_OPT_VXLAN_GBP])
+	if (tb[TCA_FLOWER_KEY_ENC_OPT_VXLAN_GBP]) {
 		md->gbp = nla_get_u32(tb[TCA_FLOWER_KEY_ENC_OPT_VXLAN_GBP]);
+		md->gbp &= VXLAN_GBP_MASK;
+	}
 
 	return sizeof(*md);
 }
@@ -1221,6 +1223,7 @@ static int fl_set_erspan_opt(const struct nlattr *nla, struct fl_flow_key *key,
 		}
 		if (tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_INDEX]) {
 			nla = tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_INDEX];
+			memset(&md->u, 0x00, sizeof(md->u));
 			md->u.index = nla_get_be32(nla);
 		}
 	} else if (md->version == 2) {
diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index 7b69ab1993ba..54209a18d7fe 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -79,7 +79,7 @@ struct tc_u_hnode {
 	/* The 'ht' field MUST be the last field in structure to allow for
 	 * more entries allocated at end of structure.
 	 */
-	struct tc_u_knode __rcu	*ht[1];
+	struct tc_u_knode __rcu	*ht[];
 };
 
 struct tc_u_common {
@@ -353,7 +353,7 @@ static int u32_init(struct tcf_proto *tp)
 	void *key = tc_u_common_ptr(tp);
 	struct tc_u_common *tp_c = tc_u_common_find(key);
 
-	root_ht = kzalloc(sizeof(*root_ht), GFP_KERNEL);
+	root_ht = kzalloc(struct_size(root_ht, ht, 1), GFP_KERNEL);
 	if (root_ht == NULL)
 		return -ENOBUFS;
 
@@ -364,7 +364,7 @@ static int u32_init(struct tcf_proto *tp)
 	idr_init(&root_ht->handle_idr);
 
 	if (tp_c == NULL) {
-		tp_c = kzalloc(sizeof(*tp_c), GFP_KERNEL);
+		tp_c = kzalloc(struct_size(tp_c, hlist->ht, 1), GFP_KERNEL);
 		if (tp_c == NULL) {
 			kfree(root_ht);
 			return -ENOBUFS;
@@ -933,7 +933,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
 			NL_SET_ERR_MSG_MOD(extack, "Divisor can only be used on a hash table");
 			return -EINVAL;
 		}
-		ht = kzalloc(sizeof(*ht) + divisor*sizeof(void *), GFP_KERNEL);
+		ht = kzalloc(struct_size(ht, ht, divisor + 1), GFP_KERNEL);
 		if (ht == NULL)
 			return -ENOBUFS;
 		if (handle == 0) {
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 265a61d011df..54c417244642 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -1131,24 +1131,10 @@ EXPORT_SYMBOL(dev_activate);
 
 static void qdisc_deactivate(struct Qdisc *qdisc)
 {
-	bool nolock = qdisc->flags & TCQ_F_NOLOCK;
-
 	if (qdisc->flags & TCQ_F_BUILTIN)
 		return;
-	if (test_bit(__QDISC_STATE_DEACTIVATED, &qdisc->state))
-		return;
-
-	if (nolock)
-		spin_lock_bh(&qdisc->seqlock);
-	spin_lock_bh(qdisc_lock(qdisc));
 
 	set_bit(__QDISC_STATE_DEACTIVATED, &qdisc->state);
-
-	qdisc_reset(qdisc);
-
-	spin_unlock_bh(qdisc_lock(qdisc));
-	if (nolock)
-		spin_unlock_bh(&qdisc->seqlock);
 }
 
 static void dev_deactivate_queue(struct net_device *dev,
@@ -1165,6 +1151,30 @@ static void dev_deactivate_queue(struct net_device *dev,
 	}
 }
 
+static void dev_reset_queue(struct net_device *dev,
+			    struct netdev_queue *dev_queue,
+			    void *_unused)
+{
+	struct Qdisc *qdisc;
+	bool nolock;
+
+	qdisc = dev_queue->qdisc_sleeping;
+	if (!qdisc)
+		return;
+
+	nolock = qdisc->flags & TCQ_F_NOLOCK;
+
+	if (nolock)
+		spin_lock_bh(&qdisc->seqlock);
+	spin_lock_bh(qdisc_lock(qdisc));
+
+	qdisc_reset(qdisc);
+
+	spin_unlock_bh(qdisc_lock(qdisc));
+	if (nolock)
+		spin_unlock_bh(&qdisc->seqlock);
+}
+
 static bool some_qdisc_is_busy(struct net_device *dev)
 {
 	unsigned int i;
@@ -1213,12 +1223,20 @@ void dev_deactivate_many(struct list_head *head)
 		dev_watchdog_down(dev);
 	}
 
-	/* Wait for outstanding qdisc-less dev_queue_xmit calls.
+	/* Wait for outstanding qdisc-less dev_queue_xmit calls or
+	 * outstanding qdisc enqueuing calls.
 	 * This is avoided if all devices are in dismantle phase :
 	 * Caller will call synchronize_net() for us
 	 */
 	synchronize_net();
 
+	list_for_each_entry(dev, head, close_list) {
+		netdev_for_each_tx_queue(dev, dev_reset_queue, NULL);
+
+		if (dev_ingress_queue(dev))
+			dev_reset_queue(dev, dev_ingress_queue(dev), NULL);
+	}
+
 	/* Wait for outstanding qdisc_run calls. */
 	list_for_each_entry(dev, head, close_list) {
 		while (some_qdisc_is_busy(dev)) {
diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index fe53c1e38c7d..b0ad7687ee2c 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -777,9 +777,11 @@ static const struct nla_policy taprio_policy[TCA_TAPRIO_ATTR_MAX + 1] = {
 	[TCA_TAPRIO_ATTR_TXTIME_DELAY]		     = { .type = NLA_U32 },
 };
 
-static int fill_sched_entry(struct nlattr **tb, struct sched_entry *entry,
+static int fill_sched_entry(struct taprio_sched *q, struct nlattr **tb,
+			    struct sched_entry *entry,
 			    struct netlink_ext_ack *extack)
 {
+	int min_duration = length_to_duration(q, ETH_ZLEN);
 	u32 interval = 0;
 
 	if (tb[TCA_TAPRIO_SCHED_ENTRY_CMD])
@@ -794,7 +796,10 @@ static int fill_sched_entry(struct nlattr **tb, struct sched_entry *entry,
 		interval = nla_get_u32(
 			tb[TCA_TAPRIO_SCHED_ENTRY_INTERVAL]);
 
-	if (interval == 0) {
+	/* The interval should allow at least the minimum ethernet
+	 * frame to go out.
+	 */
+	if (interval < min_duration) {
 		NL_SET_ERR_MSG(extack, "Invalid interval for schedule entry");
 		return -EINVAL;
 	}
@@ -804,8 +809,9 @@ static int fill_sched_entry(struct nlattr **tb, struct sched_entry *entry,
 	return 0;
 }
 
-static int parse_sched_entry(struct nlattr *n, struct sched_entry *entry,
-			     int index, struct netlink_ext_ack *extack)
+static int parse_sched_entry(struct taprio_sched *q, struct nlattr *n,
+			     struct sched_entry *entry, int index,
+			     struct netlink_ext_ack *extack)
 {
 	struct nlattr *tb[TCA_TAPRIO_SCHED_ENTRY_MAX + 1] = { };
 	int err;
@@ -819,10 +825,10 @@ static int parse_sched_entry(struct nlattr *n, struct sched_entry *entry,
 
 	entry->index = index;
 
-	return fill_sched_entry(tb, entry, extack);
+	return fill_sched_entry(q, tb, entry, extack);
 }
 
-static int parse_sched_list(struct nlattr *list,
+static int parse_sched_list(struct taprio_sched *q, struct nlattr *list,
 			    struct sched_gate_list *sched,
 			    struct netlink_ext_ack *extack)
 {
@@ -847,7 +853,7 @@ static int parse_sched_list(struct nlattr *list,
 			return -ENOMEM;
 		}
 
-		err = parse_sched_entry(n, entry, i, extack);
+		err = parse_sched_entry(q, n, entry, i, extack);
 		if (err < 0) {
 			kfree(entry);
 			return err;
@@ -862,7 +868,7 @@ static int parse_sched_list(struct nlattr *list,
 	return i;
 }
 
-static int parse_taprio_schedule(struct nlattr **tb,
+static int parse_taprio_schedule(struct taprio_sched *q, struct nlattr **tb,
 				 struct sched_gate_list *new,
 				 struct netlink_ext_ack *extack)
 {
@@ -883,8 +889,8 @@ static int parse_taprio_schedule(struct nlattr **tb,
 		new->cycle_time = nla_get_s64(tb[TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME]);
 
 	if (tb[TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST])
-		err = parse_sched_list(
-			tb[TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST], new, extack);
+		err = parse_sched_list(q, tb[TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST],
+				       new, extack);
 	if (err < 0)
 		return err;
 
@@ -1473,7 +1479,7 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt,
 		goto free_sched;
 	}
 
-	err = parse_taprio_schedule(tb, new_admin, extack);
+	err = parse_taprio_schedule(q, tb, new_admin, extack);
 	if (err < 0)
 		goto free_sched;
 
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 836615f71a7d..53d0a4161df3 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -9220,13 +9220,10 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk,
 static inline void sctp_copy_descendant(struct sock *sk_to,
 					const struct sock *sk_from)
 {
-	int ancestor_size = sizeof(struct inet_sock) +
-			    sizeof(struct sctp_sock) -
-			    offsetof(struct sctp_sock, pd_lobby);
-
-	if (sk_from->sk_family == PF_INET6)
-		ancestor_size += sizeof(struct ipv6_pinfo);
+	size_t ancestor_size = sizeof(struct inet_sock);
 
+	ancestor_size += sk_from->sk_prot->obj_size;
+	ancestor_size -= offsetof(struct sctp_sock, pd_lobby);
 	__inet_sk_copy_descendant(sk_to, sk_from, ancestor_size);
 }
 
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index ed8f97166be9..670e802a73cb 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -26,6 +26,7 @@
 #include <linux/sched/signal.h>
 #include <linux/if_vlan.h>
 #include <linux/rcupdate_wait.h>
+#include <linux/ctype.h>
 
 #include <net/sock.h>
 #include <net/tcp.h>
@@ -448,6 +449,16 @@ static void smcr_conn_save_peer_info(struct smc_sock *smc,
 	smc->conn.tx_off = bufsize * (smc->conn.peer_rmbe_idx - 1);
 }
 
+static bool smc_isascii(char *hostname)
+{
+	int i;
+
+	for (i = 0; i < SMC_MAX_HOSTNAME_LEN; i++)
+		if (!isascii(hostname[i]))
+			return false;
+	return true;
+}
+
 static void smcd_conn_save_peer_info(struct smc_sock *smc,
 				     struct smc_clc_msg_accept_confirm *clc)
 {
@@ -459,6 +470,22 @@ static void smcd_conn_save_peer_info(struct smc_sock *smc,
 	smc->conn.peer_rmbe_size = bufsize - sizeof(struct smcd_cdc_msg);
 	atomic_set(&smc->conn.peer_rmbe_space, smc->conn.peer_rmbe_size);
 	smc->conn.tx_off = bufsize * smc->conn.peer_rmbe_idx;
+	if (clc->hdr.version > SMC_V1 &&
+	    (clc->hdr.typev2 & SMC_FIRST_CONTACT_MASK)) {
+		struct smc_clc_msg_accept_confirm_v2 *clc_v2 =
+			(struct smc_clc_msg_accept_confirm_v2 *)clc;
+		struct smc_clc_first_contact_ext *fce =
+			(struct smc_clc_first_contact_ext *)
+				(((u8 *)clc_v2) + sizeof(*clc_v2));
+
+		memcpy(smc->conn.lgr->negotiated_eid, clc_v2->eid,
+		       SMC_MAX_EID_LEN);
+		smc->conn.lgr->peer_os = fce->os_type;
+		smc->conn.lgr->peer_smc_release = fce->release;
+		if (smc_isascii(fce->hostname))
+			memcpy(smc->conn.lgr->peer_hostname, fce->hostname,
+			       SMC_MAX_HOSTNAME_LEN);
+	}
 }
 
 static void smc_conn_save_peer_info(struct smc_sock *smc,
@@ -504,7 +531,8 @@ static int smc_connect_fallback(struct smc_sock *smc, int reason_code)
 }
 
 /* decline and fall back during connect */
-static int smc_connect_decline_fallback(struct smc_sock *smc, int reason_code)
+static int smc_connect_decline_fallback(struct smc_sock *smc, int reason_code,
+					u8 version)
 {
 	int rc;
 
@@ -514,7 +542,7 @@ static int smc_connect_decline_fallback(struct smc_sock *smc, int reason_code)
 		return reason_code;
 	}
 	if (reason_code != SMC_CLC_DECL_PEERDECL) {
-		rc = smc_clc_send_decline(smc, reason_code);
+		rc = smc_clc_send_decline(smc, reason_code, version);
 		if (rc < 0) {
 			if (smc->sk.sk_state == SMC_INIT)
 				sock_put(&smc->sk); /* passive closing */
@@ -564,47 +592,137 @@ static int smc_find_ism_device(struct smc_sock *smc, struct smc_init_info *ini)
 {
 	/* Find ISM device with same PNETID as connecting interface  */
 	smc_pnet_find_ism_resource(smc->clcsock->sk, ini);
-	if (!ini->ism_dev)
+	if (!ini->ism_dev[0])
 		return SMC_CLC_DECL_NOSMCDDEV;
+	else
+		ini->ism_chid[0] = smc_ism_get_chid(ini->ism_dev[0]);
 	return 0;
 }
 
+/* is chid unique for the ism devices that are already determined? */
+static bool smc_find_ism_v2_is_unique_chid(u16 chid, struct smc_init_info *ini,
+					   int cnt)
+{
+	int i = (!ini->ism_dev[0]) ? 1 : 0;
+
+	for (; i < cnt; i++)
+		if (ini->ism_chid[i] == chid)
+			return false;
+	return true;
+}
+
+/* determine possible V2 ISM devices (either without PNETID or with PNETID plus
+ * PNETID matching net_device)
+ */
+static int smc_find_ism_v2_device_clnt(struct smc_sock *smc,
+				       struct smc_init_info *ini)
+{
+	int rc = SMC_CLC_DECL_NOSMCDDEV;
+	struct smcd_dev *smcd;
+	int i = 1;
+	u16 chid;
+
+	if (smcd_indicated(ini->smc_type_v1))
+		rc = 0;		/* already initialized for V1 */
+	mutex_lock(&smcd_dev_list.mutex);
+	list_for_each_entry(smcd, &smcd_dev_list.list, list) {
+		if (smcd->going_away || smcd == ini->ism_dev[0])
+			continue;
+		chid = smc_ism_get_chid(smcd);
+		if (!smc_find_ism_v2_is_unique_chid(chid, ini, i))
+			continue;
+		if (!smc_pnet_is_pnetid_set(smcd->pnetid) ||
+		    smc_pnet_is_ndev_pnetid(sock_net(&smc->sk), smcd->pnetid)) {
+			ini->ism_dev[i] = smcd;
+			ini->ism_chid[i] = chid;
+			ini->is_smcd = true;
+			rc = 0;
+			i++;
+			if (i > SMC_MAX_ISM_DEVS)
+				break;
+		}
+	}
+	mutex_unlock(&smcd_dev_list.mutex);
+	ini->ism_offered_cnt = i - 1;
+	if (!ini->ism_dev[0] && !ini->ism_dev[1])
+		ini->smcd_version = 0;
+
+	return rc;
+}
+
 /* Check for VLAN ID and register it on ISM device just for CLC handshake */
 static int smc_connect_ism_vlan_setup(struct smc_sock *smc,
 				      struct smc_init_info *ini)
 {
-	if (ini->vlan_id && smc_ism_get_vlan(ini->ism_dev, ini->vlan_id))
+	if (ini->vlan_id && smc_ism_get_vlan(ini->ism_dev[0], ini->vlan_id))
 		return SMC_CLC_DECL_ISMVLANERR;
 	return 0;
 }
 
+static int smc_find_proposal_devices(struct smc_sock *smc,
+				     struct smc_init_info *ini)
+{
+	int rc = 0;
+
+	/* check if there is an ism device available */
+	if (ini->smcd_version & SMC_V1) {
+		if (smc_find_ism_device(smc, ini) ||
+		    smc_connect_ism_vlan_setup(smc, ini)) {
+			if (ini->smc_type_v1 == SMC_TYPE_B)
+				ini->smc_type_v1 = SMC_TYPE_R;
+			else
+				ini->smc_type_v1 = SMC_TYPE_N;
+		} /* else ISM V1 is supported for this connection */
+		if (smc_find_rdma_device(smc, ini)) {
+			if (ini->smc_type_v1 == SMC_TYPE_B)
+				ini->smc_type_v1 = SMC_TYPE_D;
+			else
+				ini->smc_type_v1 = SMC_TYPE_N;
+		} /* else RDMA is supported for this connection */
+	}
+	if (smc_ism_v2_capable && smc_find_ism_v2_device_clnt(smc, ini))
+		ini->smc_type_v2 = SMC_TYPE_N;
+
+	/* if neither ISM nor RDMA are supported, fallback */
+	if (!smcr_indicated(ini->smc_type_v1) &&
+	    ini->smc_type_v1 == SMC_TYPE_N && ini->smc_type_v2 == SMC_TYPE_N)
+		rc = SMC_CLC_DECL_NOSMCDEV;
+
+	return rc;
+}
+
 /* cleanup temporary VLAN ID registration used for CLC handshake. If ISM is
  * used, the VLAN ID will be registered again during the connection setup.
  */
-static int smc_connect_ism_vlan_cleanup(struct smc_sock *smc, bool is_smcd,
+static int smc_connect_ism_vlan_cleanup(struct smc_sock *smc,
 					struct smc_init_info *ini)
 {
-	if (!is_smcd)
+	if (!smcd_indicated(ini->smc_type_v1))
 		return 0;
-	if (ini->vlan_id && smc_ism_put_vlan(ini->ism_dev, ini->vlan_id))
+	if (ini->vlan_id && smc_ism_put_vlan(ini->ism_dev[0], ini->vlan_id))
 		return SMC_CLC_DECL_CNFERR;
 	return 0;
 }
 
+#define SMC_CLC_MAX_ACCEPT_LEN \
+	(sizeof(struct smc_clc_msg_accept_confirm_v2) + \
+	 sizeof(struct smc_clc_first_contact_ext) + \
+	 sizeof(struct smc_clc_msg_trail))
+
 /* CLC handshake during connect */
-static int smc_connect_clc(struct smc_sock *smc, int smc_type,
-			   struct smc_clc_msg_accept_confirm *aclc,
+static int smc_connect_clc(struct smc_sock *smc,
+			   struct smc_clc_msg_accept_confirm_v2 *aclc2,
 			   struct smc_init_info *ini)
 {
 	int rc = 0;
 
 	/* do inband token exchange */
-	rc = smc_clc_send_proposal(smc, smc_type, ini);
+	rc = smc_clc_send_proposal(smc, ini);
 	if (rc)
 		return rc;
 	/* receive SMC Accept CLC message */
-	return smc_clc_wait_msg(smc, aclc, sizeof(*aclc), SMC_CLC_ACCEPT,
-				CLC_WAIT_TIME);
+	return smc_clc_wait_msg(smc, aclc2, SMC_CLC_MAX_ACCEPT_LEN,
+				SMC_CLC_ACCEPT, CLC_WAIT_TIME);
 }
 
 /* setup for RDMA connection of client */
@@ -618,7 +736,7 @@ static int smc_connect_rdma(struct smc_sock *smc,
 	ini->is_smcd = false;
 	ini->ib_lcl = &aclc->r0.lcl;
 	ini->ib_clcqpn = ntoh24(aclc->r0.qpn);
-	ini->first_contact_peer = aclc->hdr.flag;
+	ini->first_contact_peer = aclc->hdr.typev2 & SMC_FIRST_CONTACT_MASK;
 
 	mutex_lock(&smc_client_lgr_pending);
 	reason_code = smc_conn_create(smc, ini);
@@ -678,7 +796,8 @@ static int smc_connect_rdma(struct smc_sock *smc,
 	}
 	smc_rmb_sync_sg_for_device(&smc->conn);
 
-	reason_code = smc_clc_send_confirm(smc);
+	reason_code = smc_clc_send_confirm(smc, ini->first_contact_local,
+					   SMC_V1);
 	if (reason_code)
 		return smc_connect_abort(smc, reason_code,
 					 ini->first_contact_local);
@@ -704,6 +823,25 @@ static int smc_connect_rdma(struct smc_sock *smc,
 	return 0;
 }
 
+/* The server has chosen one of the proposed ISM devices for the communication.
+ * Determine from the CHID of the received CLC ACCEPT the ISM device chosen.
+ */
+static int
+smc_v2_determine_accepted_chid(struct smc_clc_msg_accept_confirm_v2 *aclc,
+			       struct smc_init_info *ini)
+{
+	int i;
+
+	for (i = 0; i < ini->ism_offered_cnt + 1; i++) {
+		if (ini->ism_chid[i] == ntohs(aclc->chid)) {
+			ini->ism_selected = i;
+			return 0;
+		}
+	}
+
+	return -EPROTO;
+}
+
 /* setup for ISM connection of client */
 static int smc_connect_ism(struct smc_sock *smc,
 			   struct smc_clc_msg_accept_confirm *aclc,
@@ -712,8 +850,17 @@ static int smc_connect_ism(struct smc_sock *smc,
 	int rc = 0;
 
 	ini->is_smcd = true;
-	ini->ism_peer_gid = aclc->d0.gid;
-	ini->first_contact_peer = aclc->hdr.flag;
+	ini->first_contact_peer = aclc->hdr.typev2 & SMC_FIRST_CONTACT_MASK;
+
+	if (aclc->hdr.version == SMC_V2) {
+		struct smc_clc_msg_accept_confirm_v2 *aclc_v2 =
+			(struct smc_clc_msg_accept_confirm_v2 *)aclc;
+
+		rc = smc_v2_determine_accepted_chid(aclc_v2, ini);
+		if (rc)
+			return rc;
+	}
+	ini->ism_peer_gid[ini->ism_selected] = aclc->d0.gid;
 
 	/* there is only one lgr role for SMC-D; use server lock */
 	mutex_lock(&smc_server_lgr_pending);
@@ -736,7 +883,8 @@ static int smc_connect_ism(struct smc_sock *smc,
 	smc_rx_init(smc);
 	smc_tx_init(smc);
 
-	rc = smc_clc_send_confirm(smc);
+	rc = smc_clc_send_confirm(smc, ini->first_contact_local,
+				  aclc->hdr.version);
 	if (rc)
 		return smc_connect_abort(smc, rc, ini->first_contact_local);
 	mutex_unlock(&smc_server_lgr_pending);
@@ -749,13 +897,32 @@ static int smc_connect_ism(struct smc_sock *smc,
 	return 0;
 }
 
+/* check if received accept type and version matches a proposed one */
+static int smc_connect_check_aclc(struct smc_init_info *ini,
+				  struct smc_clc_msg_accept_confirm *aclc)
+{
+	if ((aclc->hdr.typev1 == SMC_TYPE_R &&
+	     !smcr_indicated(ini->smc_type_v1)) ||
+	    (aclc->hdr.typev1 == SMC_TYPE_D &&
+	     ((!smcd_indicated(ini->smc_type_v1) &&
+	       !smcd_indicated(ini->smc_type_v2)) ||
+	      (aclc->hdr.version == SMC_V1 &&
+	       !smcd_indicated(ini->smc_type_v1)) ||
+	      (aclc->hdr.version == SMC_V2 &&
+	       !smcd_indicated(ini->smc_type_v2)))))
+		return SMC_CLC_DECL_MODEUNSUPP;
+
+	return 0;
+}
+
 /* perform steps before actually connecting */
 static int __smc_connect(struct smc_sock *smc)
 {
-	bool ism_supported = false, rdma_supported = false;
-	struct smc_clc_msg_accept_confirm aclc;
-	struct smc_init_info ini = {0};
-	int smc_type;
+	u8 version = smc_ism_v2_capable ? SMC_V2 : SMC_V1;
+	struct smc_clc_msg_accept_confirm_v2 *aclc2;
+	struct smc_clc_msg_accept_confirm *aclc;
+	struct smc_init_info *ini = NULL;
+	u8 *buf = NULL;
 	int rc = 0;
 
 	if (smc->use_fallback)
@@ -765,58 +932,73 @@ static int __smc_connect(struct smc_sock *smc)
 	if (!tcp_sk(smc->clcsock->sk)->syn_smc)
 		return smc_connect_fallback(smc, SMC_CLC_DECL_PEERNOSMC);
 
-	/* IPSec connections opt out of SMC-R optimizations */
+	/* IPSec connections opt out of SMC optimizations */
 	if (using_ipsec(smc))
-		return smc_connect_decline_fallback(smc, SMC_CLC_DECL_IPSEC);
+		return smc_connect_decline_fallback(smc, SMC_CLC_DECL_IPSEC,
+						    version);
 
-	/* get vlan id from IP device */
-	if (smc_vlan_by_tcpsk(smc->clcsock, &ini))
-		return smc_connect_decline_fallback(smc,
-						    SMC_CLC_DECL_GETVLANERR);
+	ini = kzalloc(sizeof(*ini), GFP_KERNEL);
+	if (!ini)
+		return smc_connect_decline_fallback(smc, SMC_CLC_DECL_MEM,
+						    version);
 
-	/* check if there is an ism device available */
-	if (!smc_find_ism_device(smc, &ini) &&
-	    !smc_connect_ism_vlan_setup(smc, &ini)) {
-		/* ISM is supported for this connection */
-		ism_supported = true;
-		smc_type = SMC_TYPE_D;
-	}
-
-	/* check if there is a rdma device available */
-	if (!smc_find_rdma_device(smc, &ini)) {
-		/* RDMA is supported for this connection */
-		rdma_supported = true;
-		if (ism_supported)
-			smc_type = SMC_TYPE_B; /* both */
-		else
-			smc_type = SMC_TYPE_R; /* only RDMA */
+	ini->smcd_version = SMC_V1;
+	ini->smcd_version |= smc_ism_v2_capable ? SMC_V2 : 0;
+	ini->smc_type_v1 = SMC_TYPE_B;
+	ini->smc_type_v2 = smc_ism_v2_capable ? SMC_TYPE_D : SMC_TYPE_N;
+
+	/* get vlan id from IP device */
+	if (smc_vlan_by_tcpsk(smc->clcsock, ini)) {
+		ini->smcd_version &= ~SMC_V1;
+		ini->smc_type_v1 = SMC_TYPE_N;
+		if (!ini->smcd_version) {
+			rc = SMC_CLC_DECL_GETVLANERR;
+			goto fallback;
+		}
 	}
 
-	/* if neither ISM nor RDMA are supported, fallback */
-	if (!rdma_supported && !ism_supported)
-		return smc_connect_decline_fallback(smc, SMC_CLC_DECL_NOSMCDEV);
+	rc = smc_find_proposal_devices(smc, ini);
+	if (rc)
+		goto fallback;
 
-	/* perform CLC handshake */
-	rc = smc_connect_clc(smc, smc_type, &aclc, &ini);
-	if (rc) {
-		smc_connect_ism_vlan_cleanup(smc, ism_supported, &ini);
-		return smc_connect_decline_fallback(smc, rc);
+	buf = kzalloc(SMC_CLC_MAX_ACCEPT_LEN, GFP_KERNEL);
+	if (!buf) {
+		rc = SMC_CLC_DECL_MEM;
+		goto fallback;
 	}
+	aclc2 = (struct smc_clc_msg_accept_confirm_v2 *)buf;
+	aclc = (struct smc_clc_msg_accept_confirm *)aclc2;
+
+	/* perform CLC handshake */
+	rc = smc_connect_clc(smc, aclc2, ini);
+	if (rc)
+		goto vlan_cleanup;
+
+	/* check if smc modes and versions of CLC proposal and accept match */
+	rc = smc_connect_check_aclc(ini, aclc);
+	version = aclc->hdr.version == SMC_V1 ? SMC_V1 : version;
+	if (rc)
+		goto vlan_cleanup;
 
 	/* depending on previous steps, connect using rdma or ism */
-	if (rdma_supported && aclc.hdr.path == SMC_TYPE_R)
-		rc = smc_connect_rdma(smc, &aclc, &ini);
-	else if (ism_supported && aclc.hdr.path == SMC_TYPE_D)
-		rc = smc_connect_ism(smc, &aclc, &ini);
-	else
-		rc = SMC_CLC_DECL_MODEUNSUPP;
-	if (rc) {
-		smc_connect_ism_vlan_cleanup(smc, ism_supported, &ini);
-		return smc_connect_decline_fallback(smc, rc);
-	}
+	if (aclc->hdr.typev1 == SMC_TYPE_R)
+		rc = smc_connect_rdma(smc, aclc, ini);
+	else if (aclc->hdr.typev1 == SMC_TYPE_D)
+		rc = smc_connect_ism(smc, aclc, ini);
+	if (rc)
+		goto vlan_cleanup;
 
-	smc_connect_ism_vlan_cleanup(smc, ism_supported, &ini);
+	smc_connect_ism_vlan_cleanup(smc, ini);
+	kfree(buf);
+	kfree(ini);
 	return 0;
+
+vlan_cleanup:
+	smc_connect_ism_vlan_cleanup(smc, ini);
+	kfree(buf);
+fallback:
+	kfree(ini);
+	return smc_connect_decline_fallback(smc, rc, version);
 }
 
 static void smc_connect_work(struct work_struct *work)
@@ -1132,10 +1314,10 @@ static void smc_listen_out_err(struct smc_sock *new_smc)
 
 /* listen worker: decline and fall back if possible */
 static void smc_listen_decline(struct smc_sock *new_smc, int reason_code,
-			       bool local_first)
+			       struct smc_init_info *ini, u8 version)
 {
 	/* RDMA setup failed, switch back to TCP */
-	if (local_first)
+	if (ini->first_contact_local)
 		smc_lgr_cleanup_early(&new_smc->conn);
 	else
 		smc_conn_free(&new_smc->conn);
@@ -1146,7 +1328,7 @@ static void smc_listen_decline(struct smc_sock *new_smc, int reason_code,
 	smc_switch_to_fallback(new_smc);
 	new_smc->fallback_rsn = reason_code;
 	if (reason_code && reason_code != SMC_CLC_DECL_PEERDECL) {
-		if (smc_clc_send_decline(new_smc, reason_code) < 0) {
+		if (smc_clc_send_decline(new_smc, reason_code, version) < 0) {
 			smc_listen_out_err(new_smc);
 			return;
 		}
@@ -1154,6 +1336,47 @@ static void smc_listen_decline(struct smc_sock *new_smc, int reason_code,
 	smc_listen_out_connected(new_smc);
 }
 
+/* listen worker: version checking */
+static int smc_listen_v2_check(struct smc_sock *new_smc,
+			       struct smc_clc_msg_proposal *pclc,
+			       struct smc_init_info *ini)
+{
+	struct smc_clc_smcd_v2_extension *pclc_smcd_v2_ext;
+	struct smc_clc_v2_extension *pclc_v2_ext;
+
+	ini->smc_type_v1 = pclc->hdr.typev1;
+	ini->smc_type_v2 = pclc->hdr.typev2;
+	ini->smcd_version = ini->smc_type_v1 != SMC_TYPE_N ? SMC_V1 : 0;
+	if (pclc->hdr.version > SMC_V1)
+		ini->smcd_version |=
+				ini->smc_type_v2 != SMC_TYPE_N ? SMC_V2 : 0;
+	if (!smc_ism_v2_capable) {
+		ini->smcd_version &= ~SMC_V2;
+		goto out;
+	}
+	pclc_v2_ext = smc_get_clc_v2_ext(pclc);
+	if (!pclc_v2_ext) {
+		ini->smcd_version &= ~SMC_V2;
+		goto out;
+	}
+	pclc_smcd_v2_ext = smc_get_clc_smcd_v2_ext(pclc_v2_ext);
+	if (!pclc_smcd_v2_ext)
+		ini->smcd_version &= ~SMC_V2;
+
+out:
+	if (!ini->smcd_version) {
+		if (pclc->hdr.typev1 == SMC_TYPE_B ||
+		    pclc->hdr.typev2 == SMC_TYPE_B)
+			return SMC_CLC_DECL_NOSMCDEV;
+		if (pclc->hdr.typev1 == SMC_TYPE_D ||
+		    pclc->hdr.typev2 == SMC_TYPE_D)
+			return SMC_CLC_DECL_NOSMCDDEV;
+		return SMC_CLC_DECL_NOSMCRDEV;
+	}
+
+	return 0;
+}
+
 /* listen worker: check prefixes */
 static int smc_listen_prfx_check(struct smc_sock *new_smc,
 				 struct smc_clc_msg_proposal *pclc)
@@ -1161,6 +1384,8 @@ static int smc_listen_prfx_check(struct smc_sock *new_smc,
 	struct smc_clc_msg_proposal_prefix *pclc_prfx;
 	struct socket *newclcsock = new_smc->clcsock;
 
+	if (pclc->hdr.typev1 == SMC_TYPE_N)
+		return 0;
 	pclc_prfx = smc_clc_proposal_get_prefix(pclc);
 	if (smc_clc_prfx_match(newclcsock, pclc_prfx))
 		return SMC_CLC_DECL_DIFFPREFIX;
@@ -1188,7 +1413,6 @@ static int smc_listen_rdma_init(struct smc_sock *new_smc,
 
 /* listen worker: initialize connection and buffers for SMC-D */
 static int smc_listen_ism_init(struct smc_sock *new_smc,
-			       struct smc_clc_msg_proposal *pclc,
 			       struct smc_init_info *ini)
 {
 	int rc;
@@ -1211,6 +1435,125 @@ static int smc_listen_ism_init(struct smc_sock *new_smc,
 	return 0;
 }
 
+static bool smc_is_already_selected(struct smcd_dev *smcd,
+				    struct smc_init_info *ini,
+				    int matches)
+{
+	int i;
+
+	for (i = 0; i < matches; i++)
+		if (smcd == ini->ism_dev[i])
+			return true;
+
+	return false;
+}
+
+/* check for ISM devices matching proposed ISM devices */
+static void smc_check_ism_v2_match(struct smc_init_info *ini,
+				   u16 proposed_chid, u64 proposed_gid,
+				   unsigned int *matches)
+{
+	struct smcd_dev *smcd;
+
+	list_for_each_entry(smcd, &smcd_dev_list.list, list) {
+		if (smcd->going_away)
+			continue;
+		if (smc_is_already_selected(smcd, ini, *matches))
+			continue;
+		if (smc_ism_get_chid(smcd) == proposed_chid &&
+		    !smc_ism_cantalk(proposed_gid, ISM_RESERVED_VLANID, smcd)) {
+			ini->ism_peer_gid[*matches] = proposed_gid;
+			ini->ism_dev[*matches] = smcd;
+			(*matches)++;
+			break;
+		}
+	}
+}
+
+static void smc_find_ism_v2_device_serv(struct smc_sock *new_smc,
+					struct smc_clc_msg_proposal *pclc,
+					struct smc_init_info *ini)
+{
+	struct smc_clc_smcd_v2_extension *smcd_v2_ext;
+	struct smc_clc_v2_extension *smc_v2_ext;
+	struct smc_clc_msg_smcd *pclc_smcd;
+	unsigned int matches = 0;
+	u8 *eid = NULL;
+	int i;
+
+	if (!(ini->smcd_version & SMC_V2) || !smcd_indicated(ini->smc_type_v2))
+		return;
+
+	pclc_smcd = smc_get_clc_msg_smcd(pclc);
+	smc_v2_ext = smc_get_clc_v2_ext(pclc);
+	smcd_v2_ext = smc_get_clc_smcd_v2_ext(smc_v2_ext);
+	if (!smcd_v2_ext ||
+	    !smc_v2_ext->hdr.flag.seid) /* no system EID support for SMCD */
+		goto not_found;
+
+	mutex_lock(&smcd_dev_list.mutex);
+	if (pclc_smcd->ism.chid)
+		/* check for ISM device matching proposed native ISM device */
+		smc_check_ism_v2_match(ini, ntohs(pclc_smcd->ism.chid),
+				       ntohll(pclc_smcd->ism.gid), &matches);
+	for (i = 1; i <= smc_v2_ext->hdr.ism_gid_cnt; i++) {
+		/* check for ISM devices matching proposed non-native ISM
+		 * devices
+		 */
+		smc_check_ism_v2_match(ini,
+				       ntohs(smcd_v2_ext->gidchid[i - 1].chid),
+				       ntohll(smcd_v2_ext->gidchid[i - 1].gid),
+				       &matches);
+	}
+	mutex_unlock(&smcd_dev_list.mutex);
+
+	if (ini->ism_dev[0]) {
+		smc_ism_get_system_eid(ini->ism_dev[0], &eid);
+		if (memcmp(eid, smcd_v2_ext->system_eid, SMC_MAX_EID_LEN))
+			goto not_found;
+	} else {
+		goto not_found;
+	}
+
+	/* separate - outside the smcd_dev_list.lock */
+	for (i = 0; i < matches; i++) {
+		ini->smcd_version = SMC_V2;
+		ini->is_smcd = true;
+		ini->ism_selected = i;
+		if (smc_listen_ism_init(new_smc, ini))
+			/* try next active ISM device */
+			continue;
+		return; /* matching and usable V2 ISM device found */
+	}
+
+not_found:
+	ini->smcd_version &= ~SMC_V2;
+	ini->ism_dev[0] = NULL;
+	ini->is_smcd = false;
+}
+
+static void smc_find_ism_v1_device_serv(struct smc_sock *new_smc,
+					struct smc_clc_msg_proposal *pclc,
+					struct smc_init_info *ini)
+{
+	struct smc_clc_msg_smcd *pclc_smcd = smc_get_clc_msg_smcd(pclc);
+
+	/* check if ISM V1 is available */
+	if (!(ini->smcd_version & SMC_V1) || !smcd_indicated(ini->smc_type_v1))
+		goto not_found;
+	ini->is_smcd = true; /* prepare ISM check */
+	ini->ism_peer_gid[0] = ntohll(pclc_smcd->ism.gid);
+	if (smc_find_ism_device(new_smc, ini))
+		goto not_found;
+	ini->ism_selected = 0;
+	if (!smc_listen_ism_init(new_smc, ini))
+		return;		/* V1 ISM device found */
+
+not_found:
+	ini->ism_dev[0] = NULL;
+	ini->is_smcd = false;
+}
+
 /* listen worker: register buffers */
 static int smc_listen_rdma_reg(struct smc_sock *new_smc, bool local_first)
 {
@@ -1225,6 +1568,67 @@ static int smc_listen_rdma_reg(struct smc_sock *new_smc, bool local_first)
 	return 0;
 }
 
+static int smc_find_rdma_v1_device_serv(struct smc_sock *new_smc,
+					struct smc_clc_msg_proposal *pclc,
+					struct smc_init_info *ini)
+{
+	int rc;
+
+	if (!smcr_indicated(ini->smc_type_v1))
+		return SMC_CLC_DECL_NOSMCDEV;
+
+	/* prepare RDMA check */
+	ini->ib_lcl = &pclc->lcl;
+	rc = smc_find_rdma_device(new_smc, ini);
+	if (rc) {
+		/* no RDMA device found */
+		if (ini->smc_type_v1 == SMC_TYPE_B)
+			/* neither ISM nor RDMA device found */
+			rc = SMC_CLC_DECL_NOSMCDEV;
+		return rc;
+	}
+	rc = smc_listen_rdma_init(new_smc, ini);
+	if (rc)
+		return rc;
+	return smc_listen_rdma_reg(new_smc, ini->first_contact_local);
+}
+
+/* determine the local device matching to proposal */
+static int smc_listen_find_device(struct smc_sock *new_smc,
+				  struct smc_clc_msg_proposal *pclc,
+				  struct smc_init_info *ini)
+{
+	int rc;
+
+	/* check for ISM device matching V2 proposed device */
+	smc_find_ism_v2_device_serv(new_smc, pclc, ini);
+	if (ini->ism_dev[0])
+		return 0;
+
+	if (!(ini->smcd_version & SMC_V1))
+		return SMC_CLC_DECL_NOSMCDEV;
+
+	/* check for matching IP prefix and subnet length */
+	rc = smc_listen_prfx_check(new_smc, pclc);
+	if (rc)
+		return rc;
+
+	/* get vlan id from IP device */
+	if (smc_vlan_by_tcpsk(new_smc->clcsock, ini))
+		return SMC_CLC_DECL_GETVLANERR;
+
+	/* check for ISM device matching V1 proposed device */
+	smc_find_ism_v1_device_serv(new_smc, pclc, ini);
+	if (ini->ism_dev[0])
+		return 0;
+
+	if (pclc->hdr.typev1 == SMC_TYPE_D)
+		return SMC_CLC_DECL_NOSMCDDEV; /* skip RDMA and decline */
+
+	/* check if RDMA is available */
+	return smc_find_rdma_v1_device_serv(new_smc, pclc, ini);
+}
+
 /* listen worker: finish RDMA setup */
 static int smc_listen_rdma_finish(struct smc_sock *new_smc,
 				  struct smc_clc_msg_accept_confirm *cclc,
@@ -1250,17 +1654,18 @@ static int smc_listen_rdma_finish(struct smc_sock *new_smc,
 	return reason_code;
 }
 
-/* setup for RDMA connection of server */
+/* setup for connection of server */
 static void smc_listen_work(struct work_struct *work)
 {
 	struct smc_sock *new_smc = container_of(work, struct smc_sock,
 						smc_listen_work);
+	u8 version = smc_ism_v2_capable ? SMC_V2 : SMC_V1;
 	struct socket *newclcsock = new_smc->clcsock;
-	struct smc_clc_msg_accept_confirm cclc;
+	struct smc_clc_msg_accept_confirm_v2 *cclc2;
+	struct smc_clc_msg_accept_confirm *cclc;
 	struct smc_clc_msg_proposal_area *buf;
 	struct smc_clc_msg_proposal *pclc;
-	struct smc_init_info ini = {0};
-	bool ism_supported = false;
+	struct smc_init_info *ini = NULL;
 	int rc = 0;
 
 	if (new_smc->listen_smc->sk.sk_state != SMC_LISTEN)
@@ -1292,101 +1697,76 @@ static void smc_listen_work(struct work_struct *work)
 			      SMC_CLC_PROPOSAL, CLC_WAIT_TIME);
 	if (rc)
 		goto out_decl;
+	version = pclc->hdr.version == SMC_V1 ? SMC_V1 : version;
 
-	/* IPSec connections opt out of SMC-R optimizations */
+	/* IPSec connections opt out of SMC optimizations */
 	if (using_ipsec(new_smc)) {
 		rc = SMC_CLC_DECL_IPSEC;
 		goto out_decl;
 	}
 
-	/* check for matching IP prefix and subnet length */
-	rc = smc_listen_prfx_check(new_smc, pclc);
-	if (rc)
+	ini = kzalloc(sizeof(*ini), GFP_KERNEL);
+	if (!ini) {
+		rc = SMC_CLC_DECL_MEM;
 		goto out_decl;
+	}
 
-	/* get vlan id from IP device */
-	if (smc_vlan_by_tcpsk(new_smc->clcsock, &ini)) {
-		rc = SMC_CLC_DECL_GETVLANERR;
+	/* initial version checking */
+	rc = smc_listen_v2_check(new_smc, pclc, ini);
+	if (rc)
 		goto out_decl;
-	}
 
 	mutex_lock(&smc_server_lgr_pending);
 	smc_close_init(new_smc);
 	smc_rx_init(new_smc);
 	smc_tx_init(new_smc);
 
-	/* check if ISM is available */
-	if (pclc->hdr.path == SMC_TYPE_D || pclc->hdr.path == SMC_TYPE_B) {
-		struct smc_clc_msg_smcd *pclc_smcd = smc_get_clc_msg_smcd(pclc);
-
-		ini.is_smcd = true; /* prepare ISM check */
-		ini.ism_peer_gid = pclc_smcd->gid;
-		rc = smc_find_ism_device(new_smc, &ini);
-		if (!rc)
-			rc = smc_listen_ism_init(new_smc, pclc, &ini);
-		if (!rc)
-			ism_supported = true;
-		else if (pclc->hdr.path == SMC_TYPE_D)
-			goto out_unlock; /* skip RDMA and decline */
-	}
-
-	/* check if RDMA is available */
-	if (!ism_supported) { /* SMC_TYPE_R or SMC_TYPE_B */
-		/* prepare RDMA check */
-		ini.is_smcd = false;
-		ini.ism_dev = NULL;
-		ini.ib_lcl = &pclc->lcl;
-		rc = smc_find_rdma_device(new_smc, &ini);
-		if (rc) {
-			/* no RDMA device found */
-			if (pclc->hdr.path == SMC_TYPE_B)
-				/* neither ISM nor RDMA device found */
-				rc = SMC_CLC_DECL_NOSMCDEV;
-			goto out_unlock;
-		}
-		rc = smc_listen_rdma_init(new_smc, &ini);
-		if (rc)
-			goto out_unlock;
-		rc = smc_listen_rdma_reg(new_smc, ini.first_contact_local);
-		if (rc)
-			goto out_unlock;
-	}
+	/* determine ISM or RoCE device used for connection */
+	rc = smc_listen_find_device(new_smc, pclc, ini);
+	if (rc)
+		goto out_unlock;
 
 	/* send SMC Accept CLC message */
-	rc = smc_clc_send_accept(new_smc, ini.first_contact_local);
+	rc = smc_clc_send_accept(new_smc, ini->first_contact_local,
+				 ini->smcd_version == SMC_V2 ? SMC_V2 : SMC_V1);
 	if (rc)
 		goto out_unlock;
 
 	/* SMC-D does not need this lock any more */
-	if (ism_supported)
+	if (ini->is_smcd)
 		mutex_unlock(&smc_server_lgr_pending);
 
 	/* receive SMC Confirm CLC message */
-	rc = smc_clc_wait_msg(new_smc, &cclc, sizeof(cclc),
+	cclc2 = (struct smc_clc_msg_accept_confirm_v2 *)buf;
+	cclc = (struct smc_clc_msg_accept_confirm *)cclc2;
+	memset(buf, 0, sizeof(struct smc_clc_msg_proposal_area));
+	rc = smc_clc_wait_msg(new_smc, cclc2,
+			      sizeof(struct smc_clc_msg_proposal_area),
 			      SMC_CLC_CONFIRM, CLC_WAIT_TIME);
 	if (rc) {
-		if (!ism_supported)
+		if (!ini->is_smcd)
 			goto out_unlock;
 		goto out_decl;
 	}
 
 	/* finish worker */
-	if (!ism_supported) {
-		rc = smc_listen_rdma_finish(new_smc, &cclc,
-					    ini.first_contact_local);
+	if (!ini->is_smcd) {
+		rc = smc_listen_rdma_finish(new_smc, cclc,
+					    ini->first_contact_local);
 		if (rc)
 			goto out_unlock;
 		mutex_unlock(&smc_server_lgr_pending);
 	}
-	smc_conn_save_peer_info(new_smc, &cclc);
+	smc_conn_save_peer_info(new_smc, cclc);
 	smc_listen_out_connected(new_smc);
 	goto out_free;
 
 out_unlock:
 	mutex_unlock(&smc_server_lgr_pending);
 out_decl:
-	smc_listen_decline(new_smc, rc, ini.first_contact_local);
+	smc_listen_decline(new_smc, rc, ini, version);
 out_free:
+	kfree(ini);
 	kfree(buf);
 }
 
@@ -2092,6 +2472,9 @@ static int __init smc_init(void)
 	if (rc)
 		return rc;
 
+	smc_ism_init();
+	smc_clc_init();
+
 	rc = smc_pnet_init();
 	if (rc)
 		goto out_pernet_subsys;
diff --git a/net/smc/smc.h b/net/smc/smc.h
index 2bd57e57b7e7..d65e15f0c944 100644
--- a/net/smc/smc.h
+++ b/net/smc/smc.h
@@ -19,10 +19,19 @@
 #include "smc_ib.h"
 
 #define SMC_V1		1		/* SMC version V1 */
+#define SMC_V2		2		/* SMC version V2 */
+#define SMC_RELEASE	0
 
 #define SMCPROTO_SMC		0	/* SMC protocol, IPv4 */
 #define SMCPROTO_SMC6		1	/* SMC protocol, IPv6 */
 
+#define SMC_MAX_ISM_DEVS	8	/* max # of proposed non-native ISM
+					 * devices
+					 */
+
+#define SMC_MAX_HOSTNAME_LEN	32
+#define SMC_MAX_EID_LEN		32
+
 extern struct proto smc_proto;
 extern struct proto smc_proto6;
 
@@ -246,6 +255,9 @@ extern struct workqueue_struct	*smc_close_wq;	/* wq for close work */
 
 extern u8	local_systemid[SMC_SYSTEMID_LEN]; /* unique system identifier */
 
+#define ntohll(x) be64_to_cpu(x)
+#define htonll(x) cpu_to_be64(x)
+
 /* convert an u32 value into network byte order, store it into a 3 byte field */
 static inline void hton24(u8 *net, u32 host)
 {
diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c
index bd116e1949b9..696d89c2dce4 100644
--- a/net/smc/smc_clc.c
+++ b/net/smc/smc_clc.c
@@ -14,6 +14,8 @@
 #include <linux/inetdevice.h>
 #include <linux/if_ether.h>
 #include <linux/sched/signal.h>
+#include <linux/utsname.h>
+#include <linux/ctype.h>
 
 #include <net/addrconf.h>
 #include <net/sock.h>
@@ -27,6 +29,7 @@
 
 #define SMCR_CLC_ACCEPT_CONFIRM_LEN 68
 #define SMCD_CLC_ACCEPT_CONFIRM_LEN 48
+#define SMCD_CLC_ACCEPT_CONFIRM_LEN_V2 78
 #define SMC_CLC_RECV_BUF_LEN	100
 
 /* eye catcher "SMCR" EBCDIC for CLC messages */
@@ -34,13 +37,88 @@ static const char SMC_EYECATCHER[4] = {'\xe2', '\xd4', '\xc3', '\xd9'};
 /* eye catcher "SMCD" EBCDIC for CLC messages */
 static const char SMCD_EYECATCHER[4] = {'\xe2', '\xd4', '\xc3', '\xc4'};
 
+static u8 smc_hostname[SMC_MAX_HOSTNAME_LEN];
+
+/* check arriving CLC proposal */
+static bool smc_clc_msg_prop_valid(struct smc_clc_msg_proposal *pclc)
+{
+	struct smc_clc_msg_proposal_prefix *pclc_prfx;
+	struct smc_clc_smcd_v2_extension *smcd_v2_ext;
+	struct smc_clc_msg_hdr *hdr = &pclc->hdr;
+	struct smc_clc_v2_extension *v2_ext;
+
+	v2_ext = smc_get_clc_v2_ext(pclc);
+	pclc_prfx = smc_clc_proposal_get_prefix(pclc);
+	if (hdr->version == SMC_V1) {
+		if (hdr->typev1 == SMC_TYPE_N)
+			return false;
+		if (ntohs(hdr->length) !=
+			sizeof(*pclc) + ntohs(pclc->iparea_offset) +
+			sizeof(*pclc_prfx) +
+			pclc_prfx->ipv6_prefixes_cnt *
+				sizeof(struct smc_clc_ipv6_prefix) +
+			sizeof(struct smc_clc_msg_trail))
+			return false;
+	} else {
+		if (ntohs(hdr->length) !=
+			sizeof(*pclc) +
+			sizeof(struct smc_clc_msg_smcd) +
+			(hdr->typev1 != SMC_TYPE_N ?
+				sizeof(*pclc_prfx) +
+				pclc_prfx->ipv6_prefixes_cnt *
+				sizeof(struct smc_clc_ipv6_prefix) : 0) +
+			(hdr->typev2 != SMC_TYPE_N ?
+				sizeof(*v2_ext) +
+				v2_ext->hdr.eid_cnt * SMC_MAX_EID_LEN : 0) +
+			(smcd_indicated(hdr->typev2) ?
+				sizeof(*smcd_v2_ext) + v2_ext->hdr.ism_gid_cnt *
+					sizeof(struct smc_clc_smcd_gid_chid) :
+				0) +
+			sizeof(struct smc_clc_msg_trail))
+			return false;
+	}
+	return true;
+}
+
+/* check arriving CLC accept or confirm */
+static bool
+smc_clc_msg_acc_conf_valid(struct smc_clc_msg_accept_confirm_v2 *clc_v2)
+{
+	struct smc_clc_msg_hdr *hdr = &clc_v2->hdr;
+
+	if (hdr->typev1 != SMC_TYPE_R && hdr->typev1 != SMC_TYPE_D)
+		return false;
+	if (hdr->version == SMC_V1) {
+		if ((hdr->typev1 == SMC_TYPE_R &&
+		     ntohs(hdr->length) != SMCR_CLC_ACCEPT_CONFIRM_LEN) ||
+		    (hdr->typev1 == SMC_TYPE_D &&
+		     ntohs(hdr->length) != SMCD_CLC_ACCEPT_CONFIRM_LEN))
+			return false;
+	} else {
+		if (hdr->typev1 == SMC_TYPE_D &&
+		    ntohs(hdr->length) != SMCD_CLC_ACCEPT_CONFIRM_LEN_V2 &&
+		    (ntohs(hdr->length) != SMCD_CLC_ACCEPT_CONFIRM_LEN_V2 +
+				sizeof(struct smc_clc_first_contact_ext)))
+			return false;
+	}
+	return true;
+}
+
+static void smc_clc_fill_fce(struct smc_clc_first_contact_ext *fce, int *len)
+{
+	memset(fce, 0, sizeof(*fce));
+	fce->os_type = SMC_CLC_OS_LINUX;
+	fce->release = SMC_RELEASE;
+	memcpy(fce->hostname, smc_hostname, sizeof(smc_hostname));
+	(*len) += sizeof(*fce);
+}
+
 /* check if received message has a correct header length and contains valid
  * heading and trailing eyecatchers
  */
 static bool smc_clc_msg_hdr_valid(struct smc_clc_msg_hdr *clcm, bool check_trl)
 {
-	struct smc_clc_msg_proposal_prefix *pclc_prfx;
-	struct smc_clc_msg_accept_confirm *clc;
+	struct smc_clc_msg_accept_confirm_v2 *clc_v2;
 	struct smc_clc_msg_proposal *pclc;
 	struct smc_clc_msg_decline *dclc;
 	struct smc_clc_msg_trail *trl;
@@ -51,29 +129,19 @@ static bool smc_clc_msg_hdr_valid(struct smc_clc_msg_hdr *clcm, bool check_trl)
 	switch (clcm->type) {
 	case SMC_CLC_PROPOSAL:
 		pclc = (struct smc_clc_msg_proposal *)clcm;
-		pclc_prfx = smc_clc_proposal_get_prefix(pclc);
-		if (ntohs(pclc->hdr.length) <
-			sizeof(*pclc) + ntohs(pclc->iparea_offset) +
-			sizeof(*pclc_prfx) +
-			pclc_prfx->ipv6_prefixes_cnt *
-				sizeof(struct smc_clc_ipv6_prefix) +
-			sizeof(*trl))
+		if (!smc_clc_msg_prop_valid(pclc))
 			return false;
 		trl = (struct smc_clc_msg_trail *)
 			((u8 *)pclc + ntohs(pclc->hdr.length) - sizeof(*trl));
 		break;
 	case SMC_CLC_ACCEPT:
 	case SMC_CLC_CONFIRM:
-		if (clcm->path != SMC_TYPE_R && clcm->path != SMC_TYPE_D)
-			return false;
-		clc = (struct smc_clc_msg_accept_confirm *)clcm;
-		if ((clcm->path == SMC_TYPE_R &&
-		     ntohs(clc->hdr.length) != SMCR_CLC_ACCEPT_CONFIRM_LEN) ||
-		    (clcm->path == SMC_TYPE_D &&
-		     ntohs(clc->hdr.length) != SMCD_CLC_ACCEPT_CONFIRM_LEN))
+		clc_v2 = (struct smc_clc_msg_accept_confirm_v2 *)clcm;
+		if (!smc_clc_msg_acc_conf_valid(clc_v2))
 			return false;
 		trl = (struct smc_clc_msg_trail *)
-			((u8 *)clc + ntohs(clc->hdr.length) - sizeof(*trl));
+			((u8 *)clc_v2 + ntohs(clc_v2->hdr.length) -
+							sizeof(*trl));
 		break;
 	case SMC_CLC_DECLINE:
 		dclc = (struct smc_clc_msg_decline *)clcm;
@@ -327,9 +395,6 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
 		goto out;
 	}
 
-	if (clcm->type == SMC_CLC_PROPOSAL && clcm->path == SMC_TYPE_N)
-		reason_code = SMC_CLC_DECL_VERSMISMAT; /* just V2 offered */
-
 	/* receive the complete CLC message */
 	memset(&msg, 0, sizeof(struct msghdr));
 	if (datlen > buflen) {
@@ -365,7 +430,8 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
 		dclc = (struct smc_clc_msg_decline *)clcm;
 		reason_code = SMC_CLC_DECL_PEERDECL;
 		smc->peer_diagnosis = ntohl(dclc->peer_diagnosis);
-		if (((struct smc_clc_msg_decline *)buf)->hdr.flag) {
+		if (((struct smc_clc_msg_decline *)buf)->hdr.typev2 &
+						SMC_FIRST_CONTACT_MASK) {
 			smc->conn.lgr->sync_err = 1;
 			smc_lgr_terminate_sched(smc->conn.lgr);
 		}
@@ -377,7 +443,7 @@ out:
 }
 
 /* send CLC DECLINE message across internal TCP socket */
-int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info)
+int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info, u8 version)
 {
 	struct smc_clc_msg_decline dclc;
 	struct msghdr msg;
@@ -388,8 +454,10 @@ int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info)
 	memcpy(dclc.hdr.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER));
 	dclc.hdr.type = SMC_CLC_DECLINE;
 	dclc.hdr.length = htons(sizeof(struct smc_clc_msg_decline));
-	dclc.hdr.version = SMC_V1;
-	dclc.hdr.flag = (peer_diag_info == SMC_CLC_DECL_SYNCERR) ? 1 : 0;
+	dclc.hdr.version = version;
+	dclc.os_type = version == SMC_V1 ? 0 : SMC_CLC_OS_LINUX;
+	dclc.hdr.typev2 = (peer_diag_info == SMC_CLC_DECL_SYNCERR) ?
+						SMC_FIRST_CONTACT_MASK : 0;
 	if ((!smc->conn.lgr || !smc->conn.lgr->is_smcd) &&
 	    smc_ib_is_valid_local_systemid())
 		memcpy(dclc.id_for_peer, local_systemid,
@@ -408,18 +476,20 @@ int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info)
 }
 
 /* send CLC PROPOSAL message across internal TCP socket */
-int smc_clc_send_proposal(struct smc_sock *smc, int smc_type,
-			  struct smc_init_info *ini)
+int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini)
 {
+	struct smc_clc_smcd_v2_extension *smcd_v2_ext;
 	struct smc_clc_msg_proposal_prefix *pclc_prfx;
 	struct smc_clc_msg_proposal *pclc_base;
+	struct smc_clc_smcd_gid_chid *gidchids;
 	struct smc_clc_msg_proposal_area *pclc;
 	struct smc_clc_ipv6_prefix *ipv6_prfx;
+	struct smc_clc_v2_extension *v2_ext;
 	struct smc_clc_msg_smcd *pclc_smcd;
 	struct smc_clc_msg_trail *trl;
 	int len, i, plen, rc;
 	int reason_code = 0;
-	struct kvec vec[5];
+	struct kvec vec[8];
 	struct msghdr msg;
 
 	pclc = kzalloc(sizeof(*pclc), GFP_KERNEL);
@@ -430,56 +500,121 @@ int smc_clc_send_proposal(struct smc_sock *smc, int smc_type,
 	pclc_smcd = &pclc->pclc_smcd;
 	pclc_prfx = &pclc->pclc_prfx;
 	ipv6_prfx = pclc->pclc_prfx_ipv6;
+	v2_ext = &pclc->pclc_v2_ext;
+	smcd_v2_ext = &pclc->pclc_smcd_v2_ext;
+	gidchids = pclc->pclc_gidchids;
 	trl = &pclc->pclc_trl;
 
+	pclc_base->hdr.version = SMC_V2;
+	pclc_base->hdr.typev1 = ini->smc_type_v1;
+	pclc_base->hdr.typev2 = ini->smc_type_v2;
+	plen = sizeof(*pclc_base) + sizeof(*pclc_smcd) + sizeof(*trl);
+
 	/* retrieve ip prefixes for CLC proposal msg */
-	rc = smc_clc_prfx_set(smc->clcsock, pclc_prfx, ipv6_prfx);
-	if (rc) {
-		kfree(pclc);
-		return SMC_CLC_DECL_CNFERR; /* configuration error */
+	if (ini->smc_type_v1 != SMC_TYPE_N) {
+		rc = smc_clc_prfx_set(smc->clcsock, pclc_prfx, ipv6_prfx);
+		if (rc) {
+			if (ini->smc_type_v2 == SMC_TYPE_N) {
+				kfree(pclc);
+				return SMC_CLC_DECL_CNFERR;
+			}
+			pclc_base->hdr.typev1 = SMC_TYPE_N;
+		} else {
+			pclc_base->iparea_offset = htons(sizeof(*pclc_smcd));
+			plen += sizeof(*pclc_prfx) +
+					pclc_prfx->ipv6_prefixes_cnt *
+					sizeof(ipv6_prfx[0]);
+		}
 	}
 
-	/* send SMC Proposal CLC message */
-	plen = sizeof(*pclc_base) + sizeof(*pclc_prfx) +
-	       (pclc_prfx->ipv6_prefixes_cnt * sizeof(ipv6_prfx[0])) +
-	       sizeof(*trl);
+	/* build SMC Proposal CLC message */
 	memcpy(pclc_base->hdr.eyecatcher, SMC_EYECATCHER,
 	       sizeof(SMC_EYECATCHER));
 	pclc_base->hdr.type = SMC_CLC_PROPOSAL;
-	pclc_base->hdr.version = SMC_V1;		/* SMC version */
-	pclc_base->hdr.path = smc_type;
-	if (smc_type == SMC_TYPE_R || smc_type == SMC_TYPE_B) {
+	if (smcr_indicated(ini->smc_type_v1)) {
 		/* add SMC-R specifics */
 		memcpy(pclc_base->lcl.id_for_peer, local_systemid,
 		       sizeof(local_systemid));
 		memcpy(pclc_base->lcl.gid, ini->ib_gid, SMC_GID_SIZE);
 		memcpy(pclc_base->lcl.mac, &ini->ib_dev->mac[ini->ib_port - 1],
 		       ETH_ALEN);
-		pclc_base->iparea_offset = htons(0);
 	}
-	if (smc_type == SMC_TYPE_D || smc_type == SMC_TYPE_B) {
+	if (smcd_indicated(ini->smc_type_v1)) {
 		/* add SMC-D specifics */
-		plen += sizeof(*pclc_smcd);
-		pclc_base->iparea_offset = htons(sizeof(*pclc_smcd));
-		pclc_smcd->gid = ini->ism_dev->local_gid;
+		if (ini->ism_dev[0]) {
+			pclc_smcd->ism.gid = htonll(ini->ism_dev[0]->local_gid);
+			pclc_smcd->ism.chid =
+				htons(smc_ism_get_chid(ini->ism_dev[0]));
+		}
+	}
+	if (ini->smc_type_v2 == SMC_TYPE_N) {
+		pclc_smcd->v2_ext_offset = 0;
+	} else {
+		u16 v2_ext_offset;
+		u8 *eid = NULL;
+
+		v2_ext_offset = sizeof(*pclc_smcd) -
+			offsetofend(struct smc_clc_msg_smcd, v2_ext_offset);
+		if (ini->smc_type_v1 != SMC_TYPE_N)
+			v2_ext_offset += sizeof(*pclc_prfx) +
+						pclc_prfx->ipv6_prefixes_cnt *
+						sizeof(ipv6_prfx[0]);
+		pclc_smcd->v2_ext_offset = htons(v2_ext_offset);
+		v2_ext->hdr.eid_cnt = 0;
+		v2_ext->hdr.ism_gid_cnt = ini->ism_offered_cnt;
+		v2_ext->hdr.flag.release = SMC_RELEASE;
+		v2_ext->hdr.flag.seid = 1;
+		v2_ext->hdr.smcd_v2_ext_offset = htons(sizeof(*v2_ext) -
+				offsetofend(struct smc_clnt_opts_area_hdr,
+					    smcd_v2_ext_offset) +
+				v2_ext->hdr.eid_cnt * SMC_MAX_EID_LEN);
+		if (ini->ism_dev[0])
+			smc_ism_get_system_eid(ini->ism_dev[0], &eid);
+		else
+			smc_ism_get_system_eid(ini->ism_dev[1], &eid);
+		if (eid)
+			memcpy(smcd_v2_ext->system_eid, eid, SMC_MAX_EID_LEN);
+		plen += sizeof(*v2_ext) + sizeof(*smcd_v2_ext);
+		if (ini->ism_offered_cnt) {
+			for (i = 1; i <= ini->ism_offered_cnt; i++) {
+				gidchids[i - 1].gid =
+					htonll(ini->ism_dev[i]->local_gid);
+				gidchids[i - 1].chid =
+					htons(smc_ism_get_chid(ini->ism_dev[i]));
+			}
+			plen += ini->ism_offered_cnt *
+				sizeof(struct smc_clc_smcd_gid_chid);
+		}
 	}
 	pclc_base->hdr.length = htons(plen);
-
 	memcpy(trl->eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER));
+
+	/* send SMC Proposal CLC message */
 	memset(&msg, 0, sizeof(msg));
 	i = 0;
 	vec[i].iov_base = pclc_base;
 	vec[i++].iov_len = sizeof(*pclc_base);
-	if (smc_type == SMC_TYPE_D || smc_type == SMC_TYPE_B) {
-		vec[i].iov_base = pclc_smcd;
-		vec[i++].iov_len = sizeof(*pclc_smcd);
+	vec[i].iov_base = pclc_smcd;
+	vec[i++].iov_len = sizeof(*pclc_smcd);
+	if (ini->smc_type_v1 != SMC_TYPE_N) {
+		vec[i].iov_base = pclc_prfx;
+		vec[i++].iov_len = sizeof(*pclc_prfx);
+		if (pclc_prfx->ipv6_prefixes_cnt > 0) {
+			vec[i].iov_base = ipv6_prfx;
+			vec[i++].iov_len = pclc_prfx->ipv6_prefixes_cnt *
+					   sizeof(ipv6_prfx[0]);
+		}
 	}
-	vec[i].iov_base = pclc_prfx;
-	vec[i++].iov_len = sizeof(*pclc_prfx);
-	if (pclc_prfx->ipv6_prefixes_cnt > 0) {
-		vec[i].iov_base = ipv6_prfx;
-		vec[i++].iov_len = pclc_prfx->ipv6_prefixes_cnt *
-				   sizeof(ipv6_prfx[0]);
+	if (ini->smc_type_v2 != SMC_TYPE_N) {
+		vec[i].iov_base = v2_ext;
+		vec[i++].iov_len = sizeof(*v2_ext);
+		vec[i].iov_base = smcd_v2_ext;
+		vec[i++].iov_len = sizeof(*smcd_v2_ext);
+		if (ini->ism_offered_cnt) {
+			vec[i].iov_base = gidchids;
+			vec[i++].iov_len = ini->ism_offered_cnt *
+					sizeof(struct smc_clc_smcd_gid_chid);
+		}
 	}
 	vec[i].iov_base = trl;
 	vec[i++].iov_len = sizeof(*trl);
@@ -499,29 +634,47 @@ int smc_clc_send_proposal(struct smc_sock *smc, int smc_type,
 
 /* build and send CLC CONFIRM / ACCEPT message */
 static int smc_clc_send_confirm_accept(struct smc_sock *smc,
-				       struct smc_clc_msg_accept_confirm *clc,
-				       int first_contact)
+				       struct smc_clc_msg_accept_confirm_v2 *clc_v2,
+				       int first_contact, u8 version)
 {
 	struct smc_connection *conn = &smc->conn;
+	struct smc_clc_msg_accept_confirm *clc;
+	struct smc_clc_first_contact_ext fce;
+	struct smc_clc_msg_trail trl;
+	struct kvec vec[3];
 	struct msghdr msg;
-	struct kvec vec;
+	int i, len;
 
 	/* send SMC Confirm CLC msg */
-	clc->hdr.version = SMC_V1;		/* SMC version */
+	clc = (struct smc_clc_msg_accept_confirm *)clc_v2;
+	clc->hdr.version = version;	/* SMC version */
 	if (first_contact)
-		clc->hdr.flag = 1;
+		clc->hdr.typev2 |= SMC_FIRST_CONTACT_MASK;
 	if (conn->lgr->is_smcd) {
 		/* SMC-D specific settings */
 		memcpy(clc->hdr.eyecatcher, SMCD_EYECATCHER,
 		       sizeof(SMCD_EYECATCHER));
-		clc->hdr.path = SMC_TYPE_D;
-		clc->hdr.length = htons(SMCD_CLC_ACCEPT_CONFIRM_LEN);
+		clc->hdr.typev1 = SMC_TYPE_D;
 		clc->d0.gid = conn->lgr->smcd->local_gid;
 		clc->d0.token = conn->rmb_desc->token;
 		clc->d0.dmbe_size = conn->rmbe_size_short;
 		clc->d0.dmbe_idx = 0;
 		memcpy(&clc->d0.linkid, conn->lgr->id, SMC_LGR_ID_SIZE);
-		memcpy(clc->d0.smcd_trl.eyecatcher, SMCD_EYECATCHER,
+		if (version == SMC_V1) {
+			clc->hdr.length = htons(SMCD_CLC_ACCEPT_CONFIRM_LEN);
+		} else {
+			u8 *eid = NULL;
+
+			clc_v2->chid = htons(smc_ism_get_chid(conn->lgr->smcd));
+			smc_ism_get_system_eid(conn->lgr->smcd, &eid);
+			if (eid)
+				memcpy(clc_v2->eid, eid, SMC_MAX_EID_LEN);
+			len = SMCD_CLC_ACCEPT_CONFIRM_LEN_V2;
+			if (first_contact)
+				smc_clc_fill_fce(&fce, &len);
+			clc_v2->hdr.length = htons(len);
+		}
+		memcpy(trl.eyecatcher, SMCD_EYECATCHER,
 		       sizeof(SMCD_EYECATCHER));
 	} else {
 		struct smc_link *link = conn->lnk;
@@ -530,7 +683,7 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc,
 		link = conn->lnk;
 		memcpy(clc->hdr.eyecatcher, SMC_EYECATCHER,
 		       sizeof(SMC_EYECATCHER));
-		clc->hdr.path = SMC_TYPE_R;
+		clc->hdr.typev1 = SMC_TYPE_R;
 		clc->hdr.length = htons(SMCR_CLC_ACCEPT_CONFIRM_LEN);
 		memcpy(clc->r0.lcl.id_for_peer, local_systemid,
 		       sizeof(local_systemid));
@@ -554,29 +707,43 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc,
 		clc->r0.rmb_dma_addr = cpu_to_be64((u64)sg_dma_address
 				(conn->rmb_desc->sgt[link->link_idx].sgl));
 		hton24(clc->r0.psn, link->psn_initial);
-		memcpy(clc->r0.smcr_trl.eyecatcher, SMC_EYECATCHER,
-		       sizeof(SMC_EYECATCHER));
+		memcpy(trl.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER));
 	}
 
 	memset(&msg, 0, sizeof(msg));
-	vec.iov_base = clc;
-	vec.iov_len = ntohs(clc->hdr.length);
-	return kernel_sendmsg(smc->clcsock, &msg, &vec, 1,
+	i = 0;
+	vec[i].iov_base = clc_v2;
+	if (version > SMC_V1)
+		vec[i++].iov_len = SMCD_CLC_ACCEPT_CONFIRM_LEN_V2 - sizeof(trl);
+	else
+		vec[i++].iov_len = (clc->hdr.typev1 == SMC_TYPE_D ?
+						SMCD_CLC_ACCEPT_CONFIRM_LEN :
+						SMCR_CLC_ACCEPT_CONFIRM_LEN) -
+				   sizeof(trl);
+	if (version > SMC_V1 && first_contact) {
+		vec[i].iov_base = &fce;
+		vec[i++].iov_len = sizeof(fce);
+	}
+	vec[i].iov_base = &trl;
+	vec[i++].iov_len = sizeof(trl);
+	return kernel_sendmsg(smc->clcsock, &msg, vec, 1,
 			      ntohs(clc->hdr.length));
 }
 
 /* send CLC CONFIRM message across internal TCP socket */
-int smc_clc_send_confirm(struct smc_sock *smc)
+int smc_clc_send_confirm(struct smc_sock *smc, bool clnt_first_contact,
+			 u8 version)
 {
-	struct smc_clc_msg_accept_confirm cclc;
+	struct smc_clc_msg_accept_confirm_v2 cclc_v2;
 	int reason_code = 0;
 	int len;
 
 	/* send SMC Confirm CLC msg */
-	memset(&cclc, 0, sizeof(cclc));
-	cclc.hdr.type = SMC_CLC_CONFIRM;
-	len = smc_clc_send_confirm_accept(smc, &cclc, 0);
-	if (len < ntohs(cclc.hdr.length)) {
+	memset(&cclc_v2, 0, sizeof(cclc_v2));
+	cclc_v2.hdr.type = SMC_CLC_CONFIRM;
+	len = smc_clc_send_confirm_accept(smc, &cclc_v2, clnt_first_contact,
+					  version);
+	if (len < ntohs(cclc_v2.hdr.length)) {
 		if (len >= 0) {
 			reason_code = -ENETUNREACH;
 			smc->sk.sk_err = -reason_code;
@@ -589,16 +756,28 @@ int smc_clc_send_confirm(struct smc_sock *smc)
 }
 
 /* send CLC ACCEPT message across internal TCP socket */
-int smc_clc_send_accept(struct smc_sock *new_smc, bool srv_first_contact)
+int smc_clc_send_accept(struct smc_sock *new_smc, bool srv_first_contact,
+			u8 version)
 {
-	struct smc_clc_msg_accept_confirm aclc;
+	struct smc_clc_msg_accept_confirm_v2 aclc_v2;
 	int len;
 
-	memset(&aclc, 0, sizeof(aclc));
-	aclc.hdr.type = SMC_CLC_ACCEPT;
-	len = smc_clc_send_confirm_accept(new_smc, &aclc, srv_first_contact);
-	if (len < ntohs(aclc.hdr.length))
+	memset(&aclc_v2, 0, sizeof(aclc_v2));
+	aclc_v2.hdr.type = SMC_CLC_ACCEPT;
+	len = smc_clc_send_confirm_accept(new_smc, &aclc_v2, srv_first_contact,
+					  version);
+	if (len < ntohs(aclc_v2.hdr.length))
 		len = len >= 0 ? -EPROTO : -new_smc->clcsock->sk->sk_err;
 
 	return len > 0 ? 0 : len;
 }
+
+void __init smc_clc_init(void)
+{
+	struct new_utsname *u;
+
+	memset(smc_hostname, _S, sizeof(smc_hostname)); /* ASCII blanks */
+	u = utsname();
+	memcpy(smc_hostname, u->nodename,
+	       min_t(size_t, strlen(u->nodename), sizeof(smc_hostname)));
+}
diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h
index fcd8521c7737..b3f46ab79e47 100644
--- a/net/smc/smc_clc.h
+++ b/net/smc/smc_clc.h
@@ -54,19 +54,19 @@
 #define SMC_CLC_DECL_ERR_RDYLNK	0x09990002  /*	 ib ready link failed	      */
 #define SMC_CLC_DECL_ERR_REGRMB	0x09990003  /*	 reg rmb failed		      */
 
+#define SMC_FIRST_CONTACT_MASK	0b10	/* first contact bit within typev2 */
+
 struct smc_clc_msg_hdr {	/* header1 of clc messages */
 	u8 eyecatcher[4];	/* eye catcher */
 	u8 type;		/* proposal / accept / confirm / decline */
 	__be16 length;
 #if defined(__BIG_ENDIAN_BITFIELD)
 	u8 version : 4,
-	   flag    : 1,
-	   rsvd	   : 1,
-	   path	   : 2;
+	   typev2  : 2,
+	   typev1  : 2;
 #elif defined(__LITTLE_ENDIAN_BITFIELD)
-	u8 path    : 2,
-	   rsvd    : 1,
-	   flag    : 1,
+	u8 typev1  : 2,
+	   typev2  : 2,
 	   version : 4;
 #endif
 } __packed;			/* format defined in RFC7609 */
@@ -81,8 +81,6 @@ struct smc_clc_msg_local {	/* header2 of clc messages */
 	u8 mac[6];		/* mac of ib_device port */
 };
 
-#define SMC_CLC_MAX_V6_PREFIX	8
-
 /* Struct would be 4 byte aligned, but it is used in an array that is sent
  * to peers and must conform to RFC7609, hence we need to use packed here.
  */
@@ -91,6 +89,44 @@ struct smc_clc_ipv6_prefix {
 	u8 prefix_len;
 } __packed;			/* format defined in RFC7609 */
 
+#if defined(__BIG_ENDIAN_BITFIELD)
+struct smc_clc_v2_flag {
+	u8 release : 4,
+	   rsvd    : 3,
+	   seid    : 1;
+};
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+struct smc_clc_v2_flag {
+	u8 seid   : 1,
+	rsvd      : 3,
+	release   : 4;
+};
+#endif
+
+struct smc_clnt_opts_area_hdr {
+	u8 eid_cnt;		/* number of user defined EIDs */
+	u8 ism_gid_cnt;		/* number of ISMv2 GIDs */
+	u8 reserved1;
+	struct smc_clc_v2_flag flag;
+	u8 reserved2[2];
+	__be16 smcd_v2_ext_offset; /* SMC-Dv2 Extension Offset */
+};
+
+struct smc_clc_smcd_gid_chid {
+	__be64 gid;		/* ISM GID */
+	__be16 chid;		/* ISMv2 CHID */
+} __packed;		/* format defined in
+			 * IBM Shared Memory Communications Version 2
+			 * (https://www.ibm.com/support/pages/node/6326337)
+			 */
+
+struct smc_clc_v2_extension {
+	struct smc_clnt_opts_area_hdr hdr;
+	u8 roce[16];		/* RoCEv2 GID */
+	u8 reserved[16];
+	u8 user_eids[0][SMC_MAX_EID_LEN];
+};
+
 struct smc_clc_msg_proposal_prefix {	/* prefix part of clc proposal message*/
 	__be32 outgoing_subnet;	/* subnet mask */
 	u8 prefix_len;		/* number of significant bits in mask */
@@ -99,8 +135,15 @@ struct smc_clc_msg_proposal_prefix {	/* prefix part of clc proposal message*/
 } __aligned(4);
 
 struct smc_clc_msg_smcd {	/* SMC-D GID information */
-	u64 gid;		/* ISM GID of requestor */
-	u8 res[32];
+	struct smc_clc_smcd_gid_chid ism; /* ISM native GID+CHID of requestor */
+	__be16 v2_ext_offset;	/* SMC Version 2 Extension Offset */
+	u8 reserved[28];
+};
+
+struct smc_clc_smcd_v2_extension {
+	u8 system_eid[SMC_MAX_EID_LEN];
+	u8 reserved[16];
+	struct smc_clc_smcd_gid_chid gidchid[0];
 };
 
 struct smc_clc_msg_proposal {	/* clc proposal message sent by Linux */
@@ -109,11 +152,16 @@ struct smc_clc_msg_proposal {	/* clc proposal message sent by Linux */
 	__be16 iparea_offset;	/* offset to IP address information area */
 } __aligned(4);
 
+#define SMC_CLC_MAX_V6_PREFIX		8
+
 struct smc_clc_msg_proposal_area {
 	struct smc_clc_msg_proposal		pclc_base;
 	struct smc_clc_msg_smcd			pclc_smcd;
 	struct smc_clc_msg_proposal_prefix	pclc_prfx;
 	struct smc_clc_ipv6_prefix	pclc_prfx_ipv6[SMC_CLC_MAX_V6_PREFIX];
+	struct smc_clc_v2_extension		pclc_v2_ext;
+	struct smc_clc_smcd_v2_extension	pclc_smcd_v2_ext;
+	struct smc_clc_smcd_gid_chid		pclc_gidchids[SMC_MAX_ISM_DEVS];
 	struct smc_clc_msg_trail		pclc_trl;
 };
 
@@ -134,11 +182,9 @@ struct smcr_clc_msg_accept_confirm {	/* SMCR accept/confirm */
 	__be64 rmb_dma_addr;	/* RMB virtual address */
 	u8 reserved2;
 	u8 psn[3];		/* packet sequence number */
-	struct smc_clc_msg_trail smcr_trl;
-				/* eye catcher "SMCR" EBCDIC */
 } __packed;
 
-struct smcd_clc_msg_accept_confirm {	/* SMCD accept/confirm */
+struct smcd_clc_msg_accept_confirm_common {	/* SMCD accept/confirm */
 	u64 gid;		/* Sender GID */
 	u64 token;		/* DMB token */
 	u8 dmbe_idx;		/* DMBE index */
@@ -150,26 +196,63 @@ struct smcd_clc_msg_accept_confirm {	/* SMCD accept/confirm */
 	   dmbe_size : 4;
 #endif
 	u16 reserved4;
-	u32 linkid;		/* Link identifier */
-	u32 reserved5[3];
-	struct smc_clc_msg_trail smcd_trl;
-				/* eye catcher "SMCD" EBCDIC */
+	__be32 linkid;		/* Link identifier */
 } __packed;
 
+#define SMC_CLC_OS_ZOS		1
+#define SMC_CLC_OS_LINUX	2
+#define SMC_CLC_OS_AIX		3
+
+struct smc_clc_first_contact_ext {
+	u8 reserved1;
+#if defined(__BIG_ENDIAN_BITFIELD)
+	u8 os_type : 4,
+	   release : 4;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+	u8 release : 4,
+	   os_type : 4;
+#endif
+	u8 reserved2[2];
+	u8 hostname[SMC_MAX_HOSTNAME_LEN];
+};
+
 struct smc_clc_msg_accept_confirm {	/* clc accept / confirm message */
 	struct smc_clc_msg_hdr hdr;
 	union {
 		struct smcr_clc_msg_accept_confirm r0; /* SMC-R */
-		struct smcd_clc_msg_accept_confirm d0; /* SMC-D */
+		struct { /* SMC-D */
+			struct smcd_clc_msg_accept_confirm_common d0;
+			u32 reserved5[3];
+		};
 	};
 } __packed;			/* format defined in RFC7609 */
 
+struct smc_clc_msg_accept_confirm_v2 {	/* clc accept / confirm message */
+	struct smc_clc_msg_hdr hdr;
+	union {
+		struct smcr_clc_msg_accept_confirm r0; /* SMC-R */
+		struct { /* SMC-D */
+			struct smcd_clc_msg_accept_confirm_common d0;
+			__be16 chid;
+			u8 eid[SMC_MAX_EID_LEN];
+			u8 reserved5[8];
+		};
+	};
+};
+
 struct smc_clc_msg_decline {	/* clc decline message */
 	struct smc_clc_msg_hdr hdr;
 	u8 id_for_peer[SMC_SYSTEMID_LEN]; /* sender peer_id */
 	__be32 peer_diagnosis;	/* diagnosis information */
-	u8 reserved2[4];
-	struct smc_clc_msg_trail trl; /* eye catcher "SMCR" EBCDIC */
+#if defined(__BIG_ENDIAN_BITFIELD)
+	u8 os_type  : 4,
+	   reserved : 4;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+	u8 reserved : 4,
+	   os_type  : 4;
+#endif
+	u8 reserved2[3];
+	struct smc_clc_msg_trail trl; /* eye catcher "SMCD" or "SMCR" EBCDIC */
 } __aligned(4);
 
 /* determine start of the prefix area within the proposal message */
@@ -180,16 +263,58 @@ smc_clc_proposal_get_prefix(struct smc_clc_msg_proposal *pclc)
 	       ((u8 *)pclc + sizeof(*pclc) + ntohs(pclc->iparea_offset));
 }
 
+static inline bool smcr_indicated(int smc_type)
+{
+	return smc_type == SMC_TYPE_R || smc_type == SMC_TYPE_B;
+}
+
+static inline bool smcd_indicated(int smc_type)
+{
+	return smc_type == SMC_TYPE_D || smc_type == SMC_TYPE_B;
+}
+
 /* get SMC-D info from proposal message */
 static inline struct smc_clc_msg_smcd *
 smc_get_clc_msg_smcd(struct smc_clc_msg_proposal *prop)
 {
-	if (ntohs(prop->iparea_offset) != sizeof(struct smc_clc_msg_smcd))
+	if (smcd_indicated(prop->hdr.typev1) &&
+	    ntohs(prop->iparea_offset) != sizeof(struct smc_clc_msg_smcd))
 		return NULL;
 
 	return (struct smc_clc_msg_smcd *)(prop + 1);
 }
 
+static inline struct smc_clc_v2_extension *
+smc_get_clc_v2_ext(struct smc_clc_msg_proposal *prop)
+{
+	struct smc_clc_msg_smcd *prop_smcd = smc_get_clc_msg_smcd(prop);
+
+	if (!prop_smcd || !ntohs(prop_smcd->v2_ext_offset))
+		return NULL;
+
+	return (struct smc_clc_v2_extension *)
+	       ((u8 *)prop_smcd +
+	       offsetof(struct smc_clc_msg_smcd, v2_ext_offset) +
+	       sizeof(prop_smcd->v2_ext_offset) +
+	       ntohs(prop_smcd->v2_ext_offset));
+}
+
+static inline struct smc_clc_smcd_v2_extension *
+smc_get_clc_smcd_v2_ext(struct smc_clc_v2_extension *prop_v2ext)
+{
+	if (!prop_v2ext)
+		return NULL;
+	if (!ntohs(prop_v2ext->hdr.smcd_v2_ext_offset))
+		return NULL;
+
+	return (struct smc_clc_smcd_v2_extension *)
+		((u8 *)prop_v2ext +
+		 offsetof(struct smc_clc_v2_extension, hdr) +
+		 offsetof(struct smc_clnt_opts_area_hdr, smcd_v2_ext_offset) +
+		 sizeof(prop_v2ext->hdr.smcd_v2_ext_offset) +
+		 ntohs(prop_v2ext->hdr.smcd_v2_ext_offset));
+}
+
 struct smcd_dev;
 struct smc_init_info;
 
@@ -197,10 +322,12 @@ int smc_clc_prfx_match(struct socket *clcsock,
 		       struct smc_clc_msg_proposal_prefix *prop);
 int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
 		     u8 expected_type, unsigned long timeout);
-int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info);
-int smc_clc_send_proposal(struct smc_sock *smc, int smc_type,
-			  struct smc_init_info *ini);
-int smc_clc_send_confirm(struct smc_sock *smc);
-int smc_clc_send_accept(struct smc_sock *smc, bool srv_first_contact);
+int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info, u8 version);
+int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini);
+int smc_clc_send_confirm(struct smc_sock *smc, bool clnt_first_contact,
+			 u8 version);
+int smc_clc_send_accept(struct smc_sock *smc, bool srv_first_contact,
+			u8 version);
+void smc_clc_init(void) __init;
 
 #endif
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index c811ae1a8add..f1dbb5025c0b 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -375,7 +375,8 @@ static int smc_lgr_create(struct smc_sock *smc, struct smc_init_info *ini)
 	int i;
 
 	if (ini->is_smcd && ini->vlan_id) {
-		if (smc_ism_get_vlan(ini->ism_dev, ini->vlan_id)) {
+		if (smc_ism_get_vlan(ini->ism_dev[ini->ism_selected],
+				     ini->vlan_id)) {
 			rc = SMC_CLC_DECL_ISMVLANERR;
 			goto out;
 		}
@@ -412,13 +413,14 @@ static int smc_lgr_create(struct smc_sock *smc, struct smc_init_info *ini)
 	lgr->conns_all = RB_ROOT;
 	if (ini->is_smcd) {
 		/* SMC-D specific settings */
-		get_device(&ini->ism_dev->dev);
-		lgr->peer_gid = ini->ism_peer_gid;
-		lgr->smcd = ini->ism_dev;
-		lgr_list = &ini->ism_dev->lgr_list;
+		get_device(&ini->ism_dev[ini->ism_selected]->dev);
+		lgr->peer_gid = ini->ism_peer_gid[ini->ism_selected];
+		lgr->smcd = ini->ism_dev[ini->ism_selected];
+		lgr_list = &ini->ism_dev[ini->ism_selected]->lgr_list;
 		lgr_lock = &lgr->smcd->lgr_lock;
+		lgr->smc_version = ini->smcd_version;
 		lgr->peer_shutdown = 0;
-		atomic_inc(&ini->ism_dev->lgr_cnt);
+		atomic_inc(&ini->ism_dev[ini->ism_selected]->lgr_cnt);
 	} else {
 		/* SMC-R specific settings */
 		lgr->role = smc->listen_smc ? SMC_SERV : SMC_CLNT;
@@ -449,7 +451,7 @@ free_lgr:
 	kfree(lgr);
 ism_put_vlan:
 	if (ini->is_smcd && ini->vlan_id)
-		smc_ism_put_vlan(ini->ism_dev, ini->vlan_id);
+		smc_ism_put_vlan(ini->ism_dev[ini->ism_selected], ini->vlan_id);
 out:
 	if (rc < 0) {
 		if (rc == -ENOMEM)
@@ -1288,8 +1290,10 @@ int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini)
 	spinlock_t *lgr_lock;
 	int rc = 0;
 
-	lgr_list = ini->is_smcd ? &ini->ism_dev->lgr_list : &smc_lgr_list.list;
-	lgr_lock = ini->is_smcd ? &ini->ism_dev->lgr_lock : &smc_lgr_list.lock;
+	lgr_list = ini->is_smcd ? &ini->ism_dev[ini->ism_selected]->lgr_list :
+				  &smc_lgr_list.list;
+	lgr_lock = ini->is_smcd ? &ini->ism_dev[ini->ism_selected]->lgr_lock :
+				  &smc_lgr_list.lock;
 	ini->first_contact_local = 1;
 	role = smc->listen_smc ? SMC_SERV : SMC_CLNT;
 	if (role == SMC_CLNT && ini->first_contact_peer)
@@ -1301,7 +1305,8 @@ int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini)
 	list_for_each_entry(lgr, lgr_list, list) {
 		write_lock_bh(&lgr->conns_lock);
 		if ((ini->is_smcd ?
-		     smcd_lgr_match(lgr, ini->ism_dev, ini->ism_peer_gid) :
+		     smcd_lgr_match(lgr, ini->ism_dev[ini->ism_selected],
+				    ini->ism_peer_gid[ini->ism_selected]) :
 		     smcr_lgr_match(lgr, ini->ib_lcl, role, ini->ib_clcqpn)) &&
 		    !lgr->sync_err &&
 		    lgr->vlan_id == ini->vlan_id &&
diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h
index 37a5903789b0..f1e867ce2e63 100644
--- a/net/smc/smc_core.h
+++ b/net/smc/smc_core.h
@@ -231,6 +231,11 @@ struct smc_link_group {
 	u8			freeing : 1;	/* lgr is being freed */
 
 	bool			is_smcd;	/* SMC-R or SMC-D */
+	u8			smc_version;
+	u8			negotiated_eid[SMC_MAX_EID_LEN];
+	u8			peer_os;	/* peer operating system */
+	u8			peer_smc_release;
+	u8			peer_hostname[SMC_MAX_HOSTNAME_LEN];
 	union {
 		struct { /* SMC-R */
 			enum smc_lgr_role	role;
@@ -291,6 +296,8 @@ struct smc_clc_msg_local;
 
 struct smc_init_info {
 	u8			is_smcd;
+	u8			smc_type_v1;
+	u8			smc_type_v2;
 	u8			first_contact_peer;
 	u8			first_contact_local;
 	unsigned short		vlan_id;
@@ -301,8 +308,12 @@ struct smc_init_info {
 	u8			ib_port;
 	u32			ib_clcqpn;
 	/* SMC-D */
-	u64			ism_peer_gid;
-	struct smcd_dev		*ism_dev;
+	u64			ism_peer_gid[SMC_MAX_ISM_DEVS + 1];
+	struct smcd_dev		*ism_dev[SMC_MAX_ISM_DEVS + 1];
+	u16			ism_chid[SMC_MAX_ISM_DEVS + 1];
+	u8			ism_offered_cnt; /* # of ISM devices offered */
+	u8			ism_selected;    /* index of selected ISM dev*/
+	u8			smcd_version;
 };
 
 /* Find the connection associated with the given alert token in the link group.
diff --git a/net/smc/smc_ism.c b/net/smc/smc_ism.c
index 998c525de785..6abbdd09a580 100644
--- a/net/smc/smc_ism.c
+++ b/net/smc/smc_ism.c
@@ -21,7 +21,9 @@ struct smcd_dev_list smcd_dev_list = {
 	.mutex = __MUTEX_INITIALIZER(smcd_dev_list.mutex)
 };
 
-/* Test if an ISM communication is possible. */
+bool smc_ism_v2_capable;
+
+/* Test if an ISM communication is possible - same CPC */
 int smc_ism_cantalk(u64 peer_gid, unsigned short vlan_id, struct smcd_dev *smcd)
 {
 	return smcd->ops->query_remote_gid(smcd, peer_gid, vlan_id ? 1 : 0,
@@ -39,6 +41,16 @@ int smc_ism_write(struct smcd_dev *smcd, const struct smc_ism_position *pos,
 	return rc < 0 ? rc : 0;
 }
 
+void smc_ism_get_system_eid(struct smcd_dev *smcd, u8 **eid)
+{
+	smcd->ops->get_system_eid(smcd, eid);
+}
+
+u16 smc_ism_get_chid(struct smcd_dev *smcd)
+{
+	return smcd->ops->get_chid(smcd);
+}
+
 /* Set a connection using this DMBE. */
 void smc_ism_set_conn(struct smc_connection *conn)
 {
@@ -319,7 +331,18 @@ EXPORT_SYMBOL_GPL(smcd_alloc_dev);
 int smcd_register_dev(struct smcd_dev *smcd)
 {
 	mutex_lock(&smcd_dev_list.mutex);
-	list_add_tail(&smcd->list, &smcd_dev_list.list);
+	if (list_empty(&smcd_dev_list.list)) {
+		u8 *system_eid = NULL;
+
+		smc_ism_get_system_eid(smcd, &system_eid);
+		if (system_eid[24] != '0' || system_eid[28] != '0')
+			smc_ism_v2_capable = true;
+	}
+	/* sort list: devices without pnetid before devices with pnetid */
+	if (smcd->pnetid[0])
+		list_add_tail(&smcd->list, &smcd_dev_list.list);
+	else
+		list_add(&smcd->list, &smcd_dev_list.list);
 	mutex_unlock(&smcd_dev_list.mutex);
 
 	pr_warn_ratelimited("smc: adding smcd device %s with pnetid %.16s%s\n",
@@ -399,3 +422,8 @@ void smcd_handle_irq(struct smcd_dev *smcd, unsigned int dmbno)
 	spin_unlock_irqrestore(&smcd->lock, flags);
 }
 EXPORT_SYMBOL_GPL(smcd_handle_irq);
+
+void __init smc_ism_init(void)
+{
+	smc_ism_v2_capable = false;
+}
diff --git a/net/smc/smc_ism.h b/net/smc/smc_ism.h
index 81cc4537efd3..8048e09ddcf8 100644
--- a/net/smc/smc_ism.h
+++ b/net/smc/smc_ism.h
@@ -19,7 +19,10 @@ struct smcd_dev_list {	/* List of SMCD devices */
 	struct mutex mutex;	/* Protects list of devices */
 };
 
-extern struct smcd_dev_list	smcd_dev_list; /* list of smcd devices */
+extern struct smcd_dev_list	smcd_dev_list;	/* list of smcd devices */
+extern bool	smc_ism_v2_capable;	/* HW supports ISM V2 and thus
+					 * System EID is defined
+					 */
 
 struct smc_ism_vlanid {			/* VLAN id set on ISM device */
 	struct list_head list;
@@ -47,4 +50,7 @@ int smc_ism_unregister_dmb(struct smcd_dev *dev, struct smc_buf_desc *dmb_desc);
 int smc_ism_write(struct smcd_dev *dev, const struct smc_ism_position *pos,
 		  void *data, size_t len);
 int smc_ism_signal_shutdown(struct smc_link_group *lgr);
+void smc_ism_get_system_eid(struct smcd_dev *dev, u8 **eid);
+u16 smc_ism_get_chid(struct smcd_dev *dev);
+void smc_ism_init(void);
 #endif
diff --git a/net/smc/smc_netns.h b/net/smc/smc_netns.h
index e7a8fc4ae02f..0f4f35aa43ad 100644
--- a/net/smc/smc_netns.h
+++ b/net/smc/smc_netns.h
@@ -16,5 +16,6 @@ extern unsigned int smc_net_id;
 /* per-network namespace private data */
 struct smc_net {
 	struct smc_pnettable pnettable;
+	struct smc_pnetids_ndev pnetids_ndev;
 };
 #endif
diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c
index 70684c49510e..f3c18b991d35 100644
--- a/net/smc/smc_pnet.c
+++ b/net/smc/smc_pnet.c
@@ -29,8 +29,7 @@
 #include "smc_ism.h"
 #include "smc_core.h"
 
-#define SMC_ASCII_BLANK 32
-
+static struct net_device *__pnet_find_base_ndev(struct net_device *ndev);
 static struct net_device *pnet_find_base_ndev(struct net_device *ndev);
 
 static const struct nla_policy smc_pnet_policy[SMC_PNETID_MAX + 1] = {
@@ -73,14 +72,22 @@ struct smc_pnetentry {
 	};
 };
 
+/* Check if the pnetid is set */
+bool smc_pnet_is_pnetid_set(u8 *pnetid)
+{
+	if (pnetid[0] == 0 || pnetid[0] == _S)
+		return false;
+	return true;
+}
+
 /* Check if two given pnetids match */
 static bool smc_pnet_match(u8 *pnetid1, u8 *pnetid2)
 {
 	int i;
 
 	for (i = 0; i < SMC_MAX_PNETID_LEN; i++) {
-		if ((pnetid1[i] == 0 || pnetid1[i] == SMC_ASCII_BLANK) &&
-		    (pnetid2[i] == 0 || pnetid2[i] == SMC_ASCII_BLANK))
+		if ((pnetid1[i] == 0 || pnetid1[i] == _S) &&
+		    (pnetid2[i] == 0 || pnetid2[i] == _S))
 			break;
 		if (pnetid1[i] != pnetid2[i])
 			return false;
@@ -238,11 +245,10 @@ static int smc_pnet_remove_by_ndev(struct net_device *ndev)
 static bool smc_pnet_apply_ib(struct smc_ib_device *ib_dev, u8 ib_port,
 			      char *pnet_name)
 {
-	u8 pnet_null[SMC_MAX_PNETID_LEN] = {0};
 	bool applied = false;
 
 	mutex_lock(&smc_ib_devices.mutex);
-	if (smc_pnet_match(ib_dev->pnetid[ib_port - 1], pnet_null)) {
+	if (!smc_pnet_is_pnetid_set(ib_dev->pnetid[ib_port - 1])) {
 		memcpy(ib_dev->pnetid[ib_port - 1], pnet_name,
 		       SMC_MAX_PNETID_LEN);
 		ib_dev->pnetid_by_user[ib_port - 1] = true;
@@ -256,11 +262,10 @@ static bool smc_pnet_apply_ib(struct smc_ib_device *ib_dev, u8 ib_port,
  */
 static bool smc_pnet_apply_smcd(struct smcd_dev *smcd_dev, char *pnet_name)
 {
-	u8 pnet_null[SMC_MAX_PNETID_LEN] = {0};
 	bool applied = false;
 
 	mutex_lock(&smcd_dev_list.mutex);
-	if (smc_pnet_match(smcd_dev->pnetid, pnet_null)) {
+	if (!smc_pnet_is_pnetid_set(smcd_dev->pnetid)) {
 		memcpy(smcd_dev->pnetid, pnet_name, SMC_MAX_PNETID_LEN);
 		smcd_dev->pnetid_by_user = true;
 		applied = true;
@@ -708,10 +713,115 @@ static struct genl_family smc_pnet_nl_family __ro_after_init = {
 	.n_ops =  ARRAY_SIZE(smc_pnet_ops)
 };
 
+bool smc_pnet_is_ndev_pnetid(struct net *net, u8 *pnetid)
+{
+	struct smc_net *sn = net_generic(net, smc_net_id);
+	struct smc_pnetids_ndev_entry *pe;
+	bool rc = false;
+
+	read_lock(&sn->pnetids_ndev.lock);
+	list_for_each_entry(pe, &sn->pnetids_ndev.list, list) {
+		if (smc_pnet_match(pnetid, pe->pnetid)) {
+			rc = true;
+			goto unlock;
+		}
+	}
+
+unlock:
+	read_unlock(&sn->pnetids_ndev.lock);
+	return rc;
+}
+
+static int smc_pnet_add_pnetid(struct net *net, u8 *pnetid)
+{
+	struct smc_net *sn = net_generic(net, smc_net_id);
+	struct smc_pnetids_ndev_entry *pe, *pi;
+
+	pe = kzalloc(sizeof(*pe), GFP_KERNEL);
+	if (!pe)
+		return -ENOMEM;
+
+	write_lock(&sn->pnetids_ndev.lock);
+	list_for_each_entry(pi, &sn->pnetids_ndev.list, list) {
+		if (smc_pnet_match(pnetid, pe->pnetid)) {
+			refcount_inc(&pi->refcnt);
+			kfree(pe);
+			goto unlock;
+		}
+	}
+	refcount_set(&pe->refcnt, 1);
+	memcpy(pe->pnetid, pnetid, SMC_MAX_PNETID_LEN);
+	list_add_tail(&pe->list, &sn->pnetids_ndev.list);
+
+unlock:
+	write_unlock(&sn->pnetids_ndev.lock);
+	return 0;
+}
+
+static void smc_pnet_remove_pnetid(struct net *net, u8 *pnetid)
+{
+	struct smc_net *sn = net_generic(net, smc_net_id);
+	struct smc_pnetids_ndev_entry *pe, *pe2;
+
+	write_lock(&sn->pnetids_ndev.lock);
+	list_for_each_entry_safe(pe, pe2, &sn->pnetids_ndev.list, list) {
+		if (smc_pnet_match(pnetid, pe->pnetid)) {
+			if (refcount_dec_and_test(&pe->refcnt)) {
+				list_del(&pe->list);
+				kfree(pe);
+			}
+			break;
+		}
+	}
+	write_unlock(&sn->pnetids_ndev.lock);
+}
+
+static void smc_pnet_add_base_pnetid(struct net *net, struct net_device *dev,
+				     u8 *ndev_pnetid)
+{
+	struct net_device *base_dev;
+
+	base_dev = __pnet_find_base_ndev(dev);
+	if (base_dev->flags & IFF_UP &&
+	    !smc_pnetid_by_dev_port(base_dev->dev.parent, base_dev->dev_port,
+				    ndev_pnetid)) {
+		/* add to PNETIDs list */
+		smc_pnet_add_pnetid(net, ndev_pnetid);
+	}
+}
+
+/* create initial list of netdevice pnetids */
+static void smc_pnet_create_pnetids_list(struct net *net)
+{
+	u8 ndev_pnetid[SMC_MAX_PNETID_LEN];
+	struct net_device *dev;
+
+	rtnl_lock();
+	for_each_netdev(net, dev)
+		smc_pnet_add_base_pnetid(net, dev, ndev_pnetid);
+	rtnl_unlock();
+}
+
+/* clean up list of netdevice pnetids */
+static void smc_pnet_destroy_pnetids_list(struct net *net)
+{
+	struct smc_net *sn = net_generic(net, smc_net_id);
+	struct smc_pnetids_ndev_entry *pe, *temp_pe;
+
+	write_lock(&sn->pnetids_ndev.lock);
+	list_for_each_entry_safe(pe, temp_pe, &sn->pnetids_ndev.list, list) {
+		list_del(&pe->list);
+		kfree(pe);
+	}
+	write_unlock(&sn->pnetids_ndev.lock);
+}
+
 static int smc_pnet_netdev_event(struct notifier_block *this,
 				 unsigned long event, void *ptr)
 {
 	struct net_device *event_dev = netdev_notifier_info_to_dev(ptr);
+	struct net *net = dev_net(event_dev);
+	u8 ndev_pnetid[SMC_MAX_PNETID_LEN];
 
 	switch (event) {
 	case NETDEV_REBOOT:
@@ -721,6 +831,17 @@ static int smc_pnet_netdev_event(struct notifier_block *this,
 	case NETDEV_REGISTER:
 		smc_pnet_add_by_ndev(event_dev);
 		return NOTIFY_OK;
+	case NETDEV_UP:
+		smc_pnet_add_base_pnetid(net, event_dev, ndev_pnetid);
+		return NOTIFY_OK;
+	case NETDEV_DOWN:
+		event_dev = __pnet_find_base_ndev(event_dev);
+		if (!smc_pnetid_by_dev_port(event_dev->dev.parent,
+					    event_dev->dev_port, ndev_pnetid)) {
+			/* remove from PNETIDs list */
+			smc_pnet_remove_pnetid(net, ndev_pnetid);
+		}
+		return NOTIFY_OK;
 	default:
 		return NOTIFY_DONE;
 	}
@@ -735,9 +856,14 @@ int smc_pnet_net_init(struct net *net)
 {
 	struct smc_net *sn = net_generic(net, smc_net_id);
 	struct smc_pnettable *pnettable = &sn->pnettable;
+	struct smc_pnetids_ndev *pnetids_ndev = &sn->pnetids_ndev;
 
 	INIT_LIST_HEAD(&pnettable->pnetlist);
 	rwlock_init(&pnettable->lock);
+	INIT_LIST_HEAD(&pnetids_ndev->list);
+	rwlock_init(&pnetids_ndev->lock);
+
+	smc_pnet_create_pnetids_list(net);
 
 	return 0;
 }
@@ -752,6 +878,7 @@ int __init smc_pnet_init(void)
 	rc = register_netdevice_notifier(&smc_netdev_notifier);
 	if (rc)
 		genl_unregister_family(&smc_pnet_nl_family);
+
 	return rc;
 }
 
@@ -760,6 +887,7 @@ void smc_pnet_net_exit(struct net *net)
 {
 	/* flush pnet table */
 	smc_pnet_remove_by_pnetid(net, NULL);
+	smc_pnet_destroy_pnetids_list(net);
 }
 
 void smc_pnet_exit(void)
@@ -768,16 +896,11 @@ void smc_pnet_exit(void)
 	genl_unregister_family(&smc_pnet_nl_family);
 }
 
-/* Determine one base device for stacked net devices.
- * If the lower device level contains more than one devices
- * (for instance with bonding slaves), just the first device
- * is used to reach a base device.
- */
-static struct net_device *pnet_find_base_ndev(struct net_device *ndev)
+static struct net_device *__pnet_find_base_ndev(struct net_device *ndev)
 {
 	int i, nest_lvl;
 
-	rtnl_lock();
+	ASSERT_RTNL();
 	nest_lvl = ndev->lower_level;
 	for (i = 0; i < nest_lvl; i++) {
 		struct list_head *lower = &ndev->adj_list.lower;
@@ -787,6 +910,18 @@ static struct net_device *pnet_find_base_ndev(struct net_device *ndev)
 		lower = lower->next;
 		ndev = netdev_lower_get_next(ndev, &lower);
 	}
+	return ndev;
+}
+
+/* Determine one base device for stacked net devices.
+ * If the lower device level contains more than one devices
+ * (for instance with bonding slaves), just the first device
+ * is used to reach a base device.
+ */
+static struct net_device *pnet_find_base_ndev(struct net_device *ndev)
+{
+	rtnl_lock();
+	ndev = __pnet_find_base_ndev(ndev);
 	rtnl_unlock();
 	return ndev;
 }
@@ -929,10 +1064,10 @@ static void smc_pnet_find_ism_by_pnetid(struct net_device *ndev,
 	list_for_each_entry(ismdev, &smcd_dev_list.list, list) {
 		if (smc_pnet_match(ismdev->pnetid, ndev_pnetid) &&
 		    !ismdev->going_away &&
-		    (!ini->ism_peer_gid ||
-		     !smc_ism_cantalk(ini->ism_peer_gid, ini->vlan_id,
+		    (!ini->ism_peer_gid[0] ||
+		     !smc_ism_cantalk(ini->ism_peer_gid[0], ini->vlan_id,
 				      ismdev))) {
-			ini->ism_dev = ismdev;
+			ini->ism_dev[0] = ismdev;
 			break;
 		}
 	}
@@ -966,7 +1101,7 @@ void smc_pnet_find_ism_resource(struct sock *sk, struct smc_init_info *ini)
 {
 	struct dst_entry *dst = sk_dst_get(sk);
 
-	ini->ism_dev = NULL;
+	ini->ism_dev[0] = NULL;
 	if (!dst)
 		goto out;
 	if (!dst->dev)
diff --git a/net/smc/smc_pnet.h b/net/smc/smc_pnet.h
index 811a65986691..14039272f7e4 100644
--- a/net/smc/smc_pnet.h
+++ b/net/smc/smc_pnet.h
@@ -12,6 +12,8 @@
 #ifndef _SMC_PNET_H
 #define _SMC_PNET_H
 
+#include <net/smc.h>
+
 #if IS_ENABLED(CONFIG_HAVE_PNETID)
 #include <asm/pnet.h>
 #endif
@@ -31,6 +33,17 @@ struct smc_pnettable {
 	struct list_head pnetlist;
 };
 
+struct smc_pnetids_ndev {	/* list of pnetids for net devices in UP state*/
+	struct list_head	list;
+	rwlock_t		lock;
+};
+
+struct smc_pnetids_ndev_entry {
+	struct list_head	list;
+	u8			pnetid[SMC_MAX_PNETID_LEN];
+	refcount_t		refcnt;
+};
+
 static inline int smc_pnetid_by_dev_port(struct device *dev,
 					 unsigned short port, u8 *pnetid)
 {
@@ -52,4 +65,6 @@ int smc_pnetid_by_table_smcd(struct smcd_dev *smcd);
 void smc_pnet_find_alt_roce(struct smc_link_group *lgr,
 			    struct smc_init_info *ini,
 			    struct smc_ib_device *known_dev);
+bool smc_pnet_is_ndev_pnetid(struct net *net, u8 *pnetid);
+bool smc_pnet_is_pnetid_set(u8 *pnetid);
 #endif
diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c
index c27123e6ba80..4a67685c83eb 100644
--- a/net/sunrpc/rpcb_clnt.c
+++ b/net/sunrpc/rpcb_clnt.c
@@ -982,8 +982,8 @@ static int rpcb_dec_getaddr(struct rpc_rqst *req, struct xdr_stream *xdr,
 	p = xdr_inline_decode(xdr, len);
 	if (unlikely(p == NULL))
 		goto out_fail;
-	dprintk("RPC: %5u RPCB_%s reply: %s\n", req->rq_task->tk_pid,
-			req->rq_task->tk_msg.rpc_proc->p_name, (char *)p);
+	dprintk("RPC: %5u RPCB_%s reply: %*pE\n", req->rq_task->tk_pid,
+			req->rq_task->tk_msg.rpc_proc->p_name, len, (char *)p);
 
 	if (rpc_uaddr2sockaddr(req->rq_xprt->xprt_net, (char *)p, len,
 				sap, sizeof(address)) == 0)
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index 3f86d039875c..ad6e2e4994ce 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -933,6 +933,8 @@ static void rpcrdma_req_reset(struct rpcrdma_req *req)
 
 	rpcrdma_regbuf_dma_unmap(req->rl_sendbuf);
 	rpcrdma_regbuf_dma_unmap(req->rl_recvbuf);
+
+	frwr_reset(req);
 }
 
 /* ASSUMPTION: the rb_allreqs list is stable for the duration,
diff --git a/net/tipc/group.c b/net/tipc/group.c
index 588c2d2b0c69..b1fcd2ad5ecf 100644
--- a/net/tipc/group.c
+++ b/net/tipc/group.c
@@ -273,8 +273,8 @@ static struct tipc_member *tipc_group_find_node(struct tipc_group *grp,
 	return NULL;
 }
 
-static void tipc_group_add_to_tree(struct tipc_group *grp,
-				   struct tipc_member *m)
+static int tipc_group_add_to_tree(struct tipc_group *grp,
+				  struct tipc_member *m)
 {
 	u64 nkey, key = (u64)m->node << 32 | m->port;
 	struct rb_node **n, *parent = NULL;
@@ -291,10 +291,11 @@ static void tipc_group_add_to_tree(struct tipc_group *grp,
 		else if (key > nkey)
 			n = &(*n)->rb_right;
 		else
-			return;
+			return -EEXIST;
 	}
 	rb_link_node(&m->tree_node, parent, n);
 	rb_insert_color(&m->tree_node, &grp->members);
+	return 0;
 }
 
 static struct tipc_member *tipc_group_create_member(struct tipc_group *grp,
@@ -302,6 +303,7 @@ static struct tipc_member *tipc_group_create_member(struct tipc_group *grp,
 						    u32 instance, int state)
 {
 	struct tipc_member *m;
+	int ret;
 
 	m = kzalloc(sizeof(*m), GFP_ATOMIC);
 	if (!m)
@@ -314,8 +316,12 @@ static struct tipc_member *tipc_group_create_member(struct tipc_group *grp,
 	m->port = port;
 	m->instance = instance;
 	m->bc_acked = grp->bc_snd_nxt - 1;
+	ret = tipc_group_add_to_tree(grp, m);
+	if (ret < 0) {
+		kfree(m);
+		return NULL;
+	}
 	grp->member_cnt++;
-	tipc_group_add_to_tree(grp, m);
 	tipc_nlist_add(&grp->dests, m->node);
 	m->state = state;
 	return m;
diff --git a/net/tipc/link.c b/net/tipc/link.c
index 97dc4b5fb20b..06b880da2a8e 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -527,7 +527,8 @@ bool tipc_link_create(struct net *net, char *if_name, int bearer_id,
  * tipc_link_bc_create - create new link to be used for broadcast
  * @net: pointer to associated network namespace
  * @mtu: mtu to be used initially if no peers
- * @window: send window to be used
+ * @min_win: minimal send window to be used by link
+ * @max_win: maximal send window to be used by link
  * @inputq: queue to put messages ready for delivery
  * @namedq: queue to put binding table update messages ready for delivery
  * @link: return value, pointer to put the created link
diff --git a/net/tipc/msg.c b/net/tipc/msg.c
index 2d9a383b8192..11a429f4c6cd 100644
--- a/net/tipc/msg.c
+++ b/net/tipc/msg.c
@@ -150,7 +150,8 @@ int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf)
 	if (fragid == FIRST_FRAGMENT) {
 		if (unlikely(head))
 			goto err;
-		if (unlikely(skb_unclone(frag, GFP_ATOMIC)))
+		frag = skb_unshare(frag, GFP_ATOMIC);
+		if (unlikely(!frag))
 			goto err;
 		head = *headbuf = frag;
 		*buf = NULL;
diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c
index 90e3c70a91ad..1c7aa51cc2a3 100644
--- a/net/tipc/netlink_compat.c
+++ b/net/tipc/netlink_compat.c
@@ -1337,7 +1337,7 @@ send:
 	return err;
 }
 
-static const struct genl_ops tipc_genl_compat_ops[] = {
+static const struct genl_small_ops tipc_genl_compat_ops[] = {
 	{
 		.cmd		= TIPC_GENL_CMD,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
@@ -1352,8 +1352,8 @@ static struct genl_family tipc_genl_compat_family __ro_after_init = {
 	.maxattr	= 0,
 	.netnsok	= true,
 	.module		= THIS_MODULE,
-	.ops		= tipc_genl_compat_ops,
-	.n_ops		= ARRAY_SIZE(tipc_genl_compat_ops),
+	.small_ops	= tipc_genl_compat_ops,
+	.n_small_ops	= ARRAY_SIZE(tipc_genl_compat_ops),
 };
 
 int __init tipc_netlink_compat_start(void)
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 0f894aca98ed..e795a8a2955b 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -2770,10 +2770,7 @@ static int tipc_shutdown(struct socket *sock, int how)
 
 	trace_tipc_sk_shutdown(sk, NULL, TIPC_DUMP_ALL, " ");
 	__tipc_shutdown(sock, TIPC_CONN_SHUTDOWN);
-	if (tipc_sk_type_connectionless(sk))
-		sk->sk_shutdown = SHUTDOWN_MASK;
-	else
-		sk->sk_shutdown = SEND_SHUTDOWN;
+	sk->sk_shutdown = SHUTDOWN_MASK;
 
 	if (sk->sk_state == TIPC_DISCONNECTING) {
 		/* Discard any unreceived messages */
diff --git a/net/wimax/stack.c b/net/wimax/stack.c
index 4b9b1c5e8f3a..b6dd9d956ed8 100644
--- a/net/wimax/stack.c
+++ b/net/wimax/stack.c
@@ -401,7 +401,7 @@ static const struct nla_policy wimax_gnl_policy[WIMAX_GNL_ATTR_MAX + 1] = {
 	},
 };
 
-static const struct genl_ops wimax_gnl_ops[] = {
+static const struct genl_small_ops wimax_gnl_ops[] = {
 	{
 		.cmd = WIMAX_GNL_OP_MSG_FROM_USER,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
@@ -560,8 +560,8 @@ struct genl_family wimax_gnl_family __ro_after_init = {
 	.maxattr = WIMAX_GNL_ATTR_MAX,
 	.policy = wimax_gnl_policy,
 	.module = THIS_MODULE,
-	.ops = wimax_gnl_ops,
-	.n_ops = ARRAY_SIZE(wimax_gnl_ops),
+	.small_ops = wimax_gnl_ops,
+	.n_small_ops = ARRAY_SIZE(wimax_gnl_ops),
 	.mcgrps = wimax_gnl_mcgrps,
 	.n_mcgrps = ARRAY_SIZE(wimax_gnl_mcgrps),
 };
diff --git a/net/wireless/Kconfig b/net/wireless/Kconfig
index faf74850a1b5..27026f587fa6 100644
--- a/net/wireless/Kconfig
+++ b/net/wireless/Kconfig
@@ -217,6 +217,7 @@ config LIB80211_CRYPT_WEP
 
 config LIB80211_CRYPT_CCMP
 	tristate
+	select CRYPTO
 	select CRYPTO_AES
 	select CRYPTO_CCM
 
diff --git a/net/wireless/core.c b/net/wireless/core.c
index 354b0ccbdc24..9f23923e8d29 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -236,7 +236,9 @@ void cfg80211_stop_p2p_device(struct cfg80211_registered_device *rdev,
 	rdev->opencount--;
 
 	if (rdev->scan_req && rdev->scan_req->wdev == wdev) {
-		if (WARN_ON(!rdev->scan_req->notified))
+		if (WARN_ON(!rdev->scan_req->notified &&
+			    (!rdev->int_scan_req ||
+			     !rdev->int_scan_req->notified)))
 			rdev->scan_req->info.aborted = true;
 		___cfg80211_scan_done(rdev, false);
 	}
@@ -1336,7 +1338,9 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb,
 	case NETDEV_DOWN:
 		cfg80211_update_iface_num(rdev, wdev->iftype, -1);
 		if (rdev->scan_req && rdev->scan_req->wdev == wdev) {
-			if (WARN_ON(!rdev->scan_req->notified))
+			if (WARN_ON(!rdev->scan_req->notified &&
+				    (!rdev->int_scan_req ||
+				     !rdev->int_scan_req->notified)))
 				rdev->scan_req->info.aborted = true;
 			___cfg80211_scan_done(rdev, false);
 		}
diff --git a/net/wireless/core.h b/net/wireless/core.h
index 2ebc2a66680d..e1ec9ac8e608 100644
--- a/net/wireless/core.h
+++ b/net/wireless/core.h
@@ -3,7 +3,7 @@
  * Wireless configuration interface internals.
  *
  * Copyright 2006-2010	Johannes Berg <johannes@sipsolutions.net>
- * Copyright (C) 2018-2019 Intel Corporation
+ * Copyright (C) 2018-2020 Intel Corporation
  */
 #ifndef __NET_WIRELESS_CORE_H
 #define __NET_WIRELESS_CORE_H
@@ -72,6 +72,7 @@ struct cfg80211_registered_device {
 	u32 bss_generation;
 	u32 bss_entries;
 	struct cfg80211_scan_request *scan_req; /* protected by RTNL */
+	struct cfg80211_scan_request *int_scan_req;
 	struct sk_buff *scan_msg;
 	struct list_head sched_scan_req_list;
 	time64_t suspend_at;
@@ -457,6 +458,8 @@ void cfg80211_process_wdev_events(struct wireless_dev *wdev);
 bool cfg80211_does_bw_fit_range(const struct ieee80211_freq_range *freq_range,
 				u32 center_freq_khz, u32 bw_khz);
 
+int cfg80211_scan(struct cfg80211_registered_device *rdev);
+
 extern struct work_struct cfg80211_disconnect_work;
 
 /**
diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c
index db7333e20dd7..0ac820780437 100644
--- a/net/wireless/mlme.c
+++ b/net/wireless/mlme.c
@@ -30,6 +30,15 @@ void cfg80211_rx_assoc_resp(struct net_device *dev, struct cfg80211_bss *bss,
 	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	struct ieee80211_mgmt *mgmt = (struct ieee80211_mgmt *)buf;
 	struct cfg80211_connect_resp_params cr;
+	const u8 *resp_ie = mgmt->u.assoc_resp.variable;
+	size_t resp_ie_len = len - offsetof(struct ieee80211_mgmt,
+					    u.assoc_resp.variable);
+
+	if (bss->channel->band == NL80211_BAND_S1GHZ) {
+		resp_ie = (u8 *)&mgmt->u.s1g_assoc_resp.variable;
+		resp_ie_len = len - offsetof(struct ieee80211_mgmt,
+					     u.s1g_assoc_resp.variable);
+	}
 
 	memset(&cr, 0, sizeof(cr));
 	cr.status = (int)le16_to_cpu(mgmt->u.assoc_resp.status_code);
@@ -37,9 +46,8 @@ void cfg80211_rx_assoc_resp(struct net_device *dev, struct cfg80211_bss *bss,
 	cr.bss = bss;
 	cr.req_ie = req_ies;
 	cr.req_ie_len = req_ies_len;
-	cr.resp_ie = mgmt->u.assoc_resp.variable;
-	cr.resp_ie_len =
-		len - offsetof(struct ieee80211_mgmt, u.assoc_resp.variable);
+	cr.resp_ie = resp_ie;
+	cr.resp_ie_len = resp_ie_len;
 	cr.timeout_reason = NL80211_TIMEOUT_UNSPECIFIED;
 
 	trace_cfg80211_send_rx_assoc(dev, bss);
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 1a212db7a300..59b4677cc587 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -329,6 +329,13 @@ he_obss_pd_policy[NL80211_HE_OBSS_PD_ATTR_MAX + 1] = {
 		NLA_POLICY_RANGE(NLA_U8, 1, 20),
 	[NL80211_HE_OBSS_PD_ATTR_MAX_OFFSET] =
 		NLA_POLICY_RANGE(NLA_U8, 1, 20),
+	[NL80211_HE_OBSS_PD_ATTR_NON_SRG_MAX_OFFSET] =
+		NLA_POLICY_RANGE(NLA_U8, 1, 20),
+	[NL80211_HE_OBSS_PD_ATTR_BSS_COLOR_BITMAP] =
+		NLA_POLICY_EXACT_LEN(8),
+	[NL80211_HE_OBSS_PD_ATTR_PARTIAL_BSSID_BITMAP] =
+		NLA_POLICY_EXACT_LEN(8),
+	[NL80211_HE_OBSS_PD_ATTR_SR_CTRL] = { .type = NLA_U8 },
 };
 
 static const struct nla_policy
@@ -704,6 +711,10 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = {
 		NLA_POLICY_NESTED(nl80211_fils_discovery_policy),
 	[NL80211_ATTR_UNSOL_BCAST_PROBE_RESP] =
 		NLA_POLICY_NESTED(nl80211_unsol_bcast_probe_resp_policy),
+	[NL80211_ATTR_S1G_CAPABILITY] =
+		NLA_POLICY_EXACT_LEN(IEEE80211_S1G_CAPABILITY_LEN),
+	[NL80211_ATTR_S1G_CAPABILITY_MASK] =
+		NLA_POLICY_EXACT_LEN(IEEE80211_S1G_CAPABILITY_LEN),
 };
 
 /* policy for the key attributes */
@@ -973,6 +984,8 @@ static int nl80211_msg_put_channel(struct sk_buff *msg, struct wiphy *wiphy,
 	if (!large && chan->flags &
 	    (IEEE80211_CHAN_NO_10MHZ | IEEE80211_CHAN_NO_20MHZ))
 		return 0;
+	if (!large && chan->freq_offset)
+		return 0;
 
 	if (nla_put_u32(msg, NL80211_FREQUENCY_ATTR_FREQ,
 			chan->center_freq))
@@ -1665,7 +1678,8 @@ nl80211_send_iftype_data(struct sk_buff *msg,
 }
 
 static int nl80211_send_band_rateinfo(struct sk_buff *msg,
-				      struct ieee80211_supported_band *sband)
+				      struct ieee80211_supported_band *sband,
+				      bool large)
 {
 	struct nlattr *nl_rates, *nl_rate;
 	struct ieee80211_rate *rate;
@@ -1693,7 +1707,7 @@ static int nl80211_send_band_rateinfo(struct sk_buff *msg,
 			 sband->vht_cap.cap)))
 		return -ENOBUFS;
 
-	if (sband->n_iftype_data) {
+	if (large && sband->n_iftype_data) {
 		struct nlattr *nl_iftype_data =
 			nla_nest_start_noflag(msg,
 					      NL80211_BAND_ATTR_IFTYPE_DATA);
@@ -1721,7 +1735,7 @@ static int nl80211_send_band_rateinfo(struct sk_buff *msg,
 	}
 
 	/* add EDMG info */
-	if (sband->edmg_cap.channels &&
+	if (large && sband->edmg_cap.channels &&
 	    (nla_put_u8(msg, NL80211_BAND_ATTR_EDMG_CHANNELS,
 		       sband->edmg_cap.channels) ||
 	    nla_put_u8(msg, NL80211_BAND_ATTR_EDMG_BW_CONFIG,
@@ -2139,13 +2153,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev,
 		    nla_put_u16(msg, NL80211_ATTR_MAX_SCHED_SCAN_IE_LEN,
 				rdev->wiphy.max_sched_scan_ie_len) ||
 		    nla_put_u8(msg, NL80211_ATTR_MAX_MATCH_SETS,
-			       rdev->wiphy.max_match_sets) ||
-		    nla_put_u32(msg, NL80211_ATTR_MAX_NUM_SCHED_SCAN_PLANS,
-				rdev->wiphy.max_sched_scan_plans) ||
-		    nla_put_u32(msg, NL80211_ATTR_MAX_SCAN_PLAN_INTERVAL,
-				rdev->wiphy.max_sched_scan_plan_interval) ||
-		    nla_put_u32(msg, NL80211_ATTR_MAX_SCAN_PLAN_ITERATIONS,
-				rdev->wiphy.max_sched_scan_plan_iterations))
+			       rdev->wiphy.max_match_sets))
 			goto nla_put_failure;
 
 		if ((rdev->wiphy.flags & WIPHY_FLAG_IBSS_RSN) &&
@@ -2235,6 +2243,10 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev,
 		     band < NUM_NL80211_BANDS; band++) {
 			struct ieee80211_supported_band *sband;
 
+			/* omit higher bands for ancient software */
+			if (band > NL80211_BAND_5GHZ && !state->split)
+				break;
+
 			sband = rdev->wiphy.bands[band];
 
 			if (!sband)
@@ -2246,7 +2258,8 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev,
 
 			switch (state->chan_start) {
 			case 0:
-				if (nl80211_send_band_rateinfo(msg, sband))
+				if (nl80211_send_band_rateinfo(msg, sband,
+							       state->split))
 					goto nla_put_failure;
 				state->chan_start++;
 				if (state->split)
@@ -2348,8 +2361,6 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev,
 		    nla_put_flag(msg, NL80211_ATTR_OFFCHANNEL_TX_OK))
 			goto nla_put_failure;
 
-		if (nl80211_send_mgmt_stypes(msg, mgmt_stypes))
-			goto nla_put_failure;
 		state->split_start++;
 		if (state->split)
 			break;
@@ -2417,9 +2428,23 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev,
 		 * case we'll continue with more data in the next round,
 		 * but break unconditionally so unsplit data stops here.
 		 */
-		state->split_start++;
+		if (state->split)
+			state->split_start++;
+		else
+			state->split_start = 0;
 		break;
 	case 9:
+		if (nl80211_send_mgmt_stypes(msg, mgmt_stypes))
+			goto nla_put_failure;
+
+		if (nla_put_u32(msg, NL80211_ATTR_MAX_NUM_SCHED_SCAN_PLANS,
+				rdev->wiphy.max_sched_scan_plans) ||
+		    nla_put_u32(msg, NL80211_ATTR_MAX_SCAN_PLAN_INTERVAL,
+				rdev->wiphy.max_sched_scan_plan_interval) ||
+		    nla_put_u32(msg, NL80211_ATTR_MAX_SCAN_PLAN_ITERATIONS,
+				rdev->wiphy.max_sched_scan_plan_iterations))
+			goto nla_put_failure;
+
 		if (rdev->wiphy.extended_capabilities &&
 		    (nla_put(msg, NL80211_ATTR_EXT_CAPA,
 			     rdev->wiphy.extended_capabilities_len,
@@ -4853,18 +4878,34 @@ static int nl80211_parse_he_obss_pd(struct nlattr *attrs,
 	if (err)
 		return err;
 
-	if (!tb[NL80211_HE_OBSS_PD_ATTR_MIN_OFFSET] ||
-	    !tb[NL80211_HE_OBSS_PD_ATTR_MAX_OFFSET])
+	if (!tb[NL80211_HE_OBSS_PD_ATTR_SR_CTRL])
 		return -EINVAL;
 
-	he_obss_pd->min_offset =
-		nla_get_u32(tb[NL80211_HE_OBSS_PD_ATTR_MIN_OFFSET]);
-	he_obss_pd->max_offset =
-		nla_get_u32(tb[NL80211_HE_OBSS_PD_ATTR_MAX_OFFSET]);
+	he_obss_pd->sr_ctrl = nla_get_u8(tb[NL80211_HE_OBSS_PD_ATTR_SR_CTRL]);
+
+	if (tb[NL80211_HE_OBSS_PD_ATTR_MIN_OFFSET])
+		he_obss_pd->min_offset =
+			nla_get_u8(tb[NL80211_HE_OBSS_PD_ATTR_MIN_OFFSET]);
+	if (tb[NL80211_HE_OBSS_PD_ATTR_MAX_OFFSET])
+		he_obss_pd->max_offset =
+			nla_get_u8(tb[NL80211_HE_OBSS_PD_ATTR_MAX_OFFSET]);
+	if (tb[NL80211_HE_OBSS_PD_ATTR_NON_SRG_MAX_OFFSET])
+		he_obss_pd->non_srg_max_offset =
+			nla_get_u8(tb[NL80211_HE_OBSS_PD_ATTR_NON_SRG_MAX_OFFSET]);
 
-	if (he_obss_pd->min_offset >= he_obss_pd->max_offset)
+	if (he_obss_pd->min_offset > he_obss_pd->max_offset)
 		return -EINVAL;
 
+	if (tb[NL80211_HE_OBSS_PD_ATTR_BSS_COLOR_BITMAP])
+		memcpy(he_obss_pd->bss_color_bitmap,
+		       nla_data(tb[NL80211_HE_OBSS_PD_ATTR_BSS_COLOR_BITMAP]),
+		       sizeof(he_obss_pd->bss_color_bitmap));
+
+	if (tb[NL80211_HE_OBSS_PD_ATTR_PARTIAL_BSSID_BITMAP])
+		memcpy(he_obss_pd->partial_bssid_bitmap,
+		       nla_data(tb[NL80211_HE_OBSS_PD_ATTR_PARTIAL_BSSID_BITMAP]),
+		       sizeof(he_obss_pd->partial_bssid_bitmap));
+
 	he_obss_pd->enable = true;
 
 	return 0;
@@ -8236,7 +8277,7 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info)
 	request->scan_start = jiffies;
 
 	rdev->scan_req = request;
-	err = rdev_scan(rdev, request);
+	err = cfg80211_scan(rdev);
 
 	if (err)
 		goto out_free;
@@ -9315,6 +9356,11 @@ static int nl80211_send_survey(struct sk_buff *msg, u32 portid, u32 seq,
 			survey->channel->center_freq))
 		goto nla_put_failure;
 
+	if (survey->channel && survey->channel->freq_offset &&
+	    nla_put_u32(msg, NL80211_SURVEY_INFO_FREQUENCY_OFFSET,
+			survey->channel->freq_offset))
+		goto nla_put_failure;
+
 	if ((survey->filled & SURVEY_INFO_NOISE_DBM) &&
 	    nla_put_u8(msg, NL80211_SURVEY_INFO_NOISE, survey->noise))
 		goto nla_put_failure;
@@ -9792,6 +9838,22 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info)
 			nla_data(info->attrs[NL80211_ATTR_FILS_NONCES]);
 	}
 
+	if (info->attrs[NL80211_ATTR_S1G_CAPABILITY_MASK]) {
+		if (!info->attrs[NL80211_ATTR_S1G_CAPABILITY])
+			return -EINVAL;
+		memcpy(&req.s1g_capa_mask,
+		       nla_data(info->attrs[NL80211_ATTR_S1G_CAPABILITY_MASK]),
+		       sizeof(req.s1g_capa_mask));
+	}
+
+	if (info->attrs[NL80211_ATTR_S1G_CAPABILITY]) {
+		if (!info->attrs[NL80211_ATTR_S1G_CAPABILITY_MASK])
+			return -EINVAL;
+		memcpy(&req.s1g_capa,
+		       nla_data(info->attrs[NL80211_ATTR_S1G_CAPABILITY]),
+		       sizeof(req.s1g_capa));
+	}
+
 	err = nl80211_crypto_settings(rdev, info, &req.crypto, 1);
 	if (!err) {
 		wdev_lock(dev->ieee80211_ptr);
@@ -14603,6 +14665,9 @@ static const struct genl_ops nl80211_ops[] = {
 		.internal_flags = NL80211_FLAG_NEED_WIPHY |
 				  NL80211_FLAG_NEED_RTNL,
 	},
+};
+
+static const struct genl_small_ops nl80211_small_ops[] = {
 	{
 		.cmd = NL80211_CMD_SET_WIPHY,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
@@ -15464,6 +15529,8 @@ static struct genl_family nl80211_fam __ro_after_init = {
 	.module = THIS_MODULE,
 	.ops = nl80211_ops,
 	.n_ops = ARRAY_SIZE(nl80211_ops),
+	.small_ops = nl80211_small_ops,
+	.n_small_ops = ARRAY_SIZE(nl80211_small_ops),
 	.mcgrps = nl80211_mcgrps,
 	.n_mcgrps = ARRAY_SIZE(nl80211_mcgrps),
 	.parallel_ops = true,
@@ -15518,6 +15585,7 @@ static int nl80211_add_scan_req(struct sk_buff *msg,
 	struct cfg80211_scan_request *req = rdev->scan_req;
 	struct nlattr *nest;
 	int i;
+	struct cfg80211_scan_info *info;
 
 	if (WARN_ON(!req))
 		return 0;
@@ -15561,11 +15629,13 @@ static int nl80211_add_scan_req(struct sk_buff *msg,
 	    nla_put_u32(msg, NL80211_ATTR_SCAN_FLAGS, req->flags))
 		goto nla_put_failure;
 
-	if (req->info.scan_start_tsf &&
+	info = rdev->int_scan_req ? &rdev->int_scan_req->info :
+		&rdev->scan_req->info;
+	if (info->scan_start_tsf &&
 	    (nla_put_u64_64bit(msg, NL80211_ATTR_SCAN_START_TIME_TSF,
-			       req->info.scan_start_tsf, NL80211_BSS_PAD) ||
+			       info->scan_start_tsf, NL80211_BSS_PAD) ||
 	     nla_put(msg, NL80211_ATTR_SCAN_START_TIME_TSF_BSSID, ETH_ALEN,
-		     req->info.tsf_bssid)))
+		     info->tsf_bssid)))
 		goto nla_put_failure;
 
 	return 0;
diff --git a/net/wireless/radiotap.c b/net/wireless/radiotap.c
index d5e28239e030..36f1b59a78bf 100644
--- a/net/wireless/radiotap.c
+++ b/net/wireless/radiotap.c
@@ -59,6 +59,7 @@ static const struct ieee80211_radiotap_namespace radiotap_ns = {
  * @iterator: radiotap_iterator to initialize
  * @radiotap_header: radiotap header to parse
  * @max_length: total length we can parse into (eg, whole packet length)
+ * @vns: vendor namespaces to parse
  *
  * Returns: 0 or a negative error code if there is a problem.
  *
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index 6043a9d33d61..3dab859641e1 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -1616,8 +1616,8 @@ static const struct ieee80211_reg_rule *
 __freq_reg_info(struct wiphy *wiphy, u32 center_freq, u32 min_bw)
 {
 	const struct ieee80211_regdomain *regd = reg_get_regdomain(wiphy);
-	const struct ieee80211_reg_rule *reg_rule = NULL;
 	const u32 bws[] = {0, 1, 2, 4, 5, 8, 10, 16, 20};
+	const struct ieee80211_reg_rule *reg_rule;
 	int i = ARRAY_SIZE(bws) - 1;
 	u32 bw;
 
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index 84fc8ab16dd2..8d0e49c46db3 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -5,7 +5,7 @@
  * Copyright 2008 Johannes Berg <johannes@sipsolutions.net>
  * Copyright 2013-2014  Intel Mobile Communications GmbH
  * Copyright 2016	Intel Deutschland GmbH
- * Copyright (C) 2018-2019 Intel Corporation
+ * Copyright (C) 2018-2020 Intel Corporation
  */
 #include <linux/kernel.h>
 #include <linux/slab.h>
@@ -14,6 +14,8 @@
 #include <linux/wireless.h>
 #include <linux/nl80211.h>
 #include <linux/etherdevice.h>
+#include <linux/crc32.h>
+#include <linux/bitfield.h>
 #include <net/arp.h>
 #include <net/cfg80211.h>
 #include <net/cfg80211-wext.h>
@@ -74,6 +76,43 @@ MODULE_PARM_DESC(bss_entries_limit,
 
 #define IEEE80211_SCAN_RESULT_EXPIRE	(30 * HZ)
 
+/**
+ * struct cfg80211_colocated_ap - colocated AP information
+ *
+ * @list: linked list to all colocated aPS
+ * @bssid: BSSID of the reported AP
+ * @ssid: SSID of the reported AP
+ * @ssid_len: length of the ssid
+ * @center_freq: frequency the reported AP is on
+ * @unsolicited_probe: the reported AP is part of an ESS, where all the APs
+ *	that operate in the same channel as the reported AP and that might be
+ *	detected by a STA receiving this frame, are transmitting unsolicited
+ *	Probe Response frames every 20 TUs
+ * @oct_recommended: OCT is recommended to exchange MMPDUs with the reported AP
+ * @same_ssid: the reported AP has the same SSID as the reporting AP
+ * @multi_bss: the reported AP is part of a multiple BSSID set
+ * @transmitted_bssid: the reported AP is the transmitting BSSID
+ * @colocated_ess: all the APs that share the same ESS as the reported AP are
+ *	colocated and can be discovered via legacy bands.
+ * @short_ssid_valid: short_ssid is valid and can be used
+ * @short_ssid: the short SSID for this SSID
+ */
+struct cfg80211_colocated_ap {
+	struct list_head list;
+	u8 bssid[ETH_ALEN];
+	u8 ssid[IEEE80211_MAX_SSID_LEN];
+	size_t ssid_len;
+	u32 short_ssid;
+	u32 center_freq;
+	u8 unsolicited_probe:1,
+	   oct_recommended:1,
+	   same_ssid:1,
+	   multi_bss:1,
+	   transmitted_bssid:1,
+	   colocated_ess:1,
+	   short_ssid_valid:1;
+};
+
 static void bss_free(struct cfg80211_internal_bss *bss)
 {
 	struct cfg80211_bss_ies *ies;
@@ -448,10 +487,433 @@ static bool cfg80211_bss_expire_oldest(struct cfg80211_registered_device *rdev)
 	return ret;
 }
 
+static u8 cfg80211_parse_bss_param(u8 data,
+				   struct cfg80211_colocated_ap *coloc_ap)
+{
+	coloc_ap->oct_recommended =
+		u8_get_bits(data, IEEE80211_RNR_TBTT_PARAMS_OCT_RECOMMENDED);
+	coloc_ap->same_ssid =
+		u8_get_bits(data, IEEE80211_RNR_TBTT_PARAMS_SAME_SSID);
+	coloc_ap->multi_bss =
+		u8_get_bits(data, IEEE80211_RNR_TBTT_PARAMS_MULTI_BSSID);
+	coloc_ap->transmitted_bssid =
+		u8_get_bits(data, IEEE80211_RNR_TBTT_PARAMS_TRANSMITTED_BSSID);
+	coloc_ap->unsolicited_probe =
+		u8_get_bits(data, IEEE80211_RNR_TBTT_PARAMS_PROBE_ACTIVE);
+	coloc_ap->colocated_ess =
+		u8_get_bits(data, IEEE80211_RNR_TBTT_PARAMS_COLOC_ESS);
+
+	return u8_get_bits(data, IEEE80211_RNR_TBTT_PARAMS_COLOC_AP);
+}
+
+static int cfg80211_calc_short_ssid(const struct cfg80211_bss_ies *ies,
+				    const struct element **elem, u32 *s_ssid)
+{
+
+	*elem = cfg80211_find_elem(WLAN_EID_SSID, ies->data, ies->len);
+	if (!*elem || (*elem)->datalen > IEEE80211_MAX_SSID_LEN)
+		return -EINVAL;
+
+	*s_ssid = ~crc32_le(~0, (*elem)->data, (*elem)->datalen);
+	return 0;
+}
+
+static void cfg80211_free_coloc_ap_list(struct list_head *coloc_ap_list)
+{
+	struct cfg80211_colocated_ap *ap, *tmp_ap;
+
+	list_for_each_entry_safe(ap, tmp_ap, coloc_ap_list, list) {
+		list_del(&ap->list);
+		kfree(ap);
+	}
+}
+
+static int cfg80211_parse_ap_info(struct cfg80211_colocated_ap *entry,
+				  const u8 *pos, u8 length,
+				  const struct element *ssid_elem,
+				  int s_ssid_tmp)
+{
+	/* skip the TBTT offset */
+	pos++;
+
+	memcpy(entry->bssid, pos, ETH_ALEN);
+	pos += ETH_ALEN;
+
+	if (length == IEEE80211_TBTT_INFO_OFFSET_BSSID_SSSID_BSS_PARAM) {
+		memcpy(&entry->short_ssid, pos,
+		       sizeof(entry->short_ssid));
+		entry->short_ssid_valid = true;
+		pos += 4;
+	}
+
+	/* skip non colocated APs */
+	if (!cfg80211_parse_bss_param(*pos, entry))
+		return -EINVAL;
+	pos++;
+
+	if (length == IEEE80211_TBTT_INFO_OFFSET_BSSID_BSS_PARAM) {
+		/*
+		 * no information about the short ssid. Consider the entry valid
+		 * for now. It would later be dropped in case there are explicit
+		 * SSIDs that need to be matched
+		 */
+		if (!entry->same_ssid)
+			return 0;
+	}
+
+	if (entry->same_ssid) {
+		entry->short_ssid = s_ssid_tmp;
+		entry->short_ssid_valid = true;
+
+		/*
+		 * This is safe because we validate datalen in
+		 * cfg80211_parse_colocated_ap(), before calling this
+		 * function.
+		 */
+		memcpy(&entry->ssid, &ssid_elem->data,
+		       ssid_elem->datalen);
+		entry->ssid_len = ssid_elem->datalen;
+	}
+	return 0;
+}
+
+static int cfg80211_parse_colocated_ap(const struct cfg80211_bss_ies *ies,
+				       struct list_head *list)
+{
+	struct ieee80211_neighbor_ap_info *ap_info;
+	const struct element *elem, *ssid_elem;
+	const u8 *pos, *end;
+	u32 s_ssid_tmp;
+	int n_coloc = 0, ret;
+	LIST_HEAD(ap_list);
+
+	elem = cfg80211_find_elem(WLAN_EID_REDUCED_NEIGHBOR_REPORT, ies->data,
+				  ies->len);
+	if (!elem || elem->datalen > IEEE80211_MAX_SSID_LEN)
+		return 0;
+
+	pos = elem->data;
+	end = pos + elem->datalen;
+
+	ret = cfg80211_calc_short_ssid(ies, &ssid_elem, &s_ssid_tmp);
+	if (ret)
+		return ret;
+
+	/* RNR IE may contain more than one NEIGHBOR_AP_INFO */
+	while (pos + sizeof(*ap_info) <= end) {
+		enum nl80211_band band;
+		int freq;
+		u8 length, i, count;
+
+		ap_info = (void *)pos;
+		count = u8_get_bits(ap_info->tbtt_info_hdr,
+				    IEEE80211_AP_INFO_TBTT_HDR_COUNT) + 1;
+		length = ap_info->tbtt_info_len;
+
+		pos += sizeof(*ap_info);
+
+		if (!ieee80211_operating_class_to_band(ap_info->op_class,
+						       &band))
+			break;
+
+		freq = ieee80211_channel_to_frequency(ap_info->channel, band);
+
+		if (end - pos < count * ap_info->tbtt_info_len)
+			break;
+
+		/*
+		 * TBTT info must include bss param + BSSID +
+		 * (short SSID or same_ssid bit to be set).
+		 * ignore other options, and move to the
+		 * next AP info
+		 */
+		if (band != NL80211_BAND_6GHZ ||
+		    (length != IEEE80211_TBTT_INFO_OFFSET_BSSID_BSS_PARAM &&
+		     length < IEEE80211_TBTT_INFO_OFFSET_BSSID_SSSID_BSS_PARAM)) {
+			pos += count * ap_info->tbtt_info_len;
+			continue;
+		}
+
+		for (i = 0; i < count; i++) {
+			struct cfg80211_colocated_ap *entry;
+
+			entry = kzalloc(sizeof(*entry) + IEEE80211_MAX_SSID_LEN,
+					GFP_ATOMIC);
+
+			if (!entry)
+				break;
+
+			entry->center_freq = freq;
+
+			if (!cfg80211_parse_ap_info(entry, pos, length,
+						    ssid_elem, s_ssid_tmp)) {
+				n_coloc++;
+				list_add_tail(&entry->list, &ap_list);
+			} else {
+				kfree(entry);
+			}
+
+			pos += ap_info->tbtt_info_len;
+		}
+	}
+
+	if (pos != end) {
+		cfg80211_free_coloc_ap_list(&ap_list);
+		return 0;
+	}
+
+	list_splice_tail(&ap_list, list);
+	return n_coloc;
+}
+
+static  void cfg80211_scan_req_add_chan(struct cfg80211_scan_request *request,
+					struct ieee80211_channel *chan,
+					bool add_to_6ghz)
+{
+	int i;
+	u32 n_channels = request->n_channels;
+	struct cfg80211_scan_6ghz_params *params =
+		&request->scan_6ghz_params[request->n_6ghz_params];
+
+	for (i = 0; i < n_channels; i++) {
+		if (request->channels[i] == chan) {
+			if (add_to_6ghz)
+				params->channel_idx = i;
+			return;
+		}
+	}
+
+	request->channels[n_channels] = chan;
+	if (add_to_6ghz)
+		request->scan_6ghz_params[request->n_6ghz_params].channel_idx =
+			n_channels;
+
+	request->n_channels++;
+}
+
+static bool cfg80211_find_ssid_match(struct cfg80211_colocated_ap *ap,
+				     struct cfg80211_scan_request *request)
+{
+	u8 i;
+	u32 s_ssid;
+
+	for (i = 0; i < request->n_ssids; i++) {
+		/* wildcard ssid in the scan request */
+		if (!request->ssids[i].ssid_len)
+			return true;
+
+		if (ap->ssid_len &&
+		    ap->ssid_len == request->ssids[i].ssid_len) {
+			if (!memcmp(request->ssids[i].ssid, ap->ssid,
+				    ap->ssid_len))
+				return true;
+		} else if (ap->short_ssid_valid) {
+			s_ssid = ~crc32_le(~0, request->ssids[i].ssid,
+					   request->ssids[i].ssid_len);
+
+			if (ap->short_ssid == s_ssid)
+				return true;
+		}
+	}
+
+	return false;
+}
+
+static int cfg80211_scan_6ghz(struct cfg80211_registered_device *rdev)
+{
+	u8 i;
+	struct cfg80211_colocated_ap *ap;
+	int n_channels, count = 0, err;
+	struct cfg80211_scan_request *request, *rdev_req = rdev->scan_req;
+	LIST_HEAD(coloc_ap_list);
+	bool need_scan_psc;
+	const struct ieee80211_sband_iftype_data *iftd;
+
+	rdev_req->scan_6ghz = true;
+
+	if (!rdev->wiphy.bands[NL80211_BAND_6GHZ])
+		return -EOPNOTSUPP;
+
+	iftd = ieee80211_get_sband_iftype_data(rdev->wiphy.bands[NL80211_BAND_6GHZ],
+					       rdev_req->wdev->iftype);
+	if (!iftd || !iftd->he_cap.has_he)
+		return -EOPNOTSUPP;
+
+	n_channels = rdev->wiphy.bands[NL80211_BAND_6GHZ]->n_channels;
+
+	if (rdev_req->flags & NL80211_SCAN_FLAG_COLOCATED_6GHZ) {
+		struct cfg80211_internal_bss *intbss;
+
+		spin_lock_bh(&rdev->bss_lock);
+		list_for_each_entry(intbss, &rdev->bss_list, list) {
+			struct cfg80211_bss *res = &intbss->pub;
+			const struct cfg80211_bss_ies *ies;
+
+			ies = rcu_access_pointer(res->ies);
+			count += cfg80211_parse_colocated_ap(ies,
+							     &coloc_ap_list);
+		}
+		spin_unlock_bh(&rdev->bss_lock);
+	}
+
+	request = kzalloc(struct_size(request, channels, n_channels) +
+			  sizeof(*request->scan_6ghz_params) * count,
+			  GFP_KERNEL);
+	if (!request) {
+		cfg80211_free_coloc_ap_list(&coloc_ap_list);
+		return -ENOMEM;
+	}
+
+	*request = *rdev_req;
+	request->n_channels = 0;
+	request->scan_6ghz_params =
+		(void *)&request->channels[n_channels];
+
+	/*
+	 * PSC channels should not be scanned if all the reported co-located APs
+	 * are indicating that all APs in the same ESS are co-located
+	 */
+	if (count) {
+		need_scan_psc = false;
+
+		list_for_each_entry(ap, &coloc_ap_list, list) {
+			if (!ap->colocated_ess) {
+				need_scan_psc = true;
+				break;
+			}
+		}
+	} else {
+		need_scan_psc = true;
+	}
+
+	/*
+	 * add to the scan request the channels that need to be scanned
+	 * regardless of the collocated APs (PSC channels or all channels
+	 * in case that NL80211_SCAN_FLAG_COLOCATED_6GHZ is not set)
+	 */
+	for (i = 0; i < rdev_req->n_channels; i++) {
+		if (rdev_req->channels[i]->band == NL80211_BAND_6GHZ &&
+		    ((need_scan_psc &&
+		      cfg80211_channel_is_psc(rdev_req->channels[i])) ||
+		     !(rdev_req->flags & NL80211_SCAN_FLAG_COLOCATED_6GHZ))) {
+			cfg80211_scan_req_add_chan(request,
+						   rdev_req->channels[i],
+						   false);
+		}
+	}
+
+	if (!(rdev_req->flags & NL80211_SCAN_FLAG_COLOCATED_6GHZ))
+		goto skip;
+
+	list_for_each_entry(ap, &coloc_ap_list, list) {
+		bool found = false;
+		struct cfg80211_scan_6ghz_params *scan_6ghz_params =
+			&request->scan_6ghz_params[request->n_6ghz_params];
+		struct ieee80211_channel *chan =
+			ieee80211_get_channel(&rdev->wiphy, ap->center_freq);
+
+		if (!chan || chan->flags & IEEE80211_CHAN_DISABLED)
+			continue;
+
+		for (i = 0; i < rdev_req->n_channels; i++) {
+			if (rdev_req->channels[i] == chan)
+				found = true;
+		}
+
+		if (!found)
+			continue;
+
+		if (request->n_ssids > 0 &&
+		    !cfg80211_find_ssid_match(ap, request))
+			continue;
+
+		cfg80211_scan_req_add_chan(request, chan, true);
+		memcpy(scan_6ghz_params->bssid, ap->bssid, ETH_ALEN);
+		scan_6ghz_params->short_ssid = ap->short_ssid;
+		scan_6ghz_params->short_ssid_valid = ap->short_ssid_valid;
+		scan_6ghz_params->unsolicited_probe = ap->unsolicited_probe;
+
+		/*
+		 * If a PSC channel is added to the scan and 'need_scan_psc' is
+		 * set to false, then all the APs that the scan logic is
+		 * interested with on the channel are collocated and thus there
+		 * is no need to perform the initial PSC channel listen.
+		 */
+		if (cfg80211_channel_is_psc(chan) && !need_scan_psc)
+			scan_6ghz_params->psc_no_listen = true;
+
+		request->n_6ghz_params++;
+	}
+
+skip:
+	cfg80211_free_coloc_ap_list(&coloc_ap_list);
+
+	if (request->n_channels) {
+		struct cfg80211_scan_request *old = rdev->int_scan_req;
+
+		rdev->int_scan_req = request;
+
+		/*
+		 * If this scan follows a previous scan, save the scan start
+		 * info from the first part of the scan
+		 */
+		if (old)
+			rdev->int_scan_req->info = old->info;
+
+		err = rdev_scan(rdev, request);
+		if (err) {
+			rdev->int_scan_req = old;
+			kfree(request);
+		} else {
+			kfree(old);
+		}
+
+		return err;
+	}
+
+	kfree(request);
+	return -EINVAL;
+}
+
+int cfg80211_scan(struct cfg80211_registered_device *rdev)
+{
+	struct cfg80211_scan_request *request;
+	struct cfg80211_scan_request *rdev_req = rdev->scan_req;
+	u32 n_channels = 0, idx, i;
+
+	if (!(rdev->wiphy.flags & WIPHY_FLAG_SPLIT_SCAN_6GHZ))
+		return rdev_scan(rdev, rdev_req);
+
+	for (i = 0; i < rdev_req->n_channels; i++) {
+		if (rdev_req->channels[i]->band != NL80211_BAND_6GHZ)
+			n_channels++;
+	}
+
+	if (!n_channels)
+		return cfg80211_scan_6ghz(rdev);
+
+	request = kzalloc(struct_size(request, channels, n_channels),
+			  GFP_KERNEL);
+	if (!request)
+		return -ENOMEM;
+
+	*request = *rdev_req;
+	request->n_channels = n_channels;
+
+	for (i = idx = 0; i < rdev_req->n_channels; i++) {
+		if (rdev_req->channels[i]->band != NL80211_BAND_6GHZ)
+			request->channels[idx++] = rdev_req->channels[i];
+	}
+
+	rdev_req->scan_6ghz = false;
+	rdev->int_scan_req = request;
+	return rdev_scan(rdev, request);
+}
+
 void ___cfg80211_scan_done(struct cfg80211_registered_device *rdev,
 			   bool send_message)
 {
-	struct cfg80211_scan_request *request;
+	struct cfg80211_scan_request *request, *rdev_req;
 	struct wireless_dev *wdev;
 	struct sk_buff *msg;
 #ifdef CONFIG_CFG80211_WEXT
@@ -466,11 +928,18 @@ void ___cfg80211_scan_done(struct cfg80211_registered_device *rdev,
 		return;
 	}
 
-	request = rdev->scan_req;
-	if (!request)
+	rdev_req = rdev->scan_req;
+	if (!rdev_req)
 		return;
 
-	wdev = request->wdev;
+	wdev = rdev_req->wdev;
+	request = rdev->int_scan_req ? rdev->int_scan_req : rdev_req;
+
+	if (wdev_running(wdev) &&
+	    (rdev->wiphy.flags & WIPHY_FLAG_SPLIT_SCAN_6GHZ) &&
+	    !rdev_req->scan_6ghz && !request->info.aborted &&
+	    !cfg80211_scan_6ghz(rdev))
+		return;
 
 	/*
 	 * This must be before sending the other events!
@@ -501,8 +970,11 @@ void ___cfg80211_scan_done(struct cfg80211_registered_device *rdev,
 	if (wdev->netdev)
 		dev_put(wdev->netdev);
 
+	kfree(rdev->int_scan_req);
+	rdev->int_scan_req = NULL;
+
+	kfree(rdev->scan_req);
 	rdev->scan_req = NULL;
-	kfree(request);
 
 	if (!send_message)
 		rdev->scan_msg = msg;
@@ -525,10 +997,25 @@ void __cfg80211_scan_done(struct work_struct *wk)
 void cfg80211_scan_done(struct cfg80211_scan_request *request,
 			struct cfg80211_scan_info *info)
 {
+	struct cfg80211_scan_info old_info = request->info;
+
 	trace_cfg80211_scan_done(request, info);
-	WARN_ON(request != wiphy_to_rdev(request->wiphy)->scan_req);
+	WARN_ON(request != wiphy_to_rdev(request->wiphy)->scan_req &&
+		request != wiphy_to_rdev(request->wiphy)->int_scan_req);
 
 	request->info = *info;
+
+	/*
+	 * In case the scan is split, the scan_start_tsf and tsf_bssid should
+	 * be of the first part. In such a case old_info.scan_start_tsf should
+	 * be non zero.
+	 */
+	if (request->scan_6ghz && old_info.scan_start_tsf) {
+		request->info.scan_start_tsf = old_info.scan_start_tsf;
+		memcpy(request->info.tsf_bssid, old_info.tsf_bssid,
+		       sizeof(request->info.tsf_bssid));
+	}
+
 	request->notified = true;
 	queue_work(cfg80211_wq, &wiphy_to_rdev(request->wiphy)->scan_done_wk);
 }
@@ -1315,15 +1802,24 @@ cfg80211_get_bss_channel(struct wiphy *wiphy, const u8 *ie, size_t ielen,
 	int channel_number = -1;
 	struct ieee80211_channel *alt_channel;
 
-	tmp = cfg80211_find_ie(WLAN_EID_DS_PARAMS, ie, ielen);
-	if (tmp && tmp[1] == 1) {
-		channel_number = tmp[2];
+	if (channel->band == NL80211_BAND_S1GHZ) {
+		tmp = cfg80211_find_ie(WLAN_EID_S1G_OPERATION, ie, ielen);
+		if (tmp && tmp[1] >= sizeof(struct ieee80211_s1g_oper_ie)) {
+			struct ieee80211_s1g_oper_ie *s1gop = (void *)(tmp + 2);
+
+			channel_number = s1gop->primary_ch;
+		}
 	} else {
-		tmp = cfg80211_find_ie(WLAN_EID_HT_OPERATION, ie, ielen);
-		if (tmp && tmp[1] >= sizeof(struct ieee80211_ht_operation)) {
-			struct ieee80211_ht_operation *htop = (void *)(tmp + 2);
+		tmp = cfg80211_find_ie(WLAN_EID_DS_PARAMS, ie, ielen);
+		if (tmp && tmp[1] == 1) {
+			channel_number = tmp[2];
+		} else {
+			tmp = cfg80211_find_ie(WLAN_EID_HT_OPERATION, ie, ielen);
+			if (tmp && tmp[1] >= sizeof(struct ieee80211_ht_operation)) {
+				struct ieee80211_ht_operation *htop = (void *)(tmp + 2);
 
-			channel_number = htop->primary_chan;
+				channel_number = htop->primary_chan;
+			}
 		}
 	}
 
@@ -1807,8 +2303,11 @@ cfg80211_inform_single_bss_frame_data(struct wiphy *wiphy,
 	struct cfg80211_bss_ies *ies;
 	struct ieee80211_channel *channel;
 	bool signal_valid;
-	size_t ielen = len - offsetof(struct ieee80211_mgmt,
-				      u.probe_resp.variable);
+	struct ieee80211_ext *ext = NULL;
+	u8 *bssid, *variable;
+	u16 capability, beacon_int;
+	size_t ielen, min_hdr_len = offsetof(struct ieee80211_mgmt,
+					     u.probe_resp.variable);
 	int bss_type;
 
 	BUILD_BUG_ON(offsetof(struct ieee80211_mgmt, u.probe_resp.variable) !=
@@ -1826,21 +2325,57 @@ cfg80211_inform_single_bss_frame_data(struct wiphy *wiphy,
 		    (data->signal < 0 || data->signal > 100)))
 		return NULL;
 
-	if (WARN_ON(len < offsetof(struct ieee80211_mgmt, u.probe_resp.variable)))
+	if (ieee80211_is_s1g_beacon(mgmt->frame_control)) {
+		ext = (void *) mgmt;
+		min_hdr_len = offsetof(struct ieee80211_ext, u.s1g_beacon);
+		if (ieee80211_is_s1g_short_beacon(mgmt->frame_control))
+			min_hdr_len = offsetof(struct ieee80211_ext,
+					       u.s1g_short_beacon.variable);
+	}
+
+	if (WARN_ON(len < min_hdr_len))
 		return NULL;
 
-	channel = cfg80211_get_bss_channel(wiphy, mgmt->u.beacon.variable,
+	ielen = len - min_hdr_len;
+	variable = mgmt->u.probe_resp.variable;
+	if (ext) {
+		if (ieee80211_is_s1g_short_beacon(mgmt->frame_control))
+			variable = ext->u.s1g_short_beacon.variable;
+		else
+			variable = ext->u.s1g_beacon.variable;
+	}
+
+	channel = cfg80211_get_bss_channel(wiphy, variable,
 					   ielen, data->chan, data->scan_width);
 	if (!channel)
 		return NULL;
 
+	if (ext) {
+		struct ieee80211_s1g_bcn_compat_ie *compat;
+		u8 *ie;
+
+		ie = (void *)cfg80211_find_ie(WLAN_EID_S1G_BCN_COMPAT,
+					      variable, ielen);
+		if (!ie)
+			return NULL;
+		compat = (void *)(ie + 2);
+		bssid = ext->u.s1g_beacon.sa;
+		capability = le16_to_cpu(compat->compat_info);
+		beacon_int = le16_to_cpu(compat->beacon_int);
+	} else {
+		bssid = mgmt->bssid;
+		beacon_int = le16_to_cpu(mgmt->u.probe_resp.beacon_int);
+		capability = le16_to_cpu(mgmt->u.probe_resp.capab_info);
+	}
+
 	ies = kzalloc(sizeof(*ies) + ielen, gfp);
 	if (!ies)
 		return NULL;
 	ies->len = ielen;
 	ies->tsf = le64_to_cpu(mgmt->u.probe_resp.timestamp);
-	ies->from_beacon = ieee80211_is_beacon(mgmt->frame_control);
-	memcpy(ies->data, mgmt->u.probe_resp.variable, ielen);
+	ies->from_beacon = ieee80211_is_beacon(mgmt->frame_control) ||
+			   ieee80211_is_s1g_beacon(mgmt->frame_control);
+	memcpy(ies->data, variable, ielen);
 
 	if (ieee80211_is_probe_resp(mgmt->frame_control))
 		rcu_assign_pointer(tmp.pub.proberesp_ies, ies);
@@ -1848,12 +2383,12 @@ cfg80211_inform_single_bss_frame_data(struct wiphy *wiphy,
 		rcu_assign_pointer(tmp.pub.beacon_ies, ies);
 	rcu_assign_pointer(tmp.pub.ies, ies);
 
-	memcpy(tmp.pub.bssid, mgmt->bssid, ETH_ALEN);
+	memcpy(tmp.pub.bssid, bssid, ETH_ALEN);
+	tmp.pub.beacon_interval = beacon_int;
+	tmp.pub.capability = capability;
 	tmp.pub.channel = channel;
 	tmp.pub.scan_width = data->scan_width;
 	tmp.pub.signal = data->signal;
-	tmp.pub.beacon_interval = le16_to_cpu(mgmt->u.probe_resp.beacon_int);
-	tmp.pub.capability = le16_to_cpu(mgmt->u.probe_resp.capab_info);
 	tmp.ts_boottime = data->boottime_ns;
 	tmp.parent_tsf = data->parent_tsf;
 	tmp.pub.chains = data->chains;
diff --git a/net/wireless/util.c b/net/wireless/util.c
index ac2bb1a80f2b..f01746894a4e 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -95,7 +95,7 @@ u32 ieee80211_channel_to_freq_khz(int chan, enum nl80211_band band)
 		/* see 802.11ax D6.1 27.3.23.2 */
 		if (chan == 2)
 			return MHZ_TO_KHZ(5935);
-		if (chan <= 253)
+		if (chan <= 233)
 			return MHZ_TO_KHZ(5950 + chan * 5);
 		break;
 	case NL80211_BAND_60GHZ:
diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
index a7227b447228..56d052bc65cb 100644
--- a/net/xdp/xdp_umem.c
+++ b/net/xdp/xdp_umem.c
@@ -140,10 +140,10 @@ static int xdp_umem_account_pages(struct xdp_umem *umem)
 
 static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
 {
+	u32 npgs_rem, chunk_size = mr->chunk_size, headroom = mr->headroom;
 	bool unaligned_chunks = mr->flags & XDP_UMEM_UNALIGNED_CHUNK_FLAG;
-	u32 chunk_size = mr->chunk_size, headroom = mr->headroom;
 	u64 npgs, addr = mr->addr, size = mr->len;
-	unsigned int chunks, chunks_per_page;
+	unsigned int chunks, chunks_rem;
 	int err;
 
 	if (chunk_size < XDP_UMEM_MIN_CHUNK_SIZE || chunk_size > PAGE_SIZE) {
@@ -172,19 +172,18 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
 	if ((addr + size) < addr)
 		return -EINVAL;
 
-	npgs = size >> PAGE_SHIFT;
+	npgs = div_u64_rem(size, PAGE_SIZE, &npgs_rem);
+	if (npgs_rem)
+		npgs++;
 	if (npgs > U32_MAX)
 		return -EINVAL;
 
-	chunks = (unsigned int)div_u64(size, chunk_size);
+	chunks = (unsigned int)div_u64_rem(size, chunk_size, &chunks_rem);
 	if (chunks == 0)
 		return -EINVAL;
 
-	if (!unaligned_chunks) {
-		chunks_per_page = PAGE_SIZE / chunk_size;
-		if (chunks < chunks_per_page || chunks % chunks_per_page)
-			return -EINVAL;
-	}
+	if (!unaligned_chunks && chunks_rem)
+		return -EINVAL;
 
 	if (headroom >= chunk_size - XDP_PACKET_HEADROOM)
 		return -EINVAL;
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 5eb6662f562a..ba4dfb17c666 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -33,12 +33,6 @@
 
 static DEFINE_PER_CPU(struct list_head, xskmap_flush_list);
 
-bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs)
-{
-	return READ_ONCE(xs->rx) &&  READ_ONCE(xs->umem) &&
-		(xs->pool->fq || READ_ONCE(xs->fq_tmp));
-}
-
 void xsk_set_rx_need_wakeup(struct xsk_buff_pool *pool)
 {
 	if (pool->cached_need_wakeup & XDP_WAKEUP_RX)
@@ -709,6 +703,7 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
 			xs->pool = xp_create_and_assign_umem(xs,
 							     umem_xs->umem);
 			if (!xs->pool) {
+				err = -ENOMEM;
 				sockfd_put(sock);
 				goto out_unlock;
 			}
@@ -717,6 +712,7 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
 						   dev, qid);
 			if (err) {
 				xp_destroy(xs->pool);
+				xs->pool = NULL;
 				sockfd_put(sock);
 				goto out_unlock;
 			}
diff --git a/net/xdp/xsk.h b/net/xdp/xsk.h
index da1f73e43924..b9e896cee5bb 100644
--- a/net/xdp/xsk.h
+++ b/net/xdp/xsk.h
@@ -39,7 +39,6 @@ static inline struct xdp_sock *xdp_sk(struct sock *sk)
 	return (struct xdp_sock *)sk;
 }
 
-bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs);
 void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs,
 			     struct xdp_sock **map_entry);
 int xsk_map_inc(struct xsk_map *map);
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index 795d7c81c0ca..e63fadd000db 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -287,7 +287,7 @@ static struct xsk_dma_map *xp_create_dma_map(struct device *dev, struct net_devi
 		return NULL;
 
 	dma_map->dma_pages = kvcalloc(nr_pages, sizeof(*dma_map->dma_pages), GFP_KERNEL);
-	if (!dma_map) {
+	if (!dma_map->dma_pages) {
 		kfree(dma_map);
 		return NULL;
 	}
@@ -296,7 +296,7 @@ static struct xsk_dma_map *xp_create_dma_map(struct device *dev, struct net_devi
 	dma_map->dev = dev;
 	dma_map->dma_need_sync = false;
 	dma_map->dma_pages_cnt = nr_pages;
-	refcount_set(&dma_map->users, 0);
+	refcount_set(&dma_map->users, 1);
 	list_add(&dma_map->list, &umem->xsk_dma_list);
 	return dma_map;
 }
@@ -369,7 +369,6 @@ static int xp_init_dma_info(struct xsk_buff_pool *pool, struct xsk_dma_map *dma_
 	pool->dev = dma_map->dev;
 	pool->dma_pages_cnt = dma_map->dma_pages_cnt;
 	pool->dma_need_sync = dma_map->dma_need_sync;
-	refcount_inc(&dma_map->users);
 	memcpy(pool->dma_pages, dma_map->dma_pages,
 	       pool->dma_pages_cnt * sizeof(*pool->dma_pages));
 
@@ -390,6 +389,7 @@ int xp_dma_map(struct xsk_buff_pool *pool, struct device *dev,
 		if (err)
 			return err;
 
+		refcount_inc(&dma_map->users);
 		return 0;
 	}
 
diff --git a/net/xdp/xsk_diag.c b/net/xdp/xsk_diag.c
index 5bd8ea9d206a..c014217f5fa7 100644
--- a/net/xdp/xsk_diag.c
+++ b/net/xdp/xsk_diag.c
@@ -59,22 +59,20 @@ static int xsk_diag_put_umem(const struct xdp_sock *xs, struct sk_buff *nlskb)
 	du.num_pages = umem->npgs;
 	du.chunk_size = umem->chunk_size;
 	du.headroom = umem->headroom;
-	du.ifindex = pool->netdev ? pool->netdev->ifindex : 0;
-	du.queue_id = pool->queue_id;
+	du.ifindex = (pool && pool->netdev) ? pool->netdev->ifindex : 0;
+	du.queue_id = pool ? pool->queue_id : 0;
 	du.flags = 0;
 	if (umem->zc)
 		du.flags |= XDP_DU_F_ZEROCOPY;
 	du.refs = refcount_read(&umem->users);
 
 	err = nla_put(nlskb, XDP_DIAG_UMEM, sizeof(du), &du);
-
-	if (!err && pool->fq)
+	if (!err && pool && pool->fq)
 		err = xsk_diag_put_ring(pool->fq,
 					XDP_DIAG_UMEM_FILL_RING, nlskb);
-	if (!err && pool->cq) {
-		err = xsk_diag_put_ring(pool->cq, XDP_DIAG_UMEM_COMPLETION_RING,
-					nlskb);
-	}
+	if (!err && pool && pool->cq)
+		err = xsk_diag_put_ring(pool->cq,
+					XDP_DIAG_UMEM_COMPLETION_RING, nlskb);
 	return err;
 }
 
diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h
index 2d883f631c85..dc1dd5ef70d1 100644
--- a/net/xdp/xsk_queue.h
+++ b/net/xdp/xsk_queue.h
@@ -96,7 +96,7 @@ struct xsk_queue {
  * seen and read by the consumer.
  *
  * The consumer peeks into the ring to see if the producer has written
- * any new entries. If so, the producer can then read these entries
+ * any new entries. If so, the consumer can then read these entries
  * and when it is done reading them release them back to the producer
  * so that the producer can use these slots to fill in new entries.
  *
diff --git a/net/xdp/xskmap.c b/net/xdp/xskmap.c
index 2a4fd6677155..0c5df593bc56 100644
--- a/net/xdp/xskmap.c
+++ b/net/xdp/xskmap.c
@@ -185,11 +185,6 @@ static int xsk_map_update_elem(struct bpf_map *map, void *key, void *value,
 
 	xs = (struct xdp_sock *)sock->sk;
 
-	if (!xsk_is_setup_for_bpf_map(xs)) {
-		sockfd_put(sock);
-		return -EOPNOTSUPP;
-	}
-
 	map_entry = &m->xsk_map[i];
 	node = xsk_map_node_alloc(m, map_entry);
 	if (IS_ERR(node)) {
diff --git a/net/xfrm/Kconfig b/net/xfrm/Kconfig
index 5b9a5ab48111..3adf31a83a79 100644
--- a/net/xfrm/Kconfig
+++ b/net/xfrm/Kconfig
@@ -28,6 +28,17 @@ config XFRM_USER
 
 	  If unsure, say Y.
 
+config XFRM_USER_COMPAT
+	tristate "Compatible ABI support"
+	depends on XFRM_USER && COMPAT_FOR_U64_ALIGNMENT && \
+		HAVE_EFFICIENT_UNALIGNED_ACCESS
+	select WANT_COMPAT_NETLINK_MESSAGES
+	help
+	  Transformation(XFRM) user configuration interface like IPsec
+	  used by compatible Linux applications.
+
+	  If unsure, say N.
+
 config XFRM_INTERFACE
 	tristate "Transformation virtual interface"
 	depends on XFRM && IPV6
diff --git a/net/xfrm/Makefile b/net/xfrm/Makefile
index 2d4bb4b9f75e..494aa744bfb9 100644
--- a/net/xfrm/Makefile
+++ b/net/xfrm/Makefile
@@ -9,6 +9,7 @@ obj-$(CONFIG_XFRM) := xfrm_policy.o xfrm_state.o xfrm_hash.o \
 obj-$(CONFIG_XFRM_STATISTICS) += xfrm_proc.o
 obj-$(CONFIG_XFRM_ALGO) += xfrm_algo.o
 obj-$(CONFIG_XFRM_USER) += xfrm_user.o
+obj-$(CONFIG_XFRM_USER_COMPAT) += xfrm_compat.o
 obj-$(CONFIG_XFRM_IPCOMP) += xfrm_ipcomp.o
 obj-$(CONFIG_XFRM_INTERFACE) += xfrm_interface.o
 obj-$(CONFIG_XFRM_ESPINTCP) += espintcp.o
diff --git a/net/xfrm/xfrm_compat.c b/net/xfrm/xfrm_compat.c
new file mode 100644
index 000000000000..e28f0c9ecd6a
--- /dev/null
+++ b/net/xfrm/xfrm_compat.c
@@ -0,0 +1,625 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * XFRM compat layer
+ * Author: Dmitry Safonov <dima@arista.com>
+ * Based on code and translator idea by: Florian Westphal <fw@strlen.de>
+ */
+#include <linux/compat.h>
+#include <linux/xfrm.h>
+#include <net/xfrm.h>
+
+struct compat_xfrm_lifetime_cfg {
+	compat_u64 soft_byte_limit, hard_byte_limit;
+	compat_u64 soft_packet_limit, hard_packet_limit;
+	compat_u64 soft_add_expires_seconds, hard_add_expires_seconds;
+	compat_u64 soft_use_expires_seconds, hard_use_expires_seconds;
+}; /* same size on 32bit, but only 4 byte alignment required */
+
+struct compat_xfrm_lifetime_cur {
+	compat_u64 bytes, packets, add_time, use_time;
+}; /* same size on 32bit, but only 4 byte alignment required */
+
+struct compat_xfrm_userpolicy_info {
+	struct xfrm_selector sel;
+	struct compat_xfrm_lifetime_cfg lft;
+	struct compat_xfrm_lifetime_cur curlft;
+	__u32 priority, index;
+	u8 dir, action, flags, share;
+	/* 4 bytes additional padding on 64bit */
+};
+
+struct compat_xfrm_usersa_info {
+	struct xfrm_selector sel;
+	struct xfrm_id id;
+	xfrm_address_t saddr;
+	struct compat_xfrm_lifetime_cfg lft;
+	struct compat_xfrm_lifetime_cur curlft;
+	struct xfrm_stats stats;
+	__u32 seq, reqid;
+	u16 family;
+	u8 mode, replay_window, flags;
+	/* 4 bytes additional padding on 64bit */
+};
+
+struct compat_xfrm_user_acquire {
+	struct xfrm_id id;
+	xfrm_address_t saddr;
+	struct xfrm_selector sel;
+	struct compat_xfrm_userpolicy_info policy;
+	/* 4 bytes additional padding on 64bit */
+	__u32 aalgos, ealgos, calgos, seq;
+};
+
+struct compat_xfrm_userspi_info {
+	struct compat_xfrm_usersa_info info;
+	/* 4 bytes additional padding on 64bit */
+	__u32 min, max;
+};
+
+struct compat_xfrm_user_expire {
+	struct compat_xfrm_usersa_info state;
+	/* 8 bytes additional padding on 64bit */
+	u8 hard;
+};
+
+struct compat_xfrm_user_polexpire {
+	struct compat_xfrm_userpolicy_info pol;
+	/* 8 bytes additional padding on 64bit */
+	u8 hard;
+};
+
+#define XMSGSIZE(type) sizeof(struct type)
+
+static const int compat_msg_min[XFRM_NR_MSGTYPES] = {
+	[XFRM_MSG_NEWSA       - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_usersa_info),
+	[XFRM_MSG_DELSA       - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_id),
+	[XFRM_MSG_GETSA       - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_id),
+	[XFRM_MSG_NEWPOLICY   - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_userpolicy_info),
+	[XFRM_MSG_DELPOLICY   - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_id),
+	[XFRM_MSG_GETPOLICY   - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_id),
+	[XFRM_MSG_ALLOCSPI    - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_userspi_info),
+	[XFRM_MSG_ACQUIRE     - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_user_acquire),
+	[XFRM_MSG_EXPIRE      - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_user_expire),
+	[XFRM_MSG_UPDPOLICY   - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_userpolicy_info),
+	[XFRM_MSG_UPDSA       - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_usersa_info),
+	[XFRM_MSG_POLEXPIRE   - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_user_polexpire),
+	[XFRM_MSG_FLUSHSA     - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_flush),
+	[XFRM_MSG_FLUSHPOLICY - XFRM_MSG_BASE] = 0,
+	[XFRM_MSG_NEWAE       - XFRM_MSG_BASE] = XMSGSIZE(xfrm_aevent_id),
+	[XFRM_MSG_GETAE       - XFRM_MSG_BASE] = XMSGSIZE(xfrm_aevent_id),
+	[XFRM_MSG_REPORT      - XFRM_MSG_BASE] = XMSGSIZE(xfrm_user_report),
+	[XFRM_MSG_MIGRATE     - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_id),
+	[XFRM_MSG_NEWSADINFO  - XFRM_MSG_BASE] = sizeof(u32),
+	[XFRM_MSG_GETSADINFO  - XFRM_MSG_BASE] = sizeof(u32),
+	[XFRM_MSG_NEWSPDINFO  - XFRM_MSG_BASE] = sizeof(u32),
+	[XFRM_MSG_GETSPDINFO  - XFRM_MSG_BASE] = sizeof(u32),
+	[XFRM_MSG_MAPPING     - XFRM_MSG_BASE] = XMSGSIZE(xfrm_user_mapping)
+};
+
+static const struct nla_policy compat_policy[XFRMA_MAX+1] = {
+	[XFRMA_SA]		= { .len = XMSGSIZE(compat_xfrm_usersa_info)},
+	[XFRMA_POLICY]		= { .len = XMSGSIZE(compat_xfrm_userpolicy_info)},
+	[XFRMA_LASTUSED]	= { .type = NLA_U64},
+	[XFRMA_ALG_AUTH_TRUNC]	= { .len = sizeof(struct xfrm_algo_auth)},
+	[XFRMA_ALG_AEAD]	= { .len = sizeof(struct xfrm_algo_aead) },
+	[XFRMA_ALG_AUTH]	= { .len = sizeof(struct xfrm_algo) },
+	[XFRMA_ALG_CRYPT]	= { .len = sizeof(struct xfrm_algo) },
+	[XFRMA_ALG_COMP]	= { .len = sizeof(struct xfrm_algo) },
+	[XFRMA_ENCAP]		= { .len = sizeof(struct xfrm_encap_tmpl) },
+	[XFRMA_TMPL]		= { .len = sizeof(struct xfrm_user_tmpl) },
+	[XFRMA_SEC_CTX]		= { .len = sizeof(struct xfrm_sec_ctx) },
+	[XFRMA_LTIME_VAL]	= { .len = sizeof(struct xfrm_lifetime_cur) },
+	[XFRMA_REPLAY_VAL]	= { .len = sizeof(struct xfrm_replay_state) },
+	[XFRMA_REPLAY_THRESH]	= { .type = NLA_U32 },
+	[XFRMA_ETIMER_THRESH]	= { .type = NLA_U32 },
+	[XFRMA_SRCADDR]		= { .len = sizeof(xfrm_address_t) },
+	[XFRMA_COADDR]		= { .len = sizeof(xfrm_address_t) },
+	[XFRMA_POLICY_TYPE]	= { .len = sizeof(struct xfrm_userpolicy_type)},
+	[XFRMA_MIGRATE]		= { .len = sizeof(struct xfrm_user_migrate) },
+	[XFRMA_KMADDRESS]	= { .len = sizeof(struct xfrm_user_kmaddress) },
+	[XFRMA_MARK]		= { .len = sizeof(struct xfrm_mark) },
+	[XFRMA_TFCPAD]		= { .type = NLA_U32 },
+	[XFRMA_REPLAY_ESN_VAL]	= { .len = sizeof(struct xfrm_replay_state_esn) },
+	[XFRMA_SA_EXTRA_FLAGS]	= { .type = NLA_U32 },
+	[XFRMA_PROTO]		= { .type = NLA_U8 },
+	[XFRMA_ADDRESS_FILTER]	= { .len = sizeof(struct xfrm_address_filter) },
+	[XFRMA_OFFLOAD_DEV]	= { .len = sizeof(struct xfrm_user_offload) },
+	[XFRMA_SET_MARK]	= { .type = NLA_U32 },
+	[XFRMA_SET_MARK_MASK]	= { .type = NLA_U32 },
+	[XFRMA_IF_ID]		= { .type = NLA_U32 },
+};
+
+static struct nlmsghdr *xfrm_nlmsg_put_compat(struct sk_buff *skb,
+			const struct nlmsghdr *nlh_src, u16 type)
+{
+	int payload = compat_msg_min[type];
+	int src_len = xfrm_msg_min[type];
+	struct nlmsghdr *nlh_dst;
+
+	/* Compat messages are shorter or equal to native (+padding) */
+	if (WARN_ON_ONCE(src_len < payload))
+		return ERR_PTR(-EMSGSIZE);
+
+	nlh_dst = nlmsg_put(skb, nlh_src->nlmsg_pid, nlh_src->nlmsg_seq,
+			    nlh_src->nlmsg_type, payload, nlh_src->nlmsg_flags);
+	if (!nlh_dst)
+		return ERR_PTR(-EMSGSIZE);
+
+	memset(nlmsg_data(nlh_dst), 0, payload);
+
+	switch (nlh_src->nlmsg_type) {
+	/* Compat message has the same layout as native */
+	case XFRM_MSG_DELSA:
+	case XFRM_MSG_DELPOLICY:
+	case XFRM_MSG_FLUSHSA:
+	case XFRM_MSG_FLUSHPOLICY:
+	case XFRM_MSG_NEWAE:
+	case XFRM_MSG_REPORT:
+	case XFRM_MSG_MIGRATE:
+	case XFRM_MSG_NEWSADINFO:
+	case XFRM_MSG_NEWSPDINFO:
+	case XFRM_MSG_MAPPING:
+		WARN_ON_ONCE(src_len != payload);
+		memcpy(nlmsg_data(nlh_dst), nlmsg_data(nlh_src), src_len);
+		break;
+	/* 4 byte alignment for trailing u64 on native, but not on compat */
+	case XFRM_MSG_NEWSA:
+	case XFRM_MSG_NEWPOLICY:
+	case XFRM_MSG_UPDSA:
+	case XFRM_MSG_UPDPOLICY:
+		WARN_ON_ONCE(src_len != payload + 4);
+		memcpy(nlmsg_data(nlh_dst), nlmsg_data(nlh_src), payload);
+		break;
+	case XFRM_MSG_EXPIRE: {
+		const struct xfrm_user_expire *src_ue  = nlmsg_data(nlh_src);
+		struct compat_xfrm_user_expire *dst_ue = nlmsg_data(nlh_dst);
+
+		/* compat_xfrm_user_expire has 4-byte smaller state */
+		memcpy(dst_ue, src_ue, sizeof(dst_ue->state));
+		dst_ue->hard = src_ue->hard;
+		break;
+	}
+	case XFRM_MSG_ACQUIRE: {
+		const struct xfrm_user_acquire *src_ua  = nlmsg_data(nlh_src);
+		struct compat_xfrm_user_acquire *dst_ua = nlmsg_data(nlh_dst);
+
+		memcpy(dst_ua, src_ua, offsetof(struct compat_xfrm_user_acquire, aalgos));
+		dst_ua->aalgos = src_ua->aalgos;
+		dst_ua->ealgos = src_ua->ealgos;
+		dst_ua->calgos = src_ua->calgos;
+		dst_ua->seq    = src_ua->seq;
+		break;
+	}
+	case XFRM_MSG_POLEXPIRE: {
+		const struct xfrm_user_polexpire *src_upe  = nlmsg_data(nlh_src);
+		struct compat_xfrm_user_polexpire *dst_upe = nlmsg_data(nlh_dst);
+
+		/* compat_xfrm_user_polexpire has 4-byte smaller state */
+		memcpy(dst_upe, src_upe, sizeof(dst_upe->pol));
+		dst_upe->hard = src_upe->hard;
+		break;
+	}
+	case XFRM_MSG_ALLOCSPI: {
+		const struct xfrm_userspi_info *src_usi = nlmsg_data(nlh_src);
+		struct compat_xfrm_userspi_info *dst_usi = nlmsg_data(nlh_dst);
+
+		/* compat_xfrm_user_polexpire has 4-byte smaller state */
+		memcpy(dst_usi, src_usi, sizeof(src_usi->info));
+		dst_usi->min = src_usi->min;
+		dst_usi->max = src_usi->max;
+		break;
+	}
+	/* Not being sent by kernel */
+	case XFRM_MSG_GETSA:
+	case XFRM_MSG_GETPOLICY:
+	case XFRM_MSG_GETAE:
+	case XFRM_MSG_GETSADINFO:
+	case XFRM_MSG_GETSPDINFO:
+	default:
+		WARN_ONCE(1, "unsupported nlmsg_type %d", nlh_src->nlmsg_type);
+		return ERR_PTR(-EOPNOTSUPP);
+	}
+
+	return nlh_dst;
+}
+
+static int xfrm_nla_cpy(struct sk_buff *dst, const struct nlattr *src, int len)
+{
+	return nla_put(dst, src->nla_type, len, nla_data(src));
+}
+
+static int xfrm_xlate64_attr(struct sk_buff *dst, const struct nlattr *src)
+{
+	switch (src->nla_type) {
+	case XFRMA_PAD:
+		/* Ignore */
+		return 0;
+	case XFRMA_ALG_AUTH:
+	case XFRMA_ALG_CRYPT:
+	case XFRMA_ALG_COMP:
+	case XFRMA_ENCAP:
+	case XFRMA_TMPL:
+		return xfrm_nla_cpy(dst, src, nla_len(src));
+	case XFRMA_SA:
+		return xfrm_nla_cpy(dst, src, XMSGSIZE(compat_xfrm_usersa_info));
+	case XFRMA_POLICY:
+		return xfrm_nla_cpy(dst, src, XMSGSIZE(compat_xfrm_userpolicy_info));
+	case XFRMA_SEC_CTX:
+		return xfrm_nla_cpy(dst, src, nla_len(src));
+	case XFRMA_LTIME_VAL:
+		return nla_put_64bit(dst, src->nla_type, nla_len(src),
+			nla_data(src), XFRMA_PAD);
+	case XFRMA_REPLAY_VAL:
+	case XFRMA_REPLAY_THRESH:
+	case XFRMA_ETIMER_THRESH:
+	case XFRMA_SRCADDR:
+	case XFRMA_COADDR:
+		return xfrm_nla_cpy(dst, src, nla_len(src));
+	case XFRMA_LASTUSED:
+		return nla_put_64bit(dst, src->nla_type, nla_len(src),
+			nla_data(src), XFRMA_PAD);
+	case XFRMA_POLICY_TYPE:
+	case XFRMA_MIGRATE:
+	case XFRMA_ALG_AEAD:
+	case XFRMA_KMADDRESS:
+	case XFRMA_ALG_AUTH_TRUNC:
+	case XFRMA_MARK:
+	case XFRMA_TFCPAD:
+	case XFRMA_REPLAY_ESN_VAL:
+	case XFRMA_SA_EXTRA_FLAGS:
+	case XFRMA_PROTO:
+	case XFRMA_ADDRESS_FILTER:
+	case XFRMA_OFFLOAD_DEV:
+	case XFRMA_SET_MARK:
+	case XFRMA_SET_MARK_MASK:
+	case XFRMA_IF_ID:
+		return xfrm_nla_cpy(dst, src, nla_len(src));
+	default:
+		BUILD_BUG_ON(XFRMA_MAX != XFRMA_IF_ID);
+		WARN_ONCE(1, "unsupported nla_type %d", src->nla_type);
+		return -EOPNOTSUPP;
+	}
+}
+
+/* Take kernel-built (64bit layout) and create 32bit layout for userspace */
+static int xfrm_xlate64(struct sk_buff *dst, const struct nlmsghdr *nlh_src)
+{
+	u16 type = nlh_src->nlmsg_type - XFRM_MSG_BASE;
+	const struct nlattr *nla, *attrs;
+	struct nlmsghdr *nlh_dst;
+	int len, remaining;
+
+	nlh_dst = xfrm_nlmsg_put_compat(dst, nlh_src, type);
+	if (IS_ERR(nlh_dst))
+		return PTR_ERR(nlh_dst);
+
+	attrs = nlmsg_attrdata(nlh_src, xfrm_msg_min[type]);
+	len = nlmsg_attrlen(nlh_src, xfrm_msg_min[type]);
+
+	nla_for_each_attr(nla, attrs, len, remaining) {
+		int err = xfrm_xlate64_attr(dst, nla);
+
+		if (err)
+			return err;
+	}
+
+	nlmsg_end(dst, nlh_dst);
+
+	return 0;
+}
+
+static int xfrm_alloc_compat(struct sk_buff *skb, const struct nlmsghdr *nlh_src)
+{
+	u16 type = nlh_src->nlmsg_type - XFRM_MSG_BASE;
+	struct sk_buff *new = NULL;
+	int err;
+
+	if (WARN_ON_ONCE(type >= ARRAY_SIZE(xfrm_msg_min)))
+		return -EOPNOTSUPP;
+
+	if (skb_shinfo(skb)->frag_list == NULL) {
+		new = alloc_skb(skb->len + skb_tailroom(skb), GFP_ATOMIC);
+		if (!new)
+			return -ENOMEM;
+		skb_shinfo(skb)->frag_list = new;
+	}
+
+	err = xfrm_xlate64(skb_shinfo(skb)->frag_list, nlh_src);
+	if (err) {
+		if (new) {
+			kfree_skb(new);
+			skb_shinfo(skb)->frag_list = NULL;
+		}
+		return err;
+	}
+
+	return 0;
+}
+
+/* Calculates len of translated 64-bit message. */
+static size_t xfrm_user_rcv_calculate_len64(const struct nlmsghdr *src,
+					    struct nlattr *attrs[XFRMA_MAX+1])
+{
+	size_t len = nlmsg_len(src);
+
+	switch (src->nlmsg_type) {
+	case XFRM_MSG_NEWSA:
+	case XFRM_MSG_NEWPOLICY:
+	case XFRM_MSG_ALLOCSPI:
+	case XFRM_MSG_ACQUIRE:
+	case XFRM_MSG_UPDPOLICY:
+	case XFRM_MSG_UPDSA:
+		len += 4;
+		break;
+	case XFRM_MSG_EXPIRE:
+	case XFRM_MSG_POLEXPIRE:
+		len += 8;
+		break;
+	default:
+		break;
+	}
+
+	if (attrs[XFRMA_SA])
+		len += 4;
+	if (attrs[XFRMA_POLICY])
+		len += 4;
+
+	/* XXX: some attrs may need to be realigned
+	 * if !CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+	 */
+
+	return len;
+}
+
+static int xfrm_attr_cpy32(void *dst, size_t *pos, const struct nlattr *src,
+			   size_t size, int copy_len, int payload)
+{
+	struct nlmsghdr *nlmsg = dst;
+	struct nlattr *nla;
+
+	if (WARN_ON_ONCE(copy_len > payload))
+		copy_len = payload;
+
+	if (size - *pos < nla_attr_size(payload))
+		return -ENOBUFS;
+
+	nla = dst + *pos;
+
+	memcpy(nla, src, nla_attr_size(copy_len));
+	nla->nla_len = nla_attr_size(payload);
+	*pos += nla_attr_size(payload);
+	nlmsg->nlmsg_len += nla->nla_len;
+
+	memset(dst + *pos, 0, payload - copy_len);
+	*pos += payload - copy_len;
+
+	return 0;
+}
+
+static int xfrm_xlate32_attr(void *dst, const struct nlattr *nla,
+			     size_t *pos, size_t size,
+			     struct netlink_ext_ack *extack)
+{
+	int type = nla_type(nla);
+	u16 pol_len32, pol_len64;
+	int err;
+
+	if (type > XFRMA_MAX) {
+		BUILD_BUG_ON(XFRMA_MAX != XFRMA_IF_ID);
+		NL_SET_ERR_MSG(extack, "Bad attribute");
+		return -EOPNOTSUPP;
+	}
+	if (nla_len(nla) < compat_policy[type].len) {
+		NL_SET_ERR_MSG(extack, "Attribute bad length");
+		return -EOPNOTSUPP;
+	}
+
+	pol_len32 = compat_policy[type].len;
+	pol_len64 = xfrma_policy[type].len;
+
+	/* XFRMA_SA and XFRMA_POLICY - need to know how-to translate */
+	if (pol_len32 != pol_len64) {
+		if (nla_len(nla) != compat_policy[type].len) {
+			NL_SET_ERR_MSG(extack, "Attribute bad length");
+			return -EOPNOTSUPP;
+		}
+		err = xfrm_attr_cpy32(dst, pos, nla, size, pol_len32, pol_len64);
+		if (err)
+			return err;
+	}
+
+	return xfrm_attr_cpy32(dst, pos, nla, size, nla_len(nla), nla_len(nla));
+}
+
+static int xfrm_xlate32(struct nlmsghdr *dst, const struct nlmsghdr *src,
+			struct nlattr *attrs[XFRMA_MAX+1],
+			size_t size, u8 type, struct netlink_ext_ack *extack)
+{
+	size_t pos;
+	int i;
+
+	memcpy(dst, src, NLMSG_HDRLEN);
+	dst->nlmsg_len = NLMSG_HDRLEN + xfrm_msg_min[type];
+	memset(nlmsg_data(dst), 0, xfrm_msg_min[type]);
+
+	switch (src->nlmsg_type) {
+	/* Compat message has the same layout as native */
+	case XFRM_MSG_DELSA:
+	case XFRM_MSG_GETSA:
+	case XFRM_MSG_DELPOLICY:
+	case XFRM_MSG_GETPOLICY:
+	case XFRM_MSG_FLUSHSA:
+	case XFRM_MSG_FLUSHPOLICY:
+	case XFRM_MSG_NEWAE:
+	case XFRM_MSG_GETAE:
+	case XFRM_MSG_REPORT:
+	case XFRM_MSG_MIGRATE:
+	case XFRM_MSG_NEWSADINFO:
+	case XFRM_MSG_GETSADINFO:
+	case XFRM_MSG_NEWSPDINFO:
+	case XFRM_MSG_GETSPDINFO:
+	case XFRM_MSG_MAPPING:
+		memcpy(nlmsg_data(dst), nlmsg_data(src), compat_msg_min[type]);
+		break;
+	/* 4 byte alignment for trailing u64 on native, but not on compat */
+	case XFRM_MSG_NEWSA:
+	case XFRM_MSG_NEWPOLICY:
+	case XFRM_MSG_UPDSA:
+	case XFRM_MSG_UPDPOLICY:
+		memcpy(nlmsg_data(dst), nlmsg_data(src), compat_msg_min[type]);
+		break;
+	case XFRM_MSG_EXPIRE: {
+		const struct compat_xfrm_user_expire *src_ue = nlmsg_data(src);
+		struct xfrm_user_expire *dst_ue = nlmsg_data(dst);
+
+		/* compat_xfrm_user_expire has 4-byte smaller state */
+		memcpy(dst_ue, src_ue, sizeof(src_ue->state));
+		dst_ue->hard = src_ue->hard;
+		break;
+	}
+	case XFRM_MSG_ACQUIRE: {
+		const struct compat_xfrm_user_acquire *src_ua = nlmsg_data(src);
+		struct xfrm_user_acquire *dst_ua = nlmsg_data(dst);
+
+		memcpy(dst_ua, src_ua, offsetof(struct compat_xfrm_user_acquire, aalgos));
+		dst_ua->aalgos = src_ua->aalgos;
+		dst_ua->ealgos = src_ua->ealgos;
+		dst_ua->calgos = src_ua->calgos;
+		dst_ua->seq    = src_ua->seq;
+		break;
+	}
+	case XFRM_MSG_POLEXPIRE: {
+		const struct compat_xfrm_user_polexpire *src_upe = nlmsg_data(src);
+		struct xfrm_user_polexpire *dst_upe = nlmsg_data(dst);
+
+		/* compat_xfrm_user_polexpire has 4-byte smaller state */
+		memcpy(dst_upe, src_upe, sizeof(src_upe->pol));
+		dst_upe->hard = src_upe->hard;
+		break;
+	}
+	case XFRM_MSG_ALLOCSPI: {
+		const struct compat_xfrm_userspi_info *src_usi = nlmsg_data(src);
+		struct xfrm_userspi_info *dst_usi = nlmsg_data(dst);
+
+		/* compat_xfrm_user_polexpire has 4-byte smaller state */
+		memcpy(dst_usi, src_usi, sizeof(src_usi->info));
+		dst_usi->min = src_usi->min;
+		dst_usi->max = src_usi->max;
+		break;
+	}
+	default:
+		NL_SET_ERR_MSG(extack, "Unsupported message type");
+		return -EOPNOTSUPP;
+	}
+	pos = dst->nlmsg_len;
+
+	for (i = 1; i < XFRMA_MAX + 1; i++) {
+		int err;
+
+		if (i == XFRMA_PAD)
+			continue;
+
+		if (!attrs[i])
+			continue;
+
+		err = xfrm_xlate32_attr(dst, attrs[i], &pos, size, extack);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static struct nlmsghdr *xfrm_user_rcv_msg_compat(const struct nlmsghdr *h32,
+			int maxtype, const struct nla_policy *policy,
+			struct netlink_ext_ack *extack)
+{
+	/* netlink_rcv_skb() checks if a message has full (struct nlmsghdr) */
+	u16 type = h32->nlmsg_type - XFRM_MSG_BASE;
+	struct nlattr *attrs[XFRMA_MAX+1];
+	struct nlmsghdr *h64;
+	size_t len;
+	int err;
+
+	BUILD_BUG_ON(ARRAY_SIZE(xfrm_msg_min) != ARRAY_SIZE(compat_msg_min));
+
+	if (type >= ARRAY_SIZE(xfrm_msg_min))
+		return ERR_PTR(-EINVAL);
+
+	/* Don't call parse: the message might have only nlmsg header */
+	if ((h32->nlmsg_type == XFRM_MSG_GETSA ||
+	     h32->nlmsg_type == XFRM_MSG_GETPOLICY) &&
+	    (h32->nlmsg_flags & NLM_F_DUMP))
+		return NULL;
+
+	err = nlmsg_parse_deprecated(h32, compat_msg_min[type], attrs,
+			maxtype ? : XFRMA_MAX, policy ? : compat_policy, extack);
+	if (err < 0)
+		return ERR_PTR(err);
+
+	len = xfrm_user_rcv_calculate_len64(h32, attrs);
+	/* The message doesn't need translation */
+	if (len == nlmsg_len(h32))
+		return NULL;
+
+	len += NLMSG_HDRLEN;
+	h64 = kvmalloc(len, GFP_KERNEL | __GFP_ZERO);
+	if (!h64)
+		return ERR_PTR(-ENOMEM);
+
+	err = xfrm_xlate32(h64, h32, attrs, len, type, extack);
+	if (err < 0) {
+		kvfree(h64);
+		return ERR_PTR(err);
+	}
+
+	return h64;
+}
+
+static int xfrm_user_policy_compat(u8 **pdata32, int optlen)
+{
+	struct compat_xfrm_userpolicy_info *p = (void *)*pdata32;
+	u8 *src_templates, *dst_templates;
+	u8 *data64;
+
+	if (optlen < sizeof(*p))
+		return -EINVAL;
+
+	data64 = kmalloc_track_caller(optlen + 4, GFP_USER | __GFP_NOWARN);
+	if (!data64)
+		return -ENOMEM;
+
+	memcpy(data64, *pdata32, sizeof(*p));
+	memset(data64 + sizeof(*p), 0, 4);
+
+	src_templates = *pdata32 + sizeof(*p);
+	dst_templates = data64 + sizeof(*p) + 4;
+	memcpy(dst_templates, src_templates, optlen - sizeof(*p));
+
+	kfree(*pdata32);
+	*pdata32 = data64;
+	return 0;
+}
+
+static struct xfrm_translator xfrm_translator = {
+	.owner				= THIS_MODULE,
+	.alloc_compat			= xfrm_alloc_compat,
+	.rcv_msg_compat			= xfrm_user_rcv_msg_compat,
+	.xlate_user_policy_sockptr	= xfrm_user_policy_compat,
+};
+
+static int __init xfrm_compat_init(void)
+{
+	return xfrm_register_translator(&xfrm_translator);
+}
+
+static void __exit xfrm_compat_exit(void)
+{
+	xfrm_unregister_translator(&xfrm_translator);
+}
+
+module_init(xfrm_compat_init);
+module_exit(xfrm_compat_exit);
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Dmitry Safonov");
+MODULE_DESCRIPTION("XFRM 32-bit compatibility layer");
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 69520ad3d83b..f9961884500b 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -2264,6 +2264,66 @@ static bool km_is_alive(const struct km_event *c)
 	return is_alive;
 }
 
+#if IS_ENABLED(CONFIG_XFRM_USER_COMPAT)
+static DEFINE_SPINLOCK(xfrm_translator_lock);
+static struct xfrm_translator __rcu *xfrm_translator;
+
+struct xfrm_translator *xfrm_get_translator(void)
+{
+	struct xfrm_translator *xtr;
+
+	rcu_read_lock();
+	xtr = rcu_dereference(xfrm_translator);
+	if (unlikely(!xtr))
+		goto out;
+	if (!try_module_get(xtr->owner))
+		xtr = NULL;
+out:
+	rcu_read_unlock();
+	return xtr;
+}
+EXPORT_SYMBOL_GPL(xfrm_get_translator);
+
+void xfrm_put_translator(struct xfrm_translator *xtr)
+{
+	module_put(xtr->owner);
+}
+EXPORT_SYMBOL_GPL(xfrm_put_translator);
+
+int xfrm_register_translator(struct xfrm_translator *xtr)
+{
+	int err = 0;
+
+	spin_lock_bh(&xfrm_translator_lock);
+	if (unlikely(xfrm_translator != NULL))
+		err = -EEXIST;
+	else
+		rcu_assign_pointer(xfrm_translator, xtr);
+	spin_unlock_bh(&xfrm_translator_lock);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(xfrm_register_translator);
+
+int xfrm_unregister_translator(struct xfrm_translator *xtr)
+{
+	int err = 0;
+
+	spin_lock_bh(&xfrm_translator_lock);
+	if (likely(xfrm_translator != NULL)) {
+		if (rcu_access_pointer(xfrm_translator) != xtr)
+			err = -EINVAL;
+		else
+			RCU_INIT_POINTER(xfrm_translator, NULL);
+	}
+	spin_unlock_bh(&xfrm_translator_lock);
+	synchronize_rcu();
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(xfrm_unregister_translator);
+#endif
+
 int xfrm_user_policy(struct sock *sk, int optname, sockptr_t optval, int optlen)
 {
 	int err;
@@ -2271,9 +2331,6 @@ int xfrm_user_policy(struct sock *sk, int optname, sockptr_t optval, int optlen)
 	struct xfrm_mgr *km;
 	struct xfrm_policy *pol = NULL;
 
-	if (in_compat_syscall())
-		return -EOPNOTSUPP;
-
 	if (sockptr_is_null(optval) && !optlen) {
 		xfrm_sk_policy_insert(sk, XFRM_POLICY_IN, NULL);
 		xfrm_sk_policy_insert(sk, XFRM_POLICY_OUT, NULL);
@@ -2288,6 +2345,20 @@ int xfrm_user_policy(struct sock *sk, int optname, sockptr_t optval, int optlen)
 	if (IS_ERR(data))
 		return PTR_ERR(data);
 
+	if (in_compat_syscall()) {
+		struct xfrm_translator *xtr = xfrm_get_translator();
+
+		if (!xtr)
+			return -EOPNOTSUPP;
+
+		err = xtr->xlate_user_policy_sockptr(&data, optlen);
+		xfrm_put_translator(xtr);
+		if (err) {
+			kfree(data);
+			return err;
+		}
+	}
+
 	err = -EINVAL;
 	rcu_read_lock();
 	list_for_each_entry_rcu(km, &xfrm_km_list, list) {
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index fbb7d9d06478..d0c32a8fcc4a 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -975,6 +975,7 @@ static int dump_one_state(struct xfrm_state *x, int count, void *ptr)
 	struct xfrm_dump_info *sp = ptr;
 	struct sk_buff *in_skb = sp->in_skb;
 	struct sk_buff *skb = sp->out_skb;
+	struct xfrm_translator *xtr;
 	struct xfrm_usersa_info *p;
 	struct nlmsghdr *nlh;
 	int err;
@@ -992,6 +993,18 @@ static int dump_one_state(struct xfrm_state *x, int count, void *ptr)
 		return err;
 	}
 	nlmsg_end(skb, nlh);
+
+	xtr = xfrm_get_translator();
+	if (xtr) {
+		err = xtr->alloc_compat(skb, nlh);
+
+		xfrm_put_translator(xtr);
+		if (err) {
+			nlmsg_cancel(skb, nlh);
+			return err;
+		}
+	}
+
 	return 0;
 }
 
@@ -1006,7 +1019,6 @@ static int xfrm_dump_sa_done(struct netlink_callback *cb)
 	return 0;
 }
 
-static const struct nla_policy xfrma_policy[XFRMA_MAX+1];
 static int xfrm_dump_sa(struct sk_buff *skb, struct netlink_callback *cb)
 {
 	struct net *net = sock_net(skb->sk);
@@ -1083,12 +1095,24 @@ static inline int xfrm_nlmsg_multicast(struct net *net, struct sk_buff *skb,
 				       u32 pid, unsigned int group)
 {
 	struct sock *nlsk = rcu_dereference(net->xfrm.nlsk);
+	struct xfrm_translator *xtr;
 
 	if (!nlsk) {
 		kfree_skb(skb);
 		return -EPIPE;
 	}
 
+	xtr = xfrm_get_translator();
+	if (xtr) {
+		int err = xtr->alloc_compat(skb, nlmsg_hdr(skb));
+
+		xfrm_put_translator(xtr);
+		if (err) {
+			kfree_skb(skb);
+			return err;
+		}
+	}
+
 	return nlmsg_multicast(nlsk, skb, pid, group, GFP_ATOMIC);
 }
 
@@ -1308,6 +1332,7 @@ static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh,
 	struct net *net = sock_net(skb->sk);
 	struct xfrm_state *x;
 	struct xfrm_userspi_info *p;
+	struct xfrm_translator *xtr;
 	struct sk_buff *resp_skb;
 	xfrm_address_t *daddr;
 	int family;
@@ -1358,6 +1383,17 @@ static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh,
 		goto out;
 	}
 
+	xtr = xfrm_get_translator();
+	if (xtr) {
+		err = xtr->alloc_compat(skb, nlmsg_hdr(skb));
+
+		xfrm_put_translator(xtr);
+		if (err) {
+			kfree_skb(resp_skb);
+			goto out;
+		}
+	}
+
 	err = nlmsg_unicast(net->xfrm.nlsk, resp_skb, NETLINK_CB(skb).portid);
 
 out:
@@ -1764,6 +1800,7 @@ static int dump_one_policy(struct xfrm_policy *xp, int dir, int count, void *ptr
 	struct xfrm_userpolicy_info *p;
 	struct sk_buff *in_skb = sp->in_skb;
 	struct sk_buff *skb = sp->out_skb;
+	struct xfrm_translator *xtr;
 	struct nlmsghdr *nlh;
 	int err;
 
@@ -1788,6 +1825,18 @@ static int dump_one_policy(struct xfrm_policy *xp, int dir, int count, void *ptr
 		return err;
 	}
 	nlmsg_end(skb, nlh);
+
+	xtr = xfrm_get_translator();
+	if (xtr) {
+		err = xtr->alloc_compat(skb, nlh);
+
+		xfrm_put_translator(xtr);
+		if (err) {
+			nlmsg_cancel(skb, nlh);
+			return err;
+		}
+	}
+
 	return 0;
 }
 
@@ -2533,7 +2582,7 @@ static int xfrm_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 
 #define XMSGSIZE(type) sizeof(struct type)
 
-static const int xfrm_msg_min[XFRM_NR_MSGTYPES] = {
+const int xfrm_msg_min[XFRM_NR_MSGTYPES] = {
 	[XFRM_MSG_NEWSA       - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_info),
 	[XFRM_MSG_DELSA       - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_id),
 	[XFRM_MSG_GETSA       - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_id),
@@ -2556,10 +2605,11 @@ static const int xfrm_msg_min[XFRM_NR_MSGTYPES] = {
 	[XFRM_MSG_NEWSPDINFO  - XFRM_MSG_BASE] = sizeof(u32),
 	[XFRM_MSG_GETSPDINFO  - XFRM_MSG_BASE] = sizeof(u32),
 };
+EXPORT_SYMBOL_GPL(xfrm_msg_min);
 
 #undef XMSGSIZE
 
-static const struct nla_policy xfrma_policy[XFRMA_MAX+1] = {
+const struct nla_policy xfrma_policy[XFRMA_MAX+1] = {
 	[XFRMA_SA]		= { .len = sizeof(struct xfrm_usersa_info)},
 	[XFRMA_POLICY]		= { .len = sizeof(struct xfrm_userpolicy_info)},
 	[XFRMA_LASTUSED]	= { .type = NLA_U64},
@@ -2591,6 +2641,7 @@ static const struct nla_policy xfrma_policy[XFRMA_MAX+1] = {
 	[XFRMA_SET_MARK_MASK]	= { .type = NLA_U32 },
 	[XFRMA_IF_ID]		= { .type = NLA_U32 },
 };
+EXPORT_SYMBOL_GPL(xfrma_policy);
 
 static const struct nla_policy xfrma_spd_policy[XFRMA_SPD_MAX+1] = {
 	[XFRMA_SPD_IPV4_HTHRESH] = { .len = sizeof(struct xfrmu_spdhthresh) },
@@ -2640,11 +2691,9 @@ static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 	struct net *net = sock_net(skb->sk);
 	struct nlattr *attrs[XFRMA_MAX+1];
 	const struct xfrm_link *link;
+	struct nlmsghdr *nlh64 = NULL;
 	int type, err;
 
-	if (in_compat_syscall())
-		return -EOPNOTSUPP;
-
 	type = nlh->nlmsg_type;
 	if (type > XFRM_MSG_MAX)
 		return -EINVAL;
@@ -2656,32 +2705,55 @@ static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (!netlink_net_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
+	if (in_compat_syscall()) {
+		struct xfrm_translator *xtr = xfrm_get_translator();
+
+		if (!xtr)
+			return -EOPNOTSUPP;
+
+		nlh64 = xtr->rcv_msg_compat(nlh, link->nla_max,
+					    link->nla_pol, extack);
+		xfrm_put_translator(xtr);
+		if (IS_ERR(nlh64))
+			return PTR_ERR(nlh64);
+		if (nlh64)
+			nlh = nlh64;
+	}
+
 	if ((type == (XFRM_MSG_GETSA - XFRM_MSG_BASE) ||
 	     type == (XFRM_MSG_GETPOLICY - XFRM_MSG_BASE)) &&
 	    (nlh->nlmsg_flags & NLM_F_DUMP)) {
-		if (link->dump == NULL)
-			return -EINVAL;
+		struct netlink_dump_control c = {
+			.start = link->start,
+			.dump = link->dump,
+			.done = link->done,
+		};
 
-		{
-			struct netlink_dump_control c = {
-				.start = link->start,
-				.dump = link->dump,
-				.done = link->done,
-			};
-			return netlink_dump_start(net->xfrm.nlsk, skb, nlh, &c);
+		if (link->dump == NULL) {
+			err = -EINVAL;
+			goto err;
 		}
+
+		err = netlink_dump_start(net->xfrm.nlsk, skb, nlh, &c);
+		goto err;
 	}
 
 	err = nlmsg_parse_deprecated(nlh, xfrm_msg_min[type], attrs,
 				     link->nla_max ? : XFRMA_MAX,
 				     link->nla_pol ? : xfrma_policy, extack);
 	if (err < 0)
-		return err;
+		goto err;
 
-	if (link->doit == NULL)
-		return -EINVAL;
+	if (link->doit == NULL) {
+		err = -EINVAL;
+		goto err;
+	}
 
-	return link->doit(skb, nlh, attrs);
+	err = link->doit(skb, nlh, attrs);
+
+err:
+	kvfree(nlh64);
+	return err;
 }
 
 static void xfrm_netlink_rcv(struct sk_buff *skb)
diff --git a/samples/bpf/.gitignore b/samples/bpf/.gitignore
index 034800c4d1e6..b2f29bc8dc43 100644
--- a/samples/bpf/.gitignore
+++ b/samples/bpf/.gitignore
@@ -50,4 +50,5 @@ xdp_rxq_info
 xdp_sample_pkts
 xdp_tx_iptunnel
 xdpsock
+xsk_fwd
 testfile.img
diff --git a/samples/bpf/sockex3_kern.c b/samples/bpf/sockex3_kern.c
index cab9cca0b8eb..8142d02b33e6 100644
--- a/samples/bpf/sockex3_kern.c
+++ b/samples/bpf/sockex3_kern.c
@@ -31,28 +31,30 @@ struct {
 #define PARSE_IP 3
 #define PARSE_IPV6 4
 
-/* protocol dispatch routine.
- * It tail-calls next BPF program depending on eth proto
- * Note, we could have used:
- * bpf_tail_call(skb, &jmp_table, proto);
- * but it would need large prog_array
+/* Protocol dispatch routine. It tail-calls next BPF program depending
+ * on eth proto. Note, we could have used ...
+ *
+ *   bpf_tail_call(skb, &jmp_table, proto);
+ *
+ * ... but it would need large prog_array and cannot be optimised given
+ * the map key is not static.
  */
 static inline void parse_eth_proto(struct __sk_buff *skb, u32 proto)
 {
 	switch (proto) {
 	case ETH_P_8021Q:
 	case ETH_P_8021AD:
-		bpf_tail_call(skb, &jmp_table, PARSE_VLAN);
+		bpf_tail_call_static(skb, &jmp_table, PARSE_VLAN);
 		break;
 	case ETH_P_MPLS_UC:
 	case ETH_P_MPLS_MC:
-		bpf_tail_call(skb, &jmp_table, PARSE_MPLS);
+		bpf_tail_call_static(skb, &jmp_table, PARSE_MPLS);
 		break;
 	case ETH_P_IP:
-		bpf_tail_call(skb, &jmp_table, PARSE_IP);
+		bpf_tail_call_static(skb, &jmp_table, PARSE_IP);
 		break;
 	case ETH_P_IPV6:
-		bpf_tail_call(skb, &jmp_table, PARSE_IPV6);
+		bpf_tail_call_static(skb, &jmp_table, PARSE_IPV6);
 		break;
 	}
 }
diff --git a/samples/bpf/sockex3_user.c b/samples/bpf/sockex3_user.c
index 4dbee7427d47..7793f6a6ae7e 100644
--- a/samples/bpf/sockex3_user.c
+++ b/samples/bpf/sockex3_user.c
@@ -29,8 +29,8 @@ int main(int argc, char **argv)
 	struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
 	struct bpf_program *prog;
 	struct bpf_object *obj;
+	const char *section;
 	char filename[256];
-	const char *title;
 	FILE *f;
 
 	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
@@ -58,8 +58,8 @@ int main(int argc, char **argv)
 	bpf_object__for_each_program(prog, obj) {
 		fd = bpf_program__fd(prog);
 
-		title = bpf_program__title(prog, false);
-		if (sscanf(title, "socket/%d", &key) != 1) {
+		section = bpf_program__section_name(prog);
+		if (sscanf(section, "socket/%d", &key) != 1) {
 			fprintf(stderr, "ERROR: finding prog failed\n");
 			goto cleanup;
 		}
diff --git a/samples/bpf/spintest_user.c b/samples/bpf/spintest_user.c
index 847da9284fa8..f090d0dc60d6 100644
--- a/samples/bpf/spintest_user.c
+++ b/samples/bpf/spintest_user.c
@@ -17,7 +17,7 @@ int main(int ac, char **argv)
 	long key, next_key, value;
 	struct bpf_program *prog;
 	int map_fd, i, j = 0;
-	const char *title;
+	const char *section;
 	struct ksym *sym;
 
 	if (setrlimit(RLIMIT_MEMLOCK, &r)) {
@@ -51,8 +51,8 @@ int main(int ac, char **argv)
 	}
 
 	bpf_object__for_each_program(prog, obj) {
-		title = bpf_program__title(prog, false);
-		if (sscanf(title, "kprobe/%s", symbol) != 1)
+		section = bpf_program__section_name(prog);
+		if (sscanf(section, "kprobe/%s", symbol) != 1)
 			continue;
 
 		/* Attach prog only when symbol exists */
diff --git a/samples/bpf/test_map_in_map_kern.c b/samples/bpf/test_map_in_map_kern.c
index 8def45c5b697..b0200c8eac09 100644
--- a/samples/bpf/test_map_in_map_kern.c
+++ b/samples/bpf/test_map_in_map_kern.c
@@ -103,10 +103,9 @@ static __always_inline int do_inline_hash_lookup(void *inner_map, u32 port)
 	return result ? *result : -ENOENT;
 }
 
-SEC("kprobe/" SYSCALL(sys_connect))
+SEC("kprobe/__sys_connect")
 int trace_sys_connect(struct pt_regs *ctx)
 {
-	struct pt_regs *real_regs = (struct pt_regs *)PT_REGS_PARM1_CORE(ctx);
 	struct sockaddr_in6 *in6;
 	u16 test_case, port, dst6[8];
 	int addrlen, ret, inline_ret, ret_key = 0;
@@ -114,8 +113,8 @@ int trace_sys_connect(struct pt_regs *ctx)
 	void *outer_map, *inner_map;
 	bool inline_hash = false;
 
-	in6 = (struct sockaddr_in6 *)PT_REGS_PARM2_CORE(real_regs);
-	addrlen = (int)PT_REGS_PARM3_CORE(real_regs);
+	in6 = (struct sockaddr_in6 *)PT_REGS_PARM2_CORE(ctx);
+	addrlen = (int)PT_REGS_PARM3_CORE(ctx);
 
 	if (addrlen != sizeof(*in6))
 		return 0;
diff --git a/samples/bpf/tracex5_user.c b/samples/bpf/tracex5_user.c
index 98dad57a96c4..c17d3fb5fd64 100644
--- a/samples/bpf/tracex5_user.c
+++ b/samples/bpf/tracex5_user.c
@@ -39,8 +39,8 @@ int main(int ac, char **argv)
 	struct bpf_program *prog;
 	struct bpf_object *obj;
 	int key, fd, progs_fd;
+	const char *section;
 	char filename[256];
-	const char *title;
 	FILE *f;
 
 	setrlimit(RLIMIT_MEMLOCK, &r);
@@ -78,9 +78,9 @@ int main(int ac, char **argv)
 	}
 
 	bpf_object__for_each_program(prog, obj) {
-		title = bpf_program__title(prog, false);
+		section = bpf_program__section_name(prog);
 		/* register only syscalls to PROG_ARRAY */
-		if (sscanf(title, "kprobe/%d", &key) != 1)
+		if (sscanf(section, "kprobe/%d", &key) != 1)
 			continue;
 
 		fd = bpf_program__fd(prog);
diff --git a/samples/bpf/xdp_redirect_cpu_user.c b/samples/bpf/xdp_redirect_cpu_user.c
index 004c0622c913..3dd366e9474d 100644
--- a/samples/bpf/xdp_redirect_cpu_user.c
+++ b/samples/bpf/xdp_redirect_cpu_user.c
@@ -111,7 +111,7 @@ static void print_avail_progs(struct bpf_object *obj)
 
 	bpf_object__for_each_program(pos, obj) {
 		if (bpf_program__is_xdp(pos))
-			printf(" %s\n", bpf_program__title(pos, false));
+			printf(" %s\n", bpf_program__section_name(pos));
 	}
 }
 
diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c
index 4cead341ae57..b220173dbe1e 100644
--- a/samples/bpf/xdpsock_user.c
+++ b/samples/bpf/xdpsock_user.c
@@ -78,6 +78,7 @@ static int opt_pkt_count;
 static u16 opt_pkt_size = MIN_PKT_SIZE;
 static u32 opt_pkt_fill_pattern = 0x12345678;
 static bool opt_extra_stats;
+static bool opt_quiet;
 static int opt_poll;
 static int opt_interval = 1;
 static u32 opt_xdp_bind_flags = XDP_USE_NEED_WAKEUP;
@@ -718,6 +719,7 @@ static struct option long_options[] = {
 	{"tx-pkt-size", required_argument, 0, 's'},
 	{"tx-pkt-pattern", required_argument, 0, 'P'},
 	{"extra-stats", no_argument, 0, 'x'},
+	{"quiet", no_argument, 0, 'Q'},
 	{0, 0, 0, 0}
 };
 
@@ -753,6 +755,7 @@ static void usage(const char *prog)
 		"			Min size: %d, Max size %d.\n"
 		"  -P, --tx-pkt-pattern=nPacket fill pattern. Default: 0x%x\n"
 		"  -x, --extra-stats	Display extra statistics.\n"
+		"  -Q, --quiet          Do not display any stats.\n"
 		"\n";
 	fprintf(stderr, str, prog, XSK_UMEM__DEFAULT_FRAME_SIZE,
 		opt_batch_size, MIN_PKT_SIZE, MIN_PKT_SIZE,
@@ -768,7 +771,7 @@ static void parse_command_line(int argc, char **argv)
 	opterr = 0;
 
 	for (;;) {
-		c = getopt_long(argc, argv, "Frtli:q:pSNn:czf:muMd:b:C:s:P:x",
+		c = getopt_long(argc, argv, "Frtli:q:pSNn:czf:muMd:b:C:s:P:xQ",
 				long_options, &option_index);
 		if (c == -1)
 			break;
@@ -852,6 +855,9 @@ static void parse_command_line(int argc, char **argv)
 		case 'x':
 			opt_extra_stats = 1;
 			break;
+		case 'Q':
+			opt_quiet = 1;
+			break;
 		default:
 			usage(basename(argv[0]));
 		}
@@ -897,6 +903,14 @@ static inline void complete_tx_l2fwd(struct xsk_socket_info *xsk,
 	if (!xsk->outstanding_tx)
 		return;
 
+	/* In copy mode, Tx is driven by a syscall so we need to use e.g. sendto() to
+	 * really send the packets. In zero-copy mode we do not have to do this, since Tx
+	 * is driven by the NAPI loop. So as an optimization, we do not have to call
+	 * sendto() all the time in zero-copy mode for l2fwd.
+	 */
+	if (opt_xdp_bind_flags & XDP_COPY)
+		kick_tx(xsk);
+
 	ndescs = (xsk->outstanding_tx > opt_batch_size) ? opt_batch_size :
 		xsk->outstanding_tx;
 
@@ -1117,6 +1131,7 @@ static void l2fwd(struct xsk_socket_info *xsk, struct pollfd *fds)
 	while (ret != rcvd) {
 		if (ret < 0)
 			exit_with_error(-ret);
+		complete_tx_l2fwd(xsk, fds);
 		if (xsk_ring_prod__needs_wakeup(&xsk->tx))
 			kick_tx(xsk);
 		ret = xsk_ring_prod__reserve(&xsk->tx, rcvd, &idx_tx);
@@ -1277,9 +1292,11 @@ int main(int argc, char **argv)
 
 	setlocale(LC_ALL, "");
 
-	ret = pthread_create(&pt, NULL, poller, NULL);
-	if (ret)
-		exit_with_error(ret);
+	if (!opt_quiet) {
+		ret = pthread_create(&pt, NULL, poller, NULL);
+		if (ret)
+			exit_with_error(ret);
+	}
 
 	prev_time = get_nsecs();
 	start_time = prev_time;
@@ -1293,7 +1310,8 @@ int main(int argc, char **argv)
 
 	benchmark_done = true;
 
-	pthread_join(pt, NULL);
+	if (!opt_quiet)
+		pthread_join(pt, NULL);
 
 	xdpsock_cleanup();
 
diff --git a/scripts/bpf_helpers_doc.py b/scripts/bpf_helpers_doc.py
index 08388173973f..7d86fdd190be 100755
--- a/scripts/bpf_helpers_doc.py
+++ b/scripts/bpf_helpers_doc.py
@@ -433,6 +433,7 @@ class PrinterHelpers(Printer):
             'struct sk_msg_md',
             'struct xdp_md',
             'struct path',
+            'struct btf_ptr',
     ]
     known_types = {
             '...',
@@ -474,6 +475,7 @@ class PrinterHelpers(Printer):
             'struct udp6_sock',
             'struct task_struct',
             'struct path',
+            'struct btf_ptr',
     }
     mapped_types = {
             'u8': '__u8',
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index 60d4a79674b6..504d2e431c60 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -2639,8 +2639,8 @@ sub process {
 
 # Check if the commit log has what seems like a diff which can confuse patch
 		if ($in_commit_log && !$commit_log_has_diff &&
-		    (($line =~ m@^\s+diff\b.*a/[\w/]+@ &&
-		      $line =~ m@^\s+diff\b.*a/([\w/]+)\s+b/$1\b@) ||
+		    (($line =~ m@^\s+diff\b.*a/([\w/]+)@ &&
+		      $line =~ m@^\s+diff\b.*a/[\w/]+\s+b/$1\b@) ||
 		     $line =~ m@^\s*(?:\-\-\-\s+a/|\+\+\+\s+b/)@ ||
 		     $line =~ m/^\s*\@\@ \-\d+,\d+ \+\d+,\d+ \@\@/)) {
 			ERROR("DIFF_IN_COMMIT_MSG",
diff --git a/scripts/kconfig/lkc.h b/scripts/kconfig/lkc.h
index d4ca8297364f..8454649b17bd 100644
--- a/scripts/kconfig/lkc.h
+++ b/scripts/kconfig/lkc.h
@@ -66,23 +66,6 @@ static inline void xfwrite(const void *str, size_t len, size_t count, FILE *out)
 		fprintf(stderr, "Error in writing or end of file.\n");
 }
 
-/* menu.c */
-void _menu_init(void);
-void menu_warn(struct menu *menu, const char *fmt, ...);
-struct menu *menu_add_menu(void);
-void menu_end_menu(void);
-void menu_add_entry(struct symbol *sym);
-void menu_add_dep(struct expr *dep);
-void menu_add_visibility(struct expr *dep);
-struct property *menu_add_prompt(enum prop_type type, char *prompt, struct expr *dep);
-void menu_add_expr(enum prop_type type, struct expr *expr, struct expr *dep);
-void menu_add_symbol(enum prop_type type, struct symbol *sym, struct expr *dep);
-void menu_add_option_modules(void);
-void menu_add_option_defconfig_list(void);
-void menu_add_option_allnoconfig_y(void);
-void menu_finalize(struct menu *parent);
-void menu_set_type(int type);
-
 /* util.c */
 struct file *file_lookup(const char *name);
 void *xmalloc(size_t size);
@@ -109,6 +92,36 @@ void str_append(struct gstr *gs, const char *s);
 void str_printf(struct gstr *gs, const char *fmt, ...);
 const char *str_get(struct gstr *gs);
 
+/* menu.c */
+void _menu_init(void);
+void menu_warn(struct menu *menu, const char *fmt, ...);
+struct menu *menu_add_menu(void);
+void menu_end_menu(void);
+void menu_add_entry(struct symbol *sym);
+void menu_add_dep(struct expr *dep);
+void menu_add_visibility(struct expr *dep);
+struct property *menu_add_prompt(enum prop_type type, char *prompt, struct expr *dep);
+void menu_add_expr(enum prop_type type, struct expr *expr, struct expr *dep);
+void menu_add_symbol(enum prop_type type, struct symbol *sym, struct expr *dep);
+void menu_add_option_modules(void);
+void menu_add_option_defconfig_list(void);
+void menu_add_option_allnoconfig_y(void);
+void menu_finalize(struct menu *parent);
+void menu_set_type(int type);
+
+extern struct menu rootmenu;
+
+bool menu_is_empty(struct menu *menu);
+bool menu_is_visible(struct menu *menu);
+bool menu_has_prompt(struct menu *menu);
+const char *menu_get_prompt(struct menu *menu);
+struct menu *menu_get_root_menu(struct menu *menu);
+struct menu *menu_get_parent_menu(struct menu *menu);
+bool menu_has_help(struct menu *menu);
+const char *menu_get_help(struct menu *menu);
+struct gstr get_relations_str(struct symbol **sym_arr, struct list_head *head);
+void menu_get_ext_help(struct menu *menu, struct gstr *help);
+
 /* symbol.c */
 void sym_clear_all_valid(void);
 struct symbol *sym_choice_default(struct symbol *sym);
diff --git a/scripts/kconfig/lkc_proto.h b/scripts/kconfig/lkc_proto.h
index f9ab98238aef..9e81be33c40f 100644
--- a/scripts/kconfig/lkc_proto.h
+++ b/scripts/kconfig/lkc_proto.h
@@ -12,20 +12,6 @@ bool conf_get_changed(void);
 void conf_set_changed_callback(void (*fn)(void));
 void conf_set_message_callback(void (*fn)(const char *s));
 
-/* menu.c */
-extern struct menu rootmenu;
-
-bool menu_is_empty(struct menu *menu);
-bool menu_is_visible(struct menu *menu);
-bool menu_has_prompt(struct menu *menu);
-const char * menu_get_prompt(struct menu *menu);
-struct menu * menu_get_root_menu(struct menu *menu);
-struct menu * menu_get_parent_menu(struct menu *menu);
-bool menu_has_help(struct menu *menu);
-const char * menu_get_help(struct menu *menu);
-struct gstr get_relations_str(struct symbol **sym_arr, struct list_head *head);
-void menu_get_ext_help(struct menu *menu, struct gstr *help);
-
 /* symbol.c */
 extern struct symbol * symbol_hash[SYMBOL_HASHSIZE];
 
diff --git a/scripts/kconfig/qconf.cc b/scripts/kconfig/qconf.cc
index 8638785328a7..8ce624a3b54b 100644
--- a/scripts/kconfig/qconf.cc
+++ b/scripts/kconfig/qconf.cc
@@ -1108,6 +1108,11 @@ void ConfigInfoView::menuInfo(void)
 		if (showDebug())
 			stream << debug_info(sym);
 
+		struct gstr help_gstr = str_new();
+
+		menu_get_ext_help(_menu, &help_gstr);
+		stream << print_filter(str_get(&help_gstr));
+		str_free(&help_gstr);
 	} else if (_menu->prompt) {
 		stream << "<big><b>";
 		stream << print_filter(_menu->prompt->text);
@@ -1119,11 +1124,11 @@ void ConfigInfoView::menuInfo(void)
 					   expr_print_help, &stream, E_NONE);
 				stream << "<br><br>";
 			}
+
+			stream << "defined at " << _menu->file->name << ":"
+			       << _menu->lineno << "<br><br>";
 		}
 	}
-	if (showDebug())
-		stream << "defined at " << _menu->file->name << ":"
-		       << _menu->lineno << "<br><br>";
 
 	setText(info);
 }
@@ -1276,7 +1281,7 @@ void ConfigInfoView::clicked(const QUrl &url)
 	}
 
 	free(result);
-	delete data;
+	delete[] data;
 }
 
 void ConfigInfoView::contextMenuEvent(QContextMenuEvent *event)
diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh
index e6e2d9e5ff48..dbde59d343b1 100755
--- a/scripts/link-vmlinux.sh
+++ b/scripts/link-vmlinux.sh
@@ -341,9 +341,9 @@ fi
 vmlinux_link vmlinux "${kallsymso}" ${btf_vmlinux_bin_o}
 
 # fill in BTF IDs
-if [ -n "${CONFIG_DEBUG_INFO_BTF}" ]; then
-info BTFIDS vmlinux
-${RESOLVE_BTFIDS} vmlinux
+if [ -n "${CONFIG_DEBUG_INFO_BTF}" -a -n "${CONFIG_BPF}" ]; then
+	info BTFIDS vmlinux
+	${RESOLVE_BTFIDS} vmlinux
 fi
 
 if [ -n "${CONFIG_BUILDTIME_TABLE_SORT}" ]; then
diff --git a/scripts/tags.sh b/scripts/tags.sh
index 32d3f53af10b..850f4ccb6afc 100755
--- a/scripts/tags.sh
+++ b/scripts/tags.sh
@@ -26,7 +26,11 @@ else
 fi
 
 # ignore userspace tools
-ignore="$ignore ( -path ${tree}tools ) -prune -o"
+if [ -n "$COMPILED_SOURCE" ]; then
+	ignore="$ignore ( -path ./tools ) -prune -o"
+else
+	ignore="$ignore ( -path ${tree}tools ) -prune -o"
+fi
 
 # Detect if ALLSOURCE_ARCHS is set. If not, we assume SRCARCH
 if [ "${ALLSOURCE_ARCHS}" = "" ]; then
@@ -92,7 +96,7 @@ all_sources()
 all_compiled_sources()
 {
 	realpath -es $([ -z "$KBUILD_ABS_SRCTREE" ] && echo --relative-to=.) \
-		include/generated/autoconf.h $(find -name "*.cmd" -exec \
+		include/generated/autoconf.h $(find $ignore -name "*.cmd" -exec \
 		grep -Poh '(?(?=^source_.* \K).*|(?=^  \K\S).*(?= \\))' {} \+ |
 		awk '!a[$0]++') | sort -u
 }
diff --git a/security/device_cgroup.c b/security/device_cgroup.c
index 43ab0ad45c1b..04375df52fc9 100644
--- a/security/device_cgroup.c
+++ b/security/device_cgroup.c
@@ -354,7 +354,8 @@ static bool match_exception_partial(struct list_head *exceptions, short type,
 {
 	struct dev_exception_item *ex;
 
-	list_for_each_entry_rcu(ex, exceptions, list) {
+	list_for_each_entry_rcu(ex, exceptions, list,
+				lockdep_is_held(&devcgroup_mutex)) {
 		if ((type & DEVCG_DEV_BLOCK) && !(ex->type & DEVCG_DEV_BLOCK))
 			continue;
 		if ((type & DEVCG_DEV_CHAR) && !(ex->type & DEVCG_DEV_CHAR))
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index c521a1f17096..85e207173f5d 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -5993,6 +5993,40 @@ static void alc_fixup_disable_mic_vref(struct hda_codec *codec,
 		snd_hda_codec_set_pin_target(codec, 0x19, PIN_VREFHIZ);
 }
 
+
+static void alc294_gx502_toggle_output(struct hda_codec *codec,
+					struct hda_jack_callback *cb)
+{
+	/* The Windows driver sets the codec up in a very different way where
+	 * it appears to leave 0x10 = 0x8a20 set. For Linux we need to toggle it
+	 */
+	if (snd_hda_jack_detect_state(codec, 0x21) == HDA_JACK_PRESENT)
+		alc_write_coef_idx(codec, 0x10, 0x8a20);
+	else
+		alc_write_coef_idx(codec, 0x10, 0x0a20);
+}
+
+static void alc294_fixup_gx502_hp(struct hda_codec *codec,
+					const struct hda_fixup *fix, int action)
+{
+	/* Pin 0x21: headphones/headset mic */
+	if (!is_jack_detectable(codec, 0x21))
+		return;
+
+	switch (action) {
+	case HDA_FIXUP_ACT_PRE_PROBE:
+		snd_hda_jack_detect_enable_callback(codec, 0x21,
+				alc294_gx502_toggle_output);
+		break;
+	case HDA_FIXUP_ACT_INIT:
+		/* Make sure to start in a correct state, i.e. if
+		 * headphones have been plugged in before powering up the system
+		 */
+		alc294_gx502_toggle_output(codec, NULL);
+		break;
+	}
+}
+
 static void  alc285_fixup_hp_gpio_amp_init(struct hda_codec *codec,
 			      const struct hda_fixup *fix, int action)
 {
@@ -6173,6 +6207,9 @@ enum {
 	ALC285_FIXUP_THINKPAD_HEADSET_JACK,
 	ALC294_FIXUP_ASUS_HPE,
 	ALC294_FIXUP_ASUS_COEF_1B,
+	ALC294_FIXUP_ASUS_GX502_HP,
+	ALC294_FIXUP_ASUS_GX502_PINS,
+	ALC294_FIXUP_ASUS_GX502_VERBS,
 	ALC285_FIXUP_HP_GPIO_LED,
 	ALC285_FIXUP_HP_MUTE_LED,
 	ALC236_FIXUP_HP_MUTE_LED,
@@ -6191,6 +6228,7 @@ enum {
 	ALC269_FIXUP_LEMOTE_A1802,
 	ALC269_FIXUP_LEMOTE_A190X,
 	ALC256_FIXUP_INTEL_NUC8_RUGGED,
+	ALC255_FIXUP_XIAOMI_HEADSET_MIC,
 };
 
 static const struct hda_fixup alc269_fixups[] = {
@@ -7338,6 +7376,33 @@ static const struct hda_fixup alc269_fixups[] = {
 		.chained = true,
 		.chain_id = ALC294_FIXUP_ASUS_HEADSET_MIC
 	},
+	[ALC294_FIXUP_ASUS_GX502_PINS] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x19, 0x03a11050 }, /* front HP mic */
+			{ 0x1a, 0x01a11830 }, /* rear external mic */
+			{ 0x21, 0x03211020 }, /* front HP out */
+			{ }
+		},
+		.chained = true,
+		.chain_id = ALC294_FIXUP_ASUS_GX502_VERBS
+	},
+	[ALC294_FIXUP_ASUS_GX502_VERBS] = {
+		.type = HDA_FIXUP_VERBS,
+		.v.verbs = (const struct hda_verb[]) {
+			/* set 0x15 to HP-OUT ctrl */
+			{ 0x15, AC_VERB_SET_PIN_WIDGET_CONTROL, 0xc0 },
+			/* unmute the 0x15 amp */
+			{ 0x15, AC_VERB_SET_AMP_GAIN_MUTE, 0xb000 },
+			{ }
+		},
+		.chained = true,
+		.chain_id = ALC294_FIXUP_ASUS_GX502_HP
+	},
+	[ALC294_FIXUP_ASUS_GX502_HP] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc294_fixup_gx502_hp,
+	},
 	[ALC294_FIXUP_ASUS_COEF_1B] = {
 		.type = HDA_FIXUP_VERBS,
 		.v.verbs = (const struct hda_verb[]) {
@@ -7527,6 +7592,16 @@ static const struct hda_fixup alc269_fixups[] = {
 		.chained = true,
 		.chain_id = ALC269_FIXUP_HEADSET_MODE
 	},
+	[ALC255_FIXUP_XIAOMI_HEADSET_MIC] = {
+		.type = HDA_FIXUP_VERBS,
+		.v.verbs = (const struct hda_verb[]) {
+			{ 0x20, AC_VERB_SET_COEF_INDEX, 0x45 },
+			{ 0x20, AC_VERB_SET_PROC_COEF, 0x5089 },
+			{ }
+		},
+		.chained = true,
+		.chain_id = ALC289_FIXUP_ASUS_GA401
+	},
 };
 
 static const struct snd_pci_quirk alc269_fixup_tbl[] = {
@@ -7711,6 +7786,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x1ccd, "ASUS X555UB", ALC256_FIXUP_ASUS_MIC),
 	SND_PCI_QUIRK(0x1043, 0x1e11, "ASUS Zephyrus G15", ALC289_FIXUP_ASUS_GA502),
 	SND_PCI_QUIRK(0x1043, 0x1f11, "ASUS Zephyrus G14", ALC289_FIXUP_ASUS_GA401),
+	SND_PCI_QUIRK(0x1043, 0x1881, "ASUS Zephyrus S/M", ALC294_FIXUP_ASUS_GX502_PINS),
 	SND_PCI_QUIRK(0x1043, 0x3030, "ASUS ZN270IE", ALC256_FIXUP_ASUS_AIO_GPIO2),
 	SND_PCI_QUIRK(0x1043, 0x831a, "ASUS P901", ALC269_FIXUP_STEREO_DMIC),
 	SND_PCI_QUIRK(0x1043, 0x834a, "ASUS S101", ALC269_FIXUP_STEREO_DMIC),
@@ -7823,6 +7899,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1b35, 0x1236, "CZC TMI", ALC269_FIXUP_CZC_TMI),
 	SND_PCI_QUIRK(0x1b35, 0x1237, "CZC L101", ALC269_FIXUP_CZC_L101),
 	SND_PCI_QUIRK(0x1b7d, 0xa831, "Ordissimo EVE2 ", ALC269VB_FIXUP_ORDISSIMO_EVE2), /* Also known as Malata PC-B1303 */
+	SND_PCI_QUIRK(0x1d72, 0x1602, "RedmiBook", ALC255_FIXUP_XIAOMI_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1d72, 0x1901, "RedmiBook 14", ALC256_FIXUP_ASUS_HEADSET_MIC),
 	SND_PCI_QUIRK(0x10ec, 0x118c, "Medion EE4254 MD62100", ALC256_FIXUP_MEDION_HEADSET_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1c06, 0x2013, "Lemote A1802", ALC269_FIXUP_LEMOTE_A1802),
@@ -8000,6 +8077,7 @@ static const struct hda_model_fixup alc269_fixup_models[] = {
 	{.id = ALC298_FIXUP_HUAWEI_MBX_STEREO, .name = "huawei-mbx-stereo"},
 	{.id = ALC256_FIXUP_MEDION_HEADSET_NO_PRESENCE, .name = "alc256-medion-headset"},
 	{.id = ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET, .name = "alc298-samsung-headphone"},
+	{.id = ALC255_FIXUP_XIAOMI_HEADSET_MIC, .name = "alc255-xiaomi-headset"},
 	{}
 };
 #define ALC225_STANDARD_PINS \
diff --git a/sound/soc/codecs/max98373-sdw.c b/sound/soc/codecs/max98373-sdw.c
index 5fe724728e84..e4675cfff7b2 100644
--- a/sound/soc/codecs/max98373-sdw.c
+++ b/sound/soc/codecs/max98373-sdw.c
@@ -838,8 +838,8 @@ static int max98373_sdw_probe(struct sdw_slave *slave,
 
 	/* Regmap Initialization */
 	regmap = devm_regmap_init_sdw(slave, &max98373_sdw_regmap);
-	if (!regmap)
-		return -EINVAL;
+	if (IS_ERR(regmap))
+		return PTR_ERR(regmap);
 
 	return max98373_init(slave, regmap);
 }
diff --git a/sound/soc/codecs/pcm3168a.c b/sound/soc/codecs/pcm3168a.c
index 5e445fee4ef5..821e7395f90f 100644
--- a/sound/soc/codecs/pcm3168a.c
+++ b/sound/soc/codecs/pcm3168a.c
@@ -306,6 +306,13 @@ static int pcm3168a_set_dai_sysclk(struct snd_soc_dai *dai,
 	struct pcm3168a_priv *pcm3168a = snd_soc_component_get_drvdata(dai->component);
 	int ret;
 
+	/*
+	 * Some sound card sets 0 Hz as reset,
+	 * but it is impossible to set. Ignore it here
+	 */
+	if (freq == 0)
+		return 0;
+
 	if (freq > PCM3168A_MAX_SYSCLK)
 		return -EINVAL;
 
diff --git a/sound/soc/codecs/rt1308-sdw.c b/sound/soc/codecs/rt1308-sdw.c
index b0ba0d2acbdd..56e952a904a3 100644
--- a/sound/soc/codecs/rt1308-sdw.c
+++ b/sound/soc/codecs/rt1308-sdw.c
@@ -684,8 +684,8 @@ static int rt1308_sdw_probe(struct sdw_slave *slave,
 
 	/* Regmap Initialization */
 	regmap = devm_regmap_init_sdw(slave, &rt1308_sdw_regmap);
-	if (!regmap)
-		return -EINVAL;
+	if (IS_ERR(regmap))
+		return PTR_ERR(regmap);
 
 	rt1308_sdw_init(&slave->dev, regmap, slave);
 
diff --git a/sound/soc/codecs/rt700-sdw.c b/sound/soc/codecs/rt700-sdw.c
index 4d14048d1197..1d24bf040718 100644
--- a/sound/soc/codecs/rt700-sdw.c
+++ b/sound/soc/codecs/rt700-sdw.c
@@ -452,8 +452,8 @@ static int rt700_sdw_probe(struct sdw_slave *slave,
 
 	/* Regmap Initialization */
 	sdw_regmap = devm_regmap_init_sdw(slave, &rt700_sdw_regmap);
-	if (!sdw_regmap)
-		return -EINVAL;
+	if (IS_ERR(sdw_regmap))
+		return PTR_ERR(sdw_regmap);
 
 	regmap = devm_regmap_init(&slave->dev, NULL,
 		&slave->dev, &rt700_regmap);
diff --git a/sound/soc/codecs/rt711-sdw.c b/sound/soc/codecs/rt711-sdw.c
index 45b928954b58..7efff130a638 100644
--- a/sound/soc/codecs/rt711-sdw.c
+++ b/sound/soc/codecs/rt711-sdw.c
@@ -452,8 +452,8 @@ static int rt711_sdw_probe(struct sdw_slave *slave,
 
 	/* Regmap Initialization */
 	sdw_regmap = devm_regmap_init_sdw(slave, &rt711_sdw_regmap);
-	if (!sdw_regmap)
-		return -EINVAL;
+	if (IS_ERR(sdw_regmap))
+		return PTR_ERR(sdw_regmap);
 
 	regmap = devm_regmap_init(&slave->dev, NULL,
 		&slave->dev, &rt711_regmap);
diff --git a/sound/soc/codecs/rt715-sdw.c b/sound/soc/codecs/rt715-sdw.c
index d11b23d6b240..68a36739f1b0 100644
--- a/sound/soc/codecs/rt715-sdw.c
+++ b/sound/soc/codecs/rt715-sdw.c
@@ -527,8 +527,8 @@ static int rt715_sdw_probe(struct sdw_slave *slave,
 
 	/* Regmap Initialization */
 	sdw_regmap = devm_regmap_init_sdw(slave, &rt715_sdw_regmap);
-	if (!sdw_regmap)
-		return -EINVAL;
+	if (IS_ERR(sdw_regmap))
+		return PTR_ERR(sdw_regmap);
 
 	regmap = devm_regmap_init(&slave->dev, NULL, &slave->dev,
 		&rt715_regmap);
diff --git a/sound/soc/codecs/tlv320adcx140.c b/sound/soc/codecs/tlv320adcx140.c
index 5cd50d841177..8efe20605f9b 100644
--- a/sound/soc/codecs/tlv320adcx140.c
+++ b/sound/soc/codecs/tlv320adcx140.c
@@ -842,6 +842,18 @@ static int adcx140_codec_probe(struct snd_soc_component *component)
 	if (ret)
 		goto out;
 
+	if (adcx140->supply_areg == NULL)
+		sleep_cfg_val |= ADCX140_AREG_INTERNAL;
+
+	ret = regmap_write(adcx140->regmap, ADCX140_SLEEP_CFG, sleep_cfg_val);
+	if (ret) {
+		dev_err(adcx140->dev, "setting sleep config failed %d\n", ret);
+		goto out;
+	}
+
+	/* 8.4.3: Wait >= 1ms after entering active mode. */
+	usleep_range(1000, 100000);
+
 	pdm_count = device_property_count_u32(adcx140->dev,
 					      "ti,pdm-edge-select");
 	if (pdm_count <= ADCX140_NUM_PDM_EDGES && pdm_count > 0) {
@@ -889,18 +901,6 @@ static int adcx140_codec_probe(struct snd_soc_component *component)
 	if (ret)
 		goto out;
 
-	if (adcx140->supply_areg == NULL)
-		sleep_cfg_val |= ADCX140_AREG_INTERNAL;
-
-	ret = regmap_write(adcx140->regmap, ADCX140_SLEEP_CFG, sleep_cfg_val);
-	if (ret) {
-		dev_err(adcx140->dev, "setting sleep config failed %d\n", ret);
-		goto out;
-	}
-
-	/* 8.4.3: Wait >= 1ms after entering active mode. */
-	usleep_range(1000, 100000);
-
 	ret = regmap_update_bits(adcx140->regmap, ADCX140_BIAS_CFG,
 				ADCX140_MIC_BIAS_VAL_MSK |
 				ADCX140_MIC_BIAS_VREF_MSK, bias_cfg);
@@ -980,6 +980,8 @@ static int adcx140_i2c_probe(struct i2c_client *i2c,
 	if (!adcx140)
 		return -ENOMEM;
 
+	adcx140->dev = &i2c->dev;
+
 	adcx140->gpio_reset = devm_gpiod_get_optional(adcx140->dev,
 						      "reset", GPIOD_OUT_LOW);
 	if (IS_ERR(adcx140->gpio_reset))
@@ -1007,7 +1009,7 @@ static int adcx140_i2c_probe(struct i2c_client *i2c,
 			ret);
 		return ret;
 	}
-	adcx140->dev = &i2c->dev;
+
 	i2c_set_clientdata(i2c, adcx140);
 
 	return devm_snd_soc_register_component(&i2c->dev,
diff --git a/sound/soc/codecs/wm8994.c b/sound/soc/codecs/wm8994.c
index 038be667c1a6..fc9ea198ac79 100644
--- a/sound/soc/codecs/wm8994.c
+++ b/sound/soc/codecs/wm8994.c
@@ -3514,6 +3514,8 @@ int wm8994_mic_detect(struct snd_soc_component *component, struct snd_soc_jack *
 		return -EINVAL;
 	}
 
+	pm_runtime_get_sync(component->dev);
+
 	switch (micbias) {
 	case 1:
 		micdet = &wm8994->micdet[0];
@@ -3561,6 +3563,8 @@ int wm8994_mic_detect(struct snd_soc_component *component, struct snd_soc_jack *
 
 	snd_soc_dapm_sync(dapm);
 
+	pm_runtime_put(component->dev);
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(wm8994_mic_detect);
@@ -3932,6 +3936,8 @@ int wm8958_mic_detect(struct snd_soc_component *component, struct snd_soc_jack *
 		return -EINVAL;
 	}
 
+	pm_runtime_get_sync(component->dev);
+
 	if (jack) {
 		snd_soc_dapm_force_enable_pin(dapm, "CLK_SYS");
 		snd_soc_dapm_sync(dapm);
@@ -4000,6 +4006,8 @@ int wm8958_mic_detect(struct snd_soc_component *component, struct snd_soc_jack *
 		snd_soc_dapm_sync(dapm);
 	}
 
+	pm_runtime_put(component->dev);
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(wm8958_mic_detect);
@@ -4193,11 +4201,13 @@ static int wm8994_component_probe(struct snd_soc_component *component)
 			wm8994->hubs.dcs_readback_mode = 2;
 			break;
 		}
+		wm8994->hubs.micd_scthr = true;
 		break;
 
 	case WM8958:
 		wm8994->hubs.dcs_readback_mode = 1;
 		wm8994->hubs.hp_startup_mode = 1;
+		wm8994->hubs.micd_scthr = true;
 
 		switch (control->revision) {
 		case 0:
diff --git a/sound/soc/codecs/wm_hubs.c b/sound/soc/codecs/wm_hubs.c
index 891effe220fe..0c881846f485 100644
--- a/sound/soc/codecs/wm_hubs.c
+++ b/sound/soc/codecs/wm_hubs.c
@@ -1223,6 +1223,9 @@ int wm_hubs_handle_analogue_pdata(struct snd_soc_component *component,
 		snd_soc_component_update_bits(component, WM8993_ADDITIONAL_CONTROL,
 				    WM8993_LINEOUT2_FB, WM8993_LINEOUT2_FB);
 
+	if (!hubs->micd_scthr)
+		return 0;
+
 	snd_soc_component_update_bits(component, WM8993_MICBIAS,
 			    WM8993_JD_SCTHR_MASK | WM8993_JD_THR_MASK |
 			    WM8993_MICB1_LVL | WM8993_MICB2_LVL,
diff --git a/sound/soc/codecs/wm_hubs.h b/sound/soc/codecs/wm_hubs.h
index 4b8e5f0d6e32..988b29e63060 100644
--- a/sound/soc/codecs/wm_hubs.h
+++ b/sound/soc/codecs/wm_hubs.h
@@ -27,6 +27,7 @@ struct wm_hubs_data {
 	int hp_startup_mode;
 	int series_startup;
 	int no_series_update;
+	bool micd_scthr;
 
 	bool no_cache_dac_hp_direct;
 	struct list_head dcs_cache;
diff --git a/sound/soc/intel/atom/sst-mfld-platform-pcm.c b/sound/soc/intel/atom/sst-mfld-platform-pcm.c
index b1cac7abdc0a..fba2c795ce0d 100644
--- a/sound/soc/intel/atom/sst-mfld-platform-pcm.c
+++ b/sound/soc/intel/atom/sst-mfld-platform-pcm.c
@@ -333,6 +333,17 @@ static int sst_media_open(struct snd_pcm_substream *substream,
 	if (ret_val < 0)
 		goto out_power_up;
 
+	/*
+	 * Make sure the period to be multiple of 1ms to align the
+	 * design of firmware. Apply same rule to buffer size to make
+	 * sure alsa could always find a value for period size
+	 * regardless the buffer size given by user space.
+	 */
+	snd_pcm_hw_constraint_step(substream->runtime, 0,
+			   SNDRV_PCM_HW_PARAM_PERIOD_SIZE, 48);
+	snd_pcm_hw_constraint_step(substream->runtime, 0,
+			   SNDRV_PCM_HW_PARAM_BUFFER_SIZE, 48);
+
 	/* Make sure, that the period size is always even */
 	snd_pcm_hw_constraint_step(substream->runtime, 0,
 			   SNDRV_PCM_HW_PARAM_PERIODS, 2);
diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c
index 479992f4e97a..fc202747ba83 100644
--- a/sound/soc/intel/boards/bytcr_rt5640.c
+++ b/sound/soc/intel/boards/bytcr_rt5640.c
@@ -591,6 +591,16 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = {
 					BYT_RT5640_SSP0_AIF1 |
 					BYT_RT5640_MCLK_EN),
 	},
+	{	/* MPMAN Converter 9, similar hw as the I.T.Works TW891 2-in-1 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "MPMAN"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Converter9"),
+		},
+		.driver_data = (void *)(BYTCR_INPUT_DEFAULTS |
+					BYT_RT5640_MONO_SPEAKER |
+					BYT_RT5640_SSP0_AIF1 |
+					BYT_RT5640_MCLK_EN),
+	},
 	{
 		/* MPMAN MPWIN895CL */
 		.matches = {
diff --git a/sound/soc/intel/boards/skl_hda_dsp_generic.c b/sound/soc/intel/boards/skl_hda_dsp_generic.c
index ca4900036ead..bc50eda297ab 100644
--- a/sound/soc/intel/boards/skl_hda_dsp_generic.c
+++ b/sound/soc/intel/boards/skl_hda_dsp_generic.c
@@ -181,7 +181,7 @@ static void skl_set_hda_codec_autosuspend_delay(struct snd_soc_card *card)
 	struct snd_soc_dai *dai;
 
 	for_each_card_rtds(card, rtd) {
-		if (!strstr(rtd->dai_link->codecs->name, "ehdaudio"))
+		if (!strstr(rtd->dai_link->codecs->name, "ehdaudio0D0"))
 			continue;
 		dai = asoc_rtd_to_codec(rtd, 0);
 		hda_pvt = snd_soc_component_get_drvdata(dai->component);
diff --git a/sound/soc/intel/boards/sof_maxim_common.c b/sound/soc/intel/boards/sof_maxim_common.c
index 1a6961592029..b6e63ea13d64 100644
--- a/sound/soc/intel/boards/sof_maxim_common.c
+++ b/sound/soc/intel/boards/sof_maxim_common.c
@@ -66,6 +66,10 @@ int max98373_trigger(struct snd_pcm_substream *substream, int cmd)
 	int j;
 	int ret = 0;
 
+	/* set spk pin by playback only */
+	if (substream->stream == SNDRV_PCM_STREAM_CAPTURE)
+		return 0;
+
 	for_each_rtd_codec_dais(rtd, j, codec_dai) {
 		struct snd_soc_component *component = codec_dai->component;
 		struct snd_soc_dapm_context *dapm =
@@ -86,9 +90,6 @@ int max98373_trigger(struct snd_pcm_substream *substream, int cmd)
 		case SNDRV_PCM_TRIGGER_STOP:
 		case SNDRV_PCM_TRIGGER_SUSPEND:
 		case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
-			/* Make sure no streams are active before disable pin */
-			if (snd_soc_dai_active(codec_dai) != 1)
-				break;
 			ret = snd_soc_dapm_disable_pin(dapm, pin_name);
 			if (!ret)
 				snd_soc_dapm_sync(dapm);
diff --git a/sound/soc/intel/haswell/sst-haswell-dsp.c b/sound/soc/intel/haswell/sst-haswell-dsp.c
index de80e19454c1..88c3f63bded9 100644
--- a/sound/soc/intel/haswell/sst-haswell-dsp.c
+++ b/sound/soc/intel/haswell/sst-haswell-dsp.c
@@ -243,92 +243,45 @@ static irqreturn_t hsw_irq(int irq, void *context)
 	return ret;
 }
 
-#define CSR_DEFAULT_VALUE 0x8480040E
-#define ISC_DEFAULT_VALUE 0x0
-#define ISD_DEFAULT_VALUE 0x0
-#define IMC_DEFAULT_VALUE 0x7FFF0003
-#define IMD_DEFAULT_VALUE 0x7FFF0003
-#define IPCC_DEFAULT_VALUE 0x0
-#define IPCD_DEFAULT_VALUE 0x0
-#define CLKCTL_DEFAULT_VALUE 0x7FF
-#define CSR2_DEFAULT_VALUE 0x0
-#define LTR_CTRL_DEFAULT_VALUE 0x0
-#define HMD_CTRL_DEFAULT_VALUE 0x0
-
-static void hsw_set_shim_defaults(struct sst_dsp *sst)
-{
-	sst_dsp_shim_write_unlocked(sst, SST_CSR, CSR_DEFAULT_VALUE);
-	sst_dsp_shim_write_unlocked(sst, SST_ISRX, ISC_DEFAULT_VALUE);
-	sst_dsp_shim_write_unlocked(sst, SST_ISRD, ISD_DEFAULT_VALUE);
-	sst_dsp_shim_write_unlocked(sst, SST_IMRX, IMC_DEFAULT_VALUE);
-	sst_dsp_shim_write_unlocked(sst, SST_IMRD, IMD_DEFAULT_VALUE);
-	sst_dsp_shim_write_unlocked(sst, SST_IPCX, IPCC_DEFAULT_VALUE);
-	sst_dsp_shim_write_unlocked(sst, SST_IPCD, IPCD_DEFAULT_VALUE);
-	sst_dsp_shim_write_unlocked(sst, SST_CLKCTL, CLKCTL_DEFAULT_VALUE);
-	sst_dsp_shim_write_unlocked(sst, SST_CSR2, CSR2_DEFAULT_VALUE);
-	sst_dsp_shim_write_unlocked(sst, SST_LTRC, LTR_CTRL_DEFAULT_VALUE);
-	sst_dsp_shim_write_unlocked(sst, SST_HMDC, HMD_CTRL_DEFAULT_VALUE);
-}
-
-/* all clock-gating minus DCLCGE and DTCGE */
-#define SST_VDRTCL2_CG_OTHER	0xB7D
-
 static void hsw_set_dsp_D3(struct sst_dsp *sst)
 {
+	u32 val;
 	u32 reg;
 
-	/* disable clock core gating */
+	/* Disable core clock gating (VDRTCTL2.DCLCGE = 0) */
 	reg = readl(sst->addr.pci_cfg + SST_VDRTCTL2);
-	reg &= ~(SST_VDRTCL2_DCLCGE);
+	reg &= ~(SST_VDRTCL2_DCLCGE | SST_VDRTCL2_DTCGE);
 	writel(reg, sst->addr.pci_cfg + SST_VDRTCTL2);
 
-	/* stall, reset and set 24MHz XOSC */
-	sst_dsp_shim_update_bits_unlocked(sst, SST_CSR,
-			SST_CSR_24MHZ_LPCS | SST_CSR_STALL | SST_CSR_RST,
-			SST_CSR_24MHZ_LPCS | SST_CSR_STALL | SST_CSR_RST);
-
-	/* DRAM power gating all */
-	reg = readl(sst->addr.pci_cfg + SST_VDRTCTL0);
-	reg |= SST_VDRTCL0_ISRAMPGE_MASK |
-		SST_VDRTCL0_DSRAMPGE_MASK;
-	reg &= ~(SST_VDRTCL0_D3SRAMPGD);
-	reg |= SST_VDRTCL0_D3PGD;
-	writel(reg, sst->addr.pci_cfg + SST_VDRTCTL0);
-	udelay(50);
+	/* enable power gating and switch off DRAM & IRAM blocks */
+	val = readl(sst->addr.pci_cfg + SST_VDRTCTL0);
+	val |= SST_VDRTCL0_DSRAMPGE_MASK |
+		SST_VDRTCL0_ISRAMPGE_MASK;
+	val &= ~(SST_VDRTCL0_D3PGD | SST_VDRTCL0_D3SRAMPGD);
+	writel(val, sst->addr.pci_cfg + SST_VDRTCTL0);
 
-	/* PLL shutdown enable */
-	reg = readl(sst->addr.pci_cfg + SST_VDRTCTL2);
-	reg |= SST_VDRTCL2_APLLSE_MASK;
-	writel(reg, sst->addr.pci_cfg + SST_VDRTCTL2);
+	/* switch off audio PLL */
+	val = readl(sst->addr.pci_cfg + SST_VDRTCTL2);
+	val |= SST_VDRTCL2_APLLSE_MASK;
+	writel(val, sst->addr.pci_cfg + SST_VDRTCTL2);
 
-	/* disable MCLK */
+	/* disable MCLK(clkctl.smos = 0) */
 	sst_dsp_shim_update_bits_unlocked(sst, SST_CLKCTL,
-			SST_CLKCTL_MASK, 0);
-
-	/* switch clock gating */
-	reg = readl(sst->addr.pci_cfg + SST_VDRTCTL2);
-	reg |= SST_VDRTCL2_CG_OTHER;
-	reg &= ~(SST_VDRTCL2_DTCGE);
-	writel(reg, sst->addr.pci_cfg + SST_VDRTCTL2);
-	/* enable DTCGE separatelly */
-	reg = readl(sst->addr.pci_cfg + SST_VDRTCTL2);
-	reg |= SST_VDRTCL2_DTCGE;
-	writel(reg, sst->addr.pci_cfg + SST_VDRTCTL2);
+		SST_CLKCTL_MASK, 0);
 
-	/* set shim defaults */
-	hsw_set_shim_defaults(sst);
-
-	/* set D3 */
-	reg = readl(sst->addr.pci_cfg + SST_PMCS);
-	reg |= SST_PMCS_PS_MASK;
-	writel(reg, sst->addr.pci_cfg + SST_PMCS);
+	/* Set D3 state, delay 50 us */
+	val = readl(sst->addr.pci_cfg + SST_PMCS);
+	val |= SST_PMCS_PS_MASK;
+	writel(val, sst->addr.pci_cfg + SST_PMCS);
 	udelay(50);
 
-	/* enable clock core gating */
+	/* Enable core clock gating (VDRTCTL2.DCLCGE = 1), delay 50 us */
 	reg = readl(sst->addr.pci_cfg + SST_VDRTCTL2);
-	reg |= SST_VDRTCL2_DCLCGE;
+	reg |= SST_VDRTCL2_DCLCGE | SST_VDRTCL2_DTCGE;
 	writel(reg, sst->addr.pci_cfg + SST_VDRTCTL2);
+
 	udelay(50);
+
 }
 
 static void hsw_reset(struct sst_dsp *sst)
@@ -346,62 +299,75 @@ static void hsw_reset(struct sst_dsp *sst)
 		SST_CSR_RST | SST_CSR_STALL, SST_CSR_STALL);
 }
 
-/* recommended CSR state for power-up */
-#define SST_CSR_D0_MASK (0x18A09C0C | SST_CSR_DCS_MASK)
-
 static int hsw_set_dsp_D0(struct sst_dsp *sst)
 {
-	u32 reg;
+	int tries = 10;
+	u32 reg, fw_dump_bit;
 
-	/* disable clock core gating */
+	/* Disable core clock gating (VDRTCTL2.DCLCGE = 0) */
 	reg = readl(sst->addr.pci_cfg + SST_VDRTCTL2);
-	reg &= ~(SST_VDRTCL2_DCLCGE);
+	reg &= ~(SST_VDRTCL2_DCLCGE | SST_VDRTCL2_DTCGE);
 	writel(reg, sst->addr.pci_cfg + SST_VDRTCTL2);
 
-	/* switch clock gating */
-	reg = readl(sst->addr.pci_cfg + SST_VDRTCTL2);
-	reg |= SST_VDRTCL2_CG_OTHER;
-	reg &= ~(SST_VDRTCL2_DTCGE);
-	writel(reg, sst->addr.pci_cfg + SST_VDRTCTL2);
+	/* Disable D3PG (VDRTCTL0.D3PGD = 1) */
+	reg = readl(sst->addr.pci_cfg + SST_VDRTCTL0);
+	reg |= SST_VDRTCL0_D3PGD;
+	writel(reg, sst->addr.pci_cfg + SST_VDRTCTL0);
 
-	/* set D0 */
+	/* Set D0 state */
 	reg = readl(sst->addr.pci_cfg + SST_PMCS);
-	reg &= ~(SST_PMCS_PS_MASK);
+	reg &= ~SST_PMCS_PS_MASK;
 	writel(reg, sst->addr.pci_cfg + SST_PMCS);
 
-	/* DRAM power gating none */
-	reg = readl(sst->addr.pci_cfg + SST_VDRTCTL0);
-	reg &= ~(SST_VDRTCL0_ISRAMPGE_MASK |
-		SST_VDRTCL0_DSRAMPGE_MASK);
-	reg |= SST_VDRTCL0_D3SRAMPGD;
-	reg |= SST_VDRTCL0_D3PGD;
-	writel(reg, sst->addr.pci_cfg + SST_VDRTCTL0);
-	mdelay(10);
+	/* check that ADSP shim is enabled */
+	while (tries--) {
+		reg = readl(sst->addr.pci_cfg + SST_PMCS) & SST_PMCS_PS_MASK;
+		if (reg == 0)
+			goto finish;
+
+		msleep(1);
+	}
+
+	return -ENODEV;
 
-	/* set shim defaults */
-	hsw_set_shim_defaults(sst);
+finish:
+	/* select SSP1 19.2MHz base clock, SSP clock 0, turn off Low Power Clock */
+	sst_dsp_shim_update_bits_unlocked(sst, SST_CSR,
+		SST_CSR_S1IOCS | SST_CSR_SBCS1 | SST_CSR_LPCS, 0x0);
+
+	/* stall DSP core, set clk to 192/96Mhz */
+	sst_dsp_shim_update_bits_unlocked(sst,
+		SST_CSR, SST_CSR_STALL | SST_CSR_DCS_MASK,
+		SST_CSR_STALL | SST_CSR_DCS(4));
 
-	/* restore MCLK */
+	/* Set 24MHz MCLK, prevent local clock gating, enable SSP0 clock */
 	sst_dsp_shim_update_bits_unlocked(sst, SST_CLKCTL,
-			SST_CLKCTL_MASK, SST_CLKCTL_MASK);
+		SST_CLKCTL_MASK | SST_CLKCTL_DCPLCG | SST_CLKCTL_SCOE0,
+		SST_CLKCTL_MASK | SST_CLKCTL_DCPLCG | SST_CLKCTL_SCOE0);
 
-	/* PLL shutdown disable */
+	/* Stall and reset core, set CSR */
+	hsw_reset(sst);
+
+	/* Enable core clock gating (VDRTCTL2.DCLCGE = 1), delay 50 us */
 	reg = readl(sst->addr.pci_cfg + SST_VDRTCTL2);
-	reg &= ~(SST_VDRTCL2_APLLSE_MASK);
+	reg |= SST_VDRTCL2_DCLCGE | SST_VDRTCL2_DTCGE;
 	writel(reg, sst->addr.pci_cfg + SST_VDRTCTL2);
 
-	sst_dsp_shim_update_bits_unlocked(sst, SST_CSR,
-			SST_CSR_D0_MASK, SST_CSR_SBCS0 | SST_CSR_SBCS1 |
-			SST_CSR_STALL | SST_CSR_DCS(4));
 	udelay(50);
 
-	/* enable clock core gating */
+	/* switch on audio PLL */
 	reg = readl(sst->addr.pci_cfg + SST_VDRTCTL2);
-	reg |= SST_VDRTCL2_DCLCGE;
+	reg &= ~SST_VDRTCL2_APLLSE_MASK;
 	writel(reg, sst->addr.pci_cfg + SST_VDRTCTL2);
 
-	/* clear reset */
-	sst_dsp_shim_update_bits_unlocked(sst, SST_CSR, SST_CSR_RST, 0);
+	/* set default power gating control, enable power gating control for all blocks. that is,
+	can't be accessed, please enable each block before accessing. */
+	reg = readl(sst->addr.pci_cfg + SST_VDRTCTL0);
+	reg |= SST_VDRTCL0_DSRAMPGE_MASK | SST_VDRTCL0_ISRAMPGE_MASK;
+	/* for D0, always enable the block(DSRAM[0]) used for FW dump */
+	fw_dump_bit = 1 << SST_VDRTCL0_DSRAMPGE_SHIFT;
+	writel(reg & ~fw_dump_bit, sst->addr.pci_cfg + SST_VDRTCTL0);
+
 
 	/* disable DMA finish function for SSP0 & SSP1 */
 	sst_dsp_shim_update_bits_unlocked(sst, SST_CSR2, SST_CSR2_SDFD_SSP1,
@@ -418,6 +384,12 @@ static int hsw_set_dsp_D0(struct sst_dsp *sst)
 	sst_dsp_shim_update_bits(sst, SST_IMRD, (SST_IMRD_DONE | SST_IMRD_BUSY |
 				SST_IMRD_SSP0 | SST_IMRD_DMAC), 0x0);
 
+	/* clear IPC registers */
+	sst_dsp_shim_write(sst, SST_IPCX, 0x0);
+	sst_dsp_shim_write(sst, SST_IPCD, 0x0);
+	sst_dsp_shim_write(sst, 0x80, 0x6);
+	sst_dsp_shim_write(sst, 0xe0, 0x300a);
+
 	return 0;
 }
 
@@ -443,6 +415,11 @@ static void hsw_sleep(struct sst_dsp *sst)
 {
 	dev_dbg(sst->dev, "HSW_PM dsp runtime suspend\n");
 
+	/* put DSP into reset and stall */
+	sst_dsp_shim_update_bits(sst, SST_CSR,
+		SST_CSR_24MHZ_LPCS | SST_CSR_RST | SST_CSR_STALL,
+		SST_CSR_RST | SST_CSR_STALL | SST_CSR_24MHZ_LPCS);
+
 	hsw_set_dsp_D3(sst);
 	dev_dbg(sst->dev, "HSW_PM dsp runtime suspend exit\n");
 }
diff --git a/sound/soc/meson/axg-toddr.c b/sound/soc/meson/axg-toddr.c
index e711abcf8c12..d6adf7edea41 100644
--- a/sound/soc/meson/axg-toddr.c
+++ b/sound/soc/meson/axg-toddr.c
@@ -18,6 +18,7 @@
 #define CTRL0_TODDR_SEL_RESAMPLE	BIT(30)
 #define CTRL0_TODDR_EXT_SIGNED		BIT(29)
 #define CTRL0_TODDR_PP_MODE		BIT(28)
+#define CTRL0_TODDR_SYNC_CH		BIT(27)
 #define CTRL0_TODDR_TYPE_MASK		GENMASK(15, 13)
 #define CTRL0_TODDR_TYPE(x)		((x) << 13)
 #define CTRL0_TODDR_MSB_POS_MASK	GENMASK(12, 8)
@@ -189,10 +190,31 @@ static const struct axg_fifo_match_data axg_toddr_match_data = {
 	.dai_drv		= &axg_toddr_dai_drv
 };
 
+static int g12a_toddr_dai_startup(struct snd_pcm_substream *substream,
+				 struct snd_soc_dai *dai)
+{
+	struct axg_fifo *fifo = snd_soc_dai_get_drvdata(dai);
+	int ret;
+
+	ret = axg_toddr_dai_startup(substream, dai);
+	if (ret)
+		return ret;
+
+	/*
+	 * Make sure the first channel ends up in the at beginning of the output
+	 * As weird as it looks, without this the first channel may be misplaced
+	 * in memory, with a random shift of 2 channels.
+	 */
+	regmap_update_bits(fifo->map, FIFO_CTRL0, CTRL0_TODDR_SYNC_CH,
+			   CTRL0_TODDR_SYNC_CH);
+
+	return 0;
+}
+
 static const struct snd_soc_dai_ops g12a_toddr_ops = {
 	.prepare	= g12a_toddr_dai_prepare,
 	.hw_params	= axg_toddr_dai_hw_params,
-	.startup	= axg_toddr_dai_startup,
+	.startup	= g12a_toddr_dai_startup,
 	.shutdown	= axg_toddr_dai_shutdown,
 };
 
diff --git a/sound/soc/qcom/apq8016_sbc.c b/sound/soc/qcom/apq8016_sbc.c
index 083413abc2f6..575e2aefefe3 100644
--- a/sound/soc/qcom/apq8016_sbc.c
+++ b/sound/soc/qcom/apq8016_sbc.c
@@ -143,6 +143,7 @@ static int apq8016_sbc_platform_probe(struct platform_device *pdev)
 
 	card = &data->card;
 	card->dev = dev;
+	card->owner = THIS_MODULE;
 	card->dapm_widgets = apq8016_sbc_dapm_widgets;
 	card->num_dapm_widgets = ARRAY_SIZE(apq8016_sbc_dapm_widgets);
 
diff --git a/sound/soc/qcom/apq8096.c b/sound/soc/qcom/apq8096.c
index 253549600c5a..1a69baefc5ce 100644
--- a/sound/soc/qcom/apq8096.c
+++ b/sound/soc/qcom/apq8096.c
@@ -114,6 +114,7 @@ static int apq8096_platform_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	card->dev = dev;
+	card->owner = THIS_MODULE;
 	dev_set_drvdata(dev, card);
 	ret = qcom_snd_parse_of(card);
 	if (ret)
diff --git a/sound/soc/qcom/common.c b/sound/soc/qcom/common.c
index 5194d90ddb96..fd69cf8b1f23 100644
--- a/sound/soc/qcom/common.c
+++ b/sound/soc/qcom/common.c
@@ -52,8 +52,10 @@ int qcom_snd_parse_of(struct snd_soc_card *card)
 
 	for_each_child_of_node(dev->of_node, np) {
 		dlc = devm_kzalloc(dev, 2 * sizeof(*dlc), GFP_KERNEL);
-		if (!dlc)
-			return -ENOMEM;
+		if (!dlc) {
+			ret = -ENOMEM;
+			goto err;
+		}
 
 		link->cpus	= &dlc[0];
 		link->platforms	= &dlc[1];
diff --git a/sound/soc/qcom/sdm845.c b/sound/soc/qcom/sdm845.c
index 0d10fba53945..ab1bf23c21a6 100644
--- a/sound/soc/qcom/sdm845.c
+++ b/sound/soc/qcom/sdm845.c
@@ -555,6 +555,7 @@ static int sdm845_snd_platform_probe(struct platform_device *pdev)
 	card->dapm_widgets = sdm845_snd_widgets;
 	card->num_dapm_widgets = ARRAY_SIZE(sdm845_snd_widgets);
 	card->dev = dev;
+	card->owner = THIS_MODULE;
 	dev_set_drvdata(dev, card);
 	ret = qcom_snd_parse_of(card);
 	if (ret)
diff --git a/sound/soc/qcom/storm.c b/sound/soc/qcom/storm.c
index c0c388d4db82..80c9cf2f254a 100644
--- a/sound/soc/qcom/storm.c
+++ b/sound/soc/qcom/storm.c
@@ -96,6 +96,7 @@ static int storm_platform_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	card->dev = &pdev->dev;
+	card->owner = THIS_MODULE;
 
 	ret = snd_soc_of_parse_card_name(card, "qcom,model");
 	if (ret) {
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index 663e3839f251..054437660678 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -834,6 +834,19 @@ struct snd_soc_dai *snd_soc_find_dai(
 }
 EXPORT_SYMBOL_GPL(snd_soc_find_dai);
 
+struct snd_soc_dai *snd_soc_find_dai_with_mutex(
+	const struct snd_soc_dai_link_component *dlc)
+{
+	struct snd_soc_dai *dai;
+
+	mutex_lock(&client_mutex);
+	dai = snd_soc_find_dai(dlc);
+	mutex_unlock(&client_mutex);
+
+	return dai;
+}
+EXPORT_SYMBOL_GPL(snd_soc_find_dai_with_mutex);
+
 static int soc_dai_link_sanity_check(struct snd_soc_card *card,
 				     struct snd_soc_dai_link *link)
 {
diff --git a/sound/soc/soc-dai.c b/sound/soc/soc-dai.c
index 91a2551e4cef..0dbd312aad08 100644
--- a/sound/soc/soc-dai.c
+++ b/sound/soc/soc-dai.c
@@ -412,14 +412,14 @@ void snd_soc_dai_link_set_capabilities(struct snd_soc_dai_link *dai_link)
 		supported_codec = false;
 
 		for_each_link_cpus(dai_link, i, cpu) {
-			dai = snd_soc_find_dai(cpu);
+			dai = snd_soc_find_dai_with_mutex(cpu);
 			if (dai && snd_soc_dai_stream_valid(dai, direction)) {
 				supported_cpu = true;
 				break;
 			}
 		}
 		for_each_link_codecs(dai_link, i, codec) {
-			dai = snd_soc_find_dai(codec);
+			dai = snd_soc_find_dai_with_mutex(codec);
 			if (dai && snd_soc_dai_stream_valid(dai, direction)) {
 				supported_codec = true;
 				break;
diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c
index 00ac1cbf6f88..4c9d4cd8cf0b 100644
--- a/sound/soc/soc-pcm.c
+++ b/sound/soc/soc-pcm.c
@@ -812,7 +812,7 @@ dynamic:
 	return 0;
 
 config_err:
-	for_each_rtd_dais(rtd, i, dai)
+	for_each_rtd_dais_rollback(rtd, i, dai)
 		snd_soc_dai_shutdown(dai, substream);
 
 	snd_soc_link_shutdown(substream);
diff --git a/sound/soc/ti/ams-delta.c b/sound/soc/ti/ams-delta.c
index 5c47de96c529..57feb473a579 100644
--- a/sound/soc/ti/ams-delta.c
+++ b/sound/soc/ti/ams-delta.c
@@ -446,12 +446,12 @@ static const struct snd_soc_dai_ops ams_delta_dai_ops = {
 /* Will be used if the codec ever has its own digital_mute function */
 static int ams_delta_startup(struct snd_pcm_substream *substream)
 {
-	return ams_delta_digital_mute(NULL, 0, substream->stream);
+	return ams_delta_mute(NULL, 0, substream->stream);
 }
 
 static void ams_delta_shutdown(struct snd_pcm_substream *substream)
 {
-	ams_delta_digital_mute(NULL, 1, substream->stream);
+	ams_delta_mute(NULL, 1, substream->stream);
 }
 
 
diff --git a/tools/bpf/Makefile b/tools/bpf/Makefile
index 0a6d09a3e91f..39bb322707b4 100644
--- a/tools/bpf/Makefile
+++ b/tools/bpf/Makefile
@@ -38,7 +38,7 @@ FEATURE_TESTS = libbfd disassembler-four-args
 FEATURE_DISPLAY = libbfd disassembler-four-args
 
 check_feat := 1
-NON_CHECK_FEAT_TARGETS := clean bpftool_clean runqslower_clean
+NON_CHECK_FEAT_TARGETS := clean bpftool_clean runqslower_clean resolve_btfids_clean
 ifdef MAKECMDGOALS
 ifeq ($(filter-out $(NON_CHECK_FEAT_TARGETS),$(MAKECMDGOALS)),)
   check_feat := 0
@@ -89,7 +89,7 @@ $(OUTPUT)bpf_exp.lex.c: $(OUTPUT)bpf_exp.yacc.c
 $(OUTPUT)bpf_exp.yacc.o: $(OUTPUT)bpf_exp.yacc.c
 $(OUTPUT)bpf_exp.lex.o: $(OUTPUT)bpf_exp.lex.c
 
-clean: bpftool_clean runqslower_clean
+clean: bpftool_clean runqslower_clean resolve_btfids_clean
 	$(call QUIET_CLEAN, bpf-progs)
 	$(Q)$(RM) -r -- $(OUTPUT)*.o $(OUTPUT)bpf_jit_disasm $(OUTPUT)bpf_dbg \
 	       $(OUTPUT)bpf_asm $(OUTPUT)bpf_exp.yacc.* $(OUTPUT)bpf_exp.lex.*
diff --git a/tools/bpf/bpftool/Documentation/Makefile b/tools/bpf/bpftool/Documentation/Makefile
index 815ac9804aee..f33cb02de95c 100644
--- a/tools/bpf/bpftool/Documentation/Makefile
+++ b/tools/bpf/bpftool/Documentation/Makefile
@@ -19,7 +19,7 @@ man8dir = $(mandir)/man8
 # Load targets for building eBPF helpers man page.
 include ../../Makefile.helpers
 
-MAN8_RST = $(filter-out $(HELPERS_RST),$(wildcard *.rst))
+MAN8_RST = $(wildcard bpftool*.rst)
 
 _DOC_MAN8 = $(patsubst %.rst,%.8,$(MAN8_RST))
 DOC_MAN8 = $(addprefix $(OUTPUT),$(_DOC_MAN8))
@@ -28,12 +28,23 @@ man: man8 helpers
 man8: $(DOC_MAN8)
 
 RST2MAN_DEP := $(shell command -v rst2man 2>/dev/null)
+RST2MAN_OPTS += --verbose
+
+list_pages = $(sort $(basename $(filter-out $(1),$(MAN8_RST))))
+see_also = $(subst " ",, \
+	"\n" \
+	"SEE ALSO\n" \
+	"========\n" \
+	"\t**bpf**\ (2),\n" \
+	"\t**bpf-helpers**\\ (7)" \
+	$(foreach page,$(call list_pages,$(1)),",\n\t**$(page)**\\ (8)") \
+	"\n")
 
 $(OUTPUT)%.8: %.rst
 ifndef RST2MAN_DEP
 	$(error "rst2man not found, but required to generate man pages")
 endif
-	$(QUIET_GEN)rst2man $< > $@
+	$(QUIET_GEN)( cat $< ; printf "%b" $(call see_also,$<) ) | rst2man $(RST2MAN_OPTS) > $@
 
 clean: helpers-clean
 	$(call QUIET_CLEAN, Documentation)
diff --git a/tools/bpf/bpftool/Documentation/bpftool-btf.rst b/tools/bpf/bpftool/Documentation/bpftool-btf.rst
index 896f4c6c2870..ff4d327a582e 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-btf.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-btf.rst
@@ -71,26 +71,12 @@ DESCRIPTION
 
 OPTIONS
 =======
-	-h, --help
-		  Print short generic help message (similar to **bpftool help**).
-
-	-V, --version
-		  Print version number (similar to **bpftool version**).
-
-	-j, --json
-		  Generate JSON output. For commands that cannot produce JSON, this
-		  option has no effect.
-
-	-p, --pretty
-		  Generate human-readable JSON output. Implies **-j**.
-
-	-d, --debug
-		  Print all logs available from libbpf, including debug-level
-		  information.
+	.. include:: common_options.rst
 
 EXAMPLES
 ========
 **# bpftool btf dump id 1226**
+
 ::
 
   [1] PTR '(anon)' type_id=2
@@ -104,6 +90,7 @@ EXAMPLES
 This gives an example of default output for all supported BTF kinds.
 
 **$ cat prog.c**
+
 ::
 
   struct fwd_struct;
@@ -144,6 +131,7 @@ This gives an example of default output for all supported BTF kinds.
   }
 
 **$ bpftool btf dump file prog.o**
+
 ::
 
   [1] PTR '(anon)' type_id=2
@@ -229,20 +217,3 @@ All the standard ways to specify map or program are supported:
 **# bpftool btf dump prog tag b88e0a09b1d9759d**
 
 **# bpftool btf dump prog pinned /sys/fs/bpf/prog_name**
-
-SEE ALSO
-========
-	**bpf**\ (2),
-	**bpf-helpers**\ (7),
-	**bpftool**\ (8),
-	**bpftool-btf**\ (8),
-	**bpftool-cgroup**\ (8),
-	**bpftool-feature**\ (8),
-	**bpftool-gen**\ (8),
-	**bpftool-iter**\ (8),
-	**bpftool-link**\ (8),
-	**bpftool-map**\ (8),
-	**bpftool-net**\ (8),
-	**bpftool-perf**\ (8),
-	**bpftool-prog**\ (8),
-	**bpftool-struct_ops**\ (8)
diff --git a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst
index a226aee3574f..790944c35602 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst
@@ -116,26 +116,11 @@ DESCRIPTION
 
 OPTIONS
 =======
-	-h, --help
-		  Print short generic help message (similar to **bpftool help**).
-
-	-V, --version
-		  Print version number (similar to **bpftool version**).
-
-	-j, --json
-		  Generate JSON output. For commands that cannot produce JSON, this
-		  option has no effect.
-
-	-p, --pretty
-		  Generate human-readable JSON output. Implies **-j**.
+	.. include:: common_options.rst
 
 	-f, --bpffs
 		  Show file names of pinned programs.
 
-	-d, --debug
-		  Print all logs available from libbpf, including debug-level
-		  information.
-
 EXAMPLES
 ========
 |
@@ -158,19 +143,3 @@ EXAMPLES
 ::
 
     ID       AttachType      AttachFlags     Name
-
-SEE ALSO
-========
-	**bpf**\ (2),
-	**bpf-helpers**\ (7),
-	**bpftool**\ (8),
-	**bpftool-btf**\ (8),
-	**bpftool-feature**\ (8),
-	**bpftool-gen**\ (8),
-	**bpftool-iter**\ (8),
-	**bpftool-link**\ (8),
-	**bpftool-map**\ (8),
-	**bpftool-net**\ (8),
-	**bpftool-perf**\ (8),
-	**bpftool-prog**\ (8),
-	**bpftool-struct_ops**\ (8)
diff --git a/tools/bpf/bpftool/Documentation/bpftool-feature.rst b/tools/bpf/bpftool/Documentation/bpftool-feature.rst
index 8609f06e71de..dd3771bdbc57 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-feature.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-feature.rst
@@ -71,35 +71,4 @@ DESCRIPTION
 
 OPTIONS
 =======
-	-h, --help
-		  Print short generic help message (similar to **bpftool help**).
-
-	-V, --version
-		  Print version number (similar to **bpftool version**).
-
-	-j, --json
-		  Generate JSON output. For commands that cannot produce JSON, this
-		  option has no effect.
-
-	-p, --pretty
-		  Generate human-readable JSON output. Implies **-j**.
-
-	-d, --debug
-		  Print all logs available from libbpf, including debug-level
-		  information.
-
-SEE ALSO
-========
-	**bpf**\ (2),
-	**bpf-helpers**\ (7),
-	**bpftool**\ (8),
-	**bpftool-btf**\ (8),
-	**bpftool-cgroup**\ (8),
-	**bpftool-gen**\ (8),
-	**bpftool-iter**\ (8),
-	**bpftool-link**\ (8),
-	**bpftool-map**\ (8),
-	**bpftool-net**\ (8),
-	**bpftool-perf**\ (8),
-	**bpftool-prog**\ (8),
-	**bpftool-struct_ops**\ (8)
+	.. include:: common_options.rst
diff --git a/tools/bpf/bpftool/Documentation/bpftool-gen.rst b/tools/bpf/bpftool/Documentation/bpftool-gen.rst
index df85dbd962c0..84cf0639696f 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-gen.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-gen.rst
@@ -126,26 +126,12 @@ DESCRIPTION
 
 OPTIONS
 =======
-	-h, --help
-		  Print short generic help message (similar to **bpftool help**).
-
-	-V, --version
-		  Print version number (similar to **bpftool version**).
-
-	-j, --json
-		  Generate JSON output. For commands that cannot produce JSON,
-		  this option has no effect.
-
-	-p, --pretty
-		  Generate human-readable JSON output. Implies **-j**.
-
-	-d, --debug
-		  Print all logs available from libbpf, including debug-level
-		  information.
+	.. include:: common_options.rst
 
 EXAMPLES
 ========
 **$ cat example.c**
+
 ::
 
   #include <stdbool.h>
@@ -187,6 +173,7 @@ This is example BPF application with two BPF programs and a mix of BPF maps
 and global variables.
 
 **$ bpftool gen skeleton example.o**
+
 ::
 
   /* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
@@ -241,6 +228,7 @@ and global variables.
   #endif /* __EXAMPLE_SKEL_H__ */
 
 **$ cat example_user.c**
+
 ::
 
   #include "example.skel.h"
@@ -283,6 +271,7 @@ and global variables.
   }
 
 **# ./example_user**
+
 ::
 
   my_map name: my_map
@@ -290,19 +279,3 @@ and global variables.
   my_static_var: 7
 
 This is a stripped-out version of skeleton generated for above example code.
-
-SEE ALSO
-========
-	**bpf**\ (2),
-	**bpf-helpers**\ (7),
-	**bpftool**\ (8),
-	**bpftool-btf**\ (8),
-	**bpftool-cgroup**\ (8),
-	**bpftool-feature**\ (8),
-	**bpftool-iter**\ (8),
-	**bpftool-link**\ (8),
-	**bpftool-map**\ (8),
-	**bpftool-net**\ (8),
-	**bpftool-perf**\ (8),
-	**bpftool-prog**\ (8),
-	**bpftool-struct_ops**\ (8)
diff --git a/tools/bpf/bpftool/Documentation/bpftool-iter.rst b/tools/bpf/bpftool/Documentation/bpftool-iter.rst
index 070ffacb42b5..51f49bead619 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-iter.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-iter.rst
@@ -51,16 +51,7 @@ DESCRIPTION
 
 OPTIONS
 =======
-	-h, --help
-		  Print short generic help message (similar to **bpftool help**).
-
-	-V, --version
-		  Print version number (similar to **bpftool version**).
-
-	-d, --debug
-		  Print all logs available, even debug-level information. This
-		  includes logs from libbpf as well as from the verifier, when
-		  attempting to load programs.
+	.. include:: common_options.rst
 
 EXAMPLES
 ========
@@ -77,19 +68,3 @@ EXAMPLES
 
    Create a file-based bpf iterator from bpf_iter_hashmap.o and map with
    id 20, and pin it to /sys/fs/bpf/my_hashmap
-
-SEE ALSO
-========
-	**bpf**\ (2),
-	**bpf-helpers**\ (7),
-	**bpftool**\ (8),
-	**bpftool-btf**\ (8),
-	**bpftool-cgroup**\ (8),
-	**bpftool-feature**\ (8),
-	**bpftool-gen**\ (8),
-	**bpftool-link**\ (8),
-	**bpftool-map**\ (8),
-	**bpftool-net**\ (8),
-	**bpftool-perf**\ (8),
-	**bpftool-prog**\ (8),
-	**bpftool-struct_ops**\ (8)
diff --git a/tools/bpf/bpftool/Documentation/bpftool-link.rst b/tools/bpf/bpftool/Documentation/bpftool-link.rst
index 4a52e7a93339..5f7db2a837cc 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-link.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-link.rst
@@ -21,7 +21,7 @@ LINK COMMANDS
 
 |	**bpftool** **link { show | list }** [*LINK*]
 |	**bpftool** **link pin** *LINK* *FILE*
-|	**bpftool** **link detach *LINK*
+|	**bpftool** **link detach** *LINK*
 |	**bpftool** **link help**
 |
 |	*LINK* := { **id** *LINK_ID* | **pinned** *FILE* }
@@ -62,18 +62,7 @@ DESCRIPTION
 
 OPTIONS
 =======
-	-h, --help
-		  Print short generic help message (similar to **bpftool help**).
-
-	-V, --version
-		  Print version number (similar to **bpftool version**).
-
-	-j, --json
-		  Generate JSON output. For commands that cannot produce JSON, this
-		  option has no effect.
-
-	-p, --pretty
-		  Generate human-readable JSON output. Implies **-j**.
+	.. include:: common_options.rst
 
 	-f, --bpffs
 		  When showing BPF links, show file names of pinned
@@ -83,10 +72,6 @@ OPTIONS
 		  Do not automatically attempt to mount any virtual file system
 		  (such as tracefs or BPF virtual file system) when necessary.
 
-	-d, --debug
-		  Print all logs available, even debug-level information. This
-		  includes logs from libbpf.
-
 EXAMPLES
 ========
 **# bpftool link show**
@@ -121,20 +106,3 @@ EXAMPLES
 ::
 
     -rw------- 1 root root 0 Apr 23 21:39 link
-
-
-SEE ALSO
-========
-	**bpf**\ (2),
-	**bpf-helpers**\ (7),
-	**bpftool**\ (8),
-	**bpftool-btf**\ (8),
-	**bpftool-cgroup**\ (8),
-	**bpftool-feature**\ (8),
-	**bpftool-gen**\ (8),
-	**bpftool-iter**\ (8),
-	**bpftool-map**\ (8),
-	**bpftool-net**\ (8),
-	**bpftool-perf**\ (8),
-	**bpftool-prog**\ (8),
-	**bpftool-struct_ops**\ (8)
diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst
index 083db6c2fc67..dade10cdf295 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-map.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst
@@ -23,7 +23,8 @@ MAP COMMANDS
 
 |	**bpftool** **map** { **show** | **list** }   [*MAP*]
 |	**bpftool** **map create**     *FILE* **type** *TYPE* **key** *KEY_SIZE* **value** *VALUE_SIZE* \
-|		**entries** *MAX_ENTRIES* **name** *NAME* [**flags** *FLAGS*] [**dev** *NAME*]
+|		**entries** *MAX_ENTRIES* **name** *NAME* [**flags** *FLAGS*] [**inner_map** *MAP*] \
+|		[**dev** *NAME*]
 |	**bpftool** **map dump**       *MAP*
 |	**bpftool** **map update**     *MAP* [**key** *DATA*] [**value** *VALUE*] [*UPDATE_FLAGS*]
 |	**bpftool** **map lookup**     *MAP* [**key** *DATA*]
@@ -67,7 +68,7 @@ DESCRIPTION
 		  maps. On such kernels bpftool will automatically emit this
 		  information as well.
 
-	**bpftool map create** *FILE* **type** *TYPE* **key** *KEY_SIZE* **value** *VALUE_SIZE*  **entries** *MAX_ENTRIES* **name** *NAME* [**flags** *FLAGS*] [**dev** *NAME*]
+	**bpftool map create** *FILE* **type** *TYPE* **key** *KEY_SIZE* **value** *VALUE_SIZE*  **entries** *MAX_ENTRIES* **name** *NAME* [**flags** *FLAGS*] [**inner_map** *MAP*] [**dev** *NAME*]
 		  Create a new map with given parameters and pin it to *bpffs*
 		  as *FILE*.
 
@@ -75,6 +76,11 @@ DESCRIPTION
 		  desired flags, e.g. 1024 for **BPF_F_MMAPABLE** (see bpf.h
 		  UAPI header for existing flags).
 
+		  To create maps of type array-of-maps or hash-of-maps, the
+		  **inner_map** keyword must be used to pass an inner map. The
+		  kernel needs it to collect metadata related to the inner maps
+		  that the new map will work with.
+
 		  Keyword **dev** expects a network interface name, and is used
 		  to request hardware offload for the map.
 
@@ -155,18 +161,7 @@ DESCRIPTION
 
 OPTIONS
 =======
-	-h, --help
-		  Print short generic help message (similar to **bpftool help**).
-
-	-V, --version
-		  Print version number (similar to **bpftool version**).
-
-	-j, --json
-		  Generate JSON output. For commands that cannot produce JSON, this
-		  option has no effect.
-
-	-p, --pretty
-		  Generate human-readable JSON output. Implies **-j**.
+	.. include:: common_options.rst
 
 	-f, --bpffs
 		  Show file names of pinned maps.
@@ -175,13 +170,10 @@ OPTIONS
 		  Do not automatically attempt to mount any virtual file system
 		  (such as tracefs or BPF virtual file system) when necessary.
 
-	-d, --debug
-		  Print all logs available from libbpf, including debug-level
-		  information.
-
 EXAMPLES
 ========
 **# bpftool map show**
+
 ::
 
   10: hash  name some_map  flags 0x0
@@ -203,6 +195,7 @@ The following three commands are equivalent:
 
 
 **# bpftool map dump id 10**
+
 ::
 
   key: 00 01 02 03  value: 00 01 02 03 04 05 06 07
@@ -210,6 +203,7 @@ The following three commands are equivalent:
   Found 2 elements
 
 **# bpftool map getnext id 10 key 0 1 2 3**
+
 ::
 
   key:
@@ -276,19 +270,3 @@ would be lost as soon as bpftool exits).
 
   key: 00 00 00 00  value: 22 02 00 00
   Found 1 element
-
-SEE ALSO
-========
-	**bpf**\ (2),
-	**bpf-helpers**\ (7),
-	**bpftool**\ (8),
-	**bpftool-btf**\ (8),
-	**bpftool-cgroup**\ (8),
-	**bpftool-feature**\ (8),
-	**bpftool-gen**\ (8),
-	**bpftool-iter**\ (8),
-	**bpftool-link**\ (8),
-	**bpftool-net**\ (8),
-	**bpftool-perf**\ (8),
-	**bpftool-prog**\ (8),
-	**bpftool-struct_ops**\ (8)
diff --git a/tools/bpf/bpftool/Documentation/bpftool-net.rst b/tools/bpf/bpftool/Documentation/bpftool-net.rst
index aa7450736179..d8165d530937 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-net.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-net.rst
@@ -75,22 +75,7 @@ DESCRIPTION
 
 OPTIONS
 =======
-	-h, --help
-		  Print short generic help message (similar to **bpftool help**).
-
-	-V, --version
-		  Print version number (similar to **bpftool version**).
-
-	-j, --json
-		  Generate JSON output. For commands that cannot produce JSON, this
-		  option has no effect.
-
-	-p, --pretty
-		  Generate human-readable JSON output. Implies **-j**.
-
-	-d, --debug
-		  Print all logs available from libbpf, including debug-level
-		  information.
+	.. include:: common_options.rst
 
 EXAMPLES
 ========
@@ -187,20 +172,3 @@ EXAMPLES
 ::
 
       xdp:
-
-
-SEE ALSO
-========
-	**bpf**\ (2),
-	**bpf-helpers**\ (7),
-	**bpftool**\ (8),
-	**bpftool-btf**\ (8),
-	**bpftool-cgroup**\ (8),
-	**bpftool-feature**\ (8),
-	**bpftool-gen**\ (8),
-	**bpftool-iter**\ (8),
-	**bpftool-link**\ (8),
-	**bpftool-map**\ (8),
-	**bpftool-perf**\ (8),
-	**bpftool-prog**\ (8),
-	**bpftool-struct_ops**\ (8)
diff --git a/tools/bpf/bpftool/Documentation/bpftool-perf.rst b/tools/bpf/bpftool/Documentation/bpftool-perf.rst
index 9c592b7c6775..e958ce91de72 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-perf.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-perf.rst
@@ -40,22 +40,7 @@ DESCRIPTION
 
 OPTIONS
 =======
-	-h, --help
-		  Print short generic help message (similar to **bpftool help**).
-
-	-V, --version
-		  Print version number (similar to **bpftool version**).
-
-	-j, --json
-		  Generate JSON output. For commands that cannot produce JSON, this
-		  option has no effect.
-
-	-p, --pretty
-		  Generate human-readable JSON output. Implies **-j**.
-
-	-d, --debug
-		  Print all logs available from libbpf, including debug-level
-		  information.
+	.. include:: common_options.rst
 
 EXAMPLES
 ========
@@ -78,20 +63,3 @@ EXAMPLES
      {"pid":21765,"fd":5,"prog_id":7,"fd_type":"kretprobe","func":"__x64_sys_nanosleep","offset":0}, \
      {"pid":21767,"fd":5,"prog_id":8,"fd_type":"tracepoint","tracepoint":"sys_enter_nanosleep"}, \
      {"pid":21800,"fd":5,"prog_id":9,"fd_type":"uprobe","filename":"/home/yhs/a.out","offset":1159}]
-
-
-SEE ALSO
-========
-	**bpf**\ (2),
-	**bpf-helpers**\ (7),
-	**bpftool**\ (8),
-	**bpftool-btf**\ (8),
-	**bpftool-cgroup**\ (8),
-	**bpftool-feature**\ (8),
-	**bpftool-gen**\ (8),
-	**bpftool-iter**\ (8),
-	**bpftool-link**\ (8),
-	**bpftool-map**\ (8),
-	**bpftool-net**\ (8),
-	**bpftool-prog**\ (8),
-	**bpftool-struct_ops**\ (8)
diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
index 82e356b664e8..358c7309d419 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
@@ -210,18 +210,7 @@ DESCRIPTION
 
 OPTIONS
 =======
-	-h, --help
-		  Print short generic help message (similar to **bpftool help**).
-
-	-V, --version
-		  Print version number (similar to **bpftool version**).
-
-	-j, --json
-		  Generate JSON output. For commands that cannot produce JSON, this
-		  option has no effect.
-
-	-p, --pretty
-		  Generate human-readable JSON output. Implies **-j**.
+	.. include:: common_options.rst
 
 	-f, --bpffs
 		  When showing BPF programs, show file names of pinned
@@ -234,11 +223,6 @@ OPTIONS
 		  Do not automatically attempt to mount any virtual file system
 		  (such as tracefs or BPF virtual file system) when necessary.
 
-	-d, --debug
-		  Print all logs available, even debug-level information. This
-		  includes logs from libbpf as well as from the verifier, when
-		  attempting to load programs.
-
 EXAMPLES
 ========
 **# bpftool prog show**
@@ -342,19 +326,3 @@ EXAMPLES
       40176203 cycles                                                 (83.05%)
       42518139 instructions    #   1.06 insns per cycle               (83.39%)
            123 llc_misses      #   2.89 LLC misses per million insns  (83.15%)
-
-SEE ALSO
-========
-	**bpf**\ (2),
-	**bpf-helpers**\ (7),
-	**bpftool**\ (8),
-	**bpftool-btf**\ (8),
-	**bpftool-cgroup**\ (8),
-	**bpftool-feature**\ (8),
-	**bpftool-gen**\ (8),
-	**bpftool-iter**\ (8),
-	**bpftool-link**\ (8),
-	**bpftool-map**\ (8),
-	**bpftool-net**\ (8),
-	**bpftool-perf**\ (8),
-	**bpftool-struct_ops**\ (8)
diff --git a/tools/bpf/bpftool/Documentation/bpftool-struct_ops.rst b/tools/bpf/bpftool/Documentation/bpftool-struct_ops.rst
index d93cd1cb8b0f..506e70ee78e9 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-struct_ops.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-struct_ops.rst
@@ -60,23 +60,7 @@ DESCRIPTION
 
 OPTIONS
 =======
-	-h, --help
-		  Print short generic help message (similar to **bpftool help**).
-
-	-V, --version
-		  Print version number (similar to **bpftool version**).
-
-	-j, --json
-		  Generate JSON output. For commands that cannot produce JSON, this
-		  option has no effect.
-
-	-p, --pretty
-		  Generate human-readable JSON output. Implies **-j**.
-
-	-d, --debug
-		  Print all logs available, even debug-level information. This
-		  includes logs from libbpf as well as from the verifier, when
-		  attempting to load programs.
+	.. include:: common_options.rst
 
 EXAMPLES
 ========
@@ -98,20 +82,3 @@ EXAMPLES
 ::
 
    Registered tcp_congestion_ops cubic id 110
-
-
-SEE ALSO
-========
-	**bpf**\ (2),
-	**bpf-helpers**\ (7),
-	**bpftool**\ (8),
-	**bpftool-btf**\ (8),
-	**bpftool-cgroup**\ (8),
-	**bpftool-feature**\ (8),
-	**bpftool-gen**\ (8),
-	**bpftool-iter**\ (8),
-	**bpftool-link**\ (8),
-	**bpftool-map**\ (8),
-	**bpftool-net**\ (8),
-	**bpftool-perf**\ (8),
-	**bpftool-prog**\ (8)
diff --git a/tools/bpf/bpftool/Documentation/bpftool.rst b/tools/bpf/bpftool/Documentation/bpftool.rst
index 420d4d5df8b6..e7d949334961 100644
--- a/tools/bpf/bpftool/Documentation/bpftool.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool.rst
@@ -46,18 +46,7 @@ DESCRIPTION
 
 OPTIONS
 =======
-	-h, --help
-		  Print short help message (similar to **bpftool help**).
-
-	-V, --version
-		  Print version number (similar to **bpftool version**).
-
-	-j, --json
-		  Generate JSON output. For commands that cannot produce JSON, this
-		  option has no effect.
-
-	-p, --pretty
-		  Generate human-readable JSON output. Implies **-j**.
+	.. include:: common_options.rst
 
 	-m, --mapcompat
 		  Allow loading maps with unknown map definitions.
@@ -65,24 +54,3 @@ OPTIONS
 	-n, --nomount
 		  Do not automatically attempt to mount any virtual file system
 		  (such as tracefs or BPF virtual file system) when necessary.
-
-	-d, --debug
-		  Print all logs available, even debug-level information. This
-		  includes logs from libbpf as well as from the verifier, when
-		  attempting to load programs.
-
-SEE ALSO
-========
-	**bpf**\ (2),
-	**bpf-helpers**\ (7),
-	**bpftool-btf**\ (8),
-	**bpftool-cgroup**\ (8),
-	**bpftool-feature**\ (8),
-	**bpftool-gen**\ (8),
-	**bpftool-iter**\ (8),
-	**bpftool-link**\ (8),
-	**bpftool-map**\ (8),
-	**bpftool-net**\ (8),
-	**bpftool-perf**\ (8),
-	**bpftool-prog**\ (8),
-	**bpftool-struct_ops**\ (8)
diff --git a/tools/bpf/bpftool/Documentation/common_options.rst b/tools/bpf/bpftool/Documentation/common_options.rst
new file mode 100644
index 000000000000..05d06c74dcaa
--- /dev/null
+++ b/tools/bpf/bpftool/Documentation/common_options.rst
@@ -0,0 +1,22 @@
+-h, --help
+	  Print short help message (similar to **bpftool help**).
+
+-V, --version
+	  Print version number (similar to **bpftool version**), and optional
+	  features that were included when bpftool was compiled. Optional
+	  features include linking against libbfd to provide the disassembler
+	  for JIT-ted programs (**bpftool prog dump jited**) and usage of BPF
+	  skeletons (some features like **bpftool prog profile** or showing
+	  pids associated to BPF objects may rely on it).
+
+-j, --json
+	  Generate JSON output. For commands that cannot produce JSON, this
+	  option has no effect.
+
+-p, --pretty
+	  Generate human-readable JSON output. Implies **-j**.
+
+-d, --debug
+	  Print all logs available, even debug-level information. This includes
+	  logs from libbpf as well as from the verifier, when attempting to
+	  load programs.
diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool
index 7b68e3c0a5fb..3f1da30c4da6 100644
--- a/tools/bpf/bpftool/bash-completion/bpftool
+++ b/tools/bpf/bpftool/bash-completion/bpftool
@@ -709,9 +709,26 @@ _bpftool()
                                                    "$cur" ) )
                             return 0
                             ;;
-                        key|value|flags|name|entries)
+                        key|value|flags|entries)
                             return 0
                             ;;
+                        inner_map)
+                            COMPREPLY=( $( compgen -W "$MAP_TYPE" -- "$cur" ) )
+                            return 0
+                            ;;
+                        id)
+                            _bpftool_get_map_ids
+                            ;;
+                        name)
+                            case $pprev in
+                                inner_map)
+                                    _bpftool_get_map_names
+                                    ;;
+                                *)
+                                    return 0
+                                    ;;
+                            esac
+                            ;;
                         *)
                             _bpftool_once_attr 'type'
                             _bpftool_once_attr 'key'
@@ -719,6 +736,9 @@ _bpftool()
                             _bpftool_once_attr 'entries'
                             _bpftool_once_attr 'name'
                             _bpftool_once_attr 'flags'
+                            if _bpftool_search_list 'array_of_maps' 'hash_of_maps'; then
+                                _bpftool_once_attr 'inner_map'
+                            fi
                             _bpftool_once_attr 'dev'
                             return 0
                             ;;
diff --git a/tools/bpf/bpftool/json_writer.c b/tools/bpf/bpftool/json_writer.c
index 86501cd3c763..7fea83bedf48 100644
--- a/tools/bpf/bpftool/json_writer.c
+++ b/tools/bpf/bpftool/json_writer.c
@@ -119,6 +119,12 @@ void jsonw_pretty(json_writer_t *self, bool on)
 	self->pretty = on;
 }
 
+void jsonw_reset(json_writer_t *self)
+{
+	assert(self->depth == 0);
+	self->sep = '\0';
+}
+
 /* Basic blocks */
 static void jsonw_begin(json_writer_t *self, int c)
 {
diff --git a/tools/bpf/bpftool/json_writer.h b/tools/bpf/bpftool/json_writer.h
index 35cf1f00f96c..8ace65cdb92f 100644
--- a/tools/bpf/bpftool/json_writer.h
+++ b/tools/bpf/bpftool/json_writer.h
@@ -27,6 +27,9 @@ void jsonw_destroy(json_writer_t **self_p);
 /* Cause output to have pretty whitespace */
 void jsonw_pretty(json_writer_t *self, bool on);
 
+/* Reset separator to create new JSON */
+void jsonw_reset(json_writer_t *self);
+
 /* Add property name */
 void jsonw_name(json_writer_t *self, const char *name);
 
diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c
index 4a191fcbeb82..682daaa49e6a 100644
--- a/tools/bpf/bpftool/main.c
+++ b/tools/bpf/bpftool/main.c
@@ -70,13 +70,42 @@ static int do_help(int argc, char **argv)
 
 static int do_version(int argc, char **argv)
 {
+#ifdef HAVE_LIBBFD_SUPPORT
+	const bool has_libbfd = true;
+#else
+	const bool has_libbfd = false;
+#endif
+#ifdef BPFTOOL_WITHOUT_SKELETONS
+	const bool has_skeletons = false;
+#else
+	const bool has_skeletons = true;
+#endif
+
 	if (json_output) {
-		jsonw_start_object(json_wtr);
+		jsonw_start_object(json_wtr);	/* root object */
+
 		jsonw_name(json_wtr, "version");
 		jsonw_printf(json_wtr, "\"%s\"", BPFTOOL_VERSION);
-		jsonw_end_object(json_wtr);
+
+		jsonw_name(json_wtr, "features");
+		jsonw_start_object(json_wtr);	/* features */
+		jsonw_bool_field(json_wtr, "libbfd", has_libbfd);
+		jsonw_bool_field(json_wtr, "skeletons", has_skeletons);
+		jsonw_end_object(json_wtr);	/* features */
+
+		jsonw_end_object(json_wtr);	/* root object */
 	} else {
+		unsigned int nb_features = 0;
+
 		printf("%s v%s\n", bin_name, BPFTOOL_VERSION);
+		printf("features:");
+		if (has_libbfd) {
+			printf(" libbfd");
+			nb_features++;
+		}
+		if (has_skeletons)
+			printf("%s skeletons", nb_features++ ? "," : "");
+		printf("\n");
 	}
 	return 0;
 }
diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index bc0071228f88..a7efbd84fbcc 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -213,8 +213,9 @@ static void print_entry_json(struct bpf_map_info *info, unsigned char *key,
 	jsonw_end_object(json_wtr);
 }
 
-static void print_entry_error(struct bpf_map_info *info, unsigned char *key,
-			      const char *error_msg)
+static void
+print_entry_error_msg(struct bpf_map_info *info, unsigned char *key,
+		      const char *error_msg)
 {
 	int msg_size = strlen(error_msg);
 	bool single_line, break_names;
@@ -232,6 +233,40 @@ static void print_entry_error(struct bpf_map_info *info, unsigned char *key,
 	printf("\n");
 }
 
+static void
+print_entry_error(struct bpf_map_info *map_info, void *key, int lookup_errno)
+{
+	/* For prog_array maps or arrays of maps, failure to lookup the value
+	 * means there is no entry for that key. Do not print an error message
+	 * in that case.
+	 */
+	if ((map_is_map_of_maps(map_info->type) ||
+	     map_is_map_of_progs(map_info->type)) && lookup_errno == ENOENT)
+		return;
+
+	if (json_output) {
+		jsonw_start_object(json_wtr);	/* entry */
+		jsonw_name(json_wtr, "key");
+		print_hex_data_json(key, map_info->key_size);
+		jsonw_name(json_wtr, "value");
+		jsonw_start_object(json_wtr);	/* error */
+		jsonw_string_field(json_wtr, "error", strerror(lookup_errno));
+		jsonw_end_object(json_wtr);	/* error */
+		jsonw_end_object(json_wtr);	/* entry */
+	} else {
+		const char *msg = NULL;
+
+		if (lookup_errno == ENOENT)
+			msg = "<no entry>";
+		else if (lookup_errno == ENOSPC &&
+			 map_info->type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY)
+			msg = "<cannot read>";
+
+		print_entry_error_msg(map_info, key,
+				      msg ? : strerror(lookup_errno));
+	}
+}
+
 static void print_entry_plain(struct bpf_map_info *info, unsigned char *key,
 			      unsigned char *value)
 {
@@ -713,56 +748,23 @@ static int dump_map_elem(int fd, void *key, void *value,
 			 struct bpf_map_info *map_info, struct btf *btf,
 			 json_writer_t *btf_wtr)
 {
-	int num_elems = 0;
-	int lookup_errno;
-
-	if (!bpf_map_lookup_elem(fd, key, value)) {
-		if (json_output) {
-			print_entry_json(map_info, key, value, btf);
-		} else {
-			if (btf) {
-				struct btf_dumper d = {
-					.btf = btf,
-					.jw = btf_wtr,
-					.is_plain_text = true,
-				};
-
-				do_dump_btf(&d, map_info, key, value);
-			} else {
-				print_entry_plain(map_info, key, value);
-			}
-			num_elems++;
-		}
-		return num_elems;
+	if (bpf_map_lookup_elem(fd, key, value)) {
+		print_entry_error(map_info, key, errno);
+		return -1;
 	}
 
-	/* lookup error handling */
-	lookup_errno = errno;
-
-	if (map_is_map_of_maps(map_info->type) ||
-	    map_is_map_of_progs(map_info->type))
-		return 0;
-
 	if (json_output) {
-		jsonw_start_object(json_wtr);
-		jsonw_name(json_wtr, "key");
-		print_hex_data_json(key, map_info->key_size);
-		jsonw_name(json_wtr, "value");
-		jsonw_start_object(json_wtr);
-		jsonw_string_field(json_wtr, "error", strerror(lookup_errno));
-		jsonw_end_object(json_wtr);
-		jsonw_end_object(json_wtr);
-	} else {
-		const char *msg = NULL;
-
-		if (lookup_errno == ENOENT)
-			msg = "<no entry>";
-		else if (lookup_errno == ENOSPC &&
-			 map_info->type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY)
-			msg = "<cannot read>";
+		print_entry_json(map_info, key, value, btf);
+	} else if (btf) {
+		struct btf_dumper d = {
+			.btf = btf,
+			.jw = btf_wtr,
+			.is_plain_text = true,
+		};
 
-		print_entry_error(map_info, key,
-				  msg ? : strerror(lookup_errno));
+		do_dump_btf(&d, map_info, key, value);
+	} else {
+		print_entry_plain(map_info, key, value);
 	}
 
 	return 0;
@@ -873,7 +875,8 @@ map_dump(int fd, struct bpf_map_info *info, json_writer_t *wtr,
 				err = 0;
 			break;
 		}
-		num_elems += dump_map_elem(fd, key, value, info, btf, wtr);
+		if (!dump_map_elem(fd, key, value, info, btf, wtr))
+			num_elems++;
 		prev_key = key;
 	}
 
@@ -1247,7 +1250,7 @@ static int do_create(int argc, char **argv)
 {
 	struct bpf_create_map_attr attr = { NULL, };
 	const char *pinfile;
-	int err, fd;
+	int err = -1, fd;
 
 	if (!REQ_ARGS(7))
 		return -1;
@@ -1262,13 +1265,13 @@ static int do_create(int argc, char **argv)
 
 			if (attr.map_type) {
 				p_err("map type already specified");
-				return -1;
+				goto exit;
 			}
 
 			attr.map_type = map_type_from_str(*argv);
 			if ((int)attr.map_type < 0) {
 				p_err("unrecognized map type: %s", *argv);
-				return -1;
+				goto exit;
 			}
 			NEXT_ARG();
 		} else if (is_prefix(*argv, "name")) {
@@ -1277,43 +1280,56 @@ static int do_create(int argc, char **argv)
 		} else if (is_prefix(*argv, "key")) {
 			if (parse_u32_arg(&argc, &argv, &attr.key_size,
 					  "key size"))
-				return -1;
+				goto exit;
 		} else if (is_prefix(*argv, "value")) {
 			if (parse_u32_arg(&argc, &argv, &attr.value_size,
 					  "value size"))
-				return -1;
+				goto exit;
 		} else if (is_prefix(*argv, "entries")) {
 			if (parse_u32_arg(&argc, &argv, &attr.max_entries,
 					  "max entries"))
-				return -1;
+				goto exit;
 		} else if (is_prefix(*argv, "flags")) {
 			if (parse_u32_arg(&argc, &argv, &attr.map_flags,
 					  "flags"))
-				return -1;
+				goto exit;
 		} else if (is_prefix(*argv, "dev")) {
 			NEXT_ARG();
 
 			if (attr.map_ifindex) {
 				p_err("offload device already specified");
-				return -1;
+				goto exit;
 			}
 
 			attr.map_ifindex = if_nametoindex(*argv);
 			if (!attr.map_ifindex) {
 				p_err("unrecognized netdevice '%s': %s",
 				      *argv, strerror(errno));
-				return -1;
+				goto exit;
 			}
 			NEXT_ARG();
+		} else if (is_prefix(*argv, "inner_map")) {
+			struct bpf_map_info info = {};
+			__u32 len = sizeof(info);
+			int inner_map_fd;
+
+			NEXT_ARG();
+			if (!REQ_ARGS(2))
+				usage();
+			inner_map_fd = map_parse_fd_and_info(&argc, &argv,
+							     &info, &len);
+			if (inner_map_fd < 0)
+				return -1;
+			attr.inner_map_fd = inner_map_fd;
 		} else {
 			p_err("unknown arg %s", *argv);
-			return -1;
+			goto exit;
 		}
 	}
 
 	if (!attr.name) {
 		p_err("map name not specified");
-		return -1;
+		goto exit;
 	}
 
 	set_max_rlimit();
@@ -1321,17 +1337,22 @@ static int do_create(int argc, char **argv)
 	fd = bpf_create_map_xattr(&attr);
 	if (fd < 0) {
 		p_err("map create failed: %s", strerror(errno));
-		return -1;
+		goto exit;
 	}
 
 	err = do_pin_fd(fd, pinfile);
 	close(fd);
 	if (err)
-		return err;
+		goto exit;
 
 	if (json_output)
 		jsonw_null(json_wtr);
-	return 0;
+
+exit:
+	if (attr.inner_map_fd > 0)
+		close(attr.inner_map_fd);
+
+	return err;
 }
 
 static int do_pop_dequeue(int argc, char **argv)
@@ -1417,7 +1438,7 @@ static int do_help(int argc, char **argv)
 		"Usage: %1$s %2$s { show | list }   [MAP]\n"
 		"       %1$s %2$s create     FILE type TYPE key KEY_SIZE value VALUE_SIZE \\\n"
 		"                                  entries MAX_ENTRIES name NAME [flags FLAGS] \\\n"
-		"                                  [dev NAME]\n"
+		"                                  [inner_map MAP] [dev NAME]\n"
 		"       %1$s %2$s dump       MAP\n"
 		"       %1$s %2$s update     MAP [key DATA] [value VALUE] [UPDATE_FLAGS]\n"
 		"       %1$s %2$s lookup     MAP [key DATA]\n"
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index d393eb8263a6..d942c1e3372c 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -29,6 +29,9 @@
 #include "main.h"
 #include "xlated_dumper.h"
 
+#define BPF_METADATA_PREFIX "bpf_metadata_"
+#define BPF_METADATA_PREFIX_LEN (sizeof(BPF_METADATA_PREFIX) - 1)
+
 const char * const prog_type_name[] = {
 	[BPF_PROG_TYPE_UNSPEC]			= "unspec",
 	[BPF_PROG_TYPE_SOCKET_FILTER]		= "socket_filter",
@@ -151,6 +154,198 @@ static void show_prog_maps(int fd, __u32 num_maps)
 	}
 }
 
+static void *find_metadata(int prog_fd, struct bpf_map_info *map_info)
+{
+	struct bpf_prog_info prog_info;
+	__u32 prog_info_len;
+	__u32 map_info_len;
+	void *value = NULL;
+	__u32 *map_ids;
+	int nr_maps;
+	int key = 0;
+	int map_fd;
+	int ret;
+	__u32 i;
+
+	memset(&prog_info, 0, sizeof(prog_info));
+	prog_info_len = sizeof(prog_info);
+	ret = bpf_obj_get_info_by_fd(prog_fd, &prog_info, &prog_info_len);
+	if (ret)
+		return NULL;
+
+	if (!prog_info.nr_map_ids)
+		return NULL;
+
+	map_ids = calloc(prog_info.nr_map_ids, sizeof(__u32));
+	if (!map_ids)
+		return NULL;
+
+	nr_maps = prog_info.nr_map_ids;
+	memset(&prog_info, 0, sizeof(prog_info));
+	prog_info.nr_map_ids = nr_maps;
+	prog_info.map_ids = ptr_to_u64(map_ids);
+	prog_info_len = sizeof(prog_info);
+
+	ret = bpf_obj_get_info_by_fd(prog_fd, &prog_info, &prog_info_len);
+	if (ret)
+		goto free_map_ids;
+
+	for (i = 0; i < prog_info.nr_map_ids; i++) {
+		map_fd = bpf_map_get_fd_by_id(map_ids[i]);
+		if (map_fd < 0)
+			goto free_map_ids;
+
+		memset(map_info, 0, sizeof(*map_info));
+		map_info_len = sizeof(*map_info);
+		ret = bpf_obj_get_info_by_fd(map_fd, map_info, &map_info_len);
+		if (ret < 0) {
+			close(map_fd);
+			goto free_map_ids;
+		}
+
+		if (map_info->type != BPF_MAP_TYPE_ARRAY ||
+		    map_info->key_size != sizeof(int) ||
+		    map_info->max_entries != 1 ||
+		    !map_info->btf_value_type_id ||
+		    !strstr(map_info->name, ".rodata")) {
+			close(map_fd);
+			continue;
+		}
+
+		value = malloc(map_info->value_size);
+		if (!value) {
+			close(map_fd);
+			goto free_map_ids;
+		}
+
+		if (bpf_map_lookup_elem(map_fd, &key, value)) {
+			close(map_fd);
+			free(value);
+			value = NULL;
+			goto free_map_ids;
+		}
+
+		close(map_fd);
+		break;
+	}
+
+free_map_ids:
+	free(map_ids);
+	return value;
+}
+
+static bool has_metadata_prefix(const char *s)
+{
+	return strncmp(s, BPF_METADATA_PREFIX, BPF_METADATA_PREFIX_LEN) == 0;
+}
+
+static void show_prog_metadata(int fd, __u32 num_maps)
+{
+	const struct btf_type *t_datasec, *t_var;
+	struct bpf_map_info map_info;
+	struct btf_var_secinfo *vsi;
+	bool printed_header = false;
+	struct btf *btf = NULL;
+	unsigned int i, vlen;
+	void *value = NULL;
+	const char *name;
+	int err;
+
+	if (!num_maps)
+		return;
+
+	memset(&map_info, 0, sizeof(map_info));
+	value = find_metadata(fd, &map_info);
+	if (!value)
+		return;
+
+	err = btf__get_from_id(map_info.btf_id, &btf);
+	if (err || !btf)
+		goto out_free;
+
+	t_datasec = btf__type_by_id(btf, map_info.btf_value_type_id);
+	if (!btf_is_datasec(t_datasec))
+		goto out_free;
+
+	vlen = btf_vlen(t_datasec);
+	vsi = btf_var_secinfos(t_datasec);
+
+	/* We don't proceed to check the kinds of the elements of the DATASEC.
+	 * The verifier enforces them to be BTF_KIND_VAR.
+	 */
+
+	if (json_output) {
+		struct btf_dumper d = {
+			.btf = btf,
+			.jw = json_wtr,
+			.is_plain_text = false,
+		};
+
+		for (i = 0; i < vlen; i++, vsi++) {
+			t_var = btf__type_by_id(btf, vsi->type);
+			name = btf__name_by_offset(btf, t_var->name_off);
+
+			if (!has_metadata_prefix(name))
+				continue;
+
+			if (!printed_header) {
+				jsonw_name(json_wtr, "metadata");
+				jsonw_start_object(json_wtr);
+				printed_header = true;
+			}
+
+			jsonw_name(json_wtr, name + BPF_METADATA_PREFIX_LEN);
+			err = btf_dumper_type(&d, t_var->type, value + vsi->offset);
+			if (err) {
+				p_err("btf dump failed: %d", err);
+				break;
+			}
+		}
+		if (printed_header)
+			jsonw_end_object(json_wtr);
+	} else {
+		json_writer_t *btf_wtr = jsonw_new(stdout);
+		struct btf_dumper d = {
+			.btf = btf,
+			.jw = btf_wtr,
+			.is_plain_text = true,
+		};
+
+		if (!btf_wtr) {
+			p_err("jsonw alloc failed");
+			goto out_free;
+		}
+
+		for (i = 0; i < vlen; i++, vsi++) {
+			t_var = btf__type_by_id(btf, vsi->type);
+			name = btf__name_by_offset(btf, t_var->name_off);
+
+			if (!has_metadata_prefix(name))
+				continue;
+
+			if (!printed_header) {
+				printf("\tmetadata:");
+				printed_header = true;
+			}
+
+			printf("\n\t\t%s = ", name + BPF_METADATA_PREFIX_LEN);
+
+			jsonw_reset(btf_wtr);
+			err = btf_dumper_type(&d, t_var->type, value + vsi->offset);
+			if (err) {
+				p_err("btf dump failed: %d", err);
+				break;
+			}
+		}
+		if (printed_header)
+			jsonw_destroy(&btf_wtr);
+	}
+
+out_free:
+	btf__free(btf);
+	free(value);
+}
+
 static void print_prog_header_json(struct bpf_prog_info *info)
 {
 	jsonw_uint_field(json_wtr, "id", info->id);
@@ -228,6 +423,8 @@ static void print_prog_json(struct bpf_prog_info *info, int fd)
 
 	emit_obj_refs_json(&refs_table, info->id, json_wtr);
 
+	show_prog_metadata(fd, info->nr_map_ids);
+
 	jsonw_end_object(json_wtr);
 }
 
@@ -297,6 +494,8 @@ static void print_prog_plain(struct bpf_prog_info *info, int fd)
 	emit_obj_refs_plain(&refs_table, info->id, "\n\tpids ");
 
 	printf("\n");
+
+	show_prog_metadata(fd, info->nr_map_ids);
 }
 
 static int show_prog(int fd)
@@ -1304,7 +1503,7 @@ static int load_with_options(int argc, char **argv, bool first_prog_only)
 		enum bpf_prog_type prog_type = common_prog_type;
 
 		if (prog_type == BPF_PROG_TYPE_UNSPEC) {
-			const char *sec_name = bpf_program__title(pos, false);
+			const char *sec_name = bpf_program__section_name(pos);
 
 			err = get_prog_type_by_name(sec_name, &prog_type,
 						    &expected_attach_type);
@@ -1398,7 +1597,7 @@ static int load_with_options(int argc, char **argv, bool first_prog_only)
 		err = bpf_obj_pin(bpf_program__fd(prog), pinfile);
 		if (err) {
 			p_err("failed to pin program %s",
-			      bpf_program__title(prog, false));
+			      bpf_program__section_name(prog));
 			goto err_close_obj;
 		}
 	} else {
diff --git a/tools/bpf/resolve_btfids/Makefile b/tools/bpf/resolve_btfids/Makefile
index a88cd4426398..66cb92136de4 100644
--- a/tools/bpf/resolve_btfids/Makefile
+++ b/tools/bpf/resolve_btfids/Makefile
@@ -1,5 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0-only
 include ../../scripts/Makefile.include
+include ../../scripts/Makefile.arch
 
 ifeq ($(srctree),)
 srctree := $(patsubst %/,%,$(dir $(CURDIR)))
@@ -29,6 +30,7 @@ endif
 AR       = $(HOSTAR)
 CC       = $(HOSTCC)
 LD       = $(HOSTLD)
+ARCH     = $(HOSTARCH)
 
 OUTPUT ?= $(srctree)/tools/bpf/resolve_btfids/
 
@@ -80,6 +82,7 @@ libbpf-clean:
 clean: libsubcmd-clean libbpf-clean fixdep-clean
 	$(call msg,CLEAN,$(BINARY))
 	$(Q)$(RM) -f $(BINARY); \
+	$(RM) -rf $(if $(OUTPUT),$(OUTPUT),.)/feature; \
 	find $(if $(OUTPUT),$(OUTPUT),.) -name \*.o -or -name \*.o.cmd -or -name \*.o.d | xargs $(RM)
 
 tags:
diff --git a/tools/include/linux/btf_ids.h b/tools/include/linux/btf_ids.h
index 210b086188a3..57890b357f85 100644
--- a/tools/include/linux/btf_ids.h
+++ b/tools/include/linux/btf_ids.h
@@ -76,6 +76,13 @@ extern u32 name[];
 #define BTF_ID_LIST_GLOBAL(name)			\
 __BTF_ID_LIST(name, globl)
 
+/* The BTF_ID_LIST_SINGLE macro defines a BTF_ID_LIST with
+ * a single entry.
+ */
+#define BTF_ID_LIST_SINGLE(name, prefix, typename)	\
+	BTF_ID_LIST(name) \
+	BTF_ID(prefix, typename)
+
 /*
  * The BTF_ID_UNUSED macro defines 4 zero bytes.
  * It's used when we want to define 'unused' entry
@@ -140,6 +147,7 @@ extern struct btf_id_set name;
 #define BTF_ID(prefix, name)
 #define BTF_ID_UNUSED
 #define BTF_ID_LIST_GLOBAL(name) u32 name[1];
+#define BTF_ID_LIST_SINGLE(name, prefix, typename) static u32 name[1];
 #define BTF_SET_START(name) static struct btf_id_set name = { 0 };
 #define BTF_SET_START_GLOBAL(name) static struct btf_id_set name = { 0 };
 #define BTF_SET_END(name)
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 8dda13880957..4f556cfcbfbe 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -124,6 +124,7 @@ enum bpf_cmd {
 	BPF_ENABLE_STATS,
 	BPF_ITER_CREATE,
 	BPF_LINK_DETACH,
+	BPF_PROG_BIND_MAP,
 };
 
 enum bpf_map_type {
@@ -413,6 +414,9 @@ enum {
 
 /* Enable memory-mapping BPF map */
 	BPF_F_MMAPABLE		= (1U << 10),
+
+/* Share perf_event among processes */
+	BPF_F_PRESERVE_ELEMS	= (1U << 11),
 };
 
 /* Flags for BPF_PROG_QUERY. */
@@ -423,6 +427,11 @@ enum {
  */
 #define BPF_F_QUERY_EFFECTIVE	(1U << 0)
 
+/* Flags for BPF_PROG_TEST_RUN */
+
+/* If set, run the test on the cpu specified by bpf_attr.test.cpu */
+#define BPF_F_TEST_RUN_ON_CPU	(1U << 0)
+
 /* type for BPF_ENABLE_STATS */
 enum bpf_stats_type {
 	/* enabled run_time_ns and run_cnt */
@@ -565,6 +574,8 @@ union bpf_attr {
 						 */
 		__aligned_u64	ctx_in;
 		__aligned_u64	ctx_out;
+		__u32		flags;
+		__u32		cpu;
 	} test;
 
 	struct { /* anonymous struct used by BPF_*_GET_*_ID */
@@ -631,8 +642,13 @@ union bpf_attr {
 		};
 		__u32		attach_type;	/* attach type */
 		__u32		flags;		/* extra flags */
-		__aligned_u64	iter_info;	/* extra bpf_iter_link_info */
-		__u32		iter_info_len;	/* iter_info length */
+		union {
+			__u32		target_btf_id;	/* btf_id of target to attach to */
+			struct {
+				__aligned_u64	iter_info;	/* extra bpf_iter_link_info */
+				__u32		iter_info_len;	/* iter_info length */
+			};
+		};
 	} link_create;
 
 	struct { /* struct used by BPF_LINK_UPDATE command */
@@ -658,6 +674,12 @@ union bpf_attr {
 		__u32		flags;
 	} iter_create;
 
+	struct { /* struct used by BPF_PROG_BIND_MAP command */
+		__u32		prog_fd;
+		__u32		map_fd;
+		__u32		flags;		/* extra flags */
+	} prog_bind_map;
+
 } __attribute__((aligned(8)));
 
 /* The description below is an attempt at providing documentation to eBPF
@@ -1447,8 +1469,8 @@ union bpf_attr {
  * 	Return
  * 		The return value depends on the result of the test, and can be:
  *
- * 		* 0, if the *skb* task belongs to the cgroup2.
- * 		* 1, if the *skb* task does not belong to the cgroup2.
+ *		* 0, if current task belongs to the cgroup2.
+ *		* 1, if current task does not belong to the cgroup2.
  * 		* A negative error code, if an error occurred.
  *
  * long bpf_skb_change_tail(struct sk_buff *skb, u32 len, u64 flags)
@@ -2505,7 +2527,7 @@ union bpf_attr {
  *		result is from *reuse*\ **->socks**\ [] using the hash of the
  *		tuple.
  *
- * long bpf_sk_release(struct bpf_sock *sock)
+ * long bpf_sk_release(void *sock)
  *	Description
  *		Release the reference held by *sock*. *sock* must be a
  *		non-**NULL** pointer that was returned from
@@ -2685,7 +2707,7 @@ union bpf_attr {
  *		result is from *reuse*\ **->socks**\ [] using the hash of the
  *		tuple.
  *
- * long bpf_tcp_check_syncookie(struct bpf_sock *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len)
+ * long bpf_tcp_check_syncookie(void *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len)
  * 	Description
  * 		Check whether *iph* and *th* contain a valid SYN cookie ACK for
  * 		the listening socket in *sk*.
@@ -2854,6 +2876,7 @@ union bpf_attr {
  *		0 on success.
  *
  *		**-ENOENT** if the bpf-local-storage cannot be found.
+ *		**-EINVAL** if sk is not a fullsock (e.g. a request_sock).
  *
  * long bpf_send_signal(u32 sig)
  *	Description
@@ -2870,7 +2893,7 @@ union bpf_attr {
  *
  *		**-EAGAIN** if bpf program can try again.
  *
- * s64 bpf_tcp_gen_syncookie(struct bpf_sock *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len)
+ * s64 bpf_tcp_gen_syncookie(void *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len)
  *	Description
  *		Try to issue a SYN cookie for the packet with corresponding
  *		IP/TCP headers, *iph* and *th*, on the listening socket in *sk*.
@@ -3099,7 +3122,7 @@ union bpf_attr {
  * 	Return
  * 		The id is returned or 0 in case the id could not be retrieved.
  *
- * long bpf_sk_assign(struct sk_buff *skb, struct bpf_sock *sk, u64 flags)
+ * long bpf_sk_assign(struct sk_buff *skb, void *sk, u64 flags)
  *	Description
  *		Helper is overloaded depending on BPF program type. This
  *		description applies to **BPF_PROG_TYPE_SCHED_CLS** and
@@ -3227,11 +3250,11 @@ union bpf_attr {
  *
  *		**-EOVERFLOW** if an overflow happened: The same object will be tried again.
  *
- * u64 bpf_sk_cgroup_id(struct bpf_sock *sk)
+ * u64 bpf_sk_cgroup_id(void *sk)
  *	Description
  *		Return the cgroup v2 id of the socket *sk*.
  *
- *		*sk* must be a non-**NULL** pointer to a full socket, e.g. one
+ *		*sk* must be a non-**NULL** pointer to a socket, e.g. one
  *		returned from **bpf_sk_lookup_xxx**\ (),
  *		**bpf_sk_fullsock**\ (), etc. The format of returned id is
  *		same as in **bpf_skb_cgroup_id**\ ().
@@ -3241,7 +3264,7 @@ union bpf_attr {
  *	Return
  *		The id is returned or 0 in case the id could not be retrieved.
  *
- * u64 bpf_sk_ancestor_cgroup_id(struct bpf_sock *sk, int ancestor_level)
+ * u64 bpf_sk_ancestor_cgroup_id(void *sk, int ancestor_level)
  *	Description
  *		Return id of cgroup v2 that is ancestor of cgroup associated
  *		with the *sk* at the *ancestor_level*.  The root cgroup is at
@@ -3349,38 +3372,38 @@ union bpf_attr {
  *	Description
  *		Dynamically cast a *sk* pointer to a *tcp6_sock* pointer.
  *	Return
- *		*sk* if casting is valid, or NULL otherwise.
+ *		*sk* if casting is valid, or **NULL** otherwise.
  *
  * struct tcp_sock *bpf_skc_to_tcp_sock(void *sk)
  *	Description
  *		Dynamically cast a *sk* pointer to a *tcp_sock* pointer.
  *	Return
- *		*sk* if casting is valid, or NULL otherwise.
+ *		*sk* if casting is valid, or **NULL** otherwise.
  *
  * struct tcp_timewait_sock *bpf_skc_to_tcp_timewait_sock(void *sk)
  * 	Description
  *		Dynamically cast a *sk* pointer to a *tcp_timewait_sock* pointer.
  *	Return
- *		*sk* if casting is valid, or NULL otherwise.
+ *		*sk* if casting is valid, or **NULL** otherwise.
  *
  * struct tcp_request_sock *bpf_skc_to_tcp_request_sock(void *sk)
  * 	Description
  *		Dynamically cast a *sk* pointer to a *tcp_request_sock* pointer.
  *	Return
- *		*sk* if casting is valid, or NULL otherwise.
+ *		*sk* if casting is valid, or **NULL** otherwise.
  *
  * struct udp6_sock *bpf_skc_to_udp6_sock(void *sk)
  * 	Description
  *		Dynamically cast a *sk* pointer to a *udp6_sock* pointer.
  *	Return
- *		*sk* if casting is valid, or NULL otherwise.
+ *		*sk* if casting is valid, or **NULL** otherwise.
  *
  * long bpf_get_task_stack(struct task_struct *task, void *buf, u32 size, u64 flags)
  *	Description
  *		Return a user or a kernel stack in bpf program provided buffer.
  *		To achieve this, the helper needs *task*, which is a valid
- *		pointer to struct task_struct. To store the stacktrace, the
- *		bpf program provides *buf* with	a nonnegative *size*.
+ *		pointer to **struct task_struct**. To store the stacktrace, the
+ *		bpf program provides *buf* with a nonnegative *size*.
  *
  *		The last argument, *flags*, holds the number of stack frames to
  *		skip (from 0 to 255), masked with
@@ -3410,12 +3433,12 @@ union bpf_attr {
  * long bpf_load_hdr_opt(struct bpf_sock_ops *skops, void *searchby_res, u32 len, u64 flags)
  *	Description
  *		Load header option.  Support reading a particular TCP header
- *		option for bpf program (BPF_PROG_TYPE_SOCK_OPS).
+ *		option for bpf program (**BPF_PROG_TYPE_SOCK_OPS**).
  *
  *		If *flags* is 0, it will search the option from the
- *		sock_ops->skb_data.  The comment in "struct bpf_sock_ops"
+ *		*skops*\ **->skb_data**.  The comment in **struct bpf_sock_ops**
  *		has details on what skb_data contains under different
- *		sock_ops->op.
+ *		*skops*\ **->op**.
  *
  *		The first byte of the *searchby_res* specifies the
  *		kind that it wants to search.
@@ -3435,7 +3458,7 @@ union bpf_attr {
  *		[ 254, 4, 0xeB, 0x9F, 0, 0, .... 0 ].
  *
  *		To search for the standard window scale option (3),
- *		the searchby_res should be [ 3, 0, 0, .... 0 ].
+ *		the *searchby_res* should be [ 3, 0, 0, .... 0 ].
  *		Note, kind-length must be 0 for regular option.
  *
  *		Searching for No-Op (0) and End-of-Option-List (1) are
@@ -3445,27 +3468,30 @@ union bpf_attr {
  *		of a header option.
  *
  *		Supported flags:
+ *
  *		* **BPF_LOAD_HDR_OPT_TCP_SYN** to search from the
  *		  saved_syn packet or the just-received syn packet.
  *
  *	Return
- *		>0 when found, the header option is copied to *searchby_res*.
- *		The return value is the total length copied.
+ *		> 0 when found, the header option is copied to *searchby_res*.
+ *		The return value is the total length copied. On failure, a
+ *		negative error code is returned:
  *
- *		**-EINVAL** If param is invalid
+ *		**-EINVAL** if a parameter is invalid.
  *
- *		**-ENOMSG** The option is not found
+ *		**-ENOMSG** if the option is not found.
  *
- *		**-ENOENT** No syn packet available when
- *			    **BPF_LOAD_HDR_OPT_TCP_SYN** is used
+ *		**-ENOENT** if no syn packet is available when
+ *		**BPF_LOAD_HDR_OPT_TCP_SYN** is used.
  *
- *		**-ENOSPC** Not enough space.  Only *len* number of
- *			    bytes are copied.
+ *		**-ENOSPC** if there is not enough space.  Only *len* number of
+ *		bytes are copied.
  *
- *		**-EFAULT** Cannot parse the header options in the packet
+ *		**-EFAULT** on failure to parse the header options in the
+ *		packet.
  *
- *		**-EPERM** This helper cannot be used under the
- *			   current sock_ops->op.
+ *		**-EPERM** if the helper cannot be used under the current
+ *		*skops*\ **->op**.
  *
  * long bpf_store_hdr_opt(struct bpf_sock_ops *skops, const void *from, u32 len, u64 flags)
  *	Description
@@ -3483,44 +3509,44 @@ union bpf_attr {
  *		by searching the same option in the outgoing skb.
  *
  *		This helper can only be called during
- *		BPF_SOCK_OPS_WRITE_HDR_OPT_CB.
+ *		**BPF_SOCK_OPS_WRITE_HDR_OPT_CB**.
  *
  *	Return
  *		0 on success, or negative error in case of failure:
  *
- *		**-EINVAL** If param is invalid
+ *		**-EINVAL** If param is invalid.
  *
- *		**-ENOSPC** Not enough space in the header.
- *			    Nothing has been written
+ *		**-ENOSPC** if there is not enough space in the header.
+ *		Nothing has been written
  *
- *		**-EEXIST** The option has already existed
+ *		**-EEXIST** if the option already exists.
  *
- *		**-EFAULT** Cannot parse the existing header options
+ *		**-EFAULT** on failrue to parse the existing header options.
  *
- *		**-EPERM** This helper cannot be used under the
- *			   current sock_ops->op.
+ *		**-EPERM** if the helper cannot be used under the current
+ *		*skops*\ **->op**.
  *
  * long bpf_reserve_hdr_opt(struct bpf_sock_ops *skops, u32 len, u64 flags)
  *	Description
  *		Reserve *len* bytes for the bpf header option.  The
- *		space will be used by bpf_store_hdr_opt() later in
- *		BPF_SOCK_OPS_WRITE_HDR_OPT_CB.
+ *		space will be used by **bpf_store_hdr_opt**\ () later in
+ *		**BPF_SOCK_OPS_WRITE_HDR_OPT_CB**.
  *
- *		If bpf_reserve_hdr_opt() is called multiple times,
+ *		If **bpf_reserve_hdr_opt**\ () is called multiple times,
  *		the total number of bytes will be reserved.
  *
  *		This helper can only be called during
- *		BPF_SOCK_OPS_HDR_OPT_LEN_CB.
+ *		**BPF_SOCK_OPS_HDR_OPT_LEN_CB**.
  *
  *	Return
  *		0 on success, or negative error in case of failure:
  *
- *		**-EINVAL** if param is invalid
+ *		**-EINVAL** if a parameter is invalid.
  *
- *		**-ENOSPC** Not enough space in the header.
+ *		**-ENOSPC** if there is not enough space in the header.
  *
- *		**-EPERM** This helper cannot be used under the
- *			   current sock_ops->op.
+ *		**-EPERM** if the helper cannot be used under the current
+ *		*skops*\ **->op**.
  *
  * void *bpf_inode_storage_get(struct bpf_map *map, void *inode, void *value, u64 flags)
  *	Description
@@ -3560,9 +3586,9 @@ union bpf_attr {
  *
  * long bpf_d_path(struct path *path, char *buf, u32 sz)
  *	Description
- *		Return full path for given 'struct path' object, which
- *		needs to be the kernel BTF 'path' object. The path is
- *		returned in the provided buffer 'buf' of size 'sz' and
+ *		Return full path for given **struct path** object, which
+ *		needs to be the kernel BTF *path* object. The path is
+ *		returned in the provided buffer *buf* of size *sz* and
  *		is zero terminated.
  *
  *	Return
@@ -3573,9 +3599,75 @@ union bpf_attr {
  * long bpf_copy_from_user(void *dst, u32 size, const void *user_ptr)
  * 	Description
  * 		Read *size* bytes from user space address *user_ptr* and store
- * 		the data in *dst*. This is a wrapper of copy_from_user().
+ * 		the data in *dst*. This is a wrapper of **copy_from_user**\ ().
  * 	Return
  * 		0 on success, or a negative error in case of failure.
+ *
+ * long bpf_snprintf_btf(char *str, u32 str_size, struct btf_ptr *ptr, u32 btf_ptr_size, u64 flags)
+ *	Description
+ *		Use BTF to store a string representation of *ptr*->ptr in *str*,
+ *		using *ptr*->type_id.  This value should specify the type
+ *		that *ptr*->ptr points to. LLVM __builtin_btf_type_id(type, 1)
+ *		can be used to look up vmlinux BTF type ids. Traversing the
+ *		data structure using BTF, the type information and values are
+ *		stored in the first *str_size* - 1 bytes of *str*.  Safe copy of
+ *		the pointer data is carried out to avoid kernel crashes during
+ *		operation.  Smaller types can use string space on the stack;
+ *		larger programs can use map data to store the string
+ *		representation.
+ *
+ *		The string can be subsequently shared with userspace via
+ *		bpf_perf_event_output() or ring buffer interfaces.
+ *		bpf_trace_printk() is to be avoided as it places too small
+ *		a limit on string size to be useful.
+ *
+ *		*flags* is a combination of
+ *
+ *		**BTF_F_COMPACT**
+ *			no formatting around type information
+ *		**BTF_F_NONAME**
+ *			no struct/union member names/types
+ *		**BTF_F_PTR_RAW**
+ *			show raw (unobfuscated) pointer values;
+ *			equivalent to printk specifier %px.
+ *		**BTF_F_ZERO**
+ *			show zero-valued struct/union members; they
+ *			are not displayed by default
+ *
+ *	Return
+ *		The number of bytes that were written (or would have been
+ *		written if output had to be truncated due to string size),
+ *		or a negative error in cases of failure.
+ *
+ * long bpf_seq_printf_btf(struct seq_file *m, struct btf_ptr *ptr, u32 ptr_size, u64 flags)
+ *	Description
+ *		Use BTF to write to seq_write a string representation of
+ *		*ptr*->ptr, using *ptr*->type_id as per bpf_snprintf_btf().
+ *		*flags* are identical to those used for bpf_snprintf_btf.
+ *	Return
+ *		0 on success or a negative error in case of failure.
+ *
+ * u64 bpf_skb_cgroup_classid(struct sk_buff *skb)
+ * 	Description
+ * 		See **bpf_get_cgroup_classid**\ () for the main description.
+ * 		This helper differs from **bpf_get_cgroup_classid**\ () in that
+ * 		the cgroup v1 net_cls class is retrieved only from the *skb*'s
+ * 		associated socket instead of the current process.
+ * 	Return
+ * 		The id is returned or 0 in case the id could not be retrieved.
+ *
+ * long bpf_redirect_neigh(u32 ifindex, u64 flags)
+ * 	Description
+ * 		Redirect the packet to another net device of index *ifindex*
+ * 		and fill in L2 addresses from neighboring subsystem. This helper
+ * 		is somewhat similar to **bpf_redirect**\ (), except that it
+ * 		fills in e.g. MAC addresses based on the L3 information from
+ * 		the packet. This helper is supported for IPv4 and IPv6 protocols.
+ * 		The *flags* argument is reserved and must be 0. The helper is
+ * 		currently only supported for tc BPF program types.
+ * 	Return
+ * 		The helper returns **TC_ACT_REDIRECT** on success or
+ * 		**TC_ACT_SHOT** on error.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3727,6 +3819,10 @@ union bpf_attr {
 	FN(inode_storage_delete),	\
 	FN(d_path),			\
 	FN(copy_from_user),		\
+	FN(snprintf_btf),		\
+	FN(seq_printf_btf),		\
+	FN(skb_cgroup_classid),		\
+	FN(redirect_neigh),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
@@ -4835,4 +4931,34 @@ struct bpf_sk_lookup {
 	__u32 local_port;	/* Host byte order */
 };
 
+/*
+ * struct btf_ptr is used for typed pointer representation; the
+ * type id is used to render the pointer data as the appropriate type
+ * via the bpf_snprintf_btf() helper described above.  A flags field -
+ * potentially to specify additional details about the BTF pointer
+ * (rather than its mode of display) - is included for future use.
+ * Display flags - BTF_F_* - are passed to bpf_snprintf_btf separately.
+ */
+struct btf_ptr {
+	void *ptr;
+	__u32 type_id;
+	__u32 flags;		/* BTF ptr flags; unused at present. */
+};
+
+/*
+ * Flags to control bpf_snprintf_btf() behaviour.
+ *     - BTF_F_COMPACT: no formatting around type information
+ *     - BTF_F_NONAME: no struct/union member names/types
+ *     - BTF_F_PTR_RAW: show raw (unobfuscated) pointer values;
+ *       equivalent to %px.
+ *     - BTF_F_ZERO: show zero-valued struct/union members; they
+ *       are not displayed by default
+ */
+enum {
+	BTF_F_COMPACT	=	(1ULL << 0),
+	BTF_F_NONAME	=	(1ULL << 1),
+	BTF_F_PTR_RAW	=	(1ULL << 2),
+	BTF_F_ZERO	=	(1ULL << 3),
+};
+
 #endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h
index 3d0d8231dc19..7d6687618d80 100644
--- a/tools/include/uapi/linux/in.h
+++ b/tools/include/uapi/linux/in.h
@@ -135,7 +135,7 @@ struct in_addr {
  * this socket to prevent accepting spoofed ones.
  */
 #define IP_PMTUDISC_INTERFACE		4
-/* weaker version of IP_PMTUDISC_INTERFACE, which allos packets to get
+/* weaker version of IP_PMTUDISC_INTERFACE, which allows packets to get
  * fragmented if they exeed the interface mtu
  */
 #define IP_PMTUDISC_OMIT		5
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index f6d86033c4fa..7d8eced6f459 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -790,9 +790,10 @@ struct kvm_ppc_resize_hpt {
 #define KVM_VM_PPC_HV 1
 #define KVM_VM_PPC_PR 2
 
-/* on MIPS, 0 forces trap & emulate, 1 forces VZ ASE */
-#define KVM_VM_MIPS_TE		0
+/* on MIPS, 0 indicates auto, 1 forces VZ ASE, 2 forces trap & emulate */
+#define KVM_VM_MIPS_AUTO	0
 #define KVM_VM_MIPS_VZ		1
+#define KVM_VM_MIPS_TE		2
 
 #define KVM_S390_SIE_PAGE_OFFSET 1
 
@@ -1035,6 +1036,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_LAST_CPU 184
 #define KVM_CAP_SMALLER_MAXPHYADDR 185
 #define KVM_CAP_S390_DIAG318 186
+#define KVM_CAP_STEAL_TIME 187
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
diff --git a/tools/io_uring/io_uring-bench.c b/tools/io_uring/io_uring-bench.c
index 0f257139b003..7703f0118385 100644
--- a/tools/io_uring/io_uring-bench.c
+++ b/tools/io_uring/io_uring-bench.c
@@ -130,7 +130,7 @@ static int io_uring_register_files(struct submitter *s)
 					s->nr_files);
 }
 
-static int gettid(void)
+static int lk_gettid(void)
 {
 	return syscall(__NR_gettid);
 }
@@ -281,7 +281,7 @@ static void *submitter_fn(void *data)
 	struct io_sq_ring *ring = &s->sq_ring;
 	int ret, prepped;
 
-	printf("submitter=%d\n", gettid());
+	printf("submitter=%d\n", lk_gettid());
 
 	srand48_r(pthread_self(), &s->rand);
 
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index adbe994610f2..5f9abed3e226 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -62,7 +62,7 @@ FEATURE_USER = .libbpf
 FEATURE_TESTS = libelf zlib bpf
 FEATURE_DISPLAY = libelf zlib bpf
 
-INCLUDES = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(ARCH)/include/uapi -I$(srctree)/tools/include/uapi
+INCLUDES = -I. -I$(srctree)/tools/include -I$(srctree)/tools/include/uapi
 FEATURE_CHECK_CFLAGS-bpf = $(INCLUDES)
 
 check_feat := 1
@@ -98,19 +98,18 @@ PC_FILE		= libbpf.pc
 ifdef EXTRA_CFLAGS
   CFLAGS := $(EXTRA_CFLAGS)
 else
-  CFLAGS := -g -Wall
+  CFLAGS := -g -O2
 endif
 
 # Append required CFLAGS
 override CFLAGS += $(EXTRA_WARNINGS) -Wno-switch-enum
 override CFLAGS += -Werror -Wall
-override CFLAGS += -fPIC
 override CFLAGS += $(INCLUDES)
 override CFLAGS += -fvisibility=hidden
 override CFLAGS += -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64
 
 # flags specific for shared library
-SHLIB_FLAGS := -DSHARED
+SHLIB_FLAGS := -DSHARED -fPIC
 
 ifeq ($(VERBOSE),1)
   Q =
@@ -147,6 +146,7 @@ GLOBAL_SYM_COUNT = $(shell readelf -s --wide $(BPF_IN_SHARED) | \
 			   awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}' | \
 			   sort -u | wc -l)
 VERSIONED_SYM_COUNT = $(shell readelf --dyn-syms --wide $(OUTPUT)libbpf.so | \
+			      awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}' | \
 			      grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | sort -u | wc -l)
 
 CMD_TARGETS = $(LIB_TARGET) $(PC_FILE)
@@ -214,6 +214,7 @@ check_abi: $(OUTPUT)libbpf.so
 		    awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}'|  \
 		    sort -u > $(OUTPUT)libbpf_global_syms.tmp;		 \
 		readelf --dyn-syms --wide $(OUTPUT)libbpf.so |		 \
+		    awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}'|  \
 		    grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 |		 \
 		    sort -u > $(OUTPUT)libbpf_versioned_syms.tmp; 	 \
 		diff -u $(OUTPUT)libbpf_global_syms.tmp			 \
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 82b983ff6569..d27e34133973 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -586,19 +586,31 @@ int bpf_link_create(int prog_fd, int target_fd,
 		    enum bpf_attach_type attach_type,
 		    const struct bpf_link_create_opts *opts)
 {
+	__u32 target_btf_id, iter_info_len;
 	union bpf_attr attr;
 
 	if (!OPTS_VALID(opts, bpf_link_create_opts))
 		return -EINVAL;
 
+	iter_info_len = OPTS_GET(opts, iter_info_len, 0);
+	target_btf_id = OPTS_GET(opts, target_btf_id, 0);
+
+	if (iter_info_len && target_btf_id)
+		return -EINVAL;
+
 	memset(&attr, 0, sizeof(attr));
 	attr.link_create.prog_fd = prog_fd;
 	attr.link_create.target_fd = target_fd;
 	attr.link_create.attach_type = attach_type;
 	attr.link_create.flags = OPTS_GET(opts, flags, 0);
-	attr.link_create.iter_info =
-		ptr_to_u64(OPTS_GET(opts, iter_info, (void *)0));
-	attr.link_create.iter_info_len = OPTS_GET(opts, iter_info_len, 0);
+
+	if (iter_info_len) {
+		attr.link_create.iter_info =
+			ptr_to_u64(OPTS_GET(opts, iter_info, (void *)0));
+		attr.link_create.iter_info_len = iter_info_len;
+	} else if (target_btf_id) {
+		attr.link_create.target_btf_id = target_btf_id;
+	}
 
 	return sys_bpf(BPF_LINK_CREATE, &attr, sizeof(attr));
 }
@@ -712,6 +724,37 @@ int bpf_prog_test_run_xattr(struct bpf_prog_test_run_attr *test_attr)
 	return ret;
 }
 
+int bpf_prog_test_run_opts(int prog_fd, struct bpf_test_run_opts *opts)
+{
+	union bpf_attr attr;
+	int ret;
+
+	if (!OPTS_VALID(opts, bpf_test_run_opts))
+		return -EINVAL;
+
+	memset(&attr, 0, sizeof(attr));
+	attr.test.prog_fd = prog_fd;
+	attr.test.cpu = OPTS_GET(opts, cpu, 0);
+	attr.test.flags = OPTS_GET(opts, flags, 0);
+	attr.test.repeat = OPTS_GET(opts, repeat, 0);
+	attr.test.duration = OPTS_GET(opts, duration, 0);
+	attr.test.ctx_size_in = OPTS_GET(opts, ctx_size_in, 0);
+	attr.test.ctx_size_out = OPTS_GET(opts, ctx_size_out, 0);
+	attr.test.data_size_in = OPTS_GET(opts, data_size_in, 0);
+	attr.test.data_size_out = OPTS_GET(opts, data_size_out, 0);
+	attr.test.ctx_in = ptr_to_u64(OPTS_GET(opts, ctx_in, NULL));
+	attr.test.ctx_out = ptr_to_u64(OPTS_GET(opts, ctx_out, NULL));
+	attr.test.data_in = ptr_to_u64(OPTS_GET(opts, data_in, NULL));
+	attr.test.data_out = ptr_to_u64(OPTS_GET(opts, data_out, NULL));
+
+	ret = sys_bpf(BPF_PROG_TEST_RUN, &attr, sizeof(attr));
+	OPTS_SET(opts, data_size_out, attr.test.data_size_out);
+	OPTS_SET(opts, ctx_size_out, attr.test.ctx_size_out);
+	OPTS_SET(opts, duration, attr.test.duration);
+	OPTS_SET(opts, retval, attr.test.retval);
+	return ret;
+}
+
 static int bpf_obj_get_next_id(__u32 start_id, __u32 *next_id, int cmd)
 {
 	union bpf_attr attr;
@@ -815,7 +858,7 @@ int bpf_raw_tracepoint_open(const char *name, int prog_fd)
 	return sys_bpf(BPF_RAW_TRACEPOINT_OPEN, &attr, sizeof(attr));
 }
 
-int bpf_load_btf(void *btf, __u32 btf_size, char *log_buf, __u32 log_buf_size,
+int bpf_load_btf(const void *btf, __u32 btf_size, char *log_buf, __u32 log_buf_size,
 		 bool do_log)
 {
 	union bpf_attr attr = {};
@@ -872,3 +915,19 @@ int bpf_enable_stats(enum bpf_stats_type type)
 
 	return sys_bpf(BPF_ENABLE_STATS, &attr, sizeof(attr));
 }
+
+int bpf_prog_bind_map(int prog_fd, int map_fd,
+		      const struct bpf_prog_bind_opts *opts)
+{
+	union bpf_attr attr;
+
+	if (!OPTS_VALID(opts, bpf_prog_bind_opts))
+		return -EINVAL;
+
+	memset(&attr, 0, sizeof(attr));
+	attr.prog_bind_map.prog_fd = prog_fd;
+	attr.prog_bind_map.map_fd = map_fd;
+	attr.prog_bind_map.flags = OPTS_GET(opts, flags, 0);
+
+	return sys_bpf(BPF_PROG_BIND_MAP, &attr, sizeof(attr));
+}
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 015d13f25fcc..875dde20d56e 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -174,8 +174,9 @@ struct bpf_link_create_opts {
 	__u32 flags;
 	union bpf_iter_link_info *iter_info;
 	__u32 iter_info_len;
+	__u32 target_btf_id;
 };
-#define bpf_link_create_opts__last_field iter_info_len
+#define bpf_link_create_opts__last_field target_btf_id
 
 LIBBPF_API int bpf_link_create(int prog_fd, int target_fd,
 			       enum bpf_attach_type attach_type,
@@ -234,7 +235,7 @@ LIBBPF_API int bpf_prog_query(int target_fd, enum bpf_attach_type type,
 			      __u32 query_flags, __u32 *attach_flags,
 			      __u32 *prog_ids, __u32 *prog_cnt);
 LIBBPF_API int bpf_raw_tracepoint_open(const char *name, int prog_fd);
-LIBBPF_API int bpf_load_btf(void *btf, __u32 btf_size, char *log_buf,
+LIBBPF_API int bpf_load_btf(const void *btf, __u32 btf_size, char *log_buf,
 			    __u32 log_buf_size, bool do_log);
 LIBBPF_API int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf,
 				 __u32 *buf_len, __u32 *prog_id, __u32 *fd_type,
@@ -243,6 +244,40 @@ LIBBPF_API int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf,
 enum bpf_stats_type; /* defined in up-to-date linux/bpf.h */
 LIBBPF_API int bpf_enable_stats(enum bpf_stats_type type);
 
+struct bpf_prog_bind_opts {
+	size_t sz; /* size of this struct for forward/backward compatibility */
+	__u32 flags;
+};
+#define bpf_prog_bind_opts__last_field flags
+
+LIBBPF_API int bpf_prog_bind_map(int prog_fd, int map_fd,
+				 const struct bpf_prog_bind_opts *opts);
+
+struct bpf_test_run_opts {
+	size_t sz; /* size of this struct for forward/backward compatibility */
+	const void *data_in; /* optional */
+	void *data_out;      /* optional */
+	__u32 data_size_in;
+	__u32 data_size_out; /* in: max length of data_out
+			      * out: length of data_out
+			      */
+	const void *ctx_in; /* optional */
+	void *ctx_out;      /* optional */
+	__u32 ctx_size_in;
+	__u32 ctx_size_out; /* in: max length of ctx_out
+			     * out: length of cxt_out
+			     */
+	__u32 retval;        /* out: return code of the BPF program */
+	int repeat;
+	__u32 duration;      /* out: average per repetition in ns */
+	__u32 flags;
+	__u32 cpu;
+};
+#define bpf_test_run_opts__last_field cpu
+
+LIBBPF_API int bpf_prog_test_run_opts(int prog_fd,
+				      struct bpf_test_run_opts *opts);
+
 #ifdef __cplusplus
 } /* extern "C" */
 #endif
diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h
index 1106777df00b..2bdb7d6dbad2 100644
--- a/tools/lib/bpf/bpf_helpers.h
+++ b/tools/lib/bpf/bpf_helpers.h
@@ -54,6 +54,52 @@
 #endif
 
 /*
+ * Helper macro to throw a compilation error if __bpf_unreachable() gets
+ * built into the resulting code. This works given BPF back end does not
+ * implement __builtin_trap(). This is useful to assert that certain paths
+ * of the program code are never used and hence eliminated by the compiler.
+ *
+ * For example, consider a switch statement that covers known cases used by
+ * the program. __bpf_unreachable() can then reside in the default case. If
+ * the program gets extended such that a case is not covered in the switch
+ * statement, then it will throw a build error due to the default case not
+ * being compiled out.
+ */
+#ifndef __bpf_unreachable
+# define __bpf_unreachable()	__builtin_trap()
+#endif
+
+/*
+ * Helper function to perform a tail call with a constant/immediate map slot.
+ */
+static __always_inline void
+bpf_tail_call_static(void *ctx, const void *map, const __u32 slot)
+{
+	if (!__builtin_constant_p(slot))
+		__bpf_unreachable();
+
+	/*
+	 * Provide a hard guarantee that LLVM won't optimize setting r2 (map
+	 * pointer) and r3 (constant map index) from _different paths_ ending
+	 * up at the _same_ call insn as otherwise we won't be able to use the
+	 * jmpq/nopl retpoline-free patching by the x86-64 JIT in the kernel
+	 * given they mismatch. See also d2e4c1e6c294 ("bpf: Constant map key
+	 * tracking for prog array pokes") for details on verifier tracking.
+	 *
+	 * Note on clobber list: we need to stay in-line with BPF calling
+	 * convention, so even if we don't end up using r0, r4, r5, we need
+	 * to mark them as clobber so that LLVM doesn't end up using them
+	 * before / after the call.
+	 */
+	asm volatile("r1 = %[ctx]\n\t"
+		     "r2 = %[map]\n\t"
+		     "r3 = %[slot]\n\t"
+		     "call 12"
+		     :: [ctx]"r"(ctx), [map]"r"(map), [slot]"i"(slot)
+		     : "r0", "r1", "r2", "r3", "r4", "r5");
+}
+
+/*
  * Helper structure used by eBPF C program
  * to describe BPF map attributes to libbpf loader
  */
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index a3d259e614b0..231b07203e3d 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
 /* Copyright (c) 2018 Facebook */
 
+#include <byteswap.h>
 #include <endian.h>
 #include <stdio.h>
 #include <stdlib.h>
@@ -27,17 +28,72 @@
 static struct btf_type btf_void;
 
 struct btf {
-	union {
-		struct btf_header *hdr;
-		void *data;
-	};
-	struct btf_type **types;
-	const char *strings;
-	void *nohdr_data;
+	/* raw BTF data in native endianness */
+	void *raw_data;
+	/* raw BTF data in non-native endianness */
+	void *raw_data_swapped;
+	__u32 raw_size;
+	/* whether target endianness differs from the native one */
+	bool swapped_endian;
+
+	/*
+	 * When BTF is loaded from an ELF or raw memory it is stored
+	 * in a contiguous memory block. The hdr, type_data, and, strs_data
+	 * point inside that memory region to their respective parts of BTF
+	 * representation:
+	 *
+	 * +--------------------------------+
+	 * |  Header  |  Types  |  Strings  |
+	 * +--------------------------------+
+	 * ^          ^         ^
+	 * |          |         |
+	 * hdr        |         |
+	 * types_data-+         |
+	 * strs_data------------+
+	 *
+	 * If BTF data is later modified, e.g., due to types added or
+	 * removed, BTF deduplication performed, etc, this contiguous
+	 * representation is broken up into three independently allocated
+	 * memory regions to be able to modify them independently.
+	 * raw_data is nulled out at that point, but can be later allocated
+	 * and cached again if user calls btf__get_raw_data(), at which point
+	 * raw_data will contain a contiguous copy of header, types, and
+	 * strings:
+	 *
+	 * +----------+  +---------+  +-----------+
+	 * |  Header  |  |  Types  |  |  Strings  |
+	 * +----------+  +---------+  +-----------+
+	 * ^             ^            ^
+	 * |             |            |
+	 * hdr           |            |
+	 * types_data----+            |
+	 * strs_data------------------+
+	 *
+	 *               +----------+---------+-----------+
+	 *               |  Header  |  Types  |  Strings  |
+	 * raw_data----->+----------+---------+-----------+
+	 */
+	struct btf_header *hdr;
+
+	void *types_data;
+	size_t types_data_cap; /* used size stored in hdr->type_len */
+
+	/* type ID to `struct btf_type *` lookup index */
+	__u32 *type_offs;
+	size_t type_offs_cap;
 	__u32 nr_types;
-	__u32 types_size;
-	__u32 data_size;
+
+	void *strs_data;
+	size_t strs_data_cap; /* used size stored in hdr->str_len */
+
+	/* lookup index for each unique string in strings section */
+	struct hashmap *strs_hash;
+	/* whether strings are already deduplicated */
+	bool strs_deduped;
+	/* BTF object FD, if loaded into kernel */
 	int fd;
+
+	/* Pointer size (in bytes) for a target architecture of this BTF */
 	int ptr_sz;
 };
 
@@ -46,60 +102,114 @@ static inline __u64 ptr_to_u64(const void *ptr)
 	return (__u64) (unsigned long) ptr;
 }
 
-static int btf_add_type(struct btf *btf, struct btf_type *t)
+/* Ensure given dynamically allocated memory region pointed to by *data* with
+ * capacity of *cap_cnt* elements each taking *elem_sz* bytes has enough
+ * memory to accomodate *add_cnt* new elements, assuming *cur_cnt* elements
+ * are already used. At most *max_cnt* elements can be ever allocated.
+ * If necessary, memory is reallocated and all existing data is copied over,
+ * new pointer to the memory region is stored at *data, new memory region
+ * capacity (in number of elements) is stored in *cap.
+ * On success, memory pointer to the beginning of unused memory is returned.
+ * On error, NULL is returned.
+ */
+void *btf_add_mem(void **data, size_t *cap_cnt, size_t elem_sz,
+		  size_t cur_cnt, size_t max_cnt, size_t add_cnt)
 {
-	if (btf->types_size - btf->nr_types < 2) {
-		struct btf_type **new_types;
-		__u32 expand_by, new_size;
+	size_t new_cnt;
+	void *new_data;
 
-		if (btf->types_size == BTF_MAX_NR_TYPES)
-			return -E2BIG;
+	if (cur_cnt + add_cnt <= *cap_cnt)
+		return *data + cur_cnt * elem_sz;
 
-		expand_by = max(btf->types_size >> 2, 16U);
-		new_size = min(BTF_MAX_NR_TYPES, btf->types_size + expand_by);
+	/* requested more than the set limit */
+	if (cur_cnt + add_cnt > max_cnt)
+		return NULL;
 
-		new_types = libbpf_reallocarray(btf->types, new_size, sizeof(*new_types));
-		if (!new_types)
-			return -ENOMEM;
+	new_cnt = *cap_cnt;
+	new_cnt += new_cnt / 4;		  /* expand by 25% */
+	if (new_cnt < 16)		  /* but at least 16 elements */
+		new_cnt = 16;
+	if (new_cnt > max_cnt)		  /* but not exceeding a set limit */
+		new_cnt = max_cnt;
+	if (new_cnt < cur_cnt + add_cnt)  /* also ensure we have enough memory */
+		new_cnt = cur_cnt + add_cnt;
+
+	new_data = libbpf_reallocarray(*data, new_cnt, elem_sz);
+	if (!new_data)
+		return NULL;
 
-		if (btf->nr_types == 0)
-			new_types[0] = &btf_void;
+	/* zero out newly allocated portion of memory */
+	memset(new_data + (*cap_cnt) * elem_sz, 0, (new_cnt - *cap_cnt) * elem_sz);
 
-		btf->types = new_types;
-		btf->types_size = new_size;
-	}
+	*data = new_data;
+	*cap_cnt = new_cnt;
+	return new_data + cur_cnt * elem_sz;
+}
+
+/* Ensure given dynamically allocated memory region has enough allocated space
+ * to accommodate *need_cnt* elements of size *elem_sz* bytes each
+ */
+int btf_ensure_mem(void **data, size_t *cap_cnt, size_t elem_sz, size_t need_cnt)
+{
+	void *p;
+
+	if (need_cnt <= *cap_cnt)
+		return 0;
+
+	p = btf_add_mem(data, cap_cnt, elem_sz, *cap_cnt, SIZE_MAX, need_cnt - *cap_cnt);
+	if (!p)
+		return -ENOMEM;
+
+	return 0;
+}
 
-	btf->types[++(btf->nr_types)] = t;
+static int btf_add_type_idx_entry(struct btf *btf, __u32 type_off)
+{
+	__u32 *p;
 
+	p = btf_add_mem((void **)&btf->type_offs, &btf->type_offs_cap, sizeof(__u32),
+			btf->nr_types + 1, BTF_MAX_NR_TYPES, 1);
+	if (!p)
+		return -ENOMEM;
+
+	*p = type_off;
 	return 0;
 }
 
+static void btf_bswap_hdr(struct btf_header *h)
+{
+	h->magic = bswap_16(h->magic);
+	h->hdr_len = bswap_32(h->hdr_len);
+	h->type_off = bswap_32(h->type_off);
+	h->type_len = bswap_32(h->type_len);
+	h->str_off = bswap_32(h->str_off);
+	h->str_len = bswap_32(h->str_len);
+}
+
 static int btf_parse_hdr(struct btf *btf)
 {
-	const struct btf_header *hdr = btf->hdr;
+	struct btf_header *hdr = btf->hdr;
 	__u32 meta_left;
 
-	if (btf->data_size < sizeof(struct btf_header)) {
+	if (btf->raw_size < sizeof(struct btf_header)) {
 		pr_debug("BTF header not found\n");
 		return -EINVAL;
 	}
 
-	if (hdr->magic != BTF_MAGIC) {
+	if (hdr->magic == bswap_16(BTF_MAGIC)) {
+		btf->swapped_endian = true;
+		if (bswap_32(hdr->hdr_len) != sizeof(struct btf_header)) {
+			pr_warn("Can't load BTF with non-native endianness due to unsupported header length %u\n",
+				bswap_32(hdr->hdr_len));
+			return -ENOTSUP;
+		}
+		btf_bswap_hdr(hdr);
+	} else if (hdr->magic != BTF_MAGIC) {
 		pr_debug("Invalid BTF magic:%x\n", hdr->magic);
 		return -EINVAL;
 	}
 
-	if (hdr->version != BTF_VERSION) {
-		pr_debug("Unsupported BTF version:%u\n", hdr->version);
-		return -ENOTSUP;
-	}
-
-	if (hdr->flags) {
-		pr_debug("Unsupported BTF flags:%x\n", hdr->flags);
-		return -ENOTSUP;
-	}
-
-	meta_left = btf->data_size - sizeof(*hdr);
+	meta_left = btf->raw_size - sizeof(*hdr);
 	if (!meta_left) {
 		pr_debug("BTF has no data\n");
 		return -EINVAL;
@@ -125,15 +235,13 @@ static int btf_parse_hdr(struct btf *btf)
 		return -EINVAL;
 	}
 
-	btf->nohdr_data = btf->hdr + 1;
-
 	return 0;
 }
 
 static int btf_parse_str_sec(struct btf *btf)
 {
 	const struct btf_header *hdr = btf->hdr;
-	const char *start = btf->nohdr_data + hdr->str_off;
+	const char *start = btf->strs_data;
 	const char *end = start + btf->hdr->str_len;
 
 	if (!hdr->str_len || hdr->str_len - 1 > BTF_MAX_STR_OFFSET ||
@@ -142,14 +250,12 @@ static int btf_parse_str_sec(struct btf *btf)
 		return -EINVAL;
 	}
 
-	btf->strings = start;
-
 	return 0;
 }
 
-static int btf_type_size(struct btf_type *t)
+static int btf_type_size(const struct btf_type *t)
 {
-	int base_size = sizeof(struct btf_type);
+	const int base_size = sizeof(struct btf_type);
 	__u16 vlen = btf_vlen(t);
 
 	switch (btf_kind(t)) {
@@ -182,25 +288,120 @@ static int btf_type_size(struct btf_type *t)
 	}
 }
 
+static void btf_bswap_type_base(struct btf_type *t)
+{
+	t->name_off = bswap_32(t->name_off);
+	t->info = bswap_32(t->info);
+	t->type = bswap_32(t->type);
+}
+
+static int btf_bswap_type_rest(struct btf_type *t)
+{
+	struct btf_var_secinfo *v;
+	struct btf_member *m;
+	struct btf_array *a;
+	struct btf_param *p;
+	struct btf_enum *e;
+	__u16 vlen = btf_vlen(t);
+	int i;
+
+	switch (btf_kind(t)) {
+	case BTF_KIND_FWD:
+	case BTF_KIND_CONST:
+	case BTF_KIND_VOLATILE:
+	case BTF_KIND_RESTRICT:
+	case BTF_KIND_PTR:
+	case BTF_KIND_TYPEDEF:
+	case BTF_KIND_FUNC:
+		return 0;
+	case BTF_KIND_INT:
+		*(__u32 *)(t + 1) = bswap_32(*(__u32 *)(t + 1));
+		return 0;
+	case BTF_KIND_ENUM:
+		for (i = 0, e = btf_enum(t); i < vlen; i++, e++) {
+			e->name_off = bswap_32(e->name_off);
+			e->val = bswap_32(e->val);
+		}
+		return 0;
+	case BTF_KIND_ARRAY:
+		a = btf_array(t);
+		a->type = bswap_32(a->type);
+		a->index_type = bswap_32(a->index_type);
+		a->nelems = bswap_32(a->nelems);
+		return 0;
+	case BTF_KIND_STRUCT:
+	case BTF_KIND_UNION:
+		for (i = 0, m = btf_members(t); i < vlen; i++, m++) {
+			m->name_off = bswap_32(m->name_off);
+			m->type = bswap_32(m->type);
+			m->offset = bswap_32(m->offset);
+		}
+		return 0;
+	case BTF_KIND_FUNC_PROTO:
+		for (i = 0, p = btf_params(t); i < vlen; i++, p++) {
+			p->name_off = bswap_32(p->name_off);
+			p->type = bswap_32(p->type);
+		}
+		return 0;
+	case BTF_KIND_VAR:
+		btf_var(t)->linkage = bswap_32(btf_var(t)->linkage);
+		return 0;
+	case BTF_KIND_DATASEC:
+		for (i = 0, v = btf_var_secinfos(t); i < vlen; i++, v++) {
+			v->type = bswap_32(v->type);
+			v->offset = bswap_32(v->offset);
+			v->size = bswap_32(v->size);
+		}
+		return 0;
+	default:
+		pr_debug("Unsupported BTF_KIND:%u\n", btf_kind(t));
+		return -EINVAL;
+	}
+}
+
 static int btf_parse_type_sec(struct btf *btf)
 {
 	struct btf_header *hdr = btf->hdr;
-	void *nohdr_data = btf->nohdr_data;
-	void *next_type = nohdr_data + hdr->type_off;
-	void *end_type = nohdr_data + hdr->str_off;
+	void *next_type = btf->types_data;
+	void *end_type = next_type + hdr->type_len;
+	int err, i = 0, type_size;
 
-	while (next_type < end_type) {
-		struct btf_type *t = next_type;
-		int type_size;
-		int err;
+	/* VOID (type_id == 0) is specially handled by btf__get_type_by_id(),
+	 * so ensure we can never properly use its offset from index by
+	 * setting it to a large value
+	 */
+	err = btf_add_type_idx_entry(btf, UINT_MAX);
+	if (err)
+		return err;
+
+	while (next_type + sizeof(struct btf_type) <= end_type) {
+		i++;
+
+		if (btf->swapped_endian)
+			btf_bswap_type_base(next_type);
 
-		type_size = btf_type_size(t);
+		type_size = btf_type_size(next_type);
 		if (type_size < 0)
 			return type_size;
-		next_type += type_size;
-		err = btf_add_type(btf, t);
+		if (next_type + type_size > end_type) {
+			pr_warn("BTF type [%d] is malformed\n", i);
+			return -EINVAL;
+		}
+
+		if (btf->swapped_endian && btf_bswap_type_rest(next_type))
+			return -EINVAL;
+
+		err = btf_add_type_idx_entry(btf, next_type - btf->types_data);
 		if (err)
 			return err;
+
+		next_type += type_size;
+		btf->nr_types++;
+	}
+
+	if (next_type != end_type) {
+		pr_warn("BTF types data is malformed\n");
+		return -EINVAL;
 	}
 
 	return 0;
@@ -211,12 +412,20 @@ __u32 btf__get_nr_types(const struct btf *btf)
 	return btf->nr_types;
 }
 
+/* internal helper returning non-const pointer to a type */
+static struct btf_type *btf_type_by_id(struct btf *btf, __u32 type_id)
+{
+	if (type_id == 0)
+		return &btf_void;
+
+	return btf->types_data + btf->type_offs[type_id];
+}
+
 const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 type_id)
 {
 	if (type_id > btf->nr_types)
 		return NULL;
-
-	return btf->types[type_id];
+	return btf_type_by_id((struct btf *)btf, type_id);
 }
 
 static int determine_ptr_size(const struct btf *btf)
@@ -283,6 +492,38 @@ int btf__set_pointer_size(struct btf *btf, size_t ptr_sz)
 	return 0;
 }
 
+static bool is_host_big_endian(void)
+{
+#if __BYTE_ORDER == __LITTLE_ENDIAN
+	return false;
+#elif __BYTE_ORDER == __BIG_ENDIAN
+	return true;
+#else
+# error "Unrecognized __BYTE_ORDER__"
+#endif
+}
+
+enum btf_endianness btf__endianness(const struct btf *btf)
+{
+	if (is_host_big_endian())
+		return btf->swapped_endian ? BTF_LITTLE_ENDIAN : BTF_BIG_ENDIAN;
+	else
+		return btf->swapped_endian ? BTF_BIG_ENDIAN : BTF_LITTLE_ENDIAN;
+}
+
+int btf__set_endianness(struct btf *btf, enum btf_endianness endian)
+{
+	if (endian != BTF_LITTLE_ENDIAN && endian != BTF_BIG_ENDIAN)
+		return -EINVAL;
+
+	btf->swapped_endian = is_host_big_endian() != (endian == BTF_BIG_ENDIAN);
+	if (!btf->swapped_endian) {
+		free(btf->raw_data_swapped);
+		btf->raw_data_swapped = NULL;
+	}
+	return 0;
+}
+
 static bool btf_type_is_void(const struct btf_type *t)
 {
 	return t == &btf_void || btf_is_fwd(t);
@@ -414,7 +655,7 @@ __s32 btf__find_by_name(const struct btf *btf, const char *type_name)
 		return 0;
 
 	for (i = 1; i <= btf->nr_types; i++) {
-		const struct btf_type *t = btf->types[i];
+		const struct btf_type *t = btf__type_by_id(btf, i);
 		const char *name = btf__name_by_offset(btf, t->name_off);
 
 		if (name && !strcmp(type_name, name))
@@ -433,7 +674,7 @@ __s32 btf__find_by_name_kind(const struct btf *btf, const char *type_name,
 		return 0;
 
 	for (i = 1; i <= btf->nr_types; i++) {
-		const struct btf_type *t = btf->types[i];
+		const struct btf_type *t = btf__type_by_id(btf, i);
 		const char *name;
 
 		if (btf_kind(t) != kind)
@@ -446,6 +687,11 @@ __s32 btf__find_by_name_kind(const struct btf *btf, const char *type_name,
 	return -ENOENT;
 }
 
+static bool btf_is_modifiable(const struct btf *btf)
+{
+	return (void *)btf->hdr != btf->raw_data;
+}
+
 void btf__free(struct btf *btf)
 {
 	if (IS_ERR_OR_NULL(btf))
@@ -454,11 +700,55 @@ void btf__free(struct btf *btf)
 	if (btf->fd >= 0)
 		close(btf->fd);
 
-	free(btf->data);
-	free(btf->types);
+	if (btf_is_modifiable(btf)) {
+		/* if BTF was modified after loading, it will have a split
+		 * in-memory representation for header, types, and strings
+		 * sections, so we need to free all of them individually. It
+		 * might still have a cached contiguous raw data present,
+		 * which will be unconditionally freed below.
+		 */
+		free(btf->hdr);
+		free(btf->types_data);
+		free(btf->strs_data);
+	}
+	free(btf->raw_data);
+	free(btf->raw_data_swapped);
+	free(btf->type_offs);
 	free(btf);
 }
 
+struct btf *btf__new_empty(void)
+{
+	struct btf *btf;
+
+	btf = calloc(1, sizeof(*btf));
+	if (!btf)
+		return ERR_PTR(-ENOMEM);
+
+	btf->fd = -1;
+	btf->ptr_sz = sizeof(void *);
+	btf->swapped_endian = false;
+
+	/* +1 for empty string at offset 0 */
+	btf->raw_size = sizeof(struct btf_header) + 1;
+	btf->raw_data = calloc(1, btf->raw_size);
+	if (!btf->raw_data) {
+		free(btf);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	btf->hdr = btf->raw_data;
+	btf->hdr->hdr_len = sizeof(struct btf_header);
+	btf->hdr->magic = BTF_MAGIC;
+	btf->hdr->version = BTF_VERSION;
+
+	btf->types_data = btf->raw_data + btf->hdr->hdr_len;
+	btf->strs_data = btf->raw_data + btf->hdr->hdr_len;
+	btf->hdr->str_len = 1; /* empty string at offset 0 */
+
+	return btf;
+}
+
 struct btf *btf__new(const void *data, __u32 size)
 {
 	struct btf *btf;
@@ -468,26 +758,28 @@ struct btf *btf__new(const void *data, __u32 size)
 	if (!btf)
 		return ERR_PTR(-ENOMEM);
 
-	btf->fd = -1;
-
-	btf->data = malloc(size);
-	if (!btf->data) {
+	btf->raw_data = malloc(size);
+	if (!btf->raw_data) {
 		err = -ENOMEM;
 		goto done;
 	}
+	memcpy(btf->raw_data, data, size);
+	btf->raw_size = size;
 
-	memcpy(btf->data, data, size);
-	btf->data_size = size;
-
+	btf->hdr = btf->raw_data;
 	err = btf_parse_hdr(btf);
 	if (err)
 		goto done;
 
+	btf->strs_data = btf->raw_data + btf->hdr->hdr_len + btf->hdr->str_off;
+	btf->types_data = btf->raw_data + btf->hdr->hdr_len + btf->hdr->type_off;
+
 	err = btf_parse_str_sec(btf);
+	err = err ?: btf_parse_type_sec(btf);
 	if (err)
 		goto done;
 
-	err = btf_parse_type_sec(btf);
+	btf->fd = -1;
 
 done:
 	if (err) {
@@ -498,17 +790,6 @@ done:
 	return btf;
 }
 
-static bool btf_check_endianness(const GElf_Ehdr *ehdr)
-{
-#if __BYTE_ORDER == __LITTLE_ENDIAN
-	return ehdr->e_ident[EI_DATA] == ELFDATA2LSB;
-#elif __BYTE_ORDER == __BIG_ENDIAN
-	return ehdr->e_ident[EI_DATA] == ELFDATA2MSB;
-#else
-# error "Unrecognized __BYTE_ORDER__"
-#endif
-}
-
 struct btf *btf__parse_elf(const char *path, struct btf_ext **btf_ext)
 {
 	Elf_Data *btf_data = NULL, *btf_ext_data = NULL;
@@ -541,10 +822,6 @@ struct btf *btf__parse_elf(const char *path, struct btf_ext **btf_ext)
 		pr_warn("failed to get EHDR from %s\n", path);
 		goto done;
 	}
-	if (!btf_check_endianness(&ehdr)) {
-		pr_warn("non-native ELF endianness is not supported\n");
-		goto done;
-	}
 	if (!elf_rawdata(elf_getscn(elf, ehdr.e_shstrndx), NULL)) {
 		pr_warn("failed to get e_shstrndx from %s\n", path);
 		goto done;
@@ -656,7 +933,7 @@ struct btf *btf__parse_raw(const char *path)
 		err = -EIO;
 		goto err_out;
 	}
-	if (magic != BTF_MAGIC) {
+	if (magic != BTF_MAGIC && magic != bswap_16(BTF_MAGIC)) {
 		/* definitely not a raw BTF */
 		err = -EPROTO;
 		goto err_out;
@@ -789,7 +1066,7 @@ int btf__finalize_data(struct bpf_object *obj, struct btf *btf)
 	__u32 i;
 
 	for (i = 1; i <= btf->nr_types; i++) {
-		struct btf_type *t = btf->types[i];
+		struct btf_type *t = btf_type_by_id(btf, i);
 
 		/* Loader needs to fix up some of the things compiler
 		 * couldn't get its hands on while emitting BTF. This
@@ -806,10 +1083,13 @@ int btf__finalize_data(struct bpf_object *obj, struct btf *btf)
 	return err;
 }
 
+static void *btf_get_raw_data(const struct btf *btf, __u32 *size, bool swap_endian);
+
 int btf__load(struct btf *btf)
 {
-	__u32 log_buf_size = 0;
+	__u32 log_buf_size = 0, raw_size;
 	char *log_buf = NULL;
+	void *raw_data;
 	int err = 0;
 
 	if (btf->fd >= 0)
@@ -824,8 +1104,16 @@ retry_load:
 		*log_buf = 0;
 	}
 
-	btf->fd = bpf_load_btf(btf->data, btf->data_size,
-			       log_buf, log_buf_size, false);
+	raw_data = btf_get_raw_data(btf, &raw_size, false);
+	if (!raw_data) {
+		err = -ENOMEM;
+		goto done;
+	}
+	/* cache native raw data representation */
+	btf->raw_size = raw_size;
+	btf->raw_data = raw_data;
+
+	btf->fd = bpf_load_btf(raw_data, raw_size, log_buf, log_buf_size, false);
 	if (btf->fd < 0) {
 		if (!log_buf || errno == ENOSPC) {
 			log_buf_size = max((__u32)BPF_LOG_BUF_SIZE,
@@ -856,20 +1144,88 @@ void btf__set_fd(struct btf *btf, int fd)
 	btf->fd = fd;
 }
 
-const void *btf__get_raw_data(const struct btf *btf, __u32 *size)
+static void *btf_get_raw_data(const struct btf *btf, __u32 *size, bool swap_endian)
+{
+	struct btf_header *hdr = btf->hdr;
+	struct btf_type *t;
+	void *data, *p;
+	__u32 data_sz;
+	int i;
+
+	data = swap_endian ? btf->raw_data_swapped : btf->raw_data;
+	if (data) {
+		*size = btf->raw_size;
+		return data;
+	}
+
+	data_sz = hdr->hdr_len + hdr->type_len + hdr->str_len;
+	data = calloc(1, data_sz);
+	if (!data)
+		return NULL;
+	p = data;
+
+	memcpy(p, hdr, hdr->hdr_len);
+	if (swap_endian)
+		btf_bswap_hdr(p);
+	p += hdr->hdr_len;
+
+	memcpy(p, btf->types_data, hdr->type_len);
+	if (swap_endian) {
+		for (i = 1; i <= btf->nr_types; i++) {
+			t = p  + btf->type_offs[i];
+			/* btf_bswap_type_rest() relies on native t->info, so
+			 * we swap base type info after we swapped all the
+			 * additional information
+			 */
+			if (btf_bswap_type_rest(t))
+				goto err_out;
+			btf_bswap_type_base(t);
+		}
+	}
+	p += hdr->type_len;
+
+	memcpy(p, btf->strs_data, hdr->str_len);
+	p += hdr->str_len;
+
+	*size = data_sz;
+	return data;
+err_out:
+	free(data);
+	return NULL;
+}
+
+const void *btf__get_raw_data(const struct btf *btf_ro, __u32 *size)
 {
-	*size = btf->data_size;
-	return btf->data;
+	struct btf *btf = (struct btf *)btf_ro;
+	__u32 data_sz;
+	void *data;
+
+	data = btf_get_raw_data(btf, &data_sz, btf->swapped_endian);
+	if (!data)
+		return NULL;
+
+	btf->raw_size = data_sz;
+	if (btf->swapped_endian)
+		btf->raw_data_swapped = data;
+	else
+		btf->raw_data = data;
+	*size = data_sz;
+	return data;
 }
 
-const char *btf__name_by_offset(const struct btf *btf, __u32 offset)
+const char *btf__str_by_offset(const struct btf *btf, __u32 offset)
 {
 	if (offset < btf->hdr->str_len)
-		return &btf->strings[offset];
+		return btf->strs_data + offset;
 	else
 		return NULL;
 }
 
+const char *btf__name_by_offset(const struct btf *btf, __u32 offset)
+{
+	return btf__str_by_offset(btf, offset);
+}
+
 int btf__get_from_id(__u32 id, struct btf **btf)
 {
 	struct bpf_btf_info btf_info = { 0 };
@@ -1005,6 +1361,970 @@ int btf__get_map_kv_tids(const struct btf *btf, const char *map_name,
 	return 0;
 }
 
+static size_t strs_hash_fn(const void *key, void *ctx)
+{
+	struct btf *btf = ctx;
+	const char *str = btf->strs_data + (long)key;
+
+	return str_hash(str);
+}
+
+static bool strs_hash_equal_fn(const void *key1, const void *key2, void *ctx)
+{
+	struct btf *btf = ctx;
+	const char *str1 = btf->strs_data + (long)key1;
+	const char *str2 = btf->strs_data + (long)key2;
+
+	return strcmp(str1, str2) == 0;
+}
+
+static void btf_invalidate_raw_data(struct btf *btf)
+{
+	if (btf->raw_data) {
+		free(btf->raw_data);
+		btf->raw_data = NULL;
+	}
+	if (btf->raw_data_swapped) {
+		free(btf->raw_data_swapped);
+		btf->raw_data_swapped = NULL;
+	}
+}
+
+/* Ensure BTF is ready to be modified (by splitting into a three memory
+ * regions for header, types, and strings). Also invalidate cached
+ * raw_data, if any.
+ */
+static int btf_ensure_modifiable(struct btf *btf)
+{
+	void *hdr, *types, *strs, *strs_end, *s;
+	struct hashmap *hash = NULL;
+	long off;
+	int err;
+
+	if (btf_is_modifiable(btf)) {
+		/* any BTF modification invalidates raw_data */
+		btf_invalidate_raw_data(btf);
+		return 0;
+	}
+
+	/* split raw data into three memory regions */
+	hdr = malloc(btf->hdr->hdr_len);
+	types = malloc(btf->hdr->type_len);
+	strs = malloc(btf->hdr->str_len);
+	if (!hdr || !types || !strs)
+		goto err_out;
+
+	memcpy(hdr, btf->hdr, btf->hdr->hdr_len);
+	memcpy(types, btf->types_data, btf->hdr->type_len);
+	memcpy(strs, btf->strs_data, btf->hdr->str_len);
+
+	/* build lookup index for all strings */
+	hash = hashmap__new(strs_hash_fn, strs_hash_equal_fn, btf);
+	if (IS_ERR(hash)) {
+		err = PTR_ERR(hash);
+		hash = NULL;
+		goto err_out;
+	}
+
+	strs_end = strs + btf->hdr->str_len;
+	for (off = 0, s = strs; s < strs_end; off += strlen(s) + 1, s = strs + off) {
+		/* hashmap__add() returns EEXIST if string with the same
+		 * content already is in the hash map
+		 */
+		err = hashmap__add(hash, (void *)off, (void *)off);
+		if (err == -EEXIST)
+			continue; /* duplicate */
+		if (err)
+			goto err_out;
+	}
+
+	/* only when everything was successful, update internal state */
+	btf->hdr = hdr;
+	btf->types_data = types;
+	btf->types_data_cap = btf->hdr->type_len;
+	btf->strs_data = strs;
+	btf->strs_data_cap = btf->hdr->str_len;
+	btf->strs_hash = hash;
+	/* if BTF was created from scratch, all strings are guaranteed to be
+	 * unique and deduplicated
+	 */
+	btf->strs_deduped = btf->hdr->str_len <= 1;
+
+	/* invalidate raw_data representation */
+	btf_invalidate_raw_data(btf);
+
+	return 0;
+
+err_out:
+	hashmap__free(hash);
+	free(hdr);
+	free(types);
+	free(strs);
+	return -ENOMEM;
+}
+
+static void *btf_add_str_mem(struct btf *btf, size_t add_sz)
+{
+	return btf_add_mem(&btf->strs_data, &btf->strs_data_cap, 1,
+			   btf->hdr->str_len, BTF_MAX_STR_OFFSET, add_sz);
+}
+
+/* Find an offset in BTF string section that corresponds to a given string *s*.
+ * Returns:
+ *   - >0 offset into string section, if string is found;
+ *   - -ENOENT, if string is not in the string section;
+ *   - <0, on any other error.
+ */
+int btf__find_str(struct btf *btf, const char *s)
+{
+	long old_off, new_off, len;
+	void *p;
+
+	/* BTF needs to be in a modifiable state to build string lookup index */
+	if (btf_ensure_modifiable(btf))
+		return -ENOMEM;
+
+	/* see btf__add_str() for why we do this */
+	len = strlen(s) + 1;
+	p = btf_add_str_mem(btf, len);
+	if (!p)
+		return -ENOMEM;
+
+	new_off = btf->hdr->str_len;
+	memcpy(p, s, len);
+
+	if (hashmap__find(btf->strs_hash, (void *)new_off, (void **)&old_off))
+		return old_off;
+
+	return -ENOENT;
+}
+
+/* Add a string s to the BTF string section.
+ * Returns:
+ *   - > 0 offset into string section, on success;
+ *   - < 0, on error.
+ */
+int btf__add_str(struct btf *btf, const char *s)
+{
+	long old_off, new_off, len;
+	void *p;
+	int err;
+
+	if (btf_ensure_modifiable(btf))
+		return -ENOMEM;
+
+	/* Hashmap keys are always offsets within btf->strs_data, so to even
+	 * look up some string from the "outside", we need to first append it
+	 * at the end, so that it can be addressed with an offset. Luckily,
+	 * until btf->hdr->str_len is incremented, that string is just a piece
+	 * of garbage for the rest of BTF code, so no harm, no foul. On the
+	 * other hand, if the string is unique, it's already appended and
+	 * ready to be used, only a simple btf->hdr->str_len increment away.
+	 */
+	len = strlen(s) + 1;
+	p = btf_add_str_mem(btf, len);
+	if (!p)
+		return -ENOMEM;
+
+	new_off = btf->hdr->str_len;
+	memcpy(p, s, len);
+
+	/* Now attempt to add the string, but only if the string with the same
+	 * contents doesn't exist already (HASHMAP_ADD strategy). If such
+	 * string exists, we'll get its offset in old_off (that's old_key).
+	 */
+	err = hashmap__insert(btf->strs_hash, (void *)new_off, (void *)new_off,
+			      HASHMAP_ADD, (const void **)&old_off, NULL);
+	if (err == -EEXIST)
+		return old_off; /* duplicated string, return existing offset */
+	if (err)
+		return err;
+
+	btf->hdr->str_len += len; /* new unique string, adjust data length */
+	return new_off;
+}
+
+static void *btf_add_type_mem(struct btf *btf, size_t add_sz)
+{
+	return btf_add_mem(&btf->types_data, &btf->types_data_cap, 1,
+			   btf->hdr->type_len, UINT_MAX, add_sz);
+}
+
+static __u32 btf_type_info(int kind, int vlen, int kflag)
+{
+	return (kflag << 31) | (kind << 24) | vlen;
+}
+
+static void btf_type_inc_vlen(struct btf_type *t)
+{
+	t->info = btf_type_info(btf_kind(t), btf_vlen(t) + 1, btf_kflag(t));
+}
+
+/*
+ * Append new BTF_KIND_INT type with:
+ *   - *name* - non-empty, non-NULL type name;
+ *   - *sz* - power-of-2 (1, 2, 4, ..) size of the type, in bytes;
+ *   - encoding is a combination of BTF_INT_SIGNED, BTF_INT_CHAR, BTF_INT_BOOL.
+ * Returns:
+ *   - >0, type ID of newly added BTF type;
+ *   - <0, on error.
+ */
+int btf__add_int(struct btf *btf, const char *name, size_t byte_sz, int encoding)
+{
+	struct btf_type *t;
+	int sz, err, name_off;
+
+	/* non-empty name */
+	if (!name || !name[0])
+		return -EINVAL;
+	/* byte_sz must be power of 2 */
+	if (!byte_sz || (byte_sz & (byte_sz - 1)) || byte_sz > 16)
+		return -EINVAL;
+	if (encoding & ~(BTF_INT_SIGNED | BTF_INT_CHAR | BTF_INT_BOOL))
+		return -EINVAL;
+
+	/* deconstruct BTF, if necessary, and invalidate raw_data */
+	if (btf_ensure_modifiable(btf))
+		return -ENOMEM;
+
+	sz = sizeof(struct btf_type) + sizeof(int);
+	t = btf_add_type_mem(btf, sz);
+	if (!t)
+		return -ENOMEM;
+
+	/* if something goes wrong later, we might end up with an extra string,
+	 * but that shouldn't be a problem, because BTF can't be constructed
+	 * completely anyway and will most probably be just discarded
+	 */
+	name_off = btf__add_str(btf, name);
+	if (name_off < 0)
+		return name_off;
+
+	t->name_off = name_off;
+	t->info = btf_type_info(BTF_KIND_INT, 0, 0);
+	t->size = byte_sz;
+	/* set INT info, we don't allow setting legacy bit offset/size */
+	*(__u32 *)(t + 1) = (encoding << 24) | (byte_sz * 8);
+
+	err = btf_add_type_idx_entry(btf, btf->hdr->type_len);
+	if (err)
+		return err;
+
+	btf->hdr->type_len += sz;
+	btf->hdr->str_off += sz;
+	btf->nr_types++;
+	return btf->nr_types;
+}
+
+/* it's completely legal to append BTF types with type IDs pointing forward to
+ * types that haven't been appended yet, so we only make sure that id looks
+ * sane, we can't guarantee that ID will always be valid
+ */
+static int validate_type_id(int id)
+{
+	if (id < 0 || id > BTF_MAX_NR_TYPES)
+		return -EINVAL;
+	return 0;
+}
+
+/* generic append function for PTR, TYPEDEF, CONST/VOLATILE/RESTRICT */
+static int btf_add_ref_kind(struct btf *btf, int kind, const char *name, int ref_type_id)
+{
+	struct btf_type *t;
+	int sz, name_off = 0, err;
+
+	if (validate_type_id(ref_type_id))
+		return -EINVAL;
+
+	if (btf_ensure_modifiable(btf))
+		return -ENOMEM;
+
+	sz = sizeof(struct btf_type);
+	t = btf_add_type_mem(btf, sz);
+	if (!t)
+		return -ENOMEM;
+
+	if (name && name[0]) {
+		name_off = btf__add_str(btf, name);
+		if (name_off < 0)
+			return name_off;
+	}
+
+	t->name_off = name_off;
+	t->info = btf_type_info(kind, 0, 0);
+	t->type = ref_type_id;
+
+	err = btf_add_type_idx_entry(btf, btf->hdr->type_len);
+	if (err)
+		return err;
+
+	btf->hdr->type_len += sz;
+	btf->hdr->str_off += sz;
+	btf->nr_types++;
+	return btf->nr_types;
+}
+
+/*
+ * Append new BTF_KIND_PTR type with:
+ *   - *ref_type_id* - referenced type ID, it might not exist yet;
+ * Returns:
+ *   - >0, type ID of newly added BTF type;
+ *   - <0, on error.
+ */
+int btf__add_ptr(struct btf *btf, int ref_type_id)
+{
+	return btf_add_ref_kind(btf, BTF_KIND_PTR, NULL, ref_type_id);
+}
+
+/*
+ * Append new BTF_KIND_ARRAY type with:
+ *   - *index_type_id* - type ID of the type describing array index;
+ *   - *elem_type_id* - type ID of the type describing array element;
+ *   - *nr_elems* - the size of the array;
+ * Returns:
+ *   - >0, type ID of newly added BTF type;
+ *   - <0, on error.
+ */
+int btf__add_array(struct btf *btf, int index_type_id, int elem_type_id, __u32 nr_elems)
+{
+	struct btf_type *t;
+	struct btf_array *a;
+	int sz, err;
+
+	if (validate_type_id(index_type_id) || validate_type_id(elem_type_id))
+		return -EINVAL;
+
+	if (btf_ensure_modifiable(btf))
+		return -ENOMEM;
+
+	sz = sizeof(struct btf_type) + sizeof(struct btf_array);
+	t = btf_add_type_mem(btf, sz);
+	if (!t)
+		return -ENOMEM;
+
+	t->name_off = 0;
+	t->info = btf_type_info(BTF_KIND_ARRAY, 0, 0);
+	t->size = 0;
+
+	a = btf_array(t);
+	a->type = elem_type_id;
+	a->index_type = index_type_id;
+	a->nelems = nr_elems;
+
+	err = btf_add_type_idx_entry(btf, btf->hdr->type_len);
+	if (err)
+		return err;
+
+	btf->hdr->type_len += sz;
+	btf->hdr->str_off += sz;
+	btf->nr_types++;
+	return btf->nr_types;
+}
+
+/* generic STRUCT/UNION append function */
+static int btf_add_composite(struct btf *btf, int kind, const char *name, __u32 bytes_sz)
+{
+	struct btf_type *t;
+	int sz, err, name_off = 0;
+
+	if (btf_ensure_modifiable(btf))
+		return -ENOMEM;
+
+	sz = sizeof(struct btf_type);
+	t = btf_add_type_mem(btf, sz);
+	if (!t)
+		return -ENOMEM;
+
+	if (name && name[0]) {
+		name_off = btf__add_str(btf, name);
+		if (name_off < 0)
+			return name_off;
+	}
+
+	/* start out with vlen=0 and no kflag; this will be adjusted when
+	 * adding each member
+	 */
+	t->name_off = name_off;
+	t->info = btf_type_info(kind, 0, 0);
+	t->size = bytes_sz;
+
+	err = btf_add_type_idx_entry(btf, btf->hdr->type_len);
+	if (err)
+		return err;
+
+	btf->hdr->type_len += sz;
+	btf->hdr->str_off += sz;
+	btf->nr_types++;
+	return btf->nr_types;
+}
+
+/*
+ * Append new BTF_KIND_STRUCT type with:
+ *   - *name* - name of the struct, can be NULL or empty for anonymous structs;
+ *   - *byte_sz* - size of the struct, in bytes;
+ *
+ * Struct initially has no fields in it. Fields can be added by
+ * btf__add_field() right after btf__add_struct() succeeds. 
+ *
+ * Returns:
+ *   - >0, type ID of newly added BTF type;
+ *   - <0, on error.
+ */
+int btf__add_struct(struct btf *btf, const char *name, __u32 byte_sz)
+{
+	return btf_add_composite(btf, BTF_KIND_STRUCT, name, byte_sz);
+}
+
+/*
+ * Append new BTF_KIND_UNION type with:
+ *   - *name* - name of the union, can be NULL or empty for anonymous union;
+ *   - *byte_sz* - size of the union, in bytes;
+ *
+ * Union initially has no fields in it. Fields can be added by
+ * btf__add_field() right after btf__add_union() succeeds. All fields
+ * should have *bit_offset* of 0.
+ *
+ * Returns:
+ *   - >0, type ID of newly added BTF type;
+ *   - <0, on error.
+ */
+int btf__add_union(struct btf *btf, const char *name, __u32 byte_sz)
+{
+	return btf_add_composite(btf, BTF_KIND_UNION, name, byte_sz);
+}
+
+/*
+ * Append new field for the current STRUCT/UNION type with:
+ *   - *name* - name of the field, can be NULL or empty for anonymous field;
+ *   - *type_id* - type ID for the type describing field type;
+ *   - *bit_offset* - bit offset of the start of the field within struct/union;
+ *   - *bit_size* - bit size of a bitfield, 0 for non-bitfield fields;
+ * Returns:
+ *   -  0, on success;
+ *   - <0, on error.
+ */
+int btf__add_field(struct btf *btf, const char *name, int type_id,
+		   __u32 bit_offset, __u32 bit_size)
+{
+	struct btf_type *t;
+	struct btf_member *m;
+	bool is_bitfield;
+	int sz, name_off = 0;
+
+	/* last type should be union/struct */
+	if (btf->nr_types == 0)
+		return -EINVAL;
+	t = btf_type_by_id(btf, btf->nr_types);
+	if (!btf_is_composite(t))
+		return -EINVAL;
+
+	if (validate_type_id(type_id))
+		return -EINVAL;
+	/* best-effort bit field offset/size enforcement */
+	is_bitfield = bit_size || (bit_offset % 8 != 0);
+	if (is_bitfield && (bit_size == 0 || bit_size > 255 || bit_offset > 0xffffff))
+		return -EINVAL;
+
+	/* only offset 0 is allowed for unions */
+	if (btf_is_union(t) && bit_offset)
+		return -EINVAL;
+
+	/* decompose and invalidate raw data */
+	if (btf_ensure_modifiable(btf))
+		return -ENOMEM;
+
+	sz = sizeof(struct btf_member);
+	m = btf_add_type_mem(btf, sz);
+	if (!m)
+		return -ENOMEM;
+
+	if (name && name[0]) {
+		name_off = btf__add_str(btf, name);
+		if (name_off < 0)
+			return name_off;
+	}
+
+	m->name_off = name_off;
+	m->type = type_id;
+	m->offset = bit_offset | (bit_size << 24);
+
+	/* btf_add_type_mem can invalidate t pointer */
+	t = btf_type_by_id(btf, btf->nr_types);
+	/* update parent type's vlen and kflag */
+	t->info = btf_type_info(btf_kind(t), btf_vlen(t) + 1, is_bitfield || btf_kflag(t));
+
+	btf->hdr->type_len += sz;
+	btf->hdr->str_off += sz;
+	return 0;
+}
+
+/*
+ * Append new BTF_KIND_ENUM type with:
+ *   - *name* - name of the enum, can be NULL or empty for anonymous enums;
+ *   - *byte_sz* - size of the enum, in bytes.
+ *
+ * Enum initially has no enum values in it (and corresponds to enum forward
+ * declaration). Enumerator values can be added by btf__add_enum_value()
+ * immediately after btf__add_enum() succeeds.
+ *
+ * Returns:
+ *   - >0, type ID of newly added BTF type;
+ *   - <0, on error.
+ */
+int btf__add_enum(struct btf *btf, const char *name, __u32 byte_sz)
+{
+	struct btf_type *t;
+	int sz, err, name_off = 0;
+
+	/* byte_sz must be power of 2 */
+	if (!byte_sz || (byte_sz & (byte_sz - 1)) || byte_sz > 8)
+		return -EINVAL;
+
+	if (btf_ensure_modifiable(btf))
+		return -ENOMEM;
+
+	sz = sizeof(struct btf_type);
+	t = btf_add_type_mem(btf, sz);
+	if (!t)
+		return -ENOMEM;
+
+	if (name && name[0]) {
+		name_off = btf__add_str(btf, name);
+		if (name_off < 0)
+			return name_off;
+	}
+
+	/* start out with vlen=0; it will be adjusted when adding enum values */
+	t->name_off = name_off;
+	t->info = btf_type_info(BTF_KIND_ENUM, 0, 0);
+	t->size = byte_sz;
+
+	err = btf_add_type_idx_entry(btf, btf->hdr->type_len);
+	if (err)
+		return err;
+
+	btf->hdr->type_len += sz;
+	btf->hdr->str_off += sz;
+	btf->nr_types++;
+	return btf->nr_types;
+}
+
+/*
+ * Append new enum value for the current ENUM type with:
+ *   - *name* - name of the enumerator value, can't be NULL or empty;
+ *   - *value* - integer value corresponding to enum value *name*;
+ * Returns:
+ *   -  0, on success;
+ *   - <0, on error.
+ */
+int btf__add_enum_value(struct btf *btf, const char *name, __s64 value)
+{
+	struct btf_type *t;
+	struct btf_enum *v;
+	int sz, name_off;
+
+	/* last type should be BTF_KIND_ENUM */
+	if (btf->nr_types == 0)
+		return -EINVAL;
+	t = btf_type_by_id(btf, btf->nr_types);
+	if (!btf_is_enum(t))
+		return -EINVAL;
+
+	/* non-empty name */
+	if (!name || !name[0])
+		return -EINVAL;
+	if (value < INT_MIN || value > UINT_MAX)
+		return -E2BIG;
+
+	/* decompose and invalidate raw data */
+	if (btf_ensure_modifiable(btf))
+		return -ENOMEM;
+
+	sz = sizeof(struct btf_enum);
+	v = btf_add_type_mem(btf, sz);
+	if (!v)
+		return -ENOMEM;
+
+	name_off = btf__add_str(btf, name);
+	if (name_off < 0)
+		return name_off;
+
+	v->name_off = name_off;
+	v->val = value;
+
+	/* update parent type's vlen */
+	t = btf_type_by_id(btf, btf->nr_types);
+	btf_type_inc_vlen(t);
+
+	btf->hdr->type_len += sz;
+	btf->hdr->str_off += sz;
+	return 0;
+}
+
+/*
+ * Append new BTF_KIND_FWD type with:
+ *   - *name*, non-empty/non-NULL name;
+ *   - *fwd_kind*, kind of forward declaration, one of BTF_FWD_STRUCT,
+ *     BTF_FWD_UNION, or BTF_FWD_ENUM;
+ * Returns:
+ *   - >0, type ID of newly added BTF type;
+ *   - <0, on error.
+ */
+int btf__add_fwd(struct btf *btf, const char *name, enum btf_fwd_kind fwd_kind)
+{
+	if (!name || !name[0])
+		return -EINVAL;
+
+	switch (fwd_kind) {
+	case BTF_FWD_STRUCT:
+	case BTF_FWD_UNION: {
+		struct btf_type *t;
+		int id;
+
+		id = btf_add_ref_kind(btf, BTF_KIND_FWD, name, 0);
+		if (id <= 0)
+			return id;
+		t = btf_type_by_id(btf, id);
+		t->info = btf_type_info(BTF_KIND_FWD, 0, fwd_kind == BTF_FWD_UNION);
+		return id;
+	}
+	case BTF_FWD_ENUM:
+		/* enum forward in BTF currently is just an enum with no enum
+		 * values; we also assume a standard 4-byte size for it
+		 */
+		return btf__add_enum(btf, name, sizeof(int));
+	default:
+		return -EINVAL;
+	}
+}
+
+/*
+ * Append new BTF_KING_TYPEDEF type with:
+ *   - *name*, non-empty/non-NULL name;
+ *   - *ref_type_id* - referenced type ID, it might not exist yet;
+ * Returns:
+ *   - >0, type ID of newly added BTF type;
+ *   - <0, on error.
+ */
+int btf__add_typedef(struct btf *btf, const char *name, int ref_type_id)
+{
+	if (!name || !name[0])
+		return -EINVAL;
+
+	return btf_add_ref_kind(btf, BTF_KIND_TYPEDEF, name, ref_type_id);
+}
+
+/*
+ * Append new BTF_KIND_VOLATILE type with:
+ *   - *ref_type_id* - referenced type ID, it might not exist yet;
+ * Returns:
+ *   - >0, type ID of newly added BTF type;
+ *   - <0, on error.
+ */
+int btf__add_volatile(struct btf *btf, int ref_type_id)
+{
+	return btf_add_ref_kind(btf, BTF_KIND_VOLATILE, NULL, ref_type_id);
+}
+
+/*
+ * Append new BTF_KIND_CONST type with:
+ *   - *ref_type_id* - referenced type ID, it might not exist yet;
+ * Returns:
+ *   - >0, type ID of newly added BTF type;
+ *   - <0, on error.
+ */
+int btf__add_const(struct btf *btf, int ref_type_id)
+{
+	return btf_add_ref_kind(btf, BTF_KIND_CONST, NULL, ref_type_id);
+}
+
+/*
+ * Append new BTF_KIND_RESTRICT type with:
+ *   - *ref_type_id* - referenced type ID, it might not exist yet;
+ * Returns:
+ *   - >0, type ID of newly added BTF type;
+ *   - <0, on error.
+ */
+int btf__add_restrict(struct btf *btf, int ref_type_id)
+{
+	return btf_add_ref_kind(btf, BTF_KIND_RESTRICT, NULL, ref_type_id);
+}
+
+/*
+ * Append new BTF_KIND_FUNC type with:
+ *   - *name*, non-empty/non-NULL name;
+ *   - *proto_type_id* - FUNC_PROTO's type ID, it might not exist yet;
+ * Returns:
+ *   - >0, type ID of newly added BTF type;
+ *   - <0, on error.
+ */
+int btf__add_func(struct btf *btf, const char *name,
+		  enum btf_func_linkage linkage, int proto_type_id)
+{
+	int id;
+
+	if (!name || !name[0])
+		return -EINVAL;
+	if (linkage != BTF_FUNC_STATIC && linkage != BTF_FUNC_GLOBAL &&
+	    linkage != BTF_FUNC_EXTERN)
+		return -EINVAL;
+
+	id = btf_add_ref_kind(btf, BTF_KIND_FUNC, name, proto_type_id);
+	if (id > 0) {
+		struct btf_type *t = btf_type_by_id(btf, id);
+
+		t->info = btf_type_info(BTF_KIND_FUNC, linkage, 0);
+	}
+	return id;
+}
+
+/*
+ * Append new BTF_KIND_FUNC_PROTO with:
+ *   - *ret_type_id* - type ID for return result of a function.
+ *
+ * Function prototype initially has no arguments, but they can be added by
+ * btf__add_func_param() one by one, immediately after
+ * btf__add_func_proto() succeeded.
+ *
+ * Returns:
+ *   - >0, type ID of newly added BTF type;
+ *   - <0, on error.
+ */
+int btf__add_func_proto(struct btf *btf, int ret_type_id)
+{
+	struct btf_type *t;
+	int sz, err;
+
+	if (validate_type_id(ret_type_id))
+		return -EINVAL;
+
+	if (btf_ensure_modifiable(btf))
+		return -ENOMEM;
+
+	sz = sizeof(struct btf_type);
+	t = btf_add_type_mem(btf, sz);
+	if (!t)
+		return -ENOMEM;
+
+	/* start out with vlen=0; this will be adjusted when adding enum
+	 * values, if necessary
+	 */
+	t->name_off = 0;
+	t->info = btf_type_info(BTF_KIND_FUNC_PROTO, 0, 0);
+	t->type = ret_type_id;
+
+	err = btf_add_type_idx_entry(btf, btf->hdr->type_len);
+	if (err)
+		return err;
+
+	btf->hdr->type_len += sz;
+	btf->hdr->str_off += sz;
+	btf->nr_types++;
+	return btf->nr_types;
+}
+
+/*
+ * Append new function parameter for current FUNC_PROTO type with:
+ *   - *name* - parameter name, can be NULL or empty;
+ *   - *type_id* - type ID describing the type of the parameter.
+ * Returns:
+ *   -  0, on success;
+ *   - <0, on error.
+ */
+int btf__add_func_param(struct btf *btf, const char *name, int type_id)
+{
+	struct btf_type *t;
+	struct btf_param *p;
+	int sz, name_off = 0;
+
+	if (validate_type_id(type_id))
+		return -EINVAL;
+
+	/* last type should be BTF_KIND_FUNC_PROTO */
+	if (btf->nr_types == 0)
+		return -EINVAL;
+	t = btf_type_by_id(btf, btf->nr_types);
+	if (!btf_is_func_proto(t))
+		return -EINVAL;
+
+	/* decompose and invalidate raw data */
+	if (btf_ensure_modifiable(btf))
+		return -ENOMEM;
+
+	sz = sizeof(struct btf_param);
+	p = btf_add_type_mem(btf, sz);
+	if (!p)
+		return -ENOMEM;
+
+	if (name && name[0]) {
+		name_off = btf__add_str(btf, name);
+		if (name_off < 0)
+			return name_off;
+	}
+
+	p->name_off = name_off;
+	p->type = type_id;
+
+	/* update parent type's vlen */
+	t = btf_type_by_id(btf, btf->nr_types);
+	btf_type_inc_vlen(t);
+
+	btf->hdr->type_len += sz;
+	btf->hdr->str_off += sz;
+	return 0;
+}
+
+/*
+ * Append new BTF_KIND_VAR type with:
+ *   - *name* - non-empty/non-NULL name;
+ *   - *linkage* - variable linkage, one of BTF_VAR_STATIC,
+ *     BTF_VAR_GLOBAL_ALLOCATED, or BTF_VAR_GLOBAL_EXTERN;
+ *   - *type_id* - type ID of the type describing the type of the variable.
+ * Returns:
+ *   - >0, type ID of newly added BTF type;
+ *   - <0, on error.
+ */
+int btf__add_var(struct btf *btf, const char *name, int linkage, int type_id)
+{
+	struct btf_type *t;
+	struct btf_var *v;
+	int sz, err, name_off;
+
+	/* non-empty name */
+	if (!name || !name[0])
+		return -EINVAL;
+	if (linkage != BTF_VAR_STATIC && linkage != BTF_VAR_GLOBAL_ALLOCATED &&
+	    linkage != BTF_VAR_GLOBAL_EXTERN)
+		return -EINVAL;
+	if (validate_type_id(type_id))
+		return -EINVAL;
+
+	/* deconstruct BTF, if necessary, and invalidate raw_data */
+	if (btf_ensure_modifiable(btf))
+		return -ENOMEM;
+
+	sz = sizeof(struct btf_type) + sizeof(struct btf_var);
+	t = btf_add_type_mem(btf, sz);
+	if (!t)
+		return -ENOMEM;
+
+	name_off = btf__add_str(btf, name);
+	if (name_off < 0)
+		return name_off;
+
+	t->name_off = name_off;
+	t->info = btf_type_info(BTF_KIND_VAR, 0, 0);
+	t->type = type_id;
+
+	v = btf_var(t);
+	v->linkage = linkage;
+
+	err = btf_add_type_idx_entry(btf, btf->hdr->type_len);
+	if (err)
+		return err;
+
+	btf->hdr->type_len += sz;
+	btf->hdr->str_off += sz;
+	btf->nr_types++;
+	return btf->nr_types;
+}
+
+/*
+ * Append new BTF_KIND_DATASEC type with:
+ *   - *name* - non-empty/non-NULL name;
+ *   - *byte_sz* - data section size, in bytes.
+ *
+ * Data section is initially empty. Variables info can be added with
+ * btf__add_datasec_var_info() calls, after btf__add_datasec() succeeds.
+ *
+ * Returns:
+ *   - >0, type ID of newly added BTF type;
+ *   - <0, on error.
+ */
+int btf__add_datasec(struct btf *btf, const char *name, __u32 byte_sz)
+{
+	struct btf_type *t;
+	int sz, err, name_off;
+
+	/* non-empty name */
+	if (!name || !name[0])
+		return -EINVAL;
+
+	if (btf_ensure_modifiable(btf))
+		return -ENOMEM;
+
+	sz = sizeof(struct btf_type);
+	t = btf_add_type_mem(btf, sz);
+	if (!t)
+		return -ENOMEM;
+
+	name_off = btf__add_str(btf, name);
+	if (name_off < 0)
+		return name_off;
+
+	/* start with vlen=0, which will be update as var_secinfos are added */
+	t->name_off = name_off;
+	t->info = btf_type_info(BTF_KIND_DATASEC, 0, 0);
+	t->size = byte_sz;
+
+	err = btf_add_type_idx_entry(btf, btf->hdr->type_len);
+	if (err)
+		return err;
+
+	btf->hdr->type_len += sz;
+	btf->hdr->str_off += sz;
+	btf->nr_types++;
+	return btf->nr_types;
+}
+
+/*
+ * Append new data section variable information entry for current DATASEC type:
+ *   - *var_type_id* - type ID, describing type of the variable;
+ *   - *offset* - variable offset within data section, in bytes;
+ *   - *byte_sz* - variable size, in bytes.
+ *
+ * Returns:
+ *   -  0, on success;
+ *   - <0, on error.
+ */
+int btf__add_datasec_var_info(struct btf *btf, int var_type_id, __u32 offset, __u32 byte_sz)
+{
+	struct btf_type *t;
+	struct btf_var_secinfo *v;
+	int sz;
+
+	/* last type should be BTF_KIND_DATASEC */
+	if (btf->nr_types == 0)
+		return -EINVAL;
+	t = btf_type_by_id(btf, btf->nr_types);
+	if (!btf_is_datasec(t))
+		return -EINVAL;
+
+	if (validate_type_id(var_type_id))
+		return -EINVAL;
+
+	/* decompose and invalidate raw data */
+	if (btf_ensure_modifiable(btf))
+		return -ENOMEM;
+
+	sz = sizeof(struct btf_var_secinfo);
+	v = btf_add_type_mem(btf, sz);
+	if (!v)
+		return -ENOMEM;
+
+	v->type = var_type_id;
+	v->offset = offset;
+	v->size = byte_sz;
+
+	/* update parent type's vlen */
+	t = btf_type_by_id(btf, btf->nr_types);
+	btf_type_inc_vlen(t);
+
+	btf->hdr->type_len += sz;
+	btf->hdr->str_off += sz;
+	return 0;
+}
+
 struct btf_ext_sec_setup_param {
 	__u32 off;
 	__u32 len;
@@ -1151,7 +2471,10 @@ static int btf_ext_parse_hdr(__u8 *data, __u32 data_size)
 		return -EINVAL;
 	}
 
-	if (hdr->magic != BTF_MAGIC) {
+	if (hdr->magic == bswap_16(BTF_MAGIC)) {
+		pr_warn("BTF.ext in non-native endianness is not supported\n");
+		return -ENOTSUP;
+	} else if (hdr->magic != BTF_MAGIC) {
 		pr_debug("Invalid BTF.ext magic:%x\n", hdr->magic);
 		return -EINVAL;
 	}
@@ -1471,6 +2794,9 @@ int btf__dedup(struct btf *btf, struct btf_ext *btf_ext,
 		return -EINVAL;
 	}
 
+	if (btf_ensure_modifiable(btf))
+		return -ENOMEM;
+
 	err = btf_dedup_strings(d);
 	if (err < 0) {
 		pr_debug("btf_dedup_strings failed:%d\n", err);
@@ -1655,7 +2981,7 @@ static struct btf_dedup *btf_dedup_new(struct btf *btf, struct btf_ext *btf_ext,
 	/* special BTF "void" type is made canonical immediately */
 	d->map[0] = 0;
 	for (i = 1; i <= btf->nr_types; i++) {
-		struct btf_type *t = d->btf->types[i];
+		struct btf_type *t = btf_type_by_id(d->btf, i);
 
 		/* VAR and DATASEC are never deduped and are self-canonical */
 		if (btf_is_var(t) || btf_is_datasec(t))
@@ -1694,7 +3020,7 @@ static int btf_for_each_str_off(struct btf_dedup *d, str_off_fn_t fn, void *ctx)
 	struct btf_type *t;
 
 	for (i = 1; i <= d->btf->nr_types; i++) {
-		t = d->btf->types[i];
+		t = btf_type_by_id(d->btf, i);
 		r = fn(&t->name_off, ctx);
 		if (r)
 			return r;
@@ -1848,8 +3174,7 @@ static int btf_str_remap_offset(__u32 *str_off_ptr, void *ctx)
  */
 static int btf_dedup_strings(struct btf_dedup *d)
 {
-	const struct btf_header *hdr = d->btf->hdr;
-	char *start = (char *)d->btf->nohdr_data + hdr->str_off;
+	char *start = d->btf->strs_data;
 	char *end = start + d->btf->hdr->str_len;
 	char *p = start, *tmp_strs = NULL;
 	struct btf_str_ptrs strs = {
@@ -1861,6 +3186,9 @@ static int btf_dedup_strings(struct btf_dedup *d)
 	int i, j, err = 0, grp_idx;
 	bool grp_used;
 
+	if (d->btf->strs_deduped)
+		return 0;
+
 	/* build index of all strings */
 	while (p < end) {
 		if (strs.cnt + 1 > strs.cap) {
@@ -1953,6 +3281,7 @@ static int btf_dedup_strings(struct btf_dedup *d)
 		goto done;
 
 	d->btf->hdr->str_len = end - start;
+	d->btf->strs_deduped = true;
 
 done:
 	free(tmp_strs);
@@ -2229,7 +3558,7 @@ static bool btf_compat_fnproto(struct btf_type *t1, struct btf_type *t2)
  */
 static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id)
 {
-	struct btf_type *t = d->btf->types[type_id];
+	struct btf_type *t = btf_type_by_id(d->btf, type_id);
 	struct hashmap_entry *hash_entry;
 	struct btf_type *cand;
 	/* if we don't find equivalent type, then we are canonical */
@@ -2256,7 +3585,7 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id)
 		h = btf_hash_int(t);
 		for_each_dedup_cand(d, hash_entry, h) {
 			cand_id = (__u32)(long)hash_entry->value;
-			cand = d->btf->types[cand_id];
+			cand = btf_type_by_id(d->btf, cand_id);
 			if (btf_equal_int(t, cand)) {
 				new_id = cand_id;
 				break;
@@ -2268,7 +3597,7 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id)
 		h = btf_hash_enum(t);
 		for_each_dedup_cand(d, hash_entry, h) {
 			cand_id = (__u32)(long)hash_entry->value;
-			cand = d->btf->types[cand_id];
+			cand = btf_type_by_id(d->btf, cand_id);
 			if (btf_equal_enum(t, cand)) {
 				new_id = cand_id;
 				break;
@@ -2291,7 +3620,7 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id)
 		h = btf_hash_common(t);
 		for_each_dedup_cand(d, hash_entry, h) {
 			cand_id = (__u32)(long)hash_entry->value;
-			cand = d->btf->types[cand_id];
+			cand = btf_type_by_id(d->btf, cand_id);
 			if (btf_equal_common(t, cand)) {
 				new_id = cand_id;
 				break;
@@ -2350,13 +3679,13 @@ static uint32_t resolve_fwd_id(struct btf_dedup *d, uint32_t type_id)
 {
 	__u32 orig_type_id = type_id;
 
-	if (!btf_is_fwd(d->btf->types[type_id]))
+	if (!btf_is_fwd(btf__type_by_id(d->btf, type_id)))
 		return type_id;
 
 	while (is_type_mapped(d, type_id) && d->map[type_id] != type_id)
 		type_id = d->map[type_id];
 
-	if (!btf_is_fwd(d->btf->types[type_id]))
+	if (!btf_is_fwd(btf__type_by_id(d->btf, type_id)))
 		return type_id;
 
 	return orig_type_id;
@@ -2484,8 +3813,8 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id,
 	if (btf_dedup_hypot_map_add(d, canon_id, cand_id))
 		return -ENOMEM;
 
-	cand_type = d->btf->types[cand_id];
-	canon_type = d->btf->types[canon_id];
+	cand_type = btf_type_by_id(d->btf, cand_id);
+	canon_type = btf_type_by_id(d->btf, canon_id);
 	cand_kind = btf_kind(cand_type);
 	canon_kind = btf_kind(canon_type);
 
@@ -2636,8 +3965,8 @@ static void btf_dedup_merge_hypot_map(struct btf_dedup *d)
 		targ_type_id = d->hypot_map[cand_type_id];
 		t_id = resolve_type_id(d, targ_type_id);
 		c_id = resolve_type_id(d, cand_type_id);
-		t_kind = btf_kind(d->btf->types[t_id]);
-		c_kind = btf_kind(d->btf->types[c_id]);
+		t_kind = btf_kind(btf__type_by_id(d->btf, t_id));
+		c_kind = btf_kind(btf__type_by_id(d->btf, c_id));
 		/*
 		 * Resolve FWD into STRUCT/UNION.
 		 * It's ok to resolve FWD into STRUCT/UNION that's not yet
@@ -2705,7 +4034,7 @@ static int btf_dedup_struct_type(struct btf_dedup *d, __u32 type_id)
 	if (d->map[type_id] <= BTF_MAX_NR_TYPES)
 		return 0;
 
-	t = d->btf->types[type_id];
+	t = btf_type_by_id(d->btf, type_id);
 	kind = btf_kind(t);
 
 	if (kind != BTF_KIND_STRUCT && kind != BTF_KIND_UNION)
@@ -2726,7 +4055,7 @@ static int btf_dedup_struct_type(struct btf_dedup *d, __u32 type_id)
 		 * creating a loop (FWD -> STRUCT and STRUCT -> FWD), because
 		 * FWD and compatible STRUCT/UNION are considered equivalent.
 		 */
-		cand_type = d->btf->types[cand_id];
+		cand_type = btf_type_by_id(d->btf, cand_id);
 		if (!btf_shallow_equal_struct(t, cand_type))
 			continue;
 
@@ -2798,7 +4127,7 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id)
 	if (d->map[type_id] <= BTF_MAX_NR_TYPES)
 		return resolve_type_id(d, type_id);
 
-	t = d->btf->types[type_id];
+	t = btf_type_by_id(d->btf, type_id);
 	d->map[type_id] = BTF_IN_PROGRESS_ID;
 
 	switch (btf_kind(t)) {
@@ -2816,7 +4145,7 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id)
 		h = btf_hash_common(t);
 		for_each_dedup_cand(d, hash_entry, h) {
 			cand_id = (__u32)(long)hash_entry->value;
-			cand = d->btf->types[cand_id];
+			cand = btf_type_by_id(d->btf, cand_id);
 			if (btf_equal_common(t, cand)) {
 				new_id = cand_id;
 				break;
@@ -2840,7 +4169,7 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id)
 		h = btf_hash_array(t);
 		for_each_dedup_cand(d, hash_entry, h) {
 			cand_id = (__u32)(long)hash_entry->value;
-			cand = d->btf->types[cand_id];
+			cand = btf_type_by_id(d->btf, cand_id);
 			if (btf_equal_array(t, cand)) {
 				new_id = cand_id;
 				break;
@@ -2872,7 +4201,7 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id)
 		h = btf_hash_fnproto(t);
 		for_each_dedup_cand(d, hash_entry, h) {
 			cand_id = (__u32)(long)hash_entry->value;
-			cand = d->btf->types[cand_id];
+			cand = btf_type_by_id(d->btf, cand_id);
 			if (btf_equal_fnproto(t, cand)) {
 				new_id = cand_id;
 				break;
@@ -2920,9 +4249,9 @@ static int btf_dedup_ref_types(struct btf_dedup *d)
  */
 static int btf_dedup_compact_types(struct btf_dedup *d)
 {
-	struct btf_type **new_types;
+	__u32 *new_offs;
 	__u32 next_type_id = 1;
-	char *types_start, *p;
+	void *p;
 	int i, len;
 
 	/* we are going to reuse hypot_map to store compaction remapping */
@@ -2930,41 +4259,34 @@ static int btf_dedup_compact_types(struct btf_dedup *d)
 	for (i = 1; i <= d->btf->nr_types; i++)
 		d->hypot_map[i] = BTF_UNPROCESSED_ID;
 
-	types_start = d->btf->nohdr_data + d->btf->hdr->type_off;
-	p = types_start;
+	p = d->btf->types_data;
 
 	for (i = 1; i <= d->btf->nr_types; i++) {
 		if (d->map[i] != i)
 			continue;
 
-		len = btf_type_size(d->btf->types[i]);
+		len = btf_type_size(btf__type_by_id(d->btf, i));
 		if (len < 0)
 			return len;
 
-		memmove(p, d->btf->types[i], len);
+		memmove(p, btf__type_by_id(d->btf, i), len);
 		d->hypot_map[i] = next_type_id;
-		d->btf->types[next_type_id] = (struct btf_type *)p;
+		d->btf->type_offs[next_type_id] = p - d->btf->types_data;
 		p += len;
 		next_type_id++;
 	}
 
 	/* shrink struct btf's internal types index and update btf_header */
 	d->btf->nr_types = next_type_id - 1;
-	d->btf->types_size = d->btf->nr_types;
-	d->btf->hdr->type_len = p - types_start;
-	new_types = libbpf_reallocarray(d->btf->types, (1 + d->btf->nr_types),
-					sizeof(struct btf_type *));
-	if (!new_types)
+	d->btf->type_offs_cap = d->btf->nr_types + 1;
+	d->btf->hdr->type_len = p - d->btf->types_data;
+	new_offs = libbpf_reallocarray(d->btf->type_offs, d->btf->type_offs_cap,
+				       sizeof(*new_offs));
+	if (!new_offs)
 		return -ENOMEM;
-	d->btf->types = new_types;
-
-	/* make sure string section follows type information without gaps */
-	d->btf->hdr->str_off = p - (char *)d->btf->nohdr_data;
-	memmove(p, d->btf->strings, d->btf->hdr->str_len);
-	d->btf->strings = p;
-	p += d->btf->hdr->str_len;
-
-	d->btf->data_size = p - (char *)d->btf->data;
+	d->btf->type_offs = new_offs;
+	d->btf->hdr->str_off = d->btf->hdr->type_len;
+	d->btf->raw_size = d->btf->hdr->hdr_len + d->btf->hdr->type_len + d->btf->hdr->str_len;
 	return 0;
 }
 
@@ -2997,7 +4319,7 @@ static int btf_dedup_remap_type_id(struct btf_dedup *d, __u32 type_id)
  */
 static int btf_dedup_remap_type(struct btf_dedup *d, __u32 type_id)
 {
-	struct btf_type *t = d->btf->types[type_id];
+	struct btf_type *t = btf_type_by_id(d->btf, type_id);
 	int i, r;
 
 	switch (btf_kind(t)) {
diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h
index 91f0ad0e0325..57247240a20a 100644
--- a/tools/lib/bpf/btf.h
+++ b/tools/lib/bpf/btf.h
@@ -5,6 +5,7 @@
 #define __LIBBPF_BTF_H
 
 #include <stdarg.h>
+#include <stdbool.h>
 #include <linux/btf.h>
 #include <linux/types.h>
 
@@ -24,8 +25,14 @@ struct btf_type;
 
 struct bpf_object;
 
+enum btf_endianness {
+	BTF_LITTLE_ENDIAN = 0,
+	BTF_BIG_ENDIAN = 1,
+};
+
 LIBBPF_API void btf__free(struct btf *btf);
 LIBBPF_API struct btf *btf__new(const void *data, __u32 size);
+LIBBPF_API struct btf *btf__new_empty(void);
 LIBBPF_API struct btf *btf__parse(const char *path, struct btf_ext **btf_ext);
 LIBBPF_API struct btf *btf__parse_elf(const char *path, struct btf_ext **btf_ext);
 LIBBPF_API struct btf *btf__parse_raw(const char *path);
@@ -40,6 +47,8 @@ LIBBPF_API const struct btf_type *btf__type_by_id(const struct btf *btf,
 						  __u32 id);
 LIBBPF_API size_t btf__pointer_size(const struct btf *btf);
 LIBBPF_API int btf__set_pointer_size(struct btf *btf, size_t ptr_sz);
+LIBBPF_API enum btf_endianness btf__endianness(const struct btf *btf);
+LIBBPF_API int btf__set_endianness(struct btf *btf, enum btf_endianness endian);
 LIBBPF_API __s64 btf__resolve_size(const struct btf *btf, __u32 type_id);
 LIBBPF_API int btf__resolve_type(const struct btf *btf, __u32 type_id);
 LIBBPF_API int btf__align_of(const struct btf *btf, __u32 id);
@@ -47,6 +56,7 @@ LIBBPF_API int btf__fd(const struct btf *btf);
 LIBBPF_API void btf__set_fd(struct btf *btf, int fd);
 LIBBPF_API const void *btf__get_raw_data(const struct btf *btf, __u32 *size);
 LIBBPF_API const char *btf__name_by_offset(const struct btf *btf, __u32 offset);
+LIBBPF_API const char *btf__str_by_offset(const struct btf *btf, __u32 offset);
 LIBBPF_API int btf__get_from_id(__u32 id, struct btf **btf);
 LIBBPF_API int btf__get_map_kv_tids(const struct btf *btf, const char *map_name,
 				    __u32 expected_key_size,
@@ -57,19 +67,62 @@ LIBBPF_API struct btf_ext *btf_ext__new(__u8 *data, __u32 size);
 LIBBPF_API void btf_ext__free(struct btf_ext *btf_ext);
 LIBBPF_API const void *btf_ext__get_raw_data(const struct btf_ext *btf_ext,
 					     __u32 *size);
-LIBBPF_API int btf_ext__reloc_func_info(const struct btf *btf,
-					const struct btf_ext *btf_ext,
-					const char *sec_name, __u32 insns_cnt,
-					void **func_info, __u32 *cnt);
-LIBBPF_API int btf_ext__reloc_line_info(const struct btf *btf,
-					const struct btf_ext *btf_ext,
-					const char *sec_name, __u32 insns_cnt,
-					void **line_info, __u32 *cnt);
+LIBBPF_API LIBBPF_DEPRECATED("btf_ext__reloc_func_info was never meant as a public API and has wrong assumptions embedded in it; it will be removed in the future libbpf versions")
+int btf_ext__reloc_func_info(const struct btf *btf,
+			     const struct btf_ext *btf_ext,
+			     const char *sec_name, __u32 insns_cnt,
+			     void **func_info, __u32 *cnt);
+LIBBPF_API LIBBPF_DEPRECATED("btf_ext__reloc_line_info was never meant as a public API and has wrong assumptions embedded in it; it will be removed in the future libbpf versions")
+int btf_ext__reloc_line_info(const struct btf *btf,
+			     const struct btf_ext *btf_ext,
+			     const char *sec_name, __u32 insns_cnt,
+			     void **line_info, __u32 *cnt);
 LIBBPF_API __u32 btf_ext__func_info_rec_size(const struct btf_ext *btf_ext);
 LIBBPF_API __u32 btf_ext__line_info_rec_size(const struct btf_ext *btf_ext);
 
 LIBBPF_API struct btf *libbpf_find_kernel_btf(void);
 
+LIBBPF_API int btf__find_str(struct btf *btf, const char *s);
+LIBBPF_API int btf__add_str(struct btf *btf, const char *s);
+
+LIBBPF_API int btf__add_int(struct btf *btf, const char *name, size_t byte_sz, int encoding);
+LIBBPF_API int btf__add_ptr(struct btf *btf, int ref_type_id);
+LIBBPF_API int btf__add_array(struct btf *btf,
+			      int index_type_id, int elem_type_id, __u32 nr_elems);
+/* struct/union construction APIs */
+LIBBPF_API int btf__add_struct(struct btf *btf, const char *name, __u32 sz);
+LIBBPF_API int btf__add_union(struct btf *btf, const char *name, __u32 sz);
+LIBBPF_API int btf__add_field(struct btf *btf, const char *name, int field_type_id,
+			      __u32 bit_offset, __u32 bit_size);
+
+/* enum construction APIs */
+LIBBPF_API int btf__add_enum(struct btf *btf, const char *name, __u32 bytes_sz);
+LIBBPF_API int btf__add_enum_value(struct btf *btf, const char *name, __s64 value);
+
+enum btf_fwd_kind {
+	BTF_FWD_STRUCT = 0,
+	BTF_FWD_UNION = 1,
+	BTF_FWD_ENUM = 2,
+};
+
+LIBBPF_API int btf__add_fwd(struct btf *btf, const char *name, enum btf_fwd_kind fwd_kind);
+LIBBPF_API int btf__add_typedef(struct btf *btf, const char *name, int ref_type_id);
+LIBBPF_API int btf__add_volatile(struct btf *btf, int ref_type_id);
+LIBBPF_API int btf__add_const(struct btf *btf, int ref_type_id);
+LIBBPF_API int btf__add_restrict(struct btf *btf, int ref_type_id);
+
+/* func and func_proto construction APIs */
+LIBBPF_API int btf__add_func(struct btf *btf, const char *name,
+			     enum btf_func_linkage linkage, int proto_type_id);
+LIBBPF_API int btf__add_func_proto(struct btf *btf, int ret_type_id);
+LIBBPF_API int btf__add_func_param(struct btf *btf, const char *name, int type_id);
+
+/* var & datasec construction APIs */
+LIBBPF_API int btf__add_var(struct btf *btf, const char *name, int linkage, int type_id);
+LIBBPF_API int btf__add_datasec(struct btf *btf, const char *name, __u32 byte_sz);
+LIBBPF_API int btf__add_datasec_var_info(struct btf *btf, int var_type_id,
+					 __u32 offset, __u32 byte_sz);
+
 struct btf_dedup_opts {
 	unsigned int dedup_table_size;
 	bool dont_resolve_fwds;
diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c
index 6c079b3c8679..2f9d685bd522 100644
--- a/tools/lib/bpf/btf_dump.c
+++ b/tools/lib/bpf/btf_dump.c
@@ -60,11 +60,14 @@ struct btf_dump {
 	struct btf_dump_opts opts;
 	int ptr_sz;
 	bool strip_mods;
+	int last_id;
 
 	/* per-type auxiliary state */
 	struct btf_dump_type_aux_state *type_states;
+	size_t type_states_cap;
 	/* per-type optional cached unique name, must be freed, if present */
 	const char **cached_names;
+	size_t cached_names_cap;
 
 	/* topo-sorted list of dependent type definitions */
 	__u32 *emit_queue;
@@ -90,14 +93,7 @@ struct btf_dump {
 
 static size_t str_hash_fn(const void *key, void *ctx)
 {
-	const char *s = key;
-	size_t h = 0;
-
-	while (*s) {
-		h = h * 31 + *s;
-		s++;
-	}
-	return h;
+	return str_hash(key);
 }
 
 static bool str_equal_fn(const void *a, const void *b, void *ctx)
@@ -120,6 +116,7 @@ static void btf_dump_printf(const struct btf_dump *d, const char *fmt, ...)
 }
 
 static int btf_dump_mark_referenced(struct btf_dump *d);
+static int btf_dump_resize(struct btf_dump *d);
 
 struct btf_dump *btf_dump__new(const struct btf *btf,
 			       const struct btf_ext *btf_ext,
@@ -151,25 +148,8 @@ struct btf_dump *btf_dump__new(const struct btf *btf,
 		d->ident_names = NULL;
 		goto err;
 	}
-	d->type_states = calloc(1 + btf__get_nr_types(d->btf),
-				sizeof(d->type_states[0]));
-	if (!d->type_states) {
-		err = -ENOMEM;
-		goto err;
-	}
-	d->cached_names = calloc(1 + btf__get_nr_types(d->btf),
-				 sizeof(d->cached_names[0]));
-	if (!d->cached_names) {
-		err = -ENOMEM;
-		goto err;
-	}
 
-	/* VOID is special */
-	d->type_states[0].order_state = ORDERED;
-	d->type_states[0].emit_state = EMITTED;
-
-	/* eagerly determine referenced types for anon enums */
-	err = btf_dump_mark_referenced(d);
+	err = btf_dump_resize(d);
 	if (err)
 		goto err;
 
@@ -179,9 +159,38 @@ err:
 	return ERR_PTR(err);
 }
 
+static int btf_dump_resize(struct btf_dump *d)
+{
+	int err, last_id = btf__get_nr_types(d->btf);
+
+	if (last_id <= d->last_id)
+		return 0;
+
+	if (btf_ensure_mem((void **)&d->type_states, &d->type_states_cap,
+			   sizeof(*d->type_states), last_id + 1))
+		return -ENOMEM;
+	if (btf_ensure_mem((void **)&d->cached_names, &d->cached_names_cap,
+			   sizeof(*d->cached_names), last_id + 1))
+		return -ENOMEM;
+
+	if (d->last_id == 0) {
+		/* VOID is special */
+		d->type_states[0].order_state = ORDERED;
+		d->type_states[0].emit_state = EMITTED;
+	}
+
+	/* eagerly determine referenced types for anon enums */
+	err = btf_dump_mark_referenced(d);
+	if (err)
+		return err;
+
+	d->last_id = last_id;
+	return 0;
+}
+
 void btf_dump__free(struct btf_dump *d)
 {
-	int i, cnt;
+	int i;
 
 	if (IS_ERR_OR_NULL(d))
 		return;
@@ -189,7 +198,7 @@ void btf_dump__free(struct btf_dump *d)
 	free(d->type_states);
 	if (d->cached_names) {
 		/* any set cached name is owned by us and should be freed */
-		for (i = 0, cnt = btf__get_nr_types(d->btf); i <= cnt; i++) {
+		for (i = 0; i <= d->last_id; i++) {
 			if (d->cached_names[i])
 				free((void *)d->cached_names[i]);
 		}
@@ -229,6 +238,10 @@ int btf_dump__dump_type(struct btf_dump *d, __u32 id)
 	if (id > btf__get_nr_types(d->btf))
 		return -EINVAL;
 
+	err = btf_dump_resize(d);
+	if (err)
+		return err;
+
 	d->emit_queue_cnt = 0;
 	err = btf_dump_order_type(d, id, false);
 	if (err < 0)
@@ -258,7 +271,7 @@ static int btf_dump_mark_referenced(struct btf_dump *d)
 	const struct btf_type *t;
 	__u16 vlen;
 
-	for (i = 1; i <= n; i++) {
+	for (i = d->last_id + 1; i <= n; i++) {
 		t = btf__type_by_id(d->btf, i);
 		vlen = btf_vlen(t);
 
@@ -313,6 +326,7 @@ static int btf_dump_mark_referenced(struct btf_dump *d)
 	}
 	return 0;
 }
+
 static int btf_dump_add_emit_queue_id(struct btf_dump *d, __u32 id)
 {
 	__u32 *new_queue;
@@ -1056,11 +1070,15 @@ int btf_dump__emit_type_decl(struct btf_dump *d, __u32 id,
 			     const struct btf_dump_emit_type_decl_opts *opts)
 {
 	const char *fname;
-	int lvl;
+	int lvl, err;
 
 	if (!OPTS_VALID(opts, btf_dump_emit_type_decl_opts))
 		return -EINVAL;
 
+	err = btf_dump_resize(d);
+	if (err)
+		return -EINVAL;
+
 	fname = OPTS_GET(opts, field_name, "");
 	lvl = OPTS_GET(opts, indent_level, 0);
 	d->strip_mods = OPTS_GET(opts, strip_mods, false);
diff --git a/tools/lib/bpf/hashmap.h b/tools/lib/bpf/hashmap.h
index e0af36b0e5d8..d9b385fe808c 100644
--- a/tools/lib/bpf/hashmap.h
+++ b/tools/lib/bpf/hashmap.h
@@ -25,6 +25,18 @@ static inline size_t hash_bits(size_t h, int bits)
 #endif
 }
 
+/* generic C-string hashing function */
+static inline size_t str_hash(const char *s)
+{
+	size_t h = 0;
+
+	while (*s) {
+		h = h * 31 + *s;
+		s++;
+	}
+	return h;
+}
+
 typedef size_t (*hashmap_hash_fn)(const void *key, void *ctx);
 typedef bool (*hashmap_equal_fn)(const void *key1, const void *key2, void *ctx);
 
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index b688aadf09c5..a4f55f8a460d 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -73,8 +73,6 @@
 #define __printf(a, b)	__attribute__((format(printf, a, b)))
 
 static struct bpf_map *bpf_object__add_map(struct bpf_object *obj);
-static struct bpf_program *bpf_object__find_prog_by_idx(struct bpf_object *obj,
-							int idx);
 static const struct btf_type *
 skip_mods_and_typedefs(const struct btf *btf, __u32 id, __u32 *res_id);
 
@@ -176,6 +174,8 @@ enum kern_feature_id {
 	FEAT_EXP_ATTACH_TYPE,
 	/* bpf_probe_read_{kernel,user}[_str] helpers */
 	FEAT_PROBE_READ_KERN,
+	/* BPF_PROG_BIND_MAP is supported */
+	FEAT_PROG_BIND_MAP,
 	__FEAT_CNT,
 };
 
@@ -193,6 +193,7 @@ struct reloc_desc {
 	int insn_idx;
 	int map_idx;
 	int sym_off;
+	bool processed;
 };
 
 struct bpf_sec_def;
@@ -217,20 +218,45 @@ struct bpf_sec_def {
  * linux/filter.h.
  */
 struct bpf_program {
-	/* Index in elf obj file, for relocation use. */
-	int idx;
-	char *name;
-	int prog_ifindex;
-	char *section_name;
 	const struct bpf_sec_def *sec_def;
-	/* section_name with / replaced by _; makes recursive pinning
+	char *sec_name;
+	size_t sec_idx;
+	/* this program's instruction offset (in number of instructions)
+	 * within its containing ELF section
+	 */
+	size_t sec_insn_off;
+	/* number of original instructions in ELF section belonging to this
+	 * program, not taking into account subprogram instructions possible
+	 * appended later during relocation
+	 */
+	size_t sec_insn_cnt;
+	/* Offset (in number of instructions) of the start of instruction
+	 * belonging to this BPF program  within its containing main BPF
+	 * program. For the entry-point (main) BPF program, this is always
+	 * zero. For a sub-program, this gets reset before each of main BPF
+	 * programs are processed and relocated and is used to determined
+	 * whether sub-program was already appended to the main program, and
+	 * if yes, at which instruction offset.
+	 */
+	size_t sub_insn_off;
+
+	char *name;
+	/* sec_name with / replaced by _; makes recursive pinning
 	 * in bpf_object__pin_programs easier
 	 */
 	char *pin_name;
+
+	/* instructions that belong to BPF program; insns[0] is located at
+	 * sec_insn_off instruction within its ELF section in ELF file, so
+	 * when mapping ELF file instruction index to the local instruction,
+	 * one needs to subtract sec_insn_off; and vice versa.
+	 */
 	struct bpf_insn *insns;
-	size_t insns_cnt, main_prog_cnt;
-	enum bpf_prog_type type;
-	bool load;
+	/* actual number of instruction in this BPF program's image; for
+	 * entry-point BPF programs this includes the size of main program
+	 * itself plus all the used sub-programs, appended at the end
+	 */
+	size_t insns_cnt;
 
 	struct reloc_desc *reloc_desc;
 	int nr_reloc;
@@ -246,7 +272,10 @@ struct bpf_program {
 	void *priv;
 	bpf_program_clear_priv_t clear_priv;
 
+	bool load;
+	enum bpf_prog_type type;
 	enum bpf_attach_type expected_attach_type;
+	int prog_ifindex;
 	__u32 attach_btf_id;
 	__u32 attach_prog_fd;
 	void *func_info;
@@ -382,9 +411,10 @@ struct bpf_object {
 	struct extern_desc *externs;
 	int nr_extern;
 	int kconfig_map_idx;
+	int rodata_map_idx;
 
 	bool loaded;
-	bool has_pseudo_calls;
+	bool has_subcalls;
 
 	/*
 	 * Information when doing elf related work. Only valid if fd
@@ -446,6 +476,8 @@ static Elf_Scn *elf_sec_by_name(const struct bpf_object *obj, const char *name);
 static int elf_sec_hdr(const struct bpf_object *obj, Elf_Scn *scn, GElf_Shdr *hdr);
 static const char *elf_sec_name(const struct bpf_object *obj, Elf_Scn *scn);
 static Elf_Data *elf_sec_data(const struct bpf_object *obj, Elf_Scn *scn);
+static int elf_sym_by_sec_off(const struct bpf_object *obj, size_t sec_idx,
+			      size_t off, __u32 sym_type, GElf_Sym *sym);
 
 void bpf_program__unload(struct bpf_program *prog)
 {
@@ -486,152 +518,160 @@ static void bpf_program__exit(struct bpf_program *prog)
 
 	bpf_program__unload(prog);
 	zfree(&prog->name);
-	zfree(&prog->section_name);
+	zfree(&prog->sec_name);
 	zfree(&prog->pin_name);
 	zfree(&prog->insns);
 	zfree(&prog->reloc_desc);
 
 	prog->nr_reloc = 0;
 	prog->insns_cnt = 0;
-	prog->idx = -1;
+	prog->sec_idx = -1;
 }
 
 static char *__bpf_program__pin_name(struct bpf_program *prog)
 {
 	char *name, *p;
 
-	name = p = strdup(prog->section_name);
+	name = p = strdup(prog->sec_name);
 	while ((p = strchr(p, '/')))
 		*p = '_';
 
 	return name;
 }
 
+static bool insn_is_subprog_call(const struct bpf_insn *insn)
+{
+	return BPF_CLASS(insn->code) == BPF_JMP &&
+	       BPF_OP(insn->code) == BPF_CALL &&
+	       BPF_SRC(insn->code) == BPF_K &&
+	       insn->src_reg == BPF_PSEUDO_CALL &&
+	       insn->dst_reg == 0 &&
+	       insn->off == 0;
+}
+
 static int
-bpf_program__init(void *data, size_t size, const char *section_name, int idx,
-		  struct bpf_program *prog)
+bpf_object__init_prog(struct bpf_object *obj, struct bpf_program *prog,
+		      const char *name, size_t sec_idx, const char *sec_name,
+		      size_t sec_off, void *insn_data, size_t insn_data_sz)
 {
-	const size_t bpf_insn_sz = sizeof(struct bpf_insn);
+	int i;
 
-	if (size == 0 || size % bpf_insn_sz) {
-		pr_warn("corrupted section '%s', size: %zu\n",
-			section_name, size);
+	if (insn_data_sz == 0 || insn_data_sz % BPF_INSN_SZ || sec_off % BPF_INSN_SZ) {
+		pr_warn("sec '%s': corrupted program '%s', offset %zu, size %zu\n",
+			sec_name, name, sec_off, insn_data_sz);
 		return -EINVAL;
 	}
 
 	memset(prog, 0, sizeof(*prog));
+	prog->obj = obj;
+
+	prog->sec_idx = sec_idx;
+	prog->sec_insn_off = sec_off / BPF_INSN_SZ;
+	prog->sec_insn_cnt = insn_data_sz / BPF_INSN_SZ;
+	/* insns_cnt can later be increased by appending used subprograms */
+	prog->insns_cnt = prog->sec_insn_cnt;
 
-	prog->section_name = strdup(section_name);
-	if (!prog->section_name) {
-		pr_warn("failed to alloc name for prog under section(%d) %s\n",
-			idx, section_name);
+	prog->type = BPF_PROG_TYPE_UNSPEC;
+	prog->load = true;
+
+	prog->instances.fds = NULL;
+	prog->instances.nr = -1;
+
+	prog->sec_name = strdup(sec_name);
+	if (!prog->sec_name)
+		goto errout;
+
+	prog->name = strdup(name);
+	if (!prog->name)
 		goto errout;
-	}
 
 	prog->pin_name = __bpf_program__pin_name(prog);
-	if (!prog->pin_name) {
-		pr_warn("failed to alloc pin name for prog under section(%d) %s\n",
-			idx, section_name);
+	if (!prog->pin_name)
 		goto errout;
-	}
 
-	prog->insns = malloc(size);
-	if (!prog->insns) {
-		pr_warn("failed to alloc insns for prog under section %s\n",
-			section_name);
+	prog->insns = malloc(insn_data_sz);
+	if (!prog->insns)
 		goto errout;
+	memcpy(prog->insns, insn_data, insn_data_sz);
+
+	for (i = 0; i < prog->insns_cnt; i++) {
+		if (insn_is_subprog_call(&prog->insns[i])) {
+			obj->has_subcalls = true;
+			break;
+		}
 	}
-	prog->insns_cnt = size / bpf_insn_sz;
-	memcpy(prog->insns, data, size);
-	prog->idx = idx;
-	prog->instances.fds = NULL;
-	prog->instances.nr = -1;
-	prog->type = BPF_PROG_TYPE_UNSPEC;
-	prog->load = true;
 
 	return 0;
 errout:
+	pr_warn("sec '%s': failed to allocate memory for prog '%s'\n", sec_name, name);
 	bpf_program__exit(prog);
 	return -ENOMEM;
 }
 
 static int
-bpf_object__add_program(struct bpf_object *obj, void *data, size_t size,
-			const char *section_name, int idx)
+bpf_object__add_programs(struct bpf_object *obj, Elf_Data *sec_data,
+			 const char *sec_name, int sec_idx)
 {
-	struct bpf_program prog, *progs;
+	struct bpf_program *prog, *progs;
+	void *data = sec_data->d_buf;
+	size_t sec_sz = sec_data->d_size, sec_off, prog_sz;
 	int nr_progs, err;
-
-	err = bpf_program__init(data, size, section_name, idx, &prog);
-	if (err)
-		return err;
+	const char *name;
+	GElf_Sym sym;
 
 	progs = obj->programs;
 	nr_progs = obj->nr_programs;
+	sec_off = 0;
 
-	progs = libbpf_reallocarray(progs, nr_progs + 1, sizeof(progs[0]));
-	if (!progs) {
-		/*
-		 * In this case the original obj->programs
-		 * is still valid, so don't need special treat for
-		 * bpf_close_object().
-		 */
-		pr_warn("failed to alloc a new program under section '%s'\n",
-			section_name);
-		bpf_program__exit(&prog);
-		return -ENOMEM;
-	}
-
-	pr_debug("elf: found program '%s'\n", prog.section_name);
-	obj->programs = progs;
-	obj->nr_programs = nr_progs + 1;
-	prog.obj = obj;
-	progs[nr_progs] = prog;
-	return 0;
-}
+	while (sec_off < sec_sz) {
+		if (elf_sym_by_sec_off(obj, sec_idx, sec_off, STT_FUNC, &sym)) {
+			pr_warn("sec '%s': failed to find program symbol at offset %zu\n",
+				sec_name, sec_off);
+			return -LIBBPF_ERRNO__FORMAT;
+		}
 
-static int
-bpf_object__init_prog_names(struct bpf_object *obj)
-{
-	Elf_Data *symbols = obj->efile.symbols;
-	struct bpf_program *prog;
-	size_t pi, si;
+		prog_sz = sym.st_size;
 
-	for (pi = 0; pi < obj->nr_programs; pi++) {
-		const char *name = NULL;
+		name = elf_sym_str(obj, sym.st_name);
+		if (!name) {
+			pr_warn("sec '%s': failed to get symbol name for offset %zu\n",
+				sec_name, sec_off);
+			return -LIBBPF_ERRNO__FORMAT;
+		}
 
-		prog = &obj->programs[pi];
+		if (sec_off + prog_sz > sec_sz) {
+			pr_warn("sec '%s': program at offset %zu crosses section boundary\n",
+				sec_name, sec_off);
+			return -LIBBPF_ERRNO__FORMAT;
+		}
 
-		for (si = 0; si < symbols->d_size / sizeof(GElf_Sym) && !name; si++) {
-			GElf_Sym sym;
+		pr_debug("sec '%s': found program '%s' at insn offset %zu (%zu bytes), code size %zu insns (%zu bytes)\n",
+			 sec_name, name, sec_off / BPF_INSN_SZ, sec_off, prog_sz / BPF_INSN_SZ, prog_sz);
 
-			if (!gelf_getsym(symbols, si, &sym))
-				continue;
-			if (sym.st_shndx != prog->idx)
-				continue;
-			if (GELF_ST_BIND(sym.st_info) != STB_GLOBAL)
-				continue;
-
-			name = elf_sym_str(obj, sym.st_name);
-			if (!name) {
-				pr_warn("prog '%s': failed to get symbol name\n",
-					prog->section_name);
-				return -LIBBPF_ERRNO__LIBELF;
-			}
+		progs = libbpf_reallocarray(progs, nr_progs + 1, sizeof(*progs));
+		if (!progs) {
+			/*
+			 * In this case the original obj->programs
+			 * is still valid, so don't need special treat for
+			 * bpf_close_object().
+			 */
+			pr_warn("sec '%s': failed to alloc memory for new program '%s'\n",
+				sec_name, name);
+			return -ENOMEM;
 		}
+		obj->programs = progs;
 
-		if (!name && prog->idx == obj->efile.text_shndx)
-			name = ".text";
+		prog = &progs[nr_progs];
 
-		if (!name) {
-			pr_warn("prog '%s': failed to find program symbol\n",
-				prog->section_name);
-			return -EINVAL;
-		}
+		err = bpf_object__init_prog(obj, prog, name, sec_idx, sec_name,
+					    sec_off, data + sec_off, prog_sz);
+		if (err)
+			return err;
 
-		prog->name = strdup(name);
-		if (!prog->name)
-			return -ENOMEM;
+		nr_progs++;
+		obj->nr_programs = nr_progs;
+
+		sec_off += prog_sz;
 	}
 
 	return 0;
@@ -1033,6 +1073,7 @@ static struct bpf_object *bpf_object__new(const char *path,
 	obj->efile.bss_shndx = -1;
 	obj->efile.st_ops_shndx = -1;
 	obj->kconfig_map_idx = -1;
+	obj->rodata_map_idx = -1;
 
 	obj->kern_version = get_kernel_version();
 	obj->loaded = false;
@@ -1391,6 +1432,8 @@ static int bpf_object__init_global_data_maps(struct bpf_object *obj)
 						    obj->efile.rodata->d_size);
 		if (err)
 			return err;
+
+		obj->rodata_map_idx = obj->nr_maps - 1;
 	}
 	if (obj->efile.bss_shndx >= 0) {
 		err = bpf_object__init_internal_map(obj, LIBBPF_MAP_BSS,
@@ -2675,6 +2718,26 @@ static Elf_Data *elf_sec_data(const struct bpf_object *obj, Elf_Scn *scn)
 	return data;
 }
 
+static int elf_sym_by_sec_off(const struct bpf_object *obj, size_t sec_idx,
+			      size_t off, __u32 sym_type, GElf_Sym *sym)
+{
+	Elf_Data *symbols = obj->efile.symbols;
+	size_t n = symbols->d_size / sizeof(GElf_Sym);
+	int i;
+
+	for (i = 0; i < n; i++) {
+		if (!gelf_getsym(symbols, i, sym))
+			continue;
+		if (sym->st_shndx != sec_idx || sym->st_value != off)
+			continue;
+		if (GELF_ST_TYPE(sym->st_info) != sym_type)
+			continue;
+		return 0;
+	}
+
+	return -ENOENT;
+}
+
 static bool is_sec_name_dwarf(const char *name)
 {
 	/* approximation, but the actual list is too long */
@@ -2715,19 +2778,55 @@ static bool ignore_elf_section(GElf_Shdr *hdr, const char *name)
 	return false;
 }
 
+static int cmp_progs(const void *_a, const void *_b)
+{
+	const struct bpf_program *a = _a;
+	const struct bpf_program *b = _b;
+
+	if (a->sec_idx != b->sec_idx)
+		return a->sec_idx < b->sec_idx ? -1 : 1;
+
+	/* sec_insn_off can't be the same within the section */
+	return a->sec_insn_off < b->sec_insn_off ? -1 : 1;
+}
+
 static int bpf_object__elf_collect(struct bpf_object *obj)
 {
 	Elf *elf = obj->efile.elf;
 	Elf_Data *btf_ext_data = NULL;
 	Elf_Data *btf_data = NULL;
-	Elf_Scn *scn = NULL;
 	int idx = 0, err = 0;
+	const char *name;
+	Elf_Data *data;
+	Elf_Scn *scn;
+	GElf_Shdr sh;
 
+	/* a bunch of ELF parsing functionality depends on processing symbols,
+	 * so do the first pass and find the symbol table
+	 */
+	scn = NULL;
 	while ((scn = elf_nextscn(elf, scn)) != NULL) {
-		const char *name;
-		GElf_Shdr sh;
-		Elf_Data *data;
+		if (elf_sec_hdr(obj, scn, &sh))
+			return -LIBBPF_ERRNO__FORMAT;
+
+		if (sh.sh_type == SHT_SYMTAB) {
+			if (obj->efile.symbols) {
+				pr_warn("elf: multiple symbol tables in %s\n", obj->path);
+				return -LIBBPF_ERRNO__FORMAT;
+			}
+
+			data = elf_sec_data(obj, scn);
+			if (!data)
+				return -LIBBPF_ERRNO__FORMAT;
+
+			obj->efile.symbols = data;
+			obj->efile.symbols_shndx = elf_ndxscn(scn);
+			obj->efile.strtabidx = sh.sh_link;
+		}
+	}
 
+	scn = NULL;
+	while ((scn = elf_nextscn(elf, scn)) != NULL) {
 		idx++;
 
 		if (elf_sec_hdr(obj, scn, &sh))
@@ -2766,20 +2865,12 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 		} else if (strcmp(name, BTF_EXT_ELF_SEC) == 0) {
 			btf_ext_data = data;
 		} else if (sh.sh_type == SHT_SYMTAB) {
-			if (obj->efile.symbols) {
-				pr_warn("elf: multiple symbol tables in %s\n", obj->path);
-				return -LIBBPF_ERRNO__FORMAT;
-			}
-			obj->efile.symbols = data;
-			obj->efile.symbols_shndx = idx;
-			obj->efile.strtabidx = sh.sh_link;
+			/* already processed during the first pass above */
 		} else if (sh.sh_type == SHT_PROGBITS && data->d_size > 0) {
 			if (sh.sh_flags & SHF_EXECINSTR) {
 				if (strcmp(name, ".text") == 0)
 					obj->efile.text_shndx = idx;
-				err = bpf_object__add_program(obj, data->d_buf,
-							      data->d_size,
-							      name, idx);
+				err = bpf_object__add_programs(obj, data, name, idx);
 				if (err)
 					return err;
 			} else if (strcmp(name, DATA_SEC) == 0) {
@@ -2833,6 +2924,11 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 		pr_warn("elf: symbol strings section missing or invalid in %s\n", obj->path);
 		return -LIBBPF_ERRNO__FORMAT;
 	}
+
+	/* sort BPF programs by section name and in-section instruction offset
+	 * for faster search */
+	qsort(obj->programs, obj->nr_programs, sizeof(*obj->programs), cmp_progs);
+
 	return bpf_object__init_btf(obj, btf_data, btf_ext_data);
 }
 
@@ -3157,20 +3253,6 @@ static int bpf_object__collect_externs(struct bpf_object *obj)
 	return 0;
 }
 
-static struct bpf_program *
-bpf_object__find_prog_by_idx(struct bpf_object *obj, int idx)
-{
-	struct bpf_program *prog;
-	size_t i;
-
-	for (i = 0; i < obj->nr_programs; i++) {
-		prog = &obj->programs[i];
-		if (prog->idx == idx)
-			return prog;
-	}
-	return NULL;
-}
-
 struct bpf_program *
 bpf_object__find_program_by_title(const struct bpf_object *obj,
 				  const char *title)
@@ -3178,12 +3260,18 @@ bpf_object__find_program_by_title(const struct bpf_object *obj,
 	struct bpf_program *pos;
 
 	bpf_object__for_each_program(pos, obj) {
-		if (pos->section_name && !strcmp(pos->section_name, title))
+		if (pos->sec_name && !strcmp(pos->sec_name, title))
 			return pos;
 	}
 	return NULL;
 }
 
+static bool prog_is_subprog(const struct bpf_object *obj,
+			    const struct bpf_program *prog)
+{
+	return prog->sec_idx == obj->efile.text_shndx && obj->has_subcalls;
+}
+
 struct bpf_program *
 bpf_object__find_program_by_name(const struct bpf_object *obj,
 				 const char *name)
@@ -3191,6 +3279,8 @@ bpf_object__find_program_by_name(const struct bpf_object *obj,
 	struct bpf_program *prog;
 
 	bpf_object__for_each_program(prog, obj) {
+		if (prog_is_subprog(obj, prog))
+			continue;
 		if (!strcmp(prog->name, name))
 			return prog;
 	}
@@ -3240,6 +3330,8 @@ static int bpf_program__record_reloc(struct bpf_program *prog,
 	const char *sym_sec_name;
 	struct bpf_map *map;
 
+	reloc_desc->processed = false;
+
 	/* sub-program call relocation */
 	if (insn->code == (BPF_JMP | BPF_CALL)) {
 		if (insn->src_reg != BPF_PSEUDO_CALL) {
@@ -3261,7 +3353,6 @@ static int bpf_program__record_reloc(struct bpf_program *prog,
 		reloc_desc->type = RELO_CALL;
 		reloc_desc->insn_idx = insn_idx;
 		reloc_desc->sym_off = sym->st_value;
-		obj->has_pseudo_calls = true;
 		return 0;
 	}
 
@@ -3361,14 +3452,50 @@ static int bpf_program__record_reloc(struct bpf_program *prog,
 	return 0;
 }
 
+static bool prog_contains_insn(const struct bpf_program *prog, size_t insn_idx)
+{
+	return insn_idx >= prog->sec_insn_off &&
+	       insn_idx < prog->sec_insn_off + prog->sec_insn_cnt;
+}
+
+static struct bpf_program *find_prog_by_sec_insn(const struct bpf_object *obj,
+						 size_t sec_idx, size_t insn_idx)
+{
+	int l = 0, r = obj->nr_programs - 1, m;
+	struct bpf_program *prog;
+
+	while (l < r) {
+		m = l + (r - l + 1) / 2;
+		prog = &obj->programs[m];
+
+		if (prog->sec_idx < sec_idx ||
+		    (prog->sec_idx == sec_idx && prog->sec_insn_off <= insn_idx))
+			l = m;
+		else
+			r = m - 1;
+	}
+	/* matching program could be at index l, but it still might be the
+	 * wrong one, so we need to double check conditions for the last time
+	 */
+	prog = &obj->programs[l];
+	if (prog->sec_idx == sec_idx && prog_contains_insn(prog, insn_idx))
+		return prog;
+	return NULL;
+}
+
 static int
-bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr,
-			   Elf_Data *data, struct bpf_object *obj)
+bpf_object__collect_prog_relos(struct bpf_object *obj, GElf_Shdr *shdr, Elf_Data *data)
 {
 	Elf_Data *symbols = obj->efile.symbols;
 	const char *relo_sec_name, *sec_name;
 	size_t sec_idx = shdr->sh_info;
+	struct bpf_program *prog;
+	struct reloc_desc *relos;
 	int err, i, nrels;
+	const char *sym_name;
+	__u32 insn_idx;
+	GElf_Sym sym;
+	GElf_Rel rel;
 
 	relo_sec_name = elf_sec_str(obj, shdr->sh_name);
 	sec_name = elf_sec_name(obj, elf_sec_by_idx(obj, sec_idx));
@@ -3379,19 +3506,7 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr,
 		 relo_sec_name, sec_idx, sec_name);
 	nrels = shdr->sh_size / shdr->sh_entsize;
 
-	prog->reloc_desc = malloc(sizeof(*prog->reloc_desc) * nrels);
-	if (!prog->reloc_desc) {
-		pr_warn("failed to alloc memory in relocation\n");
-		return -ENOMEM;
-	}
-	prog->nr_reloc = nrels;
-
 	for (i = 0; i < nrels; i++) {
-		const char *sym_name;
-		__u32 insn_idx;
-		GElf_Sym sym;
-		GElf_Rel rel;
-
 		if (!gelf_getrel(data, i, &rel)) {
 			pr_warn("sec '%s': failed to get relo #%d\n", relo_sec_name, i);
 			return -LIBBPF_ERRNO__FORMAT;
@@ -3408,15 +3523,42 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr,
 		}
 
 		insn_idx = rel.r_offset / BPF_INSN_SZ;
-		sym_name = elf_sym_str(obj, sym.st_name) ?: "<?>";
+		/* relocations against static functions are recorded as
+		 * relocations against the section that contains a function;
+		 * in such case, symbol will be STT_SECTION and sym.st_name
+		 * will point to empty string (0), so fetch section name
+		 * instead
+		 */
+		if (GELF_ST_TYPE(sym.st_info) == STT_SECTION && sym.st_name == 0)
+			sym_name = elf_sec_name(obj, elf_sec_by_idx(obj, sym.st_shndx));
+		else
+			sym_name = elf_sym_str(obj, sym.st_name);
+		sym_name = sym_name ?: "<?";
 
 		pr_debug("sec '%s': relo #%d: insn #%u against '%s'\n",
 			 relo_sec_name, i, insn_idx, sym_name);
 
-		err = bpf_program__record_reloc(prog, &prog->reloc_desc[i],
+		prog = find_prog_by_sec_insn(obj, sec_idx, insn_idx);
+		if (!prog) {
+			pr_warn("sec '%s': relo #%d: program not found in section '%s' for insn #%u\n",
+				relo_sec_name, i, sec_name, insn_idx);
+			return -LIBBPF_ERRNO__RELOC;
+		}
+
+		relos = libbpf_reallocarray(prog->reloc_desc,
+					    prog->nr_reloc + 1, sizeof(*relos));
+		if (!relos)
+			return -ENOMEM;
+		prog->reloc_desc = relos;
+
+		/* adjust insn_idx to local BPF program frame of reference */
+		insn_idx -= prog->sec_insn_off;
+		err = bpf_program__record_reloc(prog, &relos[prog->nr_reloc],
 						insn_idx, sym_name, &sym, &rel);
 		if (err)
 			return err;
+
+		prog->nr_reloc++;
 	}
 	return 0;
 }
@@ -3758,6 +3900,52 @@ static int probe_kern_probe_read_kernel(void)
 	return probe_fd(bpf_load_program_xattr(&attr, NULL, 0));
 }
 
+static int probe_prog_bind_map(void)
+{
+	struct bpf_load_program_attr prg_attr;
+	struct bpf_create_map_attr map_attr;
+	char *cp, errmsg[STRERR_BUFSIZE];
+	struct bpf_insn insns[] = {
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	};
+	int ret, map, prog;
+
+	memset(&map_attr, 0, sizeof(map_attr));
+	map_attr.map_type = BPF_MAP_TYPE_ARRAY;
+	map_attr.key_size = sizeof(int);
+	map_attr.value_size = 32;
+	map_attr.max_entries = 1;
+
+	map = bpf_create_map_xattr(&map_attr);
+	if (map < 0) {
+		ret = -errno;
+		cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg));
+		pr_warn("Error in %s():%s(%d). Couldn't create simple array map.\n",
+			__func__, cp, -ret);
+		return ret;
+	}
+
+	memset(&prg_attr, 0, sizeof(prg_attr));
+	prg_attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER;
+	prg_attr.insns = insns;
+	prg_attr.insns_cnt = ARRAY_SIZE(insns);
+	prg_attr.license = "GPL";
+
+	prog = bpf_load_program_xattr(&prg_attr, NULL, 0);
+	if (prog < 0) {
+		close(map);
+		return 0;
+	}
+
+	ret = bpf_prog_bind_map(prog, map, NULL);
+
+	close(map);
+	close(prog);
+
+	return ret >= 0;
+}
+
 enum kern_feature_result {
 	FEAT_UNKNOWN = 0,
 	FEAT_SUPPORTED = 1,
@@ -3798,6 +3986,9 @@ static struct kern_feature_desc {
 	},
 	[FEAT_PROBE_READ_KERN] = {
 		"bpf_probe_read_kernel() helper", probe_kern_probe_read_kernel,
+	},
+	[FEAT_PROG_BIND_MAP] = {
+		"BPF_PROG_BIND_MAP support", probe_prog_bind_map,
 	}
 };
 
@@ -4089,75 +4280,6 @@ err_out:
 	return err;
 }
 
-static int
-check_btf_ext_reloc_err(struct bpf_program *prog, int err,
-			void *btf_prog_info, const char *info_name)
-{
-	if (err != -ENOENT) {
-		pr_warn("Error in loading %s for sec %s.\n",
-			info_name, prog->section_name);
-		return err;
-	}
-
-	/* err == -ENOENT (i.e. prog->section_name not found in btf_ext) */
-
-	if (btf_prog_info) {
-		/*
-		 * Some info has already been found but has problem
-		 * in the last btf_ext reloc. Must have to error out.
-		 */
-		pr_warn("Error in relocating %s for sec %s.\n",
-			info_name, prog->section_name);
-		return err;
-	}
-
-	/* Have problem loading the very first info. Ignore the rest. */
-	pr_warn("Cannot find %s for main program sec %s. Ignore all %s.\n",
-		info_name, prog->section_name, info_name);
-	return 0;
-}
-
-static int
-bpf_program_reloc_btf_ext(struct bpf_program *prog, struct bpf_object *obj,
-			  const char *section_name,  __u32 insn_offset)
-{
-	int err;
-
-	if (!insn_offset || prog->func_info) {
-		/*
-		 * !insn_offset => main program
-		 *
-		 * For sub prog, the main program's func_info has to
-		 * be loaded first (i.e. prog->func_info != NULL)
-		 */
-		err = btf_ext__reloc_func_info(obj->btf, obj->btf_ext,
-					       section_name, insn_offset,
-					       &prog->func_info,
-					       &prog->func_info_cnt);
-		if (err)
-			return check_btf_ext_reloc_err(prog, err,
-						       prog->func_info,
-						       "bpf_func_info");
-
-		prog->func_info_rec_size = btf_ext__func_info_rec_size(obj->btf_ext);
-	}
-
-	if (!insn_offset || prog->line_info) {
-		err = btf_ext__reloc_line_info(obj->btf, obj->btf_ext,
-					       section_name, insn_offset,
-					       &prog->line_info,
-					       &prog->line_info_cnt);
-		if (err)
-			return check_btf_ext_reloc_err(prog, err,
-						       prog->line_info,
-						       "bpf_line_info");
-
-		prog->line_info_rec_size = btf_ext__line_info_rec_size(obj->btf_ext);
-	}
-
-	return 0;
-}
-
 #define BPF_CORE_SPEC_MAX_LEN 64
 
 /* represents BPF CO-RE field or array element accessor */
@@ -4927,8 +5049,7 @@ static int bpf_core_calc_field_relo(const struct bpf_program *prog,
 			*val = sz;
 		} else {
 			pr_warn("prog '%s': relo %d at insn #%d can't be applied to array access\n",
-				bpf_program__title(prog, false),
-				relo->kind, relo->insn_off / 8);
+				prog->name, relo->kind, relo->insn_off / 8);
 			return -EINVAL;
 		}
 		if (validate)
@@ -4950,8 +5071,7 @@ static int bpf_core_calc_field_relo(const struct bpf_program *prog,
 			if (byte_sz >= 8) {
 				/* bitfield can't be read with 64-bit read */
 				pr_warn("prog '%s': relo %d at insn #%d can't be satisfied for bitfield\n",
-					bpf_program__title(prog, false),
-					relo->kind, relo->insn_off / 8);
+					prog->name, relo->kind, relo->insn_off / 8);
 				return -E2BIG;
 			}
 			byte_sz *= 2;
@@ -5116,8 +5236,8 @@ static int bpf_core_calc_relo(const struct bpf_program *prog,
 	} else if (err == -EOPNOTSUPP) {
 		/* EOPNOTSUPP means unknown/unsupported relocation */
 		pr_warn("prog '%s': relo #%d: unrecognized CO-RE relocation %s (%d) at insn #%d\n",
-			bpf_program__title(prog, false), relo_idx,
-			core_relo_kind_str(relo->kind), relo->kind, relo->insn_off / 8);
+			prog->name, relo_idx, core_relo_kind_str(relo->kind),
+			relo->kind, relo->insn_off / 8);
 	}
 
 	return err;
@@ -5131,7 +5251,7 @@ static void bpf_core_poison_insn(struct bpf_program *prog, int relo_idx,
 				 int insn_idx, struct bpf_insn *insn)
 {
 	pr_debug("prog '%s': relo #%d: substituting insn #%d w/ invalid insn\n",
-		 bpf_program__title(prog, false), relo_idx, insn_idx);
+		 prog->name, relo_idx, insn_idx);
 	insn->code = BPF_JMP | BPF_CALL;
 	insn->dst_reg = 0;
 	insn->src_reg = 0;
@@ -5175,6 +5295,11 @@ static int bpf_core_patch_insn(struct bpf_program *prog,
 	if (relo->insn_off % BPF_INSN_SZ)
 		return -EINVAL;
 	insn_idx = relo->insn_off / BPF_INSN_SZ;
+	/* adjust insn_idx from section frame of reference to the local
+	 * program's frame of reference; (sub-)program code is not yet
+	 * relocated, so it's enough to just subtract in-section offset
+	 */
+	insn_idx = insn_idx - prog->sec_insn_off;
 	insn = &prog->insns[insn_idx];
 	class = BPF_CLASS(insn->code);
 
@@ -5198,14 +5323,14 @@ static int bpf_core_patch_insn(struct bpf_program *prog,
 			return -EINVAL;
 		if (res->validate && insn->imm != orig_val) {
 			pr_warn("prog '%s': relo #%d: unexpected insn #%d (ALU/ALU64) value: got %u, exp %u -> %u\n",
-				bpf_program__title(prog, false), relo_idx,
+				prog->name, relo_idx,
 				insn_idx, insn->imm, orig_val, new_val);
 			return -EINVAL;
 		}
 		orig_val = insn->imm;
 		insn->imm = new_val;
 		pr_debug("prog '%s': relo #%d: patched insn #%d (ALU/ALU64) imm %u -> %u\n",
-			 bpf_program__title(prog, false), relo_idx, insn_idx,
+			 prog->name, relo_idx, insn_idx,
 			 orig_val, new_val);
 		break;
 	case BPF_LDX:
@@ -5213,21 +5338,18 @@ static int bpf_core_patch_insn(struct bpf_program *prog,
 	case BPF_STX:
 		if (res->validate && insn->off != orig_val) {
 			pr_warn("prog '%s': relo #%d: unexpected insn #%d (LDX/ST/STX) value: got %u, exp %u -> %u\n",
-				bpf_program__title(prog, false), relo_idx,
-				insn_idx, insn->off, orig_val, new_val);
+				prog->name, relo_idx, insn_idx, insn->off, orig_val, new_val);
 			return -EINVAL;
 		}
 		if (new_val > SHRT_MAX) {
 			pr_warn("prog '%s': relo #%d: insn #%d (LDX/ST/STX) value too big: %u\n",
-				bpf_program__title(prog, false), relo_idx,
-				insn_idx, new_val);
+				prog->name, relo_idx, insn_idx, new_val);
 			return -ERANGE;
 		}
 		orig_val = insn->off;
 		insn->off = new_val;
 		pr_debug("prog '%s': relo #%d: patched insn #%d (LDX/ST/STX) off %u -> %u\n",
-			 bpf_program__title(prog, false), relo_idx, insn_idx,
-			 orig_val, new_val);
+			 prog->name, relo_idx, insn_idx, orig_val, new_val);
 		break;
 	case BPF_LD: {
 		__u64 imm;
@@ -5238,14 +5360,14 @@ static int bpf_core_patch_insn(struct bpf_program *prog,
 		    insn[1].code != 0 || insn[1].dst_reg != 0 ||
 		    insn[1].src_reg != 0 || insn[1].off != 0) {
 			pr_warn("prog '%s': relo #%d: insn #%d (LDIMM64) has unexpected form\n",
-				bpf_program__title(prog, false), relo_idx, insn_idx);
+				prog->name, relo_idx, insn_idx);
 			return -EINVAL;
 		}
 
 		imm = insn[0].imm + ((__u64)insn[1].imm << 32);
 		if (res->validate && imm != orig_val) {
 			pr_warn("prog '%s': relo #%d: unexpected insn #%d (LDIMM64) value: got %llu, exp %u -> %u\n",
-				bpf_program__title(prog, false), relo_idx,
+				prog->name, relo_idx,
 				insn_idx, (unsigned long long)imm,
 				orig_val, new_val);
 			return -EINVAL;
@@ -5254,15 +5376,14 @@ static int bpf_core_patch_insn(struct bpf_program *prog,
 		insn[0].imm = new_val;
 		insn[1].imm = 0; /* currently only 32-bit values are supported */
 		pr_debug("prog '%s': relo #%d: patched insn #%d (LDIMM64) imm64 %llu -> %u\n",
-			 bpf_program__title(prog, false), relo_idx, insn_idx,
+			 prog->name, relo_idx, insn_idx,
 			 (unsigned long long)imm, new_val);
 		break;
 	}
 	default:
 		pr_warn("prog '%s': relo #%d: trying to relocate unrecognized insn #%d, code:0x%x, src:0x%x, dst:0x%x, off:0x%x, imm:0x%x\n",
-			bpf_program__title(prog, false), relo_idx,
-			insn_idx, insn->code, insn->src_reg, insn->dst_reg,
-			insn->off, insn->imm);
+			prog->name, relo_idx, insn_idx, insn->code,
+			insn->src_reg, insn->dst_reg, insn->off, insn->imm);
 		return -EINVAL;
 	}
 
@@ -5392,7 +5513,6 @@ static int bpf_core_apply_relo(struct bpf_program *prog,
 			       const struct btf *targ_btf,
 			       struct hashmap *cand_cache)
 {
-	const char *prog_name = bpf_program__title(prog, false);
 	struct bpf_core_spec local_spec, cand_spec, targ_spec = {};
 	const void *type_key = u32_as_hash_key(relo->type_id);
 	struct bpf_core_relo_res cand_res, targ_res;
@@ -5419,13 +5539,13 @@ static int bpf_core_apply_relo(struct bpf_program *prog,
 	err = bpf_core_parse_spec(local_btf, local_id, spec_str, relo->kind, &local_spec);
 	if (err) {
 		pr_warn("prog '%s': relo #%d: parsing [%d] %s %s + %s failed: %d\n",
-			prog_name, relo_idx, local_id, btf_kind_str(local_type),
+			prog->name, relo_idx, local_id, btf_kind_str(local_type),
 			str_is_empty(local_name) ? "<anon>" : local_name,
 			spec_str, err);
 		return -EINVAL;
 	}
 
-	pr_debug("prog '%s': relo #%d: kind <%s> (%d), spec is ", prog_name,
+	pr_debug("prog '%s': relo #%d: kind <%s> (%d), spec is ", prog->name,
 		 relo_idx, core_relo_kind_str(relo->kind), relo->kind);
 	bpf_core_dump_spec(LIBBPF_DEBUG, &local_spec);
 	libbpf_print(LIBBPF_DEBUG, "\n");
@@ -5442,7 +5562,7 @@ static int bpf_core_apply_relo(struct bpf_program *prog,
 	/* libbpf doesn't support candidate search for anonymous types */
 	if (str_is_empty(spec_str)) {
 		pr_warn("prog '%s': relo #%d: <%s> (%d) relocation doesn't support anonymous types\n",
-			prog_name, relo_idx, core_relo_kind_str(relo->kind), relo->kind);
+			prog->name, relo_idx, core_relo_kind_str(relo->kind), relo->kind);
 		return -EOPNOTSUPP;
 	}
 
@@ -5450,7 +5570,7 @@ static int bpf_core_apply_relo(struct bpf_program *prog,
 		cand_ids = bpf_core_find_cands(local_btf, local_id, targ_btf);
 		if (IS_ERR(cand_ids)) {
 			pr_warn("prog '%s': relo #%d: target candidate search failed for [%d] %s %s: %ld",
-				prog_name, relo_idx, local_id, btf_kind_str(local_type),
+				prog->name, relo_idx, local_id, btf_kind_str(local_type),
 				local_name, PTR_ERR(cand_ids));
 			return PTR_ERR(cand_ids);
 		}
@@ -5466,13 +5586,13 @@ static int bpf_core_apply_relo(struct bpf_program *prog,
 		err = bpf_core_spec_match(&local_spec, targ_btf, cand_id, &cand_spec);
 		if (err < 0) {
 			pr_warn("prog '%s': relo #%d: error matching candidate #%d ",
-				prog_name, relo_idx, i);
+				prog->name, relo_idx, i);
 			bpf_core_dump_spec(LIBBPF_WARN, &cand_spec);
 			libbpf_print(LIBBPF_WARN, ": %d\n", err);
 			return err;
 		}
 
-		pr_debug("prog '%s': relo #%d: %s candidate #%d ", prog_name,
+		pr_debug("prog '%s': relo #%d: %s candidate #%d ", prog->name,
 			 relo_idx, err == 0 ? "non-matching" : "matching", i);
 		bpf_core_dump_spec(LIBBPF_DEBUG, &cand_spec);
 		libbpf_print(LIBBPF_DEBUG, "\n");
@@ -5492,7 +5612,7 @@ static int bpf_core_apply_relo(struct bpf_program *prog,
 			 * should all resolve to the same bit offset
 			 */
 			pr_warn("prog '%s': relo #%d: field offset ambiguity: %u != %u\n",
-				prog_name, relo_idx, cand_spec.bit_offset,
+				prog->name, relo_idx, cand_spec.bit_offset,
 				targ_spec.bit_offset);
 			return -EINVAL;
 		} else if (cand_res.poison != targ_res.poison || cand_res.new_val != targ_res.new_val) {
@@ -5501,7 +5621,7 @@ static int bpf_core_apply_relo(struct bpf_program *prog,
 			 * proceed due to ambiguity
 			 */
 			pr_warn("prog '%s': relo #%d: relocation decision ambiguity: %s %u != %s %u\n",
-				prog_name, relo_idx,
+				prog->name, relo_idx,
 				cand_res.poison ? "failure" : "success", cand_res.new_val,
 				targ_res.poison ? "failure" : "success", targ_res.new_val);
 			return -EINVAL;
@@ -5534,7 +5654,7 @@ static int bpf_core_apply_relo(struct bpf_program *prog,
 	 */
 	if (j == 0) {
 		pr_debug("prog '%s': relo #%d: no matching targets found\n",
-			 prog_name, relo_idx);
+			 prog->name, relo_idx);
 
 		/* calculate single target relo result explicitly */
 		err = bpf_core_calc_relo(prog, relo, relo_idx, &local_spec, NULL, &targ_res);
@@ -5547,7 +5667,7 @@ patch_insn:
 	err = bpf_core_patch_insn(prog, relo, relo_idx, &targ_res);
 	if (err) {
 		pr_warn("prog '%s': relo #%d: failed to patch insn at offset %d: %d\n",
-			prog_name, relo_idx, relo->insn_off, err);
+			prog->name, relo_idx, relo->insn_off, err);
 		return -EINVAL;
 	}
 
@@ -5565,7 +5685,7 @@ bpf_object__relocate_core(struct bpf_object *obj, const char *targ_btf_path)
 	struct bpf_program *prog;
 	struct btf *targ_btf;
 	const char *sec_name;
-	int i, err = 0;
+	int i, err = 0, insn_idx, sec_idx;
 
 	if (obj->btf_ext->core_relo_info.len == 0)
 		return 0;
@@ -5592,24 +5712,37 @@ bpf_object__relocate_core(struct bpf_object *obj, const char *targ_btf_path)
 			err = -EINVAL;
 			goto out;
 		}
+		/* bpf_object's ELF is gone by now so it's not easy to find
+		 * section index by section name, but we can find *any*
+		 * bpf_program within desired section name and use it's
+		 * prog->sec_idx to do a proper search by section index and
+		 * instruction offset
+		 */
 		prog = NULL;
 		for (i = 0; i < obj->nr_programs; i++) {
-			if (!strcmp(obj->programs[i].section_name, sec_name)) {
-				prog = &obj->programs[i];
+			prog = &obj->programs[i];
+			if (strcmp(prog->sec_name, sec_name) == 0)
 				break;
-			}
 		}
 		if (!prog) {
-			pr_warn("failed to find program '%s' for CO-RE offset relocation\n",
-				sec_name);
-			err = -EINVAL;
-			goto out;
+			pr_warn("sec '%s': failed to find a BPF program\n", sec_name);
+			return -ENOENT;
 		}
+		sec_idx = prog->sec_idx;
 
 		pr_debug("sec '%s': found %d CO-RE relocations\n",
 			 sec_name, sec->num_info);
 
 		for_each_btf_ext_rec(seg, sec, i, rec) {
+			insn_idx = rec->insn_off / BPF_INSN_SZ;
+			prog = find_prog_by_sec_insn(obj, sec_idx, insn_idx);
+			if (!prog) {
+				pr_warn("sec '%s': failed to find program at insn #%d for CO-RE offset relocation #%d\n",
+					sec_name, insn_idx, i);
+				err = -EINVAL;
+				goto out;
+			}
+
 			err = bpf_core_apply_relo(prog, rec, i, obj->btf,
 						  targ_btf, cand_cache);
 			if (err) {
@@ -5633,89 +5766,32 @@ out:
 	return err;
 }
 
+/* Relocate data references within program code:
+ *  - map references;
+ *  - global variable references;
+ *  - extern references.
+ */
 static int
-bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj,
-			struct reloc_desc *relo)
-{
-	struct bpf_insn *insn, *new_insn;
-	struct bpf_program *text;
-	size_t new_cnt;
-	int err;
-
-	if (prog->idx != obj->efile.text_shndx && prog->main_prog_cnt == 0) {
-		text = bpf_object__find_prog_by_idx(obj, obj->efile.text_shndx);
-		if (!text) {
-			pr_warn("no .text section found yet relo into text exist\n");
-			return -LIBBPF_ERRNO__RELOC;
-		}
-		new_cnt = prog->insns_cnt + text->insns_cnt;
-		new_insn = libbpf_reallocarray(prog->insns, new_cnt, sizeof(*insn));
-		if (!new_insn) {
-			pr_warn("oom in prog realloc\n");
-			return -ENOMEM;
-		}
-		prog->insns = new_insn;
-
-		if (obj->btf_ext) {
-			err = bpf_program_reloc_btf_ext(prog, obj,
-							text->section_name,
-							prog->insns_cnt);
-			if (err)
-				return err;
-		}
-
-		memcpy(new_insn + prog->insns_cnt, text->insns,
-		       text->insns_cnt * sizeof(*insn));
-		prog->main_prog_cnt = prog->insns_cnt;
-		prog->insns_cnt = new_cnt;
-		pr_debug("added %zd insn from %s to prog %s\n",
-			 text->insns_cnt, text->section_name,
-			 prog->section_name);
-	}
-
-	insn = &prog->insns[relo->insn_idx];
-	insn->imm += relo->sym_off / 8 + prog->main_prog_cnt - relo->insn_idx;
-	return 0;
-}
-
-static int
-bpf_program__relocate(struct bpf_program *prog, struct bpf_object *obj)
+bpf_object__relocate_data(struct bpf_object *obj, struct bpf_program *prog)
 {
-	int i, err;
-
-	if (!prog)
-		return 0;
-
-	if (obj->btf_ext) {
-		err = bpf_program_reloc_btf_ext(prog, obj,
-						prog->section_name, 0);
-		if (err)
-			return err;
-	}
-
-	if (!prog->reloc_desc)
-		return 0;
+	int i;
 
 	for (i = 0; i < prog->nr_reloc; i++) {
 		struct reloc_desc *relo = &prog->reloc_desc[i];
 		struct bpf_insn *insn = &prog->insns[relo->insn_idx];
 		struct extern_desc *ext;
 
-		if (relo->insn_idx + 1 >= (int)prog->insns_cnt) {
-			pr_warn("relocation out of range: '%s'\n",
-				prog->section_name);
-			return -LIBBPF_ERRNO__RELOC;
-		}
-
 		switch (relo->type) {
 		case RELO_LD64:
 			insn[0].src_reg = BPF_PSEUDO_MAP_FD;
 			insn[0].imm = obj->maps[relo->map_idx].fd;
+			relo->processed = true;
 			break;
 		case RELO_DATA:
 			insn[0].src_reg = BPF_PSEUDO_MAP_VALUE;
 			insn[1].imm = insn[0].imm + relo->sym_off;
 			insn[0].imm = obj->maps[relo->map_idx].fd;
+			relo->processed = true;
 			break;
 		case RELO_EXTERN:
 			ext = &obj->externs[relo->sym_off];
@@ -5727,11 +5803,10 @@ bpf_program__relocate(struct bpf_program *prog, struct bpf_object *obj)
 				insn[0].imm = (__u32)ext->ksym.addr;
 				insn[1].imm = ext->ksym.addr >> 32;
 			}
+			relo->processed = true;
 			break;
 		case RELO_CALL:
-			err = bpf_program__reloc_text(prog, obj, relo);
-			if (err)
-				return err;
+			/* will be handled as a follow up pass */
 			break;
 		default:
 			pr_warn("prog '%s': relo #%d: bad relo type %d\n",
@@ -5740,8 +5815,378 @@ bpf_program__relocate(struct bpf_program *prog, struct bpf_object *obj)
 		}
 	}
 
-	zfree(&prog->reloc_desc);
-	prog->nr_reloc = 0;
+	return 0;
+}
+
+static int adjust_prog_btf_ext_info(const struct bpf_object *obj,
+				    const struct bpf_program *prog,
+				    const struct btf_ext_info *ext_info,
+				    void **prog_info, __u32 *prog_rec_cnt,
+				    __u32 *prog_rec_sz)
+{
+	void *copy_start = NULL, *copy_end = NULL;
+	void *rec, *rec_end, *new_prog_info;
+	const struct btf_ext_info_sec *sec;
+	size_t old_sz, new_sz;
+	const char *sec_name;
+	int i, off_adj;
+
+	for_each_btf_ext_sec(ext_info, sec) {
+		sec_name = btf__name_by_offset(obj->btf, sec->sec_name_off);
+		if (!sec_name)
+			return -EINVAL;
+		if (strcmp(sec_name, prog->sec_name) != 0)
+			continue;
+
+		for_each_btf_ext_rec(ext_info, sec, i, rec) {
+			__u32 insn_off = *(__u32 *)rec / BPF_INSN_SZ;
+
+			if (insn_off < prog->sec_insn_off)
+				continue;
+			if (insn_off >= prog->sec_insn_off + prog->sec_insn_cnt)
+				break;
+
+			if (!copy_start)
+				copy_start = rec;
+			copy_end = rec + ext_info->rec_size;
+		}
+
+		if (!copy_start)
+			return -ENOENT;
+
+		/* append func/line info of a given (sub-)program to the main
+		 * program func/line info
+		 */
+		old_sz = (size_t)(*prog_rec_cnt) * ext_info->rec_size;
+		new_sz = old_sz + (copy_end - copy_start);
+		new_prog_info = realloc(*prog_info, new_sz);
+		if (!new_prog_info)
+			return -ENOMEM;
+		*prog_info = new_prog_info;
+		*prog_rec_cnt = new_sz / ext_info->rec_size;
+		memcpy(new_prog_info + old_sz, copy_start, copy_end - copy_start);
+
+		/* Kernel instruction offsets are in units of 8-byte
+		 * instructions, while .BTF.ext instruction offsets generated
+		 * by Clang are in units of bytes. So convert Clang offsets
+		 * into kernel offsets and adjust offset according to program
+		 * relocated position.
+		 */
+		off_adj = prog->sub_insn_off - prog->sec_insn_off;
+		rec = new_prog_info + old_sz;
+		rec_end = new_prog_info + new_sz;
+		for (; rec < rec_end; rec += ext_info->rec_size) {
+			__u32 *insn_off = rec;
+
+			*insn_off = *insn_off / BPF_INSN_SZ + off_adj;
+		}
+		*prog_rec_sz = ext_info->rec_size;
+		return 0;
+	}
+
+	return -ENOENT;
+}
+
+static int
+reloc_prog_func_and_line_info(const struct bpf_object *obj,
+			      struct bpf_program *main_prog,
+			      const struct bpf_program *prog)
+{
+	int err;
+
+	/* no .BTF.ext relocation if .BTF.ext is missing or kernel doesn't
+	 * supprot func/line info
+	 */
+	if (!obj->btf_ext || !kernel_supports(FEAT_BTF_FUNC))
+		return 0;
+
+	/* only attempt func info relocation if main program's func_info
+	 * relocation was successful
+	 */
+	if (main_prog != prog && !main_prog->func_info)
+		goto line_info;
+
+	err = adjust_prog_btf_ext_info(obj, prog, &obj->btf_ext->func_info,
+				       &main_prog->func_info,
+				       &main_prog->func_info_cnt,
+				       &main_prog->func_info_rec_size);
+	if (err) {
+		if (err != -ENOENT) {
+			pr_warn("prog '%s': error relocating .BTF.ext function info: %d\n",
+				prog->name, err);
+			return err;
+		}
+		if (main_prog->func_info) {
+			/*
+			 * Some info has already been found but has problem
+			 * in the last btf_ext reloc. Must have to error out.
+			 */
+			pr_warn("prog '%s': missing .BTF.ext function info.\n", prog->name);
+			return err;
+		}
+		/* Have problem loading the very first info. Ignore the rest. */
+		pr_warn("prog '%s': missing .BTF.ext function info for the main program, skipping all of .BTF.ext func info.\n",
+			prog->name);
+	}
+
+line_info:
+	/* don't relocate line info if main program's relocation failed */
+	if (main_prog != prog && !main_prog->line_info)
+		return 0;
+
+	err = adjust_prog_btf_ext_info(obj, prog, &obj->btf_ext->line_info,
+				       &main_prog->line_info,
+				       &main_prog->line_info_cnt,
+				       &main_prog->line_info_rec_size);
+	if (err) {
+		if (err != -ENOENT) {
+			pr_warn("prog '%s': error relocating .BTF.ext line info: %d\n",
+				prog->name, err);
+			return err;
+		}
+		if (main_prog->line_info) {
+			/*
+			 * Some info has already been found but has problem
+			 * in the last btf_ext reloc. Must have to error out.
+			 */
+			pr_warn("prog '%s': missing .BTF.ext line info.\n", prog->name);
+			return err;
+		}
+		/* Have problem loading the very first info. Ignore the rest. */
+		pr_warn("prog '%s': missing .BTF.ext line info for the main program, skipping all of .BTF.ext line info.\n",
+			prog->name);
+	}
+	return 0;
+}
+
+static int cmp_relo_by_insn_idx(const void *key, const void *elem)
+{
+	size_t insn_idx = *(const size_t *)key;
+	const struct reloc_desc *relo = elem;
+
+	if (insn_idx == relo->insn_idx)
+		return 0;
+	return insn_idx < relo->insn_idx ? -1 : 1;
+}
+
+static struct reloc_desc *find_prog_insn_relo(const struct bpf_program *prog, size_t insn_idx)
+{
+	return bsearch(&insn_idx, prog->reloc_desc, prog->nr_reloc,
+		       sizeof(*prog->reloc_desc), cmp_relo_by_insn_idx);
+}
+
+static int
+bpf_object__reloc_code(struct bpf_object *obj, struct bpf_program *main_prog,
+		       struct bpf_program *prog)
+{
+	size_t sub_insn_idx, insn_idx, new_cnt;
+	struct bpf_program *subprog;
+	struct bpf_insn *insns, *insn;
+	struct reloc_desc *relo;
+	int err;
+
+	err = reloc_prog_func_and_line_info(obj, main_prog, prog);
+	if (err)
+		return err;
+
+	for (insn_idx = 0; insn_idx < prog->sec_insn_cnt; insn_idx++) {
+		insn = &main_prog->insns[prog->sub_insn_off + insn_idx];
+		if (!insn_is_subprog_call(insn))
+			continue;
+
+		relo = find_prog_insn_relo(prog, insn_idx);
+		if (relo && relo->type != RELO_CALL) {
+			pr_warn("prog '%s': unexpected relo for insn #%zu, type %d\n",
+				prog->name, insn_idx, relo->type);
+			return -LIBBPF_ERRNO__RELOC;
+		}
+		if (relo) {
+			/* sub-program instruction index is a combination of
+			 * an offset of a symbol pointed to by relocation and
+			 * call instruction's imm field; for global functions,
+			 * call always has imm = -1, but for static functions
+			 * relocation is against STT_SECTION and insn->imm
+			 * points to a start of a static function
+			 */
+			sub_insn_idx = relo->sym_off / BPF_INSN_SZ + insn->imm + 1;
+		} else {
+			/* if subprogram call is to a static function within
+			 * the same ELF section, there won't be any relocation
+			 * emitted, but it also means there is no additional
+			 * offset necessary, insns->imm is relative to
+			 * instruction's original position within the section
+			 */
+			sub_insn_idx = prog->sec_insn_off + insn_idx + insn->imm + 1;
+		}
+
+		/* we enforce that sub-programs should be in .text section */
+		subprog = find_prog_by_sec_insn(obj, obj->efile.text_shndx, sub_insn_idx);
+		if (!subprog) {
+			pr_warn("prog '%s': no .text section found yet sub-program call exists\n",
+				prog->name);
+			return -LIBBPF_ERRNO__RELOC;
+		}
+
+		/* if it's the first call instruction calling into this
+		 * subprogram (meaning this subprog hasn't been processed
+		 * yet) within the context of current main program:
+		 *   - append it at the end of main program's instructions blog;
+		 *   - process is recursively, while current program is put on hold;
+		 *   - if that subprogram calls some other not yet processes
+		 *   subprogram, same thing will happen recursively until
+		 *   there are no more unprocesses subprograms left to append
+		 *   and relocate.
+		 */
+		if (subprog->sub_insn_off == 0) {
+			subprog->sub_insn_off = main_prog->insns_cnt;
+
+			new_cnt = main_prog->insns_cnt + subprog->insns_cnt;
+			insns = libbpf_reallocarray(main_prog->insns, new_cnt, sizeof(*insns));
+			if (!insns) {
+				pr_warn("prog '%s': failed to realloc prog code\n", main_prog->name);
+				return -ENOMEM;
+			}
+			main_prog->insns = insns;
+			main_prog->insns_cnt = new_cnt;
+
+			memcpy(main_prog->insns + subprog->sub_insn_off, subprog->insns,
+			       subprog->insns_cnt * sizeof(*insns));
+
+			pr_debug("prog '%s': added %zu insns from sub-prog '%s'\n",
+				 main_prog->name, subprog->insns_cnt, subprog->name);
+
+			err = bpf_object__reloc_code(obj, main_prog, subprog);
+			if (err)
+				return err;
+		}
+
+		/* main_prog->insns memory could have been re-allocated, so
+		 * calculate pointer again
+		 */
+		insn = &main_prog->insns[prog->sub_insn_off + insn_idx];
+		/* calculate correct instruction position within current main
+		 * prog; each main prog can have a different set of
+		 * subprograms appended (potentially in different order as
+		 * well), so position of any subprog can be different for
+		 * different main programs */
+		insn->imm = subprog->sub_insn_off - (prog->sub_insn_off + insn_idx) - 1;
+
+		if (relo)
+			relo->processed = true;
+
+		pr_debug("prog '%s': insn #%zu relocated, imm %d points to subprog '%s' (now at %zu offset)\n",
+			 prog->name, insn_idx, insn->imm, subprog->name, subprog->sub_insn_off);
+	}
+
+	return 0;
+}
+
+/*
+ * Relocate sub-program calls.
+ *
+ * Algorithm operates as follows. Each entry-point BPF program (referred to as
+ * main prog) is processed separately. For each subprog (non-entry functions,
+ * that can be called from either entry progs or other subprogs) gets their
+ * sub_insn_off reset to zero. This serves as indicator that this subprogram
+ * hasn't been yet appended and relocated within current main prog. Once its
+ * relocated, sub_insn_off will point at the position within current main prog
+ * where given subprog was appended. This will further be used to relocate all
+ * the call instructions jumping into this subprog.
+ *
+ * We start with main program and process all call instructions. If the call
+ * is into a subprog that hasn't been processed (i.e., subprog->sub_insn_off
+ * is zero), subprog instructions are appended at the end of main program's
+ * instruction array. Then main program is "put on hold" while we recursively
+ * process newly appended subprogram. If that subprogram calls into another
+ * subprogram that hasn't been appended, new subprogram is appended again to
+ * the *main* prog's instructions (subprog's instructions are always left
+ * untouched, as they need to be in unmodified state for subsequent main progs
+ * and subprog instructions are always sent only as part of a main prog) and
+ * the process continues recursively. Once all the subprogs called from a main
+ * prog or any of its subprogs are appended (and relocated), all their
+ * positions within finalized instructions array are known, so it's easy to
+ * rewrite call instructions with correct relative offsets, corresponding to
+ * desired target subprog.
+ *
+ * Its important to realize that some subprogs might not be called from some
+ * main prog and any of its called/used subprogs. Those will keep their
+ * subprog->sub_insn_off as zero at all times and won't be appended to current
+ * main prog and won't be relocated within the context of current main prog.
+ * They might still be used from other main progs later.
+ *
+ * Visually this process can be shown as below. Suppose we have two main
+ * programs mainA and mainB and BPF object contains three subprogs: subA,
+ * subB, and subC. mainA calls only subA, mainB calls only subC, but subA and
+ * subC both call subB:
+ *
+ *        +--------+ +-------+
+ *        |        v v       |
+ *     +--+---+ +--+-+-+ +---+--+
+ *     | subA | | subB | | subC |
+ *     +--+---+ +------+ +---+--+
+ *        ^                  ^
+ *        |                  |
+ *    +---+-------+   +------+----+
+ *    |   mainA   |   |   mainB   |
+ *    +-----------+   +-----------+
+ *
+ * We'll start relocating mainA, will find subA, append it and start
+ * processing sub A recursively:
+ *
+ *    +-----------+------+
+ *    |   mainA   | subA |
+ *    +-----------+------+
+ *
+ * At this point we notice that subB is used from subA, so we append it and
+ * relocate (there are no further subcalls from subB):
+ *
+ *    +-----------+------+------+
+ *    |   mainA   | subA | subB |
+ *    +-----------+------+------+
+ *
+ * At this point, we relocate subA calls, then go one level up and finish with
+ * relocatin mainA calls. mainA is done.
+ *
+ * For mainB process is similar but results in different order. We start with
+ * mainB and skip subA and subB, as mainB never calls them (at least
+ * directly), but we see subC is needed, so we append and start processing it:
+ *
+ *    +-----------+------+
+ *    |   mainB   | subC |
+ *    +-----------+------+
+ * Now we see subC needs subB, so we go back to it, append and relocate it:
+ *
+ *    +-----------+------+------+
+ *    |   mainB   | subC | subB |
+ *    +-----------+------+------+
+ *
+ * At this point we unwind recursion, relocate calls in subC, then in mainB.
+ */
+static int
+bpf_object__relocate_calls(struct bpf_object *obj, struct bpf_program *prog)
+{
+	struct bpf_program *subprog;
+	int i, j, err;
+
+	/* mark all subprogs as not relocated (yet) within the context of
+	 * current main program
+	 */
+	for (i = 0; i < obj->nr_programs; i++) {
+		subprog = &obj->programs[i];
+		if (!prog_is_subprog(obj, subprog))
+			continue;
+
+		subprog->sub_insn_off = 0;
+		for (j = 0; j < subprog->nr_reloc; j++)
+			if (subprog->reloc_desc[j].type == RELO_CALL)
+				subprog->reloc_desc[j].processed = false;
+	}
+
+	err = bpf_object__reloc_code(obj, prog, prog);
+	if (err)
+		return err;
+
+
 	return 0;
 }
 
@@ -5760,37 +6205,45 @@ bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path)
 			return err;
 		}
 	}
-	/* ensure .text is relocated first, as it's going to be copied as-is
-	 * later for sub-program calls
+	/* relocate data references first for all programs and sub-programs,
+	 * as they don't change relative to code locations, so subsequent
+	 * subprogram processing won't need to re-calculate any of them
 	 */
 	for (i = 0; i < obj->nr_programs; i++) {
 		prog = &obj->programs[i];
-		if (prog->idx != obj->efile.text_shndx)
-			continue;
-
-		err = bpf_program__relocate(prog, obj);
+		err = bpf_object__relocate_data(obj, prog);
 		if (err) {
 			pr_warn("prog '%s': failed to relocate data references: %d\n",
 				prog->name, err);
 			return err;
 		}
-		break;
 	}
-	/* now relocate everything but .text, which by now is relocated
-	 * properly, so we can copy raw sub-program instructions as is safely
+	/* now relocate subprogram calls and append used subprograms to main
+	 * programs; each copy of subprogram code needs to be relocated
+	 * differently for each main program, because its code location might
+	 * have changed
 	 */
 	for (i = 0; i < obj->nr_programs; i++) {
 		prog = &obj->programs[i];
-		if (prog->idx == obj->efile.text_shndx)
+		/* sub-program's sub-calls are relocated within the context of
+		 * its main program only
+		 */
+		if (prog_is_subprog(obj, prog))
 			continue;
 
-		err = bpf_program__relocate(prog, obj);
+		err = bpf_object__relocate_calls(obj, prog);
 		if (err) {
 			pr_warn("prog '%s': failed to relocate calls: %d\n",
 				prog->name, err);
 			return err;
 		}
 	}
+	/* free up relocation descriptors */
+	for (i = 0; i < obj->nr_programs; i++) {
+		prog = &obj->programs[i];
+		zfree(&prog->reloc_desc);
+		prog->nr_reloc = 0;
+	}
 	return 0;
 }
 
@@ -5804,8 +6257,8 @@ static int bpf_object__collect_map_relos(struct bpf_object *obj,
 	int i, j, nrels, new_sz;
 	const struct btf_var_secinfo *vi = NULL;
 	const struct btf_type *sec, *var, *def;
+	struct bpf_map *map = NULL, *targ_map;
 	const struct btf_member *member;
-	struct bpf_map *map, *targ_map;
 	const char *name, *mname;
 	Elf_Data *symbols;
 	unsigned int moff;
@@ -5910,41 +6363,53 @@ static int bpf_object__collect_map_relos(struct bpf_object *obj,
 	return 0;
 }
 
-static int bpf_object__collect_reloc(struct bpf_object *obj)
+static int cmp_relocs(const void *_a, const void *_b)
 {
-	int i, err;
+	const struct reloc_desc *a = _a;
+	const struct reloc_desc *b = _b;
 
-	if (!obj_elf_valid(obj)) {
-		pr_warn("Internal error: elf object is closed\n");
-		return -LIBBPF_ERRNO__INTERNAL;
-	}
+	if (a->insn_idx != b->insn_idx)
+		return a->insn_idx < b->insn_idx ? -1 : 1;
+
+	/* no two relocations should have the same insn_idx, but ... */
+	if (a->type != b->type)
+		return a->type < b->type ? -1 : 1;
+
+	return 0;
+}
+
+static int bpf_object__collect_relos(struct bpf_object *obj)
+{
+	int i, err;
 
 	for (i = 0; i < obj->efile.nr_reloc_sects; i++) {
 		GElf_Shdr *shdr = &obj->efile.reloc_sects[i].shdr;
 		Elf_Data *data = obj->efile.reloc_sects[i].data;
 		int idx = shdr->sh_info;
-		struct bpf_program *prog;
 
 		if (shdr->sh_type != SHT_REL) {
 			pr_warn("internal error at %d\n", __LINE__);
 			return -LIBBPF_ERRNO__INTERNAL;
 		}
 
-		if (idx == obj->efile.st_ops_shndx) {
+		if (idx == obj->efile.st_ops_shndx)
 			err = bpf_object__collect_st_ops_relos(obj, shdr, data);
-		} else if (idx == obj->efile.btf_maps_shndx) {
+		else if (idx == obj->efile.btf_maps_shndx)
 			err = bpf_object__collect_map_relos(obj, shdr, data);
-		} else {
-			prog = bpf_object__find_prog_by_idx(obj, idx);
-			if (!prog) {
-				pr_warn("relocation failed: no prog in section(%d)\n", idx);
-				return -LIBBPF_ERRNO__RELOC;
-			}
-			err = bpf_program__collect_reloc(prog, shdr, data, obj);
-		}
+		else
+			err = bpf_object__collect_prog_relos(obj, shdr, data);
 		if (err)
 			return err;
 	}
+
+	for (i = 0; i < obj->nr_programs; i++) {
+		struct bpf_program *p = &obj->programs[i];
+		
+		if (!p->nr_reloc)
+			continue;
+
+		qsort(p->reloc_desc, p->nr_reloc, sizeof(*p->reloc_desc), cmp_relocs);
+	}
 	return 0;
 }
 
@@ -6058,6 +6523,20 @@ retry_load:
 	if (ret >= 0) {
 		if (log_buf && load_attr.log_level)
 			pr_debug("verifier log:\n%s", log_buf);
+
+		if (prog->obj->rodata_map_idx >= 0 &&
+		    kernel_supports(FEAT_PROG_BIND_MAP)) {
+			struct bpf_map *rodata_map =
+				&prog->obj->maps[prog->obj->rodata_map_idx];
+
+			if (bpf_prog_bind_map(ret, bpf_map__fd(rodata_map), NULL)) {
+				cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
+				pr_warn("prog '%s': failed to bind .rodata map: %s\n",
+					prog->name, cp);
+				/* Don't fail hard if can't bind rodata. */
+			}
+		}
+
 		*pfd = ret;
 		ret = 0;
 		goto out;
@@ -6110,8 +6589,7 @@ int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver)
 	int err = 0, fd, i, btf_id;
 
 	if (prog->obj->loaded) {
-		pr_warn("prog '%s'('%s'): can't load after object was loaded\n",
-			prog->name, prog->section_name);
+		pr_warn("prog '%s': can't load after object was loaded\n", prog->name);
 		return -EINVAL;
 	}
 
@@ -6127,7 +6605,7 @@ int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver)
 	if (prog->instances.nr < 0 || !prog->instances.fds) {
 		if (prog->preprocessor) {
 			pr_warn("Internal error: can't load program '%s'\n",
-				prog->section_name);
+				prog->name);
 			return -LIBBPF_ERRNO__INTERNAL;
 		}
 
@@ -6142,8 +6620,8 @@ int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver)
 
 	if (!prog->preprocessor) {
 		if (prog->instances.nr != 1) {
-			pr_warn("Program '%s' is inconsistent: nr(%d) != 1\n",
-				prog->section_name, prog->instances.nr);
+			pr_warn("prog '%s': inconsistent nr(%d) != 1\n",
+				prog->name, prog->instances.nr);
 		}
 		err = load_program(prog, prog->insns, prog->insns_cnt,
 				   license, kern_ver, &fd);
@@ -6161,13 +6639,13 @@ int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver)
 				   prog->insns_cnt, &result);
 		if (err) {
 			pr_warn("Preprocessing the %dth instance of program '%s' failed\n",
-				i, prog->section_name);
+				i, prog->name);
 			goto out;
 		}
 
 		if (!result.new_insn_ptr || !result.new_insn_cnt) {
 			pr_debug("Skip loading the %dth instance of program '%s'\n",
-				 i, prog->section_name);
+				 i, prog->name);
 			prog->instances.fds[i] = -1;
 			if (result.pfd)
 				*result.pfd = -1;
@@ -6178,7 +6656,7 @@ int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver)
 				   result.new_insn_cnt, license, kern_ver, &fd);
 		if (err) {
 			pr_warn("Loading the %dth instance of program '%s' failed\n",
-				i, prog->section_name);
+				i, prog->name);
 			goto out;
 		}
 
@@ -6188,18 +6666,12 @@ int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver)
 	}
 out:
 	if (err)
-		pr_warn("failed to load program '%s'\n", prog->section_name);
+		pr_warn("failed to load program '%s'\n", prog->name);
 	zfree(&prog->insns);
 	prog->insns_cnt = 0;
 	return err;
 }
 
-static bool bpf_program__is_function_storage(const struct bpf_program *prog,
-					     const struct bpf_object *obj)
-{
-	return prog->idx == obj->efile.text_shndx && obj->has_pseudo_calls;
-}
-
 static int
 bpf_object__load_progs(struct bpf_object *obj, int log_level)
 {
@@ -6216,7 +6688,7 @@ bpf_object__load_progs(struct bpf_object *obj, int log_level)
 
 	for (i = 0; i < obj->nr_programs; i++) {
 		prog = &obj->programs[i];
-		if (bpf_program__is_function_storage(prog, obj))
+		if (prog_is_subprog(obj, prog))
 			continue;
 		if (!prog->load) {
 			pr_debug("prog '%s': skipped loading\n", prog->name);
@@ -6280,14 +6752,13 @@ __bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz,
 	err = err ? : bpf_object__collect_externs(obj);
 	err = err ? : bpf_object__finalize_btf(obj);
 	err = err ? : bpf_object__init_maps(obj, opts);
-	err = err ? : bpf_object__init_prog_names(obj);
-	err = err ? : bpf_object__collect_reloc(obj);
+	err = err ? : bpf_object__collect_relos(obj);
 	if (err)
 		goto out;
 	bpf_object__elf_finish(obj);
 
 	bpf_object__for_each_program(prog, obj) {
-		prog->sec_def = find_sec_def(prog->section_name);
+		prog->sec_def = find_sec_def(prog->sec_name);
 		if (!prog->sec_def)
 			/* couldn't guess, but user might manually specify */
 			continue;
@@ -6668,7 +7139,7 @@ int bpf_program__pin_instance(struct bpf_program *prog, const char *path,
 
 	if (instance < 0 || instance >= prog->instances.nr) {
 		pr_warn("invalid prog instance %d of prog %s (max %d)\n",
-			instance, prog->section_name, prog->instances.nr);
+			instance, prog->name, prog->instances.nr);
 		return -EINVAL;
 	}
 
@@ -6699,7 +7170,7 @@ int bpf_program__unpin_instance(struct bpf_program *prog, const char *path,
 
 	if (instance < 0 || instance >= prog->instances.nr) {
 		pr_warn("invalid prog instance %d of prog %s (max %d)\n",
-			instance, prog->section_name, prog->instances.nr);
+			instance, prog->name, prog->instances.nr);
 		return -EINVAL;
 	}
 
@@ -6729,8 +7200,7 @@ int bpf_program__pin(struct bpf_program *prog, const char *path)
 	}
 
 	if (prog->instances.nr <= 0) {
-		pr_warn("no instances of prog %s to pin\n",
-			   prog->section_name);
+		pr_warn("no instances of prog %s to pin\n", prog->name);
 		return -EINVAL;
 	}
 
@@ -6792,8 +7262,7 @@ int bpf_program__unpin(struct bpf_program *prog, const char *path)
 	}
 
 	if (prog->instances.nr <= 0) {
-		pr_warn("no instances of prog %s to pin\n",
-			   prog->section_name);
+		pr_warn("no instances of prog %s to pin\n", prog->name);
 		return -EINVAL;
 	}
 
@@ -7285,7 +7754,7 @@ bpf_program__next(struct bpf_program *prev, const struct bpf_object *obj)
 
 	do {
 		prog = __bpf_program__iter(prog, obj, true);
-	} while (prog && bpf_program__is_function_storage(prog, obj));
+	} while (prog && prog_is_subprog(obj, prog));
 
 	return prog;
 }
@@ -7297,7 +7766,7 @@ bpf_program__prev(struct bpf_program *next, const struct bpf_object *obj)
 
 	do {
 		prog = __bpf_program__iter(prog, obj, false);
-	} while (prog && bpf_program__is_function_storage(prog, obj));
+	} while (prog && prog_is_subprog(obj, prog));
 
 	return prog;
 }
@@ -7328,11 +7797,16 @@ const char *bpf_program__name(const struct bpf_program *prog)
 	return prog->name;
 }
 
+const char *bpf_program__section_name(const struct bpf_program *prog)
+{
+	return prog->sec_name;
+}
+
 const char *bpf_program__title(const struct bpf_program *prog, bool needs_copy)
 {
 	const char *title;
 
-	title = prog->section_name;
+	title = prog->sec_name;
 	if (needs_copy) {
 		title = strdup(title);
 		if (!title) {
@@ -7405,14 +7879,14 @@ int bpf_program__nth_fd(const struct bpf_program *prog, int n)
 
 	if (n >= prog->instances.nr || n < 0) {
 		pr_warn("Can't get the %dth fd from program %s: only %d instances\n",
-			n, prog->section_name, prog->instances.nr);
+			n, prog->name, prog->instances.nr);
 		return -EINVAL;
 	}
 
 	fd = prog->instances.fds[n];
 	if (fd < 0) {
 		pr_warn("%dth instance of program '%s' is invalid\n",
-			n, prog->section_name);
+			n, prog->name);
 		return -ENOENT;
 	}
 
@@ -7772,7 +8246,7 @@ static int bpf_object__collect_st_ops_relos(struct bpf_object *obj,
 	const struct btf *btf;
 	struct bpf_map *map;
 	Elf_Data *symbols;
-	unsigned int moff;
+	unsigned int moff, insn_idx;
 	const char *name;
 	__u32 member_idx;
 	GElf_Sym sym;
@@ -7817,6 +8291,12 @@ static int bpf_object__collect_st_ops_relos(struct bpf_object *obj,
 				map->name, (size_t)rel.r_offset, shdr_idx);
 			return -LIBBPF_ERRNO__RELOC;
 		}
+		if (sym.st_value % BPF_INSN_SZ) {
+			pr_warn("struct_ops reloc %s: invalid target program offset %llu\n",
+				map->name, (unsigned long long)sym.st_value);
+			return -LIBBPF_ERRNO__FORMAT;
+		}
+		insn_idx = sym.st_value / BPF_INSN_SZ;
 
 		member = find_member_by_offset(st_ops->type, moff * 8);
 		if (!member) {
@@ -7833,7 +8313,7 @@ static int bpf_object__collect_st_ops_relos(struct bpf_object *obj,
 			return -EINVAL;
 		}
 
-		prog = bpf_object__find_prog_by_idx(obj, shdr_idx);
+		prog = find_prog_by_sec_insn(obj, shdr_idx, insn_idx);
 		if (!prog) {
 			pr_warn("struct_ops reloc %s: cannot find prog at shdr_idx %u to relocate func ptr %s\n",
 				map->name, shdr_idx, name);
@@ -7843,7 +8323,7 @@ static int bpf_object__collect_st_ops_relos(struct bpf_object *obj,
 		if (prog->type == BPF_PROG_TYPE_UNSPEC) {
 			const struct bpf_sec_def *sec_def;
 
-			sec_def = find_sec_def(prog->section_name);
+			sec_def = find_sec_def(prog->sec_name);
 			if (sec_def &&
 			    sec_def->prog_type != BPF_PROG_TYPE_STRUCT_OPS) {
 				/* for pr_warn */
@@ -7866,7 +8346,7 @@ static int bpf_object__collect_st_ops_relos(struct bpf_object *obj,
 
 invalid_prog:
 	pr_warn("struct_ops reloc %s: cannot use prog %s in sec %s with type %u attach_btf_id %u expected_attach_type %u for func ptr %s\n",
-		map->name, prog->name, prog->section_name, prog->type,
+		map->name, prog->name, prog->sec_name, prog->type,
 		prog->attach_btf_id, prog->expected_attach_type, name);
 	return -EINVAL;
 }
@@ -7970,7 +8450,7 @@ static int libbpf_find_attach_btf_id(struct bpf_program *prog)
 {
 	enum bpf_attach_type attach_type = prog->expected_attach_type;
 	__u32 attach_prog_fd = prog->attach_prog_fd;
-	const char *name = prog->section_name;
+	const char *name = prog->sec_name;
 	int i, err;
 
 	if (!name)
@@ -8497,14 +8977,14 @@ struct bpf_link *bpf_program__attach_perf_event(struct bpf_program *prog,
 	int prog_fd, err;
 
 	if (pfd < 0) {
-		pr_warn("program '%s': invalid perf event FD %d\n",
-			bpf_program__title(prog, false), pfd);
+		pr_warn("prog '%s': invalid perf event FD %d\n",
+			prog->name, pfd);
 		return ERR_PTR(-EINVAL);
 	}
 	prog_fd = bpf_program__fd(prog);
 	if (prog_fd < 0) {
-		pr_warn("program '%s': can't attach BPF program w/o FD (did you load it?)\n",
-			bpf_program__title(prog, false));
+		pr_warn("prog '%s': can't attach BPF program w/o FD (did you load it?)\n",
+			prog->name);
 		return ERR_PTR(-EINVAL);
 	}
 
@@ -8517,20 +8997,18 @@ struct bpf_link *bpf_program__attach_perf_event(struct bpf_program *prog,
 	if (ioctl(pfd, PERF_EVENT_IOC_SET_BPF, prog_fd) < 0) {
 		err = -errno;
 		free(link);
-		pr_warn("program '%s': failed to attach to pfd %d: %s\n",
-			bpf_program__title(prog, false), pfd,
-			   libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
+		pr_warn("prog '%s': failed to attach to pfd %d: %s\n",
+			prog->name, pfd, libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
 		if (err == -EPROTO)
-			pr_warn("program '%s': try add PERF_SAMPLE_CALLCHAIN to or remove exclude_callchain_[kernel|user] from pfd %d\n",
-				bpf_program__title(prog, false), pfd);
+			pr_warn("prog '%s': try add PERF_SAMPLE_CALLCHAIN to or remove exclude_callchain_[kernel|user] from pfd %d\n",
+				prog->name, pfd);
 		return ERR_PTR(err);
 	}
 	if (ioctl(pfd, PERF_EVENT_IOC_ENABLE, 0) < 0) {
 		err = -errno;
 		free(link);
-		pr_warn("program '%s': failed to enable pfd %d: %s\n",
-			bpf_program__title(prog, false), pfd,
-			   libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
+		pr_warn("prog '%s': failed to enable pfd %d: %s\n",
+			prog->name, pfd, libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
 		return ERR_PTR(err);
 	}
 	return link;
@@ -8652,9 +9130,8 @@ struct bpf_link *bpf_program__attach_kprobe(struct bpf_program *prog,
 	pfd = perf_event_open_probe(false /* uprobe */, retprobe, func_name,
 				    0 /* offset */, -1 /* pid */);
 	if (pfd < 0) {
-		pr_warn("program '%s': failed to create %s '%s' perf event: %s\n",
-			bpf_program__title(prog, false),
-			retprobe ? "kretprobe" : "kprobe", func_name,
+		pr_warn("prog '%s': failed to create %s '%s' perf event: %s\n",
+			prog->name, retprobe ? "kretprobe" : "kprobe", func_name,
 			libbpf_strerror_r(pfd, errmsg, sizeof(errmsg)));
 		return ERR_PTR(pfd);
 	}
@@ -8662,9 +9139,8 @@ struct bpf_link *bpf_program__attach_kprobe(struct bpf_program *prog,
 	if (IS_ERR(link)) {
 		close(pfd);
 		err = PTR_ERR(link);
-		pr_warn("program '%s': failed to attach to %s '%s': %s\n",
-			bpf_program__title(prog, false),
-			retprobe ? "kretprobe" : "kprobe", func_name,
+		pr_warn("prog '%s': failed to attach to %s '%s': %s\n",
+			prog->name, retprobe ? "kretprobe" : "kprobe", func_name,
 			libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
 		return link;
 	}
@@ -8677,7 +9153,7 @@ static struct bpf_link *attach_kprobe(const struct bpf_sec_def *sec,
 	const char *func_name;
 	bool retprobe;
 
-	func_name = bpf_program__title(prog, false) + sec->len;
+	func_name = prog->sec_name + sec->len;
 	retprobe = strcmp(sec->sec, "kretprobe/") == 0;
 
 	return bpf_program__attach_kprobe(prog, retprobe, func_name);
@@ -8695,9 +9171,8 @@ struct bpf_link *bpf_program__attach_uprobe(struct bpf_program *prog,
 	pfd = perf_event_open_probe(true /* uprobe */, retprobe,
 				    binary_path, func_offset, pid);
 	if (pfd < 0) {
-		pr_warn("program '%s': failed to create %s '%s:0x%zx' perf event: %s\n",
-			bpf_program__title(prog, false),
-			retprobe ? "uretprobe" : "uprobe",
+		pr_warn("prog '%s': failed to create %s '%s:0x%zx' perf event: %s\n",
+			prog->name, retprobe ? "uretprobe" : "uprobe",
 			binary_path, func_offset,
 			libbpf_strerror_r(pfd, errmsg, sizeof(errmsg)));
 		return ERR_PTR(pfd);
@@ -8706,9 +9181,8 @@ struct bpf_link *bpf_program__attach_uprobe(struct bpf_program *prog,
 	if (IS_ERR(link)) {
 		close(pfd);
 		err = PTR_ERR(link);
-		pr_warn("program '%s': failed to attach to %s '%s:0x%zx': %s\n",
-			bpf_program__title(prog, false),
-			retprobe ? "uretprobe" : "uprobe",
+		pr_warn("prog '%s': failed to attach to %s '%s:0x%zx': %s\n",
+			prog->name, retprobe ? "uretprobe" : "uprobe",
 			binary_path, func_offset,
 			libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
 		return link;
@@ -8776,9 +9250,8 @@ struct bpf_link *bpf_program__attach_tracepoint(struct bpf_program *prog,
 
 	pfd = perf_event_open_tracepoint(tp_category, tp_name);
 	if (pfd < 0) {
-		pr_warn("program '%s': failed to create tracepoint '%s/%s' perf event: %s\n",
-			bpf_program__title(prog, false),
-			tp_category, tp_name,
+		pr_warn("prog '%s': failed to create tracepoint '%s/%s' perf event: %s\n",
+			prog->name, tp_category, tp_name,
 			libbpf_strerror_r(pfd, errmsg, sizeof(errmsg)));
 		return ERR_PTR(pfd);
 	}
@@ -8786,9 +9259,8 @@ struct bpf_link *bpf_program__attach_tracepoint(struct bpf_program *prog,
 	if (IS_ERR(link)) {
 		close(pfd);
 		err = PTR_ERR(link);
-		pr_warn("program '%s': failed to attach to tracepoint '%s/%s': %s\n",
-			bpf_program__title(prog, false),
-			tp_category, tp_name,
+		pr_warn("prog '%s': failed to attach to tracepoint '%s/%s': %s\n",
+			prog->name, tp_category, tp_name,
 			libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
 		return link;
 	}
@@ -8801,7 +9273,7 @@ static struct bpf_link *attach_tp(const struct bpf_sec_def *sec,
 	char *sec_name, *tp_cat, *tp_name;
 	struct bpf_link *link;
 
-	sec_name = strdup(bpf_program__title(prog, false));
+	sec_name = strdup(prog->sec_name);
 	if (!sec_name)
 		return ERR_PTR(-ENOMEM);
 
@@ -8830,8 +9302,7 @@ struct bpf_link *bpf_program__attach_raw_tracepoint(struct bpf_program *prog,
 
 	prog_fd = bpf_program__fd(prog);
 	if (prog_fd < 0) {
-		pr_warn("program '%s': can't attach before loaded\n",
-			bpf_program__title(prog, false));
+		pr_warn("prog '%s': can't attach before loaded\n", prog->name);
 		return ERR_PTR(-EINVAL);
 	}
 
@@ -8844,9 +9315,8 @@ struct bpf_link *bpf_program__attach_raw_tracepoint(struct bpf_program *prog,
 	if (pfd < 0) {
 		pfd = -errno;
 		free(link);
-		pr_warn("program '%s': failed to attach to raw tracepoint '%s': %s\n",
-			bpf_program__title(prog, false), tp_name,
-			libbpf_strerror_r(pfd, errmsg, sizeof(errmsg)));
+		pr_warn("prog '%s': failed to attach to raw tracepoint '%s': %s\n",
+			prog->name, tp_name, libbpf_strerror_r(pfd, errmsg, sizeof(errmsg)));
 		return ERR_PTR(pfd);
 	}
 	link->fd = pfd;
@@ -8856,7 +9326,7 @@ struct bpf_link *bpf_program__attach_raw_tracepoint(struct bpf_program *prog,
 static struct bpf_link *attach_raw_tp(const struct bpf_sec_def *sec,
 				      struct bpf_program *prog)
 {
-	const char *tp_name = bpf_program__title(prog, false) + sec->len;
+	const char *tp_name = prog->sec_name + sec->len;
 
 	return bpf_program__attach_raw_tracepoint(prog, tp_name);
 }
@@ -8870,8 +9340,7 @@ static struct bpf_link *bpf_program__attach_btf_id(struct bpf_program *prog)
 
 	prog_fd = bpf_program__fd(prog);
 	if (prog_fd < 0) {
-		pr_warn("program '%s': can't attach before loaded\n",
-			bpf_program__title(prog, false));
+		pr_warn("prog '%s': can't attach before loaded\n", prog->name);
 		return ERR_PTR(-EINVAL);
 	}
 
@@ -8884,9 +9353,8 @@ static struct bpf_link *bpf_program__attach_btf_id(struct bpf_program *prog)
 	if (pfd < 0) {
 		pfd = -errno;
 		free(link);
-		pr_warn("program '%s': failed to attach: %s\n",
-			bpf_program__title(prog, false),
-			libbpf_strerror_r(pfd, errmsg, sizeof(errmsg)));
+		pr_warn("prog '%s': failed to attach: %s\n",
+			prog->name, libbpf_strerror_r(pfd, errmsg, sizeof(errmsg)));
 		return ERR_PTR(pfd);
 	}
 	link->fd = pfd;
@@ -8922,9 +9390,11 @@ static struct bpf_link *attach_iter(const struct bpf_sec_def *sec,
 }
 
 static struct bpf_link *
-bpf_program__attach_fd(struct bpf_program *prog, int target_fd,
+bpf_program__attach_fd(struct bpf_program *prog, int target_fd, int btf_id,
 		       const char *target_name)
 {
+	DECLARE_LIBBPF_OPTS(bpf_link_create_opts, opts,
+			    .target_btf_id = btf_id);
 	enum bpf_attach_type attach_type;
 	char errmsg[STRERR_BUFSIZE];
 	struct bpf_link *link;
@@ -8932,8 +9402,7 @@ bpf_program__attach_fd(struct bpf_program *prog, int target_fd,
 
 	prog_fd = bpf_program__fd(prog);
 	if (prog_fd < 0) {
-		pr_warn("program '%s': can't attach before loaded\n",
-			bpf_program__title(prog, false));
+		pr_warn("prog '%s': can't attach before loaded\n", prog->name);
 		return ERR_PTR(-EINVAL);
 	}
 
@@ -8943,12 +9412,12 @@ bpf_program__attach_fd(struct bpf_program *prog, int target_fd,
 	link->detach = &bpf_link__detach_fd;
 
 	attach_type = bpf_program__get_expected_attach_type(prog);
-	link_fd = bpf_link_create(prog_fd, target_fd, attach_type, NULL);
+	link_fd = bpf_link_create(prog_fd, target_fd, attach_type, &opts);
 	if (link_fd < 0) {
 		link_fd = -errno;
 		free(link);
-		pr_warn("program '%s': failed to attach to %s: %s\n",
-			bpf_program__title(prog, false), target_name,
+		pr_warn("prog '%s': failed to attach to %s: %s\n",
+			prog->name, target_name,
 			libbpf_strerror_r(link_fd, errmsg, sizeof(errmsg)));
 		return ERR_PTR(link_fd);
 	}
@@ -8959,19 +9428,51 @@ bpf_program__attach_fd(struct bpf_program *prog, int target_fd,
 struct bpf_link *
 bpf_program__attach_cgroup(struct bpf_program *prog, int cgroup_fd)
 {
-	return bpf_program__attach_fd(prog, cgroup_fd, "cgroup");
+	return bpf_program__attach_fd(prog, cgroup_fd, 0, "cgroup");
 }
 
 struct bpf_link *
 bpf_program__attach_netns(struct bpf_program *prog, int netns_fd)
 {
-	return bpf_program__attach_fd(prog, netns_fd, "netns");
+	return bpf_program__attach_fd(prog, netns_fd, 0, "netns");
 }
 
 struct bpf_link *bpf_program__attach_xdp(struct bpf_program *prog, int ifindex)
 {
 	/* target_fd/target_ifindex use the same field in LINK_CREATE */
-	return bpf_program__attach_fd(prog, ifindex, "xdp");
+	return bpf_program__attach_fd(prog, ifindex, 0, "xdp");
+}
+
+struct bpf_link *bpf_program__attach_freplace(struct bpf_program *prog,
+					      int target_fd,
+					      const char *attach_func_name)
+{
+	int btf_id;
+
+	if (!!target_fd != !!attach_func_name) {
+		pr_warn("prog '%s': supply none or both of target_fd and attach_func_name\n",
+			prog->name);
+		return ERR_PTR(-EINVAL);
+	}
+
+	if (prog->type != BPF_PROG_TYPE_EXT) {
+		pr_warn("prog '%s': only BPF_PROG_TYPE_EXT can attach as freplace",
+			prog->name);
+		return ERR_PTR(-EINVAL);
+	}
+
+	if (target_fd) {
+		btf_id = libbpf_find_prog_btf_id(attach_func_name, target_fd);
+		if (btf_id < 0)
+			return ERR_PTR(btf_id);
+
+		return bpf_program__attach_fd(prog, target_fd, btf_id, "freplace");
+	} else {
+		/* no target, so use raw_tracepoint_open for compatibility
+		 * with old kernels
+		 */
+		return bpf_program__attach_trace(prog);
+	}
 }
 
 struct bpf_link *
@@ -8992,8 +9493,7 @@ bpf_program__attach_iter(struct bpf_program *prog,
 
 	prog_fd = bpf_program__fd(prog);
 	if (prog_fd < 0) {
-		pr_warn("program '%s': can't attach before loaded\n",
-			bpf_program__title(prog, false));
+		pr_warn("prog '%s': can't attach before loaded\n", prog->name);
 		return ERR_PTR(-EINVAL);
 	}
 
@@ -9007,9 +9507,8 @@ bpf_program__attach_iter(struct bpf_program *prog,
 	if (link_fd < 0) {
 		link_fd = -errno;
 		free(link);
-		pr_warn("program '%s': failed to attach to iterator: %s\n",
-			bpf_program__title(prog, false),
-			libbpf_strerror_r(link_fd, errmsg, sizeof(errmsg)));
+		pr_warn("prog '%s': failed to attach to iterator: %s\n",
+			prog->name, libbpf_strerror_r(link_fd, errmsg, sizeof(errmsg)));
 		return ERR_PTR(link_fd);
 	}
 	link->fd = link_fd;
@@ -9020,7 +9519,7 @@ struct bpf_link *bpf_program__attach(struct bpf_program *prog)
 {
 	const struct bpf_sec_def *sec_def;
 
-	sec_def = find_sec_def(bpf_program__title(prog, false));
+	sec_def = find_sec_def(prog->sec_name);
 	if (!sec_def || !sec_def->attach_fn)
 		return ERR_PTR(-ESRCH);
 
@@ -10090,12 +10589,11 @@ int bpf_object__attach_skeleton(struct bpf_object_skeleton *s)
 		struct bpf_program *prog = *s->progs[i].prog;
 		struct bpf_link **link = s->progs[i].link;
 		const struct bpf_sec_def *sec_def;
-		const char *sec_name = bpf_program__title(prog, false);
 
 		if (!prog->load)
 			continue;
 
-		sec_def = find_sec_def(sec_name);
+		sec_def = find_sec_def(prog->sec_name);
 		if (!sec_def || !sec_def->attach_fn)
 			continue;
 
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 308e0ded8f14..6909ee81113a 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -198,8 +198,9 @@ LIBBPF_API void bpf_program__set_ifindex(struct bpf_program *prog,
 					 __u32 ifindex);
 
 LIBBPF_API const char *bpf_program__name(const struct bpf_program *prog);
-LIBBPF_API const char *bpf_program__title(const struct bpf_program *prog,
-					  bool needs_copy);
+LIBBPF_API const char *bpf_program__section_name(const struct bpf_program *prog);
+LIBBPF_API LIBBPF_DEPRECATED("BPF program title is confusing term; please use bpf_program__section_name() instead")
+const char *bpf_program__title(const struct bpf_program *prog, bool needs_copy);
 LIBBPF_API bool bpf_program__autoload(const struct bpf_program *prog);
 LIBBPF_API int bpf_program__set_autoload(struct bpf_program *prog, bool autoload);
 
@@ -260,6 +261,9 @@ LIBBPF_API struct bpf_link *
 bpf_program__attach_netns(struct bpf_program *prog, int netns_fd);
 LIBBPF_API struct bpf_link *
 bpf_program__attach_xdp(struct bpf_program *prog, int ifindex);
+LIBBPF_API struct bpf_link *
+bpf_program__attach_freplace(struct bpf_program *prog,
+			     int target_fd, const char *attach_func_name);
 
 struct bpf_map;
 
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index 3fedcdc4ae2f..4ebfadf45b47 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -302,6 +302,35 @@ LIBBPF_0.1.0 {
 
 LIBBPF_0.2.0 {
 	global:
+		bpf_prog_bind_map;
+		bpf_prog_test_run_opts;
+		bpf_program__attach_freplace;
+		bpf_program__section_name;
+		btf__add_array;
+		btf__add_const;
+		btf__add_enum;
+		btf__add_enum_value;
+		btf__add_datasec;
+		btf__add_datasec_var_info;
+		btf__add_field;
+		btf__add_func;
+		btf__add_func_param;
+		btf__add_func_proto;
+		btf__add_fwd;
+		btf__add_int;
+		btf__add_ptr;
+		btf__add_restrict;
+		btf__add_str;
+		btf__add_struct;
+		btf__add_typedef;
+		btf__add_union;
+		btf__add_var;
+		btf__add_volatile;
+		btf__endianness;
+		btf__find_str;
+		btf__new_empty;
+		btf__set_endianness;
+		btf__str_by_offset;
 		perf_buffer__buffer_cnt;
 		perf_buffer__buffer_fd;
 		perf_buffer__epoll_fd;
diff --git a/tools/lib/bpf/libbpf_common.h b/tools/lib/bpf/libbpf_common.h
index a23ae1ac27eb..947d8bd8a7bb 100644
--- a/tools/lib/bpf/libbpf_common.h
+++ b/tools/lib/bpf/libbpf_common.h
@@ -15,6 +15,8 @@
 #define LIBBPF_API __attribute__((visibility("default")))
 #endif
 
+#define LIBBPF_DEPRECATED(msg) __attribute__((deprecated(msg)))
+
 /* Helper macro to declare and initialize libbpf options struct
  *
  * This dance with uninitialized declaration, followed by memset to zero,
diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index 4d1c366fca2c..d99bc847bf84 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -105,6 +105,10 @@ static inline void *libbpf_reallocarray(void *ptr, size_t nmemb, size_t size)
 	return realloc(ptr, total);
 }
 
+void *btf_add_mem(void **data, size_t *cap_cnt, size_t elem_sz,
+		  size_t cur_cnt, size_t max_cnt, size_t add_cnt);
+int btf_ensure_mem(void **data, size_t *cap_cnt, size_t elem_sz, size_t need_cnt);
+
 static inline bool libbpf_validate_opts(const char *opts,
 					size_t opts_sz, size_t user_sz,
 					const char *type_name)
@@ -136,6 +140,11 @@ static inline bool libbpf_validate_opts(const char *opts,
 	((opts) && opts->sz >= offsetofend(typeof(*(opts)), field))
 #define OPTS_GET(opts, field, fallback_value) \
 	(OPTS_HAS(opts, field) ? (opts)->field : fallback_value)
+#define OPTS_SET(opts, field, value)		\
+	do {					\
+		if (OPTS_HAS(opts, field))	\
+			(opts)->field = value;	\
+	} while (0)
 
 int parse_cpu_mask_str(const char *s, bool **mask, int *mask_sz);
 int parse_cpu_mask_file(const char *fcpu, bool **mask, int *mask_sz);
diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c
index 49c324594792..30b4ca5d2ac7 100644
--- a/tools/lib/bpf/xsk.c
+++ b/tools/lib/bpf/xsk.c
@@ -20,6 +20,7 @@
 #include <linux/if_ether.h>
 #include <linux/if_packet.h>
 #include <linux/if_xdp.h>
+#include <linux/kernel.h>
 #include <linux/list.h>
 #include <linux/sockios.h>
 #include <net/if.h>
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index e034a8f24f46..90a66891441a 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -619,7 +619,7 @@ static int add_jump_destinations(struct objtool_file *file)
 		if (!is_static_jump(insn))
 			continue;
 
-		if (insn->ignore || insn->offset == FAKE_JUMP_OFFSET)
+		if (insn->offset == FAKE_JUMP_OFFSET)
 			continue;
 
 		reloc = find_reloc_by_dest_range(file->elf, insn->sec,
diff --git a/tools/perf/bench/sched-messaging.c b/tools/perf/bench/sched-messaging.c
index 71d830d7b923..cecce93ccc63 100644
--- a/tools/perf/bench/sched-messaging.c
+++ b/tools/perf/bench/sched-messaging.c
@@ -66,11 +66,10 @@ static void fdpair(int fds[2])
 /* Block until we're ready to go */
 static void ready(int ready_out, int wakefd)
 {
-	char dummy;
 	struct pollfd pollfd = { .fd = wakefd, .events = POLLIN };
 
 	/* Tell them we're ready. */
-	if (write(ready_out, &dummy, 1) != 1)
+	if (write(ready_out, "R", 1) != 1)
 		err(EXIT_FAILURE, "CLIENT: ready write");
 
 	/* Wait for "GO" signal */
@@ -85,6 +84,7 @@ static void *sender(struct sender_context *ctx)
 	unsigned int i, j;
 
 	ready(ctx->ready_out, ctx->wakefd);
+	memset(data, 'S', sizeof(data));
 
 	/* Now pump to every receiver. */
 	for (i = 0; i < nr_loops; i++) {
diff --git a/tools/perf/pmu-events/arch/x86/amdzen1/core.json b/tools/perf/pmu-events/arch/x86/amdzen1/core.json
index 7e1aa8273935..653b11b23399 100644
--- a/tools/perf/pmu-events/arch/x86/amdzen1/core.json
+++ b/tools/perf/pmu-events/arch/x86/amdzen1/core.json
@@ -61,7 +61,7 @@
   {
     "EventName": "ex_ret_brn_ind_misp",
     "EventCode": "0xca",
-    "BriefDescription": "Retired Indirect Branch Instructions Mispredicted.",
+    "BriefDescription": "Retired Indirect Branch Instructions Mispredicted."
   },
   {
     "EventName": "ex_ret_mmx_fp_instr.sse_instr",
diff --git a/tools/perf/pmu-events/arch/x86/amdzen2/core.json b/tools/perf/pmu-events/arch/x86/amdzen2/core.json
index de89e5a44ff1..4b75183da94a 100644
--- a/tools/perf/pmu-events/arch/x86/amdzen2/core.json
+++ b/tools/perf/pmu-events/arch/x86/amdzen2/core.json
@@ -125,6 +125,6 @@
   {
     "EventName": "ex_ret_fus_brnch_inst",
     "EventCode": "0x1d0",
-    "BriefDescription": "Retired Fused Instructions. The number of fuse-branch instructions retired per cycle. The number of events logged per cycle can vary from 0-8.",
+    "BriefDescription": "Retired Fused Instructions. The number of fuse-branch instructions retired per cycle. The number of events logged per cycle can vary from 0-8."
   }
 ]
diff --git a/tools/perf/tests/attr/README b/tools/perf/tests/attr/README
index 6cd408108595..a36f49fb4dbe 100644
--- a/tools/perf/tests/attr/README
+++ b/tools/perf/tests/attr/README
@@ -49,6 +49,7 @@ Following tests are defined (with perf commands):
   perf record --call-graph fp kill              (test-record-graph-fp)
   perf record --group -e cycles,instructions kill (test-record-group)
   perf record -e '{cycles,instructions}' kill   (test-record-group1)
+  perf record -e '{cycles/period=1/,instructions/period=2/}:S' kill (test-record-group2)
   perf record -D kill                           (test-record-no-delay)
   perf record -i kill                           (test-record-no-inherit)
   perf record -n kill                           (test-record-no-samples)
diff --git a/tools/perf/tests/attr/test-record-group2 b/tools/perf/tests/attr/test-record-group2
new file mode 100644
index 000000000000..6b9f8d182ce1
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-group2
@@ -0,0 +1,29 @@
+[config]
+command = record
+args    = --no-bpf-event -e '{cycles/period=1234000/,instructions/period=6789000/}:S' kill >/dev/null 2>&1
+ret     = 1
+
+[event-1:base-record]
+fd=1
+group_fd=-1
+config=0|1
+sample_period=1234000
+sample_type=87
+read_format=12
+inherit=0
+freq=0
+
+[event-2:base-record]
+fd=2
+group_fd=1
+config=0|1
+sample_period=6789000
+sample_type=87
+read_format=12
+disabled=0
+inherit=0
+mmap=0
+comm=0
+freq=0
+enable_on_exec=0
+task=0
diff --git a/tools/perf/tests/bp_signal.c b/tools/perf/tests/bp_signal.c
index da8ec1e8e064..cc9fbcedb364 100644
--- a/tools/perf/tests/bp_signal.c
+++ b/tools/perf/tests/bp_signal.c
@@ -45,10 +45,13 @@ volatile long the_var;
 #if defined (__x86_64__)
 extern void __test_function(volatile long *ptr);
 asm (
+	".pushsection .text;"
 	".globl __test_function\n"
+	".type __test_function, @function;"
 	"__test_function:\n"
 	"incq (%rdi)\n"
-	"ret\n");
+	"ret\n"
+	".popsection\n");
 #else
 static void __test_function(volatile long *ptr)
 {
diff --git a/tools/perf/tests/parse-metric.c b/tools/perf/tests/parse-metric.c
index 23db8acc492d..cd7331aac3bd 100644
--- a/tools/perf/tests/parse-metric.c
+++ b/tools/perf/tests/parse-metric.c
@@ -153,8 +153,10 @@ static int __compute_metric(const char *name, struct value *vals,
 		return -ENOMEM;
 
 	cpus = perf_cpu_map__new("0");
-	if (!cpus)
+	if (!cpus) {
+		evlist__delete(evlist);
 		return -ENOMEM;
+	}
 
 	perf_evlist__set_maps(&evlist->core, cpus, NULL);
 
@@ -163,10 +165,11 @@ static int __compute_metric(const char *name, struct value *vals,
 					     false, false,
 					     &metric_events);
 	if (err)
-		return err;
+		goto out;
 
-	if (perf_evlist__alloc_stats(evlist, false))
-		return -1;
+	err = perf_evlist__alloc_stats(evlist, false);
+	if (err)
+		goto out;
 
 	/* Load the runtime stats with given numbers for events. */
 	runtime_stat__init(&st);
@@ -178,13 +181,14 @@ static int __compute_metric(const char *name, struct value *vals,
 	if (name2 && ratio2)
 		*ratio2 = compute_single(&metric_events, evlist, &st, name2);
 
+out:
 	/* ... clenup. */
 	metricgroup__rblist_exit(&metric_events);
 	runtime_stat__exit(&st);
 	perf_evlist__free_stats(evlist);
 	perf_cpu_map__put(cpus);
 	evlist__delete(evlist);
-	return 0;
+	return err;
 }
 
 static int compute_metric(const char *name, struct value *vals, double *ratio)
diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c
index eb19f9a0bc15..d3517a74d95e 100644
--- a/tools/perf/tests/pmu-events.c
+++ b/tools/perf/tests/pmu-events.c
@@ -274,6 +274,7 @@ static int __test__pmu_event_aliases(char *pmu_name, int *count)
 	int res = 0;
 	bool use_uncore_table;
 	struct pmu_events_map *map = __test_pmu_get_events_map();
+	struct perf_pmu_alias *a, *tmp;
 
 	if (!map)
 		return -1;
@@ -347,6 +348,10 @@ static int __test__pmu_event_aliases(char *pmu_name, int *count)
 			  pmu_name, alias->name);
 	}
 
+	list_for_each_entry_safe(a, tmp, &aliases, list) {
+		list_del(&a->list);
+		perf_pmu_free_alias(a);
+	}
 	free(pmu);
 	return res;
 }
diff --git a/tools/perf/tests/pmu.c b/tools/perf/tests/pmu.c
index 5c11fe2b3040..714e6830a758 100644
--- a/tools/perf/tests/pmu.c
+++ b/tools/perf/tests/pmu.c
@@ -173,6 +173,7 @@ int test__pmu(struct test *test __maybe_unused, int subtest __maybe_unused)
 		ret = 0;
 	} while (0);
 
+	perf_pmu__del_formats(&formats);
 	test_format_dir_put(format);
 	return ret;
 }
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index 2feb751516ab..0374adcb223c 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -328,12 +328,6 @@ config_bpf_program(struct bpf_program *prog)
 	probe_conf.no_inlines = false;
 	probe_conf.force_add = false;
 
-	config_str = bpf_program__title(prog, false);
-	if (IS_ERR(config_str)) {
-		pr_debug("bpf: unable to get title for program\n");
-		return PTR_ERR(config_str);
-	}
-
 	priv = calloc(sizeof(*priv), 1);
 	if (!priv) {
 		pr_debug("bpf: failed to alloc priv\n");
@@ -341,6 +335,7 @@ config_bpf_program(struct bpf_program *prog)
 	}
 	pev = &priv->pev;
 
+	config_str = bpf_program__section_name(prog);
 	pr_debug("bpf: config program '%s'\n", config_str);
 	err = parse_prog_config(config_str, &main_str, &is_tp, pev);
 	if (err)
@@ -454,10 +449,7 @@ preproc_gen_prologue(struct bpf_program *prog, int n,
 	if (err) {
 		const char *title;
 
-		title = bpf_program__title(prog, false);
-		if (!title)
-			title = "[unknown]";
-
+		title = bpf_program__section_name(prog);
 		pr_debug("Failed to generate prologue for program %s\n",
 			 title);
 		return err;
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index e3fa3bf7498a..c0768c61eb43 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -946,6 +946,10 @@ int perf_evlist__create_maps(struct evlist *evlist, struct target *target)
 
 	perf_evlist__set_maps(&evlist->core, cpus, threads);
 
+	/* as evlist now has references, put count here */
+	perf_cpu_map__put(cpus);
+	perf_thread_map__put(threads);
+
 	return 0;
 
 out_delete_threads:
@@ -1273,11 +1277,12 @@ static int perf_evlist__create_syswide_maps(struct evlist *evlist)
 		goto out_put;
 
 	perf_evlist__set_maps(&evlist->core, cpus, threads);
-out:
-	return err;
+
+	perf_thread_map__put(threads);
 out_put:
 	perf_cpu_map__put(cpus);
-	goto out;
+out:
+	return err;
 }
 
 int evlist__open(struct evlist *evlist)
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index fd865002cbbd..459b51e90063 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -976,16 +976,20 @@ void evsel__config(struct evsel *evsel, struct record_opts *opts,
 	 * We default some events to have a default interval. But keep
 	 * it a weak assumption overridable by the user.
 	 */
-	if (!attr->sample_period || (opts->user_freq != UINT_MAX ||
-				     opts->user_interval != ULLONG_MAX)) {
+	if (!attr->sample_period) {
 		if (opts->freq) {
-			evsel__set_sample_bit(evsel, PERIOD);
 			attr->freq		= 1;
 			attr->sample_freq	= opts->freq;
 		} else {
 			attr->sample_period = opts->default_interval;
 		}
 	}
+	/*
+	 * If attr->freq was set (here or earlier), ask for period
+	 * to be sampled.
+	 */
+	if (attr->freq)
+		evsel__set_sample_bit(evsel, PERIOD);
 
 	if (opts->no_samples)
 		attr->sample_freq = 0;
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index 8831b964288f..ab5030fcfed4 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -85,6 +85,7 @@ static void metric_event_delete(struct rblist *rblist __maybe_unused,
 
 	list_for_each_entry_safe(expr, tmp, &me->head, nd) {
 		free(expr->metric_refs);
+		free(expr->metric_events);
 		free(expr);
 	}
 
@@ -316,6 +317,7 @@ static int metricgroup__setup_events(struct list_head *groups,
 			if (!metric_refs) {
 				ret = -ENOMEM;
 				free(metric_events);
+				free(expr);
 				break;
 			}
 
@@ -530,6 +532,9 @@ void metricgroup__print(bool metrics, bool metricgroups, char *filter,
 						continue;
 					strlist__add(me->metrics, s);
 				}
+
+				if (!raw)
+					free(s);
 			}
 			free(omg);
 		}
@@ -667,7 +672,6 @@ static int __add_metric(struct list_head *metric_list,
 		m->has_constraint = metric_no_group || metricgroup__has_constraint(pe);
 		INIT_LIST_HEAD(&m->metric_refs);
 		m->metric_refs_cnt = 0;
-		*mp = m;
 
 		parent = expr_ids__alloc(ids);
 		if (!parent) {
@@ -680,6 +684,7 @@ static int __add_metric(struct list_head *metric_list,
 			free(m);
 			return -ENOMEM;
 		}
+		*mp = m;
 	} else {
 		/*
 		 * We got here for the referenced metric, via the
@@ -714,8 +719,11 @@ static int __add_metric(struct list_head *metric_list,
 	 * all the metric's IDs and add it to the parent context.
 	 */
 	if (expr__find_other(pe->metric_expr, NULL, &m->pctx, runtime) < 0) {
-		expr__ctx_clear(&m->pctx);
-		free(m);
+		if (m->metric_refs_cnt == 0) {
+			expr__ctx_clear(&m->pctx);
+			free(m);
+			*mp = NULL;
+		}
 		return -EINVAL;
 	}
 
@@ -934,7 +942,7 @@ static int metricgroup__add_metric(const char *metric, bool metric_no_group,
 
 		ret = add_metric(&list, pe, metric_no_group, &m, NULL, &ids);
 		if (ret)
-			return ret;
+			goto out;
 
 		/*
 		 * Process any possible referenced metrics
@@ -943,12 +951,14 @@ static int metricgroup__add_metric(const char *metric, bool metric_no_group,
 		ret = resolve_metric(metric_no_group,
 				     &list, map, &ids);
 		if (ret)
-			return ret;
+			goto out;
 	}
 
 	/* End of pmu events. */
-	if (!has_match)
-		return -EINVAL;
+	if (!has_match) {
+		ret = -EINVAL;
+		goto out;
+	}
 
 	list_for_each_entry(m, &list, nd) {
 		if (events->len > 0)
@@ -963,9 +973,14 @@ static int metricgroup__add_metric(const char *metric, bool metric_no_group,
 		}
 	}
 
+out:
+	/*
+	 * add to metric_list so that they can be released
+	 * even if it's failed
+	 */
 	list_splice(&list, metric_list);
 	expr_ids__exit(&ids);
-	return 0;
+	return ret;
 }
 
 static int metricgroup__add_metric_list(const char *list, bool metric_no_group,
@@ -1040,7 +1055,7 @@ static int parse_groups(struct evlist *perf_evlist, const char *str,
 	ret = metricgroup__add_metric_list(str, metric_no_group,
 					   &extra_events, &metric_list, map);
 	if (ret)
-		return ret;
+		goto out;
 	pr_debug("adding %s\n", extra_events.buf);
 	bzero(&parse_error, sizeof(parse_error));
 	ret = __parse_events(perf_evlist, extra_events.buf, &parse_error, fake_pmu);
@@ -1048,11 +1063,11 @@ static int parse_groups(struct evlist *perf_evlist, const char *str,
 		parse_events_print_error(&parse_error, extra_events.buf);
 		goto out;
 	}
-	strbuf_release(&extra_events);
 	ret = metricgroup__setup_events(&metric_list, metric_no_merge,
 					perf_evlist, metric_events);
 out:
 	metricgroup__free_metrics(&metric_list);
+	strbuf_release(&extra_events);
 	return ret;
 }
 
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index c4d2394e2b2d..667cbca1547a 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -411,7 +411,7 @@ static int add_event_tool(struct list_head *list, int *idx,
 		return -ENOMEM;
 	evsel->tool_event = tool_event;
 	if (tool_event == PERF_TOOL_DURATION_TIME)
-		evsel->unit = strdup("ns");
+		evsel->unit = "ns";
 	return 0;
 }
 
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index f1688e1f6ed7..d41caeb35cf6 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -274,7 +274,7 @@ static void perf_pmu_update_alias(struct perf_pmu_alias *old,
 }
 
 /* Delete an alias entry. */
-static void perf_pmu_free_alias(struct perf_pmu_alias *newalias)
+void perf_pmu_free_alias(struct perf_pmu_alias *newalias)
 {
 	zfree(&newalias->name);
 	zfree(&newalias->desc);
@@ -1354,6 +1354,17 @@ void perf_pmu__set_format(unsigned long *bits, long from, long to)
 		set_bit(b, bits);
 }
 
+void perf_pmu__del_formats(struct list_head *formats)
+{
+	struct perf_pmu_format *fmt, *tmp;
+
+	list_for_each_entry_safe(fmt, tmp, formats, list) {
+		list_del(&fmt->list);
+		free(fmt->name);
+		free(fmt);
+	}
+}
+
 static int sub_non_neg(int a, int b)
 {
 	if (b > a)
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 44ccbdbb1c37..a64e9c9ce731 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -94,6 +94,7 @@ int perf_pmu__new_format(struct list_head *list, char *name,
 			 int config, unsigned long *bits);
 void perf_pmu__set_format(unsigned long *bits, long from, long to);
 int perf_pmu__format_parse(char *dir, struct list_head *head);
+void perf_pmu__del_formats(struct list_head *formats);
 
 struct perf_pmu *perf_pmu__scan(struct perf_pmu *pmu);
 
@@ -113,6 +114,7 @@ void pmu_add_cpu_aliases_map(struct list_head *head, struct perf_pmu *pmu,
 
 struct pmu_events_map *perf_pmu__find_map(struct perf_pmu *pmu);
 bool pmu_uncore_alias_match(const char *pmu_name, const char *name);
+void perf_pmu_free_alias(struct perf_pmu_alias *alias);
 
 int perf_pmu__convert_scale(const char *scale, char **end, double *sval);
 
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index a4cc11592f6b..ea9aa1d7cf50 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -2,6 +2,7 @@
 #include "debug.h"
 #include "evlist.h"
 #include "evsel.h"
+#include "evsel_config.h"
 #include "parse-events.h"
 #include <errno.h>
 #include <limits.h>
@@ -33,11 +34,24 @@ static struct evsel *evsel__read_sampler(struct evsel *evsel, struct evlist *evl
 	return leader;
 }
 
+static u64 evsel__config_term_mask(struct evsel *evsel)
+{
+	struct evsel_config_term *term;
+	struct list_head *config_terms = &evsel->config_terms;
+	u64 term_types = 0;
+
+	list_for_each_entry(term, config_terms, list) {
+		term_types |= 1 << term->type;
+	}
+	return term_types;
+}
+
 static void evsel__config_leader_sampling(struct evsel *evsel, struct evlist *evlist)
 {
 	struct perf_event_attr *attr = &evsel->core.attr;
 	struct evsel *leader = evsel->leader;
 	struct evsel *read_sampler;
+	u64 term_types, freq_mask;
 
 	if (!leader->sample_read)
 		return;
@@ -47,16 +61,20 @@ static void evsel__config_leader_sampling(struct evsel *evsel, struct evlist *ev
 	if (evsel == read_sampler)
 		return;
 
+	term_types = evsel__config_term_mask(evsel);
 	/*
-	 * Disable sampling for all group members other than the leader in
-	 * case the leader 'leads' the sampling, except when the leader is an
-	 * AUX area event, in which case the 2nd event in the group is the one
-	 * that 'leads' the sampling.
+	 * Disable sampling for all group members except those with explicit
+	 * config terms or the leader. In the case of an AUX area event, the 2nd
+	 * event in the group is the one that 'leads' the sampling.
 	 */
-	attr->freq           = 0;
-	attr->sample_freq    = 0;
-	attr->sample_period  = 0;
-	attr->write_backward = 0;
+	freq_mask = (1 << EVSEL__CONFIG_TERM_FREQ) | (1 << EVSEL__CONFIG_TERM_PERIOD);
+	if ((term_types & freq_mask) == 0) {
+		attr->freq           = 0;
+		attr->sample_freq    = 0;
+		attr->sample_period  = 0;
+	}
+	if ((term_types & (1 << EVSEL__CONFIG_TERM_OVERWRITE)) == 0)
+		attr->write_backward = 0;
 
 	/*
 	 * We don't get a sample for slave events, we make them when delivering
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index e1ba6c1b916a..924b54d15d54 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -517,7 +517,7 @@ static void print_l1_dcache_misses(struct perf_stat_config *config,
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
 
-	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all L1-dcache hits", ratio);
+	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all L1-dcache accesses", ratio);
 }
 
 static void print_l1_icache_misses(struct perf_stat_config *config,
@@ -538,7 +538,7 @@ static void print_l1_icache_misses(struct perf_stat_config *config,
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all L1-icache hits", ratio);
+	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all L1-icache accesses", ratio);
 }
 
 static void print_dtlb_cache_misses(struct perf_stat_config *config,
@@ -558,7 +558,7 @@ static void print_dtlb_cache_misses(struct perf_stat_config *config,
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all dTLB cache hits", ratio);
+	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all dTLB cache accesses", ratio);
 }
 
 static void print_itlb_cache_misses(struct perf_stat_config *config,
@@ -578,7 +578,7 @@ static void print_itlb_cache_misses(struct perf_stat_config *config,
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all iTLB cache hits", ratio);
+	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all iTLB cache accesses", ratio);
 }
 
 static void print_ll_cache_misses(struct perf_stat_config *config,
@@ -598,7 +598,7 @@ static void print_ll_cache_misses(struct perf_stat_config *config,
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all LL-cache hits", ratio);
+	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all LL-cache accesses", ratio);
 }
 
 /*
@@ -853,14 +853,16 @@ static void generic_metric(struct perf_stat_config *config,
 double test_generic_metric(struct metric_expr *mexp, int cpu, struct runtime_stat *st)
 {
 	struct expr_parse_ctx pctx;
-	double ratio;
+	double ratio = 0.0;
 
 	if (prepare_metric(mexp->metric_events, mexp->metric_refs, &pctx, cpu, st) < 0)
-		return 0.;
+		goto out;
 
 	if (expr__parse(&ratio, &pctx, mexp->metric_expr, 1))
-		return 0.;
+		ratio = 0.0;
 
+out:
+	expr__ctx_clear(&pctx);
 	return ratio;
 }
 
@@ -918,7 +920,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 		if (runtime_stat_n(st, STAT_L1_DCACHE, ctx, cpu) != 0)
 			print_l1_dcache_misses(config, cpu, evsel, avg, out, st);
 		else
-			print_metric(config, ctxp, NULL, NULL, "of all L1-dcache hits", 0);
+			print_metric(config, ctxp, NULL, NULL, "of all L1-dcache accesses", 0);
 	} else if (
 		evsel->core.attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->core.attr.config ==  ( PERF_COUNT_HW_CACHE_L1I |
@@ -928,7 +930,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 		if (runtime_stat_n(st, STAT_L1_ICACHE, ctx, cpu) != 0)
 			print_l1_icache_misses(config, cpu, evsel, avg, out, st);
 		else
-			print_metric(config, ctxp, NULL, NULL, "of all L1-icache hits", 0);
+			print_metric(config, ctxp, NULL, NULL, "of all L1-icache accesses", 0);
 	} else if (
 		evsel->core.attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->core.attr.config ==  ( PERF_COUNT_HW_CACHE_DTLB |
@@ -938,7 +940,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 		if (runtime_stat_n(st, STAT_DTLB_CACHE, ctx, cpu) != 0)
 			print_dtlb_cache_misses(config, cpu, evsel, avg, out, st);
 		else
-			print_metric(config, ctxp, NULL, NULL, "of all dTLB cache hits", 0);
+			print_metric(config, ctxp, NULL, NULL, "of all dTLB cache accesses", 0);
 	} else if (
 		evsel->core.attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->core.attr.config ==  ( PERF_COUNT_HW_CACHE_ITLB |
@@ -948,7 +950,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 		if (runtime_stat_n(st, STAT_ITLB_CACHE, ctx, cpu) != 0)
 			print_itlb_cache_misses(config, cpu, evsel, avg, out, st);
 		else
-			print_metric(config, ctxp, NULL, NULL, "of all iTLB cache hits", 0);
+			print_metric(config, ctxp, NULL, NULL, "of all iTLB cache accesses", 0);
 	} else if (
 		evsel->core.attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->core.attr.config ==  ( PERF_COUNT_HW_CACHE_LL |
@@ -958,7 +960,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 		if (runtime_stat_n(st, STAT_LL_CACHE, ctx, cpu) != 0)
 			print_ll_cache_misses(config, cpu, evsel, avg, out, st);
 		else
-			print_metric(config, ctxp, NULL, NULL, "of all LL-cache hits", 0);
+			print_metric(config, ctxp, NULL, NULL, "of all LL-cache accesses", 0);
 	} else if (evsel__match(evsel, HARDWARE, HW_CACHE_MISSES)) {
 		total = runtime_stat_avg(st, STAT_CACHEREFS, ctx, cpu);
 
diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index 9a0946ddb705..3ab1200e172f 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -13,9 +13,7 @@ test_verifier_log
 feature
 test_sock
 test_sock_addr
-test_sock_fields
 urandom_read
-test_btf
 test_sockmap
 test_lirc_mode2_user
 get_cgroup_id_user
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 65d3d9aaeb31..bdbeafec371b 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -33,9 +33,9 @@ LDLIBS += -lcap -lelf -lz -lrt -lpthread
 # Order correspond to 'make run_tests' order
 TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \
 	test_verifier_log test_dev_cgroup test_tcpbpf_user \
-	test_sock test_btf test_sockmap get_cgroup_id_user test_socket_cookie \
+	test_sock test_sockmap get_cgroup_id_user test_socket_cookie \
 	test_cgroup_storage \
-	test_netcnt test_tcpnotify_user test_sock_fields test_sysctl \
+	test_netcnt test_tcpnotify_user test_sysctl \
 	test_progs-no_alu32 \
 	test_current_pid_tgid_new_ns
 
@@ -68,7 +68,8 @@ TEST_PROGS := test_kmod.sh \
 	test_tc_edt.sh \
 	test_xdping.sh \
 	test_bpftool_build.sh \
-	test_bpftool.sh
+	test_bpftool.sh \
+	test_bpftool_metadata.sh \
 
 TEST_PROGS_EXTENDED := with_addr.sh \
 	with_tunnels.sh \
@@ -176,6 +177,11 @@ $(DEFAULT_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile)    \
 	$(Q)$(MAKE) $(submake_extras)  -C $(BPFTOOLDIR)			       \
 		    OUTPUT=$(BUILD_DIR)/bpftool/			       \
 		    prefix= DESTDIR=$(SCRATCH_DIR)/ install
+	$(Q)mkdir -p $(BUILD_DIR)/bpftool/Documentation
+	$(Q)RST2MAN_OPTS="--exit-status=1" $(MAKE) $(submake_extras)	       \
+		    -C $(BPFTOOLDIR)/Documentation			       \
+		    OUTPUT=$(BUILD_DIR)/bpftool/Documentation/		       \
+		    prefix= DESTDIR=$(SCRATCH_DIR)/ install
 
 $(BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile)		       \
 	   ../../../include/uapi/linux/bpf.h                                   \
diff --git a/tools/testing/selftests/bpf/bench.c b/tools/testing/selftests/bpf/bench.c
index 1a427685a8a8..332ed2f7b402 100644
--- a/tools/testing/selftests/bpf/bench.c
+++ b/tools/testing/selftests/bpf/bench.c
@@ -311,7 +311,6 @@ extern const struct bench bench_rename_kretprobe;
 extern const struct bench bench_rename_rawtp;
 extern const struct bench bench_rename_fentry;
 extern const struct bench bench_rename_fexit;
-extern const struct bench bench_rename_fmodret;
 extern const struct bench bench_trig_base;
 extern const struct bench bench_trig_tp;
 extern const struct bench bench_trig_rawtp;
@@ -333,7 +332,6 @@ static const struct bench *benchs[] = {
 	&bench_rename_rawtp,
 	&bench_rename_fentry,
 	&bench_rename_fexit,
-	&bench_rename_fmodret,
 	&bench_trig_base,
 	&bench_trig_tp,
 	&bench_trig_rawtp,
@@ -464,4 +462,3 @@ int main(int argc, char **argv)
 
 	return 0;
 }
-
diff --git a/tools/testing/selftests/bpf/benchs/bench_rename.c b/tools/testing/selftests/bpf/benchs/bench_rename.c
index e74cff40f4fe..a967674098ad 100644
--- a/tools/testing/selftests/bpf/benchs/bench_rename.c
+++ b/tools/testing/selftests/bpf/benchs/bench_rename.c
@@ -106,12 +106,6 @@ static void setup_fexit()
 	attach_bpf(ctx.skel->progs.prog5);
 }
 
-static void setup_fmodret()
-{
-	setup_ctx();
-	attach_bpf(ctx.skel->progs.prog6);
-}
-
 static void *consumer(void *input)
 {
 	return NULL;
@@ -182,14 +176,3 @@ const struct bench bench_rename_fexit = {
 	.report_progress = hits_drops_report_progress,
 	.report_final = hits_drops_report_final,
 };
-
-const struct bench bench_rename_fmodret = {
-	.name = "rename-fmodret",
-	.validate = validate,
-	.setup = setup_fmodret,
-	.producer_thread = producer,
-	.consumer_thread = consumer,
-	.measure = measure,
-	.report_progress = hits_drops_report_progress,
-	.report_final = hits_drops_report_final,
-};
diff --git a/tools/testing/selftests/bpf/bpf_tcp_helpers.h b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
index 5bf2fe9b1efa..2915664c335d 100644
--- a/tools/testing/selftests/bpf/bpf_tcp_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
@@ -16,6 +16,7 @@ BPF_PROG(name, args)
 
 struct sock_common {
 	unsigned char	skc_state;
+	__u16		skc_num;
 } __attribute__((preserve_access_index));
 
 enum sk_pacing {
@@ -45,6 +46,10 @@ struct inet_connection_sock {
 	__u64			  icsk_ca_priv[104 / sizeof(__u64)];
 } __attribute__((preserve_access_index));
 
+struct request_sock {
+	struct sock_common		__req_common;
+} __attribute__((preserve_access_index));
+
 struct tcp_sock {
 	struct inet_connection_sock	inet_conn;
 
@@ -115,14 +120,6 @@ enum tcp_ca_event {
 	CA_EVENT_ECN_IS_CE = 5,
 };
 
-enum tcp_ca_state {
-	TCP_CA_Open = 0,
-	TCP_CA_Disorder = 1,
-	TCP_CA_CWR = 2,
-	TCP_CA_Recovery = 3,
-	TCP_CA_Loss = 4
-};
-
 struct ack_sample {
 	__u32 pkts_acked;
 	__s32 rtt_us;
diff --git a/tools/testing/selftests/bpf/flow_dissector_load.h b/tools/testing/selftests/bpf/flow_dissector_load.h
index daeaeb518894..7290401ec172 100644
--- a/tools/testing/selftests/bpf/flow_dissector_load.h
+++ b/tools/testing/selftests/bpf/flow_dissector_load.h
@@ -23,7 +23,13 @@ static inline int bpf_flow_load(struct bpf_object **obj,
 	if (ret)
 		return ret;
 
-	main_prog = bpf_object__find_program_by_title(*obj, section_name);
+	main_prog = NULL;
+	bpf_object__for_each_program(prog, *obj) {
+		if (strcmp(section_name, bpf_program__section_name(prog)) == 0) {
+			main_prog = prog;
+			break;
+		}
+	}
 	if (!main_prog)
 		return -1;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
index 7375d9a6d242..448885b95eed 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
@@ -7,6 +7,7 @@
 #include "bpf_iter_task.skel.h"
 #include "bpf_iter_task_stack.skel.h"
 #include "bpf_iter_task_file.skel.h"
+#include "bpf_iter_task_btf.skel.h"
 #include "bpf_iter_tcp4.skel.h"
 #include "bpf_iter_tcp6.skel.h"
 #include "bpf_iter_udp4.skel.h"
@@ -132,20 +133,118 @@ static void test_task_stack(void)
 	bpf_iter_task_stack__destroy(skel);
 }
 
+static void *do_nothing(void *arg)
+{
+	pthread_exit(arg);
+}
+
 static void test_task_file(void)
 {
 	struct bpf_iter_task_file *skel;
+	pthread_t thread_id;
+	void *ret;
 
 	skel = bpf_iter_task_file__open_and_load();
 	if (CHECK(!skel, "bpf_iter_task_file__open_and_load",
 		  "skeleton open_and_load failed\n"))
 		return;
 
+	skel->bss->tgid = getpid();
+
+	if (CHECK(pthread_create(&thread_id, NULL, &do_nothing, NULL),
+		  "pthread_create", "pthread_create failed\n"))
+		goto done;
+
 	do_dummy_read(skel->progs.dump_task_file);
 
+	if (CHECK(pthread_join(thread_id, &ret) || ret != NULL,
+		  "pthread_join", "pthread_join failed\n"))
+		goto done;
+
+	CHECK(skel->bss->count != 0, "check_count",
+	      "invalid non pthread file visit count %d\n", skel->bss->count);
+
+done:
 	bpf_iter_task_file__destroy(skel);
 }
 
+#define TASKBUFSZ		32768
+
+static char taskbuf[TASKBUFSZ];
+
+static int do_btf_read(struct bpf_iter_task_btf *skel)
+{
+	struct bpf_program *prog = skel->progs.dump_task_struct;
+	struct bpf_iter_task_btf__bss *bss = skel->bss;
+	int iter_fd = -1, len = 0, bufleft = TASKBUFSZ;
+	struct bpf_link *link;
+	char *buf = taskbuf;
+	int ret = 0;
+
+	link = bpf_program__attach_iter(prog, NULL);
+	if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n"))
+		return ret;
+
+	iter_fd = bpf_iter_create(bpf_link__fd(link));
+	if (CHECK(iter_fd < 0, "create_iter", "create_iter failed\n"))
+		goto free_link;
+
+	do {
+		len = read(iter_fd, buf, bufleft);
+		if (len > 0) {
+			buf += len;
+			bufleft -= len;
+		}
+	} while (len > 0);
+
+	if (bss->skip) {
+		printf("%s:SKIP:no __builtin_btf_type_id\n", __func__);
+		ret = 1;
+		test__skip();
+		goto free_link;
+	}
+
+	if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno)))
+		goto free_link;
+
+	CHECK(strstr(taskbuf, "(struct task_struct)") == NULL,
+	      "check for btf representation of task_struct in iter data",
+	      "struct task_struct not found");
+free_link:
+	if (iter_fd > 0)
+		close(iter_fd);
+	bpf_link__destroy(link);
+	return ret;
+}
+
+static void test_task_btf(void)
+{
+	struct bpf_iter_task_btf__bss *bss;
+	struct bpf_iter_task_btf *skel;
+	int ret;
+
+	skel = bpf_iter_task_btf__open_and_load();
+	if (CHECK(!skel, "bpf_iter_task_btf__open_and_load",
+		  "skeleton open_and_load failed\n"))
+		return;
+
+	bss = skel->bss;
+
+	ret = do_btf_read(skel);
+	if (ret)
+		goto cleanup;
+
+	if (CHECK(bss->tasks == 0, "check if iterated over tasks",
+		  "no task iteration, did BPF program run?\n"))
+		goto cleanup;
+
+	CHECK(bss->seq_err != 0, "check for unexpected err",
+	      "bpf_seq_printf_btf returned %ld", bss->seq_err);
+
+cleanup:
+	bpf_iter_task_btf__destroy(skel);
+}
+
 static void test_tcp4(void)
 {
 	struct bpf_iter_tcp4 *skel;
@@ -331,7 +430,7 @@ static void test_overflow(bool test_e2big_overflow, bool ret1)
 	struct bpf_map_info map_info = {};
 	struct bpf_iter_test_kern4 *skel;
 	struct bpf_link *link;
-	__u32 page_size;
+	__u32 iter_size;
 	char *buf;
 
 	skel = bpf_iter_test_kern4__open();
@@ -353,19 +452,19 @@ static void test_overflow(bool test_e2big_overflow, bool ret1)
 		  "map_creation failed: %s\n", strerror(errno)))
 		goto free_map1;
 
-	/* bpf_seq_printf kernel buffer is one page, so one map
+	/* bpf_seq_printf kernel buffer is 8 pages, so one map
 	 * bpf_seq_write will mostly fill it, and the other map
 	 * will partially fill and then trigger overflow and need
 	 * bpf_seq_read restart.
 	 */
-	page_size = sysconf(_SC_PAGE_SIZE);
+	iter_size = sysconf(_SC_PAGE_SIZE) << 3;
 
 	if (test_e2big_overflow) {
-		skel->rodata->print_len = (page_size + 8) / 8;
-		expected_read_len = 2 * (page_size + 8);
+		skel->rodata->print_len = (iter_size + 8) / 8;
+		expected_read_len = 2 * (iter_size + 8);
 	} else if (!ret1) {
-		skel->rodata->print_len = (page_size - 8) / 8;
-		expected_read_len = 2 * (page_size - 8);
+		skel->rodata->print_len = (iter_size - 8) / 8;
+		expected_read_len = 2 * (iter_size - 8);
 	} else {
 		skel->rodata->print_len = 1;
 		expected_read_len = 2 * 8;
@@ -936,6 +1035,8 @@ void test_bpf_iter(void)
 		test_task_stack();
 	if (test__start_subtest("task_file"))
 		test_task_file();
+	if (test__start_subtest("task_btf"))
+		test_task_btf();
 	if (test__start_subtest("tcp4"))
 		test_tcp4();
 	if (test__start_subtest("tcp6"))
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c
index e9f2f12ba06b..e698ee6bb6c2 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c
@@ -49,6 +49,7 @@ void test_bpf_verif_scale(void)
 		{ "test_verif_scale3.o", BPF_PROG_TYPE_SCHED_CLS },
 
 		{ "pyperf_global.o", BPF_PROG_TYPE_RAW_TRACEPOINT },
+		{ "pyperf_subprogs.o", BPF_PROG_TYPE_RAW_TRACEPOINT },
 
 		/* full unroll by llvm */
 		{ "pyperf50.o", BPF_PROG_TYPE_RAW_TRACEPOINT },
@@ -86,6 +87,9 @@ void test_bpf_verif_scale(void)
 		{ "strobemeta_nounroll1.o", BPF_PROG_TYPE_RAW_TRACEPOINT },
 		{ "strobemeta_nounroll2.o", BPF_PROG_TYPE_RAW_TRACEPOINT },
 
+		/* non-inlined subprogs */
+		{ "strobemeta_subprogs.o", BPF_PROG_TYPE_RAW_TRACEPOINT },
+
 		{ "test_sysctl_loop1.o", BPF_PROG_TYPE_CGROUP_SYSCTL },
 		{ "test_sysctl_loop2.o", BPF_PROG_TYPE_CGROUP_SYSCTL },
 
diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/prog_tests/btf.c
index c75fc6447186..93162484c2ca 100644
--- a/tools/testing/selftests/bpf/test_btf.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf.c
@@ -24,40 +24,17 @@
 
 #include "bpf_rlimit.h"
 #include "bpf_util.h"
-#include "test_btf.h"
+#include "../test_btf.h"
+#include "test_progs.h"
 
 #define MAX_INSNS	512
 #define MAX_SUBPROGS	16
 
-static uint32_t pass_cnt;
-static uint32_t error_cnt;
-static uint32_t skip_cnt;
+static int duration = 0;
+static bool always_log;
 
-#define CHECK(condition, format...) ({					\
-	int __ret = !!(condition);					\
-	if (__ret) {							\
-		fprintf(stderr, "%s:%d:FAIL ", __func__, __LINE__);	\
-		fprintf(stderr, format);				\
-	}								\
-	__ret;								\
-})
-
-static int count_result(int err)
-{
-	if (err)
-		error_cnt++;
-	else
-		pass_cnt++;
-
-	fprintf(stderr, "\n");
-	return err;
-}
-
-static int __base_pr(enum libbpf_print_level level __attribute__((unused)),
-		     const char *format, va_list args)
-{
-	return vfprintf(stderr, format, args);
-}
+#undef CHECK
+#define CHECK(condition, format...) _CHECK(condition, "check", duration, format)
 
 #define BTF_END_RAW 0xdeadbeef
 #define NAME_TBD 0xdeadb33f
@@ -69,21 +46,6 @@ static int __base_pr(enum libbpf_print_level level __attribute__((unused)),
 #define MAX_NR_RAW_U32 1024
 #define BTF_LOG_BUF_SIZE 65535
 
-static struct args {
-	unsigned int raw_test_num;
-	unsigned int file_test_num;
-	unsigned int get_info_test_num;
-	unsigned int info_raw_test_num;
-	unsigned int dedup_test_num;
-	bool raw_test;
-	bool file_test;
-	bool get_info_test;
-	bool pprint_test;
-	bool always_log;
-	bool info_raw_test;
-	bool dedup_test;
-} args;
-
 static char btf_log_buf[BTF_LOG_BUF_SIZE];
 
 static struct btf_header hdr_tmpl = {
@@ -3664,7 +3626,7 @@ done:
 	return raw_btf;
 }
 
-static int do_test_raw(unsigned int test_num)
+static void do_test_raw(unsigned int test_num)
 {
 	struct btf_raw_test *test = &raw_tests[test_num - 1];
 	struct bpf_create_map_attr create_attr = {};
@@ -3674,15 +3636,16 @@ static int do_test_raw(unsigned int test_num)
 	void *raw_btf;
 	int err;
 
-	fprintf(stderr, "BTF raw test[%u] (%s): ", test_num, test->descr);
+	if (!test__start_subtest(test->descr))
+		return;
+
 	raw_btf = btf_raw_create(&hdr_tmpl,
 				 test->raw_types,
 				 test->str_sec,
 				 test->str_sec_size,
 				 &raw_btf_size, NULL);
-
 	if (!raw_btf)
-		return -1;
+		return;
 
 	hdr = raw_btf;
 
@@ -3694,7 +3657,7 @@ static int do_test_raw(unsigned int test_num)
 	*btf_log_buf = '\0';
 	btf_fd = bpf_load_btf(raw_btf, raw_btf_size,
 			      btf_log_buf, BTF_LOG_BUF_SIZE,
-			      args.always_log);
+			      always_log);
 	free(raw_btf);
 
 	err = ((btf_fd == -1) != test->btf_load_err);
@@ -3725,32 +3688,12 @@ static int do_test_raw(unsigned int test_num)
 	      map_fd, test->map_create_err);
 
 done:
-	if (!err)
-		fprintf(stderr, "OK");
-
-	if (*btf_log_buf && (err || args.always_log))
+	if (*btf_log_buf && (err || always_log))
 		fprintf(stderr, "\n%s", btf_log_buf);
-
 	if (btf_fd != -1)
 		close(btf_fd);
 	if (map_fd != -1)
 		close(map_fd);
-
-	return err;
-}
-
-static int test_raw(void)
-{
-	unsigned int i;
-	int err = 0;
-
-	if (args.raw_test_num)
-		return count_result(do_test_raw(args.raw_test_num));
-
-	for (i = 1; i <= ARRAY_SIZE(raw_tests); i++)
-		err |= count_result(do_test_raw(i));
-
-	return err;
 }
 
 struct btf_get_info_test {
@@ -3814,11 +3757,6 @@ const struct btf_get_info_test get_info_tests[] = {
 },
 };
 
-static inline __u64 ptr_to_u64(const void *ptr)
-{
-	return (__u64)(unsigned long)ptr;
-}
-
 static int test_big_btf_info(unsigned int test_num)
 {
 	const struct btf_get_info_test *test = &get_info_tests[test_num - 1];
@@ -3851,7 +3789,7 @@ static int test_big_btf_info(unsigned int test_num)
 
 	btf_fd = bpf_load_btf(raw_btf, raw_btf_size,
 			      btf_log_buf, BTF_LOG_BUF_SIZE,
-			      args.always_log);
+			      always_log);
 	if (CHECK(btf_fd == -1, "errno:%d", errno)) {
 		err = -1;
 		goto done;
@@ -3892,7 +3830,7 @@ static int test_big_btf_info(unsigned int test_num)
 	fprintf(stderr, "OK");
 
 done:
-	if (*btf_log_buf && (err || args.always_log))
+	if (*btf_log_buf && (err || always_log))
 		fprintf(stderr, "\n%s", btf_log_buf);
 
 	free(raw_btf);
@@ -3939,7 +3877,7 @@ static int test_btf_id(unsigned int test_num)
 
 	btf_fd[0] = bpf_load_btf(raw_btf, raw_btf_size,
 				 btf_log_buf, BTF_LOG_BUF_SIZE,
-				 args.always_log);
+				 always_log);
 	if (CHECK(btf_fd[0] == -1, "errno:%d", errno)) {
 		err = -1;
 		goto done;
@@ -4024,7 +3962,7 @@ static int test_btf_id(unsigned int test_num)
 	fprintf(stderr, "OK");
 
 done:
-	if (*btf_log_buf && (err || args.always_log))
+	if (*btf_log_buf && (err || always_log))
 		fprintf(stderr, "\n%s", btf_log_buf);
 
 	free(raw_btf);
@@ -4039,7 +3977,7 @@ done:
 	return err;
 }
 
-static int do_test_get_info(unsigned int test_num)
+static void do_test_get_info(unsigned int test_num)
 {
 	const struct btf_get_info_test *test = &get_info_tests[test_num - 1];
 	unsigned int raw_btf_size, user_btf_size, expected_nbytes;
@@ -4048,11 +3986,14 @@ static int do_test_get_info(unsigned int test_num)
 	int btf_fd = -1, err, ret;
 	uint32_t info_len;
 
-	fprintf(stderr, "BTF GET_INFO test[%u] (%s): ",
-		test_num, test->descr);
+	if (!test__start_subtest(test->descr))
+		return;
 
-	if (test->special_test)
-		return test->special_test(test_num);
+	if (test->special_test) {
+		err = test->special_test(test_num);
+		if (CHECK(err, "failed: %d\n", err))
+			return;
+	}
 
 	raw_btf = btf_raw_create(&hdr_tmpl,
 				 test->raw_types,
@@ -4061,7 +4002,7 @@ static int do_test_get_info(unsigned int test_num)
 				 &raw_btf_size, NULL);
 
 	if (!raw_btf)
-		return -1;
+		return;
 
 	*btf_log_buf = '\0';
 
@@ -4073,7 +4014,7 @@ static int do_test_get_info(unsigned int test_num)
 
 	btf_fd = bpf_load_btf(raw_btf, raw_btf_size,
 			      btf_log_buf, BTF_LOG_BUF_SIZE,
-			      args.always_log);
+			      always_log);
 	if (CHECK(btf_fd == -1, "errno:%d", errno)) {
 		err = -1;
 		goto done;
@@ -4114,7 +4055,7 @@ static int do_test_get_info(unsigned int test_num)
 	fprintf(stderr, "OK");
 
 done:
-	if (*btf_log_buf && (err || args.always_log))
+	if (*btf_log_buf && (err || always_log))
 		fprintf(stderr, "\n%s", btf_log_buf);
 
 	free(raw_btf);
@@ -4122,22 +4063,6 @@ done:
 
 	if (btf_fd != -1)
 		close(btf_fd);
-
-	return err;
-}
-
-static int test_get_info(void)
-{
-	unsigned int i;
-	int err = 0;
-
-	if (args.get_info_test_num)
-		return count_result(do_test_get_info(args.get_info_test_num));
-
-	for (i = 1; i <= ARRAY_SIZE(get_info_tests); i++)
-		err |= count_result(do_test_get_info(i));
-
-	return err;
 }
 
 struct btf_file_test {
@@ -4151,7 +4076,7 @@ static struct btf_file_test file_tests[] = {
 	{ .file = "test_btf_nokv.o", .btf_kv_notfound = true, },
 };
 
-static int do_test_file(unsigned int test_num)
+static void do_test_file(unsigned int test_num)
 {
 	const struct btf_file_test *test = &file_tests[test_num - 1];
 	const char *expected_fnames[] = {"_dummy_tracepoint",
@@ -4169,17 +4094,17 @@ static int do_test_file(unsigned int test_num)
 	struct bpf_map *map;
 	int i, err, prog_fd;
 
-	fprintf(stderr, "BTF libbpf test[%u] (%s): ", test_num,
-		test->file);
+	if (!test__start_subtest(test->file))
+		return;
 
 	btf = btf__parse_elf(test->file, &btf_ext);
 	if (IS_ERR(btf)) {
 		if (PTR_ERR(btf) == -ENOENT) {
-			fprintf(stderr, "SKIP. No ELF %s found", BTF_ELF_SEC);
-			skip_cnt++;
-			return 0;
+			printf("%s:SKIP: No ELF %s found", __func__, BTF_ELF_SEC);
+			test__skip();
+			return;
 		}
-		return PTR_ERR(btf);
+		return;
 	}
 	btf__free(btf);
 
@@ -4188,7 +4113,7 @@ static int do_test_file(unsigned int test_num)
 
 	obj = bpf_object__open(test->file);
 	if (CHECK(IS_ERR(obj), "obj: %ld", PTR_ERR(obj)))
-		return PTR_ERR(obj);
+		return;
 
 	prog = bpf_program__next(NULL, obj);
 	if (CHECK(!prog, "Cannot find bpf_prog")) {
@@ -4310,21 +4235,6 @@ skip:
 done:
 	free(func_info);
 	bpf_object__close(obj);
-	return err;
-}
-
-static int test_file(void)
-{
-	unsigned int i;
-	int err = 0;
-
-	if (args.file_test_num)
-		return count_result(do_test_file(args.file_test_num));
-
-	for (i = 1; i <= ARRAY_SIZE(file_tests); i++)
-		err |= count_result(do_test_file(i));
-
-	return err;
 }
 
 const char *pprint_enum_str[] = {
@@ -4428,7 +4338,7 @@ static struct btf_raw_test pprint_test_template[] = {
 	.value_size = sizeof(struct pprint_mapv),
 	.key_type_id = 3,	/* unsigned int */
 	.value_type_id = 16,	/* struct pprint_mapv */
-	.max_entries = 128 * 1024,
+	.max_entries = 128,
 },
 
 {
@@ -4493,7 +4403,7 @@ static struct btf_raw_test pprint_test_template[] = {
 	.value_size = sizeof(struct pprint_mapv),
 	.key_type_id = 3,	/* unsigned int */
 	.value_type_id = 16,	/* struct pprint_mapv */
-	.max_entries = 128 * 1024,
+	.max_entries = 128,
 },
 
 {
@@ -4564,7 +4474,7 @@ static struct btf_raw_test pprint_test_template[] = {
 	.value_size = sizeof(struct pprint_mapv),
 	.key_type_id = 3,	/* unsigned int */
 	.value_type_id = 16,	/* struct pprint_mapv */
-	.max_entries = 128 * 1024,
+	.max_entries = 128,
 },
 
 #ifdef __SIZEOF_INT128__
@@ -4591,7 +4501,7 @@ static struct btf_raw_test pprint_test_template[] = {
 	.value_size = sizeof(struct pprint_mapv_int128),
 	.key_type_id = 1,
 	.value_type_id = 4,
-	.max_entries = 128 * 1024,
+	.max_entries = 128,
 	.mapv_kind = PPRINT_MAPV_KIND_INT128,
 },
 #endif
@@ -4790,7 +4700,7 @@ static int check_line(const char *expected_line, int nexpected_line,
 }
 
 
-static int do_test_pprint(int test_num)
+static void do_test_pprint(int test_num)
 {
 	const struct btf_raw_test *test = &pprint_test_template[test_num];
 	enum pprint_mapv_kind_t mapv_kind = test->mapv_kind;
@@ -4809,18 +4719,20 @@ static int do_test_pprint(int test_num)
 	uint8_t *raw_btf;
 	ssize_t nread;
 
-	fprintf(stderr, "%s(#%d)......", test->descr, test_num);
+	if (!test__start_subtest(test->descr))
+		return;
+
 	raw_btf = btf_raw_create(&hdr_tmpl, test->raw_types,
 				 test->str_sec, test->str_sec_size,
 				 &raw_btf_size, NULL);
 
 	if (!raw_btf)
-		return -1;
+		return;
 
 	*btf_log_buf = '\0';
 	btf_fd = bpf_load_btf(raw_btf, raw_btf_size,
 			      btf_log_buf, BTF_LOG_BUF_SIZE,
-			      args.always_log);
+			      always_log);
 	free(raw_btf);
 
 	if (CHECK(btf_fd == -1, "errno:%d", errno)) {
@@ -4971,7 +4883,7 @@ done:
 		free(mapv);
 	if (!err)
 		fprintf(stderr, "OK");
-	if (*btf_log_buf && (err || args.always_log))
+	if (*btf_log_buf && (err || always_log))
 		fprintf(stderr, "\n%s", btf_log_buf);
 	if (btf_fd != -1)
 		close(btf_fd);
@@ -4981,14 +4893,11 @@ done:
 		fclose(pin_file);
 	unlink(pin_path);
 	free(line);
-
-	return err;
 }
 
-static int test_pprint(void)
+static void test_pprint(void)
 {
 	unsigned int i;
-	int err = 0;
 
 	/* test various maps with the first test template */
 	for (i = 0; i < ARRAY_SIZE(pprint_tests_meta); i++) {
@@ -4999,7 +4908,7 @@ static int test_pprint(void)
 		pprint_test_template[0].lossless_map = pprint_tests_meta[i].lossless_map;
 		pprint_test_template[0].percpu_map = pprint_tests_meta[i].percpu_map;
 
-		err |= count_result(do_test_pprint(0));
+		do_test_pprint(0);
 	}
 
 	/* test rest test templates with the first map */
@@ -5010,10 +4919,8 @@ static int test_pprint(void)
 		pprint_test_template[i].ordered_map = pprint_tests_meta[0].ordered_map;
 		pprint_test_template[i].lossless_map = pprint_tests_meta[0].lossless_map;
 		pprint_test_template[i].percpu_map = pprint_tests_meta[0].percpu_map;
-		err |= count_result(do_test_pprint(i));
+		do_test_pprint(i);
 	}
-
-	return err;
 }
 
 #define BPF_LINE_INFO_ENC(insn_off, file_off, line_off, line_num, line_col) \
@@ -6178,7 +6085,7 @@ done:
 	return err;
 }
 
-static int do_test_info_raw(unsigned int test_num)
+static void do_test_info_raw(unsigned int test_num)
 {
 	const struct prog_info_raw_test *test = &info_raw_tests[test_num - 1];
 	unsigned int raw_btf_size, linfo_str_off, linfo_size;
@@ -6187,18 +6094,19 @@ static int do_test_info_raw(unsigned int test_num)
 	const char *ret_next_str;
 	union bpf_attr attr = {};
 
-	fprintf(stderr, "BTF prog info raw test[%u] (%s): ", test_num, test->descr);
+	if (!test__start_subtest(test->descr))
+		return;
+
 	raw_btf = btf_raw_create(&hdr_tmpl, test->raw_types,
 				 test->str_sec, test->str_sec_size,
 				 &raw_btf_size, &ret_next_str);
-
 	if (!raw_btf)
-		return -1;
+		return;
 
 	*btf_log_buf = '\0';
 	btf_fd = bpf_load_btf(raw_btf, raw_btf_size,
 			      btf_log_buf, BTF_LOG_BUF_SIZE,
-			      args.always_log);
+			      always_log);
 	free(raw_btf);
 
 	if (CHECK(btf_fd == -1, "invalid btf_fd errno:%d", errno)) {
@@ -6206,7 +6114,7 @@ static int do_test_info_raw(unsigned int test_num)
 		goto done;
 	}
 
-	if (*btf_log_buf && args.always_log)
+	if (*btf_log_buf && always_log)
 		fprintf(stderr, "\n%s", btf_log_buf);
 	*btf_log_buf = '\0';
 
@@ -6261,10 +6169,7 @@ static int do_test_info_raw(unsigned int test_num)
 		goto done;
 
 done:
-	if (!err)
-		fprintf(stderr, "OK");
-
-	if (*btf_log_buf && (err || args.always_log))
+	if (*btf_log_buf && (err || always_log))
 		fprintf(stderr, "\n%s", btf_log_buf);
 
 	if (btf_fd != -1)
@@ -6274,22 +6179,6 @@ done:
 
 	if (!IS_ERR(patched_linfo))
 		free(patched_linfo);
-
-	return err;
-}
-
-static int test_info_raw(void)
-{
-	unsigned int i;
-	int err = 0;
-
-	if (args.info_raw_test_num)
-		return count_result(do_test_info_raw(args.info_raw_test_num));
-
-	for (i = 1; i <= ARRAY_SIZE(info_raw_tests); i++)
-		err |= count_result(do_test_info_raw(i));
-
-	return err;
 }
 
 struct btf_raw_data {
@@ -6754,7 +6643,7 @@ static void dump_btf_strings(const char *strs, __u32 len)
 	}
 }
 
-static int do_test_dedup(unsigned int test_num)
+static void do_test_dedup(unsigned int test_num)
 {
 	const struct btf_dedup_test *test = &dedup_tests[test_num - 1];
 	__u32 test_nr_types, expect_nr_types, test_btf_size, expect_btf_size;
@@ -6769,13 +6658,15 @@ static int do_test_dedup(unsigned int test_num)
 	void *raw_btf;
 	int err = 0, i;
 
-	fprintf(stderr, "BTF dedup test[%u] (%s):", test_num, test->descr);
+	if (!test__start_subtest(test->descr))
+		return;
 
 	raw_btf = btf_raw_create(&hdr_tmpl, test->input.raw_types,
 				 test->input.str_sec, test->input.str_sec_size,
 				 &raw_btf_size, &ret_test_next_str);
 	if (!raw_btf)
-		return -1;
+		return;
+
 	test_btf = btf__new((__u8 *)raw_btf, raw_btf_size);
 	free(raw_btf);
 	if (CHECK(IS_ERR(test_btf), "invalid test_btf errno:%ld",
@@ -6789,7 +6680,7 @@ static int do_test_dedup(unsigned int test_num)
 				 test->expect.str_sec_size,
 				 &raw_btf_size, &ret_expect_next_str);
 	if (!raw_btf)
-		return -1;
+		return;
 	expect_btf = btf__new((__u8 *)raw_btf, raw_btf_size);
 	free(raw_btf);
 	if (CHECK(IS_ERR(expect_btf), "invalid expect_btf errno:%ld",
@@ -6894,174 +6785,27 @@ static int do_test_dedup(unsigned int test_num)
 	}
 
 done:
-	if (!err)
-		fprintf(stderr, "OK");
 	if (!IS_ERR(test_btf))
 		btf__free(test_btf);
 	if (!IS_ERR(expect_btf))
 		btf__free(expect_btf);
-
-	return err;
 }
 
-static int test_dedup(void)
+void test_btf(void)
 {
-	unsigned int i;
-	int err = 0;
+	int i;
 
-	if (args.dedup_test_num)
-		return count_result(do_test_dedup(args.dedup_test_num));
+	always_log = env.verbosity > VERBOSE_NONE;
 
+	for (i = 1; i <= ARRAY_SIZE(raw_tests); i++)
+		do_test_raw(i);
+	for (i = 1; i <= ARRAY_SIZE(get_info_tests); i++)
+		do_test_get_info(i);
+	for (i = 1; i <= ARRAY_SIZE(file_tests); i++)
+		do_test_file(i);
+	for (i = 1; i <= ARRAY_SIZE(info_raw_tests); i++)
+		do_test_info_raw(i);
 	for (i = 1; i <= ARRAY_SIZE(dedup_tests); i++)
-		err |= count_result(do_test_dedup(i));
-
-	return err;
-}
-
-static void usage(const char *cmd)
-{
-	fprintf(stderr, "Usage: %s [-l] [[-r btf_raw_test_num (1 - %zu)] |\n"
-			"\t[-g btf_get_info_test_num (1 - %zu)] |\n"
-			"\t[-f btf_file_test_num (1 - %zu)] |\n"
-			"\t[-k btf_prog_info_raw_test_num (1 - %zu)] |\n"
-			"\t[-p (pretty print test)] |\n"
-			"\t[-d btf_dedup_test_num (1 - %zu)]]\n",
-		cmd, ARRAY_SIZE(raw_tests), ARRAY_SIZE(get_info_tests),
-		ARRAY_SIZE(file_tests), ARRAY_SIZE(info_raw_tests),
-		ARRAY_SIZE(dedup_tests));
-}
-
-static int parse_args(int argc, char **argv)
-{
-	const char *optstr = "hlpk:f:r:g:d:";
-	int opt;
-
-	while ((opt = getopt(argc, argv, optstr)) != -1) {
-		switch (opt) {
-		case 'l':
-			args.always_log = true;
-			break;
-		case 'f':
-			args.file_test_num = atoi(optarg);
-			args.file_test = true;
-			break;
-		case 'r':
-			args.raw_test_num = atoi(optarg);
-			args.raw_test = true;
-			break;
-		case 'g':
-			args.get_info_test_num = atoi(optarg);
-			args.get_info_test = true;
-			break;
-		case 'p':
-			args.pprint_test = true;
-			break;
-		case 'k':
-			args.info_raw_test_num = atoi(optarg);
-			args.info_raw_test = true;
-			break;
-		case 'd':
-			args.dedup_test_num = atoi(optarg);
-			args.dedup_test = true;
-			break;
-		case 'h':
-			usage(argv[0]);
-			exit(0);
-		default:
-			usage(argv[0]);
-			return -1;
-		}
-	}
-
-	if (args.raw_test_num &&
-	    (args.raw_test_num < 1 ||
-	     args.raw_test_num > ARRAY_SIZE(raw_tests))) {
-		fprintf(stderr, "BTF raw test number must be [1 - %zu]\n",
-			ARRAY_SIZE(raw_tests));
-		return -1;
-	}
-
-	if (args.file_test_num &&
-	    (args.file_test_num < 1 ||
-	     args.file_test_num > ARRAY_SIZE(file_tests))) {
-		fprintf(stderr, "BTF file test number must be [1 - %zu]\n",
-			ARRAY_SIZE(file_tests));
-		return -1;
-	}
-
-	if (args.get_info_test_num &&
-	    (args.get_info_test_num < 1 ||
-	     args.get_info_test_num > ARRAY_SIZE(get_info_tests))) {
-		fprintf(stderr, "BTF get info test number must be [1 - %zu]\n",
-			ARRAY_SIZE(get_info_tests));
-		return -1;
-	}
-
-	if (args.info_raw_test_num &&
-	    (args.info_raw_test_num < 1 ||
-	     args.info_raw_test_num > ARRAY_SIZE(info_raw_tests))) {
-		fprintf(stderr, "BTF prog info raw test number must be [1 - %zu]\n",
-			ARRAY_SIZE(info_raw_tests));
-		return -1;
-	}
-
-	if (args.dedup_test_num &&
-	    (args.dedup_test_num < 1 ||
-	     args.dedup_test_num > ARRAY_SIZE(dedup_tests))) {
-		fprintf(stderr, "BTF dedup test number must be [1 - %zu]\n",
-			ARRAY_SIZE(dedup_tests));
-		return -1;
-	}
-
-	return 0;
-}
-
-static void print_summary(void)
-{
-	fprintf(stderr, "PASS:%u SKIP:%u FAIL:%u\n",
-		pass_cnt - skip_cnt, skip_cnt, error_cnt);
-}
-
-int main(int argc, char **argv)
-{
-	int err = 0;
-
-	err = parse_args(argc, argv);
-	if (err)
-		return err;
-
-	if (args.always_log)
-		libbpf_set_print(__base_pr);
-
-	if (args.raw_test)
-		err |= test_raw();
-
-	if (args.get_info_test)
-		err |= test_get_info();
-
-	if (args.file_test)
-		err |= test_file();
-
-	if (args.pprint_test)
-		err |= test_pprint();
-
-	if (args.info_raw_test)
-		err |= test_info_raw();
-
-	if (args.dedup_test)
-		err |= test_dedup();
-
-	if (args.raw_test || args.get_info_test || args.file_test ||
-	    args.pprint_test || args.info_raw_test || args.dedup_test)
-		goto done;
-
-	err |= test_raw();
-	err |= test_get_info();
-	err |= test_file();
-	err |= test_info_raw();
-	err |= test_dedup();
-
-done:
-	print_summary();
-	return err;
+		do_test_dedup(i);
+	test_pprint();
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_dump.c b/tools/testing/selftests/bpf/prog_tests/btf_dump.c
index 39fb81d9daeb..c60091ee8a21 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_dump.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_dump.c
@@ -129,6 +129,109 @@ done:
 	return err;
 }
 
+static char *dump_buf;
+static size_t dump_buf_sz;
+static FILE *dump_buf_file;
+
+void test_btf_dump_incremental(void)
+{
+	struct btf *btf = NULL;
+	struct btf_dump *d = NULL;
+	struct btf_dump_opts opts;
+	int id, err, i;
+
+	dump_buf_file = open_memstream(&dump_buf, &dump_buf_sz);
+	if (!ASSERT_OK_PTR(dump_buf_file, "dump_memstream"))
+		return;
+	btf = btf__new_empty();
+	if (!ASSERT_OK_PTR(btf, "new_empty"))
+		goto err_out;
+	opts.ctx = dump_buf_file;
+	d = btf_dump__new(btf, NULL, &opts, btf_dump_printf);
+	if (!ASSERT_OK(libbpf_get_error(d), "btf_dump__new"))
+		goto err_out;
+
+	/* First, generate BTF corresponding to the following C code:
+	 *
+	 * enum { VAL = 1 };
+	 *
+	 * struct s { int x; };
+	 *
+	 */
+	id = btf__add_enum(btf, NULL, 4);
+	ASSERT_EQ(id, 1, "enum_id");
+	err = btf__add_enum_value(btf, "VAL", 1);
+	ASSERT_OK(err, "enum_val_ok");
+
+	id = btf__add_int(btf, "int", 4, BTF_INT_SIGNED);
+	ASSERT_EQ(id, 2, "int_id");
+
+	id = btf__add_struct(btf, "s", 4);
+	ASSERT_EQ(id, 3, "struct_id");
+	err = btf__add_field(btf, "x", 2, 0, 0);
+	ASSERT_OK(err, "field_ok");
+
+	for (i = 1; i <= btf__get_nr_types(btf); i++) {
+		err = btf_dump__dump_type(d, i);
+		ASSERT_OK(err, "dump_type_ok");
+	}
+
+	fflush(dump_buf_file);
+	dump_buf[dump_buf_sz] = 0; /* some libc implementations don't do this */
+	ASSERT_STREQ(dump_buf,
+"enum {\n"
+"	VAL = 1,\n"
+"};\n"
+"\n"
+"struct s {\n"
+"	int x;\n"
+"};\n\n", "c_dump1");
+
+	/* Now, after dumping original BTF, append another struct that embeds
+	 * anonymous enum. It also has a name conflict with the first struct:
+	 *
+	 * struct s___2 {
+	 *     enum { VAL___2 = 1 } x;
+	 *     struct s s;
+	 * };
+	 *
+	 * This will test that btf_dump'er maintains internal state properly.
+	 * Note that VAL___2 enum value. It's because we've already emitted
+	 * that enum as a global anonymous enum, so btf_dump will ensure that
+	 * enum values don't conflict;
+	 *
+	 */
+	fseek(dump_buf_file, 0, SEEK_SET);
+
+	id = btf__add_struct(btf, "s", 4);
+	ASSERT_EQ(id, 4, "struct_id");
+	err = btf__add_field(btf, "x", 1, 0, 0);
+	ASSERT_OK(err, "field_ok");
+	err = btf__add_field(btf, "s", 3, 32, 0);
+	ASSERT_OK(err, "field_ok");
+
+	for (i = 1; i <= btf__get_nr_types(btf); i++) {
+		err = btf_dump__dump_type(d, i);
+		ASSERT_OK(err, "dump_type_ok");
+	}
+
+	fflush(dump_buf_file);
+	dump_buf[dump_buf_sz] = 0; /* some libc implementations don't do this */
+	ASSERT_STREQ(dump_buf,
+"struct s___2 {\n"
+"	enum {\n"
+"		VAL___2 = 1,\n"
+"	} x;\n"
+"	struct s s;\n"
+"};\n\n" , "c_dump1");
+
+err_out:
+	fclose(dump_buf_file);
+	free(dump_buf);
+	btf_dump__free(d);
+	btf__free(btf);
+}
+
 void test_btf_dump() {
 	int i;
 
@@ -140,4 +243,6 @@ void test_btf_dump() {
 
 		test_btf_dump_case(i, &btf_dump_test_cases[i]);
 	}
+	if (test__start_subtest("btf_dump: incremental"))
+		test_btf_dump_incremental();
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_endian.c b/tools/testing/selftests/bpf/prog_tests/btf_endian.c
new file mode 100644
index 000000000000..8c52d72c876e
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/btf_endian.c
@@ -0,0 +1,101 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#define _GNU_SOURCE
+#include <string.h>
+#include <byteswap.h>
+#include <test_progs.h>
+#include <bpf/btf.h>
+
+static int duration = 0;
+
+void test_btf_endian() {
+#if __BYTE_ORDER == __LITTLE_ENDIAN
+	enum btf_endianness endian = BTF_LITTLE_ENDIAN;
+#elif __BYTE_ORDER == __BIG_ENDIAN
+	enum btf_endianness endian = BTF_BIG_ENDIAN;
+#else
+#error "Unrecognized __BYTE_ORDER"
+#endif
+	enum btf_endianness swap_endian = 1 - endian;
+	struct btf *btf = NULL, *swap_btf = NULL;
+	const void *raw_data, *swap_raw_data;
+	const struct btf_type *t;
+	const struct btf_header *hdr;
+	__u32 raw_sz, swap_raw_sz;
+	int var_id;
+
+	/* Load BTF in native endianness */
+	btf = btf__parse_elf("btf_dump_test_case_syntax.o", NULL);
+	if (!ASSERT_OK_PTR(btf, "parse_native_btf"))
+		goto err_out;
+
+	ASSERT_EQ(btf__endianness(btf), endian, "endian");
+	btf__set_endianness(btf, swap_endian);
+	ASSERT_EQ(btf__endianness(btf), swap_endian, "endian");
+
+	/* Get raw BTF data in non-native endianness... */
+	raw_data = btf__get_raw_data(btf, &raw_sz);
+	if (!ASSERT_OK_PTR(raw_data, "raw_data_inverted"))
+		goto err_out;
+
+	/* ...and open it as a new BTF instance */
+	swap_btf = btf__new(raw_data, raw_sz);
+	if (!ASSERT_OK_PTR(swap_btf, "parse_swap_btf"))
+		goto err_out;
+
+	ASSERT_EQ(btf__endianness(swap_btf), swap_endian, "endian");
+	ASSERT_EQ(btf__get_nr_types(swap_btf), btf__get_nr_types(btf), "nr_types");
+
+	swap_raw_data = btf__get_raw_data(swap_btf, &swap_raw_sz);
+	if (!ASSERT_OK_PTR(swap_raw_data, "swap_raw_data"))
+		goto err_out;
+
+	/* both raw data should be identical (with non-native endianness) */
+	ASSERT_OK(memcmp(raw_data, swap_raw_data, raw_sz), "mem_identical");
+
+	/* make sure that at least BTF header data is really swapped */
+	hdr = swap_raw_data;
+	ASSERT_EQ(bswap_16(hdr->magic), BTF_MAGIC, "btf_magic_swapped");
+	ASSERT_EQ(raw_sz, swap_raw_sz, "raw_sizes");
+
+	/* swap it back to native endianness */
+	btf__set_endianness(swap_btf, endian);
+	swap_raw_data = btf__get_raw_data(swap_btf, &swap_raw_sz);
+	if (!ASSERT_OK_PTR(swap_raw_data, "swap_raw_data"))
+		goto err_out;
+
+	/* now header should have native BTF_MAGIC */
+	hdr = swap_raw_data;
+	ASSERT_EQ(hdr->magic, BTF_MAGIC, "btf_magic_native");
+	ASSERT_EQ(raw_sz, swap_raw_sz, "raw_sizes");
+
+	/* now modify original BTF */
+	var_id = btf__add_var(btf, "some_var", BTF_VAR_GLOBAL_ALLOCATED, 1);
+	CHECK(var_id <= 0, "var_id", "failed %d\n", var_id);
+
+	btf__free(swap_btf);
+	swap_btf = NULL;
+
+	btf__set_endianness(btf, swap_endian);
+	raw_data = btf__get_raw_data(btf, &raw_sz);
+	if (!ASSERT_OK_PTR(raw_data, "raw_data_inverted"))
+		goto err_out;
+
+	/* and re-open swapped raw data again */
+	swap_btf = btf__new(raw_data, raw_sz);
+	if (!ASSERT_OK_PTR(swap_btf, "parse_swap_btf"))
+		goto err_out;
+
+	ASSERT_EQ(btf__endianness(swap_btf), swap_endian, "endian");
+	ASSERT_EQ(btf__get_nr_types(swap_btf), btf__get_nr_types(btf), "nr_types");
+
+	/* the type should appear as if it was stored in native endianness */
+	t = btf__type_by_id(swap_btf, var_id);
+	ASSERT_STREQ(btf__str_by_offset(swap_btf, t->name_off), "some_var", "var_name");
+	ASSERT_EQ(btf_var(t)->linkage, BTF_VAR_GLOBAL_ALLOCATED, "var_linkage");
+	ASSERT_EQ(t->type, 1, "var_type");
+
+err_out:
+	btf__free(btf);
+	btf__free(swap_btf);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_skc_cls_ingress.c b/tools/testing/selftests/bpf/prog_tests/btf_skc_cls_ingress.c
new file mode 100644
index 000000000000..86ccf37e26b3
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/btf_skc_cls_ingress.c
@@ -0,0 +1,234 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+
+#define _GNU_SOURCE
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+#include <sched.h>
+#include <linux/compiler.h>
+#include <bpf/libbpf.h>
+
+#include "network_helpers.h"
+#include "test_progs.h"
+#include "test_btf_skc_cls_ingress.skel.h"
+
+static struct test_btf_skc_cls_ingress *skel;
+struct sockaddr_in6 srv_sa6;
+static __u32 duration;
+
+#define PROG_PIN_FILE "/sys/fs/bpf/btf_skc_cls_ingress"
+
+static int write_sysctl(const char *sysctl, const char *value)
+{
+	int fd, err, len;
+
+	fd = open(sysctl, O_WRONLY);
+	if (CHECK(fd == -1, "open sysctl", "open(%s): %s (%d)\n",
+		  sysctl, strerror(errno), errno))
+		return -1;
+
+	len = strlen(value);
+	err = write(fd, value, len);
+	close(fd);
+	if (CHECK(err != len, "write sysctl",
+		  "write(%s, %s, %d): err:%d %s (%d)\n",
+		  sysctl, value, len, err, strerror(errno), errno))
+		return -1;
+
+	return 0;
+}
+
+static int prepare_netns(void)
+{
+	if (CHECK(unshare(CLONE_NEWNET), "create netns",
+		  "unshare(CLONE_NEWNET): %s (%d)",
+		  strerror(errno), errno))
+		return -1;
+
+	if (CHECK(system("ip link set dev lo up"),
+		  "ip link set dev lo up", "failed\n"))
+		return -1;
+
+	if (CHECK(system("tc qdisc add dev lo clsact"),
+		  "tc qdisc add dev lo clsact", "failed\n"))
+		return -1;
+
+	if (CHECK(system("tc filter add dev lo ingress bpf direct-action object-pinned " PROG_PIN_FILE),
+		  "install tc cls-prog at ingress", "failed\n"))
+		return -1;
+
+	/* Ensure 20 bytes options (i.e. in total 40 bytes tcp header) for the
+	 * bpf_tcp_gen_syncookie() helper.
+	 */
+	if (write_sysctl("/proc/sys/net/ipv4/tcp_window_scaling", "1") ||
+	    write_sysctl("/proc/sys/net/ipv4/tcp_timestamps", "1") ||
+	    write_sysctl("/proc/sys/net/ipv4/tcp_sack", "1"))
+		return -1;
+
+	return 0;
+}
+
+static void reset_test(void)
+{
+	memset(&skel->bss->srv_sa6, 0, sizeof(skel->bss->srv_sa6));
+	skel->bss->listen_tp_sport = 0;
+	skel->bss->req_sk_sport = 0;
+	skel->bss->recv_cookie = 0;
+	skel->bss->gen_cookie = 0;
+	skel->bss->linum = 0;
+}
+
+static void print_err_line(void)
+{
+	if (skel->bss->linum)
+		printf("bpf prog error at line %u\n", skel->bss->linum);
+}
+
+static void test_conn(void)
+{
+	int listen_fd = -1, cli_fd = -1, err;
+	socklen_t addrlen = sizeof(srv_sa6);
+	int srv_port;
+
+	if (write_sysctl("/proc/sys/net/ipv4/tcp_syncookies", "1"))
+		return;
+
+	listen_fd = start_server(AF_INET6, SOCK_STREAM, "::1", 0, 0);
+	if (CHECK_FAIL(listen_fd == -1))
+		return;
+
+	err = getsockname(listen_fd, (struct sockaddr *)&srv_sa6, &addrlen);
+	if (CHECK(err, "getsockname(listen_fd)", "err:%d errno:%d\n", err,
+		  errno))
+		goto done;
+	memcpy(&skel->bss->srv_sa6, &srv_sa6, sizeof(srv_sa6));
+	srv_port = ntohs(srv_sa6.sin6_port);
+
+	cli_fd = connect_to_fd(listen_fd, 0);
+	if (CHECK_FAIL(cli_fd == -1))
+		goto done;
+
+	if (CHECK(skel->bss->listen_tp_sport != srv_port ||
+		  skel->bss->req_sk_sport != srv_port,
+		  "Unexpected sk src port",
+		  "listen_tp_sport:%u req_sk_sport:%u expected:%u\n",
+		  skel->bss->listen_tp_sport, skel->bss->req_sk_sport,
+		  srv_port))
+		goto done;
+
+	if (CHECK(skel->bss->gen_cookie || skel->bss->recv_cookie,
+		  "Unexpected syncookie states",
+		  "gen_cookie:%u recv_cookie:%u\n",
+		  skel->bss->gen_cookie, skel->bss->recv_cookie))
+		goto done;
+
+	CHECK(skel->bss->linum, "bpf prog detected error", "at line %u\n",
+	      skel->bss->linum);
+
+done:
+	if (listen_fd != -1)
+		close(listen_fd);
+	if (cli_fd != -1)
+		close(cli_fd);
+}
+
+static void test_syncookie(void)
+{
+	int listen_fd = -1, cli_fd = -1, err;
+	socklen_t addrlen = sizeof(srv_sa6);
+	int srv_port;
+
+	/* Enforce syncookie mode */
+	if (write_sysctl("/proc/sys/net/ipv4/tcp_syncookies", "2"))
+		return;
+
+	listen_fd = start_server(AF_INET6, SOCK_STREAM, "::1", 0, 0);
+	if (CHECK_FAIL(listen_fd == -1))
+		return;
+
+	err = getsockname(listen_fd, (struct sockaddr *)&srv_sa6, &addrlen);
+	if (CHECK(err, "getsockname(listen_fd)", "err:%d errno:%d\n", err,
+		  errno))
+		goto done;
+	memcpy(&skel->bss->srv_sa6, &srv_sa6, sizeof(srv_sa6));
+	srv_port = ntohs(srv_sa6.sin6_port);
+
+	cli_fd = connect_to_fd(listen_fd, 0);
+	if (CHECK_FAIL(cli_fd == -1))
+		goto done;
+
+	if (CHECK(skel->bss->listen_tp_sport != srv_port,
+		  "Unexpected tp src port",
+		  "listen_tp_sport:%u expected:%u\n",
+		  skel->bss->listen_tp_sport, srv_port))
+		goto done;
+
+	if (CHECK(skel->bss->req_sk_sport,
+		  "Unexpected req_sk src port",
+		  "req_sk_sport:%u expected:0\n",
+		   skel->bss->req_sk_sport))
+		goto done;
+
+	if (CHECK(!skel->bss->gen_cookie ||
+		  skel->bss->gen_cookie != skel->bss->recv_cookie,
+		  "Unexpected syncookie states",
+		  "gen_cookie:%u recv_cookie:%u\n",
+		  skel->bss->gen_cookie, skel->bss->recv_cookie))
+		goto done;
+
+	CHECK(skel->bss->linum, "bpf prog detected error", "at line %u\n",
+	      skel->bss->linum);
+
+done:
+	if (listen_fd != -1)
+		close(listen_fd);
+	if (cli_fd != -1)
+		close(cli_fd);
+}
+
+struct test {
+	const char *desc;
+	void (*run)(void);
+};
+
+#define DEF_TEST(name) { #name, test_##name }
+static struct test tests[] = {
+	DEF_TEST(conn),
+	DEF_TEST(syncookie),
+};
+
+void test_btf_skc_cls_ingress(void)
+{
+	int i, err;
+
+	skel = test_btf_skc_cls_ingress__open_and_load();
+	if (CHECK(!skel, "test_btf_skc_cls_ingress__open_and_load", "failed\n"))
+		return;
+
+	err = bpf_program__pin(skel->progs.cls_ingress, PROG_PIN_FILE);
+	if (CHECK(err, "bpf_program__pin",
+		  "cannot pin bpf prog to %s. err:%d\n", PROG_PIN_FILE, err)) {
+		test_btf_skc_cls_ingress__destroy(skel);
+		return;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(tests); i++) {
+		if (!test__start_subtest(tests[i].desc))
+			continue;
+
+		if (prepare_netns())
+			break;
+
+		tests[i].run();
+
+		print_err_line();
+		reset_test();
+	}
+
+	bpf_program__unpin(skel->progs.cls_ingress, PROG_PIN_FILE);
+	test_btf_skc_cls_ingress__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_write.c b/tools/testing/selftests/bpf/prog_tests/btf_write.c
new file mode 100644
index 000000000000..314e1e7c36df
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/btf_write.c
@@ -0,0 +1,244 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#include <test_progs.h>
+#include <bpf/btf.h>
+
+static int duration = 0;
+
+void test_btf_write() {
+	const struct btf_var_secinfo *vi;
+	const struct btf_type *t;
+	const struct btf_member *m;
+	const struct btf_enum *v;
+	const struct btf_param *p;
+	struct btf *btf;
+	int id, err, str_off;
+
+	btf = btf__new_empty();
+	if (CHECK(IS_ERR(btf), "new_empty", "failed: %ld\n", PTR_ERR(btf)))
+		return;
+
+	str_off = btf__find_str(btf, "int");
+	ASSERT_EQ(str_off, -ENOENT, "int_str_missing_off");
+
+	str_off = btf__add_str(btf, "int");
+	ASSERT_EQ(str_off, 1, "int_str_off");
+
+	str_off = btf__find_str(btf, "int");
+	ASSERT_EQ(str_off, 1, "int_str_found_off");
+
+	/* BTF_KIND_INT */
+	id = btf__add_int(btf, "int", 4,  BTF_INT_SIGNED);
+	ASSERT_EQ(id, 1, "int_id");
+
+	t = btf__type_by_id(btf, 1);
+	/* should re-use previously added "int" string */
+	ASSERT_EQ(t->name_off, str_off, "int_name_off");
+	ASSERT_STREQ(btf__str_by_offset(btf, t->name_off), "int", "int_name");
+	ASSERT_EQ(btf_kind(t), BTF_KIND_INT, "int_kind");
+	ASSERT_EQ(t->size, 4, "int_sz");
+	ASSERT_EQ(btf_int_encoding(t), BTF_INT_SIGNED, "int_enc");
+	ASSERT_EQ(btf_int_bits(t), 32, "int_bits");
+
+	/* invalid int size */
+	id = btf__add_int(btf, "bad sz int", 7, 0);
+	ASSERT_ERR(id, "int_bad_sz");
+	/* invalid encoding */
+	id = btf__add_int(btf, "bad enc int", 4, 123);
+	ASSERT_ERR(id, "int_bad_enc");
+	/* NULL name */
+	id = btf__add_int(btf, NULL, 4, 0);
+	ASSERT_ERR(id, "int_bad_null_name");
+	/* empty name */
+	id = btf__add_int(btf, "", 4, 0);
+	ASSERT_ERR(id, "int_bad_empty_name");
+
+	/* PTR/CONST/VOLATILE/RESTRICT */
+	id = btf__add_ptr(btf, 1);
+	ASSERT_EQ(id, 2, "ptr_id");
+	t = btf__type_by_id(btf, 2);
+	ASSERT_EQ(btf_kind(t), BTF_KIND_PTR, "ptr_kind");
+	ASSERT_EQ(t->type, 1, "ptr_type");
+
+	id = btf__add_const(btf, 5); /* points forward to restrict */
+	ASSERT_EQ(id, 3, "const_id");
+	t = btf__type_by_id(btf, 3);
+	ASSERT_EQ(btf_kind(t), BTF_KIND_CONST, "const_kind");
+	ASSERT_EQ(t->type, 5, "const_type");
+
+	id = btf__add_volatile(btf, 3);
+	ASSERT_EQ(id, 4, "volatile_id");
+	t = btf__type_by_id(btf, 4);
+	ASSERT_EQ(btf_kind(t), BTF_KIND_VOLATILE, "volatile_kind");
+	ASSERT_EQ(t->type, 3, "volatile_type");
+
+	id = btf__add_restrict(btf, 4);
+	ASSERT_EQ(id, 5, "restrict_id");
+	t = btf__type_by_id(btf, 5);
+	ASSERT_EQ(btf_kind(t), BTF_KIND_RESTRICT, "restrict_kind");
+	ASSERT_EQ(t->type, 4, "restrict_type");
+
+	/* ARRAY */
+	id = btf__add_array(btf, 1, 2, 10); /* int *[10] */
+	ASSERT_EQ(id, 6, "array_id");
+	t = btf__type_by_id(btf, 6);
+	ASSERT_EQ(btf_kind(t), BTF_KIND_ARRAY, "array_kind");
+	ASSERT_EQ(btf_array(t)->index_type, 1, "array_index_type");
+	ASSERT_EQ(btf_array(t)->type, 2, "array_elem_type");
+	ASSERT_EQ(btf_array(t)->nelems, 10, "array_nelems");
+
+	/* STRUCT */
+	err = btf__add_field(btf, "field", 1, 0, 0);
+	ASSERT_ERR(err, "no_struct_field");
+	id = btf__add_struct(btf, "s1", 8);
+	ASSERT_EQ(id, 7, "struct_id");
+	err = btf__add_field(btf, "f1", 1, 0, 0);
+	ASSERT_OK(err, "f1_res");
+	err = btf__add_field(btf, "f2", 1, 32, 16);
+	ASSERT_OK(err, "f2_res");
+
+	t = btf__type_by_id(btf, 7);
+	ASSERT_STREQ(btf__str_by_offset(btf, t->name_off), "s1", "struct_name");
+	ASSERT_EQ(btf_kind(t), BTF_KIND_STRUCT, "struct_kind");
+	ASSERT_EQ(btf_vlen(t), 2, "struct_vlen");
+	ASSERT_EQ(btf_kflag(t), true, "struct_kflag");
+	ASSERT_EQ(t->size, 8, "struct_sz");
+	m = btf_members(t) + 0;
+	ASSERT_STREQ(btf__str_by_offset(btf, m->name_off), "f1", "f1_name");
+	ASSERT_EQ(m->type, 1, "f1_type");
+	ASSERT_EQ(btf_member_bit_offset(t, 0), 0, "f1_bit_off");
+	ASSERT_EQ(btf_member_bitfield_size(t, 0), 0, "f1_bit_sz");
+	m = btf_members(t) + 1;
+	ASSERT_STREQ(btf__str_by_offset(btf, m->name_off), "f2", "f2_name");
+	ASSERT_EQ(m->type, 1, "f2_type");
+	ASSERT_EQ(btf_member_bit_offset(t, 1), 32, "f2_bit_off");
+	ASSERT_EQ(btf_member_bitfield_size(t, 1), 16, "f2_bit_sz");
+
+	/* UNION */
+	id = btf__add_union(btf, "u1", 8);
+	ASSERT_EQ(id, 8, "union_id");
+
+	/* invalid, non-zero offset */
+	err = btf__add_field(btf, "field", 1, 1, 0);
+	ASSERT_ERR(err, "no_struct_field");
+
+	err = btf__add_field(btf, "f1", 1, 0, 16);
+	ASSERT_OK(err, "f1_res");
+
+	t = btf__type_by_id(btf, 8);
+	ASSERT_STREQ(btf__str_by_offset(btf, t->name_off), "u1", "union_name");
+	ASSERT_EQ(btf_kind(t), BTF_KIND_UNION, "union_kind");
+	ASSERT_EQ(btf_vlen(t), 1, "union_vlen");
+	ASSERT_EQ(btf_kflag(t), true, "union_kflag");
+	ASSERT_EQ(t->size, 8, "union_sz");
+	m = btf_members(t) + 0;
+	ASSERT_STREQ(btf__str_by_offset(btf, m->name_off), "f1", "f1_name");
+	ASSERT_EQ(m->type, 1, "f1_type");
+	ASSERT_EQ(btf_member_bit_offset(t, 0), 0, "f1_bit_off");
+	ASSERT_EQ(btf_member_bitfield_size(t, 0), 16, "f1_bit_sz");
+
+	/* ENUM */
+	id = btf__add_enum(btf, "e1", 4);
+	ASSERT_EQ(id, 9, "enum_id");
+	err = btf__add_enum_value(btf, "v1", 1);
+	ASSERT_OK(err, "v1_res");
+	err = btf__add_enum_value(btf, "v2", 2);
+	ASSERT_OK(err, "v2_res");
+
+	t = btf__type_by_id(btf, 9);
+	ASSERT_STREQ(btf__str_by_offset(btf, t->name_off), "e1", "enum_name");
+	ASSERT_EQ(btf_kind(t), BTF_KIND_ENUM, "enum_kind");
+	ASSERT_EQ(btf_vlen(t), 2, "enum_vlen");
+	ASSERT_EQ(t->size, 4, "enum_sz");
+	v = btf_enum(t) + 0;
+	ASSERT_STREQ(btf__str_by_offset(btf, v->name_off), "v1", "v1_name");
+	ASSERT_EQ(v->val, 1, "v1_val");
+	v = btf_enum(t) + 1;
+	ASSERT_STREQ(btf__str_by_offset(btf, v->name_off), "v2", "v2_name");
+	ASSERT_EQ(v->val, 2, "v2_val");
+
+	/* FWDs */
+	id = btf__add_fwd(btf, "struct_fwd", BTF_FWD_STRUCT);
+	ASSERT_EQ(id, 10, "struct_fwd_id");
+	t = btf__type_by_id(btf, 10);
+	ASSERT_STREQ(btf__str_by_offset(btf, t->name_off), "struct_fwd", "fwd_name");
+	ASSERT_EQ(btf_kind(t), BTF_KIND_FWD, "fwd_kind");
+	ASSERT_EQ(btf_kflag(t), 0, "fwd_kflag");
+
+	id = btf__add_fwd(btf, "union_fwd", BTF_FWD_UNION);
+	ASSERT_EQ(id, 11, "union_fwd_id");
+	t = btf__type_by_id(btf, 11);
+	ASSERT_STREQ(btf__str_by_offset(btf, t->name_off), "union_fwd", "fwd_name");
+	ASSERT_EQ(btf_kind(t), BTF_KIND_FWD, "fwd_kind");
+	ASSERT_EQ(btf_kflag(t), 1, "fwd_kflag");
+
+	id = btf__add_fwd(btf, "enum_fwd", BTF_FWD_ENUM);
+	ASSERT_EQ(id, 12, "enum_fwd_id");
+	t = btf__type_by_id(btf, 12);
+	ASSERT_STREQ(btf__str_by_offset(btf, t->name_off), "enum_fwd", "fwd_name");
+	ASSERT_EQ(btf_kind(t), BTF_KIND_ENUM, "enum_fwd_kind");
+	ASSERT_EQ(btf_vlen(t), 0, "enum_fwd_kind");
+	ASSERT_EQ(t->size, 4, "enum_fwd_sz");
+
+	/* TYPEDEF */
+	id = btf__add_typedef(btf, "typedef1", 1);
+	ASSERT_EQ(id, 13, "typedef_fwd_id");
+	t = btf__type_by_id(btf, 13);
+	ASSERT_STREQ(btf__str_by_offset(btf, t->name_off), "typedef1", "typedef_name");
+	ASSERT_EQ(btf_kind(t), BTF_KIND_TYPEDEF, "typedef_kind");
+	ASSERT_EQ(t->type, 1, "typedef_type");
+
+	/* FUNC & FUNC_PROTO */
+	id = btf__add_func(btf, "func1", BTF_FUNC_GLOBAL, 15);
+	ASSERT_EQ(id, 14, "func_id");
+	t = btf__type_by_id(btf, 14);
+	ASSERT_STREQ(btf__str_by_offset(btf, t->name_off), "func1", "func_name");
+	ASSERT_EQ(t->type, 15, "func_type");
+	ASSERT_EQ(btf_kind(t), BTF_KIND_FUNC, "func_kind");
+	ASSERT_EQ(btf_vlen(t), BTF_FUNC_GLOBAL, "func_vlen");
+
+	id = btf__add_func_proto(btf, 1);
+	ASSERT_EQ(id, 15, "func_proto_id");
+	err = btf__add_func_param(btf, "p1", 1);
+	ASSERT_OK(err, "p1_res");
+	err = btf__add_func_param(btf, "p2", 2);
+	ASSERT_OK(err, "p2_res");
+
+	t = btf__type_by_id(btf, 15);
+	ASSERT_EQ(btf_kind(t), BTF_KIND_FUNC_PROTO, "func_proto_kind");
+	ASSERT_EQ(btf_vlen(t), 2, "func_proto_vlen");
+	ASSERT_EQ(t->type, 1, "func_proto_ret_type");
+	p = btf_params(t) + 0;
+	ASSERT_STREQ(btf__str_by_offset(btf, p->name_off), "p1", "p1_name");
+	ASSERT_EQ(p->type, 1, "p1_type");
+	p = btf_params(t) + 1;
+	ASSERT_STREQ(btf__str_by_offset(btf, p->name_off), "p2", "p2_name");
+	ASSERT_EQ(p->type, 2, "p2_type");
+
+	/* VAR */
+	id = btf__add_var(btf, "var1", BTF_VAR_GLOBAL_ALLOCATED, 1);
+	ASSERT_EQ(id, 16, "var_id");
+	t = btf__type_by_id(btf, 16);
+	ASSERT_STREQ(btf__str_by_offset(btf, t->name_off), "var1", "var_name");
+	ASSERT_EQ(btf_kind(t), BTF_KIND_VAR, "var_kind");
+	ASSERT_EQ(t->type, 1, "var_type");
+	ASSERT_EQ(btf_var(t)->linkage, BTF_VAR_GLOBAL_ALLOCATED, "var_type");
+
+	/* DATASECT */
+	id = btf__add_datasec(btf, "datasec1", 12);
+	ASSERT_EQ(id, 17, "datasec_id");
+	err = btf__add_datasec_var_info(btf, 1, 4, 8);
+	ASSERT_OK(err, "v1_res");
+
+	t = btf__type_by_id(btf, 17);
+	ASSERT_STREQ(btf__str_by_offset(btf, t->name_off), "datasec1", "datasec_name");
+	ASSERT_EQ(t->size, 12, "datasec_sz");
+	ASSERT_EQ(btf_kind(t), BTF_KIND_DATASEC, "datasec_kind");
+	ASSERT_EQ(btf_vlen(t), 1, "datasec_vlen");
+	vi = btf_var_secinfos(t) + 0;
+	ASSERT_EQ(vi->type, 1, "v1_type");
+	ASSERT_EQ(vi->offset, 4, "v1_off");
+	ASSERT_EQ(vi->size, 8, "v1_sz");
+
+	btf__free(btf);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/cls_redirect.c b/tools/testing/selftests/bpf/prog_tests/cls_redirect.c
index f259085cca6a..9781d85cb223 100644
--- a/tools/testing/selftests/bpf/prog_tests/cls_redirect.c
+++ b/tools/testing/selftests/bpf/prog_tests/cls_redirect.c
@@ -12,10 +12,13 @@
 
 #include "progs/test_cls_redirect.h"
 #include "test_cls_redirect.skel.h"
+#include "test_cls_redirect_subprogs.skel.h"
 
 #define ENCAP_IP INADDR_LOOPBACK
 #define ENCAP_PORT (1234)
 
+static int duration = 0;
+
 struct addr_port {
 	in_port_t port;
 	union {
@@ -361,30 +364,18 @@ static void close_fds(int *fds, int n)
 			close(fds[i]);
 }
 
-void test_cls_redirect(void)
+static void test_cls_redirect_common(struct bpf_program *prog)
 {
-	struct test_cls_redirect *skel = NULL;
 	struct bpf_prog_test_run_attr tattr = {};
 	int families[] = { AF_INET, AF_INET6 };
 	struct sockaddr_storage ss;
 	struct sockaddr *addr;
 	socklen_t slen;
 	int i, j, err;
-
 	int servers[__NR_KIND][ARRAY_SIZE(families)] = {};
 	int conns[__NR_KIND][ARRAY_SIZE(families)] = {};
 	struct tuple tuples[__NR_KIND][ARRAY_SIZE(families)];
 
-	skel = test_cls_redirect__open();
-	if (CHECK_FAIL(!skel))
-		return;
-
-	skel->rodata->ENCAPSULATION_IP = htonl(ENCAP_IP);
-	skel->rodata->ENCAPSULATION_PORT = htons(ENCAP_PORT);
-
-	if (CHECK_FAIL(test_cls_redirect__load(skel)))
-		goto cleanup;
-
 	addr = (struct sockaddr *)&ss;
 	for (i = 0; i < ARRAY_SIZE(families); i++) {
 		slen = prepare_addr(&ss, families[i]);
@@ -402,7 +393,7 @@ void test_cls_redirect(void)
 			goto cleanup;
 	}
 
-	tattr.prog_fd = bpf_program__fd(skel->progs.cls_redirect);
+	tattr.prog_fd = bpf_program__fd(prog);
 	for (i = 0; i < ARRAY_SIZE(tests); i++) {
 		struct test_cfg *test = &tests[i];
 
@@ -450,7 +441,58 @@ void test_cls_redirect(void)
 	}
 
 cleanup:
-	test_cls_redirect__destroy(skel);
 	close_fds((int *)servers, sizeof(servers) / sizeof(servers[0][0]));
 	close_fds((int *)conns, sizeof(conns) / sizeof(conns[0][0]));
 }
+
+static void test_cls_redirect_inlined(void)
+{
+	struct test_cls_redirect *skel;
+	int err;
+
+	skel = test_cls_redirect__open();
+	if (CHECK(!skel, "skel_open", "failed\n"))
+		return;
+
+	skel->rodata->ENCAPSULATION_IP = htonl(ENCAP_IP);
+	skel->rodata->ENCAPSULATION_PORT = htons(ENCAP_PORT);
+
+	err = test_cls_redirect__load(skel);
+	if (CHECK(err, "skel_load", "failed: %d\n", err))
+		goto cleanup;
+
+	test_cls_redirect_common(skel->progs.cls_redirect);
+
+cleanup:
+	test_cls_redirect__destroy(skel);
+}
+
+static void test_cls_redirect_subprogs(void)
+{
+	struct test_cls_redirect_subprogs *skel;
+	int err;
+
+	skel = test_cls_redirect_subprogs__open();
+	if (CHECK(!skel, "skel_open", "failed\n"))
+		return;
+
+	skel->rodata->ENCAPSULATION_IP = htonl(ENCAP_IP);
+	skel->rodata->ENCAPSULATION_PORT = htons(ENCAP_PORT);
+
+	err = test_cls_redirect_subprogs__load(skel);
+	if (CHECK(err, "skel_load", "failed: %d\n", err))
+		goto cleanup;
+
+	test_cls_redirect_common(skel->progs.cls_redirect);
+
+cleanup:
+	test_cls_redirect_subprogs__destroy(skel);
+}
+
+void test_cls_redirect(void)
+{
+	if (test__start_subtest("cls_redirect_inlined"))
+		test_cls_redirect_inlined();
+	if (test__start_subtest("cls_redirect_subprogs"))
+		test_cls_redirect_subprogs();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/d_path.c b/tools/testing/selftests/bpf/prog_tests/d_path.c
index fc12e0d445ff..0a577a248d34 100644
--- a/tools/testing/selftests/bpf/prog_tests/d_path.c
+++ b/tools/testing/selftests/bpf/prog_tests/d_path.c
@@ -120,6 +120,16 @@ void test_d_path(void)
 	if (err < 0)
 		goto cleanup;
 
+	if (CHECK(!bss->called_stat,
+		  "stat",
+		  "trampoline for security_inode_getattr was not called\n"))
+		goto cleanup;
+
+	if (CHECK(!bss->called_close,
+		  "close",
+		  "trampoline for filp_close was not called\n"))
+		goto cleanup;
+
 	for (int i = 0; i < MAX_FILES; i++) {
 		CHECK(strncmp(src.paths[i], bss->paths_stat[i], MAX_PATH_LEN),
 		      "check",
diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
index a550dab9ba7a..5c0448910426 100644
--- a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
+++ b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
@@ -2,36 +2,79 @@
 /* Copyright (c) 2019 Facebook */
 #include <test_progs.h>
 #include <network_helpers.h>
+#include <bpf/btf.h>
+
+typedef int (*test_cb)(struct bpf_object *obj);
+
+static int check_data_map(struct bpf_object *obj, int prog_cnt, bool reset)
+{
+	struct bpf_map *data_map = NULL, *map;
+	__u64 *result = NULL;
+	const int zero = 0;
+	__u32 duration = 0;
+	int ret = -1, i;
+
+	result = malloc((prog_cnt + 32 /* spare */) * sizeof(__u64));
+	if (CHECK(!result, "alloc_memory", "failed to alloc memory"))
+		return -ENOMEM;
+
+	bpf_object__for_each_map(map, obj)
+		if (bpf_map__is_internal(map)) {
+			data_map = map;
+			break;
+		}
+	if (CHECK(!data_map, "find_data_map", "data map not found\n"))
+		goto out;
+
+	ret = bpf_map_lookup_elem(bpf_map__fd(data_map), &zero, result);
+	if (CHECK(ret, "get_result",
+		  "failed to get output data: %d\n", ret))
+		goto out;
+
+	for (i = 0; i < prog_cnt; i++) {
+		if (CHECK(result[i] != 1, "result",
+			  "fexit_bpf2bpf result[%d] failed err %llu\n",
+			  i, result[i]))
+			goto out;
+		result[i] = 0;
+	}
+	if (reset) {
+		ret = bpf_map_update_elem(bpf_map__fd(data_map), &zero, result, 0);
+		if (CHECK(ret, "reset_result", "failed to reset result\n"))
+			goto out;
+	}
+
+	ret = 0;
+out:
+	free(result);
+	return ret;
+}
 
 static void test_fexit_bpf2bpf_common(const char *obj_file,
 				      const char *target_obj_file,
 				      int prog_cnt,
 				      const char **prog_name,
-				      bool run_prog)
+				      bool run_prog,
+				      test_cb cb)
 {
-	struct bpf_object *obj = NULL, *pkt_obj;
-	int err, pkt_fd, i;
-	struct bpf_link **link = NULL;
+	struct bpf_object *obj = NULL, *tgt_obj;
 	struct bpf_program **prog = NULL;
+	struct bpf_link **link = NULL;
 	__u32 duration = 0, retval;
-	struct bpf_map *data_map;
-	const int zero = 0;
-	__u64 *result = NULL;
+	int err, tgt_fd, i;
 
 	err = bpf_prog_load(target_obj_file, BPF_PROG_TYPE_UNSPEC,
-			    &pkt_obj, &pkt_fd);
+			    &tgt_obj, &tgt_fd);
 	if (CHECK(err, "tgt_prog_load", "file %s err %d errno %d\n",
 		  target_obj_file, err, errno))
 		return;
 	DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts,
-			    .attach_prog_fd = pkt_fd,
+			    .attach_prog_fd = tgt_fd,
 			   );
 
 	link = calloc(sizeof(struct bpf_link *), prog_cnt);
 	prog = calloc(sizeof(struct bpf_program *), prog_cnt);
-	result = malloc((prog_cnt + 32 /* spare */) * sizeof(__u64));
-	if (CHECK(!link || !prog || !result, "alloc_memory",
-		  "failed to alloc memory"))
+	if (CHECK(!link || !prog, "alloc_memory", "failed to alloc memory"))
 		goto close_prog;
 
 	obj = bpf_object__open_file(obj_file, &opts);
@@ -53,39 +96,33 @@ static void test_fexit_bpf2bpf_common(const char *obj_file,
 			goto close_prog;
 	}
 
-	if (!run_prog)
-		goto close_prog;
+	if (cb) {
+		err = cb(obj);
+		if (err)
+			goto close_prog;
+	}
 
-	data_map = bpf_object__find_map_by_name(obj, "fexit_bp.bss");
-	if (CHECK(!data_map, "find_data_map", "data map not found\n"))
+	if (!run_prog)
 		goto close_prog;
 
-	err = bpf_prog_test_run(pkt_fd, 1, &pkt_v6, sizeof(pkt_v6),
+	err = bpf_prog_test_run(tgt_fd, 1, &pkt_v6, sizeof(pkt_v6),
 				NULL, NULL, &retval, &duration);
 	CHECK(err || retval, "ipv6",
 	      "err %d errno %d retval %d duration %d\n",
 	      err, errno, retval, duration);
 
-	err = bpf_map_lookup_elem(bpf_map__fd(data_map), &zero, result);
-	if (CHECK(err, "get_result",
-		  "failed to get output data: %d\n", err))
+	if (check_data_map(obj, prog_cnt, false))
 		goto close_prog;
 
-	for (i = 0; i < prog_cnt; i++)
-		if (CHECK(result[i] != 1, "result", "fexit_bpf2bpf failed err %llu\n",
-			  result[i]))
-			goto close_prog;
-
 close_prog:
 	for (i = 0; i < prog_cnt; i++)
 		if (!IS_ERR_OR_NULL(link[i]))
 			bpf_link__destroy(link[i]);
 	if (!IS_ERR_OR_NULL(obj))
 		bpf_object__close(obj);
-	bpf_object__close(pkt_obj);
+	bpf_object__close(tgt_obj);
 	free(link);
 	free(prog);
-	free(result);
 }
 
 static void test_target_no_callees(void)
@@ -96,7 +133,7 @@ static void test_target_no_callees(void)
 	test_fexit_bpf2bpf_common("./fexit_bpf2bpf_simple.o",
 				  "./test_pkt_md_access.o",
 				  ARRAY_SIZE(prog_name),
-				  prog_name, true);
+				  prog_name, true, NULL);
 }
 
 static void test_target_yes_callees(void)
@@ -110,7 +147,7 @@ static void test_target_yes_callees(void)
 	test_fexit_bpf2bpf_common("./fexit_bpf2bpf.o",
 				  "./test_pkt_access.o",
 				  ARRAY_SIZE(prog_name),
-				  prog_name, true);
+				  prog_name, true, NULL);
 }
 
 static void test_func_replace(void)
@@ -128,7 +165,7 @@ static void test_func_replace(void)
 	test_fexit_bpf2bpf_common("./fexit_bpf2bpf.o",
 				  "./test_pkt_access.o",
 				  ARRAY_SIZE(prog_name),
-				  prog_name, true);
+				  prog_name, true, NULL);
 }
 
 static void test_func_replace_verify(void)
@@ -139,9 +176,116 @@ static void test_func_replace_verify(void)
 	test_fexit_bpf2bpf_common("./freplace_connect4.o",
 				  "./connect4_prog.o",
 				  ARRAY_SIZE(prog_name),
-				  prog_name, false);
+				  prog_name, false, NULL);
 }
 
+static int test_second_attach(struct bpf_object *obj)
+{
+	const char *prog_name = "freplace/get_constant";
+	const char *tgt_name = prog_name + 9; /* cut off freplace/ */
+	const char *tgt_obj_file = "./test_pkt_access.o";
+	struct bpf_program *prog = NULL;
+	struct bpf_object *tgt_obj;
+	__u32 duration = 0, retval;
+	struct bpf_link *link;
+	int err = 0, tgt_fd;
+
+	prog = bpf_object__find_program_by_title(obj, prog_name);
+	if (CHECK(!prog, "find_prog", "prog %s not found\n", prog_name))
+		return -ENOENT;
+
+	err = bpf_prog_load(tgt_obj_file, BPF_PROG_TYPE_UNSPEC,
+			    &tgt_obj, &tgt_fd);
+	if (CHECK(err, "second_prog_load", "file %s err %d errno %d\n",
+		  tgt_obj_file, err, errno))
+		return err;
+
+	link = bpf_program__attach_freplace(prog, tgt_fd, tgt_name);
+	if (CHECK(IS_ERR(link), "second_link", "failed to attach second link prog_fd %d tgt_fd %d\n", bpf_program__fd(prog), tgt_fd))
+		goto out;
+
+	err = bpf_prog_test_run(tgt_fd, 1, &pkt_v6, sizeof(pkt_v6),
+				NULL, NULL, &retval, &duration);
+	if (CHECK(err || retval, "ipv6",
+		  "err %d errno %d retval %d duration %d\n",
+		  err, errno, retval, duration))
+		goto out;
+
+	err = check_data_map(obj, 1, true);
+	if (err)
+		goto out;
+
+out:
+	bpf_link__destroy(link);
+	bpf_object__close(tgt_obj);
+	return err;
+}
+
+static void test_func_replace_multi(void)
+{
+	const char *prog_name[] = {
+		"freplace/get_constant",
+	};
+	test_fexit_bpf2bpf_common("./freplace_get_constant.o",
+				  "./test_pkt_access.o",
+				  ARRAY_SIZE(prog_name),
+				  prog_name, true, test_second_attach);
+}
+
+static void test_fmod_ret_freplace(void)
+{
+	struct bpf_object *freplace_obj = NULL, *pkt_obj, *fmod_obj = NULL;
+	const char *freplace_name = "./freplace_get_constant.o";
+	const char *fmod_ret_name = "./fmod_ret_freplace.o";
+	DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts);
+	const char *tgt_name = "./test_pkt_access.o";
+	struct bpf_link *freplace_link = NULL;
+	struct bpf_program *prog;
+	__u32 duration = 0;
+	int err, pkt_fd;
+
+	err = bpf_prog_load(tgt_name, BPF_PROG_TYPE_UNSPEC,
+			    &pkt_obj, &pkt_fd);
+	/* the target prog should load fine */
+	if (CHECK(err, "tgt_prog_load", "file %s err %d errno %d\n",
+		  tgt_name, err, errno))
+		return;
+	opts.attach_prog_fd = pkt_fd;
+
+	freplace_obj = bpf_object__open_file(freplace_name, &opts);
+	if (CHECK(IS_ERR_OR_NULL(freplace_obj), "freplace_obj_open",
+		  "failed to open %s: %ld\n", freplace_name,
+		  PTR_ERR(freplace_obj)))
+		goto out;
+
+	err = bpf_object__load(freplace_obj);
+	if (CHECK(err, "freplace_obj_load", "err %d\n", err))
+		goto out;
+
+	prog = bpf_program__next(NULL, freplace_obj);
+	freplace_link = bpf_program__attach_trace(prog);
+	if (CHECK(IS_ERR(freplace_link), "freplace_attach_trace", "failed to link\n"))
+		goto out;
+
+	opts.attach_prog_fd = bpf_program__fd(prog);
+	fmod_obj = bpf_object__open_file(fmod_ret_name, &opts);
+	if (CHECK(IS_ERR_OR_NULL(fmod_obj), "fmod_obj_open",
+		  "failed to open %s: %ld\n", fmod_ret_name,
+		  PTR_ERR(fmod_obj)))
+		goto out;
+
+	err = bpf_object__load(fmod_obj);
+	if (CHECK(!err, "fmod_obj_load", "loading fmod_ret should fail\n"))
+		goto out;
+
+out:
+	bpf_link__destroy(freplace_link);
+	bpf_object__close(freplace_obj);
+	bpf_object__close(fmod_obj);
+	bpf_object__close(pkt_obj);
+}
+
+
 static void test_func_sockmap_update(void)
 {
 	const char *prog_name[] = {
@@ -150,7 +294,7 @@ static void test_func_sockmap_update(void)
 	test_fexit_bpf2bpf_common("./freplace_cls_redirect.o",
 				  "./test_cls_redirect.o",
 				  ARRAY_SIZE(prog_name),
-				  prog_name, false);
+				  prog_name, false, NULL);
 }
 
 static void test_obj_load_failure_common(const char *obj_file,
@@ -208,11 +352,22 @@ static void test_func_map_prog_compatibility(void)
 
 void test_fexit_bpf2bpf(void)
 {
-	test_target_no_callees();
-	test_target_yes_callees();
-	test_func_replace();
-	test_func_replace_verify();
-	test_func_sockmap_update();
-	test_func_replace_return_code();
-	test_func_map_prog_compatibility();
+	if (test__start_subtest("target_no_callees"))
+		test_target_no_callees();
+	if (test__start_subtest("target_yes_callees"))
+		test_target_yes_callees();
+	if (test__start_subtest("func_replace"))
+		test_func_replace();
+	if (test__start_subtest("func_replace_verify"))
+		test_func_replace_verify();
+	if (test__start_subtest("func_sockmap_update"))
+		test_func_sockmap_update();
+	if (test__start_subtest("func_replace_return_code"))
+		test_func_replace_return_code();
+	if (test__start_subtest("func_map_prog_compatibility"))
+		test_func_map_prog_compatibility();
+	if (test__start_subtest("func_replace_multi"))
+		test_func_replace_multi();
+	if (test__start_subtest("fmod_ret_freplace"))
+		test_fmod_ret_freplace();
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/global_data_init.c b/tools/testing/selftests/bpf/prog_tests/global_data_init.c
index 3bdaa5a40744..ee46b11f1f9a 100644
--- a/tools/testing/selftests/bpf/prog_tests/global_data_init.c
+++ b/tools/testing/selftests/bpf/prog_tests/global_data_init.c
@@ -12,7 +12,8 @@ void test_global_data_init(void)
 	size_t sz;
 
 	obj = bpf_object__open_file(file, NULL);
-	if (CHECK_FAIL(!obj))
+	err = libbpf_get_error(obj);
+	if (CHECK_FAIL(err))
 		return;
 
 	map = bpf_object__find_map_by_name(obj, "test_glo.rodata");
diff --git a/tools/testing/selftests/bpf/prog_tests/ksyms.c b/tools/testing/selftests/bpf/prog_tests/ksyms.c
index e3d6777226a8..b771804b2342 100644
--- a/tools/testing/selftests/bpf/prog_tests/ksyms.c
+++ b/tools/testing/selftests/bpf/prog_tests/ksyms.c
@@ -32,6 +32,7 @@ out:
 
 void test_ksyms(void)
 {
+	__u64 per_cpu_start_addr = kallsyms_find("__per_cpu_start");
 	__u64 link_fops_addr = kallsyms_find("bpf_link_fops");
 	const char *btf_path = "/sys/kernel/btf/vmlinux";
 	struct test_ksyms *skel;
@@ -63,8 +64,9 @@ void test_ksyms(void)
 	      "got %llu, exp %llu\n", data->out__bpf_link_fops1, (__u64)0);
 	CHECK(data->out__btf_size != btf_size, "btf_size",
 	      "got %llu, exp %llu\n", data->out__btf_size, btf_size);
-	CHECK(data->out__per_cpu_start != 0, "__per_cpu_start",
-	      "got %llu, exp %llu\n", data->out__per_cpu_start, (__u64)0);
+	CHECK(data->out__per_cpu_start != per_cpu_start_addr, "__per_cpu_start",
+	      "got %llu, exp %llu\n", data->out__per_cpu_start,
+	      per_cpu_start_addr);
 
 cleanup:
 	test_ksyms__destroy(skel);
diff --git a/tools/testing/selftests/bpf/prog_tests/l4lb_all.c b/tools/testing/selftests/bpf/prog_tests/l4lb_all.c
index c2d373e294bb..8073105548ff 100644
--- a/tools/testing/selftests/bpf/prog_tests/l4lb_all.c
+++ b/tools/testing/selftests/bpf/prog_tests/l4lb_all.c
@@ -80,9 +80,8 @@ out:
 
 void test_l4lb_all(void)
 {
-	const char *file1 = "./test_l4lb.o";
-	const char *file2 = "./test_l4lb_noinline.o";
-
-	test_l4lb(file1);
-	test_l4lb(file2);
+	if (test__start_subtest("l4lb_inline"))
+		test_l4lb("test_l4lb.o");
+	if (test__start_subtest("l4lb_noinline"))
+		test_l4lb("test_l4lb_noinline.o");
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/metadata.c b/tools/testing/selftests/bpf/prog_tests/metadata.c
new file mode 100644
index 000000000000..2c53eade88e3
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/metadata.c
@@ -0,0 +1,141 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+/*
+ * Copyright 2020 Google LLC.
+ */
+
+#include <test_progs.h>
+#include <cgroup_helpers.h>
+#include <network_helpers.h>
+
+#include "metadata_unused.skel.h"
+#include "metadata_used.skel.h"
+
+static int duration;
+
+static int prog_holds_map(int prog_fd, int map_fd)
+{
+	struct bpf_prog_info prog_info = {};
+	struct bpf_prog_info map_info = {};
+	__u32 prog_info_len;
+	__u32 map_info_len;
+	__u32 *map_ids;
+	int nr_maps;
+	int ret;
+	int i;
+
+	map_info_len = sizeof(map_info);
+	ret = bpf_obj_get_info_by_fd(map_fd, &map_info, &map_info_len);
+	if (ret)
+		return -errno;
+
+	prog_info_len = sizeof(prog_info);
+	ret = bpf_obj_get_info_by_fd(prog_fd, &prog_info, &prog_info_len);
+	if (ret)
+		return -errno;
+
+	map_ids = calloc(prog_info.nr_map_ids, sizeof(__u32));
+	if (!map_ids)
+		return -ENOMEM;
+
+	nr_maps = prog_info.nr_map_ids;
+	memset(&prog_info, 0, sizeof(prog_info));
+	prog_info.nr_map_ids = nr_maps;
+	prog_info.map_ids = ptr_to_u64(map_ids);
+	prog_info_len = sizeof(prog_info);
+
+	ret = bpf_obj_get_info_by_fd(prog_fd, &prog_info, &prog_info_len);
+	if (ret) {
+		ret = -errno;
+		goto free_map_ids;
+	}
+
+	ret = -ENOENT;
+	for (i = 0; i < prog_info.nr_map_ids; i++) {
+		if (map_ids[i] == map_info.id) {
+			ret = 0;
+			break;
+		}
+	}
+
+free_map_ids:
+	free(map_ids);
+	return ret;
+}
+
+static void test_metadata_unused(void)
+{
+	struct metadata_unused *obj;
+	int err;
+
+	obj = metadata_unused__open_and_load();
+	if (CHECK(!obj, "skel-load", "errno %d", errno))
+		return;
+
+	err = prog_holds_map(bpf_program__fd(obj->progs.prog),
+			     bpf_map__fd(obj->maps.rodata));
+	if (CHECK(err, "prog-holds-rodata", "errno: %d", err))
+		return;
+
+	/* Assert that we can access the metadata in skel and the values are
+	 * what we expect.
+	 */
+	if (CHECK(strncmp(obj->rodata->bpf_metadata_a, "foo",
+			  sizeof(obj->rodata->bpf_metadata_a)),
+		  "bpf_metadata_a", "expected \"foo\", value differ"))
+		goto close_bpf_object;
+	if (CHECK(obj->rodata->bpf_metadata_b != 1, "bpf_metadata_b",
+		  "expected 1, got %d", obj->rodata->bpf_metadata_b))
+		goto close_bpf_object;
+
+	/* Assert that binding metadata map to prog again succeeds. */
+	err = bpf_prog_bind_map(bpf_program__fd(obj->progs.prog),
+				bpf_map__fd(obj->maps.rodata), NULL);
+	CHECK(err, "rebind_map", "errno %d, expected 0", errno);
+
+close_bpf_object:
+	metadata_unused__destroy(obj);
+}
+
+static void test_metadata_used(void)
+{
+	struct metadata_used *obj;
+	int err;
+
+	obj = metadata_used__open_and_load();
+	if (CHECK(!obj, "skel-load", "errno %d", errno))
+		return;
+
+	err = prog_holds_map(bpf_program__fd(obj->progs.prog),
+			     bpf_map__fd(obj->maps.rodata));
+	if (CHECK(err, "prog-holds-rodata", "errno: %d", err))
+		return;
+
+	/* Assert that we can access the metadata in skel and the values are
+	 * what we expect.
+	 */
+	if (CHECK(strncmp(obj->rodata->bpf_metadata_a, "bar",
+			  sizeof(obj->rodata->bpf_metadata_a)),
+		  "metadata_a", "expected \"bar\", value differ"))
+		goto close_bpf_object;
+	if (CHECK(obj->rodata->bpf_metadata_b != 2, "metadata_b",
+		  "expected 2, got %d", obj->rodata->bpf_metadata_b))
+		goto close_bpf_object;
+
+	/* Assert that binding metadata map to prog again succeeds. */
+	err = bpf_prog_bind_map(bpf_program__fd(obj->progs.prog),
+				bpf_map__fd(obj->maps.rodata), NULL);
+	CHECK(err, "rebind_map", "errno %d, expected 0", errno);
+
+close_bpf_object:
+	metadata_used__destroy(obj);
+}
+
+void test_metadata(void)
+{
+	if (test__start_subtest("unused"))
+		test_metadata_unused();
+
+	if (test__start_subtest("used"))
+		test_metadata_used();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/pe_preserve_elems.c b/tools/testing/selftests/bpf/prog_tests/pe_preserve_elems.c
new file mode 100644
index 000000000000..673d38395253
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/pe_preserve_elems.c
@@ -0,0 +1,66 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2019 Facebook */
+#include <test_progs.h>
+#include <linux/bpf.h>
+#include "test_pe_preserve_elems.skel.h"
+
+static int duration;
+
+static void test_one_map(struct bpf_map *map, struct bpf_program *prog,
+			 bool has_share_pe)
+{
+	int err, key = 0, pfd = -1, mfd = bpf_map__fd(map);
+	DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts);
+	struct perf_event_attr attr = {
+		.size = sizeof(struct perf_event_attr),
+		.type = PERF_TYPE_SOFTWARE,
+		.config = PERF_COUNT_SW_CPU_CLOCK,
+	};
+
+	pfd = syscall(__NR_perf_event_open, &attr, 0 /* pid */,
+		      -1 /* cpu 0 */, -1 /* group id */, 0 /* flags */);
+	if (CHECK(pfd < 0, "perf_event_open", "failed\n"))
+		return;
+
+	err = bpf_map_update_elem(mfd, &key, &pfd, BPF_ANY);
+	close(pfd);
+	if (CHECK(err < 0, "bpf_map_update_elem", "failed\n"))
+		return;
+
+	err = bpf_prog_test_run_opts(bpf_program__fd(prog), &opts);
+	if (CHECK(err < 0, "bpf_prog_test_run_opts", "failed\n"))
+		return;
+	if (CHECK(opts.retval != 0, "bpf_perf_event_read_value",
+		  "failed with %d\n", opts.retval))
+		return;
+
+	/* closing mfd, prog still holds a reference on map */
+	close(mfd);
+
+	err = bpf_prog_test_run_opts(bpf_program__fd(prog), &opts);
+	if (CHECK(err < 0, "bpf_prog_test_run_opts", "failed\n"))
+		return;
+
+	if (has_share_pe) {
+		CHECK(opts.retval != 0, "bpf_perf_event_read_value",
+		      "failed with %d\n", opts.retval);
+	} else {
+		CHECK(opts.retval != -ENOENT, "bpf_perf_event_read_value",
+		      "should have failed with %d, but got %d\n", -ENOENT,
+		      opts.retval);
+	}
+}
+
+void test_pe_preserve_elems(void)
+{
+	struct test_pe_preserve_elems *skel;
+
+	skel = test_pe_preserve_elems__open_and_load();
+	if (CHECK(!skel, "skel_open", "failed to open skeleton\n"))
+		return;
+
+	test_one_map(skel->maps.array_1, skel->progs.read_array_1, false);
+	test_one_map(skel->maps.array_2, skel->progs.read_array_2, true);
+
+	test_pe_preserve_elems__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/raw_tp_test_run.c b/tools/testing/selftests/bpf/prog_tests/raw_tp_test_run.c
new file mode 100644
index 000000000000..c5fb191874ac
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/raw_tp_test_run.c
@@ -0,0 +1,96 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2019 Facebook */
+#include <test_progs.h>
+#include <linux/bpf.h>
+#include "bpf/libbpf_internal.h"
+#include "test_raw_tp_test_run.skel.h"
+
+static int duration;
+
+void test_raw_tp_test_run(void)
+{
+	struct bpf_prog_test_run_attr test_attr = {};
+	int comm_fd = -1, err, nr_online, i, prog_fd;
+	__u64 args[2] = {0x1234ULL, 0x5678ULL};
+	int expected_retval = 0x1234 + 0x5678;
+	struct test_raw_tp_test_run *skel;
+	char buf[] = "new_name";
+	bool *online = NULL;
+	DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts,
+			    .ctx_in = args,
+			    .ctx_size_in = sizeof(args),
+			    .flags = BPF_F_TEST_RUN_ON_CPU,
+		);
+
+	err = parse_cpu_mask_file("/sys/devices/system/cpu/online", &online,
+				  &nr_online);
+	if (CHECK(err, "parse_cpu_mask_file", "err %d\n", err))
+		return;
+
+	skel = test_raw_tp_test_run__open_and_load();
+	if (CHECK(!skel, "skel_open", "failed to open skeleton\n"))
+		goto cleanup;
+
+	err = test_raw_tp_test_run__attach(skel);
+	if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err))
+		goto cleanup;
+
+	comm_fd = open("/proc/self/comm", O_WRONLY|O_TRUNC);
+	if (CHECK(comm_fd < 0, "open /proc/self/comm", "err %d\n", errno))
+		goto cleanup;
+
+	err = write(comm_fd, buf, sizeof(buf));
+	CHECK(err < 0, "task rename", "err %d", errno);
+
+	CHECK(skel->bss->count == 0, "check_count", "didn't increase\n");
+	CHECK(skel->data->on_cpu != 0xffffffff, "check_on_cpu", "got wrong value\n");
+
+	prog_fd = bpf_program__fd(skel->progs.rename);
+	test_attr.prog_fd = prog_fd;
+	test_attr.ctx_in = args;
+	test_attr.ctx_size_in = sizeof(__u64);
+
+	err = bpf_prog_test_run_xattr(&test_attr);
+	CHECK(err == 0, "test_run", "should fail for too small ctx\n");
+
+	test_attr.ctx_size_in = sizeof(args);
+	err = bpf_prog_test_run_xattr(&test_attr);
+	CHECK(err < 0, "test_run", "err %d\n", errno);
+	CHECK(test_attr.retval != expected_retval, "check_retval",
+	      "expect 0x%x, got 0x%x\n", expected_retval, test_attr.retval);
+
+	for (i = 0; i < nr_online; i++) {
+		if (!online[i])
+			continue;
+
+		opts.cpu = i;
+		opts.retval = 0;
+		err = bpf_prog_test_run_opts(prog_fd, &opts);
+		CHECK(err < 0, "test_run_opts", "err %d\n", errno);
+		CHECK(skel->data->on_cpu != i, "check_on_cpu",
+		      "expect %d got %d\n", i, skel->data->on_cpu);
+		CHECK(opts.retval != expected_retval,
+		      "check_retval", "expect 0x%x, got 0x%x\n",
+		      expected_retval, opts.retval);
+	}
+
+	/* invalid cpu ID should fail with ENXIO */
+	opts.cpu = 0xffffffff;
+	err = bpf_prog_test_run_opts(prog_fd, &opts);
+	CHECK(err != -1 || errno != ENXIO,
+	      "test_run_opts_fail",
+	      "should failed with ENXIO\n");
+
+	/* non-zero cpu w/o BPF_F_TEST_RUN_ON_CPU should fail with EINVAL */
+	opts.cpu = 1;
+	opts.flags = 0;
+	err = bpf_prog_test_run_opts(prog_fd, &opts);
+	CHECK(err != -1 || errno != EINVAL,
+	      "test_run_opts_fail",
+	      "should failed with EINVAL\n");
+
+cleanup:
+	close(comm_fd);
+	test_raw_tp_test_run__destroy(skel);
+	free(online);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/reference_tracking.c b/tools/testing/selftests/bpf/prog_tests/reference_tracking.c
index fc0d7f4f02cf..ac1ee10cffd8 100644
--- a/tools/testing/selftests/bpf/prog_tests/reference_tracking.c
+++ b/tools/testing/selftests/bpf/prog_tests/reference_tracking.c
@@ -27,7 +27,7 @@ void test_reference_tracking(void)
 		const char *title;
 
 		/* Ignore .text sections */
-		title = bpf_program__title(prog, false);
+		title = bpf_program__section_name(prog);
 		if (strstr(title, ".text") != NULL)
 			continue;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c b/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c
index 8826c652adad..6ace5e9efec1 100644
--- a/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c
+++ b/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c
@@ -28,6 +28,12 @@ struct symbol test_symbols[] = {
 	{ "func",    BTF_KIND_FUNC,    -1 },
 };
 
+/* Align the .BTF_ids section to 4 bytes */
+asm (
+".pushsection " BTF_IDS_SECTION " ,\"a\"; \n"
+".balign 4, 0;                            \n"
+".popsection;                             \n");
+
 BTF_ID_LIST(test_list_local)
 BTF_ID_UNUSED
 BTF_ID(typedef, S)
diff --git a/tools/testing/selftests/bpf/prog_tests/sk_assign.c b/tools/testing/selftests/bpf/prog_tests/sk_assign.c
index a49a26f95a8b..3a469099f30d 100644
--- a/tools/testing/selftests/bpf/prog_tests/sk_assign.c
+++ b/tools/testing/selftests/bpf/prog_tests/sk_assign.c
@@ -265,7 +265,7 @@ void test_sk_assign(void)
 		TEST("ipv6 udp port redir", AF_INET6, SOCK_DGRAM, false),
 		TEST("ipv6 udp addr redir", AF_INET6, SOCK_DGRAM, true),
 	};
-	int server = -1;
+	__s64 server = -1;
 	int server_map;
 	int self_net;
 	int i;
diff --git a/tools/testing/selftests/bpf/prog_tests/snprintf_btf.c b/tools/testing/selftests/bpf/prog_tests/snprintf_btf.c
new file mode 100644
index 000000000000..686b40f11a45
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/snprintf_btf.c
@@ -0,0 +1,62 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include <linux/btf.h>
+#include "netif_receive_skb.skel.h"
+
+/* Demonstrate that bpf_snprintf_btf succeeds and that various data types
+ * are formatted correctly.
+ */
+void test_snprintf_btf(void)
+{
+	struct netif_receive_skb *skel;
+	struct netif_receive_skb__bss *bss;
+	int err, duration = 0;
+
+	skel = netif_receive_skb__open();
+	if (CHECK(!skel, "skel_open", "failed to open skeleton\n"))
+		return;
+
+	err = netif_receive_skb__load(skel);
+	if (CHECK(err, "skel_load", "failed to load skeleton: %d\n", err))
+		goto cleanup;
+
+	bss = skel->bss;
+
+	err = netif_receive_skb__attach(skel);
+	if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err))
+		goto cleanup;
+
+	/* generate receive event */
+	err = system("ping -c 1 127.0.0.1 > /dev/null");
+	if (CHECK(err, "system", "ping failed: %d\n", err))
+		goto cleanup;
+
+	if (bss->skip) {
+		printf("%s:SKIP:no __builtin_btf_type_id\n", __func__);
+		test__skip();
+		goto cleanup;
+	}
+
+	/*
+	 * Make sure netif_receive_skb program was triggered
+	 * and it set expected return values from bpf_trace_printk()s
+	 * and all tests ran.
+	 */
+	if (CHECK(bss->ret <= 0,
+		  "bpf_snprintf_btf: got return value",
+		  "ret <= 0 %ld test %d\n", bss->ret, bss->ran_subtests))
+		goto cleanup;
+
+	if (CHECK(bss->ran_subtests == 0, "check if subtests ran",
+		  "no subtests ran, did BPF program run?"))
+		goto cleanup;
+
+	if (CHECK(bss->num_subtests != bss->ran_subtests,
+		  "check all subtests ran",
+		  "only ran %d of %d tests\n", bss->num_subtests,
+		  bss->ran_subtests))
+		goto cleanup;
+
+cleanup:
+	netif_receive_skb__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/sock_fields.c b/tools/testing/selftests/bpf/prog_tests/sock_fields.c
new file mode 100644
index 000000000000..af87118e748e
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/sock_fields.c
@@ -0,0 +1,382 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019 Facebook */
+
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+#include <linux/compiler.h>
+
+#include "network_helpers.h"
+#include "cgroup_helpers.h"
+#include "test_progs.h"
+#include "bpf_rlimit.h"
+#include "test_sock_fields.skel.h"
+
+enum bpf_linum_array_idx {
+	EGRESS_LINUM_IDX,
+	INGRESS_LINUM_IDX,
+	__NR_BPF_LINUM_ARRAY_IDX,
+};
+
+struct bpf_spinlock_cnt {
+	struct bpf_spin_lock lock;
+	__u32 cnt;
+};
+
+#define PARENT_CGROUP	"/test-bpf-sock-fields"
+#define CHILD_CGROUP	"/test-bpf-sock-fields/child"
+#define DATA "Hello BPF!"
+#define DATA_LEN sizeof(DATA)
+
+static struct sockaddr_in6 srv_sa6, cli_sa6;
+static int sk_pkt_out_cnt10_fd;
+static struct test_sock_fields *skel;
+static int sk_pkt_out_cnt_fd;
+static __u64 parent_cg_id;
+static __u64 child_cg_id;
+static int linum_map_fd;
+static __u32 duration;
+
+static __u32 egress_linum_idx = EGRESS_LINUM_IDX;
+static __u32 ingress_linum_idx = INGRESS_LINUM_IDX;
+
+static void print_sk(const struct bpf_sock *sk, const char *prefix)
+{
+	char src_ip4[24], dst_ip4[24];
+	char src_ip6[64], dst_ip6[64];
+
+	inet_ntop(AF_INET, &sk->src_ip4, src_ip4, sizeof(src_ip4));
+	inet_ntop(AF_INET6, &sk->src_ip6, src_ip6, sizeof(src_ip6));
+	inet_ntop(AF_INET, &sk->dst_ip4, dst_ip4, sizeof(dst_ip4));
+	inet_ntop(AF_INET6, &sk->dst_ip6, dst_ip6, sizeof(dst_ip6));
+
+	printf("%s: state:%u bound_dev_if:%u family:%u type:%u protocol:%u mark:%u priority:%u "
+	       "src_ip4:%x(%s) src_ip6:%x:%x:%x:%x(%s) src_port:%u "
+	       "dst_ip4:%x(%s) dst_ip6:%x:%x:%x:%x(%s) dst_port:%u\n",
+	       prefix,
+	       sk->state, sk->bound_dev_if, sk->family, sk->type, sk->protocol,
+	       sk->mark, sk->priority,
+	       sk->src_ip4, src_ip4,
+	       sk->src_ip6[0], sk->src_ip6[1], sk->src_ip6[2], sk->src_ip6[3],
+	       src_ip6, sk->src_port,
+	       sk->dst_ip4, dst_ip4,
+	       sk->dst_ip6[0], sk->dst_ip6[1], sk->dst_ip6[2], sk->dst_ip6[3],
+	       dst_ip6, ntohs(sk->dst_port));
+}
+
+static void print_tp(const struct bpf_tcp_sock *tp, const char *prefix)
+{
+	printf("%s: snd_cwnd:%u srtt_us:%u rtt_min:%u snd_ssthresh:%u rcv_nxt:%u "
+	       "snd_nxt:%u snd:una:%u mss_cache:%u ecn_flags:%u "
+	       "rate_delivered:%u rate_interval_us:%u packets_out:%u "
+	       "retrans_out:%u total_retrans:%u segs_in:%u data_segs_in:%u "
+	       "segs_out:%u data_segs_out:%u lost_out:%u sacked_out:%u "
+	       "bytes_received:%llu bytes_acked:%llu\n",
+	       prefix,
+	       tp->snd_cwnd, tp->srtt_us, tp->rtt_min, tp->snd_ssthresh,
+	       tp->rcv_nxt, tp->snd_nxt, tp->snd_una, tp->mss_cache,
+	       tp->ecn_flags, tp->rate_delivered, tp->rate_interval_us,
+	       tp->packets_out, tp->retrans_out, tp->total_retrans,
+	       tp->segs_in, tp->data_segs_in, tp->segs_out,
+	       tp->data_segs_out, tp->lost_out, tp->sacked_out,
+	       tp->bytes_received, tp->bytes_acked);
+}
+
+static void check_result(void)
+{
+	struct bpf_tcp_sock srv_tp, cli_tp, listen_tp;
+	struct bpf_sock srv_sk, cli_sk, listen_sk;
+	__u32 ingress_linum, egress_linum;
+	int err;
+
+	err = bpf_map_lookup_elem(linum_map_fd, &egress_linum_idx,
+				  &egress_linum);
+	CHECK(err == -1, "bpf_map_lookup_elem(linum_map_fd)",
+	      "err:%d errno:%d\n", err, errno);
+
+	err = bpf_map_lookup_elem(linum_map_fd, &ingress_linum_idx,
+				  &ingress_linum);
+	CHECK(err == -1, "bpf_map_lookup_elem(linum_map_fd)",
+	      "err:%d errno:%d\n", err, errno);
+
+	memcpy(&srv_sk, &skel->bss->srv_sk, sizeof(srv_sk));
+	memcpy(&srv_tp, &skel->bss->srv_tp, sizeof(srv_tp));
+	memcpy(&cli_sk, &skel->bss->cli_sk, sizeof(cli_sk));
+	memcpy(&cli_tp, &skel->bss->cli_tp, sizeof(cli_tp));
+	memcpy(&listen_sk, &skel->bss->listen_sk, sizeof(listen_sk));
+	memcpy(&listen_tp, &skel->bss->listen_tp, sizeof(listen_tp));
+
+	print_sk(&listen_sk, "listen_sk");
+	print_sk(&srv_sk, "srv_sk");
+	print_sk(&cli_sk, "cli_sk");
+	print_tp(&listen_tp, "listen_tp");
+	print_tp(&srv_tp, "srv_tp");
+	print_tp(&cli_tp, "cli_tp");
+
+	CHECK(listen_sk.state != 10 ||
+	      listen_sk.family != AF_INET6 ||
+	      listen_sk.protocol != IPPROTO_TCP ||
+	      memcmp(listen_sk.src_ip6, &in6addr_loopback,
+		     sizeof(listen_sk.src_ip6)) ||
+	      listen_sk.dst_ip6[0] || listen_sk.dst_ip6[1] ||
+	      listen_sk.dst_ip6[2] || listen_sk.dst_ip6[3] ||
+	      listen_sk.src_port != ntohs(srv_sa6.sin6_port) ||
+	      listen_sk.dst_port,
+	      "listen_sk",
+	      "Unexpected. Check listen_sk output. ingress_linum:%u\n",
+	      ingress_linum);
+
+	CHECK(srv_sk.state == 10 ||
+	      !srv_sk.state ||
+	      srv_sk.family != AF_INET6 ||
+	      srv_sk.protocol != IPPROTO_TCP ||
+	      memcmp(srv_sk.src_ip6, &in6addr_loopback,
+		     sizeof(srv_sk.src_ip6)) ||
+	      memcmp(srv_sk.dst_ip6, &in6addr_loopback,
+		     sizeof(srv_sk.dst_ip6)) ||
+	      srv_sk.src_port != ntohs(srv_sa6.sin6_port) ||
+	      srv_sk.dst_port != cli_sa6.sin6_port,
+	      "srv_sk", "Unexpected. Check srv_sk output. egress_linum:%u\n",
+	      egress_linum);
+
+	CHECK(!skel->bss->lsndtime, "srv_tp", "Unexpected lsndtime:0\n");
+
+	CHECK(cli_sk.state == 10 ||
+	      !cli_sk.state ||
+	      cli_sk.family != AF_INET6 ||
+	      cli_sk.protocol != IPPROTO_TCP ||
+	      memcmp(cli_sk.src_ip6, &in6addr_loopback,
+		     sizeof(cli_sk.src_ip6)) ||
+	      memcmp(cli_sk.dst_ip6, &in6addr_loopback,
+		     sizeof(cli_sk.dst_ip6)) ||
+	      cli_sk.src_port != ntohs(cli_sa6.sin6_port) ||
+	      cli_sk.dst_port != srv_sa6.sin6_port,
+	      "cli_sk", "Unexpected. Check cli_sk output. egress_linum:%u\n",
+	      egress_linum);
+
+	CHECK(listen_tp.data_segs_out ||
+	      listen_tp.data_segs_in ||
+	      listen_tp.total_retrans ||
+	      listen_tp.bytes_acked,
+	      "listen_tp",
+	      "Unexpected. Check listen_tp output. ingress_linum:%u\n",
+	      ingress_linum);
+
+	CHECK(srv_tp.data_segs_out != 2 ||
+	      srv_tp.data_segs_in ||
+	      srv_tp.snd_cwnd != 10 ||
+	      srv_tp.total_retrans ||
+	      srv_tp.bytes_acked < 2 * DATA_LEN,
+	      "srv_tp", "Unexpected. Check srv_tp output. egress_linum:%u\n",
+	      egress_linum);
+
+	CHECK(cli_tp.data_segs_out ||
+	      cli_tp.data_segs_in != 2 ||
+	      cli_tp.snd_cwnd != 10 ||
+	      cli_tp.total_retrans ||
+	      cli_tp.bytes_received < 2 * DATA_LEN,
+	      "cli_tp", "Unexpected. Check cli_tp output. egress_linum:%u\n",
+	      egress_linum);
+
+	CHECK(skel->bss->parent_cg_id != parent_cg_id,
+	      "parent_cg_id", "%zu != %zu\n",
+	      (size_t)skel->bss->parent_cg_id, (size_t)parent_cg_id);
+
+	CHECK(skel->bss->child_cg_id != child_cg_id,
+	      "child_cg_id", "%zu != %zu\n",
+	       (size_t)skel->bss->child_cg_id, (size_t)child_cg_id);
+}
+
+static void check_sk_pkt_out_cnt(int accept_fd, int cli_fd)
+{
+	struct bpf_spinlock_cnt pkt_out_cnt = {}, pkt_out_cnt10 = {};
+	int err;
+
+	pkt_out_cnt.cnt = ~0;
+	pkt_out_cnt10.cnt = ~0;
+	err = bpf_map_lookup_elem(sk_pkt_out_cnt_fd, &accept_fd, &pkt_out_cnt);
+	if (!err)
+		err = bpf_map_lookup_elem(sk_pkt_out_cnt10_fd, &accept_fd,
+					  &pkt_out_cnt10);
+
+	/* The bpf prog only counts for fullsock and
+	 * passive connection did not become fullsock until 3WHS
+	 * had been finished, so the bpf prog only counted two data
+	 * packet out.
+	 */
+	CHECK(err || pkt_out_cnt.cnt < 0xeB9F + 2 ||
+	      pkt_out_cnt10.cnt < 0xeB9F + 20,
+	      "bpf_map_lookup_elem(sk_pkt_out_cnt, &accept_fd)",
+	      "err:%d errno:%d pkt_out_cnt:%u pkt_out_cnt10:%u\n",
+	      err, errno, pkt_out_cnt.cnt, pkt_out_cnt10.cnt);
+
+	pkt_out_cnt.cnt = ~0;
+	pkt_out_cnt10.cnt = ~0;
+	err = bpf_map_lookup_elem(sk_pkt_out_cnt_fd, &cli_fd, &pkt_out_cnt);
+	if (!err)
+		err = bpf_map_lookup_elem(sk_pkt_out_cnt10_fd, &cli_fd,
+					  &pkt_out_cnt10);
+	/* Active connection is fullsock from the beginning.
+	 * 1 SYN and 1 ACK during 3WHS
+	 * 2 Acks on data packet.
+	 *
+	 * The bpf_prog initialized it to 0xeB9F.
+	 */
+	CHECK(err || pkt_out_cnt.cnt < 0xeB9F + 4 ||
+	      pkt_out_cnt10.cnt < 0xeB9F + 40,
+	      "bpf_map_lookup_elem(sk_pkt_out_cnt, &cli_fd)",
+	      "err:%d errno:%d pkt_out_cnt:%u pkt_out_cnt10:%u\n",
+	      err, errno, pkt_out_cnt.cnt, pkt_out_cnt10.cnt);
+}
+
+static int init_sk_storage(int sk_fd, __u32 pkt_out_cnt)
+{
+	struct bpf_spinlock_cnt scnt = {};
+	int err;
+
+	scnt.cnt = pkt_out_cnt;
+	err = bpf_map_update_elem(sk_pkt_out_cnt_fd, &sk_fd, &scnt,
+				  BPF_NOEXIST);
+	if (CHECK(err, "bpf_map_update_elem(sk_pkt_out_cnt_fd)",
+		  "err:%d errno:%d\n", err, errno))
+		return err;
+
+	err = bpf_map_update_elem(sk_pkt_out_cnt10_fd, &sk_fd, &scnt,
+				  BPF_NOEXIST);
+	if (CHECK(err, "bpf_map_update_elem(sk_pkt_out_cnt10_fd)",
+		  "err:%d errno:%d\n", err, errno))
+		return err;
+
+	return 0;
+}
+
+static void test(void)
+{
+	int listen_fd = -1, cli_fd = -1, accept_fd = -1, err, i;
+	socklen_t addrlen = sizeof(struct sockaddr_in6);
+	char buf[DATA_LEN];
+
+	/* Prepare listen_fd */
+	listen_fd = start_server(AF_INET6, SOCK_STREAM, "::1", 0, 0);
+	/* start_server() has logged the error details */
+	if (CHECK_FAIL(listen_fd == -1))
+		goto done;
+
+	err = getsockname(listen_fd, (struct sockaddr *)&srv_sa6, &addrlen);
+	if (CHECK(err, "getsockname(listen_fd)", "err:%d errno:%d\n", err,
+		  errno))
+		goto done;
+	memcpy(&skel->bss->srv_sa6, &srv_sa6, sizeof(srv_sa6));
+
+	cli_fd = connect_to_fd(listen_fd, 0);
+	if (CHECK_FAIL(cli_fd == -1))
+		goto done;
+
+	err = getsockname(cli_fd, (struct sockaddr *)&cli_sa6, &addrlen);
+	if (CHECK(err, "getsockname(cli_fd)", "err:%d errno:%d\n",
+		  err, errno))
+		goto done;
+
+	accept_fd = accept(listen_fd, NULL, NULL);
+	if (CHECK(accept_fd == -1, "accept(listen_fd)",
+		  "accept_fd:%d errno:%d\n",
+		  accept_fd, errno))
+		goto done;
+
+	if (init_sk_storage(accept_fd, 0xeB9F))
+		goto done;
+
+	for (i = 0; i < 2; i++) {
+		/* Send some data from accept_fd to cli_fd.
+		 * MSG_EOR to stop kernel from coalescing two pkts.
+		 */
+		err = send(accept_fd, DATA, DATA_LEN, MSG_EOR);
+		if (CHECK(err != DATA_LEN, "send(accept_fd)",
+			  "err:%d errno:%d\n", err, errno))
+			goto done;
+
+		err = recv(cli_fd, buf, DATA_LEN, 0);
+		if (CHECK(err != DATA_LEN, "recv(cli_fd)", "err:%d errno:%d\n",
+			  err, errno))
+			goto done;
+	}
+
+	shutdown(cli_fd, SHUT_WR);
+	err = recv(accept_fd, buf, 1, 0);
+	if (CHECK(err, "recv(accept_fd) for fin", "err:%d errno:%d\n",
+		  err, errno))
+		goto done;
+	shutdown(accept_fd, SHUT_WR);
+	err = recv(cli_fd, buf, 1, 0);
+	if (CHECK(err, "recv(cli_fd) for fin", "err:%d errno:%d\n",
+		  err, errno))
+		goto done;
+	check_sk_pkt_out_cnt(accept_fd, cli_fd);
+	check_result();
+
+done:
+	if (accept_fd != -1)
+		close(accept_fd);
+	if (cli_fd != -1)
+		close(cli_fd);
+	if (listen_fd != -1)
+		close(listen_fd);
+}
+
+void test_sock_fields(void)
+{
+	struct bpf_link *egress_link = NULL, *ingress_link = NULL;
+	int parent_cg_fd = -1, child_cg_fd = -1;
+
+	/* Create a cgroup, get fd, and join it */
+	parent_cg_fd = test__join_cgroup(PARENT_CGROUP);
+	if (CHECK_FAIL(parent_cg_fd < 0))
+		return;
+	parent_cg_id = get_cgroup_id(PARENT_CGROUP);
+	if (CHECK_FAIL(!parent_cg_id))
+		goto done;
+
+	child_cg_fd = test__join_cgroup(CHILD_CGROUP);
+	if (CHECK_FAIL(child_cg_fd < 0))
+		goto done;
+	child_cg_id = get_cgroup_id(CHILD_CGROUP);
+	if (CHECK_FAIL(!child_cg_id))
+		goto done;
+
+	skel = test_sock_fields__open_and_load();
+	if (CHECK(!skel, "test_sock_fields__open_and_load", "failed\n"))
+		goto done;
+
+	egress_link = bpf_program__attach_cgroup(skel->progs.egress_read_sock_fields,
+						 child_cg_fd);
+	if (CHECK(IS_ERR(egress_link), "attach_cgroup(egress)", "err:%ld\n",
+		  PTR_ERR(egress_link)))
+		goto done;
+
+	ingress_link = bpf_program__attach_cgroup(skel->progs.ingress_read_sock_fields,
+						  child_cg_fd);
+	if (CHECK(IS_ERR(ingress_link), "attach_cgroup(ingress)", "err:%ld\n",
+		  PTR_ERR(ingress_link)))
+		goto done;
+
+	linum_map_fd = bpf_map__fd(skel->maps.linum_map);
+	sk_pkt_out_cnt_fd = bpf_map__fd(skel->maps.sk_pkt_out_cnt);
+	sk_pkt_out_cnt10_fd = bpf_map__fd(skel->maps.sk_pkt_out_cnt10);
+
+	test();
+
+done:
+	bpf_link__destroy(egress_link);
+	bpf_link__destroy(ingress_link);
+	test_sock_fields__destroy(skel);
+	if (child_cg_fd != -1)
+		close(child_cg_fd);
+	if (parent_cg_fd != -1)
+		close(parent_cg_fd);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
index 0b79d78b98db..4c4224e3e10a 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
@@ -6,6 +6,7 @@
 #include "test_skmsg_load_helpers.skel.h"
 #include "test_sockmap_update.skel.h"
 #include "test_sockmap_invalid_update.skel.h"
+#include "bpf_iter_sockmap.skel.h"
 
 #define TCP_REPAIR		19	/* TCP sock is under repair right now */
 
@@ -47,6 +48,37 @@ error:
 	return -1;
 }
 
+static void compare_cookies(struct bpf_map *src, struct bpf_map *dst)
+{
+	__u32 i, max_entries = bpf_map__max_entries(src);
+	int err, duration = 0, src_fd, dst_fd;
+
+	src_fd = bpf_map__fd(src);
+	dst_fd = bpf_map__fd(dst);
+
+	for (i = 0; i < max_entries; i++) {
+		__u64 src_cookie, dst_cookie;
+
+		err = bpf_map_lookup_elem(src_fd, &i, &src_cookie);
+		if (err && errno == ENOENT) {
+			err = bpf_map_lookup_elem(dst_fd, &i, &dst_cookie);
+			CHECK(!err, "map_lookup_elem(dst)", "element %u not deleted\n", i);
+			CHECK(err && errno != ENOENT, "map_lookup_elem(dst)", "%s\n",
+			      strerror(errno));
+			continue;
+		}
+		if (CHECK(err, "lookup_elem(src)", "%s\n", strerror(errno)))
+			continue;
+
+		err = bpf_map_lookup_elem(dst_fd, &i, &dst_cookie);
+		if (CHECK(err, "lookup_elem(dst)", "%s\n", strerror(errno)))
+			continue;
+
+		CHECK(dst_cookie != src_cookie, "cookie mismatch",
+		      "%llu != %llu (pos %u)\n", dst_cookie, src_cookie, i);
+	}
+}
+
 /* Create a map, populate it with one socket, and free the map. */
 static void test_sockmap_create_update_free(enum bpf_map_type map_type)
 {
@@ -106,9 +138,9 @@ out:
 static void test_sockmap_update(enum bpf_map_type map_type)
 {
 	struct bpf_prog_test_run_attr tattr;
-	int err, prog, src, dst, duration = 0;
+	int err, prog, src, duration = 0;
 	struct test_sockmap_update *skel;
-	__u64 src_cookie, dst_cookie;
+	struct bpf_map *dst_map;
 	const __u32 zero = 0;
 	char dummy[14] = {0};
 	__s64 sk;
@@ -124,18 +156,14 @@ static void test_sockmap_update(enum bpf_map_type map_type)
 	prog = bpf_program__fd(skel->progs.copy_sock_map);
 	src = bpf_map__fd(skel->maps.src);
 	if (map_type == BPF_MAP_TYPE_SOCKMAP)
-		dst = bpf_map__fd(skel->maps.dst_sock_map);
+		dst_map = skel->maps.dst_sock_map;
 	else
-		dst = bpf_map__fd(skel->maps.dst_sock_hash);
+		dst_map = skel->maps.dst_sock_hash;
 
 	err = bpf_map_update_elem(src, &zero, &sk, BPF_NOEXIST);
 	if (CHECK(err, "update_elem(src)", "errno=%u\n", errno))
 		goto out;
 
-	err = bpf_map_lookup_elem(src, &zero, &src_cookie);
-	if (CHECK(err, "lookup_elem(src, cookie)", "errno=%u\n", errno))
-		goto out;
-
 	tattr = (struct bpf_prog_test_run_attr){
 		.prog_fd = prog,
 		.repeat = 1,
@@ -148,12 +176,7 @@ static void test_sockmap_update(enum bpf_map_type map_type)
 		       "errno=%u retval=%u\n", errno, tattr.retval))
 		goto out;
 
-	err = bpf_map_lookup_elem(dst, &zero, &dst_cookie);
-	if (CHECK(err, "lookup_elem(dst, cookie)", "errno=%u\n", errno))
-		goto out;
-
-	CHECK(dst_cookie != src_cookie, "cookie mismatch", "%llu != %llu\n",
-	      dst_cookie, src_cookie);
+	compare_cookies(skel->maps.src, dst_map);
 
 out:
 	test_sockmap_update__destroy(skel);
@@ -171,6 +194,92 @@ static void test_sockmap_invalid_update(void)
 		test_sockmap_invalid_update__destroy(skel);
 }
 
+static void test_sockmap_copy(enum bpf_map_type map_type)
+{
+	DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts);
+	int err, len, src_fd, iter_fd, duration = 0;
+	union bpf_iter_link_info linfo = {0};
+	__u32 i, num_sockets, num_elems;
+	struct bpf_iter_sockmap *skel;
+	__s64 *sock_fd = NULL;
+	struct bpf_link *link;
+	struct bpf_map *src;
+	char buf[64];
+
+	skel = bpf_iter_sockmap__open_and_load();
+	if (CHECK(!skel, "bpf_iter_sockmap__open_and_load", "skeleton open_and_load failed\n"))
+		return;
+
+	if (map_type == BPF_MAP_TYPE_SOCKMAP) {
+		src = skel->maps.sockmap;
+		num_elems = bpf_map__max_entries(src);
+		num_sockets = num_elems - 1;
+	} else {
+		src = skel->maps.sockhash;
+		num_elems = bpf_map__max_entries(src) - 1;
+		num_sockets = num_elems;
+	}
+
+	sock_fd = calloc(num_sockets, sizeof(*sock_fd));
+	if (CHECK(!sock_fd, "calloc(sock_fd)", "failed to allocate\n"))
+		goto out;
+
+	for (i = 0; i < num_sockets; i++)
+		sock_fd[i] = -1;
+
+	src_fd = bpf_map__fd(src);
+
+	for (i = 0; i < num_sockets; i++) {
+		sock_fd[i] = connected_socket_v4();
+		if (CHECK(sock_fd[i] == -1, "connected_socket_v4", "cannot connect\n"))
+			goto out;
+
+		err = bpf_map_update_elem(src_fd, &i, &sock_fd[i], BPF_NOEXIST);
+		if (CHECK(err, "map_update", "failed: %s\n", strerror(errno)))
+			goto out;
+	}
+
+	linfo.map.map_fd = src_fd;
+	opts.link_info = &linfo;
+	opts.link_info_len = sizeof(linfo);
+	link = bpf_program__attach_iter(skel->progs.copy, &opts);
+	if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n"))
+		goto out;
+
+	iter_fd = bpf_iter_create(bpf_link__fd(link));
+	if (CHECK(iter_fd < 0, "create_iter", "create_iter failed\n"))
+		goto free_link;
+
+	/* do some tests */
+	while ((len = read(iter_fd, buf, sizeof(buf))) > 0)
+		;
+	if (CHECK(len < 0, "read", "failed: %s\n", strerror(errno)))
+		goto close_iter;
+
+	/* test results */
+	if (CHECK(skel->bss->elems != num_elems, "elems", "got %u expected %u\n",
+		  skel->bss->elems, num_elems))
+		goto close_iter;
+
+	if (CHECK(skel->bss->socks != num_sockets, "socks", "got %u expected %u\n",
+		  skel->bss->socks, num_sockets))
+		goto close_iter;
+
+	compare_cookies(src, skel->maps.dst);
+
+close_iter:
+	close(iter_fd);
+free_link:
+	bpf_link__destroy(link);
+out:
+	for (i = 0; sock_fd && i < num_sockets; i++)
+		if (sock_fd[i] >= 0)
+			close(sock_fd[i]);
+	if (sock_fd)
+		free(sock_fd);
+	bpf_iter_sockmap__destroy(skel);
+}
+
 void test_sockmap_basic(void)
 {
 	if (test__start_subtest("sockmap create_update_free"))
@@ -187,4 +296,8 @@ void test_sockmap_basic(void)
 		test_sockmap_update(BPF_MAP_TYPE_SOCKHASH);
 	if (test__start_subtest("sockmap update in unsafe context"))
 		test_sockmap_invalid_update();
+	if (test__start_subtest("sockmap copy"))
+		test_sockmap_copy(BPF_MAP_TYPE_SOCKMAP);
+	if (test__start_subtest("sockhash copy"))
+		test_sockmap_copy(BPF_MAP_TYPE_SOCKHASH);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c
index 5f54c6aec7f0..b25c9c45c148 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c
@@ -45,9 +45,9 @@ static int getsetsockopt(void)
 		goto err;
 	}
 
-	if (*(int *)big_buf != 0x08) {
+	if (*big_buf != 0x08) {
 		log_err("Unexpected getsockopt(IP_TOS) optval 0x%x != 0x08",
-			*(int *)big_buf);
+			(int)*big_buf);
 		goto err;
 	}
 
diff --git a/tools/testing/selftests/bpf/prog_tests/subprogs.c b/tools/testing/selftests/bpf/prog_tests/subprogs.c
new file mode 100644
index 000000000000..a00abf58c037
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/subprogs.c
@@ -0,0 +1,31 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#include <test_progs.h>
+#include <time.h>
+#include "test_subprogs.skel.h"
+
+static int duration;
+
+void test_subprogs(void)
+{
+	struct test_subprogs *skel;
+	int err;
+
+	skel = test_subprogs__open_and_load();
+	if (CHECK(!skel, "skel_open", "failed to open skeleton\n"))
+		return;
+
+	err = test_subprogs__attach(skel);
+	if (CHECK(err, "skel_attach", "failed to attach skeleton: %d\n", err))
+		goto cleanup;
+
+	usleep(1);
+
+	CHECK(skel->bss->res1 != 12, "res1", "got %d, exp %d\n", skel->bss->res1, 12);
+	CHECK(skel->bss->res2 != 17, "res2", "got %d, exp %d\n", skel->bss->res2, 17);
+	CHECK(skel->bss->res3 != 19, "res3", "got %d, exp %d\n", skel->bss->res3, 19);
+	CHECK(skel->bss->res4 != 36, "res4", "got %d, exp %d\n", skel->bss->res4, 36);
+
+cleanup:
+	test_subprogs__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/tailcalls.c b/tools/testing/selftests/bpf/prog_tests/tailcalls.c
index bb8fe646dd9f..ee27d68d2a1c 100644
--- a/tools/testing/selftests/bpf/prog_tests/tailcalls.c
+++ b/tools/testing/selftests/bpf/prog_tests/tailcalls.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
+#include <network_helpers.h>
 
 /* test_tailcall_1 checks basic functionality by patching multiple locations
  * in a single program for a single tail call slot with nop->jmp, jmp->nop
@@ -472,6 +473,329 @@ out:
 	bpf_object__close(obj);
 }
 
+/* test_tailcall_bpf2bpf_1 purpose is to make sure that tailcalls are working
+ * correctly in correlation with BPF subprograms
+ */
+static void test_tailcall_bpf2bpf_1(void)
+{
+	int err, map_fd, prog_fd, main_fd, i;
+	struct bpf_map *prog_array;
+	struct bpf_program *prog;
+	struct bpf_object *obj;
+	__u32 retval, duration;
+	char prog_name[32];
+
+	err = bpf_prog_load("tailcall_bpf2bpf1.o", BPF_PROG_TYPE_SCHED_CLS,
+			    &obj, &prog_fd);
+	if (CHECK_FAIL(err))
+		return;
+
+	prog = bpf_object__find_program_by_title(obj, "classifier");
+	if (CHECK_FAIL(!prog))
+		goto out;
+
+	main_fd = bpf_program__fd(prog);
+	if (CHECK_FAIL(main_fd < 0))
+		goto out;
+
+	prog_array = bpf_object__find_map_by_name(obj, "jmp_table");
+	if (CHECK_FAIL(!prog_array))
+		goto out;
+
+	map_fd = bpf_map__fd(prog_array);
+	if (CHECK_FAIL(map_fd < 0))
+		goto out;
+
+	/* nop -> jmp */
+	for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) {
+		snprintf(prog_name, sizeof(prog_name), "classifier/%i", i);
+
+		prog = bpf_object__find_program_by_title(obj, prog_name);
+		if (CHECK_FAIL(!prog))
+			goto out;
+
+		prog_fd = bpf_program__fd(prog);
+		if (CHECK_FAIL(prog_fd < 0))
+			goto out;
+
+		err = bpf_map_update_elem(map_fd, &i, &prog_fd, BPF_ANY);
+		if (CHECK_FAIL(err))
+			goto out;
+	}
+
+	err = bpf_prog_test_run(main_fd, 1, &pkt_v4, sizeof(pkt_v4), 0,
+				0, &retval, &duration);
+	CHECK(err || retval != 1, "tailcall",
+	      "err %d errno %d retval %d\n", err, errno, retval);
+
+	/* jmp -> nop, call subprog that will do tailcall */
+	i = 1;
+	err = bpf_map_delete_elem(map_fd, &i);
+	if (CHECK_FAIL(err))
+		goto out;
+
+	err = bpf_prog_test_run(main_fd, 1, &pkt_v4, sizeof(pkt_v4), 0,
+				0, &retval, &duration);
+	CHECK(err || retval != 0, "tailcall", "err %d errno %d retval %d\n",
+	      err, errno, retval);
+
+	/* make sure that subprog can access ctx and entry prog that
+	 * called this subprog can properly return
+	 */
+	i = 0;
+	err = bpf_map_delete_elem(map_fd, &i);
+	if (CHECK_FAIL(err))
+		goto out;
+
+	err = bpf_prog_test_run(main_fd, 1, &pkt_v4, sizeof(pkt_v4), 0,
+				0, &retval, &duration);
+	CHECK(err || retval != sizeof(pkt_v4) * 2,
+	      "tailcall", "err %d errno %d retval %d\n",
+	      err, errno, retval);
+out:
+	bpf_object__close(obj);
+}
+
+/* test_tailcall_bpf2bpf_2 checks that the count value of the tail call limit
+ * enforcement matches with expectations when tailcall is preceded with
+ * bpf2bpf call.
+ */
+static void test_tailcall_bpf2bpf_2(void)
+{
+	int err, map_fd, prog_fd, main_fd, data_fd, i, val;
+	struct bpf_map *prog_array, *data_map;
+	struct bpf_program *prog;
+	struct bpf_object *obj;
+	__u32 retval, duration;
+	char buff[128] = {};
+
+	err = bpf_prog_load("tailcall_bpf2bpf2.o", BPF_PROG_TYPE_SCHED_CLS,
+			    &obj, &prog_fd);
+	if (CHECK_FAIL(err))
+		return;
+
+	prog = bpf_object__find_program_by_title(obj, "classifier");
+	if (CHECK_FAIL(!prog))
+		goto out;
+
+	main_fd = bpf_program__fd(prog);
+	if (CHECK_FAIL(main_fd < 0))
+		goto out;
+
+	prog_array = bpf_object__find_map_by_name(obj, "jmp_table");
+	if (CHECK_FAIL(!prog_array))
+		goto out;
+
+	map_fd = bpf_map__fd(prog_array);
+	if (CHECK_FAIL(map_fd < 0))
+		goto out;
+
+	prog = bpf_object__find_program_by_title(obj, "classifier/0");
+	if (CHECK_FAIL(!prog))
+		goto out;
+
+	prog_fd = bpf_program__fd(prog);
+	if (CHECK_FAIL(prog_fd < 0))
+		goto out;
+
+	i = 0;
+	err = bpf_map_update_elem(map_fd, &i, &prog_fd, BPF_ANY);
+	if (CHECK_FAIL(err))
+		goto out;
+
+	err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0,
+				&duration, &retval, NULL);
+	CHECK(err || retval != 1, "tailcall", "err %d errno %d retval %d\n",
+	      err, errno, retval);
+
+	data_map = bpf_object__find_map_by_name(obj, "tailcall.bss");
+	if (CHECK_FAIL(!data_map || !bpf_map__is_internal(data_map)))
+		return;
+
+	data_fd = bpf_map__fd(data_map);
+	if (CHECK_FAIL(map_fd < 0))
+		return;
+
+	i = 0;
+	err = bpf_map_lookup_elem(data_fd, &i, &val);
+	CHECK(err || val != 33, "tailcall count", "err %d errno %d count %d\n",
+	      err, errno, val);
+
+	i = 0;
+	err = bpf_map_delete_elem(map_fd, &i);
+	if (CHECK_FAIL(err))
+		goto out;
+
+	err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0,
+				&duration, &retval, NULL);
+	CHECK(err || retval != 0, "tailcall", "err %d errno %d retval %d\n",
+	      err, errno, retval);
+out:
+	bpf_object__close(obj);
+}
+
+/* test_tailcall_bpf2bpf_3 checks that non-trivial amount of stack (up to
+ * 256 bytes) can be used within bpf subprograms that have the tailcalls
+ * in them
+ */
+static void test_tailcall_bpf2bpf_3(void)
+{
+	int err, map_fd, prog_fd, main_fd, i;
+	struct bpf_map *prog_array;
+	struct bpf_program *prog;
+	struct bpf_object *obj;
+	__u32 retval, duration;
+	char prog_name[32];
+
+	err = bpf_prog_load("tailcall_bpf2bpf3.o", BPF_PROG_TYPE_SCHED_CLS,
+			    &obj, &prog_fd);
+	if (CHECK_FAIL(err))
+		return;
+
+	prog = bpf_object__find_program_by_title(obj, "classifier");
+	if (CHECK_FAIL(!prog))
+		goto out;
+
+	main_fd = bpf_program__fd(prog);
+	if (CHECK_FAIL(main_fd < 0))
+		goto out;
+
+	prog_array = bpf_object__find_map_by_name(obj, "jmp_table");
+	if (CHECK_FAIL(!prog_array))
+		goto out;
+
+	map_fd = bpf_map__fd(prog_array);
+	if (CHECK_FAIL(map_fd < 0))
+		goto out;
+
+	for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) {
+		snprintf(prog_name, sizeof(prog_name), "classifier/%i", i);
+
+		prog = bpf_object__find_program_by_title(obj, prog_name);
+		if (CHECK_FAIL(!prog))
+			goto out;
+
+		prog_fd = bpf_program__fd(prog);
+		if (CHECK_FAIL(prog_fd < 0))
+			goto out;
+
+		err = bpf_map_update_elem(map_fd, &i, &prog_fd, BPF_ANY);
+		if (CHECK_FAIL(err))
+			goto out;
+	}
+
+	err = bpf_prog_test_run(main_fd, 1, &pkt_v4, sizeof(pkt_v4), 0,
+				&duration, &retval, NULL);
+	CHECK(err || retval != sizeof(pkt_v4) * 3,
+	      "tailcall", "err %d errno %d retval %d\n",
+	      err, errno, retval);
+
+	i = 1;
+	err = bpf_map_delete_elem(map_fd, &i);
+	if (CHECK_FAIL(err))
+		goto out;
+
+	err = bpf_prog_test_run(main_fd, 1, &pkt_v4, sizeof(pkt_v4), 0,
+				&duration, &retval, NULL);
+	CHECK(err || retval != sizeof(pkt_v4),
+	      "tailcall", "err %d errno %d retval %d\n",
+	      err, errno, retval);
+
+	i = 0;
+	err = bpf_map_delete_elem(map_fd, &i);
+	if (CHECK_FAIL(err))
+		goto out;
+
+	err = bpf_prog_test_run(main_fd, 1, &pkt_v4, sizeof(pkt_v4), 0,
+				&duration, &retval, NULL);
+	CHECK(err || retval != sizeof(pkt_v4) * 2,
+	      "tailcall", "err %d errno %d retval %d\n",
+	      err, errno, retval);
+out:
+	bpf_object__close(obj);
+}
+
+/* test_tailcall_bpf2bpf_4 checks that tailcall counter is correctly preserved
+ * across tailcalls combined with bpf2bpf calls. for making sure that tailcall
+ * counter behaves correctly, bpf program will go through following flow:
+ *
+ * entry -> entry_subprog -> tailcall0 -> bpf_func0 -> subprog0 ->
+ * -> tailcall1 -> bpf_func1 -> subprog1 -> tailcall2 -> bpf_func2 ->
+ * subprog2 [here bump global counter] --------^
+ *
+ * We go through first two tailcalls and start counting from the subprog2 where
+ * the loop begins. At the end of the test make sure that the global counter is
+ * equal to 31, because tailcall counter includes the first two tailcalls
+ * whereas global counter is incremented only on loop presented on flow above.
+ */
+static void test_tailcall_bpf2bpf_4(void)
+{
+	int err, map_fd, prog_fd, main_fd, data_fd, i, val;
+	struct bpf_map *prog_array, *data_map;
+	struct bpf_program *prog;
+	struct bpf_object *obj;
+	__u32 retval, duration;
+	char prog_name[32];
+
+	err = bpf_prog_load("tailcall_bpf2bpf4.o", BPF_PROG_TYPE_SCHED_CLS,
+			    &obj, &prog_fd);
+	if (CHECK_FAIL(err))
+		return;
+
+	prog = bpf_object__find_program_by_title(obj, "classifier");
+	if (CHECK_FAIL(!prog))
+		goto out;
+
+	main_fd = bpf_program__fd(prog);
+	if (CHECK_FAIL(main_fd < 0))
+		goto out;
+
+	prog_array = bpf_object__find_map_by_name(obj, "jmp_table");
+	if (CHECK_FAIL(!prog_array))
+		goto out;
+
+	map_fd = bpf_map__fd(prog_array);
+	if (CHECK_FAIL(map_fd < 0))
+		goto out;
+
+	for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) {
+		snprintf(prog_name, sizeof(prog_name), "classifier/%i", i);
+
+		prog = bpf_object__find_program_by_title(obj, prog_name);
+		if (CHECK_FAIL(!prog))
+			goto out;
+
+		prog_fd = bpf_program__fd(prog);
+		if (CHECK_FAIL(prog_fd < 0))
+			goto out;
+
+		err = bpf_map_update_elem(map_fd, &i, &prog_fd, BPF_ANY);
+		if (CHECK_FAIL(err))
+			goto out;
+	}
+
+	err = bpf_prog_test_run(main_fd, 1, &pkt_v4, sizeof(pkt_v4), 0,
+				&duration, &retval, NULL);
+	CHECK(err || retval != sizeof(pkt_v4) * 3, "tailcall", "err %d errno %d retval %d\n",
+	      err, errno, retval);
+
+	data_map = bpf_object__find_map_by_name(obj, "tailcall.bss");
+	if (CHECK_FAIL(!data_map || !bpf_map__is_internal(data_map)))
+		return;
+
+	data_fd = bpf_map__fd(data_map);
+	if (CHECK_FAIL(map_fd < 0))
+		return;
+
+	i = 0;
+	err = bpf_map_lookup_elem(data_fd, &i, &val);
+	CHECK(err || val != 31, "tailcall count", "err %d errno %d count %d\n",
+	      err, errno, val);
+
+out:
+	bpf_object__close(obj);
+}
+
 void test_tailcalls(void)
 {
 	if (test__start_subtest("tailcall_1"))
@@ -484,4 +808,12 @@ void test_tailcalls(void)
 		test_tailcall_4();
 	if (test__start_subtest("tailcall_5"))
 		test_tailcall_5();
+	if (test__start_subtest("tailcall_bpf2bpf_1"))
+		test_tailcall_bpf2bpf_1();
+	if (test__start_subtest("tailcall_bpf2bpf_2"))
+		test_tailcall_bpf2bpf_2();
+	if (test__start_subtest("tailcall_bpf2bpf_3"))
+		test_tailcall_bpf2bpf_3();
+	if (test__start_subtest("tailcall_bpf2bpf_4"))
+		test_tailcall_bpf2bpf_4();
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/test_overhead.c b/tools/testing/selftests/bpf/prog_tests/test_overhead.c
index 2702df2b2343..9966685866fd 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_overhead.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_overhead.c
@@ -61,10 +61,9 @@ void test_test_overhead(void)
 	const char *raw_tp_name = "raw_tp/task_rename";
 	const char *fentry_name = "fentry/__set_task_comm";
 	const char *fexit_name = "fexit/__set_task_comm";
-	const char *fmodret_name = "fmod_ret/__set_task_comm";
 	const char *kprobe_func = "__set_task_comm";
 	struct bpf_program *kprobe_prog, *kretprobe_prog, *raw_tp_prog;
-	struct bpf_program *fentry_prog, *fexit_prog, *fmodret_prog;
+	struct bpf_program *fentry_prog, *fexit_prog;
 	struct bpf_object *obj;
 	struct bpf_link *link;
 	int err, duration = 0;
@@ -97,11 +96,6 @@ void test_test_overhead(void)
 	if (CHECK(!fexit_prog, "find_probe",
 		  "prog '%s' not found\n", fexit_name))
 		goto cleanup;
-	fmodret_prog = bpf_object__find_program_by_title(obj, fmodret_name);
-	if (CHECK(!fmodret_prog, "find_probe",
-		  "prog '%s' not found\n", fmodret_name))
-		goto cleanup;
-
 	err = bpf_object__load(obj);
 	if (CHECK(err, "obj_load", "err %d\n", err))
 		goto cleanup;
@@ -148,12 +142,6 @@ void test_test_overhead(void)
 	test_run("fexit");
 	bpf_link__destroy(link);
 
-	/* attach fmod_ret */
-	link = bpf_program__attach_trace(fmodret_prog);
-	if (CHECK(IS_ERR(link), "attach fmod_ret", "err %ld\n", PTR_ERR(link)))
-		goto cleanup;
-	test_run("fmod_ret");
-	bpf_link__destroy(link);
 cleanup:
 	prctl(PR_SET_NAME, comm, 0L, 0L, 0L);
 	bpf_object__close(obj);
diff --git a/tools/testing/selftests/bpf/prog_tests/trace_ext.c b/tools/testing/selftests/bpf/prog_tests/trace_ext.c
new file mode 100644
index 000000000000..924441d4362d
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/trace_ext.c
@@ -0,0 +1,111 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+#include <test_progs.h>
+#include <network_helpers.h>
+#include <sys/stat.h>
+#include <linux/sched.h>
+#include <sys/syscall.h>
+
+#include "test_pkt_md_access.skel.h"
+#include "test_trace_ext.skel.h"
+#include "test_trace_ext_tracing.skel.h"
+
+static __u32 duration;
+
+void test_trace_ext(void)
+{
+	struct test_pkt_md_access *skel_pkt = NULL;
+	struct test_trace_ext_tracing *skel_trace = NULL;
+	struct test_trace_ext_tracing__bss *bss_trace;
+	struct test_trace_ext *skel_ext = NULL;
+	struct test_trace_ext__bss *bss_ext;
+	int err, pkt_fd, ext_fd;
+	struct bpf_program *prog;
+	char buf[100];
+	__u32 retval;
+	__u64 len;
+
+	/* open/load/attach test_pkt_md_access */
+	skel_pkt = test_pkt_md_access__open_and_load();
+	if (CHECK(!skel_pkt, "setup", "classifier/test_pkt_md_access open failed\n"))
+		goto cleanup;
+
+	err = test_pkt_md_access__attach(skel_pkt);
+	if (CHECK(err, "setup", "classifier/test_pkt_md_access attach failed: %d\n", err))
+		goto cleanup;
+
+	prog = skel_pkt->progs.test_pkt_md_access;
+	pkt_fd = bpf_program__fd(prog);
+
+	/* open extension */
+	skel_ext = test_trace_ext__open();
+	if (CHECK(!skel_ext, "setup", "freplace/test_pkt_md_access open failed\n"))
+		goto cleanup;
+
+	/* set extension's attach target - test_pkt_md_access  */
+	prog = skel_ext->progs.test_pkt_md_access_new;
+	bpf_program__set_attach_target(prog, pkt_fd, "test_pkt_md_access");
+
+	/* load/attach extension */
+	err = test_trace_ext__load(skel_ext);
+	if (CHECK(err, "setup", "freplace/test_pkt_md_access load failed\n")) {
+		libbpf_strerror(err, buf, sizeof(buf));
+		fprintf(stderr, "%s\n", buf);
+		goto cleanup;
+	}
+
+	err = test_trace_ext__attach(skel_ext);
+	if (CHECK(err, "setup", "freplace/test_pkt_md_access attach failed: %d\n", err))
+		goto cleanup;
+
+	prog = skel_ext->progs.test_pkt_md_access_new;
+	ext_fd = bpf_program__fd(prog);
+
+	/* open tracing  */
+	skel_trace = test_trace_ext_tracing__open();
+	if (CHECK(!skel_trace, "setup", "tracing/test_pkt_md_access_new open failed\n"))
+		goto cleanup;
+
+	/* set tracing's attach target - fentry */
+	prog = skel_trace->progs.fentry;
+	bpf_program__set_attach_target(prog, ext_fd, "test_pkt_md_access_new");
+
+	/* set tracing's attach target - fexit */
+	prog = skel_trace->progs.fexit;
+	bpf_program__set_attach_target(prog, ext_fd, "test_pkt_md_access_new");
+
+	/* load/attach tracing */
+	err = test_trace_ext_tracing__load(skel_trace);
+	if (CHECK(err, "setup", "tracing/test_pkt_md_access_new load failed\n")) {
+		libbpf_strerror(err, buf, sizeof(buf));
+		fprintf(stderr, "%s\n", buf);
+		goto cleanup;
+	}
+
+	err = test_trace_ext_tracing__attach(skel_trace);
+	if (CHECK(err, "setup", "tracing/test_pkt_md_access_new attach failed: %d\n", err))
+		goto cleanup;
+
+	/* trigger the test */
+	err = bpf_prog_test_run(pkt_fd, 1, &pkt_v4, sizeof(pkt_v4),
+				NULL, NULL, &retval, &duration);
+	CHECK(err || retval, "run", "err %d errno %d retval %d\n", err, errno, retval);
+
+	bss_ext = skel_ext->bss;
+	bss_trace = skel_trace->bss;
+
+	len = bss_ext->ext_called;
+
+	CHECK(bss_ext->ext_called == 0,
+		"check", "failed to trigger freplace/test_pkt_md_access\n");
+	CHECK(bss_trace->fentry_called != len,
+		"check", "failed to trigger fentry/test_pkt_md_access_new\n");
+	CHECK(bss_trace->fexit_called != len,
+		"check", "failed to trigger fexit/test_pkt_md_access_new\n");
+
+cleanup:
+	test_trace_ext_tracing__destroy(skel_trace);
+	test_trace_ext__destroy(skel_ext);
+	test_pkt_md_access__destroy(skel_pkt);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_noinline.c b/tools/testing/selftests/bpf/prog_tests/xdp_noinline.c
index f284f72158ef..a1f06424cf83 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_noinline.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_noinline.c
@@ -1,11 +1,12 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
 #include <network_helpers.h>
+#include "test_xdp_noinline.skel.h"
 
 void test_xdp_noinline(void)
 {
-	const char *file = "./test_xdp_noinline.o";
 	unsigned int nr_cpus = bpf_num_possible_cpus();
+	struct test_xdp_noinline *skel;
 	struct vip key = {.protocol = 6};
 	struct vip_meta {
 		__u32 flags;
@@ -25,58 +26,42 @@ void test_xdp_noinline(void)
 	} real_def = {.dst = MAGIC_VAL};
 	__u32 ch_key = 11, real_num = 3;
 	__u32 duration, retval, size;
-	int err, i, prog_fd, map_fd;
+	int err, i;
 	__u64 bytes = 0, pkts = 0;
-	struct bpf_object *obj;
 	char buf[128];
 	u32 *magic = (u32 *)buf;
 
-	err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd);
-	if (CHECK_FAIL(err))
+	skel = test_xdp_noinline__open_and_load();
+	if (CHECK(!skel, "skel_open_and_load", "failed\n"))
 		return;
 
-	map_fd = bpf_find_map(__func__, obj, "vip_map");
-	if (map_fd < 0)
-		goto out;
-	bpf_map_update_elem(map_fd, &key, &value, 0);
+	bpf_map_update_elem(bpf_map__fd(skel->maps.vip_map), &key, &value, 0);
+	bpf_map_update_elem(bpf_map__fd(skel->maps.ch_rings), &ch_key, &real_num, 0);
+	bpf_map_update_elem(bpf_map__fd(skel->maps.reals), &real_num, &real_def, 0);
 
-	map_fd = bpf_find_map(__func__, obj, "ch_rings");
-	if (map_fd < 0)
-		goto out;
-	bpf_map_update_elem(map_fd, &ch_key, &real_num, 0);
-
-	map_fd = bpf_find_map(__func__, obj, "reals");
-	if (map_fd < 0)
-		goto out;
-	bpf_map_update_elem(map_fd, &real_num, &real_def, 0);
-
-	err = bpf_prog_test_run(prog_fd, NUM_ITER, &pkt_v4, sizeof(pkt_v4),
+	err = bpf_prog_test_run(bpf_program__fd(skel->progs.balancer_ingress_v4),
+				NUM_ITER, &pkt_v4, sizeof(pkt_v4),
 				buf, &size, &retval, &duration);
 	CHECK(err || retval != 1 || size != 54 ||
 	      *magic != MAGIC_VAL, "ipv4",
 	      "err %d errno %d retval %d size %d magic %x\n",
 	      err, errno, retval, size, *magic);
 
-	err = bpf_prog_test_run(prog_fd, NUM_ITER, &pkt_v6, sizeof(pkt_v6),
+	err = bpf_prog_test_run(bpf_program__fd(skel->progs.balancer_ingress_v6),
+				NUM_ITER, &pkt_v6, sizeof(pkt_v6),
 				buf, &size, &retval, &duration);
 	CHECK(err || retval != 1 || size != 74 ||
 	      *magic != MAGIC_VAL, "ipv6",
 	      "err %d errno %d retval %d size %d magic %x\n",
 	      err, errno, retval, size, *magic);
 
-	map_fd = bpf_find_map(__func__, obj, "stats");
-	if (map_fd < 0)
-		goto out;
-	bpf_map_lookup_elem(map_fd, &stats_key, stats);
+	bpf_map_lookup_elem(bpf_map__fd(skel->maps.stats), &stats_key, stats);
 	for (i = 0; i < nr_cpus; i++) {
 		bytes += stats[i].bytes;
 		pkts += stats[i].pkts;
 	}
-	if (CHECK_FAIL(bytes != MAGIC_BYTES * NUM_ITER * 2 ||
-		       pkts != NUM_ITER * 2)) {
-		printf("test_xdp_noinline:FAIL:stats %lld %lld\n",
-		       bytes, pkts);
-	}
-out:
-	bpf_object__close(obj);
+	CHECK(bytes != MAGIC_BYTES * NUM_ITER * 2 || pkts != NUM_ITER * 2,
+	      "stats", "bytes %lld pkts %lld\n",
+	      (unsigned long long)bytes, (unsigned long long)pkts);
+	test_xdp_noinline__destroy(skel);
 }
diff --git a/tools/testing/selftests/bpf/progs/bpf_cubic.c b/tools/testing/selftests/bpf/progs/bpf_cubic.c
index ef574087f1e1..6939bfd8690f 100644
--- a/tools/testing/selftests/bpf/progs/bpf_cubic.c
+++ b/tools/testing/selftests/bpf/progs/bpf_cubic.c
@@ -15,6 +15,8 @@
  */
 
 #include <linux/bpf.h>
+#include <linux/stddef.h>
+#include <linux/tcp.h>
 #include "bpf_tcp_helpers.h"
 
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/bpf_dctcp.c b/tools/testing/selftests/bpf/progs/bpf_dctcp.c
index 3fb4260570b1..4dc1a967776a 100644
--- a/tools/testing/selftests/bpf/progs/bpf_dctcp.c
+++ b/tools/testing/selftests/bpf/progs/bpf_dctcp.c
@@ -9,6 +9,8 @@
 #include <stddef.h>
 #include <linux/bpf.h>
 #include <linux/types.h>
+#include <linux/stddef.h>
+#include <linux/tcp.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 #include "bpf_tcp_helpers.h"
diff --git a/tools/testing/selftests/bpf/progs/bpf_flow.c b/tools/testing/selftests/bpf/progs/bpf_flow.c
index de6de9221518..5a65f6b51377 100644
--- a/tools/testing/selftests/bpf/progs/bpf_flow.c
+++ b/tools/testing/selftests/bpf/progs/bpf_flow.c
@@ -118,18 +118,18 @@ static __always_inline int parse_eth_proto(struct __sk_buff *skb, __be16 proto)
 
 	switch (proto) {
 	case bpf_htons(ETH_P_IP):
-		bpf_tail_call(skb, &jmp_table, IP);
+		bpf_tail_call_static(skb, &jmp_table, IP);
 		break;
 	case bpf_htons(ETH_P_IPV6):
-		bpf_tail_call(skb, &jmp_table, IPV6);
+		bpf_tail_call_static(skb, &jmp_table, IPV6);
 		break;
 	case bpf_htons(ETH_P_MPLS_MC):
 	case bpf_htons(ETH_P_MPLS_UC):
-		bpf_tail_call(skb, &jmp_table, MPLS);
+		bpf_tail_call_static(skb, &jmp_table, MPLS);
 		break;
 	case bpf_htons(ETH_P_8021Q):
 	case bpf_htons(ETH_P_8021AD):
-		bpf_tail_call(skb, &jmp_table, VLAN);
+		bpf_tail_call_static(skb, &jmp_table, VLAN);
 		break;
 	default:
 		/* Protocol not supported */
@@ -246,10 +246,10 @@ static __always_inline int parse_ipv6_proto(struct __sk_buff *skb, __u8 nexthdr)
 	switch (nexthdr) {
 	case IPPROTO_HOPOPTS:
 	case IPPROTO_DSTOPTS:
-		bpf_tail_call(skb, &jmp_table, IPV6OP);
+		bpf_tail_call_static(skb, &jmp_table, IPV6OP);
 		break;
 	case IPPROTO_FRAGMENT:
-		bpf_tail_call(skb, &jmp_table, IPV6FR);
+		bpf_tail_call_static(skb, &jmp_table, IPV6FR);
 		break;
 	default:
 		return parse_ip_proto(skb, nexthdr);
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter.h b/tools/testing/selftests/bpf/progs/bpf_iter.h
index c196280df90d..6a1255465fd6 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter.h
+++ b/tools/testing/selftests/bpf/progs/bpf_iter.h
@@ -13,6 +13,12 @@
 #define udp6_sock udp6_sock___not_used
 #define bpf_iter__bpf_map_elem bpf_iter__bpf_map_elem___not_used
 #define bpf_iter__bpf_sk_storage_map bpf_iter__bpf_sk_storage_map___not_used
+#define bpf_iter__sockmap bpf_iter__sockmap___not_used
+#define btf_ptr btf_ptr___not_used
+#define BTF_F_COMPACT BTF_F_COMPACT___not_used
+#define BTF_F_NONAME BTF_F_NONAME___not_used
+#define BTF_F_PTR_RAW BTF_F_PTR_RAW___not_used
+#define BTF_F_ZERO BTF_F_ZERO___not_used
 #include "vmlinux.h"
 #undef bpf_iter_meta
 #undef bpf_iter__bpf_map
@@ -26,6 +32,12 @@
 #undef udp6_sock
 #undef bpf_iter__bpf_map_elem
 #undef bpf_iter__bpf_sk_storage_map
+#undef bpf_iter__sockmap
+#undef btf_ptr
+#undef BTF_F_COMPACT
+#undef BTF_F_NONAME
+#undef BTF_F_PTR_RAW
+#undef BTF_F_ZERO
 
 struct bpf_iter_meta {
 	struct seq_file *seq;
@@ -96,3 +108,23 @@ struct bpf_iter__bpf_sk_storage_map {
 	struct sock *sk;
 	void *value;
 };
+
+struct bpf_iter__sockmap {
+	struct bpf_iter_meta *meta;
+	struct bpf_map *map;
+	void *key;
+	struct sock *sk;
+};
+
+struct btf_ptr {
+	void *ptr;
+	__u32 type_id;
+	__u32 flags;
+};
+
+enum {
+	BTF_F_COMPACT	=	(1ULL << 0),
+	BTF_F_NONAME	=	(1ULL << 1),
+	BTF_F_PTR_RAW	=	(1ULL << 2),
+	BTF_F_ZERO	=	(1ULL << 3),
+};
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_hash_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_hash_map.c
index 07ddbfdbcab7..6dfce3fd68bc 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_hash_map.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_hash_map.c
@@ -47,7 +47,10 @@ int dump_bpf_hash_map(struct bpf_iter__bpf_map_elem *ctx)
 	__u32 seq_num = ctx->meta->seq_num;
 	struct bpf_map *map = ctx->map;
 	struct key_t *key = ctx->key;
+	struct key_t tmp_key;
 	__u64 *val = ctx->value;
+	__u64 tmp_val = 0;
+	int ret;
 
 	if (in_test_mode) {
 		/* test mode is used by selftests to
@@ -61,6 +64,18 @@ int dump_bpf_hash_map(struct bpf_iter__bpf_map_elem *ctx)
 		if (key == (void *)0 || val == (void *)0)
 			return 0;
 
+		/* update the value and then delete the <key, value> pair.
+		 * it should not impact the existing 'val' which is still
+		 * accessible under rcu.
+		 */
+		__builtin_memcpy(&tmp_key, key, sizeof(struct key_t));
+		ret = bpf_map_update_elem(&hashmap1, &tmp_key, &tmp_val, 0);
+		if (ret)
+			return 0;
+		ret = bpf_map_delete_elem(&hashmap1, &tmp_key);
+		if (ret)
+			return 0;
+
 		key_sum_a += key->a;
 		key_sum_b += key->b;
 		key_sum_c += key->c;
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_sockmap.c b/tools/testing/selftests/bpf/progs/bpf_iter_sockmap.c
new file mode 100644
index 000000000000..f3af0e30cead
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_sockmap.c
@@ -0,0 +1,59 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Cloudflare */
+#include "bpf_iter.h"
+#include "bpf_tracing_net.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <errno.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct {
+	__uint(type, BPF_MAP_TYPE_SOCKMAP);
+	__uint(max_entries, 64);
+	__type(key, __u32);
+	__type(value, __u64);
+} sockmap SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_SOCKHASH);
+	__uint(max_entries, 64);
+	__type(key, __u32);
+	__type(value, __u64);
+} sockhash SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_SOCKHASH);
+	__uint(max_entries, 64);
+	__type(key, __u32);
+	__type(value, __u64);
+} dst SEC(".maps");
+
+__u32 elems = 0;
+__u32 socks = 0;
+
+SEC("iter/sockmap")
+int copy(struct bpf_iter__sockmap *ctx)
+{
+	struct sock *sk = ctx->sk;
+	__u32 tmp, *key = ctx->key;
+	int ret;
+
+	if (!key)
+		return 0;
+
+	elems++;
+
+	/* We need a temporary buffer on the stack, since the verifier doesn't
+	 * let us use the pointer from the context as an argument to the helper.
+	 */
+	tmp = *key;
+
+	if (sk) {
+		socks++;
+		return bpf_map_update_elem(&dst, &tmp, sk, 0) != 0;
+	}
+
+	ret = bpf_map_delete_elem(&dst, &tmp);
+	return ret && ret != -ENOENT;
+}
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task_btf.c b/tools/testing/selftests/bpf/progs/bpf_iter_task_btf.c
new file mode 100644
index 000000000000..a1ddc36f13ec
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_task_btf.c
@@ -0,0 +1,50 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020, Oracle and/or its affiliates. */
+#include "bpf_iter.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
+
+#include <errno.h>
+
+char _license[] SEC("license") = "GPL";
+
+long tasks = 0;
+long seq_err = 0;
+bool skip = false;
+
+SEC("iter/task")
+int dump_task_struct(struct bpf_iter__task *ctx)
+{
+	struct seq_file *seq = ctx->meta->seq;
+	struct task_struct *task = ctx->task;
+	static struct btf_ptr ptr = { };
+	long ret;
+
+#if __has_builtin(__builtin_btf_type_id)
+	ptr.type_id = bpf_core_type_id_kernel(struct task_struct);
+	ptr.ptr = task;
+
+	if (ctx->meta->seq_num == 0)
+		BPF_SEQ_PRINTF(seq, "Raw BTF task\n");
+
+	ret = bpf_seq_printf_btf(seq, &ptr, sizeof(ptr), 0);
+	switch (ret) {
+	case 0:
+		tasks++;
+		break;
+	case -ERANGE:
+		/* NULL task or task->fs, don't count it as an error. */
+		break;
+	case -E2BIG:
+		return 1;
+	default:
+		seq_err = ret;
+		break;
+	}
+#else
+	skip = true;
+#endif
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task_file.c b/tools/testing/selftests/bpf/progs/bpf_iter_task_file.c
index 8b787baa2654..b2f7c7c5f952 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_task_file.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_task_file.c
@@ -6,6 +6,9 @@
 
 char _license[] SEC("license") = "GPL";
 
+int count = 0;
+int tgid = 0;
+
 SEC("iter/task_file")
 int dump_task_file(struct bpf_iter__task_file *ctx)
 {
@@ -17,8 +20,13 @@ int dump_task_file(struct bpf_iter__task_file *ctx)
 	if (task == (void *)0 || file == (void *)0)
 		return 0;
 
-	if (ctx->meta->seq_num == 0)
+	if (ctx->meta->seq_num == 0) {
+		count = 0;
 		BPF_SEQ_PRINTF(seq, "    tgid      gid       fd      file\n");
+	}
+
+	if (tgid == task->tgid && task->tgid != task->pid)
+		count++;
 
 	BPF_SEQ_PRINTF(seq, "%8d %8d %8d %lx\n", task->tgid, task->pid, fd,
 		       (long)file->f_op);
diff --git a/tools/testing/selftests/bpf/progs/btf_ptr.h b/tools/testing/selftests/bpf/progs/btf_ptr.h
new file mode 100644
index 000000000000..c3c9797c67db
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/btf_ptr.h
@@ -0,0 +1,27 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2020, Oracle and/or its affiliates. */
+/* "undefine" structs in vmlinux.h, because we "override" them below */
+#define btf_ptr btf_ptr___not_used
+#define BTF_F_COMPACT BTF_F_COMPACT___not_used
+#define BTF_F_NONAME BTF_F_NONAME___not_used
+#define BTF_F_PTR_RAW BTF_F_PTR_RAW___not_used
+#define BTF_F_ZERO BTF_F_ZERO___not_used
+#include "vmlinux.h"
+#undef btf_ptr
+#undef BTF_F_COMPACT
+#undef BTF_F_NONAME
+#undef BTF_F_PTR_RAW
+#undef BTF_F_ZERO
+
+struct btf_ptr {
+	void *ptr;
+	__u32 type_id;
+	__u32 flags;
+};
+
+enum {
+	BTF_F_COMPACT	=	(1ULL << 0),
+	BTF_F_NONAME	=	(1ULL << 1),
+	BTF_F_PTR_RAW	=	(1ULL << 2),
+	BTF_F_ZERO	=	(1ULL << 3),
+};
diff --git a/tools/testing/selftests/bpf/progs/fmod_ret_freplace.c b/tools/testing/selftests/bpf/progs/fmod_ret_freplace.c
new file mode 100644
index 000000000000..c8943ccee6c0
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/fmod_ret_freplace.c
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+volatile __u64 test_fmod_ret = 0;
+SEC("fmod_ret/security_new_get_constant")
+int BPF_PROG(fmod_ret_test, long val, int ret)
+{
+	test_fmod_ret = 1;
+	return 120;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/freplace_get_constant.c b/tools/testing/selftests/bpf/progs/freplace_get_constant.c
new file mode 100644
index 000000000000..705e4b64dfc2
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/freplace_get_constant.c
@@ -0,0 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+volatile __u64 test_get_constant = 0;
+SEC("freplace/get_constant")
+int security_new_get_constant(long val)
+{
+	if (val != 123)
+		return 0;
+	test_get_constant = 1;
+	return test_get_constant; /* original get_constant() returns val - 122 */
+}
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/map_ptr_kern.c b/tools/testing/selftests/bpf/progs/map_ptr_kern.c
index 982a2d8aa844..c325405751e2 100644
--- a/tools/testing/selftests/bpf/progs/map_ptr_kern.c
+++ b/tools/testing/selftests/bpf/progs/map_ptr_kern.c
@@ -82,6 +82,14 @@ static inline int check_default(struct bpf_map *indirect,
 	return 1;
 }
 
+static __noinline int
+check_default_noinline(struct bpf_map *indirect, struct bpf_map *direct)
+{
+	VERIFY(check(indirect, direct, sizeof(__u32), sizeof(__u32),
+		     MAX_ENTRIES));
+	return 1;
+}
+
 typedef struct {
 	int counter;
 } atomic_t;
@@ -107,7 +115,7 @@ static inline int check_hash(void)
 	struct bpf_map *map = (struct bpf_map *)&m_hash;
 	int i;
 
-	VERIFY(check_default(&hash->map, map));
+	VERIFY(check_default_noinline(&hash->map, map));
 
 	VERIFY(hash->n_buckets == MAX_ENTRIES);
 	VERIFY(hash->elem_size == 64);
diff --git a/tools/testing/selftests/bpf/progs/metadata_unused.c b/tools/testing/selftests/bpf/progs/metadata_unused.c
new file mode 100644
index 000000000000..672a0d19f8d0
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/metadata_unused.c
@@ -0,0 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+volatile const char bpf_metadata_a[] SEC(".rodata") = "foo";
+volatile const int bpf_metadata_b SEC(".rodata") = 1;
+
+SEC("cgroup_skb/egress")
+int prog(struct xdp_md *ctx)
+{
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/metadata_used.c b/tools/testing/selftests/bpf/progs/metadata_used.c
new file mode 100644
index 000000000000..b7198e65383d
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/metadata_used.c
@@ -0,0 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+volatile const char bpf_metadata_a[] SEC(".rodata") = "bar";
+volatile const int bpf_metadata_b SEC(".rodata") = 2;
+
+SEC("cgroup_skb/egress")
+int prog(struct xdp_md *ctx)
+{
+	return bpf_metadata_b ? 1 : 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/netif_receive_skb.c b/tools/testing/selftests/bpf/progs/netif_receive_skb.c
new file mode 100644
index 000000000000..6b670039ea67
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/netif_receive_skb.c
@@ -0,0 +1,249 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020, Oracle and/or its affiliates. */
+
+#include "btf_ptr.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
+
+#include <errno.h>
+
+long ret = 0;
+int num_subtests = 0;
+int ran_subtests = 0;
+bool skip = false;
+
+#define STRSIZE			2048
+#define EXPECTED_STRSIZE	256
+
+#ifndef ARRAY_SIZE
+#define ARRAY_SIZE(x)	(sizeof(x) / sizeof((x)[0]))
+#endif
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, char[STRSIZE]);
+} strdata SEC(".maps");
+
+static int __strncmp(const void *m1, const void *m2, size_t len)
+{
+	const unsigned char *s1 = m1;
+	const unsigned char *s2 = m2;
+	int i, delta = 0;
+
+	for (i = 0; i < len; i++) {
+		delta = s1[i] - s2[i];
+		if (delta || s1[i] == 0 || s2[i] == 0)
+			break;
+	}
+	return delta;
+}
+
+#if __has_builtin(__builtin_btf_type_id)
+#define	TEST_BTF(_str, _type, _flags, _expected, ...)			\
+	do {								\
+		static const char _expectedval[EXPECTED_STRSIZE] =	\
+							_expected;	\
+		static const char _ptrtype[64] = #_type;		\
+		__u64 _hflags = _flags | BTF_F_COMPACT;			\
+		static _type _ptrdata = __VA_ARGS__;			\
+		static struct btf_ptr _ptr = { };			\
+		int _cmp;						\
+									\
+		++num_subtests;						\
+		if (ret < 0)						\
+			break;						\
+		++ran_subtests;						\
+		_ptr.ptr = &_ptrdata;					\
+		_ptr.type_id = bpf_core_type_id_kernel(_type);		\
+		if (_ptr.type_id <= 0) {				\
+			ret = -EINVAL;					\
+			break;						\
+		}							\
+		ret = bpf_snprintf_btf(_str, STRSIZE,			\
+				       &_ptr, sizeof(_ptr), _hflags);	\
+		if (ret)						\
+			break;						\
+		_cmp = __strncmp(_str, _expectedval, EXPECTED_STRSIZE);	\
+		if (_cmp != 0) {					\
+			bpf_printk("(%d) got %s", _cmp, _str);		\
+			bpf_printk("(%d) expected %s", _cmp,		\
+				   _expectedval);			\
+			ret = -EBADMSG;					\
+			break;						\
+		}							\
+	} while (0)
+#endif
+
+/* Use where expected data string matches its stringified declaration */
+#define TEST_BTF_C(_str, _type, _flags, ...)				\
+	TEST_BTF(_str, _type, _flags, "(" #_type ")" #__VA_ARGS__,	\
+		 __VA_ARGS__)
+
+/* TRACE_EVENT(netif_receive_skb,
+ *	TP_PROTO(struct sk_buff *skb),
+ */
+SEC("tp_btf/netif_receive_skb")
+int BPF_PROG(trace_netif_receive_skb, struct sk_buff *skb)
+{
+	static __u64 flags[] = { 0, BTF_F_COMPACT, BTF_F_ZERO, BTF_F_PTR_RAW,
+				 BTF_F_NONAME, BTF_F_COMPACT | BTF_F_ZERO |
+				 BTF_F_PTR_RAW | BTF_F_NONAME };
+	static struct btf_ptr p = { };
+	__u32 key = 0;
+	int i, __ret;
+	char *str;
+
+#if __has_builtin(__builtin_btf_type_id)
+	str = bpf_map_lookup_elem(&strdata, &key);
+	if (!str)
+		return 0;
+
+	/* Ensure we can write skb string representation */
+	p.type_id = bpf_core_type_id_kernel(struct sk_buff);
+	p.ptr = skb;
+	for (i = 0; i < ARRAY_SIZE(flags); i++) {
+		++num_subtests;
+		ret = bpf_snprintf_btf(str, STRSIZE, &p, sizeof(p), 0);
+		if (ret < 0)
+			bpf_printk("returned %d when writing skb", ret);
+		++ran_subtests;
+	}
+
+	/* Check invalid ptr value */
+	p.ptr = 0;
+	__ret = bpf_snprintf_btf(str, STRSIZE, &p, sizeof(p), 0);
+	if (__ret >= 0) {
+		bpf_printk("printing NULL should generate error, got (%d)",
+			   __ret);
+		ret = -ERANGE;
+	}
+
+	/* Verify type display for various types. */
+
+	/* simple int */
+	TEST_BTF_C(str, int, 0, 1234);
+	TEST_BTF(str, int, BTF_F_NONAME, "1234", 1234);
+	/* zero value should be printed at toplevel */
+	TEST_BTF(str, int, 0, "(int)0", 0);
+	TEST_BTF(str, int, BTF_F_NONAME, "0", 0);
+	TEST_BTF(str, int, BTF_F_ZERO, "(int)0", 0);
+	TEST_BTF(str, int, BTF_F_NONAME | BTF_F_ZERO, "0", 0);
+	TEST_BTF_C(str, int, 0, -4567);
+	TEST_BTF(str, int, BTF_F_NONAME, "-4567", -4567);
+
+	/* simple char */
+	TEST_BTF_C(str, char, 0, 100);
+	TEST_BTF(str, char, BTF_F_NONAME, "100", 100);
+	/* zero value should be printed at toplevel */
+	TEST_BTF(str, char, 0, "(char)0", 0);
+	TEST_BTF(str, char, BTF_F_NONAME, "0", 0);
+	TEST_BTF(str, char, BTF_F_ZERO, "(char)0", 0);
+	TEST_BTF(str, char, BTF_F_NONAME | BTF_F_ZERO, "0", 0);
+
+	/* simple typedef */
+	TEST_BTF_C(str, uint64_t, 0, 100);
+	TEST_BTF(str, u64, BTF_F_NONAME, "1", 1);
+	/* zero value should be printed at toplevel */
+	TEST_BTF(str, u64, 0, "(u64)0", 0);
+	TEST_BTF(str, u64, BTF_F_NONAME, "0", 0);
+	TEST_BTF(str, u64, BTF_F_ZERO, "(u64)0", 0);
+	TEST_BTF(str, u64, BTF_F_NONAME|BTF_F_ZERO, "0", 0);
+
+	/* typedef struct */
+	TEST_BTF_C(str, atomic_t, 0, {.counter = (int)1,});
+	TEST_BTF(str, atomic_t, BTF_F_NONAME, "{1,}", {.counter = 1,});
+	/* typedef with 0 value should be printed at toplevel */
+	TEST_BTF(str, atomic_t, 0, "(atomic_t){}", {.counter = 0,});
+	TEST_BTF(str, atomic_t, BTF_F_NONAME, "{}", {.counter = 0,});
+	TEST_BTF(str, atomic_t, BTF_F_ZERO, "(atomic_t){.counter = (int)0,}",
+		 {.counter = 0,});
+	TEST_BTF(str, atomic_t, BTF_F_NONAME|BTF_F_ZERO,
+		 "{0,}", {.counter = 0,});
+
+	/* enum where enum value does (and does not) exist */
+	TEST_BTF_C(str, enum bpf_cmd, 0, BPF_MAP_CREATE);
+	TEST_BTF(str, enum bpf_cmd, 0, "(enum bpf_cmd)BPF_MAP_CREATE", 0);
+	TEST_BTF(str, enum bpf_cmd, BTF_F_NONAME, "BPF_MAP_CREATE",
+		 BPF_MAP_CREATE);
+	TEST_BTF(str, enum bpf_cmd, BTF_F_NONAME|BTF_F_ZERO,
+		 "BPF_MAP_CREATE", 0);
+
+	TEST_BTF(str, enum bpf_cmd, BTF_F_ZERO, "(enum bpf_cmd)BPF_MAP_CREATE",
+		 BPF_MAP_CREATE);
+	TEST_BTF(str, enum bpf_cmd, BTF_F_NONAME|BTF_F_ZERO,
+		 "BPF_MAP_CREATE", BPF_MAP_CREATE);
+	TEST_BTF_C(str, enum bpf_cmd, 0, 2000);
+	TEST_BTF(str, enum bpf_cmd, BTF_F_NONAME, "2000", 2000);
+
+	/* simple struct */
+	TEST_BTF_C(str, struct btf_enum, 0,
+		   {.name_off = (__u32)3,.val = (__s32)-1,});
+	TEST_BTF(str, struct btf_enum, BTF_F_NONAME, "{3,-1,}",
+		 { .name_off = 3, .val = -1,});
+	TEST_BTF(str, struct btf_enum, BTF_F_NONAME, "{-1,}",
+		 { .name_off = 0, .val = -1,});
+	TEST_BTF(str, struct btf_enum, BTF_F_NONAME|BTF_F_ZERO, "{0,-1,}",
+		 { .name_off = 0, .val = -1,});
+	/* empty struct should be printed */
+	TEST_BTF(str, struct btf_enum, 0, "(struct btf_enum){}",
+		 { .name_off = 0, .val = 0,});
+	TEST_BTF(str, struct btf_enum, BTF_F_NONAME, "{}",
+		 { .name_off = 0, .val = 0,});
+	TEST_BTF(str, struct btf_enum, BTF_F_ZERO,
+		 "(struct btf_enum){.name_off = (__u32)0,.val = (__s32)0,}",
+		 { .name_off = 0, .val = 0,});
+
+	/* struct with pointers */
+	TEST_BTF(str, struct list_head, BTF_F_PTR_RAW,
+		 "(struct list_head){.next = (struct list_head *)0x0000000000000001,}",
+		 { .next = (struct list_head *)1 });
+	/* NULL pointer should not be displayed */
+	TEST_BTF(str, struct list_head, BTF_F_PTR_RAW,
+		 "(struct list_head){}",
+		 { .next = (struct list_head *)0 });
+
+	/* struct with char array */
+	TEST_BTF(str, struct bpf_prog_info, 0,
+		 "(struct bpf_prog_info){.name = (char[])['f','o','o',],}",
+		 { .name = "foo",});
+	TEST_BTF(str, struct bpf_prog_info, BTF_F_NONAME,
+		 "{['f','o','o',],}",
+		 {.name = "foo",});
+	/* leading null char means do not display string */
+	TEST_BTF(str, struct bpf_prog_info, 0,
+		 "(struct bpf_prog_info){}",
+		 {.name = {'\0', 'f', 'o', 'o'}});
+	/* handle non-printable characters */
+	TEST_BTF(str, struct bpf_prog_info, 0,
+		 "(struct bpf_prog_info){.name = (char[])[1,2,3,],}",
+		 { .name = {1, 2, 3, 0}});
+
+	/* struct with non-char array */
+	TEST_BTF(str, struct __sk_buff, 0,
+		 "(struct __sk_buff){.cb = (__u32[])[1,2,3,4,5,],}",
+		 { .cb = {1, 2, 3, 4, 5,},});
+	TEST_BTF(str, struct __sk_buff, BTF_F_NONAME,
+		 "{[1,2,3,4,5,],}",
+		 { .cb = { 1, 2, 3, 4, 5},});
+	/* For non-char, arrays, show non-zero values only */
+	TEST_BTF(str, struct __sk_buff, 0,
+		 "(struct __sk_buff){.cb = (__u32[])[1,],}",
+		 { .cb = { 0, 0, 1, 0, 0},});
+
+	/* struct with bitfields */
+	TEST_BTF_C(str, struct bpf_insn, 0,
+		   {.code = (__u8)1,.dst_reg = (__u8)0x2,.src_reg = (__u8)0x3,.off = (__s16)4,.imm = (__s32)5,});
+	TEST_BTF(str, struct bpf_insn, BTF_F_NONAME, "{1,0x2,0x3,4,5,}",
+		 {.code = 1, .dst_reg = 0x2, .src_reg = 0x3, .off = 4,
+		  .imm = 5,});
+#else
+	skip = true;
+#endif
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/pyperf.h b/tools/testing/selftests/bpf/progs/pyperf.h
index cc615b82b56e..2fb7adafb6b6 100644
--- a/tools/testing/selftests/bpf/progs/pyperf.h
+++ b/tools/testing/selftests/bpf/progs/pyperf.h
@@ -67,7 +67,12 @@ typedef struct {
 	void* co_name; // PyCodeObject.co_name
 } FrameData;
 
-static __always_inline void *get_thread_state(void *tls_base, PidData *pidData)
+#ifdef SUBPROGS
+__noinline
+#else
+__always_inline
+#endif
+static void *get_thread_state(void *tls_base, PidData *pidData)
 {
 	void* thread_state;
 	int key;
@@ -155,7 +160,9 @@ struct {
 } stackmap SEC(".maps");
 
 #ifdef GLOBAL_FUNC
-__attribute__((noinline))
+__noinline
+#elif defined(SUBPROGS)
+static __noinline
 #else
 static __always_inline
 #endif
diff --git a/tools/testing/selftests/bpf/progs/pyperf_subprogs.c b/tools/testing/selftests/bpf/progs/pyperf_subprogs.c
new file mode 100644
index 000000000000..60e27a7f0cca
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/pyperf_subprogs.c
@@ -0,0 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#define STACK_MAX_LEN 50
+#define SUBPROGS
+#include "pyperf.h"
diff --git a/tools/testing/selftests/bpf/progs/strobemeta.h b/tools/testing/selftests/bpf/progs/strobemeta.h
index ad61b722a9de..7de534f38c3f 100644
--- a/tools/testing/selftests/bpf/progs/strobemeta.h
+++ b/tools/testing/selftests/bpf/progs/strobemeta.h
@@ -266,8 +266,12 @@ struct tls_index {
 	uint64_t offset;
 };
 
-static __always_inline void *calc_location(struct strobe_value_loc *loc,
-					   void *tls_base)
+#ifdef SUBPROGS
+__noinline
+#else
+__always_inline
+#endif
+static void *calc_location(struct strobe_value_loc *loc, void *tls_base)
 {
 	/*
 	 * tls_mode value is:
@@ -327,10 +331,15 @@ static __always_inline void *calc_location(struct strobe_value_loc *loc,
 		: NULL;
 }
 
-static __always_inline void read_int_var(struct strobemeta_cfg *cfg,
-					 size_t idx, void *tls_base,
-					 struct strobe_value_generic *value,
-					 struct strobemeta_payload *data)
+#ifdef SUBPROGS
+__noinline
+#else
+__always_inline
+#endif
+static void read_int_var(struct strobemeta_cfg *cfg,
+			 size_t idx, void *tls_base,
+			 struct strobe_value_generic *value,
+			 struct strobemeta_payload *data)
 {
 	void *location = calc_location(&cfg->int_locs[idx], tls_base);
 	if (!location)
@@ -440,8 +449,13 @@ static __always_inline void *read_map_var(struct strobemeta_cfg *cfg,
  * read_strobe_meta returns NULL, if no metadata was read; otherwise returns
  * pointer to *right after* payload ends
  */
-static __always_inline void *read_strobe_meta(struct task_struct *task,
-					      struct strobemeta_payload *data)
+#ifdef SUBPROGS
+__noinline
+#else
+__always_inline
+#endif
+static void *read_strobe_meta(struct task_struct *task,
+			      struct strobemeta_payload *data)
 {
 	pid_t pid = bpf_get_current_pid_tgid() >> 32;
 	struct strobe_value_generic value = {0};
diff --git a/tools/testing/selftests/bpf/progs/strobemeta_subprogs.c b/tools/testing/selftests/bpf/progs/strobemeta_subprogs.c
new file mode 100644
index 000000000000..b6c01f8fc559
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/strobemeta_subprogs.c
@@ -0,0 +1,10 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+// Copyright (c) 2019 Facebook
+
+#define STROBE_MAX_INTS 2
+#define STROBE_MAX_STRS 25
+#define STROBE_MAX_MAPS 13
+#define STROBE_MAX_MAP_ENTRIES 20
+#define NO_UNROLL
+#define SUBPROGS
+#include "strobemeta.h"
diff --git a/tools/testing/selftests/bpf/progs/tailcall1.c b/tools/testing/selftests/bpf/progs/tailcall1.c
index 1f407e65ae52..7115bcefbe8a 100644
--- a/tools/testing/selftests/bpf/progs/tailcall1.c
+++ b/tools/testing/selftests/bpf/progs/tailcall1.c
@@ -26,20 +26,20 @@ int entry(struct __sk_buff *skb)
 	/* Multiple locations to make sure we patch
 	 * all of them.
 	 */
-	bpf_tail_call(skb, &jmp_table, 0);
-	bpf_tail_call(skb, &jmp_table, 0);
-	bpf_tail_call(skb, &jmp_table, 0);
-	bpf_tail_call(skb, &jmp_table, 0);
-
-	bpf_tail_call(skb, &jmp_table, 1);
-	bpf_tail_call(skb, &jmp_table, 1);
-	bpf_tail_call(skb, &jmp_table, 1);
-	bpf_tail_call(skb, &jmp_table, 1);
-
-	bpf_tail_call(skb, &jmp_table, 2);
-	bpf_tail_call(skb, &jmp_table, 2);
-	bpf_tail_call(skb, &jmp_table, 2);
-	bpf_tail_call(skb, &jmp_table, 2);
+	bpf_tail_call_static(skb, &jmp_table, 0);
+	bpf_tail_call_static(skb, &jmp_table, 0);
+	bpf_tail_call_static(skb, &jmp_table, 0);
+	bpf_tail_call_static(skb, &jmp_table, 0);
+
+	bpf_tail_call_static(skb, &jmp_table, 1);
+	bpf_tail_call_static(skb, &jmp_table, 1);
+	bpf_tail_call_static(skb, &jmp_table, 1);
+	bpf_tail_call_static(skb, &jmp_table, 1);
+
+	bpf_tail_call_static(skb, &jmp_table, 2);
+	bpf_tail_call_static(skb, &jmp_table, 2);
+	bpf_tail_call_static(skb, &jmp_table, 2);
+	bpf_tail_call_static(skb, &jmp_table, 2);
 
 	return 3;
 }
diff --git a/tools/testing/selftests/bpf/progs/tailcall2.c b/tools/testing/selftests/bpf/progs/tailcall2.c
index a093e739cf0e..0431e4fe7efd 100644
--- a/tools/testing/selftests/bpf/progs/tailcall2.c
+++ b/tools/testing/selftests/bpf/progs/tailcall2.c
@@ -13,14 +13,14 @@ struct {
 SEC("classifier/0")
 int bpf_func_0(struct __sk_buff *skb)
 {
-	bpf_tail_call(skb, &jmp_table, 1);
+	bpf_tail_call_static(skb, &jmp_table, 1);
 	return 0;
 }
 
 SEC("classifier/1")
 int bpf_func_1(struct __sk_buff *skb)
 {
-	bpf_tail_call(skb, &jmp_table, 2);
+	bpf_tail_call_static(skb, &jmp_table, 2);
 	return 1;
 }
 
@@ -33,25 +33,25 @@ int bpf_func_2(struct __sk_buff *skb)
 SEC("classifier/3")
 int bpf_func_3(struct __sk_buff *skb)
 {
-	bpf_tail_call(skb, &jmp_table, 4);
+	bpf_tail_call_static(skb, &jmp_table, 4);
 	return 3;
 }
 
 SEC("classifier/4")
 int bpf_func_4(struct __sk_buff *skb)
 {
-	bpf_tail_call(skb, &jmp_table, 3);
+	bpf_tail_call_static(skb, &jmp_table, 3);
 	return 4;
 }
 
 SEC("classifier")
 int entry(struct __sk_buff *skb)
 {
-	bpf_tail_call(skb, &jmp_table, 0);
+	bpf_tail_call_static(skb, &jmp_table, 0);
 	/* Check multi-prog update. */
-	bpf_tail_call(skb, &jmp_table, 2);
+	bpf_tail_call_static(skb, &jmp_table, 2);
 	/* Check tail call limit. */
-	bpf_tail_call(skb, &jmp_table, 3);
+	bpf_tail_call_static(skb, &jmp_table, 3);
 	return 3;
 }
 
diff --git a/tools/testing/selftests/bpf/progs/tailcall3.c b/tools/testing/selftests/bpf/progs/tailcall3.c
index cabda877cf0a..739dc2a51e74 100644
--- a/tools/testing/selftests/bpf/progs/tailcall3.c
+++ b/tools/testing/selftests/bpf/progs/tailcall3.c
@@ -16,14 +16,14 @@ SEC("classifier/0")
 int bpf_func_0(struct __sk_buff *skb)
 {
 	count++;
-	bpf_tail_call(skb, &jmp_table, 0);
+	bpf_tail_call_static(skb, &jmp_table, 0);
 	return 1;
 }
 
 SEC("classifier")
 int entry(struct __sk_buff *skb)
 {
-	bpf_tail_call(skb, &jmp_table, 0);
+	bpf_tail_call_static(skb, &jmp_table, 0);
 	return 0;
 }
 
diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf1.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf1.c
new file mode 100644
index 000000000000..0103f3dd9f02
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf1.c
@@ -0,0 +1,38 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+	__uint(max_entries, 2);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(__u32));
+} jmp_table SEC(".maps");
+
+#define TAIL_FUNC(x) 				\
+	SEC("classifier/" #x)			\
+	int bpf_func_##x(struct __sk_buff *skb)	\
+	{					\
+		return x;			\
+	}
+TAIL_FUNC(0)
+TAIL_FUNC(1)
+
+static __noinline
+int subprog_tail(struct __sk_buff *skb)
+{
+	bpf_tail_call_static(skb, &jmp_table, 0);
+
+	return skb->len * 2;
+}
+
+SEC("classifier")
+int entry(struct __sk_buff *skb)
+{
+	bpf_tail_call_static(skb, &jmp_table, 1);
+
+	return subprog_tail(skb);
+}
+
+char __license[] SEC("license") = "GPL";
+int _version SEC("version") = 1;
diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf2.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf2.c
new file mode 100644
index 000000000000..7b1c04183824
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf2.c
@@ -0,0 +1,41 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_legacy.h"
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+	__uint(max_entries, 1);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(__u32));
+} jmp_table SEC(".maps");
+
+static __noinline
+int subprog_tail(struct __sk_buff *skb)
+{
+	if (load_byte(skb, 0))
+		bpf_tail_call_static(skb, &jmp_table, 1);
+	else
+		bpf_tail_call_static(skb, &jmp_table, 0);
+	return 1;
+}
+
+static volatile int count;
+
+SEC("classifier/0")
+int bpf_func_0(struct __sk_buff *skb)
+{
+	count++;
+	return subprog_tail(skb);
+}
+
+SEC("classifier")
+int entry(struct __sk_buff *skb)
+{
+	bpf_tail_call_static(skb, &jmp_table, 0);
+
+	return 0;
+}
+
+char __license[] SEC("license") = "GPL";
+int _version SEC("version") = 1;
diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf3.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf3.c
new file mode 100644
index 000000000000..0d5482bea6c9
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf3.c
@@ -0,0 +1,61 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_legacy.h"
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+	__uint(max_entries, 2);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(__u32));
+} jmp_table SEC(".maps");
+
+__noinline
+int subprog_tail2(struct __sk_buff *skb)
+{
+	volatile char arr[64] = {};
+
+	if (load_word(skb, 0) || load_half(skb, 0))
+		bpf_tail_call_static(skb, &jmp_table, 10);
+	else
+		bpf_tail_call_static(skb, &jmp_table, 1);
+
+	return skb->len;
+}
+
+static __noinline
+int subprog_tail(struct __sk_buff *skb)
+{
+	volatile char arr[64] = {};
+
+	bpf_tail_call_static(skb, &jmp_table, 0);
+
+	return skb->len * 2;
+}
+
+SEC("classifier/0")
+int bpf_func_0(struct __sk_buff *skb)
+{
+	volatile char arr[128] = {};
+
+	return subprog_tail2(skb);
+}
+
+SEC("classifier/1")
+int bpf_func_1(struct __sk_buff *skb)
+{
+	volatile char arr[128] = {};
+
+	return skb->len * 3;
+}
+
+SEC("classifier")
+int entry(struct __sk_buff *skb)
+{
+	volatile char arr[128] = {};
+
+	return subprog_tail(skb);
+}
+
+char __license[] SEC("license") = "GPL";
+int _version SEC("version") = 1;
diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf4.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf4.c
new file mode 100644
index 000000000000..9a1b166b7fbe
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf4.c
@@ -0,0 +1,61 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+	__uint(max_entries, 3);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(__u32));
+} jmp_table SEC(".maps");
+
+static volatile int count;
+
+__noinline
+int subprog_tail_2(struct __sk_buff *skb)
+{
+	bpf_tail_call_static(skb, &jmp_table, 2);
+	return skb->len * 3;
+}
+
+__noinline
+int subprog_tail_1(struct __sk_buff *skb)
+{
+	bpf_tail_call_static(skb, &jmp_table, 1);
+	return skb->len * 2;
+}
+
+__noinline
+int subprog_tail(struct __sk_buff *skb)
+{
+	bpf_tail_call_static(skb, &jmp_table, 0);
+	return skb->len;
+}
+
+SEC("classifier/1")
+int bpf_func_1(struct __sk_buff *skb)
+{
+	return subprog_tail_2(skb);
+}
+
+SEC("classifier/2")
+int bpf_func_2(struct __sk_buff *skb)
+{
+	count++;
+	return subprog_tail_2(skb);
+}
+
+SEC("classifier/0")
+int bpf_func_0(struct __sk_buff *skb)
+{
+	return subprog_tail_1(skb);
+}
+
+SEC("classifier")
+int entry(struct __sk_buff *skb)
+{
+	return subprog_tail(skb);
+}
+
+char __license[] SEC("license") = "GPL";
+int _version SEC("version") = 1;
diff --git a/tools/testing/selftests/bpf/progs/test_btf_skc_cls_ingress.c b/tools/testing/selftests/bpf/progs/test_btf_skc_cls_ingress.c
new file mode 100644
index 000000000000..9a6b85dd52d2
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_btf_skc_cls_ingress.c
@@ -0,0 +1,174 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+
+#include <string.h>
+#include <errno.h>
+#include <netinet/in.h>
+#include <linux/stddef.h>
+#include <linux/bpf.h>
+#include <linux/ipv6.h>
+#include <linux/tcp.h>
+#include <linux/if_ether.h>
+#include <linux/pkt_cls.h>
+
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+#include "bpf_tcp_helpers.h"
+
+struct sockaddr_in6 srv_sa6 = {};
+__u16 listen_tp_sport = 0;
+__u16 req_sk_sport = 0;
+__u32 recv_cookie = 0;
+__u32 gen_cookie = 0;
+__u32 linum = 0;
+
+#define LOG() ({ if (!linum) linum = __LINE__; })
+
+static void test_syncookie_helper(struct ipv6hdr *ip6h, struct tcphdr *th,
+				  struct tcp_sock *tp,
+				  struct __sk_buff *skb)
+{
+	if (th->syn) {
+		__s64 mss_cookie;
+		void *data_end;
+
+		data_end = (void *)(long)(skb->data_end);
+
+		if (th->doff * 4 != 40) {
+			LOG();
+			return;
+		}
+
+		if ((void *)th + 40 > data_end) {
+			LOG();
+			return;
+		}
+
+		mss_cookie = bpf_tcp_gen_syncookie(tp, ip6h, sizeof(*ip6h),
+						   th, 40);
+		if (mss_cookie < 0) {
+			if (mss_cookie != -ENOENT)
+				LOG();
+		} else {
+			gen_cookie = (__u32)mss_cookie;
+		}
+	} else if (gen_cookie) {
+		/* It was in cookie mode */
+		int ret = bpf_tcp_check_syncookie(tp, ip6h, sizeof(*ip6h),
+						  th, sizeof(*th));
+
+		if (ret < 0) {
+			if (ret != -ENOENT)
+				LOG();
+		} else {
+			recv_cookie = bpf_ntohl(th->ack_seq) - 1;
+		}
+	}
+}
+
+static int handle_ip6_tcp(struct ipv6hdr *ip6h, struct __sk_buff *skb)
+{
+	struct bpf_sock_tuple *tuple;
+	struct bpf_sock *bpf_skc;
+	unsigned int tuple_len;
+	struct tcphdr *th;
+	void *data_end;
+
+	data_end = (void *)(long)(skb->data_end);
+
+	th = (struct tcphdr *)(ip6h + 1);
+	if (th + 1 > data_end)
+		return TC_ACT_OK;
+
+	/* Is it the testing traffic? */
+	if (th->dest != srv_sa6.sin6_port)
+		return TC_ACT_OK;
+
+	tuple_len = sizeof(tuple->ipv6);
+	tuple = (struct bpf_sock_tuple *)&ip6h->saddr;
+	if ((void *)tuple + tuple_len > data_end) {
+		LOG();
+		return TC_ACT_OK;
+	}
+
+	bpf_skc = bpf_skc_lookup_tcp(skb, tuple, tuple_len,
+				     BPF_F_CURRENT_NETNS, 0);
+	if (!bpf_skc) {
+		LOG();
+		return TC_ACT_OK;
+	}
+
+	if (bpf_skc->state == BPF_TCP_NEW_SYN_RECV) {
+		struct request_sock *req_sk;
+
+		req_sk = (struct request_sock *)bpf_skc_to_tcp_request_sock(bpf_skc);
+		if (!req_sk) {
+			LOG();
+			goto release;
+		}
+
+		if (bpf_sk_assign(skb, req_sk, 0)) {
+			LOG();
+			goto release;
+		}
+
+		req_sk_sport = req_sk->__req_common.skc_num;
+
+		bpf_sk_release(req_sk);
+		return TC_ACT_OK;
+	} else if (bpf_skc->state == BPF_TCP_LISTEN) {
+		struct tcp_sock *tp;
+
+		tp = bpf_skc_to_tcp_sock(bpf_skc);
+		if (!tp) {
+			LOG();
+			goto release;
+		}
+
+		if (bpf_sk_assign(skb, tp, 0)) {
+			LOG();
+			goto release;
+		}
+
+		listen_tp_sport = tp->inet_conn.icsk_inet.sk.__sk_common.skc_num;
+
+		test_syncookie_helper(ip6h, th, tp, skb);
+		bpf_sk_release(tp);
+		return TC_ACT_OK;
+	}
+
+	if (bpf_sk_assign(skb, bpf_skc, 0))
+		LOG();
+
+release:
+	bpf_sk_release(bpf_skc);
+	return TC_ACT_OK;
+}
+
+SEC("classifier/ingress")
+int cls_ingress(struct __sk_buff *skb)
+{
+	struct ipv6hdr *ip6h;
+	struct ethhdr *eth;
+	void *data_end;
+
+	data_end = (void *)(long)(skb->data_end);
+
+	eth = (struct ethhdr *)(long)(skb->data);
+	if (eth + 1 > data_end)
+		return TC_ACT_OK;
+
+	if (eth->h_proto != bpf_htons(ETH_P_IPV6))
+		return TC_ACT_OK;
+
+	ip6h = (struct ipv6hdr *)(eth + 1);
+	if (ip6h + 1 > data_end)
+		return TC_ACT_OK;
+
+	if (ip6h->nexthdr == IPPROTO_TCP)
+		return handle_ip6_tcp(ip6h, skb);
+
+	return TC_ACT_OK;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_cls_redirect.c b/tools/testing/selftests/bpf/progs/test_cls_redirect.c
index f0b72e86bee5..c9f8464996ea 100644
--- a/tools/testing/selftests/bpf/progs/test_cls_redirect.c
+++ b/tools/testing/selftests/bpf/progs/test_cls_redirect.c
@@ -22,6 +22,12 @@
 
 #include "test_cls_redirect.h"
 
+#ifdef SUBPROGS
+#define INLINING __noinline
+#else
+#define INLINING __always_inline
+#endif
+
 #define offsetofend(TYPE, MEMBER) \
 	(offsetof(TYPE, MEMBER) + sizeof((((TYPE *)0)->MEMBER)))
 
@@ -125,7 +131,7 @@ typedef struct buf {
 	uint8_t *const tail;
 } buf_t;
 
-static size_t buf_off(const buf_t *buf)
+static __always_inline size_t buf_off(const buf_t *buf)
 {
 	/* Clang seems to optimize constructs like
 	 *    a - b + c
@@ -145,7 +151,7 @@ static size_t buf_off(const buf_t *buf)
 	return off;
 }
 
-static bool buf_copy(buf_t *buf, void *dst, size_t len)
+static __always_inline bool buf_copy(buf_t *buf, void *dst, size_t len)
 {
 	if (bpf_skb_load_bytes(buf->skb, buf_off(buf), dst, len)) {
 		return false;
@@ -155,7 +161,7 @@ static bool buf_copy(buf_t *buf, void *dst, size_t len)
 	return true;
 }
 
-static bool buf_skip(buf_t *buf, const size_t len)
+static __always_inline bool buf_skip(buf_t *buf, const size_t len)
 {
 	/* Check whether off + len is valid in the non-linear part. */
 	if (buf_off(buf) + len > buf->skb->len) {
@@ -173,7 +179,7 @@ static bool buf_skip(buf_t *buf, const size_t len)
  * If scratch is not NULL, the function will attempt to load non-linear
  * data via bpf_skb_load_bytes. On success, scratch is returned.
  */
-static void *buf_assign(buf_t *buf, const size_t len, void *scratch)
+static __always_inline void *buf_assign(buf_t *buf, const size_t len, void *scratch)
 {
 	if (buf->head + len > buf->tail) {
 		if (scratch == NULL) {
@@ -188,7 +194,7 @@ static void *buf_assign(buf_t *buf, const size_t len, void *scratch)
 	return ptr;
 }
 
-static bool pkt_skip_ipv4_options(buf_t *buf, const struct iphdr *ipv4)
+static INLINING bool pkt_skip_ipv4_options(buf_t *buf, const struct iphdr *ipv4)
 {
 	if (ipv4->ihl <= 5) {
 		return true;
@@ -197,13 +203,13 @@ static bool pkt_skip_ipv4_options(buf_t *buf, const struct iphdr *ipv4)
 	return buf_skip(buf, (ipv4->ihl - 5) * 4);
 }
 
-static bool ipv4_is_fragment(const struct iphdr *ip)
+static INLINING bool ipv4_is_fragment(const struct iphdr *ip)
 {
 	uint16_t frag_off = ip->frag_off & bpf_htons(IP_OFFSET_MASK);
 	return (ip->frag_off & bpf_htons(IP_MF)) != 0 || frag_off > 0;
 }
 
-static struct iphdr *pkt_parse_ipv4(buf_t *pkt, struct iphdr *scratch)
+static __always_inline struct iphdr *pkt_parse_ipv4(buf_t *pkt, struct iphdr *scratch)
 {
 	struct iphdr *ipv4 = buf_assign(pkt, sizeof(*ipv4), scratch);
 	if (ipv4 == NULL) {
@@ -222,7 +228,7 @@ static struct iphdr *pkt_parse_ipv4(buf_t *pkt, struct iphdr *scratch)
 }
 
 /* Parse the L4 ports from a packet, assuming a layout like TCP or UDP. */
-static bool pkt_parse_icmp_l4_ports(buf_t *pkt, flow_ports_t *ports)
+static INLINING bool pkt_parse_icmp_l4_ports(buf_t *pkt, flow_ports_t *ports)
 {
 	if (!buf_copy(pkt, ports, sizeof(*ports))) {
 		return false;
@@ -237,7 +243,7 @@ static bool pkt_parse_icmp_l4_ports(buf_t *pkt, flow_ports_t *ports)
 	return true;
 }
 
-static uint16_t pkt_checksum_fold(uint32_t csum)
+static INLINING uint16_t pkt_checksum_fold(uint32_t csum)
 {
 	/* The highest reasonable value for an IPv4 header
 	 * checksum requires two folds, so we just do that always.
@@ -247,7 +253,7 @@ static uint16_t pkt_checksum_fold(uint32_t csum)
 	return (uint16_t)~csum;
 }
 
-static void pkt_ipv4_checksum(struct iphdr *iph)
+static INLINING void pkt_ipv4_checksum(struct iphdr *iph)
 {
 	iph->check = 0;
 
@@ -268,10 +274,11 @@ static void pkt_ipv4_checksum(struct iphdr *iph)
 	iph->check = pkt_checksum_fold(acc);
 }
 
-static bool pkt_skip_ipv6_extension_headers(buf_t *pkt,
-					    const struct ipv6hdr *ipv6,
-					    uint8_t *upper_proto,
-					    bool *is_fragment)
+static INLINING
+bool pkt_skip_ipv6_extension_headers(buf_t *pkt,
+				     const struct ipv6hdr *ipv6,
+				     uint8_t *upper_proto,
+				     bool *is_fragment)
 {
 	/* We understand five extension headers.
 	 * https://tools.ietf.org/html/rfc8200#section-4.1 states that all
@@ -336,7 +343,7 @@ static bool pkt_skip_ipv6_extension_headers(buf_t *pkt,
  * scratch is allocated on the stack. However, this usage should be safe since
  * it's the callers stack after all.
  */
-static inline __attribute__((__always_inline__)) struct ipv6hdr *
+static __always_inline struct ipv6hdr *
 pkt_parse_ipv6(buf_t *pkt, struct ipv6hdr *scratch, uint8_t *proto,
 	       bool *is_fragment)
 {
@@ -354,20 +361,20 @@ pkt_parse_ipv6(buf_t *pkt, struct ipv6hdr *scratch, uint8_t *proto,
 
 /* Global metrics, per CPU
  */
-struct bpf_map_def metrics_map SEC("maps") = {
-	.type = BPF_MAP_TYPE_PERCPU_ARRAY,
-	.key_size = sizeof(unsigned int),
-	.value_size = sizeof(metrics_t),
-	.max_entries = 1,
-};
-
-static metrics_t *get_global_metrics(void)
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, unsigned int);
+	__type(value, metrics_t);
+} metrics_map SEC(".maps");
+
+static INLINING metrics_t *get_global_metrics(void)
 {
 	uint64_t key = 0;
 	return bpf_map_lookup_elem(&metrics_map, &key);
 }
 
-static ret_t accept_locally(struct __sk_buff *skb, encap_headers_t *encap)
+static INLINING ret_t accept_locally(struct __sk_buff *skb, encap_headers_t *encap)
 {
 	const int payload_off =
 		sizeof(*encap) +
@@ -388,8 +395,8 @@ static ret_t accept_locally(struct __sk_buff *skb, encap_headers_t *encap)
 	return bpf_redirect(skb->ifindex, BPF_F_INGRESS);
 }
 
-static ret_t forward_with_gre(struct __sk_buff *skb, encap_headers_t *encap,
-			      struct in_addr *next_hop, metrics_t *metrics)
+static INLINING ret_t forward_with_gre(struct __sk_buff *skb, encap_headers_t *encap,
+				       struct in_addr *next_hop, metrics_t *metrics)
 {
 	metrics->forwarded_packets_total_gre++;
 
@@ -509,8 +516,8 @@ static ret_t forward_with_gre(struct __sk_buff *skb, encap_headers_t *encap,
 	return bpf_redirect(skb->ifindex, 0);
 }
 
-static ret_t forward_to_next_hop(struct __sk_buff *skb, encap_headers_t *encap,
-				 struct in_addr *next_hop, metrics_t *metrics)
+static INLINING ret_t forward_to_next_hop(struct __sk_buff *skb, encap_headers_t *encap,
+					  struct in_addr *next_hop, metrics_t *metrics)
 {
 	/* swap L2 addresses */
 	/* This assumes that packets are received from a router.
@@ -546,7 +553,7 @@ static ret_t forward_to_next_hop(struct __sk_buff *skb, encap_headers_t *encap,
 	return bpf_redirect(skb->ifindex, 0);
 }
 
-static ret_t skip_next_hops(buf_t *pkt, int n)
+static INLINING ret_t skip_next_hops(buf_t *pkt, int n)
 {
 	switch (n) {
 	case 1:
@@ -566,8 +573,8 @@ static ret_t skip_next_hops(buf_t *pkt, int n)
  * pkt is positioned just after the variable length GLB header
  * iff the call is successful.
  */
-static ret_t get_next_hop(buf_t *pkt, encap_headers_t *encap,
-			  struct in_addr *next_hop)
+static INLINING ret_t get_next_hop(buf_t *pkt, encap_headers_t *encap,
+				   struct in_addr *next_hop)
 {
 	if (encap->unigue.next_hop > encap->unigue.hop_count) {
 		return TC_ACT_SHOT;
@@ -601,8 +608,8 @@ static ret_t get_next_hop(buf_t *pkt, encap_headers_t *encap,
  * return value, and calling code works while still being "generic" to
  * IPv4 and IPv6.
  */
-static uint64_t fill_tuple(struct bpf_sock_tuple *tuple, void *iph,
-			   uint64_t iphlen, uint16_t sport, uint16_t dport)
+static INLINING uint64_t fill_tuple(struct bpf_sock_tuple *tuple, void *iph,
+				    uint64_t iphlen, uint16_t sport, uint16_t dport)
 {
 	switch (iphlen) {
 	case sizeof(struct iphdr): {
@@ -630,9 +637,9 @@ static uint64_t fill_tuple(struct bpf_sock_tuple *tuple, void *iph,
 	}
 }
 
-static verdict_t classify_tcp(struct __sk_buff *skb,
-			      struct bpf_sock_tuple *tuple, uint64_t tuplen,
-			      void *iph, struct tcphdr *tcp)
+static INLINING verdict_t classify_tcp(struct __sk_buff *skb,
+				       struct bpf_sock_tuple *tuple, uint64_t tuplen,
+				       void *iph, struct tcphdr *tcp)
 {
 	struct bpf_sock *sk =
 		bpf_skc_lookup_tcp(skb, tuple, tuplen, BPF_F_CURRENT_NETNS, 0);
@@ -663,8 +670,8 @@ static verdict_t classify_tcp(struct __sk_buff *skb,
 	return UNKNOWN;
 }
 
-static verdict_t classify_udp(struct __sk_buff *skb,
-			      struct bpf_sock_tuple *tuple, uint64_t tuplen)
+static INLINING verdict_t classify_udp(struct __sk_buff *skb,
+				       struct bpf_sock_tuple *tuple, uint64_t tuplen)
 {
 	struct bpf_sock *sk =
 		bpf_sk_lookup_udp(skb, tuple, tuplen, BPF_F_CURRENT_NETNS, 0);
@@ -681,9 +688,9 @@ static verdict_t classify_udp(struct __sk_buff *skb,
 	return UNKNOWN;
 }
 
-static verdict_t classify_icmp(struct __sk_buff *skb, uint8_t proto,
-			       struct bpf_sock_tuple *tuple, uint64_t tuplen,
-			       metrics_t *metrics)
+static INLINING verdict_t classify_icmp(struct __sk_buff *skb, uint8_t proto,
+					struct bpf_sock_tuple *tuple, uint64_t tuplen,
+					metrics_t *metrics)
 {
 	switch (proto) {
 	case IPPROTO_TCP:
@@ -698,7 +705,7 @@ static verdict_t classify_icmp(struct __sk_buff *skb, uint8_t proto,
 	}
 }
 
-static verdict_t process_icmpv4(buf_t *pkt, metrics_t *metrics)
+static INLINING verdict_t process_icmpv4(buf_t *pkt, metrics_t *metrics)
 {
 	struct icmphdr icmp;
 	if (!buf_copy(pkt, &icmp, sizeof(icmp))) {
@@ -745,7 +752,7 @@ static verdict_t process_icmpv4(buf_t *pkt, metrics_t *metrics)
 			     sizeof(tuple.ipv4), metrics);
 }
 
-static verdict_t process_icmpv6(buf_t *pkt, metrics_t *metrics)
+static INLINING verdict_t process_icmpv6(buf_t *pkt, metrics_t *metrics)
 {
 	struct icmp6hdr icmp6;
 	if (!buf_copy(pkt, &icmp6, sizeof(icmp6))) {
@@ -797,8 +804,8 @@ static verdict_t process_icmpv6(buf_t *pkt, metrics_t *metrics)
 			     metrics);
 }
 
-static verdict_t process_tcp(buf_t *pkt, void *iph, uint64_t iphlen,
-			     metrics_t *metrics)
+static INLINING verdict_t process_tcp(buf_t *pkt, void *iph, uint64_t iphlen,
+				      metrics_t *metrics)
 {
 	metrics->l4_protocol_packets_total_tcp++;
 
@@ -819,8 +826,8 @@ static verdict_t process_tcp(buf_t *pkt, void *iph, uint64_t iphlen,
 	return classify_tcp(pkt->skb, &tuple, tuplen, iph, tcp);
 }
 
-static verdict_t process_udp(buf_t *pkt, void *iph, uint64_t iphlen,
-			     metrics_t *metrics)
+static INLINING verdict_t process_udp(buf_t *pkt, void *iph, uint64_t iphlen,
+				      metrics_t *metrics)
 {
 	metrics->l4_protocol_packets_total_udp++;
 
@@ -837,7 +844,7 @@ static verdict_t process_udp(buf_t *pkt, void *iph, uint64_t iphlen,
 	return classify_udp(pkt->skb, &tuple, tuplen);
 }
 
-static verdict_t process_ipv4(buf_t *pkt, metrics_t *metrics)
+static INLINING verdict_t process_ipv4(buf_t *pkt, metrics_t *metrics)
 {
 	metrics->l3_protocol_packets_total_ipv4++;
 
@@ -874,7 +881,7 @@ static verdict_t process_ipv4(buf_t *pkt, metrics_t *metrics)
 	}
 }
 
-static verdict_t process_ipv6(buf_t *pkt, metrics_t *metrics)
+static INLINING verdict_t process_ipv6(buf_t *pkt, metrics_t *metrics)
 {
 	metrics->l3_protocol_packets_total_ipv6++;
 
diff --git a/tools/testing/selftests/bpf/progs/test_cls_redirect_subprogs.c b/tools/testing/selftests/bpf/progs/test_cls_redirect_subprogs.c
new file mode 100644
index 000000000000..eed26b70e3a2
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_cls_redirect_subprogs.c
@@ -0,0 +1,2 @@
+#define SUBPROGS
+#include "test_cls_redirect.c"
diff --git a/tools/testing/selftests/bpf/progs/test_d_path.c b/tools/testing/selftests/bpf/progs/test_d_path.c
index 61f007855649..84e1f883f97b 100644
--- a/tools/testing/selftests/bpf/progs/test_d_path.c
+++ b/tools/testing/selftests/bpf/progs/test_d_path.c
@@ -15,7 +15,10 @@ char paths_close[MAX_FILES][MAX_PATH_LEN] = {};
 int rets_stat[MAX_FILES] = {};
 int rets_close[MAX_FILES] = {};
 
-SEC("fentry/vfs_getattr")
+int called_stat = 0;
+int called_close = 0;
+
+SEC("fentry/security_inode_getattr")
 int BPF_PROG(prog_stat, struct path *path, struct kstat *stat,
 	     __u32 request_mask, unsigned int query_flags)
 {
@@ -23,6 +26,8 @@ int BPF_PROG(prog_stat, struct path *path, struct kstat *stat,
 	__u32 cnt = cnt_stat;
 	int ret;
 
+	called_stat = 1;
+
 	if (pid != my_pid)
 		return 0;
 
@@ -42,6 +47,8 @@ int BPF_PROG(prog_close, struct file *file, void *id)
 	__u32 cnt = cnt_close;
 	int ret;
 
+	called_close = 1;
+
 	if (pid != my_pid)
 		return 0;
 
diff --git a/tools/testing/selftests/bpf/progs/test_l4lb_noinline.c b/tools/testing/selftests/bpf/progs/test_l4lb_noinline.c
index 28351936a438..b9e2753f4f91 100644
--- a/tools/testing/selftests/bpf/progs/test_l4lb_noinline.c
+++ b/tools/testing/selftests/bpf/progs/test_l4lb_noinline.c
@@ -17,9 +17,7 @@
 #include "test_iptunnel_common.h"
 #include <bpf/bpf_endian.h>
 
-int _version SEC("version") = 1;
-
-static __u32 rol32(__u32 word, unsigned int shift)
+static __always_inline __u32 rol32(__u32 word, unsigned int shift)
 {
 	return (word << shift) | (word >> ((-shift) & 31));
 }
@@ -52,7 +50,7 @@ static __u32 rol32(__u32 word, unsigned int shift)
 
 typedef unsigned int u32;
 
-static u32 jhash(const void *key, u32 length, u32 initval)
+static __noinline u32 jhash(const void *key, u32 length, u32 initval)
 {
 	u32 a, b, c;
 	const unsigned char *k = key;
@@ -88,7 +86,7 @@ static u32 jhash(const void *key, u32 length, u32 initval)
 	return c;
 }
 
-static u32 __jhash_nwords(u32 a, u32 b, u32 c, u32 initval)
+static __noinline u32 __jhash_nwords(u32 a, u32 b, u32 c, u32 initval)
 {
 	a += initval;
 	b += initval;
@@ -97,7 +95,7 @@ static u32 __jhash_nwords(u32 a, u32 b, u32 c, u32 initval)
 	return c;
 }
 
-static u32 jhash_2words(u32 a, u32 b, u32 initval)
+static __noinline u32 jhash_2words(u32 a, u32 b, u32 initval)
 {
 	return __jhash_nwords(a, b, 0, initval + JHASH_INITVAL + (2 << 2));
 }
@@ -200,8 +198,7 @@ struct {
 	__type(value, struct ctl_value);
 } ctl_array SEC(".maps");
 
-static __u32 get_packet_hash(struct packet_description *pckt,
-			     bool ipv6)
+static __noinline __u32 get_packet_hash(struct packet_description *pckt, bool ipv6)
 {
 	if (ipv6)
 		return jhash_2words(jhash(pckt->srcv6, 16, MAX_VIPS),
@@ -210,10 +207,10 @@ static __u32 get_packet_hash(struct packet_description *pckt,
 		return jhash_2words(pckt->src, pckt->ports, CH_RINGS_SIZE);
 }
 
-static bool get_packet_dst(struct real_definition **real,
-			   struct packet_description *pckt,
-			   struct vip_meta *vip_info,
-			   bool is_ipv6)
+static __noinline bool get_packet_dst(struct real_definition **real,
+				      struct packet_description *pckt,
+				      struct vip_meta *vip_info,
+				      bool is_ipv6)
 {
 	__u32 hash = get_packet_hash(pckt, is_ipv6);
 	__u32 key = RING_SIZE * vip_info->vip_num + hash % RING_SIZE;
@@ -233,8 +230,8 @@ static bool get_packet_dst(struct real_definition **real,
 	return true;
 }
 
-static int parse_icmpv6(void *data, void *data_end, __u64 off,
-			struct packet_description *pckt)
+static __noinline int parse_icmpv6(void *data, void *data_end, __u64 off,
+				   struct packet_description *pckt)
 {
 	struct icmp6hdr *icmp_hdr;
 	struct ipv6hdr *ip6h;
@@ -255,8 +252,8 @@ static int parse_icmpv6(void *data, void *data_end, __u64 off,
 	return TC_ACT_UNSPEC;
 }
 
-static int parse_icmp(void *data, void *data_end, __u64 off,
-		      struct packet_description *pckt)
+static __noinline int parse_icmp(void *data, void *data_end, __u64 off,
+				 struct packet_description *pckt)
 {
 	struct icmphdr *icmp_hdr;
 	struct iphdr *iph;
@@ -280,8 +277,8 @@ static int parse_icmp(void *data, void *data_end, __u64 off,
 	return TC_ACT_UNSPEC;
 }
 
-static bool parse_udp(void *data, __u64 off, void *data_end,
-		      struct packet_description *pckt)
+static __noinline bool parse_udp(void *data, __u64 off, void *data_end,
+				 struct packet_description *pckt)
 {
 	struct udphdr *udp;
 	udp = data + off;
@@ -299,8 +296,8 @@ static bool parse_udp(void *data, __u64 off, void *data_end,
 	return true;
 }
 
-static bool parse_tcp(void *data, __u64 off, void *data_end,
-		      struct packet_description *pckt)
+static __noinline bool parse_tcp(void *data, __u64 off, void *data_end,
+				 struct packet_description *pckt)
 {
 	struct tcphdr *tcp;
 
@@ -321,8 +318,8 @@ static bool parse_tcp(void *data, __u64 off, void *data_end,
 	return true;
 }
 
-static int process_packet(void *data, __u64 off, void *data_end,
-			  bool is_ipv6, struct __sk_buff *skb)
+static __noinline int process_packet(void *data, __u64 off, void *data_end,
+				     bool is_ipv6, struct __sk_buff *skb)
 {
 	void *pkt_start = (void *)(long)skb->data;
 	struct packet_description pckt = {};
diff --git a/tools/testing/selftests/bpf/progs/test_overhead.c b/tools/testing/selftests/bpf/progs/test_overhead.c
index 42403d088abc..abb7344b531f 100644
--- a/tools/testing/selftests/bpf/progs/test_overhead.c
+++ b/tools/testing/selftests/bpf/progs/test_overhead.c
@@ -39,10 +39,4 @@ int BPF_PROG(prog5, struct task_struct *tsk, const char *buf, bool exec)
 	return 0;
 }
 
-SEC("fmod_ret/__set_task_comm")
-int BPF_PROG(prog6, struct task_struct *tsk, const char *buf, bool exec)
-{
-	return !tsk;
-}
-
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_pe_preserve_elems.c b/tools/testing/selftests/bpf/progs/test_pe_preserve_elems.c
new file mode 100644
index 000000000000..fb22de7c365d
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_pe_preserve_elems.c
@@ -0,0 +1,38 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2020 Facebook
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
+	__uint(max_entries, 1);
+	__uint(key_size, sizeof(int));
+	__uint(value_size, sizeof(int));
+} array_1 SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
+	__uint(max_entries, 1);
+	__uint(key_size, sizeof(int));
+	__uint(value_size, sizeof(int));
+	__uint(map_flags, BPF_F_PRESERVE_ELEMS);
+} array_2 SEC(".maps");
+
+SEC("raw_tp/sched_switch")
+int BPF_PROG(read_array_1)
+{
+	struct bpf_perf_event_value val;
+
+	return bpf_perf_event_read_value(&array_1, 0, &val, sizeof(val));
+}
+
+SEC("raw_tp/task_rename")
+int BPF_PROG(read_array_2)
+{
+	struct bpf_perf_event_value val;
+
+	return bpf_perf_event_read_value(&array_2, 0, &val, sizeof(val));
+}
+
+char LICENSE[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_raw_tp_test_run.c b/tools/testing/selftests/bpf/progs/test_raw_tp_test_run.c
new file mode 100644
index 000000000000..4c63cc87b9d0
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_raw_tp_test_run.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+__u32 count = 0;
+__u32 on_cpu = 0xffffffff;
+
+SEC("raw_tp/task_rename")
+int BPF_PROG(rename, struct task_struct *task, char *comm)
+{
+
+	count++;
+	if ((__u64) task == 0x1234ULL && (__u64) comm == 0x5678ULL) {
+		on_cpu = bpf_get_smp_processor_id();
+		return (long)task + (long)comm;
+	}
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_sk_lookup.c b/tools/testing/selftests/bpf/progs/test_sk_lookup.c
index bbf8296f4d66..1032b292af5b 100644
--- a/tools/testing/selftests/bpf/progs/test_sk_lookup.c
+++ b/tools/testing/selftests/bpf/progs/test_sk_lookup.c
@@ -19,6 +19,17 @@
 #define IP6(aaaa, bbbb, cccc, dddd)			\
 	{ bpf_htonl(aaaa), bpf_htonl(bbbb), bpf_htonl(cccc), bpf_htonl(dddd) }
 
+/* Macros for least-significant byte and word accesses. */
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+#define LSE_INDEX(index, size) (index)
+#else
+#define LSE_INDEX(index, size) ((size) - (index) - 1)
+#endif
+#define LSB(value, index)				\
+	(((__u8 *)&(value))[LSE_INDEX((index), sizeof(value))])
+#define LSW(value, index)				\
+	(((__u16 *)&(value))[LSE_INDEX((index), sizeof(value) / 2)])
+
 #define MAX_SOCKS 32
 
 struct {
@@ -369,171 +380,146 @@ int ctx_narrow_access(struct bpf_sk_lookup *ctx)
 {
 	struct bpf_sock *sk;
 	int err, family;
-	__u16 *half;
-	__u8 *byte;
 	bool v4;
 
 	v4 = (ctx->family == AF_INET);
 
 	/* Narrow loads from family field */
-	byte = (__u8 *)&ctx->family;
-	half = (__u16 *)&ctx->family;
-	if (byte[0] != (v4 ? AF_INET : AF_INET6) ||
-	    byte[1] != 0 || byte[2] != 0 || byte[3] != 0)
+	if (LSB(ctx->family, 0) != (v4 ? AF_INET : AF_INET6) ||
+	    LSB(ctx->family, 1) != 0 || LSB(ctx->family, 2) != 0 || LSB(ctx->family, 3) != 0)
 		return SK_DROP;
-	if (half[0] != (v4 ? AF_INET : AF_INET6))
+	if (LSW(ctx->family, 0) != (v4 ? AF_INET : AF_INET6))
 		return SK_DROP;
 
-	byte = (__u8 *)&ctx->protocol;
-	if (byte[0] != IPPROTO_TCP ||
-	    byte[1] != 0 || byte[2] != 0 || byte[3] != 0)
+	/* Narrow loads from protocol field */
+	if (LSB(ctx->protocol, 0) != IPPROTO_TCP ||
+	    LSB(ctx->protocol, 1) != 0 || LSB(ctx->protocol, 2) != 0 || LSB(ctx->protocol, 3) != 0)
 		return SK_DROP;
-	half = (__u16 *)&ctx->protocol;
-	if (half[0] != IPPROTO_TCP)
+	if (LSW(ctx->protocol, 0) != IPPROTO_TCP)
 		return SK_DROP;
 
 	/* Narrow loads from remote_port field. Expect non-0 value. */
-	byte = (__u8 *)&ctx->remote_port;
-	if (byte[0] == 0 && byte[1] == 0 && byte[2] == 0 && byte[3] == 0)
+	if (LSB(ctx->remote_port, 0) == 0 && LSB(ctx->remote_port, 1) == 0 &&
+	    LSB(ctx->remote_port, 2) == 0 && LSB(ctx->remote_port, 3) == 0)
 		return SK_DROP;
-	half = (__u16 *)&ctx->remote_port;
-	if (half[0] == 0)
+	if (LSW(ctx->remote_port, 0) == 0)
 		return SK_DROP;
 
 	/* Narrow loads from local_port field. Expect DST_PORT. */
-	byte = (__u8 *)&ctx->local_port;
-	if (byte[0] != ((DST_PORT >> 0) & 0xff) ||
-	    byte[1] != ((DST_PORT >> 8) & 0xff) ||
-	    byte[2] != 0 || byte[3] != 0)
+	if (LSB(ctx->local_port, 0) != ((DST_PORT >> 0) & 0xff) ||
+	    LSB(ctx->local_port, 1) != ((DST_PORT >> 8) & 0xff) ||
+	    LSB(ctx->local_port, 2) != 0 || LSB(ctx->local_port, 3) != 0)
 		return SK_DROP;
-	half = (__u16 *)&ctx->local_port;
-	if (half[0] != DST_PORT)
+	if (LSW(ctx->local_port, 0) != DST_PORT)
 		return SK_DROP;
 
 	/* Narrow loads from IPv4 fields */
 	if (v4) {
 		/* Expect non-0.0.0.0 in remote_ip4 */
-		byte = (__u8 *)&ctx->remote_ip4;
-		if (byte[0] == 0 && byte[1] == 0 &&
-		    byte[2] == 0 && byte[3] == 0)
+		if (LSB(ctx->remote_ip4, 0) == 0 && LSB(ctx->remote_ip4, 1) == 0 &&
+		    LSB(ctx->remote_ip4, 2) == 0 && LSB(ctx->remote_ip4, 3) == 0)
 			return SK_DROP;
-		half = (__u16 *)&ctx->remote_ip4;
-		if (half[0] == 0 && half[1] == 0)
+		if (LSW(ctx->remote_ip4, 0) == 0 && LSW(ctx->remote_ip4, 1) == 0)
 			return SK_DROP;
 
 		/* Expect DST_IP4 in local_ip4 */
-		byte = (__u8 *)&ctx->local_ip4;
-		if (byte[0] != ((DST_IP4 >>  0) & 0xff) ||
-		    byte[1] != ((DST_IP4 >>  8) & 0xff) ||
-		    byte[2] != ((DST_IP4 >> 16) & 0xff) ||
-		    byte[3] != ((DST_IP4 >> 24) & 0xff))
+		if (LSB(ctx->local_ip4, 0) != ((DST_IP4 >> 0) & 0xff) ||
+		    LSB(ctx->local_ip4, 1) != ((DST_IP4 >> 8) & 0xff) ||
+		    LSB(ctx->local_ip4, 2) != ((DST_IP4 >> 16) & 0xff) ||
+		    LSB(ctx->local_ip4, 3) != ((DST_IP4 >> 24) & 0xff))
 			return SK_DROP;
-		half = (__u16 *)&ctx->local_ip4;
-		if (half[0] != ((DST_IP4 >>  0) & 0xffff) ||
-		    half[1] != ((DST_IP4 >> 16) & 0xffff))
+		if (LSW(ctx->local_ip4, 0) != ((DST_IP4 >> 0) & 0xffff) ||
+		    LSW(ctx->local_ip4, 1) != ((DST_IP4 >> 16) & 0xffff))
 			return SK_DROP;
 	} else {
 		/* Expect 0.0.0.0 IPs when family != AF_INET */
-		byte = (__u8 *)&ctx->remote_ip4;
-		if (byte[0] != 0 || byte[1] != 0 &&
-		    byte[2] != 0 || byte[3] != 0)
+		if (LSB(ctx->remote_ip4, 0) != 0 || LSB(ctx->remote_ip4, 1) != 0 ||
+		    LSB(ctx->remote_ip4, 2) != 0 || LSB(ctx->remote_ip4, 3) != 0)
 			return SK_DROP;
-		half = (__u16 *)&ctx->remote_ip4;
-		if (half[0] != 0 || half[1] != 0)
+		if (LSW(ctx->remote_ip4, 0) != 0 || LSW(ctx->remote_ip4, 1) != 0)
 			return SK_DROP;
 
-		byte = (__u8 *)&ctx->local_ip4;
-		if (byte[0] != 0 || byte[1] != 0 &&
-		    byte[2] != 0 || byte[3] != 0)
+		if (LSB(ctx->local_ip4, 0) != 0 || LSB(ctx->local_ip4, 1) != 0 ||
+		    LSB(ctx->local_ip4, 2) != 0 || LSB(ctx->local_ip4, 3) != 0)
 			return SK_DROP;
-		half = (__u16 *)&ctx->local_ip4;
-		if (half[0] != 0 || half[1] != 0)
+		if (LSW(ctx->local_ip4, 0) != 0 || LSW(ctx->local_ip4, 1) != 0)
 			return SK_DROP;
 	}
 
 	/* Narrow loads from IPv6 fields */
 	if (!v4) {
-		/* Expenct non-:: IP in remote_ip6 */
-		byte = (__u8 *)&ctx->remote_ip6;
-		if (byte[0] == 0 && byte[1] == 0 &&
-		    byte[2] == 0 && byte[3] == 0 &&
-		    byte[4] == 0 && byte[5] == 0 &&
-		    byte[6] == 0 && byte[7] == 0 &&
-		    byte[8] == 0 && byte[9] == 0 &&
-		    byte[10] == 0 && byte[11] == 0 &&
-		    byte[12] == 0 && byte[13] == 0 &&
-		    byte[14] == 0 && byte[15] == 0)
+		/* Expect non-:: IP in remote_ip6 */
+		if (LSB(ctx->remote_ip6[0], 0) == 0 && LSB(ctx->remote_ip6[0], 1) == 0 &&
+		    LSB(ctx->remote_ip6[0], 2) == 0 && LSB(ctx->remote_ip6[0], 3) == 0 &&
+		    LSB(ctx->remote_ip6[1], 0) == 0 && LSB(ctx->remote_ip6[1], 1) == 0 &&
+		    LSB(ctx->remote_ip6[1], 2) == 0 && LSB(ctx->remote_ip6[1], 3) == 0 &&
+		    LSB(ctx->remote_ip6[2], 0) == 0 && LSB(ctx->remote_ip6[2], 1) == 0 &&
+		    LSB(ctx->remote_ip6[2], 2) == 0 && LSB(ctx->remote_ip6[2], 3) == 0 &&
+		    LSB(ctx->remote_ip6[3], 0) == 0 && LSB(ctx->remote_ip6[3], 1) == 0 &&
+		    LSB(ctx->remote_ip6[3], 2) == 0 && LSB(ctx->remote_ip6[3], 3) == 0)
 			return SK_DROP;
-		half = (__u16 *)&ctx->remote_ip6;
-		if (half[0] == 0 && half[1] == 0 &&
-		    half[2] == 0 && half[3] == 0 &&
-		    half[4] == 0 && half[5] == 0 &&
-		    half[6] == 0 && half[7] == 0)
+		if (LSW(ctx->remote_ip6[0], 0) == 0 && LSW(ctx->remote_ip6[0], 1) == 0 &&
+		    LSW(ctx->remote_ip6[1], 0) == 0 && LSW(ctx->remote_ip6[1], 1) == 0 &&
+		    LSW(ctx->remote_ip6[2], 0) == 0 && LSW(ctx->remote_ip6[2], 1) == 0 &&
+		    LSW(ctx->remote_ip6[3], 0) == 0 && LSW(ctx->remote_ip6[3], 1) == 0)
 			return SK_DROP;
-
 		/* Expect DST_IP6 in local_ip6 */
-		byte = (__u8 *)&ctx->local_ip6;
-		if (byte[0] != ((DST_IP6[0] >>  0) & 0xff) ||
-		    byte[1] != ((DST_IP6[0] >>  8) & 0xff) ||
-		    byte[2] != ((DST_IP6[0] >> 16) & 0xff) ||
-		    byte[3] != ((DST_IP6[0] >> 24) & 0xff) ||
-		    byte[4] != ((DST_IP6[1] >>  0) & 0xff) ||
-		    byte[5] != ((DST_IP6[1] >>  8) & 0xff) ||
-		    byte[6] != ((DST_IP6[1] >> 16) & 0xff) ||
-		    byte[7] != ((DST_IP6[1] >> 24) & 0xff) ||
-		    byte[8] != ((DST_IP6[2] >>  0) & 0xff) ||
-		    byte[9] != ((DST_IP6[2] >>  8) & 0xff) ||
-		    byte[10] != ((DST_IP6[2] >> 16) & 0xff) ||
-		    byte[11] != ((DST_IP6[2] >> 24) & 0xff) ||
-		    byte[12] != ((DST_IP6[3] >>  0) & 0xff) ||
-		    byte[13] != ((DST_IP6[3] >>  8) & 0xff) ||
-		    byte[14] != ((DST_IP6[3] >> 16) & 0xff) ||
-		    byte[15] != ((DST_IP6[3] >> 24) & 0xff))
+		if (LSB(ctx->local_ip6[0], 0) != ((DST_IP6[0] >> 0) & 0xff) ||
+		    LSB(ctx->local_ip6[0], 1) != ((DST_IP6[0] >> 8) & 0xff) ||
+		    LSB(ctx->local_ip6[0], 2) != ((DST_IP6[0] >> 16) & 0xff) ||
+		    LSB(ctx->local_ip6[0], 3) != ((DST_IP6[0] >> 24) & 0xff) ||
+		    LSB(ctx->local_ip6[1], 0) != ((DST_IP6[1] >> 0) & 0xff) ||
+		    LSB(ctx->local_ip6[1], 1) != ((DST_IP6[1] >> 8) & 0xff) ||
+		    LSB(ctx->local_ip6[1], 2) != ((DST_IP6[1] >> 16) & 0xff) ||
+		    LSB(ctx->local_ip6[1], 3) != ((DST_IP6[1] >> 24) & 0xff) ||
+		    LSB(ctx->local_ip6[2], 0) != ((DST_IP6[2] >> 0) & 0xff) ||
+		    LSB(ctx->local_ip6[2], 1) != ((DST_IP6[2] >> 8) & 0xff) ||
+		    LSB(ctx->local_ip6[2], 2) != ((DST_IP6[2] >> 16) & 0xff) ||
+		    LSB(ctx->local_ip6[2], 3) != ((DST_IP6[2] >> 24) & 0xff) ||
+		    LSB(ctx->local_ip6[3], 0) != ((DST_IP6[3] >> 0) & 0xff) ||
+		    LSB(ctx->local_ip6[3], 1) != ((DST_IP6[3] >> 8) & 0xff) ||
+		    LSB(ctx->local_ip6[3], 2) != ((DST_IP6[3] >> 16) & 0xff) ||
+		    LSB(ctx->local_ip6[3], 3) != ((DST_IP6[3] >> 24) & 0xff))
 			return SK_DROP;
-		half = (__u16 *)&ctx->local_ip6;
-		if (half[0] != ((DST_IP6[0] >>  0) & 0xffff) ||
-		    half[1] != ((DST_IP6[0] >> 16) & 0xffff) ||
-		    half[2] != ((DST_IP6[1] >>  0) & 0xffff) ||
-		    half[3] != ((DST_IP6[1] >> 16) & 0xffff) ||
-		    half[4] != ((DST_IP6[2] >>  0) & 0xffff) ||
-		    half[5] != ((DST_IP6[2] >> 16) & 0xffff) ||
-		    half[6] != ((DST_IP6[3] >>  0) & 0xffff) ||
-		    half[7] != ((DST_IP6[3] >> 16) & 0xffff))
+		if (LSW(ctx->local_ip6[0], 0) != ((DST_IP6[0] >> 0) & 0xffff) ||
+		    LSW(ctx->local_ip6[0], 1) != ((DST_IP6[0] >> 16) & 0xffff) ||
+		    LSW(ctx->local_ip6[1], 0) != ((DST_IP6[1] >> 0) & 0xffff) ||
+		    LSW(ctx->local_ip6[1], 1) != ((DST_IP6[1] >> 16) & 0xffff) ||
+		    LSW(ctx->local_ip6[2], 0) != ((DST_IP6[2] >> 0) & 0xffff) ||
+		    LSW(ctx->local_ip6[2], 1) != ((DST_IP6[2] >> 16) & 0xffff) ||
+		    LSW(ctx->local_ip6[3], 0) != ((DST_IP6[3] >> 0) & 0xffff) ||
+		    LSW(ctx->local_ip6[3], 1) != ((DST_IP6[3] >> 16) & 0xffff))
 			return SK_DROP;
 	} else {
 		/* Expect :: IPs when family != AF_INET6 */
-		byte = (__u8 *)&ctx->remote_ip6;
-		if (byte[0] != 0 || byte[1] != 0 ||
-		    byte[2] != 0 || byte[3] != 0 ||
-		    byte[4] != 0 || byte[5] != 0 ||
-		    byte[6] != 0 || byte[7] != 0 ||
-		    byte[8] != 0 || byte[9] != 0 ||
-		    byte[10] != 0 || byte[11] != 0 ||
-		    byte[12] != 0 || byte[13] != 0 ||
-		    byte[14] != 0 || byte[15] != 0)
+		if (LSB(ctx->remote_ip6[0], 0) != 0 || LSB(ctx->remote_ip6[0], 1) != 0 ||
+		    LSB(ctx->remote_ip6[0], 2) != 0 || LSB(ctx->remote_ip6[0], 3) != 0 ||
+		    LSB(ctx->remote_ip6[1], 0) != 0 || LSB(ctx->remote_ip6[1], 1) != 0 ||
+		    LSB(ctx->remote_ip6[1], 2) != 0 || LSB(ctx->remote_ip6[1], 3) != 0 ||
+		    LSB(ctx->remote_ip6[2], 0) != 0 || LSB(ctx->remote_ip6[2], 1) != 0 ||
+		    LSB(ctx->remote_ip6[2], 2) != 0 || LSB(ctx->remote_ip6[2], 3) != 0 ||
+		    LSB(ctx->remote_ip6[3], 0) != 0 || LSB(ctx->remote_ip6[3], 1) != 0 ||
+		    LSB(ctx->remote_ip6[3], 2) != 0 || LSB(ctx->remote_ip6[3], 3) != 0)
 			return SK_DROP;
-		half = (__u16 *)&ctx->remote_ip6;
-		if (half[0] != 0 || half[1] != 0 ||
-		    half[2] != 0 || half[3] != 0 ||
-		    half[4] != 0 || half[5] != 0 ||
-		    half[6] != 0 || half[7] != 0)
+		if (LSW(ctx->remote_ip6[0], 0) != 0 || LSW(ctx->remote_ip6[0], 1) != 0 ||
+		    LSW(ctx->remote_ip6[1], 0) != 0 || LSW(ctx->remote_ip6[1], 1) != 0 ||
+		    LSW(ctx->remote_ip6[2], 0) != 0 || LSW(ctx->remote_ip6[2], 1) != 0 ||
+		    LSW(ctx->remote_ip6[3], 0) != 0 || LSW(ctx->remote_ip6[3], 1) != 0)
 			return SK_DROP;
 
-		byte = (__u8 *)&ctx->local_ip6;
-		if (byte[0] != 0 || byte[1] != 0 ||
-		    byte[2] != 0 || byte[3] != 0 ||
-		    byte[4] != 0 || byte[5] != 0 ||
-		    byte[6] != 0 || byte[7] != 0 ||
-		    byte[8] != 0 || byte[9] != 0 ||
-		    byte[10] != 0 || byte[11] != 0 ||
-		    byte[12] != 0 || byte[13] != 0 ||
-		    byte[14] != 0 || byte[15] != 0)
+		if (LSB(ctx->local_ip6[0], 0) != 0 || LSB(ctx->local_ip6[0], 1) != 0 ||
+		    LSB(ctx->local_ip6[0], 2) != 0 || LSB(ctx->local_ip6[0], 3) != 0 ||
+		    LSB(ctx->local_ip6[1], 0) != 0 || LSB(ctx->local_ip6[1], 1) != 0 ||
+		    LSB(ctx->local_ip6[1], 2) != 0 || LSB(ctx->local_ip6[1], 3) != 0 ||
+		    LSB(ctx->local_ip6[2], 0) != 0 || LSB(ctx->local_ip6[2], 1) != 0 ||
+		    LSB(ctx->local_ip6[2], 2) != 0 || LSB(ctx->local_ip6[2], 3) != 0 ||
+		    LSB(ctx->local_ip6[3], 0) != 0 || LSB(ctx->local_ip6[3], 1) != 0 ||
+		    LSB(ctx->local_ip6[3], 2) != 0 || LSB(ctx->local_ip6[3], 3) != 0)
 			return SK_DROP;
-		half = (__u16 *)&ctx->local_ip6;
-		if (half[0] != 0 || half[1] != 0 ||
-		    half[2] != 0 || half[3] != 0 ||
-		    half[4] != 0 || half[5] != 0 ||
-		    half[6] != 0 || half[7] != 0)
+		if (LSW(ctx->remote_ip6[0], 0) != 0 || LSW(ctx->remote_ip6[0], 1) != 0 ||
+		    LSW(ctx->remote_ip6[1], 0) != 0 || LSW(ctx->remote_ip6[1], 1) != 0 ||
+		    LSW(ctx->remote_ip6[2], 0) != 0 || LSW(ctx->remote_ip6[2], 1) != 0 ||
+		    LSW(ctx->remote_ip6[3], 0) != 0 || LSW(ctx->remote_ip6[3], 1) != 0)
 			return SK_DROP;
 	}
 
diff --git a/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c b/tools/testing/selftests/bpf/progs/test_sock_fields.c
index 9bcaa37f476a..81b57b9aaaea 100644
--- a/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_sock_fields.c
@@ -7,19 +7,7 @@
 
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
-
-enum bpf_addr_array_idx {
-	ADDR_SRV_IDX,
-	ADDR_CLI_IDX,
-	__NR_BPF_ADDR_ARRAY_IDX,
-};
-
-enum bpf_result_array_idx {
-	EGRESS_SRV_IDX,
-	EGRESS_CLI_IDX,
-	INGRESS_LISTEN_IDX,
-	__NR_BPF_RESULT_ARRAY_IDX,
-};
+#include "bpf_tcp_helpers.h"
 
 enum bpf_linum_array_idx {
 	EGRESS_LINUM_IDX,
@@ -29,27 +17,6 @@ enum bpf_linum_array_idx {
 
 struct {
 	__uint(type, BPF_MAP_TYPE_ARRAY);
-	__uint(max_entries, __NR_BPF_ADDR_ARRAY_IDX);
-	__type(key, __u32);
-	__type(value, struct sockaddr_in6);
-} addr_map SEC(".maps");
-
-struct {
-	__uint(type, BPF_MAP_TYPE_ARRAY);
-	__uint(max_entries, __NR_BPF_RESULT_ARRAY_IDX);
-	__type(key, __u32);
-	__type(value, struct bpf_sock);
-} sock_result_map SEC(".maps");
-
-struct {
-	__uint(type, BPF_MAP_TYPE_ARRAY);
-	__uint(max_entries, __NR_BPF_RESULT_ARRAY_IDX);
-	__type(key, __u32);
-	__type(value, struct bpf_tcp_sock);
-} tcp_sock_result_map SEC(".maps");
-
-struct {
-	__uint(type, BPF_MAP_TYPE_ARRAY);
 	__uint(max_entries, __NR_BPF_LINUM_ARRAY_IDX);
 	__type(key, __u32);
 	__type(value, __u32);
@@ -74,6 +41,17 @@ struct {
 	__type(value, struct bpf_spinlock_cnt);
 } sk_pkt_out_cnt10 SEC(".maps");
 
+struct bpf_tcp_sock listen_tp = {};
+struct sockaddr_in6 srv_sa6 = {};
+struct bpf_tcp_sock cli_tp = {};
+struct bpf_tcp_sock srv_tp = {};
+struct bpf_sock listen_sk = {};
+struct bpf_sock srv_sk = {};
+struct bpf_sock cli_sk = {};
+__u64 parent_cg_id = 0;
+__u64 child_cg_id = 0;
+__u64 lsndtime = 0;
+
 static bool is_loopback6(__u32 *a6)
 {
 	return !a6[0] && !a6[1] && !a6[2] && a6[3] == bpf_htonl(1);
@@ -130,62 +108,86 @@ static void tpcpy(struct bpf_tcp_sock *dst,
 	dst->bytes_acked = src->bytes_acked;
 }
 
-#define RETURN {						\
+/* Always return CG_OK so that no pkt will be filtered out */
+#define CG_OK 1
+
+#define RET_LOG() ({						\
 	linum = __LINE__;					\
-	bpf_map_update_elem(&linum_map, &linum_idx, &linum, 0);	\
-	return 1;						\
-}
+	bpf_map_update_elem(&linum_map, &linum_idx, &linum, BPF_NOEXIST);	\
+	return CG_OK;						\
+})
 
 SEC("cgroup_skb/egress")
 int egress_read_sock_fields(struct __sk_buff *skb)
 {
 	struct bpf_spinlock_cnt cli_cnt_init = { .lock = 0, .cnt = 0xeB9F };
-	__u32 srv_idx = ADDR_SRV_IDX, cli_idx = ADDR_CLI_IDX, result_idx;
 	struct bpf_spinlock_cnt *pkt_out_cnt, *pkt_out_cnt10;
-	struct sockaddr_in6 *srv_sa6, *cli_sa6;
 	struct bpf_tcp_sock *tp, *tp_ret;
 	struct bpf_sock *sk, *sk_ret;
 	__u32 linum, linum_idx;
+	struct tcp_sock *ktp;
 
 	linum_idx = EGRESS_LINUM_IDX;
 
 	sk = skb->sk;
-	if (!sk || sk->state == 10)
-		RETURN;
+	if (!sk)
+		RET_LOG();
 
+	/* Not the testing egress traffic or
+	 * TCP_LISTEN (10) socket will be copied at the ingress side.
+	 */
+	if (sk->family != AF_INET6 || !is_loopback6(sk->src_ip6) ||
+	    sk->state == 10)
+		return CG_OK;
+
+	if (sk->src_port == bpf_ntohs(srv_sa6.sin6_port)) {
+		/* Server socket */
+		sk_ret = &srv_sk;
+		tp_ret = &srv_tp;
+	} else if (sk->dst_port == srv_sa6.sin6_port) {
+		/* Client socket */
+		sk_ret = &cli_sk;
+		tp_ret = &cli_tp;
+	} else {
+		/* Not the testing egress traffic */
+		return CG_OK;
+	}
+
+	/* It must be a fullsock for cgroup_skb/egress prog */
 	sk = bpf_sk_fullsock(sk);
-	if (!sk || sk->family != AF_INET6 || sk->protocol != IPPROTO_TCP ||
-	    !is_loopback6(sk->src_ip6))
-		RETURN;
+	if (!sk)
+		RET_LOG();
+
+	/* Not the testing egress traffic */
+	if (sk->protocol != IPPROTO_TCP)
+		return CG_OK;
 
 	tp = bpf_tcp_sock(sk);
 	if (!tp)
-		RETURN;
+		RET_LOG();
 
-	srv_sa6 = bpf_map_lookup_elem(&addr_map, &srv_idx);
-	cli_sa6 = bpf_map_lookup_elem(&addr_map, &cli_idx);
-	if (!srv_sa6 || !cli_sa6)
-		RETURN;
+	skcpy(sk_ret, sk);
+	tpcpy(tp_ret, tp);
 
-	if (sk->src_port == bpf_ntohs(srv_sa6->sin6_port))
-		result_idx = EGRESS_SRV_IDX;
-	else if (sk->src_port == bpf_ntohs(cli_sa6->sin6_port))
-		result_idx = EGRESS_CLI_IDX;
-	else
-		RETURN;
+	if (sk_ret == &srv_sk) {
+		ktp = bpf_skc_to_tcp_sock(sk);
 
-	sk_ret = bpf_map_lookup_elem(&sock_result_map, &result_idx);
-	tp_ret = bpf_map_lookup_elem(&tcp_sock_result_map, &result_idx);
-	if (!sk_ret || !tp_ret)
-		RETURN;
+		if (!ktp)
+			RET_LOG();
 
-	skcpy(sk_ret, sk);
-	tpcpy(tp_ret, tp);
+		lsndtime = ktp->lsndtime;
+
+		child_cg_id = bpf_sk_cgroup_id(ktp);
+		if (!child_cg_id)
+			RET_LOG();
+
+		parent_cg_id = bpf_sk_ancestor_cgroup_id(ktp, 2);
+		if (!parent_cg_id)
+			RET_LOG();
 
-	if (result_idx == EGRESS_SRV_IDX) {
 		/* The userspace has created it for srv sk */
-		pkt_out_cnt = bpf_sk_storage_get(&sk_pkt_out_cnt, sk, 0, 0);
-		pkt_out_cnt10 = bpf_sk_storage_get(&sk_pkt_out_cnt10, sk,
+		pkt_out_cnt = bpf_sk_storage_get(&sk_pkt_out_cnt, ktp, 0, 0);
+		pkt_out_cnt10 = bpf_sk_storage_get(&sk_pkt_out_cnt10, ktp,
 						   0, 0);
 	} else {
 		pkt_out_cnt = bpf_sk_storage_get(&sk_pkt_out_cnt, sk,
@@ -197,7 +199,7 @@ int egress_read_sock_fields(struct __sk_buff *skb)
 	}
 
 	if (!pkt_out_cnt || !pkt_out_cnt10)
-		RETURN;
+		RET_LOG();
 
 	/* Even both cnt and cnt10 have lock defined in their BTF,
 	 * intentionally one cnt takes lock while one does not
@@ -208,48 +210,44 @@ int egress_read_sock_fields(struct __sk_buff *skb)
 	pkt_out_cnt10->cnt += 10;
 	bpf_spin_unlock(&pkt_out_cnt10->lock);
 
-	RETURN;
+	return CG_OK;
 }
 
 SEC("cgroup_skb/ingress")
 int ingress_read_sock_fields(struct __sk_buff *skb)
 {
-	__u32 srv_idx = ADDR_SRV_IDX, result_idx = INGRESS_LISTEN_IDX;
-	struct bpf_tcp_sock *tp, *tp_ret;
-	struct bpf_sock *sk, *sk_ret;
-	struct sockaddr_in6 *srv_sa6;
+	struct bpf_tcp_sock *tp;
 	__u32 linum, linum_idx;
+	struct bpf_sock *sk;
 
 	linum_idx = INGRESS_LINUM_IDX;
 
 	sk = skb->sk;
-	if (!sk || sk->family != AF_INET6 || !is_loopback6(sk->src_ip6))
-		RETURN;
+	if (!sk)
+		RET_LOG();
 
-	srv_sa6 = bpf_map_lookup_elem(&addr_map, &srv_idx);
-	if (!srv_sa6 || sk->src_port != bpf_ntohs(srv_sa6->sin6_port))
-		RETURN;
+	/* Not the testing ingress traffic to the server */
+	if (sk->family != AF_INET6 || !is_loopback6(sk->src_ip6) ||
+	    sk->src_port != bpf_ntohs(srv_sa6.sin6_port))
+		return CG_OK;
 
-	if (sk->state != 10 && sk->state != 12)
-		RETURN;
+	/* Only interested in TCP_LISTEN */
+	if (sk->state != 10)
+		return CG_OK;
 
-	sk = bpf_get_listener_sock(sk);
+	/* It must be a fullsock for cgroup_skb/ingress prog */
+	sk = bpf_sk_fullsock(sk);
 	if (!sk)
-		RETURN;
+		RET_LOG();
 
 	tp = bpf_tcp_sock(sk);
 	if (!tp)
-		RETURN;
-
-	sk_ret = bpf_map_lookup_elem(&sock_result_map, &result_idx);
-	tp_ret = bpf_map_lookup_elem(&tcp_sock_result_map, &result_idx);
-	if (!sk_ret || !tp_ret)
-		RETURN;
+		RET_LOG();
 
-	skcpy(sk_ret, sk);
-	tpcpy(tp_ret, tp);
+	skcpy(&listen_sk, sk);
+	tpcpy(&listen_tp, tp);
 
-	RETURN;
+	return CG_OK;
 }
 
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_subprogs.c b/tools/testing/selftests/bpf/progs/test_subprogs.c
new file mode 100644
index 000000000000..d3c5673c0218
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_subprogs.c
@@ -0,0 +1,103 @@
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
+
+const char LICENSE[] SEC("license") = "GPL";
+
+__noinline int sub1(int x)
+{
+	return x + 1;
+}
+
+static __noinline int sub5(int v);
+
+__noinline int sub2(int y)
+{
+	return sub5(y + 2);
+}
+
+static __noinline int sub3(int z)
+{
+	return z + 3 + sub1(4);
+}
+
+static __noinline int sub4(int w)
+{
+	return w + sub3(5) + sub1(6);
+}
+
+/* sub5() is an identitify function, just to test weirder functions layout and
+ * call patterns
+ */
+static __noinline int sub5(int v)
+{
+	return sub1(v) - 1; /* compensates sub1()'s + 1 */
+}
+
+/* unfortunately verifier rejects `struct task_struct *t` as an unkown pointer
+ * type, so we need to accept pointer as integer and then cast it inside the
+ * function
+ */
+__noinline int get_task_tgid(uintptr_t t)
+{
+	/* this ensures that CO-RE relocs work in multi-subprogs .text */
+	return BPF_CORE_READ((struct task_struct *)(void *)t, tgid);
+}
+
+int res1 = 0;
+int res2 = 0;
+int res3 = 0;
+int res4 = 0;
+
+SEC("raw_tp/sys_enter")
+int prog1(void *ctx)
+{
+	/* perform some CO-RE relocations to ensure they work with multi-prog
+	 * sections correctly
+	 */
+	struct task_struct *t = (void *)bpf_get_current_task();
+
+	if (!BPF_CORE_READ(t, pid) || !get_task_tgid((uintptr_t)t))
+		return 1;
+
+	res1 = sub1(1) + sub3(2); /* (1 + 1) + (2 + 3 + (4 + 1)) = 12 */
+	return 0;
+}
+
+SEC("raw_tp/sys_exit")
+int prog2(void *ctx)
+{
+	struct task_struct *t = (void *)bpf_get_current_task();
+
+	if (!BPF_CORE_READ(t, pid) || !get_task_tgid((uintptr_t)t))
+		return 1;
+
+	res2 = sub2(3) + sub3(4); /* (3 + 2) + (4 + 3 + (4 + 1)) = 17 */
+	return 0;
+}
+
+/* prog3 has the same section name as prog1 */
+SEC("raw_tp/sys_enter")
+int prog3(void *ctx)
+{
+	struct task_struct *t = (void *)bpf_get_current_task();
+
+	if (!BPF_CORE_READ(t, pid) || !get_task_tgid((uintptr_t)t))
+		return 1;
+
+	res3 = sub3(5) + 6; /* (5 + 3 + (4 + 1)) + 6 = 19 */
+	return 0;
+}
+
+/* prog4 has the same section name as prog2 */
+SEC("raw_tp/sys_exit")
+int prog4(void *ctx)
+{
+	struct task_struct *t = (void *)bpf_get_current_task();
+
+	if (!BPF_CORE_READ(t, pid) || !get_task_tgid((uintptr_t)t))
+		return 1;
+
+	res4 = sub4(7) + sub1(8); /* (7 + (5 + 3 + (4 + 1)) + (6 + 1)) + (8 + 1) = 36 */
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_sysctl_loop1.c b/tools/testing/selftests/bpf/progs/test_sysctl_loop1.c
index 458b0d69133e..553a282d816a 100644
--- a/tools/testing/selftests/bpf/progs/test_sysctl_loop1.c
+++ b/tools/testing/selftests/bpf/progs/test_sysctl_loop1.c
@@ -18,11 +18,11 @@
 #define MAX_ULONG_STR_LEN 7
 #define MAX_VALUE_STR_LEN (TCP_MEM_LOOPS * MAX_ULONG_STR_LEN)
 
+const char tcp_mem_name[] = "net/ipv4/tcp_mem/very_very_very_very_long_pointless_string";
 static __always_inline int is_tcp_mem(struct bpf_sysctl *ctx)
 {
-	volatile char tcp_mem_name[] = "net/ipv4/tcp_mem/very_very_very_very_long_pointless_string";
 	unsigned char i;
-	char name[64];
+	char name[sizeof(tcp_mem_name)];
 	int ret;
 
 	memset(name, 0, sizeof(name));
diff --git a/tools/testing/selftests/bpf/progs/test_sysctl_loop2.c b/tools/testing/selftests/bpf/progs/test_sysctl_loop2.c
index b2e6f9b0894d..2b64bc563a12 100644
--- a/tools/testing/selftests/bpf/progs/test_sysctl_loop2.c
+++ b/tools/testing/selftests/bpf/progs/test_sysctl_loop2.c
@@ -18,11 +18,11 @@
 #define MAX_ULONG_STR_LEN 7
 #define MAX_VALUE_STR_LEN (TCP_MEM_LOOPS * MAX_ULONG_STR_LEN)
 
+const char tcp_mem_name[] = "net/ipv4/tcp_mem/very_very_very_very_long_pointless_string_to_stress_byte_loop";
 static __attribute__((noinline)) int is_tcp_mem(struct bpf_sysctl *ctx)
 {
-	volatile char tcp_mem_name[] = "net/ipv4/tcp_mem/very_very_very_very_long_pointless_string_to_stress_byte_loop";
 	unsigned char i;
-	char name[64];
+	char name[sizeof(tcp_mem_name)];
 	int ret;
 
 	memset(name, 0, sizeof(name));
diff --git a/tools/testing/selftests/bpf/progs/test_sysctl_prog.c b/tools/testing/selftests/bpf/progs/test_sysctl_prog.c
index 50525235380e..5489823c83fc 100644
--- a/tools/testing/selftests/bpf/progs/test_sysctl_prog.c
+++ b/tools/testing/selftests/bpf/progs/test_sysctl_prog.c
@@ -19,11 +19,11 @@
 #define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
 #endif
 
+const char tcp_mem_name[] = "net/ipv4/tcp_mem";
 static __always_inline int is_tcp_mem(struct bpf_sysctl *ctx)
 {
-	char tcp_mem_name[] = "net/ipv4/tcp_mem";
 	unsigned char i;
-	char name[64];
+	char name[sizeof(tcp_mem_name)];
 	int ret;
 
 	memset(name, 0, sizeof(name));
diff --git a/tools/testing/selftests/bpf/progs/test_tc_neigh.c b/tools/testing/selftests/bpf/progs/test_tc_neigh.c
new file mode 100644
index 000000000000..889a72c3024f
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_tc_neigh.c
@@ -0,0 +1,144 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stdint.h>
+#include <stdbool.h>
+
+#include <linux/bpf.h>
+#include <linux/stddef.h>
+#include <linux/pkt_cls.h>
+#include <linux/if_ether.h>
+#include <linux/in.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+#ifndef barrier_data
+# define barrier_data(ptr)	asm volatile("": :"r"(ptr) :"memory")
+#endif
+
+#ifndef ctx_ptr
+# define ctx_ptr(field)		(void *)(long)(field)
+#endif
+
+#define dst_to_src_tmp		0xeeddddeeU
+#define src_to_dst_tmp		0xeeffffeeU
+
+#define ip4_src			0xac100164 /* 172.16.1.100 */
+#define ip4_dst			0xac100264 /* 172.16.2.100 */
+
+#define ip6_src			{ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, \
+				  0x00, 0x01, 0xde, 0xad, 0xbe, 0xef, 0xca, 0xfe }
+#define ip6_dst			{ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, \
+				  0x00, 0x02, 0xde, 0xad, 0xbe, 0xef, 0xca, 0xfe }
+
+#ifndef v6_equal
+# define v6_equal(a, b)		(a.s6_addr32[0] == b.s6_addr32[0] && \
+				 a.s6_addr32[1] == b.s6_addr32[1] && \
+				 a.s6_addr32[2] == b.s6_addr32[2] && \
+				 a.s6_addr32[3] == b.s6_addr32[3])
+#endif
+
+static __always_inline bool is_remote_ep_v4(struct __sk_buff *skb,
+					    __be32 addr)
+{
+	void *data_end = ctx_ptr(skb->data_end);
+	void *data = ctx_ptr(skb->data);
+	struct iphdr *ip4h;
+
+	if (data + sizeof(struct ethhdr) > data_end)
+		return false;
+
+	ip4h = (struct iphdr *)(data + sizeof(struct ethhdr));
+	if ((void *)(ip4h + 1) > data_end)
+		return false;
+
+	return ip4h->daddr == addr;
+}
+
+static __always_inline bool is_remote_ep_v6(struct __sk_buff *skb,
+					    struct in6_addr addr)
+{
+	void *data_end = ctx_ptr(skb->data_end);
+	void *data = ctx_ptr(skb->data);
+	struct ipv6hdr *ip6h;
+
+	if (data + sizeof(struct ethhdr) > data_end)
+		return false;
+
+	ip6h = (struct ipv6hdr *)(data + sizeof(struct ethhdr));
+	if ((void *)(ip6h + 1) > data_end)
+		return false;
+
+	return v6_equal(ip6h->daddr, addr);
+}
+
+SEC("chk_neigh") int tc_chk(struct __sk_buff *skb)
+{
+	void *data_end = ctx_ptr(skb->data_end);
+	void *data = ctx_ptr(skb->data);
+	__u32 *raw = data;
+
+	if (data + sizeof(struct ethhdr) > data_end)
+		return TC_ACT_SHOT;
+
+	return !raw[0] && !raw[1] && !raw[2] ? TC_ACT_SHOT : TC_ACT_OK;
+}
+
+SEC("dst_ingress") int tc_dst(struct __sk_buff *skb)
+{
+	int idx = dst_to_src_tmp;
+	__u8 zero[ETH_ALEN * 2];
+	bool redirect = false;
+
+	switch (skb->protocol) {
+	case __bpf_constant_htons(ETH_P_IP):
+		redirect = is_remote_ep_v4(skb, __bpf_constant_htonl(ip4_src));
+		break;
+	case __bpf_constant_htons(ETH_P_IPV6):
+		redirect = is_remote_ep_v6(skb, (struct in6_addr)ip6_src);
+		break;
+	}
+
+	if (!redirect)
+		return TC_ACT_OK;
+
+	barrier_data(&idx);
+	idx = bpf_ntohl(idx);
+
+	__builtin_memset(&zero, 0, sizeof(zero));
+	if (bpf_skb_store_bytes(skb, 0, &zero, sizeof(zero), 0) < 0)
+		return TC_ACT_SHOT;
+
+	return bpf_redirect_neigh(idx, 0);
+}
+
+SEC("src_ingress") int tc_src(struct __sk_buff *skb)
+{
+	int idx = src_to_dst_tmp;
+	__u8 zero[ETH_ALEN * 2];
+	bool redirect = false;
+
+	switch (skb->protocol) {
+	case __bpf_constant_htons(ETH_P_IP):
+		redirect = is_remote_ep_v4(skb, __bpf_constant_htonl(ip4_dst));
+		break;
+	case __bpf_constant_htons(ETH_P_IPV6):
+		redirect = is_remote_ep_v6(skb, (struct in6_addr)ip6_dst);
+		break;
+	}
+
+	if (!redirect)
+		return TC_ACT_OK;
+
+	barrier_data(&idx);
+	idx = bpf_ntohl(idx);
+
+	__builtin_memset(&zero, 0, sizeof(zero));
+	if (bpf_skb_store_bytes(skb, 0, &zero, sizeof(zero), 0) < 0)
+		return TC_ACT_SHOT;
+
+	return bpf_redirect_neigh(idx, 0);
+}
+
+char __license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_trace_ext.c b/tools/testing/selftests/bpf/progs/test_trace_ext.c
new file mode 100644
index 000000000000..d19a634d0e78
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_trace_ext.c
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Facebook
+#include <linux/bpf.h>
+#include <stdbool.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+#include <bpf/bpf_tracing.h>
+
+__u64 ext_called = 0;
+
+SEC("freplace/test_pkt_md_access")
+int test_pkt_md_access_new(struct __sk_buff *skb)
+{
+	ext_called = skb->len;
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_trace_ext_tracing.c b/tools/testing/selftests/bpf/progs/test_trace_ext_tracing.c
new file mode 100644
index 000000000000..52f3baf98f20
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_trace_ext_tracing.c
@@ -0,0 +1,25 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+__u64 fentry_called = 0;
+
+SEC("fentry/test_pkt_md_access_new")
+int BPF_PROG(fentry, struct sk_buff *skb)
+{
+	fentry_called = skb->len;
+	return 0;
+}
+
+__u64 fexit_called = 0;
+
+SEC("fexit/test_pkt_md_access_new")
+int BPF_PROG(fexit, struct sk_buff *skb)
+{
+	fexit_called = skb->len;
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_noinline.c b/tools/testing/selftests/bpf/progs/test_xdp_noinline.c
index 8beecec166d9..3a67921f62b5 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_noinline.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_noinline.c
@@ -16,7 +16,7 @@
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
 
-static __u32 rol32(__u32 word, unsigned int shift)
+static __always_inline __u32 rol32(__u32 word, unsigned int shift)
 {
 	return (word << shift) | (word >> ((-shift) & 31));
 }
@@ -49,7 +49,7 @@ static __u32 rol32(__u32 word, unsigned int shift)
 
 typedef unsigned int u32;
 
-static __attribute__ ((noinline))
+static __noinline
 u32 jhash(const void *key, u32 length, u32 initval)
 {
 	u32 a, b, c;
@@ -86,7 +86,7 @@ u32 jhash(const void *key, u32 length, u32 initval)
 	return c;
 }
 
-__attribute__ ((noinline))
+__noinline
 u32 __jhash_nwords(u32 a, u32 b, u32 c, u32 initval)
 {
 	a += initval;
@@ -96,7 +96,7 @@ u32 __jhash_nwords(u32 a, u32 b, u32 c, u32 initval)
 	return c;
 }
 
-__attribute__ ((noinline))
+__noinline
 u32 jhash_2words(u32 a, u32 b, u32 initval)
 {
 	return __jhash_nwords(a, b, 0, initval + JHASH_INITVAL + (2 << 2));
@@ -213,7 +213,7 @@ struct eth_hdr {
 	unsigned short eth_proto;
 };
 
-static inline __u64 calc_offset(bool is_ipv6, bool is_icmp)
+static __noinline __u64 calc_offset(bool is_ipv6, bool is_icmp)
 {
 	__u64 off = sizeof(struct eth_hdr);
 	if (is_ipv6) {
@@ -797,8 +797,8 @@ out:
 	return XDP_DROP;
 }
 
-__attribute__ ((section("xdp-test"), used))
-int balancer_ingress(struct xdp_md *ctx)
+SEC("xdp-test-v4")
+int balancer_ingress_v4(struct xdp_md *ctx)
 {
 	void *data = (void *)(long)ctx->data;
 	void *data_end = (void *)(long)ctx->data_end;
@@ -812,11 +812,27 @@ int balancer_ingress(struct xdp_md *ctx)
 	eth_proto = bpf_ntohs(eth->eth_proto);
 	if (eth_proto == ETH_P_IP)
 		return process_packet(data, nh_off, data_end, 0, ctx);
-	else if (eth_proto == ETH_P_IPV6)
+	else
+		return XDP_DROP;
+}
+
+SEC("xdp-test-v6")
+int balancer_ingress_v6(struct xdp_md *ctx)
+{
+	void *data = (void *)(long)ctx->data;
+	void *data_end = (void *)(long)ctx->data_end;
+	struct eth_hdr *eth = data;
+	__u32 eth_proto;
+	__u32 nh_off;
+
+	nh_off = sizeof(struct eth_hdr);
+	if (data + nh_off > data_end)
+		return XDP_DROP;
+	eth_proto = bpf_ntohs(eth->eth_proto);
+	if (eth_proto == ETH_P_IPV6)
 		return process_packet(data, nh_off, data_end, 1, ctx);
 	else
 		return XDP_DROP;
 }
 
-char _license[] __attribute__ ((section("license"), used)) = "GPL";
-int _version __attribute__ ((section("version"), used)) = 1;
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_bpftool_build.sh b/tools/testing/selftests/bpf/test_bpftool_build.sh
index ac349a5cea7e..2db3c60e1e61 100755
--- a/tools/testing/selftests/bpf/test_bpftool_build.sh
+++ b/tools/testing/selftests/bpf/test_bpftool_build.sh
@@ -85,6 +85,23 @@ make_with_tmpdir() {
 	echo
 }
 
+make_doc_and_clean() {
+	echo -e "\$PWD:    $PWD"
+	echo -e "command: make -s $* doc >/dev/null"
+	RST2MAN_OPTS="--exit-status=1" make $J -s $* doc
+	if [ $? -ne 0 ] ; then
+		ERROR=1
+		printf "FAILURE: Errors or warnings when building documentation\n"
+	fi
+	(
+		if [ $# -ge 1 ] ; then
+			cd ${@: -1}
+		fi
+		make -s doc-clean
+	)
+	echo
+}
+
 echo "Trying to build bpftool"
 echo -e "... through kbuild\n"
 
@@ -145,3 +162,7 @@ make_and_clean
 make_with_tmpdir OUTPUT
 
 make_with_tmpdir O
+
+echo -e "Checking documentation build\n"
+# From tools/bpf/bpftool
+make_doc_and_clean
diff --git a/tools/testing/selftests/bpf/test_bpftool_metadata.sh b/tools/testing/selftests/bpf/test_bpftool_metadata.sh
new file mode 100755
index 000000000000..1bf81b49457a
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_bpftool_metadata.sh
@@ -0,0 +1,82 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+TESTNAME=bpftool_metadata
+BPF_FS=$(awk '$3 == "bpf" {print $2; exit}' /proc/mounts)
+BPF_DIR=$BPF_FS/test_$TESTNAME
+
+_cleanup()
+{
+	set +e
+	rm -rf $BPF_DIR 2> /dev/null
+}
+
+cleanup_skip()
+{
+	echo "selftests: $TESTNAME [SKIP]"
+	_cleanup
+
+	exit $ksft_skip
+}
+
+cleanup()
+{
+	if [ "$?" = 0 ]; then
+		echo "selftests: $TESTNAME [PASS]"
+	else
+		echo "selftests: $TESTNAME [FAILED]"
+	fi
+	_cleanup
+}
+
+if [ $(id -u) -ne 0 ]; then
+	echo "selftests: $TESTNAME [SKIP] Need root privileges"
+	exit $ksft_skip
+fi
+
+if [ -z "$BPF_FS" ]; then
+	echo "selftests: $TESTNAME [SKIP] Could not run test without bpffs mounted"
+	exit $ksft_skip
+fi
+
+if ! bpftool version > /dev/null 2>&1; then
+	echo "selftests: $TESTNAME [SKIP] Could not run test without bpftool"
+	exit $ksft_skip
+fi
+
+set -e
+
+trap cleanup_skip EXIT
+
+mkdir $BPF_DIR
+
+trap cleanup EXIT
+
+bpftool prog load metadata_unused.o $BPF_DIR/unused
+
+METADATA_PLAIN="$(bpftool prog)"
+echo "$METADATA_PLAIN" | grep 'a = "foo"' > /dev/null
+echo "$METADATA_PLAIN" | grep 'b = 1' > /dev/null
+
+bpftool prog --json | grep '"metadata":{"a":"foo","b":1}' > /dev/null
+
+bpftool map | grep 'metadata.rodata' > /dev/null
+
+rm $BPF_DIR/unused
+
+bpftool prog load metadata_used.o $BPF_DIR/used
+
+METADATA_PLAIN="$(bpftool prog)"
+echo "$METADATA_PLAIN" | grep 'a = "bar"' > /dev/null
+echo "$METADATA_PLAIN" | grep 'b = 2' > /dev/null
+
+bpftool prog --json | grep '"metadata":{"a":"bar","b":2}' > /dev/null
+
+bpftool map | grep 'metadata.rodata' > /dev/null
+
+rm $BPF_DIR/used
+
+exit 0
diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h
index dbb820dde138..238f5f61189e 100644
--- a/tools/testing/selftests/bpf/test_progs.h
+++ b/tools/testing/selftests/bpf/test_progs.h
@@ -130,6 +130,69 @@ extern int test__join_cgroup(const char *path);
 #define CHECK_ATTR(condition, tag, format...) \
 	_CHECK(condition, tag, tattr.duration, format)
 
+#define ASSERT_EQ(actual, expected, name) ({				\
+	static int duration = 0;					\
+	typeof(actual) ___act = (actual);				\
+	typeof(expected) ___exp = (expected);				\
+	bool ___ok = ___act == ___exp;					\
+	CHECK(!___ok, (name),						\
+	      "unexpected %s: actual %lld != expected %lld\n",		\
+	      (name), (long long)(___act), (long long)(___exp));	\
+	___ok;								\
+})
+
+#define ASSERT_STREQ(actual, expected, name) ({				\
+	static int duration = 0;					\
+	const char *___act = actual;					\
+	const char *___exp = expected;					\
+	bool ___ok = strcmp(___act, ___exp) == 0;			\
+	CHECK(!___ok, (name),						\
+	      "unexpected %s: actual '%s' != expected '%s'\n",		\
+	      (name), ___act, ___exp);					\
+	___ok;								\
+})
+
+#define ASSERT_OK(res, name) ({						\
+	static int duration = 0;					\
+	long long ___res = (res);					\
+	bool ___ok = ___res == 0;					\
+	CHECK(!___ok, (name), "unexpected error: %lld\n", ___res);	\
+	___ok;								\
+})
+
+#define ASSERT_ERR(res, name) ({					\
+	static int duration = 0;					\
+	long long ___res = (res);					\
+	bool ___ok = ___res < 0;					\
+	CHECK(!___ok, (name), "unexpected success: %lld\n", ___res);	\
+	___ok;								\
+})
+
+#define ASSERT_NULL(ptr, name) ({					\
+	static int duration = 0;					\
+	const void *___res = (ptr);					\
+	bool ___ok = !___res;						\
+	CHECK(!___ok, (name), "unexpected pointer: %p\n", ___res);	\
+	___ok;								\
+})
+
+#define ASSERT_OK_PTR(ptr, name) ({					\
+	static int duration = 0;					\
+	const void *___res = (ptr);					\
+	bool ___ok = !IS_ERR_OR_NULL(___res);				\
+	CHECK(!___ok, (name),						\
+	      "unexpected error: %ld\n", PTR_ERR(___res));		\
+	___ok;								\
+})
+
+#define ASSERT_ERR_PTR(ptr, name) ({					\
+	static int duration = 0;					\
+	const void *___res = (ptr);					\
+	bool ___ok = IS_ERR(___res)					\
+	CHECK(!___ok, (name), "unexpected pointer: %p\n", ___res);	\
+	___ok;								\
+})
+
 static inline __u64 ptr_to_u64(const void *ptr)
 {
 	return (__u64) (unsigned long) ptr;
diff --git a/tools/testing/selftests/bpf/test_sock_fields.c b/tools/testing/selftests/bpf/test_sock_fields.c
deleted file mode 100644
index 6c9f269c396d..000000000000
--- a/tools/testing/selftests/bpf/test_sock_fields.c
+++ /dev/null
@@ -1,482 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/* Copyright (c) 2019 Facebook */
-
-#include <sys/socket.h>
-#include <sys/epoll.h>
-#include <netinet/in.h>
-#include <arpa/inet.h>
-#include <unistd.h>
-#include <stdlib.h>
-#include <string.h>
-#include <errno.h>
-
-#include <bpf/bpf.h>
-#include <bpf/libbpf.h>
-
-#include "cgroup_helpers.h"
-#include "bpf_rlimit.h"
-
-enum bpf_addr_array_idx {
-	ADDR_SRV_IDX,
-	ADDR_CLI_IDX,
-	__NR_BPF_ADDR_ARRAY_IDX,
-};
-
-enum bpf_result_array_idx {
-	EGRESS_SRV_IDX,
-	EGRESS_CLI_IDX,
-	INGRESS_LISTEN_IDX,
-	__NR_BPF_RESULT_ARRAY_IDX,
-};
-
-enum bpf_linum_array_idx {
-	EGRESS_LINUM_IDX,
-	INGRESS_LINUM_IDX,
-	__NR_BPF_LINUM_ARRAY_IDX,
-};
-
-struct bpf_spinlock_cnt {
-	struct bpf_spin_lock lock;
-	__u32 cnt;
-};
-
-#define CHECK(condition, tag, format...) ({				\
-	int __ret = !!(condition);					\
-	if (__ret) {							\
-		printf("%s(%d):FAIL:%s ", __func__, __LINE__, tag);	\
-		printf(format);						\
-		printf("\n");						\
-		exit(-1);						\
-	}								\
-})
-
-#define TEST_CGROUP "/test-bpf-sock-fields"
-#define DATA "Hello BPF!"
-#define DATA_LEN sizeof(DATA)
-
-static struct sockaddr_in6 srv_sa6, cli_sa6;
-static int sk_pkt_out_cnt10_fd;
-static int sk_pkt_out_cnt_fd;
-static int linum_map_fd;
-static int addr_map_fd;
-static int tp_map_fd;
-static int sk_map_fd;
-
-static __u32 addr_srv_idx = ADDR_SRV_IDX;
-static __u32 addr_cli_idx = ADDR_CLI_IDX;
-
-static __u32 egress_srv_idx = EGRESS_SRV_IDX;
-static __u32 egress_cli_idx = EGRESS_CLI_IDX;
-static __u32 ingress_listen_idx = INGRESS_LISTEN_IDX;
-
-static __u32 egress_linum_idx = EGRESS_LINUM_IDX;
-static __u32 ingress_linum_idx = INGRESS_LINUM_IDX;
-
-static void init_loopback6(struct sockaddr_in6 *sa6)
-{
-	memset(sa6, 0, sizeof(*sa6));
-	sa6->sin6_family = AF_INET6;
-	sa6->sin6_addr = in6addr_loopback;
-}
-
-static void print_sk(const struct bpf_sock *sk)
-{
-	char src_ip4[24], dst_ip4[24];
-	char src_ip6[64], dst_ip6[64];
-
-	inet_ntop(AF_INET, &sk->src_ip4, src_ip4, sizeof(src_ip4));
-	inet_ntop(AF_INET6, &sk->src_ip6, src_ip6, sizeof(src_ip6));
-	inet_ntop(AF_INET, &sk->dst_ip4, dst_ip4, sizeof(dst_ip4));
-	inet_ntop(AF_INET6, &sk->dst_ip6, dst_ip6, sizeof(dst_ip6));
-
-	printf("state:%u bound_dev_if:%u family:%u type:%u protocol:%u mark:%u priority:%u "
-	       "src_ip4:%x(%s) src_ip6:%x:%x:%x:%x(%s) src_port:%u "
-	       "dst_ip4:%x(%s) dst_ip6:%x:%x:%x:%x(%s) dst_port:%u\n",
-	       sk->state, sk->bound_dev_if, sk->family, sk->type, sk->protocol,
-	       sk->mark, sk->priority,
-	       sk->src_ip4, src_ip4,
-	       sk->src_ip6[0], sk->src_ip6[1], sk->src_ip6[2], sk->src_ip6[3],
-	       src_ip6, sk->src_port,
-	       sk->dst_ip4, dst_ip4,
-	       sk->dst_ip6[0], sk->dst_ip6[1], sk->dst_ip6[2], sk->dst_ip6[3],
-	       dst_ip6, ntohs(sk->dst_port));
-}
-
-static void print_tp(const struct bpf_tcp_sock *tp)
-{
-	printf("snd_cwnd:%u srtt_us:%u rtt_min:%u snd_ssthresh:%u rcv_nxt:%u "
-	       "snd_nxt:%u snd:una:%u mss_cache:%u ecn_flags:%u "
-	       "rate_delivered:%u rate_interval_us:%u packets_out:%u "
-	       "retrans_out:%u total_retrans:%u segs_in:%u data_segs_in:%u "
-	       "segs_out:%u data_segs_out:%u lost_out:%u sacked_out:%u "
-	       "bytes_received:%llu bytes_acked:%llu\n",
-	       tp->snd_cwnd, tp->srtt_us, tp->rtt_min, tp->snd_ssthresh,
-	       tp->rcv_nxt, tp->snd_nxt, tp->snd_una, tp->mss_cache,
-	       tp->ecn_flags, tp->rate_delivered, tp->rate_interval_us,
-	       tp->packets_out, tp->retrans_out, tp->total_retrans,
-	       tp->segs_in, tp->data_segs_in, tp->segs_out,
-	       tp->data_segs_out, tp->lost_out, tp->sacked_out,
-	       tp->bytes_received, tp->bytes_acked);
-}
-
-static void check_result(void)
-{
-	struct bpf_tcp_sock srv_tp, cli_tp, listen_tp;
-	struct bpf_sock srv_sk, cli_sk, listen_sk;
-	__u32 ingress_linum, egress_linum;
-	int err;
-
-	err = bpf_map_lookup_elem(linum_map_fd, &egress_linum_idx,
-				  &egress_linum);
-	CHECK(err == -1, "bpf_map_lookup_elem(linum_map_fd)",
-	      "err:%d errno:%d", err, errno);
-
-	err = bpf_map_lookup_elem(linum_map_fd, &ingress_linum_idx,
-				  &ingress_linum);
-	CHECK(err == -1, "bpf_map_lookup_elem(linum_map_fd)",
-	      "err:%d errno:%d", err, errno);
-
-	err = bpf_map_lookup_elem(sk_map_fd, &egress_srv_idx, &srv_sk);
-	CHECK(err == -1, "bpf_map_lookup_elem(sk_map_fd, &egress_srv_idx)",
-	      "err:%d errno:%d", err, errno);
-	err = bpf_map_lookup_elem(tp_map_fd, &egress_srv_idx, &srv_tp);
-	CHECK(err == -1, "bpf_map_lookup_elem(tp_map_fd, &egress_srv_idx)",
-	      "err:%d errno:%d", err, errno);
-
-	err = bpf_map_lookup_elem(sk_map_fd, &egress_cli_idx, &cli_sk);
-	CHECK(err == -1, "bpf_map_lookup_elem(sk_map_fd, &egress_cli_idx)",
-	      "err:%d errno:%d", err, errno);
-	err = bpf_map_lookup_elem(tp_map_fd, &egress_cli_idx, &cli_tp);
-	CHECK(err == -1, "bpf_map_lookup_elem(tp_map_fd, &egress_cli_idx)",
-	      "err:%d errno:%d", err, errno);
-
-	err = bpf_map_lookup_elem(sk_map_fd, &ingress_listen_idx, &listen_sk);
-	CHECK(err == -1, "bpf_map_lookup_elem(sk_map_fd, &ingress_listen_idx)",
-	      "err:%d errno:%d", err, errno);
-	err = bpf_map_lookup_elem(tp_map_fd, &ingress_listen_idx, &listen_tp);
-	CHECK(err == -1, "bpf_map_lookup_elem(tp_map_fd, &ingress_listen_idx)",
-	      "err:%d errno:%d", err, errno);
-
-	printf("listen_sk: ");
-	print_sk(&listen_sk);
-	printf("\n");
-
-	printf("srv_sk: ");
-	print_sk(&srv_sk);
-	printf("\n");
-
-	printf("cli_sk: ");
-	print_sk(&cli_sk);
-	printf("\n");
-
-	printf("listen_tp: ");
-	print_tp(&listen_tp);
-	printf("\n");
-
-	printf("srv_tp: ");
-	print_tp(&srv_tp);
-	printf("\n");
-
-	printf("cli_tp: ");
-	print_tp(&cli_tp);
-	printf("\n");
-
-	CHECK(listen_sk.state != 10 ||
-	      listen_sk.family != AF_INET6 ||
-	      listen_sk.protocol != IPPROTO_TCP ||
-	      memcmp(listen_sk.src_ip6, &in6addr_loopback,
-		     sizeof(listen_sk.src_ip6)) ||
-	      listen_sk.dst_ip6[0] || listen_sk.dst_ip6[1] ||
-	      listen_sk.dst_ip6[2] || listen_sk.dst_ip6[3] ||
-	      listen_sk.src_port != ntohs(srv_sa6.sin6_port) ||
-	      listen_sk.dst_port,
-	      "Unexpected listen_sk",
-	      "Check listen_sk output. ingress_linum:%u",
-	      ingress_linum);
-
-	CHECK(srv_sk.state == 10 ||
-	      !srv_sk.state ||
-	      srv_sk.family != AF_INET6 ||
-	      srv_sk.protocol != IPPROTO_TCP ||
-	      memcmp(srv_sk.src_ip6, &in6addr_loopback,
-		     sizeof(srv_sk.src_ip6)) ||
-	      memcmp(srv_sk.dst_ip6, &in6addr_loopback,
-		     sizeof(srv_sk.dst_ip6)) ||
-	      srv_sk.src_port != ntohs(srv_sa6.sin6_port) ||
-	      srv_sk.dst_port != cli_sa6.sin6_port,
-	      "Unexpected srv_sk", "Check srv_sk output. egress_linum:%u",
-	      egress_linum);
-
-	CHECK(cli_sk.state == 10 ||
-	      !cli_sk.state ||
-	      cli_sk.family != AF_INET6 ||
-	      cli_sk.protocol != IPPROTO_TCP ||
-	      memcmp(cli_sk.src_ip6, &in6addr_loopback,
-		     sizeof(cli_sk.src_ip6)) ||
-	      memcmp(cli_sk.dst_ip6, &in6addr_loopback,
-		     sizeof(cli_sk.dst_ip6)) ||
-	      cli_sk.src_port != ntohs(cli_sa6.sin6_port) ||
-	      cli_sk.dst_port != srv_sa6.sin6_port,
-	      "Unexpected cli_sk", "Check cli_sk output. egress_linum:%u",
-	      egress_linum);
-
-	CHECK(listen_tp.data_segs_out ||
-	      listen_tp.data_segs_in ||
-	      listen_tp.total_retrans ||
-	      listen_tp.bytes_acked,
-	      "Unexpected listen_tp", "Check listen_tp output. ingress_linum:%u",
-	      ingress_linum);
-
-	CHECK(srv_tp.data_segs_out != 2 ||
-	      srv_tp.data_segs_in ||
-	      srv_tp.snd_cwnd != 10 ||
-	      srv_tp.total_retrans ||
-	      srv_tp.bytes_acked != 2 * DATA_LEN,
-	      "Unexpected srv_tp", "Check srv_tp output. egress_linum:%u",
-	      egress_linum);
-
-	CHECK(cli_tp.data_segs_out ||
-	      cli_tp.data_segs_in != 2 ||
-	      cli_tp.snd_cwnd != 10 ||
-	      cli_tp.total_retrans ||
-	      cli_tp.bytes_received != 2 * DATA_LEN,
-	      "Unexpected cli_tp", "Check cli_tp output. egress_linum:%u",
-	      egress_linum);
-}
-
-static void check_sk_pkt_out_cnt(int accept_fd, int cli_fd)
-{
-	struct bpf_spinlock_cnt pkt_out_cnt = {}, pkt_out_cnt10 = {};
-	int err;
-
-	pkt_out_cnt.cnt = ~0;
-	pkt_out_cnt10.cnt = ~0;
-	err = bpf_map_lookup_elem(sk_pkt_out_cnt_fd, &accept_fd, &pkt_out_cnt);
-	if (!err)
-		err = bpf_map_lookup_elem(sk_pkt_out_cnt10_fd, &accept_fd,
-					  &pkt_out_cnt10);
-
-	/* The bpf prog only counts for fullsock and
-	 * passive conneciton did not become fullsock until 3WHS
-	 * had been finished.
-	 * The bpf prog only counted two data packet out but we
-	 * specially init accept_fd's pkt_out_cnt by 2 in
-	 * init_sk_storage().  Hence, 4 here.
-	 */
-	CHECK(err || pkt_out_cnt.cnt != 4 || pkt_out_cnt10.cnt != 40,
-	      "bpf_map_lookup_elem(sk_pkt_out_cnt, &accept_fd)",
-	      "err:%d errno:%d pkt_out_cnt:%u pkt_out_cnt10:%u",
-	      err, errno, pkt_out_cnt.cnt, pkt_out_cnt10.cnt);
-
-	pkt_out_cnt.cnt = ~0;
-	pkt_out_cnt10.cnt = ~0;
-	err = bpf_map_lookup_elem(sk_pkt_out_cnt_fd, &cli_fd, &pkt_out_cnt);
-	if (!err)
-		err = bpf_map_lookup_elem(sk_pkt_out_cnt10_fd, &cli_fd,
-					  &pkt_out_cnt10);
-	/* Active connection is fullsock from the beginning.
-	 * 1 SYN and 1 ACK during 3WHS
-	 * 2 Acks on data packet.
-	 *
-	 * The bpf_prog initialized it to 0xeB9F.
-	 */
-	CHECK(err || pkt_out_cnt.cnt != 0xeB9F + 4 ||
-	      pkt_out_cnt10.cnt != 0xeB9F + 40,
-	      "bpf_map_lookup_elem(sk_pkt_out_cnt, &cli_fd)",
-	      "err:%d errno:%d pkt_out_cnt:%u pkt_out_cnt10:%u",
-	      err, errno, pkt_out_cnt.cnt, pkt_out_cnt10.cnt);
-}
-
-static void init_sk_storage(int sk_fd, __u32 pkt_out_cnt)
-{
-	struct bpf_spinlock_cnt scnt = {};
-	int err;
-
-	scnt.cnt = pkt_out_cnt;
-	err = bpf_map_update_elem(sk_pkt_out_cnt_fd, &sk_fd, &scnt,
-				  BPF_NOEXIST);
-	CHECK(err, "bpf_map_update_elem(sk_pkt_out_cnt_fd)",
-	      "err:%d errno:%d", err, errno);
-
-	scnt.cnt *= 10;
-	err = bpf_map_update_elem(sk_pkt_out_cnt10_fd, &sk_fd, &scnt,
-				  BPF_NOEXIST);
-	CHECK(err, "bpf_map_update_elem(sk_pkt_out_cnt10_fd)",
-	      "err:%d errno:%d", err, errno);
-}
-
-static void test(void)
-{
-	int listen_fd, cli_fd, accept_fd, epfd, err;
-	struct epoll_event ev;
-	socklen_t addrlen;
-	int i;
-
-	addrlen = sizeof(struct sockaddr_in6);
-	ev.events = EPOLLIN;
-
-	epfd = epoll_create(1);
-	CHECK(epfd == -1, "epoll_create()", "epfd:%d errno:%d", epfd, errno);
-
-	/* Prepare listen_fd */
-	listen_fd = socket(AF_INET6, SOCK_STREAM | SOCK_NONBLOCK, 0);
-	CHECK(listen_fd == -1, "socket()", "listen_fd:%d errno:%d",
-	      listen_fd, errno);
-
-	init_loopback6(&srv_sa6);
-	err = bind(listen_fd, (struct sockaddr *)&srv_sa6, sizeof(srv_sa6));
-	CHECK(err, "bind(listen_fd)", "err:%d errno:%d", err, errno);
-
-	err = getsockname(listen_fd, (struct sockaddr *)&srv_sa6, &addrlen);
-	CHECK(err, "getsockname(listen_fd)", "err:%d errno:%d", err, errno);
-
-	err = listen(listen_fd, 1);
-	CHECK(err, "listen(listen_fd)", "err:%d errno:%d", err, errno);
-
-	/* Prepare cli_fd */
-	cli_fd = socket(AF_INET6, SOCK_STREAM | SOCK_NONBLOCK, 0);
-	CHECK(cli_fd == -1, "socket()", "cli_fd:%d errno:%d", cli_fd, errno);
-
-	init_loopback6(&cli_sa6);
-	err = bind(cli_fd, (struct sockaddr *)&cli_sa6, sizeof(cli_sa6));
-	CHECK(err, "bind(cli_fd)", "err:%d errno:%d", err, errno);
-
-	err = getsockname(cli_fd, (struct sockaddr *)&cli_sa6, &addrlen);
-	CHECK(err, "getsockname(cli_fd)", "err:%d errno:%d",
-	      err, errno);
-
-	/* Update addr_map with srv_sa6 and cli_sa6 */
-	err = bpf_map_update_elem(addr_map_fd, &addr_srv_idx, &srv_sa6, 0);
-	CHECK(err, "map_update", "err:%d errno:%d", err, errno);
-
-	err = bpf_map_update_elem(addr_map_fd, &addr_cli_idx, &cli_sa6, 0);
-	CHECK(err, "map_update", "err:%d errno:%d", err, errno);
-
-	/* Connect from cli_sa6 to srv_sa6 */
-	err = connect(cli_fd, (struct sockaddr *)&srv_sa6, addrlen);
-	printf("srv_sa6.sin6_port:%u cli_sa6.sin6_port:%u\n\n",
-	       ntohs(srv_sa6.sin6_port), ntohs(cli_sa6.sin6_port));
-	CHECK(err && errno != EINPROGRESS,
-	      "connect(cli_fd)", "err:%d errno:%d", err, errno);
-
-	ev.data.fd = listen_fd;
-	err = epoll_ctl(epfd, EPOLL_CTL_ADD, listen_fd, &ev);
-	CHECK(err, "epoll_ctl(EPOLL_CTL_ADD, listen_fd)", "err:%d errno:%d",
-	      err, errno);
-
-	/* Accept the connection */
-	/* Have some timeout in accept(listen_fd). Just in case. */
-	err = epoll_wait(epfd, &ev, 1, 1000);
-	CHECK(err != 1 || ev.data.fd != listen_fd,
-	      "epoll_wait(listen_fd)",
-	      "err:%d errno:%d ev.data.fd:%d listen_fd:%d",
-	      err, errno, ev.data.fd, listen_fd);
-
-	accept_fd = accept(listen_fd, NULL, NULL);
-	CHECK(accept_fd == -1, "accept(listen_fd)", "accept_fd:%d errno:%d",
-	      accept_fd, errno);
-	close(listen_fd);
-
-	ev.data.fd = cli_fd;
-	err = epoll_ctl(epfd, EPOLL_CTL_ADD, cli_fd, &ev);
-	CHECK(err, "epoll_ctl(EPOLL_CTL_ADD, cli_fd)", "err:%d errno:%d",
-	      err, errno);
-
-	init_sk_storage(accept_fd, 2);
-
-	for (i = 0; i < 2; i++) {
-		/* Send some data from accept_fd to cli_fd */
-		err = send(accept_fd, DATA, DATA_LEN, 0);
-		CHECK(err != DATA_LEN, "send(accept_fd)", "err:%d errno:%d",
-		      err, errno);
-
-		/* Have some timeout in recv(cli_fd). Just in case. */
-		err = epoll_wait(epfd, &ev, 1, 1000);
-		CHECK(err != 1 || ev.data.fd != cli_fd,
-		      "epoll_wait(cli_fd)", "err:%d errno:%d ev.data.fd:%d cli_fd:%d",
-		      err, errno, ev.data.fd, cli_fd);
-
-		err = recv(cli_fd, NULL, 0, MSG_TRUNC);
-		CHECK(err, "recv(cli_fd)", "err:%d errno:%d", err, errno);
-	}
-
-	check_sk_pkt_out_cnt(accept_fd, cli_fd);
-
-	close(epfd);
-	close(accept_fd);
-	close(cli_fd);
-
-	check_result();
-}
-
-int main(int argc, char **argv)
-{
-	struct bpf_prog_load_attr attr = {
-		.file = "test_sock_fields_kern.o",
-		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-		.prog_flags = BPF_F_TEST_RND_HI32,
-	};
-	int cgroup_fd, egress_fd, ingress_fd, err;
-	struct bpf_program *ingress_prog;
-	struct bpf_object *obj;
-	struct bpf_map *map;
-
-	/* Create a cgroup, get fd, and join it */
-	cgroup_fd = cgroup_setup_and_join(TEST_CGROUP);
-	CHECK(cgroup_fd < 0, "cgroup_setup_and_join()",
-	      "cgroup_fd:%d errno:%d", cgroup_fd, errno);
-	atexit(cleanup_cgroup_environment);
-
-	err = bpf_prog_load_xattr(&attr, &obj, &egress_fd);
-	CHECK(err, "bpf_prog_load_xattr()", "err:%d", err);
-
-	ingress_prog = bpf_object__find_program_by_title(obj,
-							 "cgroup_skb/ingress");
-	CHECK(!ingress_prog,
-	      "bpf_object__find_program_by_title(cgroup_skb/ingress)",
-	      "not found");
-	ingress_fd = bpf_program__fd(ingress_prog);
-
-	err = bpf_prog_attach(egress_fd, cgroup_fd, BPF_CGROUP_INET_EGRESS, 0);
-	CHECK(err == -1, "bpf_prog_attach(CPF_CGROUP_INET_EGRESS)",
-	      "err:%d errno%d", err, errno);
-
-	err = bpf_prog_attach(ingress_fd, cgroup_fd,
-			      BPF_CGROUP_INET_INGRESS, 0);
-	CHECK(err == -1, "bpf_prog_attach(CPF_CGROUP_INET_INGRESS)",
-	      "err:%d errno%d", err, errno);
-	close(cgroup_fd);
-
-	map = bpf_object__find_map_by_name(obj, "addr_map");
-	CHECK(!map, "cannot find addr_map", "(null)");
-	addr_map_fd = bpf_map__fd(map);
-
-	map = bpf_object__find_map_by_name(obj, "sock_result_map");
-	CHECK(!map, "cannot find sock_result_map", "(null)");
-	sk_map_fd = bpf_map__fd(map);
-
-	map = bpf_object__find_map_by_name(obj, "tcp_sock_result_map");
-	CHECK(!map, "cannot find tcp_sock_result_map", "(null)");
-	tp_map_fd = bpf_map__fd(map);
-
-	map = bpf_object__find_map_by_name(obj, "linum_map");
-	CHECK(!map, "cannot find linum_map", "(null)");
-	linum_map_fd = bpf_map__fd(map);
-
-	map = bpf_object__find_map_by_name(obj, "sk_pkt_out_cnt");
-	CHECK(!map, "cannot find sk_pkt_out_cnt", "(null)");
-	sk_pkt_out_cnt_fd = bpf_map__fd(map);
-
-	map = bpf_object__find_map_by_name(obj, "sk_pkt_out_cnt10");
-	CHECK(!map, "cannot find sk_pkt_out_cnt10", "(null)");
-	sk_pkt_out_cnt10_fd = bpf_map__fd(map);
-
-	test();
-
-	bpf_object__close(obj);
-	cleanup_cgroup_environment();
-
-	printf("PASS\n");
-
-	return 0;
-}
diff --git a/tools/testing/selftests/bpf/test_socket_cookie.c b/tools/testing/selftests/bpf/test_socket_cookie.c
index 154a8fd2a48d..ca7ca87e91aa 100644
--- a/tools/testing/selftests/bpf/test_socket_cookie.c
+++ b/tools/testing/selftests/bpf/test_socket_cookie.c
@@ -151,7 +151,7 @@ static int run_test(int cgfd)
 	}
 
 	bpf_object__for_each_program(prog, pobj) {
-		prog_name = bpf_program__title(prog, /*needs_copy*/ false);
+		prog_name = bpf_program__section_name(prog);
 
 		if (libbpf_attach_type_by_name(prog_name, &attach_type))
 			goto err;
diff --git a/tools/testing/selftests/bpf/test_tc_neigh.sh b/tools/testing/selftests/bpf/test_tc_neigh.sh
new file mode 100755
index 000000000000..31d8c3df8b24
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_tc_neigh.sh
@@ -0,0 +1,168 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# This test sets up 3 netns (src <-> fwd <-> dst). There is no direct veth link
+# between src and dst. The netns fwd has veth links to each src and dst. The
+# client is in src and server in dst. The test installs a TC BPF program to each
+# host facing veth in fwd which calls into bpf_redirect_peer() to perform the
+# neigh addr population and redirect; it also installs a dropper prog on the
+# egress side to drop skbs if neigh addrs were not populated.
+
+if [[ $EUID -ne 0 ]]; then
+	echo "This script must be run as root"
+	echo "FAIL"
+	exit 1
+fi
+
+# check that nc, dd, ping, ping6 and timeout are present
+command -v nc >/dev/null 2>&1 || \
+	{ echo >&2 "nc is not available"; exit 1; }
+command -v dd >/dev/null 2>&1 || \
+	{ echo >&2 "dd is not available"; exit 1; }
+command -v timeout >/dev/null 2>&1 || \
+	{ echo >&2 "timeout is not available"; exit 1; }
+command -v ping >/dev/null 2>&1 || \
+	{ echo >&2 "ping is not available"; exit 1; }
+command -v ping6 >/dev/null 2>&1 || \
+	{ echo >&2 "ping6 is not available"; exit 1; }
+
+readonly GREEN='\033[0;92m'
+readonly RED='\033[0;31m'
+readonly NC='\033[0m' # No Color
+
+readonly PING_ARG="-c 3 -w 10 -q"
+
+readonly TIMEOUT=10
+
+readonly NS_SRC="ns-src-$(mktemp -u XXXXXX)"
+readonly NS_FWD="ns-fwd-$(mktemp -u XXXXXX)"
+readonly NS_DST="ns-dst-$(mktemp -u XXXXXX)"
+
+readonly IP4_SRC="172.16.1.100"
+readonly IP4_DST="172.16.2.100"
+
+readonly IP6_SRC="::1:dead:beef:cafe"
+readonly IP6_DST="::2:dead:beef:cafe"
+
+readonly IP4_SLL="169.254.0.1"
+readonly IP4_DLL="169.254.0.2"
+readonly IP4_NET="169.254.0.0"
+
+cleanup()
+{
+	ip netns del ${NS_SRC}
+	ip netns del ${NS_FWD}
+	ip netns del ${NS_DST}
+}
+
+trap cleanup EXIT
+
+set -e
+
+ip netns add "${NS_SRC}"
+ip netns add "${NS_FWD}"
+ip netns add "${NS_DST}"
+
+ip link add veth_src type veth peer name veth_src_fwd
+ip link add veth_dst type veth peer name veth_dst_fwd
+
+ip link set veth_src netns ${NS_SRC}
+ip link set veth_src_fwd netns ${NS_FWD}
+
+ip link set veth_dst netns ${NS_DST}
+ip link set veth_dst_fwd netns ${NS_FWD}
+
+ip -netns ${NS_SRC} addr add ${IP4_SRC}/32 dev veth_src
+ip -netns ${NS_DST} addr add ${IP4_DST}/32 dev veth_dst
+
+# The fwd netns automatically get a v6 LL address / routes, but also needs v4
+# one in order to start ARP probing. IP4_NET route is added to the endpoints
+# so that the ARP processing will reply.
+
+ip -netns ${NS_FWD} addr add ${IP4_SLL}/32 dev veth_src_fwd
+ip -netns ${NS_FWD} addr add ${IP4_DLL}/32 dev veth_dst_fwd
+
+ip -netns ${NS_SRC} addr add ${IP6_SRC}/128 dev veth_src nodad
+ip -netns ${NS_DST} addr add ${IP6_DST}/128 dev veth_dst nodad
+
+ip -netns ${NS_SRC} link set dev veth_src up
+ip -netns ${NS_FWD} link set dev veth_src_fwd up
+
+ip -netns ${NS_DST} link set dev veth_dst up
+ip -netns ${NS_FWD} link set dev veth_dst_fwd up
+
+ip -netns ${NS_SRC} route add ${IP4_DST}/32 dev veth_src scope global
+ip -netns ${NS_SRC} route add ${IP4_NET}/16 dev veth_src scope global
+ip -netns ${NS_FWD} route add ${IP4_SRC}/32 dev veth_src_fwd scope global
+
+ip -netns ${NS_SRC} route add ${IP6_DST}/128 dev veth_src scope global
+ip -netns ${NS_FWD} route add ${IP6_SRC}/128 dev veth_src_fwd scope global
+
+ip -netns ${NS_DST} route add ${IP4_SRC}/32 dev veth_dst scope global
+ip -netns ${NS_DST} route add ${IP4_NET}/16 dev veth_dst scope global
+ip -netns ${NS_FWD} route add ${IP4_DST}/32 dev veth_dst_fwd scope global
+
+ip -netns ${NS_DST} route add ${IP6_SRC}/128 dev veth_dst scope global
+ip -netns ${NS_FWD} route add ${IP6_DST}/128 dev veth_dst_fwd scope global
+
+fmac_src=$(ip netns exec ${NS_FWD} cat /sys/class/net/veth_src_fwd/address)
+fmac_dst=$(ip netns exec ${NS_FWD} cat /sys/class/net/veth_dst_fwd/address)
+
+ip -netns ${NS_SRC} neigh add ${IP4_DST} dev veth_src lladdr $fmac_src
+ip -netns ${NS_DST} neigh add ${IP4_SRC} dev veth_dst lladdr $fmac_dst
+
+ip -netns ${NS_SRC} neigh add ${IP6_DST} dev veth_src lladdr $fmac_src
+ip -netns ${NS_DST} neigh add ${IP6_SRC} dev veth_dst lladdr $fmac_dst
+
+veth_dst=$(ip netns exec ${NS_FWD} cat /sys/class/net/veth_dst_fwd/ifindex | awk '{printf "%08x\n", $1}')
+veth_src=$(ip netns exec ${NS_FWD} cat /sys/class/net/veth_src_fwd/ifindex | awk '{printf "%08x\n", $1}')
+
+xxd -p < test_tc_neigh.o   | sed "s/eeddddee/$veth_src/g" | xxd -r -p > test_tc_neigh.x.o
+xxd -p < test_tc_neigh.x.o | sed "s/eeffffee/$veth_dst/g" | xxd -r -p > test_tc_neigh.y.o
+
+ip netns exec ${NS_FWD} tc qdisc add dev veth_src_fwd clsact
+ip netns exec ${NS_FWD} tc filter add dev veth_src_fwd ingress bpf da obj test_tc_neigh.y.o sec src_ingress
+ip netns exec ${NS_FWD} tc filter add dev veth_src_fwd egress  bpf da obj test_tc_neigh.y.o sec chk_neigh
+
+ip netns exec ${NS_FWD} tc qdisc add dev veth_dst_fwd clsact
+ip netns exec ${NS_FWD} tc filter add dev veth_dst_fwd ingress bpf da obj test_tc_neigh.y.o sec dst_ingress
+ip netns exec ${NS_FWD} tc filter add dev veth_dst_fwd egress  bpf da obj test_tc_neigh.y.o sec chk_neigh
+
+rm -f test_tc_neigh.x.o test_tc_neigh.y.o
+
+ip netns exec ${NS_DST} bash -c "nc -4 -l -p 9004 &"
+ip netns exec ${NS_DST} bash -c "nc -6 -l -p 9006 &"
+
+set +e
+
+TEST="TCPv4 connectivity test"
+ip netns exec ${NS_SRC} bash -c "timeout ${TIMEOUT} dd if=/dev/zero bs=1000 count=100 > /dev/tcp/${IP4_DST}/9004"
+if [ $? -ne 0 ]; then
+	echo -e "${TEST}: ${RED}FAIL${NC}"
+	exit 1
+fi
+echo -e "${TEST}: ${GREEN}PASS${NC}"
+
+TEST="TCPv6 connectivity test"
+ip netns exec ${NS_SRC} bash -c "timeout ${TIMEOUT} dd if=/dev/zero bs=1000 count=100 > /dev/tcp/${IP6_DST}/9006"
+if [ $? -ne 0 ]; then
+	echo -e "${TEST}: ${RED}FAIL${NC}"
+	exit 1
+fi
+echo -e "${TEST}: ${GREEN}PASS${NC}"
+
+TEST="ICMPv4 connectivity test"
+ip netns exec ${NS_SRC} ping  $PING_ARG ${IP4_DST}
+if [ $? -ne 0 ]; then
+	echo -e "${TEST}: ${RED}FAIL${NC}"
+	exit 1
+fi
+echo -e "${TEST}: ${GREEN}PASS${NC}"
+
+TEST="ICMPv6 connectivity test"
+ip netns exec ${NS_SRC} ping6 $PING_ARG ${IP6_DST}
+if [ $? -ne 0 ]; then
+	echo -e "${TEST}: ${RED}FAIL${NC}"
+	exit 1
+fi
+echo -e "${TEST}: ${GREEN}PASS${NC}"
diff --git a/tools/testing/selftests/bpf/verifier/and.c b/tools/testing/selftests/bpf/verifier/and.c
index d781bc86e100..ca8fdb1b3f01 100644
--- a/tools/testing/selftests/bpf/verifier/and.c
+++ b/tools/testing/selftests/bpf/verifier/and.c
@@ -48,3 +48,19 @@
 	.result = REJECT,
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
+{
+	"check known subreg with unknown reg",
+	.insns = {
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
+	BPF_ALU64_IMM(BPF_LSH, BPF_REG_0, 32),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1),
+	BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 0xFFFF1234),
+	/* Upper bits are unknown but AND above masks out 1 zero'ing lower bits */
+	BPF_JMP32_IMM(BPF_JLT, BPF_REG_0, 1, 1),
+	BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_1, 512),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.retval = 0
+},
diff --git a/tools/testing/selftests/bpf/verifier/calls.c b/tools/testing/selftests/bpf/verifier/calls.c
index 94258c6b5235..c4f5d909e58a 100644
--- a/tools/testing/selftests/bpf/verifier/calls.c
+++ b/tools/testing/selftests/bpf/verifier/calls.c
@@ -647,13 +647,14 @@
 	.result = REJECT,
 },
 {
-	"calls: ld_abs with changing ctx data in callee",
+	"calls: subprog call with ld_abs in main prog",
 	.insns = {
 	BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
 	BPF_LD_ABS(BPF_B, 0),
 	BPF_LD_ABS(BPF_H, 0),
 	BPF_LD_ABS(BPF_W, 0),
 	BPF_MOV64_REG(BPF_REG_7, BPF_REG_6),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
 	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 5),
 	BPF_MOV64_REG(BPF_REG_6, BPF_REG_7),
 	BPF_LD_ABS(BPF_B, 0),
@@ -666,8 +667,7 @@
 	BPF_EXIT_INSN(),
 	},
 	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.errstr = "BPF_LD_[ABS|IND] instructions cannot be mixed",
-	.result = REJECT,
+	.result = ACCEPT,
 },
 {
 	"calls: two calls with bad fallthrough",
diff --git a/tools/testing/selftests/bpf/verifier/map_ptr.c b/tools/testing/selftests/bpf/verifier/map_ptr.c
index b52209db8250..637f9293bda8 100644
--- a/tools/testing/selftests/bpf/verifier/map_ptr.c
+++ b/tools/testing/selftests/bpf/verifier/map_ptr.c
@@ -60,3 +60,35 @@
 	.result = ACCEPT,
 	.retval = 1,
 },
+{
+	"bpf_map_ptr: r = 0, map_ptr = map_ptr + r",
+	.insns = {
+	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_hash_16b = { 4 },
+	.result = ACCEPT,
+},
+{
+	"bpf_map_ptr: r = 0, r = r + map_ptr",
+	.insns = {
+	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+	BPF_MOV64_IMM(BPF_REG_1, 0),
+	BPF_LD_MAP_FD(BPF_REG_0, 0),
+	BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_hash_16b = { 4 },
+	.result = ACCEPT,
+},
diff --git a/tools/testing/selftests/bpf/verifier/ref_tracking.c b/tools/testing/selftests/bpf/verifier/ref_tracking.c
index 056e0273bf12..006b5bd99c08 100644
--- a/tools/testing/selftests/bpf/verifier/ref_tracking.c
+++ b/tools/testing/selftests/bpf/verifier/ref_tracking.c
@@ -854,3 +854,50 @@
 	.errstr = "Unreleased reference",
 	.result = REJECT,
 },
+{
+	"reference tracking: bpf_sk_release(btf_tcp_sock)",
+	.insns = {
+	BPF_SK_LOOKUP(sk_lookup_tcp),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_EMIT_CALL(BPF_FUNC_skc_to_tcp_sock),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 3),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+	BPF_EMIT_CALL(BPF_FUNC_sk_release),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_EMIT_CALL(BPF_FUNC_sk_release),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	.result = ACCEPT,
+	.result_unpriv = REJECT,
+	.errstr_unpriv = "unknown func",
+},
+{
+	"reference tracking: use ptr from bpf_skc_to_tcp_sock() after release",
+	.insns = {
+	BPF_SK_LOOKUP(sk_lookup_tcp),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_EMIT_CALL(BPF_FUNC_skc_to_tcp_sock),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 3),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+	BPF_EMIT_CALL(BPF_FUNC_sk_release),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+	BPF_EMIT_CALL(BPF_FUNC_sk_release),
+	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_7, 0),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	.result = REJECT,
+	.errstr = "invalid mem access",
+	.result_unpriv = REJECT,
+	.errstr_unpriv = "unknown func",
+},
diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_ets_strict.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_ets_strict.sh
index 6d1790b5de7a..e9f8718af979 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/qos_ets_strict.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/qos_ets_strict.sh
@@ -147,17 +147,26 @@ switch_create()
 
 	# Make sure that ingress quotas are smaller than egress so that there is
 	# room for both streams of traffic to be admitted to shared buffer.
+	devlink_pool_size_thtype_save 0
 	devlink_pool_size_thtype_set 0 dynamic 10000000
+	devlink_pool_size_thtype_save 4
 	devlink_pool_size_thtype_set 4 dynamic 10000000
 
+	devlink_port_pool_th_save $swp1 0
 	devlink_port_pool_th_set $swp1 0 6
+	devlink_tc_bind_pool_th_save $swp1 1 ingress
 	devlink_tc_bind_pool_th_set $swp1 1 ingress 0 6
 
+	devlink_port_pool_th_save $swp2 0
 	devlink_port_pool_th_set $swp2 0 6
+	devlink_tc_bind_pool_th_save $swp2 2 ingress
 	devlink_tc_bind_pool_th_set $swp2 2 ingress 0 6
 
+	devlink_tc_bind_pool_th_save $swp3 1 egress
 	devlink_tc_bind_pool_th_set $swp3 1 egress 4 7
+	devlink_tc_bind_pool_th_save $swp3 2 egress
 	devlink_tc_bind_pool_th_set $swp3 2 egress 4 7
+	devlink_port_pool_th_save $swp3 4
 	devlink_port_pool_th_set $swp3 4 7
 }
 
diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_headroom.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_headroom.sh
new file mode 100755
index 000000000000..27de3d9ed08e
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/qos_headroom.sh
@@ -0,0 +1,379 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ALL_TESTS="
+	test_defaults
+	test_dcb_ets
+	test_mtu
+	test_pfc
+	test_int_buf
+	test_tc_priomap
+	test_tc_mtu
+	test_tc_sizes
+	test_tc_int_buf
+"
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+NUM_NETIFS=0
+source $lib_dir/lib.sh
+source $lib_dir/devlink_lib.sh
+source qos_lib.sh
+
+swp=$NETIF_NO_CABLE
+
+cleanup()
+{
+	pre_cleanup
+}
+
+get_prio_pg()
+{
+	__mlnx_qos -i $swp | sed -n '/^PFC/,/^[^[:space:]]/p' |
+		grep buffer | sed 's/ \+/ /g' | cut -d' ' -f 2-
+}
+
+get_prio_pfc()
+{
+	__mlnx_qos -i $swp | sed -n '/^PFC/,/^[^[:space:]]/p' |
+		grep enabled | sed 's/ \+/ /g' | cut -d' ' -f 2-
+}
+
+get_prio_tc()
+{
+	__mlnx_qos -i $swp | sed -n '/^tc/,$p' |
+		awk '/^tc/ { TC = $2 }
+		     /priority:/ { PRIO[$2]=TC }
+		     END {
+			for (i in PRIO)
+			    printf("%d ", PRIO[i])
+		     }'
+}
+
+get_buf_size()
+{
+	local idx=$1; shift
+
+	__mlnx_qos -i $swp | grep Receive | sed 's/.*: //' | cut -d, -f $((idx + 1))
+}
+
+get_tot_size()
+{
+	__mlnx_qos -i $swp | grep Receive | sed 's/.*total_size=//'
+}
+
+check_prio_pg()
+{
+	local expect=$1; shift
+
+	local current=$(get_prio_pg)
+	test "$current" = "$expect"
+	check_err $? "prio2buffer is '$current', expected '$expect'"
+}
+
+check_prio_pfc()
+{
+	local expect=$1; shift
+
+	local current=$(get_prio_pfc)
+	test "$current" = "$expect"
+	check_err $? "prio PFC is '$current', expected '$expect'"
+}
+
+check_prio_tc()
+{
+	local expect=$1; shift
+
+	local current=$(get_prio_tc)
+	test "$current" = "$expect"
+	check_err $? "prio_tc is '$current', expected '$expect'"
+}
+
+__check_buf_size()
+{
+	local idx=$1; shift
+	local expr=$1; shift
+	local what=$1; shift
+
+	local current=$(get_buf_size $idx)
+	((current $expr))
+	check_err $? "${what}buffer $idx size is '$current', expected '$expr'"
+	echo $current
+}
+
+check_buf_size()
+{
+	__check_buf_size "$@" > /dev/null
+}
+
+test_defaults()
+{
+	RET=0
+
+	check_prio_pg "0 0 0 0 0 0 0 0 "
+	check_prio_tc "0 0 0 0 0 0 0 0 "
+	check_prio_pfc "0 0 0 0 0 0 0 0 "
+
+	log_test "Default headroom configuration"
+}
+
+test_dcb_ets()
+{
+	RET=0
+
+	__mlnx_qos -i $swp --prio_tc=0,2,4,6,1,3,5,7 > /dev/null
+
+	check_prio_pg "0 2 4 6 1 3 5 7 "
+	check_prio_tc "0 2 4 6 1 3 5 7 "
+	check_prio_pfc "0 0 0 0 0 0 0 0 "
+
+	__mlnx_qos -i $swp --prio_tc=0,0,0,0,0,0,0,0 > /dev/null
+
+	check_prio_pg "0 0 0 0 0 0 0 0 "
+	check_prio_tc "0 0 0 0 0 0 0 0 "
+
+	__mlnx_qos -i $swp --prio2buffer=1,3,5,7,0,2,4,6 &> /dev/null
+	check_fail $? "prio2buffer accepted in DCB mode"
+
+	log_test "Configuring headroom through ETS"
+}
+
+test_mtu()
+{
+	local what=$1; shift
+	local buf0size_2
+	local buf0size
+
+	RET=0
+	buf0size=$(__check_buf_size 0 "> 0")
+
+	mtu_set $swp 3000
+	buf0size_2=$(__check_buf_size 0 "> $buf0size" "MTU 3000: ")
+	mtu_restore $swp
+
+	mtu_set $swp 6000
+	check_buf_size 0 "> $buf0size_2" "MTU 6000: "
+	mtu_restore $swp
+
+	check_buf_size 0 "== $buf0size"
+
+	log_test "${what}MTU impacts buffer size"
+}
+
+test_tc_mtu()
+{
+	# In TC mode, MTU still impacts the threshold below which a buffer is
+	# not permitted to go.
+
+	tc qdisc replace dev $swp root handle 1: bfifo limit 1.5M
+	test_mtu "TC: "
+	tc qdisc delete dev $swp root
+}
+
+test_pfc()
+{
+	RET=0
+
+	__mlnx_qos -i $swp --prio_tc=0,0,0,0,0,1,2,3 > /dev/null
+
+	local buf0size=$(get_buf_size 0)
+	local buf1size=$(get_buf_size 1)
+	local buf2size=$(get_buf_size 2)
+	local buf3size=$(get_buf_size 3)
+	check_buf_size 0 "> 0"
+	check_buf_size 1 "> 0"
+	check_buf_size 2 "> 0"
+	check_buf_size 3 "> 0"
+	check_buf_size 4 "== 0"
+	check_buf_size 5 "== 0"
+	check_buf_size 6 "== 0"
+	check_buf_size 7 "== 0"
+
+	log_test "Buffer size sans PFC"
+
+	RET=0
+
+	__mlnx_qos -i $swp --pfc=0,0,0,0,0,1,1,1 --cable_len=0 > /dev/null
+
+	check_prio_pg "0 0 0 0 0 1 2 3 "
+	check_prio_pfc "0 0 0 0 0 1 1 1 "
+	check_buf_size 0 "== $buf0size"
+	check_buf_size 1 "> $buf1size"
+	check_buf_size 2 "> $buf2size"
+	check_buf_size 3 "> $buf3size"
+
+	local buf1size=$(get_buf_size 1)
+	check_buf_size 2 "== $buf1size"
+	check_buf_size 3 "== $buf1size"
+
+	log_test "PFC: Cable length 0"
+
+	RET=0
+
+	__mlnx_qos -i $swp --pfc=0,0,0,0,0,1,1,1 --cable_len=1000 > /dev/null
+
+	check_buf_size 0 "== $buf0size"
+	check_buf_size 1 "> $buf1size"
+	check_buf_size 2 "> $buf1size"
+	check_buf_size 3 "> $buf1size"
+
+	log_test "PFC: Cable length 1000"
+
+	RET=0
+
+	__mlnx_qos -i $swp --pfc=0,0,0,0,0,0,0,0 --cable_len=0 > /dev/null
+	__mlnx_qos -i $swp --prio_tc=0,0,0,0,0,0,0,0 > /dev/null
+
+	check_prio_pg "0 0 0 0 0 0 0 0 "
+	check_prio_tc "0 0 0 0 0 0 0 0 "
+	check_buf_size 0 "> 0"
+	check_buf_size 1 "== 0"
+	check_buf_size 2 "== 0"
+	check_buf_size 3 "== 0"
+	check_buf_size 4 "== 0"
+	check_buf_size 5 "== 0"
+	check_buf_size 6 "== 0"
+	check_buf_size 7 "== 0"
+
+	log_test "PFC: Restore defaults"
+}
+
+test_tc_priomap()
+{
+	RET=0
+
+	__mlnx_qos -i $swp --prio_tc=0,1,2,3,4,5,6,7 > /dev/null
+	check_prio_pg "0 1 2 3 4 5 6 7 "
+
+	tc qdisc replace dev $swp root handle 1: bfifo limit 1.5M
+	check_prio_pg "0 0 0 0 0 0 0 0 "
+
+	__mlnx_qos -i $swp --prio2buffer=1,3,5,7,0,2,4,6 > /dev/null
+	check_prio_pg "1 3 5 7 0 2 4 6 "
+
+	tc qdisc delete dev $swp root
+	check_prio_pg "0 1 2 3 4 5 6 7 "
+
+	# Clean up.
+	tc qdisc replace dev $swp root handle 1: bfifo limit 1.5M
+	__mlnx_qos -i $swp --prio2buffer=0,0,0,0,0,0,0,0 > /dev/null
+	tc qdisc delete dev $swp root
+	__mlnx_qos -i $swp --prio_tc=0,0,0,0,0,0,0,0 > /dev/null
+
+	log_test "TC: priomap"
+}
+
+test_tc_sizes()
+{
+	local cell_size=$(devlink_cell_size_get)
+	local size=$((cell_size * 1000))
+
+	RET=0
+
+	__mlnx_qos -i $swp --buffer_size=$size,0,0,0,0,0,0,0 &> /dev/null
+	check_fail $? "buffer_size should fail before qdisc is added"
+
+	tc qdisc replace dev $swp root handle 1: bfifo limit 1.5M
+
+	__mlnx_qos -i $swp --buffer_size=$size,0,0,0,0,0,0,0 > /dev/null
+	check_err $? "buffer_size should pass after qdisc is added"
+	check_buf_size 0 "== $size" "set size: "
+
+	mtu_set $swp 6000
+	check_buf_size 0 "== $size" "set MTU: "
+	mtu_restore $swp
+
+	__mlnx_qos -i $swp --buffer_size=0,0,0,0,0,0,0,0 > /dev/null
+
+	# After replacing the qdisc for the same kind, buffer_size still has to
+	# work.
+	tc qdisc replace dev $swp root handle 1: bfifo limit 1M
+
+	__mlnx_qos -i $swp --buffer_size=$size,0,0,0,0,0,0,0 > /dev/null
+	check_buf_size 0 "== $size" "post replace, set size: "
+
+	__mlnx_qos -i $swp --buffer_size=0,0,0,0,0,0,0,0 > /dev/null
+
+	# Likewise after replacing for a different kind.
+	tc qdisc replace dev $swp root handle 2: prio bands 8
+
+	__mlnx_qos -i $swp --buffer_size=$size,0,0,0,0,0,0,0 > /dev/null
+	check_buf_size 0 "== $size" "post replace different kind, set size: "
+
+	tc qdisc delete dev $swp root
+
+	__mlnx_qos -i $swp --buffer_size=$size,0,0,0,0,0,0,0 &> /dev/null
+	check_fail $? "buffer_size should fail after qdisc is deleted"
+
+	log_test "TC: buffer size"
+}
+
+test_int_buf()
+{
+	local what=$1; shift
+
+	RET=0
+
+	local buf0size=$(get_buf_size 0)
+	local tot_size=$(get_tot_size)
+
+	# Size of internal buffer and buffer 9.
+	local dsize=$((tot_size - buf0size))
+
+	tc qdisc add dev $swp clsact
+	tc filter add dev $swp egress matchall skip_sw action mirred egress mirror dev $swp
+
+	local buf0size_2=$(get_buf_size 0)
+	local tot_size_2=$(get_tot_size)
+	local dsize_2=$((tot_size_2 - buf0size_2))
+
+	# Egress SPAN should have added to the "invisible" buffer configuration.
+	((dsize_2 > dsize))
+	check_err $? "Invisible buffers account for '$dsize_2', expected '> $dsize'"
+
+	mtu_set $swp 3000
+
+	local buf0size_3=$(get_buf_size 0)
+	local tot_size_3=$(get_tot_size)
+	local dsize_3=$((tot_size_3 - buf0size_3))
+
+	# MTU change might change buffer 0, which will show at total, but the
+	# hidden buffers should stay the same size.
+	((dsize_3 == dsize_2))
+	check_err $? "MTU change: Invisible buffers account for '$dsize_3', expected '== $dsize_2'"
+
+	mtu_restore $swp
+	tc qdisc del dev $swp clsact
+
+	# After SPAN removal, hidden buffers should be back to the original sizes.
+	local buf0size_4=$(get_buf_size 0)
+	local tot_size_4=$(get_tot_size)
+	local dsize_4=$((tot_size_4 - buf0size_4))
+	((dsize_4 == dsize))
+	check_err $? "SPAN removed: Invisible buffers account for '$dsize_4', expected '== $dsize'"
+
+	log_test "${what}internal buffer size"
+}
+
+test_tc_int_buf()
+{
+	local cell_size=$(devlink_cell_size_get)
+	local size=$((cell_size * 1000))
+
+	tc qdisc replace dev $swp root handle 1: bfifo limit 1.5M
+	test_int_buf "TC: "
+
+	__mlnx_qos -i $swp --buffer_size=$size,0,0,0,0,0,0,0 > /dev/null
+	test_int_buf "TC+buffsize: "
+
+	__mlnx_qos -i $swp --buffer_size=0,0,0,0,0,0,0,0 > /dev/null
+	tc qdisc delete dev $swp root
+}
+
+trap cleanup EXIT
+
+bail_on_lldpad
+setup_wait
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_lib.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_lib.sh
index faa51012cdac..0bf76f13c030 100644
--- a/tools/testing/selftests/drivers/net/mlxsw/qos_lib.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/qos_lib.sh
@@ -82,3 +82,17 @@ bail_on_lldpad()
 		fi
 	fi
 }
+
+__mlnx_qos()
+{
+	local err
+
+	mlnx_qos "$@" 2>/dev/null
+	err=$?
+
+	if ((err)); then
+		echo "Error ($err) in mlnx_qos $@" >/dev/stderr
+	fi
+
+	return $err
+}
diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh
index b025daea062d..8f164c80e215 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh
@@ -145,12 +145,17 @@ switch_create()
 
 	# Make sure that ingress quotas are smaller than egress so that there is
 	# room for both streams of traffic to be admitted to shared buffer.
+	devlink_port_pool_th_save $swp1 0
 	devlink_port_pool_th_set $swp1 0 5
+	devlink_tc_bind_pool_th_save $swp1 0 ingress
 	devlink_tc_bind_pool_th_set $swp1 0 ingress 0 5
 
+	devlink_port_pool_th_save $swp2 0
 	devlink_port_pool_th_set $swp2 0 5
+	devlink_tc_bind_pool_th_save $swp2 1 ingress
 	devlink_tc_bind_pool_th_set $swp2 1 ingress 0 5
 
+	devlink_port_pool_th_save $swp3 4
 	devlink_port_pool_th_set $swp3 4 12
 }
 
diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh
new file mode 100755
index 000000000000..4d900bc1f76c
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh
@@ -0,0 +1,403 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# This test injects a 10-MB burst of traffic with VLAN tag and 802.1p priority
+# of 1. This stream is consistently prioritized as priority 1, is put to PG
+# buffer 1, and scheduled at TC 1.
+#
+# - the stream first ingresses through $swp1, where it is forwarded to $swp3
+#
+# - then it ingresses through $swp4. Here it is put to a lossless buffer and put
+#   to a small pool ("PFC pool"). The traffic is forwarded to $swp2, which is
+#   shaped, and thus the PFC pool eventually fills, therefore the headroom
+#   fills, and $swp3 is paused.
+#
+# - since $swp3 now can't send traffic, the traffic ingressing $swp1 is kept at
+#   a pool ("overflow pool"). The overflow pool needs to be large enough to
+#   contain the whole burst.
+#
+# - eventually the PFC pool gets some traffic out, headroom therefore gets some
+#   traffic to the pool, and $swp3 is unpaused again. This way the traffic is
+#   gradually forwarded from the overflow pool, through the PFC pool, out of
+#   $swp2, and eventually to $h2.
+#
+# - if PFC works, all lossless flow packets that ingress through $swp1 should
+#   also be seen ingressing $h2. If it doesn't, there will be drops due to
+#   discrepancy between the speeds of $swp1 and $h2.
+#
+# - it should all play out relatively quickly, so that SLL and HLL will not
+#   cause drops.
+#
+# +-----------------------+
+# | H1                    |
+# |   + $h1.111           |
+# |   | 192.0.2.33/28     |
+# |   |                   |
+# |   + $h1               |
+# +---|-------------------+  +--------------------+
+#     |                      |                    |
+# +---|----------------------|--------------------|---------------------------+
+# |   + $swp1          $swp3 +                    + $swp4                     |
+# |   | iPOOL1        iPOOL0 |                    | iPOOL2                    |
+# |   | ePOOL4        ePOOL5 |                    | ePOOL4                    |
+# |   |                1Gbps |                    | 1Gbps                     |
+# |   |        PFC:enabled=1 |                    | PFC:enabled=1             |
+# | +-|----------------------|-+                +-|------------------------+  |
+# | | + $swp1.111  $swp3.111 + |                | + $swp4.111              |  |
+# | |                          |                |                          |  |
+# | | BR1                      |                | BR2                      |  |
+# | |                          |                |                          |  |
+# | |                          |                |         + $swp2.111      |  |
+# | +--------------------------+                +---------|----------------+  |
+# |                                                       |                   |
+# | iPOOL0: 500KB dynamic                                 |                   |
+# | iPOOL1: 10MB static                                   |                   |
+# | iPOOL2: 1MB static                                    + $swp2             |
+# | ePOOL4: 500KB dynamic                                 | iPOOL0            |
+# | ePOOL5: 10MB static                                   | ePOOL6            |
+# | ePOOL6: "infinite" static                             | 200Mbps shaper    |
+# +-------------------------------------------------------|-------------------+
+#                                                         |
+#                                                     +---|-------------------+
+#                                                     |   + $h2            H2 |
+#                                                     |   |                   |
+#                                                     |   + $h2.111           |
+#                                                     |     192.0.2.34/28     |
+#                                                     +-----------------------+
+#
+# iPOOL0+ePOOL4 is a helper pool for control traffic etc.
+# iPOOL1+ePOOL5 are overflow pools.
+# iPOOL2+ePOOL6 are PFC pools.
+
+ALL_TESTS="
+	ping_ipv4
+	test_qos_pfc
+"
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+NUM_NETIFS=6
+source $lib_dir/lib.sh
+source $lib_dir/devlink_lib.sh
+source qos_lib.sh
+
+_1KB=1000
+_100KB=$((100 * _1KB))
+_500KB=$((500 * _1KB))
+_1MB=$((1000 * _1KB))
+_10MB=$((10 * _1MB))
+
+h1_create()
+{
+	simple_if_init $h1
+	mtu_set $h1 10000
+
+	vlan_create $h1 111 v$h1 192.0.2.33/28
+}
+
+h1_destroy()
+{
+	vlan_destroy $h1 111
+
+	mtu_restore $h1
+	simple_if_fini $h1
+}
+
+h2_create()
+{
+	simple_if_init $h2
+	mtu_set $h2 10000
+
+	vlan_create $h2 111 v$h2 192.0.2.34/28
+}
+
+h2_destroy()
+{
+	vlan_destroy $h2 111
+
+	mtu_restore $h2
+	simple_if_fini $h2
+}
+
+switch_create()
+{
+	# pools
+	# -----
+
+	devlink_pool_size_thtype_save 0
+	devlink_pool_size_thtype_save 4
+	devlink_pool_size_thtype_save 1
+	devlink_pool_size_thtype_save 5
+	devlink_pool_size_thtype_save 2
+	devlink_pool_size_thtype_save 6
+
+	devlink_port_pool_th_save $swp1 1
+	devlink_port_pool_th_save $swp2 6
+	devlink_port_pool_th_save $swp3 5
+	devlink_port_pool_th_save $swp4 2
+
+	devlink_tc_bind_pool_th_save $swp1 1 ingress
+	devlink_tc_bind_pool_th_save $swp2 1 egress
+	devlink_tc_bind_pool_th_save $swp3 1 egress
+	devlink_tc_bind_pool_th_save $swp4 1 ingress
+
+	# Control traffic pools. Just reduce the size. Keep them dynamic so that
+	# we don't need to change all the uninteresting quotas.
+	devlink_pool_size_thtype_set 0 dynamic $_500KB
+	devlink_pool_size_thtype_set 4 dynamic $_500KB
+
+	# Overflow pools.
+	devlink_pool_size_thtype_set 1 static $_10MB
+	devlink_pool_size_thtype_set 5 static $_10MB
+
+	# PFC pools. As per the writ, the size of egress PFC pool should be
+	# infinice, but actually it just needs to be large enough to not matter
+	# in practice, so reuse the 10MB limit.
+	devlink_pool_size_thtype_set 2 static $_1MB
+	devlink_pool_size_thtype_set 6 static $_10MB
+
+	# $swp1
+	# -----
+
+	ip link set dev $swp1 up
+	mtu_set $swp1 10000
+	vlan_create $swp1 111
+	ip link set dev $swp1.111 type vlan ingress-qos-map 0:0 1:1
+
+	devlink_port_pool_th_set $swp1 1 $_10MB
+	devlink_tc_bind_pool_th_set $swp1 1 ingress 1 $_10MB
+
+	# Configure qdisc so that we can configure PG and therefore pool
+	# assignment.
+	tc qdisc replace dev $swp1 root handle 1: \
+	   ets bands 8 strict 8 priomap 7 6
+	__mlnx_qos -i $swp1 --prio2buffer=0,1,0,0,0,0,0,0 >/dev/null
+
+	# $swp2
+	# -----
+
+	ip link set dev $swp2 up
+	mtu_set $swp2 10000
+	vlan_create $swp2 111
+	ip link set dev $swp2.111 type vlan egress-qos-map 0:0 1:1
+
+	devlink_port_pool_th_set $swp2 6 $_10MB
+	devlink_tc_bind_pool_th_set $swp2 1 egress 6 $_10MB
+
+	# prio 0->TC0 (band 7), 1->TC1 (band 6). TC1 is shaped.
+	tc qdisc replace dev $swp2 root handle 1: \
+	   ets bands 8 strict 8 priomap 7 6
+	tc qdisc replace dev $swp2 parent 1:7 handle 17: \
+	   tbf rate 200Mbit burst 131072 limit 1M
+
+	# $swp3
+	# -----
+
+	ip link set dev $swp3 up
+	mtu_set $swp3 10000
+	vlan_create $swp3 111
+	ip link set dev $swp3.111 type vlan egress-qos-map 0:0 1:1
+
+	devlink_port_pool_th_set $swp3 5 $_10MB
+	devlink_tc_bind_pool_th_set $swp3 1 egress 5 $_10MB
+
+	# prio 0->TC0 (band 7), 1->TC1 (band 6)
+	tc qdisc replace dev $swp3 root handle 1: \
+	   ets bands 8 strict 8 priomap 7 6
+
+	# Need to enable PFC so that PAUSE takes effect. Therefore need to put
+	# the lossless prio into a buffer of its own. Don't bother with buffer
+	# sizes though, there is not going to be any pressure in the "backward"
+	# direction.
+	__mlnx_qos -i $swp3 --prio2buffer=0,1,0,0,0,0,0,0 >/dev/null
+	__mlnx_qos -i $swp3 --pfc=0,1,0,0,0,0,0,0 >/dev/null
+
+	# $swp4
+	# -----
+
+	ip link set dev $swp4 up
+	mtu_set $swp4 10000
+	vlan_create $swp4 111
+	ip link set dev $swp4.111 type vlan ingress-qos-map 0:0 1:1
+
+	devlink_port_pool_th_set $swp4 2 $_1MB
+	devlink_tc_bind_pool_th_set $swp4 1 ingress 2 $_1MB
+
+	# Configure qdisc so that we can hand-tune headroom.
+	tc qdisc replace dev $swp4 root handle 1: \
+	   ets bands 8 strict 8 priomap 7 6
+	__mlnx_qos -i $swp4 --prio2buffer=0,1,0,0,0,0,0,0 >/dev/null
+	__mlnx_qos -i $swp4 --pfc=0,1,0,0,0,0,0,0 >/dev/null
+	# PG0 will get autoconfigured to Xoff, give PG1 arbitrarily 100K, which
+	# is (-2*MTU) about 80K of delay provision.
+	__mlnx_qos -i $swp3 --buffer_size=0,$_100KB,0,0,0,0,0,0 >/dev/null
+
+	# bridges
+	# -------
+
+	ip link add name br1 type bridge vlan_filtering 0
+	ip link set dev $swp1.111 master br1
+	ip link set dev $swp3.111 master br1
+	ip link set dev br1 up
+
+	ip link add name br2 type bridge vlan_filtering 0
+	ip link set dev $swp2.111 master br2
+	ip link set dev $swp4.111 master br2
+	ip link set dev br2 up
+}
+
+switch_destroy()
+{
+	# Do this first so that we can reset the limits to values that are only
+	# valid for the original static / dynamic setting.
+	devlink_pool_size_thtype_restore 6
+	devlink_pool_size_thtype_restore 5
+	devlink_pool_size_thtype_restore 4
+	devlink_pool_size_thtype_restore 2
+	devlink_pool_size_thtype_restore 1
+	devlink_pool_size_thtype_restore 0
+
+	# bridges
+	# -------
+
+	ip link set dev br2 down
+	ip link set dev $swp4.111 nomaster
+	ip link set dev $swp2.111 nomaster
+	ip link del dev br2
+
+	ip link set dev br1 down
+	ip link set dev $swp3.111 nomaster
+	ip link set dev $swp1.111 nomaster
+	ip link del dev br1
+
+	# $swp4
+	# -----
+
+	__mlnx_qos -i $swp4 --buffer_size=0,0,0,0,0,0,0,0 >/dev/null
+	__mlnx_qos -i $swp4 --pfc=0,0,0,0,0,0,0,0 >/dev/null
+	__mlnx_qos -i $swp4 --prio2buffer=0,0,0,0,0,0,0,0 >/dev/null
+	tc qdisc del dev $swp4 root
+
+	devlink_tc_bind_pool_th_restore $swp4 1 ingress
+	devlink_port_pool_th_restore $swp4 2
+
+	vlan_destroy $swp4 111
+	mtu_restore $swp4
+	ip link set dev $swp4 down
+
+	# $swp3
+	# -----
+
+	__mlnx_qos -i $swp3 --pfc=0,0,0,0,0,0,0,0 >/dev/null
+	__mlnx_qos -i $swp3 --prio2buffer=0,0,0,0,0,0,0,0 >/dev/null
+	tc qdisc del dev $swp3 root
+
+	devlink_tc_bind_pool_th_restore $swp3 1 egress
+	devlink_port_pool_th_restore $swp3 5
+
+	vlan_destroy $swp3 111
+	mtu_restore $swp3
+	ip link set dev $swp3 down
+
+	# $swp2
+	# -----
+
+	tc qdisc del dev $swp2 parent 1:7
+	tc qdisc del dev $swp2 root
+
+	devlink_tc_bind_pool_th_restore $swp2 1 egress
+	devlink_port_pool_th_restore $swp2 6
+
+	vlan_destroy $swp2 111
+	mtu_restore $swp2
+	ip link set dev $swp2 down
+
+	# $swp1
+	# -----
+
+	__mlnx_qos -i $swp1 --prio2buffer=0,0,0,0,0,0,0,0 >/dev/null
+	tc qdisc del dev $swp1 root
+
+	devlink_tc_bind_pool_th_restore $swp1 1 ingress
+	devlink_port_pool_th_restore $swp1 1
+
+	vlan_destroy $swp1 111
+	mtu_restore $swp1
+	ip link set dev $swp1 down
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	swp1=${NETIFS[p2]}
+
+	swp2=${NETIFS[p3]}
+	h2=${NETIFS[p4]}
+
+	swp3=${NETIFS[p5]}
+	swp4=${NETIFS[p6]}
+
+	h2mac=$(mac_get $h2)
+
+	vrf_prepare
+
+	h1_create
+	h2_create
+	switch_create
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	switch_destroy
+	h2_destroy
+	h1_destroy
+
+	vrf_cleanup
+}
+
+ping_ipv4()
+{
+	ping_test $h1 192.0.2.34
+}
+
+test_qos_pfc()
+{
+	RET=0
+
+	# 10M pool, each packet is 8K of payload + headers
+	local pkts=$((_10MB / 8050))
+	local size=$((pkts * 8050))
+	local in0=$(ethtool_stats_get $swp1 rx_octets_prio_1)
+	local out0=$(ethtool_stats_get $swp2 tx_octets_prio_1)
+
+	$MZ $h1 -p 8000 -Q 1:111 -A 192.0.2.33 -B 192.0.2.34 \
+		-a own -b $h2mac -c $pkts -t udp -q
+	sleep 2
+
+	local in1=$(ethtool_stats_get $swp1 rx_octets_prio_1)
+	local out1=$(ethtool_stats_get $swp2 tx_octets_prio_1)
+
+	local din=$((in1 - in0))
+	local dout=$((out1 - out0))
+
+	local pct_in=$((din * 100 / size))
+
+	((pct_in > 95 && pct_in < 105))
+	check_err $? "Relative ingress out of expected bounds, $pct_in% should be 100%"
+
+	((dout == din))
+	check_err $? "$((din - dout)) bytes out of $din ingressed got lost"
+
+	log_test "PFC"
+}
+
+trap cleanup EXIT
+
+bail_on_lldpad
+setup_prepare
+setup_wait
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_ets.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_ets.sh
index 94c37124a840..af64bc9ea8ab 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/sch_ets.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/sch_ets.sh
@@ -27,11 +27,17 @@ switch_create()
 	# amount of traffic that is admitted to the shared buffers. This makes
 	# sure that there is always enough traffic of all types to select from
 	# for the DWRR process.
+	devlink_port_pool_th_save $swp1 0
 	devlink_port_pool_th_set $swp1 0 12
+	devlink_tc_bind_pool_th_save $swp1 0 ingress
 	devlink_tc_bind_pool_th_set $swp1 0 ingress 0 12
+	devlink_port_pool_th_save $swp2 4
 	devlink_port_pool_th_set $swp2 4 12
+	devlink_tc_bind_pool_th_save $swp2 7 egress
 	devlink_tc_bind_pool_th_set $swp2 7 egress 4 5
+	devlink_tc_bind_pool_th_save $swp2 6 egress
 	devlink_tc_bind_pool_th_set $swp2 6 egress 4 5
+	devlink_tc_bind_pool_th_save $swp2 5 egress
 	devlink_tc_bind_pool_th_set $swp2 5 egress 4 5
 
 	# Note: sch_ets_core.sh uses VLAN ingress-qos-map to assign packet
diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh
index 517297a14ecf..b0cb1aaffdda 100644
--- a/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh
@@ -208,6 +208,7 @@ switch_create()
 	ip link set dev br2_11 up
 
 	local size=$(devlink_pool_size_thtype 0 | cut -d' ' -f 1)
+	devlink_port_pool_th_save $swp3 8
 	devlink_port_pool_th_set $swp3 8 $size
 }
 
diff --git a/tools/testing/selftests/drivers/net/netdevsim/devlink.sh b/tools/testing/selftests/drivers/net/netdevsim/devlink.sh
index de4b32fc4223..40909c254365 100755
--- a/tools/testing/selftests/drivers/net/netdevsim/devlink.sh
+++ b/tools/testing/selftests/drivers/net/netdevsim/devlink.sh
@@ -23,6 +23,27 @@ fw_flash_test()
 	devlink dev flash $DL_HANDLE file dummy
 	check_err $? "Failed to flash with status updates on"
 
+	devlink dev flash $DL_HANDLE file dummy component fw.mgmt
+	check_err $? "Failed to flash with component attribute"
+
+	devlink dev flash $DL_HANDLE file dummy overwrite settings
+	check_fail $? "Flash with overwrite settings should be rejected"
+
+	echo "1"> $DEBUGFS_DIR/fw_update_overwrite_mask
+	check_err $? "Failed to change allowed overwrite mask"
+
+	devlink dev flash $DL_HANDLE file dummy overwrite settings
+	check_err $? "Failed to flash with settings overwrite enabled"
+
+	devlink dev flash $DL_HANDLE file dummy overwrite identifiers
+	check_fail $? "Flash with overwrite settings should be identifiers"
+
+	echo "3"> $DEBUGFS_DIR/fw_update_overwrite_mask
+	check_err $? "Failed to change allowed overwrite mask"
+
+	devlink dev flash $DL_HANDLE file dummy overwrite identifiers overwrite settings
+	check_err $? "Failed to flash with settings and identifiers overwrite enabled"
+
 	echo "n"> $DEBUGFS_DIR/fw_update_status
 	check_err $? "Failed to disable status updates"
 
diff --git a/tools/testing/selftests/drivers/net/netdevsim/ethtool-pause.sh b/tools/testing/selftests/drivers/net/netdevsim/ethtool-pause.sh
index dd6ad6501c9c..25c896b9e2eb 100755
--- a/tools/testing/selftests/drivers/net/netdevsim/ethtool-pause.sh
+++ b/tools/testing/selftests/drivers/net/netdevsim/ethtool-pause.sh
@@ -3,7 +3,7 @@
 
 NSIM_ID=$((RANDOM % 1024))
 NSIM_DEV_SYS=/sys/bus/netdevsim/devices/netdevsim$NSIM_ID
-NSIM_DEV_DFS=/sys/kernel/debug/netdevsim/netdevsim$NSIM_ID
+NSIM_DEV_DFS=/sys/kernel/debug/netdevsim/netdevsim$NSIM_ID/ports/0
 NSIM_NETDEV=
 num_passes=0
 num_errors=0
diff --git a/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh b/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh
index ba1d53b9f815..1b08e042cf94 100644..100755
--- a/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh
+++ b/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh
@@ -7,6 +7,7 @@ NSIM_DEV_SYS=/sys/bus/netdevsim/devices/netdevsim$NSIM_ID
 NSIM_DEV_DFS=/sys/kernel/debug/netdevsim/netdevsim$NSIM_ID
 NSIM_NETDEV=
 HAS_ETHTOOL=
+STATIC_ENTRIES=
 EXIT_STATUS=0
 num_cases=0
 num_errors=0
@@ -193,6 +194,21 @@ function check_tables {
 	sleep 0.02
 	((retries--))
     done
+
+    if [ -n "$HAS_ETHTOOL" -a -n "${STATIC_ENTRIES[0]}" ]; then
+	fail=0
+	for i in "${!STATIC_ENTRIES[@]}"; do
+	    pp_expected=`pre_ethtool ${STATIC_ENTRIES[i]}`
+	    cnt=$(ethtool --show-tunnels $NSIM_NETDEV | grep -c "$pp_expected")
+	    if [ $cnt -ne 1 ]; then
+		err_cnt "ethtool static entry: $pfx - $msg"
+		echo "       check_table: ethtool does not contain '$pp_expected'"
+		ethtool --show-tunnels $NSIM_NETDEV
+		fail=1
+	    fi
+	done
+	[ $fail == 0 ] && pass_cnt
+    fi
 }
 
 function print_table {
@@ -775,6 +791,157 @@ for port in 0 1; do
     exp1=( 0 0 0 0 )
 done
 
+cleanup_nsim
+
+# shared port tables
+pfx="table sharing"
+
+echo $NSIM_ID > /sys/bus/netdevsim/new_device
+echo 0 > $NSIM_DEV_SYS/del_port
+
+echo 0 > $NSIM_DEV_DFS/udp_ports_open_only
+echo 1 > $NSIM_DEV_DFS/udp_ports_sleep
+echo 1 > $NSIM_DEV_DFS/udp_ports_shared
+
+old_netdevs=$(ls /sys/class/net)
+echo 1 > $NSIM_DEV_SYS/new_port
+NSIM_NETDEV=`get_netdev_name old_netdevs`
+old_netdevs=$(ls /sys/class/net)
+echo 2 > $NSIM_DEV_SYS/new_port
+NSIM_NETDEV2=`get_netdev_name old_netdevs`
+
+msg="VxLAN v4 devices"
+exp0=( `mke 4789 1` 0 0 0 )
+exp1=( 0 0 0 0 )
+new_vxlan vxlan0 4789 $NSIM_NETDEV
+new_vxlan vxlan1 4789 $NSIM_NETDEV2
+
+msg="VxLAN v4 devices go down"
+exp0=( 0 0 0 0 )
+ifconfig vxlan1 down
+ifconfig vxlan0 down
+check_tables
+
+for ifc in vxlan0 vxlan1; do
+    ifconfig $ifc up
+done
+
+msg="VxLAN v6 device"
+exp0=( `mke 4789 1` `mke 4790 1` 0 0 )
+new_vxlan vxlanC 4790 $NSIM_NETDEV 6
+
+msg="Geneve device"
+exp1=( `mke 6081 2` 0 0 0 )
+new_geneve gnv0 6081
+
+msg="NIC device goes down"
+ifconfig $NSIM_NETDEV down
+check_tables
+
+msg="NIC device goes up again"
+ifconfig $NSIM_NETDEV up
+check_tables
+
+for i in `seq 2`; do
+    msg="turn feature off - 1, rep $i"
+    ethtool -K $NSIM_NETDEV rx-udp_tunnel-port-offload off
+    check_tables
+
+    msg="turn feature off - 2, rep $i"
+    exp0=( 0 0 0 0 )
+    exp1=( 0 0 0 0 )
+    ethtool -K $NSIM_NETDEV2 rx-udp_tunnel-port-offload off
+    check_tables
+
+    msg="turn feature on - 1, rep $i"
+    exp0=( `mke 4789 1` `mke 4790 1` 0 0 )
+    exp1=( `mke 6081 2` 0 0 0 )
+    ethtool -K $NSIM_NETDEV rx-udp_tunnel-port-offload on
+    check_tables
+
+    msg="turn feature on - 2, rep $i"
+    ethtool -K $NSIM_NETDEV2 rx-udp_tunnel-port-offload on
+    check_tables
+done
+
+msg="tunnels destroyed 1"
+cleanup_tuns
+exp0=( 0 0 0 0 )
+exp1=( 0 0 0 0 )
+check_tables
+
+overflow_table0 "overflow NIC table"
+
+msg="re-add a port"
+
+echo 2 > $NSIM_DEV_SYS/del_port
+echo 2 > $NSIM_DEV_SYS/new_port
+check_tables
+
+msg="replace VxLAN in overflow table"
+exp0=( `mke 10000 1` `mke 10004 1` `mke 10002 1` `mke 10003 1` )
+del_dev vxlan1
+
+msg="vacate VxLAN in overflow table"
+exp0=( `mke 10000 1` `mke 10004 1` 0 `mke 10003 1` )
+del_dev vxlan2
+
+echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports_reset
+check_tables
+
+msg="tunnels destroyed 2"
+cleanup_tuns
+exp0=( 0 0 0 0 )
+exp1=( 0 0 0 0 )
+check_tables
+
+echo 1 > $NSIM_DEV_SYS/del_port
+echo 2 > $NSIM_DEV_SYS/del_port
+
+cleanup_nsim
+
+# Static IANA port
+pfx="static IANA vxlan"
+
+echo $NSIM_ID > /sys/bus/netdevsim/new_device
+echo 0 > $NSIM_DEV_SYS/del_port
+
+echo 1 > $NSIM_DEV_DFS/udp_ports_static_iana_vxlan
+STATIC_ENTRIES=( `mke 4789 1` )
+
+port=1
+old_netdevs=$(ls /sys/class/net)
+echo $port > $NSIM_DEV_SYS/new_port
+NSIM_NETDEV=`get_netdev_name old_netdevs`
+
+msg="check empty"
+exp0=( 0 0 0 0 )
+exp1=( 0 0 0 0 )
+check_tables
+
+msg="add on static port"
+new_vxlan vxlan0 4789 $NSIM_NETDEV
+new_vxlan vxlan1 4789 $NSIM_NETDEV
+
+msg="add on different port"
+exp0=( `mke 4790 1` 0 0 0 )
+new_vxlan vxlan2 4790 $NSIM_NETDEV
+
+cleanup_tuns
+
+msg="tunnels destroyed"
+exp0=( 0 0 0 0 )
+exp1=( 0 0 0 0 )
+check_tables
+
+msg="different type"
+new_geneve gnv0	4789
+
+cleanup_tuns
+cleanup_nsim
+
+# END
+
 modprobe -r netdevsim
 
 if [ $num_errors -eq 0 ]; then
diff --git a/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh b/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh
new file mode 100755
index 000000000000..71a538add08a
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh
@@ -0,0 +1,273 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright 2020 NXP Semiconductors
+
+WAIT_TIME=1
+NUM_NETIFS=4
+lib_dir=$(dirname $0)/../../../net/forwarding
+source $lib_dir/tc_common.sh
+source $lib_dir/lib.sh
+
+require_command tcpdump
+
+#
+#   +---------------------------------------------+
+#   |       DUT ports         Generator ports     |
+#   | +--------+ +--------+ +--------+ +--------+ |
+#   | |        | |        | |        | |        | |
+#   | |  eth0  | |  eth1  | |  eth2  | |  eth3  | |
+#   | |        | |        | |        | |        | |
+#   +-+--------+-+--------+-+--------+-+--------+-+
+#          |         |           |          |
+#          |         |           |          |
+#          |         +-----------+          |
+#          |                                |
+#          +--------------------------------+
+
+eth0=${NETIFS[p1]}
+eth1=${NETIFS[p2]}
+eth2=${NETIFS[p3]}
+eth3=${NETIFS[p4]}
+
+eth0_mac="de:ad:be:ef:00:00"
+eth1_mac="de:ad:be:ef:00:01"
+eth2_mac="de:ad:be:ef:00:02"
+eth3_mac="de:ad:be:ef:00:03"
+
+# Helpers to map a VCAP IS1 and VCAP IS2 lookup and policy to a chain number
+# used by the kernel driver. The numbers are:
+# VCAP IS1 lookup 0:            10000
+# VCAP IS1 lookup 1:            11000
+# VCAP IS1 lookup 2:            12000
+# VCAP IS2 lookup 0 policy 0:   20000
+# VCAP IS2 lookup 0 policy 1:   20001
+# VCAP IS2 lookup 0 policy 255: 20255
+# VCAP IS2 lookup 1 policy 0:   21000
+# VCAP IS2 lookup 1 policy 1:   21001
+# VCAP IS2 lookup 1 policy 255: 21255
+IS1()
+{
+	local lookup=$1
+
+	echo $((10000 + 1000 * lookup))
+}
+
+IS2()
+{
+	local lookup=$1
+	local pag=$2
+
+	echo $((20000 + 1000 * lookup + pag))
+}
+
+ES0()
+{
+	echo 0
+}
+
+# The Ocelot switches have a fixed ingress pipeline composed of:
+#
+# +----------------------------------------------+      +-----------------------------------------+
+# |                   VCAP IS1                   |      |                  VCAP IS2               |
+# |                                              |      |                                         |
+# | +----------+    +----------+    +----------+ |      |            +----------+    +----------+ |
+# | | Lookup 0 |    | Lookup 1 |    | Lookup 2 | | --+------> PAG 0: | Lookup 0 | -> | Lookup 1 | |
+# | +----------+ -> +----------+ -> +----------+ |   |  |            +----------+    +----------+ |
+# | |key&action|    |key&action|    |key&action| |   |  |            |key&action|    |key&action| |
+# | |key&action|    |key&action|    |key&action| |   |  |            |    ..    |    |    ..    | |
+# | |    ..    |    |    ..    |    |    ..    | |   |  |            +----------+    +----------+ |
+# | +----------+    +----------+    +----------+ |   |  |                                         |
+# |                                 selects PAG  |   |  |            +----------+    +----------+ |
+# +----------------------------------------------+   +------> PAG 1: | Lookup 0 | -> | Lookup 1 | |
+#                                                    |  |            +----------+    +----------+ |
+#                                                    |  |            |key&action|    |key&action| |
+#                                                    |  |            |    ..    |    |    ..    | |
+#                                                    |  |            +----------+    +----------+ |
+#                                                    |  |      ...                                |
+#                                                    |  |                                         |
+#                                                    |  |            +----------+    +----------+ |
+#                                                    +----> PAG 254: | Lookup 0 | -> | Lookup 1 | |
+#                                                    |  |            +----------+    +----------+ |
+#                                                    |  |            |key&action|    |key&action| |
+#                                                    |  |            |    ..    |    |    ..    | |
+#                                                    |  |            +----------+    +----------+ |
+#                                                    |  |                                         |
+#                                                    |  |            +----------+    +----------+ |
+#                                                    +----> PAG 255: | Lookup 0 | -> | Lookup 1 | |
+#                                                       |            +----------+    +----------+ |
+#                                                       |            |key&action|    |key&action| |
+#                                                       |            |    ..    |    |    ..    | |
+#                                                       |            +----------+    +----------+ |
+#                                                       +-----------------------------------------+
+#
+# Both the VCAP IS1 (Ingress Stage 1) and IS2 (Ingress Stage 2) are indexed
+# (looked up) multiple times: IS1 3 times, and IS2 2 times. Each filter
+# (key and action pair) can be configured to only match during the first, or
+# second, etc, lookup.
+#
+# During one TCAM lookup, the filter processing stops at the first entry that
+# matches, then the pipeline jumps to the next lookup.
+# The driver maps each individual lookup of each individual ingress TCAM to a
+# separate chain number. For correct rule offloading, it is mandatory that each
+# filter installed in one TCAM is terminated by a non-optional GOTO action to
+# the next lookup from the fixed pipeline.
+#
+# A chain can only be used if there is a GOTO action correctly set up from the
+# prior lookup in the processing pipeline. Setting up all chains is not
+# mandatory.
+
+# NOTE: VCAP IS1 currently uses only S1_NORMAL half keys and VCAP IS2
+# dynamically chooses between MAC_ETYPE, ARP, IP4_TCP_UDP, IP4_OTHER, which are
+# all half keys as well.
+
+create_tcam_skeleton()
+{
+	local eth=$1
+
+	tc qdisc add dev $eth clsact
+
+	# VCAP IS1 is the Ingress Classification TCAM and can offload the
+	# following actions:
+	# - skbedit priority
+	# - vlan pop
+	# - vlan modify
+	# - goto (only in lookup 2, the last IS1 lookup)
+	tc filter add dev $eth ingress chain 0 pref 49152 flower \
+		skip_sw action goto chain $(IS1 0)
+	tc filter add dev $eth ingress chain $(IS1 0) pref 49152 \
+		flower skip_sw action goto chain $(IS1 1)
+	tc filter add dev $eth ingress chain $(IS1 1) pref 49152 \
+		flower skip_sw action goto chain $(IS1 2)
+	tc filter add dev $eth ingress chain $(IS1 2) pref 49152 \
+		flower skip_sw action goto chain $(IS2 0 0)
+
+	# VCAP IS2 is the Security Enforcement ingress TCAM and can offload the
+	# following actions:
+	# - trap
+	# - drop
+	# - police
+	# The two VCAP IS2 lookups can be segmented into up to 256 groups of
+	# rules, called Policies. A Policy is selected through the Policy
+	# Association Group (PAG) action of VCAP IS1 (which is the
+	# GOTO offload).
+	tc filter add dev $eth ingress chain $(IS2 0 0) pref 49152 \
+		flower skip_sw action goto chain $(IS2 1 0)
+}
+
+setup_prepare()
+{
+	create_tcam_skeleton $eth0
+
+	ip link add br0 type bridge
+	ip link set $eth0 master br0
+	ip link set $eth1 master br0
+	ip link set br0 up
+
+	ip link add link $eth3 name $eth3.100 type vlan id 100
+	ip link set $eth3.100 up
+
+	tc filter add dev $eth0 ingress chain $(IS1 1) pref 1 \
+		protocol 802.1Q flower skip_sw vlan_id 100 \
+		action vlan pop \
+		action goto chain $(IS1 2)
+
+	tc filter add dev $eth0 egress chain $(ES0) pref 1 \
+		flower skip_sw indev $eth1 \
+		action vlan push protocol 802.1Q id 100
+
+	tc filter add dev $eth0 ingress chain $(IS1 0) \
+		protocol ipv4 flower skip_sw src_ip 10.1.1.2 \
+		action skbedit priority 7 \
+		action goto chain $(IS1 1)
+
+	tc filter add dev $eth0 ingress chain $(IS2 0 0) \
+		protocol ipv4 flower skip_sw ip_proto udp dst_port 5201 \
+		action police rate 50mbit burst 64k \
+		action goto chain $(IS2 1 0)
+}
+
+cleanup()
+{
+	ip link del $eth3.100
+	tc qdisc del dev $eth0 clsact
+	ip link del br0
+}
+
+test_vlan_pop()
+{
+	printf "Testing VLAN pop..			"
+
+	tcpdump_start $eth2
+
+	# Work around Mausezahn VLAN builder bug
+	# (https://github.com/netsniff-ng/netsniff-ng/issues/225) by using
+	# an 8021q upper
+	$MZ $eth3.100 -q -c 1 -p 64 -a $eth3_mac -b $eth2_mac -t ip
+
+	sleep 1
+
+	tcpdump_stop
+
+	if tcpdump_show | grep -q "$eth3_mac > $eth2_mac, ethertype IPv4"; then
+		echo "OK"
+	else
+		echo "FAIL"
+	fi
+
+	tcpdump_cleanup
+}
+
+test_vlan_push()
+{
+	printf "Testing VLAN push..			"
+
+	tcpdump_start $eth3.100
+
+	$MZ $eth2 -q -c 1 -p 64 -a $eth2_mac -b $eth3_mac -t ip
+
+	sleep 1
+
+	tcpdump_stop
+
+	if tcpdump_show | grep -q "$eth2_mac > $eth3_mac"; then
+		echo "OK"
+	else
+		echo "FAIL"
+	fi
+
+	tcpdump_cleanup
+}
+
+test_skbedit_priority()
+{
+	local num_pkts=100
+
+	printf "Testing frame prioritization..		"
+
+	before=$(ethtool_stats_get $eth0 'rx_green_prio_7')
+
+	$MZ $eth3 -q -c $num_pkts -p 64 -a $eth3_mac -b $eth2_mac -t ip -A 10.1.1.2
+
+	after=$(ethtool_stats_get $eth0 'rx_green_prio_7')
+
+	if [ $((after - before)) = $num_pkts ]; then
+		echo "OK"
+	else
+		echo "FAIL"
+	fi
+}
+
+trap cleanup EXIT
+
+ALL_TESTS="
+	test_vlan_pop
+	test_vlan_push
+	test_skbedit_priority
+"
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore
index 742c499328b2..61ae899cfc17 100644
--- a/tools/testing/selftests/net/.gitignore
+++ b/tools/testing/selftests/net/.gitignore
@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0-only
+ipsec
 msg_zerocopy
 socket
 psock_fanout
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 9491bbaa0831..4773ce72edbd 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -19,6 +19,7 @@ TEST_PROGS += txtimestamp.sh
 TEST_PROGS += vrf-xfrm-tests.sh
 TEST_PROGS += rxtimestamp.sh
 TEST_PROGS += devlink_port_split.py
+TEST_PROGS += drop_monitor_tests.sh
 TEST_PROGS_EXTENDED := in_netns.sh
 TEST_GEN_FILES =  socket nettest
 TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy reuseport_addr_any
@@ -29,6 +30,7 @@ TEST_GEN_FILES += tcp_fastopen_backup_key
 TEST_GEN_FILES += fin_ack_lat
 TEST_GEN_FILES += reuseaddr_ports_exhausted
 TEST_GEN_FILES += hwtstamp_config rxtimestamp timestamping txtimestamp
+TEST_GEN_FILES += ipsec
 TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa
 TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict tls
 
diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config
index 5a57ea02802d..43649242adc0 100644
--- a/tools/testing/selftests/net/config
+++ b/tools/testing/selftests/net/config
@@ -30,3 +30,6 @@ CONFIG_NET_SCH_ETF=m
 CONFIG_NET_SCH_NETEM=y
 CONFIG_TEST_BLACKHOLE_DEV=m
 CONFIG_KALLSYMS=y
+CONFIG_TRACEPOINTS=y
+CONFIG_NET_DROP_MONITOR=m
+CONFIG_NETDEVSIM=m
diff --git a/tools/testing/selftests/net/drop_monitor_tests.sh b/tools/testing/selftests/net/drop_monitor_tests.sh
new file mode 100755
index 000000000000..b7650e30d18b
--- /dev/null
+++ b/tools/testing/selftests/net/drop_monitor_tests.sh
@@ -0,0 +1,215 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# This test is for checking drop monitor functionality.
+
+ret=0
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+# all tests in this script. Can be overridden with -t option
+TESTS="
+	sw_drops
+	hw_drops
+"
+
+IP="ip -netns ns1"
+TC="tc -netns ns1"
+DEVLINK="devlink -N ns1"
+NS_EXEC="ip netns exec ns1"
+NETDEVSIM_PATH=/sys/bus/netdevsim/
+DEV_ADDR=1337
+DEV=netdevsim${DEV_ADDR}
+DEVLINK_DEV=netdevsim/${DEV}
+
+log_test()
+{
+	local rc=$1
+	local expected=$2
+	local msg="$3"
+
+	if [ ${rc} -eq ${expected} ]; then
+		printf "    TEST: %-60s  [ OK ]\n" "${msg}"
+		nsuccess=$((nsuccess+1))
+	else
+		ret=1
+		nfail=$((nfail+1))
+		printf "    TEST: %-60s  [FAIL]\n" "${msg}"
+	fi
+}
+
+setup()
+{
+	modprobe netdevsim &> /dev/null
+
+	set -e
+	ip netns add ns1
+	$IP link add dummy10 up type dummy
+
+	$NS_EXEC echo "$DEV_ADDR 1" > ${NETDEVSIM_PATH}/new_device
+	udevadm settle
+	local netdev=$($NS_EXEC ls ${NETDEVSIM_PATH}/devices/${DEV}/net/)
+	$IP link set dev $netdev up
+
+	set +e
+}
+
+cleanup()
+{
+	$NS_EXEC echo "$DEV_ADDR" > ${NETDEVSIM_PATH}/del_device
+	ip netns del ns1
+}
+
+sw_drops_test()
+{
+	echo
+	echo "Software drops test"
+
+	setup
+
+	local dir=$(mktemp -d)
+
+	$TC qdisc add dev dummy10 clsact
+	$TC filter add dev dummy10 egress pref 1 handle 101 proto ip \
+		flower dst_ip 192.0.2.10 action drop
+
+	$NS_EXEC mausezahn dummy10 -a 00:11:22:33:44:55 -b 00:aa:bb:cc:dd:ee \
+		-A 192.0.2.1 -B 192.0.2.10 -t udp sp=12345,dp=54321 -c 0 -q \
+		-d 100msec &
+	timeout 5 dwdump -o sw -w ${dir}/packets.pcap
+	(( $(tshark -r ${dir}/packets.pcap \
+		-Y 'ip.dst == 192.0.2.10' 2> /dev/null | wc -l) != 0))
+	log_test $? 0 "Capturing active software drops"
+
+	rm ${dir}/packets.pcap
+
+	{ kill %% && wait %%; } 2>/dev/null
+	timeout 5 dwdump -o sw -w ${dir}/packets.pcap
+	(( $(tshark -r ${dir}/packets.pcap \
+		-Y 'ip.dst == 192.0.2.10' 2> /dev/null | wc -l) == 0))
+	log_test $? 0 "Capturing inactive software drops"
+
+	rm -r $dir
+
+	cleanup
+}
+
+hw_drops_test()
+{
+	echo
+	echo "Hardware drops test"
+
+	setup
+
+	local dir=$(mktemp -d)
+
+	$DEVLINK trap set $DEVLINK_DEV trap blackhole_route action trap
+	timeout 5 dwdump -o hw -w ${dir}/packets.pcap
+	(( $(tshark -r ${dir}/packets.pcap \
+		-Y 'net_dm.hw_trap_name== blackhole_route' 2> /dev/null \
+		| wc -l) != 0))
+	log_test $? 0 "Capturing active hardware drops"
+
+	rm ${dir}/packets.pcap
+
+	$DEVLINK trap set $DEVLINK_DEV trap blackhole_route action drop
+	timeout 5 dwdump -o hw -w ${dir}/packets.pcap
+	(( $(tshark -r ${dir}/packets.pcap \
+		-Y 'net_dm.hw_trap_name== blackhole_route' 2> /dev/null \
+		| wc -l) == 0))
+	log_test $? 0 "Capturing inactive hardware drops"
+
+	rm -r $dir
+
+	cleanup
+}
+
+################################################################################
+# usage
+
+usage()
+{
+	cat <<EOF
+usage: ${0##*/} OPTS
+
+        -t <test>   Test(s) to run (default: all)
+                    (options: $TESTS)
+EOF
+}
+
+################################################################################
+# main
+
+while getopts ":t:h" opt; do
+	case $opt in
+		t) TESTS=$OPTARG;;
+		h) usage; exit 0;;
+		*) usage; exit 1;;
+	esac
+done
+
+if [ "$(id -u)" -ne 0 ];then
+	echo "SKIP: Need root privileges"
+	exit $ksft_skip;
+fi
+
+if [ ! -x "$(command -v ip)" ]; then
+	echo "SKIP: Could not run test without ip tool"
+	exit $ksft_skip
+fi
+
+if [ ! -x "$(command -v devlink)" ]; then
+	echo "SKIP: Could not run test without devlink tool"
+	exit $ksft_skip
+fi
+
+if [ ! -x "$(command -v tshark)" ]; then
+	echo "SKIP: Could not run test without tshark tool"
+	exit $ksft_skip
+fi
+
+if [ ! -x "$(command -v dwdump)" ]; then
+	echo "SKIP: Could not run test without dwdump tool"
+	exit $ksft_skip
+fi
+
+if [ ! -x "$(command -v udevadm)" ]; then
+	echo "SKIP: Could not run test without udevadm tool"
+	exit $ksft_skip
+fi
+
+if [ ! -x "$(command -v timeout)" ]; then
+	echo "SKIP: Could not run test without timeout tool"
+	exit $ksft_skip
+fi
+
+if [ ! -x "$(command -v mausezahn)" ]; then
+	echo "SKIP: Could not run test without mausezahn tool"
+	exit $ksft_skip
+fi
+
+tshark -G fields 2> /dev/null | grep -q net_dm
+if [ $? -ne 0 ]; then
+	echo "SKIP: tshark too old, missing net_dm dissector"
+	exit $ksft_skip
+fi
+
+# start clean
+cleanup &> /dev/null
+
+for t in $TESTS
+do
+	case $t in
+	sw_drops|sw)			sw_drops_test;;
+	hw_drops|hw)			hw_drops_test;;
+
+	help) echo "Test names: $TESTS"; exit 0;;
+	esac
+done
+
+if [ "$TESTS" != "none" ]; then
+	printf "\nTests passed: %3d\n" ${nsuccess}
+	printf "Tests failed: %3d\n"   ${nfail}
+fi
+
+exit $ret
diff --git a/tools/testing/selftests/net/forwarding/devlink_lib.sh b/tools/testing/selftests/net/forwarding/devlink_lib.sh
index 75fe24bcb9cd..9c12c4fd3afc 100644
--- a/tools/testing/selftests/net/forwarding/devlink_lib.sh
+++ b/tools/testing/selftests/net/forwarding/devlink_lib.sh
@@ -5,7 +5,7 @@
 # Defines
 
 if [[ ! -v DEVLINK_DEV ]]; then
-	DEVLINK_DEV=$(devlink port show "${NETIFS[p1]}" -j \
+	DEVLINK_DEV=$(devlink port show "${NETIFS[p1]:-$NETIF_NO_CABLE}" -j \
 			     | jq -r '.port | keys[]' | cut -d/ -f-2)
 	if [ -z "$DEVLINK_DEV" ]; then
 		echo "SKIP: ${NETIFS[p1]} has no devlink device registered for it"
@@ -117,6 +117,12 @@ devlink_reload()
 
 declare -A DEVLINK_ORIG
 
+# Changing pool type from static to dynamic causes reinterpretation of threshold
+# values. They therefore need to be saved before pool type is changed, then the
+# pool type can be changed, and then the new values need to be set up. Therefore
+# instead of saving the current state implicitly in the _set call, provide
+# functions for all three primitives: save, set, and restore.
+
 devlink_port_pool_threshold()
 {
 	local port=$1; shift
@@ -126,14 +132,21 @@ devlink_port_pool_threshold()
 		| jq '.port_pool."'"$port"'"[].threshold'
 }
 
-devlink_port_pool_th_set()
+devlink_port_pool_th_save()
 {
 	local port=$1; shift
 	local pool=$1; shift
-	local th=$1; shift
 	local key="port_pool($port,$pool).threshold"
 
 	DEVLINK_ORIG[$key]=$(devlink_port_pool_threshold $port $pool)
+}
+
+devlink_port_pool_th_set()
+{
+	local port=$1; shift
+	local pool=$1; shift
+	local th=$1; shift
+
 	devlink sb port pool set $port pool $pool th $th
 }
 
@@ -142,8 +155,13 @@ devlink_port_pool_th_restore()
 	local port=$1; shift
 	local pool=$1; shift
 	local key="port_pool($port,$pool).threshold"
+	local -a orig=(${DEVLINK_ORIG[$key]})
 
-	devlink sb port pool set $port pool $pool th ${DEVLINK_ORIG[$key]}
+	if [[ -z $orig ]]; then
+		echo "WARNING: Mismatched devlink_port_pool_th_restore"
+	else
+		devlink sb port pool set $port pool $pool th $orig
+	fi
 }
 
 devlink_pool_size_thtype()
@@ -154,14 +172,20 @@ devlink_pool_size_thtype()
 	    | jq -r '.pool[][] | (.size, .thtype)'
 }
 
+devlink_pool_size_thtype_save()
+{
+	local pool=$1; shift
+	local key="pool($pool).size_thtype"
+
+	DEVLINK_ORIG[$key]=$(devlink_pool_size_thtype $pool)
+}
+
 devlink_pool_size_thtype_set()
 {
 	local pool=$1; shift
 	local thtype=$1; shift
 	local size=$1; shift
-	local key="pool($pool).size_thtype"
 
-	DEVLINK_ORIG[$key]=$(devlink_pool_size_thtype $pool)
 	devlink sb pool set "$DEVLINK_DEV" pool $pool size $size thtype $thtype
 }
 
@@ -171,8 +195,12 @@ devlink_pool_size_thtype_restore()
 	local key="pool($pool).size_thtype"
 	local -a orig=(${DEVLINK_ORIG[$key]})
 
-	devlink sb pool set "$DEVLINK_DEV" pool $pool \
-		size ${orig[0]} thtype ${orig[1]}
+	if [[ -z ${orig[0]} ]]; then
+		echo "WARNING: Mismatched devlink_pool_size_thtype_restore"
+	else
+		devlink sb pool set "$DEVLINK_DEV" pool $pool \
+			size ${orig[0]} thtype ${orig[1]}
+	fi
 }
 
 devlink_tc_bind_pool_th()
@@ -185,6 +213,16 @@ devlink_tc_bind_pool_th()
 	    | jq -r '.tc_bind[][] | (.pool, .threshold)'
 }
 
+devlink_tc_bind_pool_th_save()
+{
+	local port=$1; shift
+	local tc=$1; shift
+	local dir=$1; shift
+	local key="tc_bind($port,$dir,$tc).pool_th"
+
+	DEVLINK_ORIG[$key]=$(devlink_tc_bind_pool_th $port $tc $dir)
+}
+
 devlink_tc_bind_pool_th_set()
 {
 	local port=$1; shift
@@ -192,9 +230,7 @@ devlink_tc_bind_pool_th_set()
 	local dir=$1; shift
 	local pool=$1; shift
 	local th=$1; shift
-	local key="tc_bind($port,$dir,$tc).pool_th"
 
-	DEVLINK_ORIG[$key]=$(devlink_tc_bind_pool_th $port $tc $dir)
 	devlink sb tc bind set $port tc $tc type $dir pool $pool th $th
 }
 
@@ -206,8 +242,12 @@ devlink_tc_bind_pool_th_restore()
 	local key="tc_bind($port,$dir,$tc).pool_th"
 	local -a orig=(${DEVLINK_ORIG[$key]})
 
-	devlink sb tc bind set $port tc $tc type $dir \
-		pool ${orig[0]} th ${orig[1]}
+	if [[ -z ${orig[0]} ]]; then
+		echo "WARNING: Mismatched devlink_tc_bind_pool_th_restore"
+	else
+		devlink sb tc bind set $port tc $tc type $dir \
+			pool ${orig[0]} th ${orig[1]}
+	fi
 }
 
 devlink_traps_num_get()
@@ -509,3 +549,9 @@ devlink_cpu_port_get()
 
 	echo "$DEVLINK_DEV/$cpu_dl_port_num"
 }
+
+devlink_cell_size_get()
+{
+	devlink sb pool show "$DEVLINK_DEV" pool 0 -j \
+	    | jq '.pool[][].cell_size'
+}
diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index 977fc2b326a2..927f9ba49e08 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -1227,3 +1227,46 @@ stop_traffic()
 	# Suppress noise from killing mausezahn.
 	{ kill %% && wait %%; } 2>/dev/null
 }
+
+tcpdump_start()
+{
+	local if_name=$1; shift
+	local ns=$1; shift
+
+	capfile=$(mktemp)
+	capout=$(mktemp)
+
+	if [ -z $ns ]; then
+		ns_cmd=""
+	else
+		ns_cmd="ip netns exec ${ns}"
+	fi
+
+	if [ -z $SUDO_USER ] ; then
+		capuser=""
+	else
+		capuser="-Z $SUDO_USER"
+	fi
+
+	$ns_cmd tcpdump -e -n -Q in -i $if_name \
+		-s 65535 -B 32768 $capuser -w $capfile > "$capout" 2>&1 &
+	cappid=$!
+
+	sleep 1
+}
+
+tcpdump_stop()
+{
+	$ns_cmd kill $cappid
+	sleep 1
+}
+
+tcpdump_cleanup()
+{
+	rm $capfile $capout
+}
+
+tcpdump_show()
+{
+	tcpdump -e -n -r $capfile 2>&1
+}
diff --git a/tools/testing/selftests/net/ipsec.c b/tools/testing/selftests/net/ipsec.c
new file mode 100644
index 000000000000..17ced7d6ce25
--- /dev/null
+++ b/tools/testing/selftests/net/ipsec.c
@@ -0,0 +1,2195 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ipsec.c - Check xfrm on veth inside a net-ns.
+ * Copyright (c) 2018 Dmitry Safonov
+ */
+
+#define _GNU_SOURCE
+
+#include <arpa/inet.h>
+#include <asm/types.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <limits.h>
+#include <linux/limits.h>
+#include <linux/netlink.h>
+#include <linux/random.h>
+#include <linux/rtnetlink.h>
+#include <linux/veth.h>
+#include <linux/xfrm.h>
+#include <netinet/in.h>
+#include <net/if.h>
+#include <sched.h>
+#include <stdbool.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/mman.h>
+#include <sys/socket.h>
+#include <sys/stat.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <time.h>
+#include <unistd.h>
+
+#include "../kselftest.h"
+
+#define printk(fmt, ...)						\
+	ksft_print_msg("%d[%u] " fmt "\n", getpid(), __LINE__, ##__VA_ARGS__)
+
+#define pr_err(fmt, ...)	printk(fmt ": %m", ##__VA_ARGS__)
+
+#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]))
+#define BUILD_BUG_ON(condition) ((void)sizeof(char[1 - 2*!!(condition)]))
+
+#define IPV4_STR_SZ	16	/* xxx.xxx.xxx.xxx is longest + \0 */
+#define MAX_PAYLOAD	2048
+#define XFRM_ALGO_KEY_BUF_SIZE	512
+#define MAX_PROCESSES	(1 << 14) /* /16 mask divided by /30 subnets */
+#define INADDR_A	((in_addr_t) 0x0a000000) /* 10.0.0.0 */
+#define INADDR_B	((in_addr_t) 0xc0a80000) /* 192.168.0.0 */
+
+/* /30 mask for one veth connection */
+#define PREFIX_LEN	30
+#define child_ip(nr)	(4*nr + 1)
+#define grchild_ip(nr)	(4*nr + 2)
+
+#define VETH_FMT	"ktst-%d"
+#define VETH_LEN	12
+
+static int nsfd_parent	= -1;
+static int nsfd_childa	= -1;
+static int nsfd_childb	= -1;
+static long page_size;
+
+/*
+ * ksft_cnt is static in kselftest, so isn't shared with children.
+ * We have to send a test result back to parent and count there.
+ * results_fd is a pipe with test feedback from children.
+ */
+static int results_fd[2];
+
+const unsigned int ping_delay_nsec	= 50 * 1000 * 1000;
+const unsigned int ping_timeout		= 300;
+const unsigned int ping_count		= 100;
+const unsigned int ping_success		= 80;
+
+static void randomize_buffer(void *buf, size_t buflen)
+{
+	int *p = (int *)buf;
+	size_t words = buflen / sizeof(int);
+	size_t leftover = buflen % sizeof(int);
+
+	if (!buflen)
+		return;
+
+	while (words--)
+		*p++ = rand();
+
+	if (leftover) {
+		int tmp = rand();
+
+		memcpy(buf + buflen - leftover, &tmp, leftover);
+	}
+
+	return;
+}
+
+static int unshare_open(void)
+{
+	const char *netns_path = "/proc/self/ns/net";
+	int fd;
+
+	if (unshare(CLONE_NEWNET) != 0) {
+		pr_err("unshare()");
+		return -1;
+	}
+
+	fd = open(netns_path, O_RDONLY);
+	if (fd <= 0) {
+		pr_err("open(%s)", netns_path);
+		return -1;
+	}
+
+	return fd;
+}
+
+static int switch_ns(int fd)
+{
+	if (setns(fd, CLONE_NEWNET)) {
+		pr_err("setns()");
+		return -1;
+	}
+	return 0;
+}
+
+/*
+ * Running the test inside a new parent net namespace to bother less
+ * about cleanup on error-path.
+ */
+static int init_namespaces(void)
+{
+	nsfd_parent = unshare_open();
+	if (nsfd_parent <= 0)
+		return -1;
+
+	nsfd_childa = unshare_open();
+	if (nsfd_childa <= 0)
+		return -1;
+
+	if (switch_ns(nsfd_parent))
+		return -1;
+
+	nsfd_childb = unshare_open();
+	if (nsfd_childb <= 0)
+		return -1;
+
+	if (switch_ns(nsfd_parent))
+		return -1;
+	return 0;
+}
+
+static int netlink_sock(int *sock, uint32_t *seq_nr, int proto)
+{
+	if (*sock > 0) {
+		seq_nr++;
+		return 0;
+	}
+
+	*sock = socket(AF_NETLINK, SOCK_RAW | SOCK_CLOEXEC, proto);
+	if (*sock <= 0) {
+		pr_err("socket(AF_NETLINK)");
+		return -1;
+	}
+
+	randomize_buffer(seq_nr, sizeof(*seq_nr));
+
+	return 0;
+}
+
+static inline struct rtattr *rtattr_hdr(struct nlmsghdr *nh)
+{
+	return (struct rtattr *)((char *)(nh) + RTA_ALIGN((nh)->nlmsg_len));
+}
+
+static int rtattr_pack(struct nlmsghdr *nh, size_t req_sz,
+		unsigned short rta_type, const void *payload, size_t size)
+{
+	/* NLMSG_ALIGNTO == RTA_ALIGNTO, nlmsg_len already aligned */
+	struct rtattr *attr = rtattr_hdr(nh);
+	size_t nl_size = RTA_ALIGN(nh->nlmsg_len) + RTA_LENGTH(size);
+
+	if (req_sz < nl_size) {
+		printk("req buf is too small: %zu < %zu", req_sz, nl_size);
+		return -1;
+	}
+	nh->nlmsg_len = nl_size;
+
+	attr->rta_len = RTA_LENGTH(size);
+	attr->rta_type = rta_type;
+	memcpy(RTA_DATA(attr), payload, size);
+
+	return 0;
+}
+
+static struct rtattr *_rtattr_begin(struct nlmsghdr *nh, size_t req_sz,
+		unsigned short rta_type, const void *payload, size_t size)
+{
+	struct rtattr *ret = rtattr_hdr(nh);
+
+	if (rtattr_pack(nh, req_sz, rta_type, payload, size))
+		return 0;
+
+	return ret;
+}
+
+static inline struct rtattr *rtattr_begin(struct nlmsghdr *nh, size_t req_sz,
+		unsigned short rta_type)
+{
+	return _rtattr_begin(nh, req_sz, rta_type, 0, 0);
+}
+
+static inline void rtattr_end(struct nlmsghdr *nh, struct rtattr *attr)
+{
+	char *nlmsg_end = (char *)nh + nh->nlmsg_len;
+
+	attr->rta_len = nlmsg_end - (char *)attr;
+}
+
+static int veth_pack_peerb(struct nlmsghdr *nh, size_t req_sz,
+		const char *peer, int ns)
+{
+	struct ifinfomsg pi;
+	struct rtattr *peer_attr;
+
+	memset(&pi, 0, sizeof(pi));
+	pi.ifi_family	= AF_UNSPEC;
+	pi.ifi_change	= 0xFFFFFFFF;
+
+	peer_attr = _rtattr_begin(nh, req_sz, VETH_INFO_PEER, &pi, sizeof(pi));
+	if (!peer_attr)
+		return -1;
+
+	if (rtattr_pack(nh, req_sz, IFLA_IFNAME, peer, strlen(peer)))
+		return -1;
+
+	if (rtattr_pack(nh, req_sz, IFLA_NET_NS_FD, &ns, sizeof(ns)))
+		return -1;
+
+	rtattr_end(nh, peer_attr);
+
+	return 0;
+}
+
+static int netlink_check_answer(int sock)
+{
+	struct nlmsgerror {
+		struct nlmsghdr hdr;
+		int error;
+		struct nlmsghdr orig_msg;
+	} answer;
+
+	if (recv(sock, &answer, sizeof(answer), 0) < 0) {
+		pr_err("recv()");
+		return -1;
+	} else if (answer.hdr.nlmsg_type != NLMSG_ERROR) {
+		printk("expected NLMSG_ERROR, got %d", (int)answer.hdr.nlmsg_type);
+		return -1;
+	} else if (answer.error) {
+		printk("NLMSG_ERROR: %d: %s",
+			answer.error, strerror(-answer.error));
+		return answer.error;
+	}
+
+	return 0;
+}
+
+static int veth_add(int sock, uint32_t seq, const char *peera, int ns_a,
+		const char *peerb, int ns_b)
+{
+	uint16_t flags = NLM_F_REQUEST | NLM_F_ACK | NLM_F_EXCL | NLM_F_CREATE;
+	struct {
+		struct nlmsghdr		nh;
+		struct ifinfomsg	info;
+		char			attrbuf[MAX_PAYLOAD];
+	} req;
+	const char veth_type[] = "veth";
+	struct rtattr *link_info, *info_data;
+
+	memset(&req, 0, sizeof(req));
+	req.nh.nlmsg_len	= NLMSG_LENGTH(sizeof(req.info));
+	req.nh.nlmsg_type	= RTM_NEWLINK;
+	req.nh.nlmsg_flags	= flags;
+	req.nh.nlmsg_seq	= seq;
+	req.info.ifi_family	= AF_UNSPEC;
+	req.info.ifi_change	= 0xFFFFFFFF;
+
+	if (rtattr_pack(&req.nh, sizeof(req), IFLA_IFNAME, peera, strlen(peera)))
+		return -1;
+
+	if (rtattr_pack(&req.nh, sizeof(req), IFLA_NET_NS_FD, &ns_a, sizeof(ns_a)))
+		return -1;
+
+	link_info = rtattr_begin(&req.nh, sizeof(req), IFLA_LINKINFO);
+	if (!link_info)
+		return -1;
+
+	if (rtattr_pack(&req.nh, sizeof(req), IFLA_INFO_KIND, veth_type, sizeof(veth_type)))
+		return -1;
+
+	info_data = rtattr_begin(&req.nh, sizeof(req), IFLA_INFO_DATA);
+	if (!info_data)
+		return -1;
+
+	if (veth_pack_peerb(&req.nh, sizeof(req), peerb, ns_b))
+		return -1;
+
+	rtattr_end(&req.nh, info_data);
+	rtattr_end(&req.nh, link_info);
+
+	if (send(sock, &req, req.nh.nlmsg_len, 0) < 0) {
+		pr_err("send()");
+		return -1;
+	}
+	return netlink_check_answer(sock);
+}
+
+static int ip4_addr_set(int sock, uint32_t seq, const char *intf,
+		struct in_addr addr, uint8_t prefix)
+{
+	uint16_t flags = NLM_F_REQUEST | NLM_F_ACK | NLM_F_EXCL | NLM_F_CREATE;
+	struct {
+		struct nlmsghdr		nh;
+		struct ifaddrmsg	info;
+		char			attrbuf[MAX_PAYLOAD];
+	} req;
+
+	memset(&req, 0, sizeof(req));
+	req.nh.nlmsg_len	= NLMSG_LENGTH(sizeof(req.info));
+	req.nh.nlmsg_type	= RTM_NEWADDR;
+	req.nh.nlmsg_flags	= flags;
+	req.nh.nlmsg_seq	= seq;
+	req.info.ifa_family	= AF_INET;
+	req.info.ifa_prefixlen	= prefix;
+	req.info.ifa_index	= if_nametoindex(intf);
+
+#ifdef DEBUG
+	{
+		char addr_str[IPV4_STR_SZ] = {};
+
+		strncpy(addr_str, inet_ntoa(addr), IPV4_STR_SZ - 1);
+
+		printk("ip addr set %s", addr_str);
+	}
+#endif
+
+	if (rtattr_pack(&req.nh, sizeof(req), IFA_LOCAL, &addr, sizeof(addr)))
+		return -1;
+
+	if (rtattr_pack(&req.nh, sizeof(req), IFA_ADDRESS, &addr, sizeof(addr)))
+		return -1;
+
+	if (send(sock, &req, req.nh.nlmsg_len, 0) < 0) {
+		pr_err("send()");
+		return -1;
+	}
+	return netlink_check_answer(sock);
+}
+
+static int link_set_up(int sock, uint32_t seq, const char *intf)
+{
+	struct {
+		struct nlmsghdr		nh;
+		struct ifinfomsg	info;
+		char			attrbuf[MAX_PAYLOAD];
+	} req;
+
+	memset(&req, 0, sizeof(req));
+	req.nh.nlmsg_len	= NLMSG_LENGTH(sizeof(req.info));
+	req.nh.nlmsg_type	= RTM_NEWLINK;
+	req.nh.nlmsg_flags	= NLM_F_REQUEST | NLM_F_ACK;
+	req.nh.nlmsg_seq	= seq;
+	req.info.ifi_family	= AF_UNSPEC;
+	req.info.ifi_change	= 0xFFFFFFFF;
+	req.info.ifi_index	= if_nametoindex(intf);
+	req.info.ifi_flags	= IFF_UP;
+	req.info.ifi_change	= IFF_UP;
+
+	if (send(sock, &req, req.nh.nlmsg_len, 0) < 0) {
+		pr_err("send()");
+		return -1;
+	}
+	return netlink_check_answer(sock);
+}
+
+static int ip4_route_set(int sock, uint32_t seq, const char *intf,
+		struct in_addr src, struct in_addr dst)
+{
+	struct {
+		struct nlmsghdr	nh;
+		struct rtmsg	rt;
+		char		attrbuf[MAX_PAYLOAD];
+	} req;
+	unsigned int index = if_nametoindex(intf);
+
+	memset(&req, 0, sizeof(req));
+	req.nh.nlmsg_len	= NLMSG_LENGTH(sizeof(req.rt));
+	req.nh.nlmsg_type	= RTM_NEWROUTE;
+	req.nh.nlmsg_flags	= NLM_F_REQUEST | NLM_F_ACK | NLM_F_CREATE;
+	req.nh.nlmsg_seq	= seq;
+	req.rt.rtm_family	= AF_INET;
+	req.rt.rtm_dst_len	= 32;
+	req.rt.rtm_table	= RT_TABLE_MAIN;
+	req.rt.rtm_protocol	= RTPROT_BOOT;
+	req.rt.rtm_scope	= RT_SCOPE_LINK;
+	req.rt.rtm_type		= RTN_UNICAST;
+
+	if (rtattr_pack(&req.nh, sizeof(req), RTA_DST, &dst, sizeof(dst)))
+		return -1;
+
+	if (rtattr_pack(&req.nh, sizeof(req), RTA_PREFSRC, &src, sizeof(src)))
+		return -1;
+
+	if (rtattr_pack(&req.nh, sizeof(req), RTA_OIF, &index, sizeof(index)))
+		return -1;
+
+	if (send(sock, &req, req.nh.nlmsg_len, 0) < 0) {
+		pr_err("send()");
+		return -1;
+	}
+
+	return netlink_check_answer(sock);
+}
+
+static int tunnel_set_route(int route_sock, uint32_t *route_seq, char *veth,
+		struct in_addr tunsrc, struct in_addr tundst)
+{
+	if (ip4_addr_set(route_sock, (*route_seq)++, "lo",
+			tunsrc, PREFIX_LEN)) {
+		printk("Failed to set ipv4 addr");
+		return -1;
+	}
+
+	if (ip4_route_set(route_sock, (*route_seq)++, veth, tunsrc, tundst)) {
+		printk("Failed to set ipv4 route");
+		return -1;
+	}
+
+	return 0;
+}
+
+static int init_child(int nsfd, char *veth, unsigned int src, unsigned int dst)
+{
+	struct in_addr intsrc = inet_makeaddr(INADDR_B, src);
+	struct in_addr tunsrc = inet_makeaddr(INADDR_A, src);
+	struct in_addr tundst = inet_makeaddr(INADDR_A, dst);
+	int route_sock = -1, ret = -1;
+	uint32_t route_seq;
+
+	if (switch_ns(nsfd))
+		return -1;
+
+	if (netlink_sock(&route_sock, &route_seq, NETLINK_ROUTE)) {
+		printk("Failed to open netlink route socket in child");
+		return -1;
+	}
+
+	if (ip4_addr_set(route_sock, route_seq++, veth, intsrc, PREFIX_LEN)) {
+		printk("Failed to set ipv4 addr");
+		goto err;
+	}
+
+	if (link_set_up(route_sock, route_seq++, veth)) {
+		printk("Failed to bring up %s", veth);
+		goto err;
+	}
+
+	if (tunnel_set_route(route_sock, &route_seq, veth, tunsrc, tundst)) {
+		printk("Failed to add tunnel route on %s", veth);
+		goto err;
+	}
+	ret = 0;
+
+err:
+	close(route_sock);
+	return ret;
+}
+
+#define ALGO_LEN	64
+enum desc_type {
+	CREATE_TUNNEL	= 0,
+	ALLOCATE_SPI,
+	MONITOR_ACQUIRE,
+	EXPIRE_STATE,
+	EXPIRE_POLICY,
+};
+const char *desc_name[] = {
+	"create tunnel",
+	"alloc spi",
+	"monitor acquire",
+	"expire state",
+	"expire policy"
+};
+struct xfrm_desc {
+	enum desc_type	type;
+	uint8_t		proto;
+	char		a_algo[ALGO_LEN];
+	char		e_algo[ALGO_LEN];
+	char		c_algo[ALGO_LEN];
+	char		ae_algo[ALGO_LEN];
+	unsigned int	icv_len;
+	/* unsigned key_len; */
+};
+
+enum msg_type {
+	MSG_ACK		= 0,
+	MSG_EXIT,
+	MSG_PING,
+	MSG_XFRM_PREPARE,
+	MSG_XFRM_ADD,
+	MSG_XFRM_DEL,
+	MSG_XFRM_CLEANUP,
+};
+
+struct test_desc {
+	enum msg_type type;
+	union {
+		struct {
+			in_addr_t reply_ip;
+			unsigned int port;
+		} ping;
+		struct xfrm_desc xfrm_desc;
+	} body;
+};
+
+struct test_result {
+	struct xfrm_desc desc;
+	unsigned int res;
+};
+
+static void write_test_result(unsigned int res, struct xfrm_desc *d)
+{
+	struct test_result tr = {};
+	ssize_t ret;
+
+	tr.desc = *d;
+	tr.res = res;
+
+	ret = write(results_fd[1], &tr, sizeof(tr));
+	if (ret != sizeof(tr))
+		pr_err("Failed to write the result in pipe %zd", ret);
+}
+
+static void write_msg(int fd, struct test_desc *msg, bool exit_of_fail)
+{
+	ssize_t bytes = write(fd, msg, sizeof(*msg));
+
+	/* Make sure that write/read is atomic to a pipe */
+	BUILD_BUG_ON(sizeof(struct test_desc) > PIPE_BUF);
+
+	if (bytes < 0) {
+		pr_err("write()");
+		if (exit_of_fail)
+			exit(KSFT_FAIL);
+	}
+	if (bytes != sizeof(*msg)) {
+		pr_err("sent part of the message %zd/%zu", bytes, sizeof(*msg));
+		if (exit_of_fail)
+			exit(KSFT_FAIL);
+	}
+}
+
+static void read_msg(int fd, struct test_desc *msg, bool exit_of_fail)
+{
+	ssize_t bytes = read(fd, msg, sizeof(*msg));
+
+	if (bytes < 0) {
+		pr_err("read()");
+		if (exit_of_fail)
+			exit(KSFT_FAIL);
+	}
+	if (bytes != sizeof(*msg)) {
+		pr_err("got incomplete message %zd/%zu", bytes, sizeof(*msg));
+		if (exit_of_fail)
+			exit(KSFT_FAIL);
+	}
+}
+
+static int udp_ping_init(struct in_addr listen_ip, unsigned int u_timeout,
+		unsigned int *server_port, int sock[2])
+{
+	struct sockaddr_in server;
+	struct timeval t = { .tv_sec = 0, .tv_usec = u_timeout };
+	socklen_t s_len = sizeof(server);
+
+	sock[0] = socket(AF_INET, SOCK_DGRAM, 0);
+	if (sock[0] < 0) {
+		pr_err("socket()");
+		return -1;
+	}
+
+	server.sin_family	= AF_INET;
+	server.sin_port		= 0;
+	memcpy(&server.sin_addr.s_addr, &listen_ip, sizeof(struct in_addr));
+
+	if (bind(sock[0], (struct sockaddr *)&server, s_len)) {
+		pr_err("bind()");
+		goto err_close_server;
+	}
+
+	if (getsockname(sock[0], (struct sockaddr *)&server, &s_len)) {
+		pr_err("getsockname()");
+		goto err_close_server;
+	}
+
+	*server_port = ntohs(server.sin_port);
+
+	if (setsockopt(sock[0], SOL_SOCKET, SO_RCVTIMEO, (const char *)&t, sizeof t)) {
+		pr_err("setsockopt()");
+		goto err_close_server;
+	}
+
+	sock[1] = socket(AF_INET, SOCK_DGRAM, 0);
+	if (sock[1] < 0) {
+		pr_err("socket()");
+		goto err_close_server;
+	}
+
+	return 0;
+
+err_close_server:
+	close(sock[0]);
+	return -1;
+}
+
+static int udp_ping_send(int sock[2], in_addr_t dest_ip, unsigned int port,
+		char *buf, size_t buf_len)
+{
+	struct sockaddr_in server;
+	const struct sockaddr *dest_addr = (struct sockaddr *)&server;
+	char *sock_buf[buf_len];
+	ssize_t r_bytes, s_bytes;
+
+	server.sin_family	= AF_INET;
+	server.sin_port		= htons(port);
+	server.sin_addr.s_addr	= dest_ip;
+
+	s_bytes = sendto(sock[1], buf, buf_len, 0, dest_addr, sizeof(server));
+	if (s_bytes < 0) {
+		pr_err("sendto()");
+		return -1;
+	} else if (s_bytes != buf_len) {
+		printk("send part of the message: %zd/%zu", s_bytes, sizeof(server));
+		return -1;
+	}
+
+	r_bytes = recv(sock[0], sock_buf, buf_len, 0);
+	if (r_bytes < 0) {
+		if (errno != EAGAIN)
+			pr_err("recv()");
+		return -1;
+	} else if (r_bytes == 0) { /* EOF */
+		printk("EOF on reply to ping");
+		return -1;
+	} else if (r_bytes != buf_len || memcmp(buf, sock_buf, buf_len)) {
+		printk("ping reply packet is corrupted %zd/%zu", r_bytes, buf_len);
+		return -1;
+	}
+
+	return 0;
+}
+
+static int udp_ping_reply(int sock[2], in_addr_t dest_ip, unsigned int port,
+		char *buf, size_t buf_len)
+{
+	struct sockaddr_in server;
+	const struct sockaddr *dest_addr = (struct sockaddr *)&server;
+	char *sock_buf[buf_len];
+	ssize_t r_bytes, s_bytes;
+
+	server.sin_family	= AF_INET;
+	server.sin_port		= htons(port);
+	server.sin_addr.s_addr	= dest_ip;
+
+	r_bytes = recv(sock[0], sock_buf, buf_len, 0);
+	if (r_bytes < 0) {
+		if (errno != EAGAIN)
+			pr_err("recv()");
+		return -1;
+	}
+	if (r_bytes == 0) { /* EOF */
+		printk("EOF on reply to ping");
+		return -1;
+	}
+	if (r_bytes != buf_len || memcmp(buf, sock_buf, buf_len)) {
+		printk("ping reply packet is corrupted %zd/%zu", r_bytes, buf_len);
+		return -1;
+	}
+
+	s_bytes = sendto(sock[1], buf, buf_len, 0, dest_addr, sizeof(server));
+	if (s_bytes < 0) {
+		pr_err("sendto()");
+		return -1;
+	} else if (s_bytes != buf_len) {
+		printk("send part of the message: %zd/%zu", s_bytes, sizeof(server));
+		return -1;
+	}
+
+	return 0;
+}
+
+typedef int (*ping_f)(int sock[2], in_addr_t dest_ip, unsigned int port,
+		char *buf, size_t buf_len);
+static int do_ping(int cmd_fd, char *buf, size_t buf_len, struct in_addr from,
+		bool init_side, int d_port, in_addr_t to, ping_f func)
+{
+	struct test_desc msg;
+	unsigned int s_port, i, ping_succeeded = 0;
+	int ping_sock[2];
+	char to_str[IPV4_STR_SZ] = {}, from_str[IPV4_STR_SZ] = {};
+
+	if (udp_ping_init(from, ping_timeout, &s_port, ping_sock)) {
+		printk("Failed to init ping");
+		return -1;
+	}
+
+	memset(&msg, 0, sizeof(msg));
+	msg.type		= MSG_PING;
+	msg.body.ping.port	= s_port;
+	memcpy(&msg.body.ping.reply_ip, &from, sizeof(from));
+
+	write_msg(cmd_fd, &msg, 0);
+	if (init_side) {
+		/* The other end sends ip to ping */
+		read_msg(cmd_fd, &msg, 0);
+		if (msg.type != MSG_PING)
+			return -1;
+		to = msg.body.ping.reply_ip;
+		d_port = msg.body.ping.port;
+	}
+
+	for (i = 0; i < ping_count ; i++) {
+		struct timespec sleep_time = {
+			.tv_sec = 0,
+			.tv_nsec = ping_delay_nsec,
+		};
+
+		ping_succeeded += !func(ping_sock, to, d_port, buf, page_size);
+		nanosleep(&sleep_time, 0);
+	}
+
+	close(ping_sock[0]);
+	close(ping_sock[1]);
+
+	strncpy(to_str, inet_ntoa(*(struct in_addr *)&to), IPV4_STR_SZ - 1);
+	strncpy(from_str, inet_ntoa(from), IPV4_STR_SZ - 1);
+
+	if (ping_succeeded < ping_success) {
+		printk("ping (%s) %s->%s failed %u/%u times",
+			init_side ? "send" : "reply", from_str, to_str,
+			ping_count - ping_succeeded, ping_count);
+		return -1;
+	}
+
+#ifdef DEBUG
+	printk("ping (%s) %s->%s succeeded %u/%u times",
+		init_side ? "send" : "reply", from_str, to_str,
+		ping_succeeded, ping_count);
+#endif
+
+	return 0;
+}
+
+static int xfrm_fill_key(char *name, char *buf,
+		size_t buf_len, unsigned int *key_len)
+{
+	/* TODO: use set/map instead */
+	if (strncmp(name, "digest_null", ALGO_LEN) == 0)
+		*key_len = 0;
+	else if (strncmp(name, "ecb(cipher_null)", ALGO_LEN) == 0)
+		*key_len = 0;
+	else if (strncmp(name, "cbc(des)", ALGO_LEN) == 0)
+		*key_len = 64;
+	else if (strncmp(name, "hmac(md5)", ALGO_LEN) == 0)
+		*key_len = 128;
+	else if (strncmp(name, "cmac(aes)", ALGO_LEN) == 0)
+		*key_len = 128;
+	else if (strncmp(name, "xcbc(aes)", ALGO_LEN) == 0)
+		*key_len = 128;
+	else if (strncmp(name, "cbc(cast5)", ALGO_LEN) == 0)
+		*key_len = 128;
+	else if (strncmp(name, "cbc(serpent)", ALGO_LEN) == 0)
+		*key_len = 128;
+	else if (strncmp(name, "hmac(sha1)", ALGO_LEN) == 0)
+		*key_len = 160;
+	else if (strncmp(name, "hmac(rmd160)", ALGO_LEN) == 0)
+		*key_len = 160;
+	else if (strncmp(name, "cbc(des3_ede)", ALGO_LEN) == 0)
+		*key_len = 192;
+	else if (strncmp(name, "hmac(sha256)", ALGO_LEN) == 0)
+		*key_len = 256;
+	else if (strncmp(name, "cbc(aes)", ALGO_LEN) == 0)
+		*key_len = 256;
+	else if (strncmp(name, "cbc(camellia)", ALGO_LEN) == 0)
+		*key_len = 256;
+	else if (strncmp(name, "cbc(twofish)", ALGO_LEN) == 0)
+		*key_len = 256;
+	else if (strncmp(name, "rfc3686(ctr(aes))", ALGO_LEN) == 0)
+		*key_len = 288;
+	else if (strncmp(name, "hmac(sha384)", ALGO_LEN) == 0)
+		*key_len = 384;
+	else if (strncmp(name, "cbc(blowfish)", ALGO_LEN) == 0)
+		*key_len = 448;
+	else if (strncmp(name, "hmac(sha512)", ALGO_LEN) == 0)
+		*key_len = 512;
+	else if (strncmp(name, "rfc4106(gcm(aes))-128", ALGO_LEN) == 0)
+		*key_len = 160;
+	else if (strncmp(name, "rfc4543(gcm(aes))-128", ALGO_LEN) == 0)
+		*key_len = 160;
+	else if (strncmp(name, "rfc4309(ccm(aes))-128", ALGO_LEN) == 0)
+		*key_len = 152;
+	else if (strncmp(name, "rfc4106(gcm(aes))-192", ALGO_LEN) == 0)
+		*key_len = 224;
+	else if (strncmp(name, "rfc4543(gcm(aes))-192", ALGO_LEN) == 0)
+		*key_len = 224;
+	else if (strncmp(name, "rfc4309(ccm(aes))-192", ALGO_LEN) == 0)
+		*key_len = 216;
+	else if (strncmp(name, "rfc4106(gcm(aes))-256", ALGO_LEN) == 0)
+		*key_len = 288;
+	else if (strncmp(name, "rfc4543(gcm(aes))-256", ALGO_LEN) == 0)
+		*key_len = 288;
+	else if (strncmp(name, "rfc4309(ccm(aes))-256", ALGO_LEN) == 0)
+		*key_len = 280;
+	else if (strncmp(name, "rfc7539(chacha20,poly1305)-128", ALGO_LEN) == 0)
+		*key_len = 0;
+
+	if (*key_len > buf_len) {
+		printk("Can't pack a key - too big for buffer");
+		return -1;
+	}
+
+	randomize_buffer(buf, *key_len);
+
+	return 0;
+}
+
+static int xfrm_state_pack_algo(struct nlmsghdr *nh, size_t req_sz,
+		struct xfrm_desc *desc)
+{
+	struct {
+		union {
+			struct xfrm_algo	alg;
+			struct xfrm_algo_aead	aead;
+			struct xfrm_algo_auth	auth;
+		} u;
+		char buf[XFRM_ALGO_KEY_BUF_SIZE];
+	} alg = {};
+	size_t alen, elen, clen, aelen;
+	unsigned short type;
+
+	alen = strlen(desc->a_algo);
+	elen = strlen(desc->e_algo);
+	clen = strlen(desc->c_algo);
+	aelen = strlen(desc->ae_algo);
+
+	/* Verify desc */
+	switch (desc->proto) {
+	case IPPROTO_AH:
+		if (!alen || elen || clen || aelen) {
+			printk("BUG: buggy ah desc");
+			return -1;
+		}
+		strncpy(alg.u.alg.alg_name, desc->a_algo, ALGO_LEN - 1);
+		if (xfrm_fill_key(desc->a_algo, alg.u.alg.alg_key,
+				sizeof(alg.buf), &alg.u.alg.alg_key_len))
+			return -1;
+		type = XFRMA_ALG_AUTH;
+		break;
+	case IPPROTO_COMP:
+		if (!clen || elen || alen || aelen) {
+			printk("BUG: buggy comp desc");
+			return -1;
+		}
+		strncpy(alg.u.alg.alg_name, desc->c_algo, ALGO_LEN - 1);
+		if (xfrm_fill_key(desc->c_algo, alg.u.alg.alg_key,
+				sizeof(alg.buf), &alg.u.alg.alg_key_len))
+			return -1;
+		type = XFRMA_ALG_COMP;
+		break;
+	case IPPROTO_ESP:
+		if (!((alen && elen) ^ aelen) || clen) {
+			printk("BUG: buggy esp desc");
+			return -1;
+		}
+		if (aelen) {
+			alg.u.aead.alg_icv_len = desc->icv_len;
+			strncpy(alg.u.aead.alg_name, desc->ae_algo, ALGO_LEN - 1);
+			if (xfrm_fill_key(desc->ae_algo, alg.u.aead.alg_key,
+						sizeof(alg.buf), &alg.u.aead.alg_key_len))
+				return -1;
+			type = XFRMA_ALG_AEAD;
+		} else {
+
+			strncpy(alg.u.alg.alg_name, desc->e_algo, ALGO_LEN - 1);
+			type = XFRMA_ALG_CRYPT;
+			if (xfrm_fill_key(desc->e_algo, alg.u.alg.alg_key,
+						sizeof(alg.buf), &alg.u.alg.alg_key_len))
+				return -1;
+			if (rtattr_pack(nh, req_sz, type, &alg, sizeof(alg)))
+				return -1;
+
+			strncpy(alg.u.alg.alg_name, desc->a_algo, ALGO_LEN);
+			type = XFRMA_ALG_AUTH;
+			if (xfrm_fill_key(desc->a_algo, alg.u.alg.alg_key,
+						sizeof(alg.buf), &alg.u.alg.alg_key_len))
+				return -1;
+		}
+		break;
+	default:
+		printk("BUG: unknown proto in desc");
+		return -1;
+	}
+
+	if (rtattr_pack(nh, req_sz, type, &alg, sizeof(alg)))
+		return -1;
+
+	return 0;
+}
+
+static inline uint32_t gen_spi(struct in_addr src)
+{
+	return htonl(inet_lnaof(src));
+}
+
+static int xfrm_state_add(int xfrm_sock, uint32_t seq, uint32_t spi,
+		struct in_addr src, struct in_addr dst,
+		struct xfrm_desc *desc)
+{
+	struct {
+		struct nlmsghdr		nh;
+		struct xfrm_usersa_info	info;
+		char			attrbuf[MAX_PAYLOAD];
+	} req;
+
+	memset(&req, 0, sizeof(req));
+	req.nh.nlmsg_len	= NLMSG_LENGTH(sizeof(req.info));
+	req.nh.nlmsg_type	= XFRM_MSG_NEWSA;
+	req.nh.nlmsg_flags	= NLM_F_REQUEST | NLM_F_ACK;
+	req.nh.nlmsg_seq	= seq;
+
+	/* Fill selector. */
+	memcpy(&req.info.sel.daddr, &dst, sizeof(dst));
+	memcpy(&req.info.sel.saddr, &src, sizeof(src));
+	req.info.sel.family		= AF_INET;
+	req.info.sel.prefixlen_d	= PREFIX_LEN;
+	req.info.sel.prefixlen_s	= PREFIX_LEN;
+
+	/* Fill id */
+	memcpy(&req.info.id.daddr, &dst, sizeof(dst));
+	/* Note: zero-spi cannot be deleted */
+	req.info.id.spi = spi;
+	req.info.id.proto	= desc->proto;
+
+	memcpy(&req.info.saddr, &src, sizeof(src));
+
+	/* Fill lifteme_cfg */
+	req.info.lft.soft_byte_limit	= XFRM_INF;
+	req.info.lft.hard_byte_limit	= XFRM_INF;
+	req.info.lft.soft_packet_limit	= XFRM_INF;
+	req.info.lft.hard_packet_limit	= XFRM_INF;
+
+	req.info.family		= AF_INET;
+	req.info.mode		= XFRM_MODE_TUNNEL;
+
+	if (xfrm_state_pack_algo(&req.nh, sizeof(req), desc))
+		return -1;
+
+	if (send(xfrm_sock, &req, req.nh.nlmsg_len, 0) < 0) {
+		pr_err("send()");
+		return -1;
+	}
+
+	return netlink_check_answer(xfrm_sock);
+}
+
+static bool xfrm_usersa_found(struct xfrm_usersa_info *info, uint32_t spi,
+		struct in_addr src, struct in_addr dst,
+		struct xfrm_desc *desc)
+{
+	if (memcmp(&info->sel.daddr, &dst, sizeof(dst)))
+		return false;
+
+	if (memcmp(&info->sel.saddr, &src, sizeof(src)))
+		return false;
+
+	if (info->sel.family != AF_INET					||
+			info->sel.prefixlen_d != PREFIX_LEN		||
+			info->sel.prefixlen_s != PREFIX_LEN)
+		return false;
+
+	if (info->id.spi != spi || info->id.proto != desc->proto)
+		return false;
+
+	if (memcmp(&info->id.daddr, &dst, sizeof(dst)))
+		return false;
+
+	if (memcmp(&info->saddr, &src, sizeof(src)))
+		return false;
+
+	if (info->lft.soft_byte_limit != XFRM_INF			||
+			info->lft.hard_byte_limit != XFRM_INF		||
+			info->lft.soft_packet_limit != XFRM_INF		||
+			info->lft.hard_packet_limit != XFRM_INF)
+		return false;
+
+	if (info->family != AF_INET || info->mode != XFRM_MODE_TUNNEL)
+		return false;
+
+	/* XXX: check xfrm algo, see xfrm_state_pack_algo(). */
+
+	return true;
+}
+
+static int xfrm_state_check(int xfrm_sock, uint32_t seq, uint32_t spi,
+		struct in_addr src, struct in_addr dst,
+		struct xfrm_desc *desc)
+{
+	struct {
+		struct nlmsghdr		nh;
+		char			attrbuf[MAX_PAYLOAD];
+	} req;
+	struct {
+		struct nlmsghdr		nh;
+		union {
+			struct xfrm_usersa_info	info;
+			int error;
+		};
+		char			attrbuf[MAX_PAYLOAD];
+	} answer;
+	struct xfrm_address_filter filter = {};
+	bool found = false;
+
+
+	memset(&req, 0, sizeof(req));
+	req.nh.nlmsg_len	= NLMSG_LENGTH(0);
+	req.nh.nlmsg_type	= XFRM_MSG_GETSA;
+	req.nh.nlmsg_flags	= NLM_F_REQUEST | NLM_F_DUMP;
+	req.nh.nlmsg_seq	= seq;
+
+	/*
+	 * Add dump filter by source address as there may be other tunnels
+	 * in this netns (if tests run in parallel).
+	 */
+	filter.family = AF_INET;
+	filter.splen = 0x1f;	/* 0xffffffff mask see addr_match() */
+	memcpy(&filter.saddr, &src, sizeof(src));
+	if (rtattr_pack(&req.nh, sizeof(req), XFRMA_ADDRESS_FILTER,
+				&filter, sizeof(filter)))
+		return -1;
+
+	if (send(xfrm_sock, &req, req.nh.nlmsg_len, 0) < 0) {
+		pr_err("send()");
+		return -1;
+	}
+
+	while (1) {
+		if (recv(xfrm_sock, &answer, sizeof(answer), 0) < 0) {
+			pr_err("recv()");
+			return -1;
+		}
+		if (answer.nh.nlmsg_type == NLMSG_ERROR) {
+			printk("NLMSG_ERROR: %d: %s",
+				answer.error, strerror(-answer.error));
+			return -1;
+		} else if (answer.nh.nlmsg_type == NLMSG_DONE) {
+			if (found)
+				return 0;
+			printk("didn't find allocated xfrm state in dump");
+			return -1;
+		} else if (answer.nh.nlmsg_type == XFRM_MSG_NEWSA) {
+			if (xfrm_usersa_found(&answer.info, spi, src, dst, desc))
+				found = true;
+		}
+	}
+}
+
+static int xfrm_set(int xfrm_sock, uint32_t *seq,
+		struct in_addr src, struct in_addr dst,
+		struct in_addr tunsrc, struct in_addr tundst,
+		struct xfrm_desc *desc)
+{
+	int err;
+
+	err = xfrm_state_add(xfrm_sock, (*seq)++, gen_spi(src), src, dst, desc);
+	if (err) {
+		printk("Failed to add xfrm state");
+		return -1;
+	}
+
+	err = xfrm_state_add(xfrm_sock, (*seq)++, gen_spi(src), dst, src, desc);
+	if (err) {
+		printk("Failed to add xfrm state");
+		return -1;
+	}
+
+	/* Check dumps for XFRM_MSG_GETSA */
+	err = xfrm_state_check(xfrm_sock, (*seq)++, gen_spi(src), src, dst, desc);
+	err |= xfrm_state_check(xfrm_sock, (*seq)++, gen_spi(src), dst, src, desc);
+	if (err) {
+		printk("Failed to check xfrm state");
+		return -1;
+	}
+
+	return 0;
+}
+
+static int xfrm_policy_add(int xfrm_sock, uint32_t seq, uint32_t spi,
+		struct in_addr src, struct in_addr dst, uint8_t dir,
+		struct in_addr tunsrc, struct in_addr tundst, uint8_t proto)
+{
+	struct {
+		struct nlmsghdr			nh;
+		struct xfrm_userpolicy_info	info;
+		char				attrbuf[MAX_PAYLOAD];
+	} req;
+	struct xfrm_user_tmpl tmpl;
+
+	memset(&req, 0, sizeof(req));
+	memset(&tmpl, 0, sizeof(tmpl));
+	req.nh.nlmsg_len	= NLMSG_LENGTH(sizeof(req.info));
+	req.nh.nlmsg_type	= XFRM_MSG_NEWPOLICY;
+	req.nh.nlmsg_flags	= NLM_F_REQUEST | NLM_F_ACK;
+	req.nh.nlmsg_seq	= seq;
+
+	/* Fill selector. */
+	memcpy(&req.info.sel.daddr, &dst, sizeof(tundst));
+	memcpy(&req.info.sel.saddr, &src, sizeof(tunsrc));
+	req.info.sel.family		= AF_INET;
+	req.info.sel.prefixlen_d	= PREFIX_LEN;
+	req.info.sel.prefixlen_s	= PREFIX_LEN;
+
+	/* Fill lifteme_cfg */
+	req.info.lft.soft_byte_limit	= XFRM_INF;
+	req.info.lft.hard_byte_limit	= XFRM_INF;
+	req.info.lft.soft_packet_limit	= XFRM_INF;
+	req.info.lft.hard_packet_limit	= XFRM_INF;
+
+	req.info.dir = dir;
+
+	/* Fill tmpl */
+	memcpy(&tmpl.id.daddr, &dst, sizeof(dst));
+	/* Note: zero-spi cannot be deleted */
+	tmpl.id.spi = spi;
+	tmpl.id.proto	= proto;
+	tmpl.family	= AF_INET;
+	memcpy(&tmpl.saddr, &src, sizeof(src));
+	tmpl.mode	= XFRM_MODE_TUNNEL;
+	tmpl.aalgos = (~(uint32_t)0);
+	tmpl.ealgos = (~(uint32_t)0);
+	tmpl.calgos = (~(uint32_t)0);
+
+	if (rtattr_pack(&req.nh, sizeof(req), XFRMA_TMPL, &tmpl, sizeof(tmpl)))
+		return -1;
+
+	if (send(xfrm_sock, &req, req.nh.nlmsg_len, 0) < 0) {
+		pr_err("send()");
+		return -1;
+	}
+
+	return netlink_check_answer(xfrm_sock);
+}
+
+static int xfrm_prepare(int xfrm_sock, uint32_t *seq,
+		struct in_addr src, struct in_addr dst,
+		struct in_addr tunsrc, struct in_addr tundst, uint8_t proto)
+{
+	if (xfrm_policy_add(xfrm_sock, (*seq)++, gen_spi(src), src, dst,
+				XFRM_POLICY_OUT, tunsrc, tundst, proto)) {
+		printk("Failed to add xfrm policy");
+		return -1;
+	}
+
+	if (xfrm_policy_add(xfrm_sock, (*seq)++, gen_spi(src), dst, src,
+				XFRM_POLICY_IN, tunsrc, tundst, proto)) {
+		printk("Failed to add xfrm policy");
+		return -1;
+	}
+
+	return 0;
+}
+
+static int xfrm_policy_del(int xfrm_sock, uint32_t seq,
+		struct in_addr src, struct in_addr dst, uint8_t dir,
+		struct in_addr tunsrc, struct in_addr tundst)
+{
+	struct {
+		struct nlmsghdr			nh;
+		struct xfrm_userpolicy_id	id;
+		char				attrbuf[MAX_PAYLOAD];
+	} req;
+
+	memset(&req, 0, sizeof(req));
+	req.nh.nlmsg_len	= NLMSG_LENGTH(sizeof(req.id));
+	req.nh.nlmsg_type	= XFRM_MSG_DELPOLICY;
+	req.nh.nlmsg_flags	= NLM_F_REQUEST | NLM_F_ACK;
+	req.nh.nlmsg_seq	= seq;
+
+	/* Fill id */
+	memcpy(&req.id.sel.daddr, &dst, sizeof(tundst));
+	memcpy(&req.id.sel.saddr, &src, sizeof(tunsrc));
+	req.id.sel.family		= AF_INET;
+	req.id.sel.prefixlen_d		= PREFIX_LEN;
+	req.id.sel.prefixlen_s		= PREFIX_LEN;
+	req.id.dir = dir;
+
+	if (send(xfrm_sock, &req, req.nh.nlmsg_len, 0) < 0) {
+		pr_err("send()");
+		return -1;
+	}
+
+	return netlink_check_answer(xfrm_sock);
+}
+
+static int xfrm_cleanup(int xfrm_sock, uint32_t *seq,
+		struct in_addr src, struct in_addr dst,
+		struct in_addr tunsrc, struct in_addr tundst)
+{
+	if (xfrm_policy_del(xfrm_sock, (*seq)++, src, dst,
+				XFRM_POLICY_OUT, tunsrc, tundst)) {
+		printk("Failed to add xfrm policy");
+		return -1;
+	}
+
+	if (xfrm_policy_del(xfrm_sock, (*seq)++, dst, src,
+				XFRM_POLICY_IN, tunsrc, tundst)) {
+		printk("Failed to add xfrm policy");
+		return -1;
+	}
+
+	return 0;
+}
+
+static int xfrm_state_del(int xfrm_sock, uint32_t seq, uint32_t spi,
+		struct in_addr src, struct in_addr dst, uint8_t proto)
+{
+	struct {
+		struct nlmsghdr		nh;
+		struct xfrm_usersa_id	id;
+		char			attrbuf[MAX_PAYLOAD];
+	} req;
+	xfrm_address_t saddr = {};
+
+	memset(&req, 0, sizeof(req));
+	req.nh.nlmsg_len	= NLMSG_LENGTH(sizeof(req.id));
+	req.nh.nlmsg_type	= XFRM_MSG_DELSA;
+	req.nh.nlmsg_flags	= NLM_F_REQUEST | NLM_F_ACK;
+	req.nh.nlmsg_seq	= seq;
+
+	memcpy(&req.id.daddr, &dst, sizeof(dst));
+	req.id.family		= AF_INET;
+	req.id.proto		= proto;
+	/* Note: zero-spi cannot be deleted */
+	req.id.spi = spi;
+
+	memcpy(&saddr, &src, sizeof(src));
+	if (rtattr_pack(&req.nh, sizeof(req), XFRMA_SRCADDR, &saddr, sizeof(saddr)))
+		return -1;
+
+	if (send(xfrm_sock, &req, req.nh.nlmsg_len, 0) < 0) {
+		pr_err("send()");
+		return -1;
+	}
+
+	return netlink_check_answer(xfrm_sock);
+}
+
+static int xfrm_delete(int xfrm_sock, uint32_t *seq,
+		struct in_addr src, struct in_addr dst,
+		struct in_addr tunsrc, struct in_addr tundst, uint8_t proto)
+{
+	if (xfrm_state_del(xfrm_sock, (*seq)++, gen_spi(src), src, dst, proto)) {
+		printk("Failed to remove xfrm state");
+		return -1;
+	}
+
+	if (xfrm_state_del(xfrm_sock, (*seq)++, gen_spi(src), dst, src, proto)) {
+		printk("Failed to remove xfrm state");
+		return -1;
+	}
+
+	return 0;
+}
+
+static int xfrm_state_allocspi(int xfrm_sock, uint32_t *seq,
+		uint32_t spi, uint8_t proto)
+{
+	struct {
+		struct nlmsghdr			nh;
+		struct xfrm_userspi_info	spi;
+	} req;
+	struct {
+		struct nlmsghdr			nh;
+		union {
+			struct xfrm_usersa_info	info;
+			int error;
+		};
+	} answer;
+
+	memset(&req, 0, sizeof(req));
+	req.nh.nlmsg_len	= NLMSG_LENGTH(sizeof(req.spi));
+	req.nh.nlmsg_type	= XFRM_MSG_ALLOCSPI;
+	req.nh.nlmsg_flags	= NLM_F_REQUEST;
+	req.nh.nlmsg_seq	= (*seq)++;
+
+	req.spi.info.family	= AF_INET;
+	req.spi.min		= spi;
+	req.spi.max		= spi;
+	req.spi.info.id.proto	= proto;
+
+	if (send(xfrm_sock, &req, req.nh.nlmsg_len, 0) < 0) {
+		pr_err("send()");
+		return KSFT_FAIL;
+	}
+
+	if (recv(xfrm_sock, &answer, sizeof(answer), 0) < 0) {
+		pr_err("recv()");
+		return KSFT_FAIL;
+	} else if (answer.nh.nlmsg_type == XFRM_MSG_NEWSA) {
+		uint32_t new_spi = htonl(answer.info.id.spi);
+
+		if (new_spi != spi) {
+			printk("allocated spi is different from requested: %#x != %#x",
+					new_spi, spi);
+			return KSFT_FAIL;
+		}
+		return KSFT_PASS;
+	} else if (answer.nh.nlmsg_type != NLMSG_ERROR) {
+		printk("expected NLMSG_ERROR, got %d", (int)answer.nh.nlmsg_type);
+		return KSFT_FAIL;
+	}
+
+	printk("NLMSG_ERROR: %d: %s", answer.error, strerror(-answer.error));
+	return (answer.error) ? KSFT_FAIL : KSFT_PASS;
+}
+
+static int netlink_sock_bind(int *sock, uint32_t *seq, int proto, uint32_t groups)
+{
+	struct sockaddr_nl snl = {};
+	socklen_t addr_len;
+	int ret = -1;
+
+	snl.nl_family = AF_NETLINK;
+	snl.nl_groups = groups;
+
+	if (netlink_sock(sock, seq, proto)) {
+		printk("Failed to open xfrm netlink socket");
+		return -1;
+	}
+
+	if (bind(*sock, (struct sockaddr *)&snl, sizeof(snl)) < 0) {
+		pr_err("bind()");
+		goto out_close;
+	}
+
+	addr_len = sizeof(snl);
+	if (getsockname(*sock, (struct sockaddr *)&snl, &addr_len) < 0) {
+		pr_err("getsockname()");
+		goto out_close;
+	}
+	if (addr_len != sizeof(snl)) {
+		printk("Wrong address length %d", addr_len);
+		goto out_close;
+	}
+	if (snl.nl_family != AF_NETLINK) {
+		printk("Wrong address family %d", snl.nl_family);
+		goto out_close;
+	}
+	return 0;
+
+out_close:
+	close(*sock);
+	return ret;
+}
+
+static int xfrm_monitor_acquire(int xfrm_sock, uint32_t *seq, unsigned int nr)
+{
+	struct {
+		struct nlmsghdr nh;
+		union {
+			struct xfrm_user_acquire acq;
+			int error;
+		};
+		char attrbuf[MAX_PAYLOAD];
+	} req;
+	struct xfrm_user_tmpl xfrm_tmpl = {};
+	int xfrm_listen = -1, ret = KSFT_FAIL;
+	uint32_t seq_listen;
+
+	if (netlink_sock_bind(&xfrm_listen, &seq_listen, NETLINK_XFRM, XFRMNLGRP_ACQUIRE))
+		return KSFT_FAIL;
+
+	memset(&req, 0, sizeof(req));
+	req.nh.nlmsg_len	= NLMSG_LENGTH(sizeof(req.acq));
+	req.nh.nlmsg_type	= XFRM_MSG_ACQUIRE;
+	req.nh.nlmsg_flags	= NLM_F_REQUEST | NLM_F_ACK;
+	req.nh.nlmsg_seq	= (*seq)++;
+
+	req.acq.policy.sel.family	= AF_INET;
+	req.acq.aalgos	= 0xfeed;
+	req.acq.ealgos	= 0xbaad;
+	req.acq.calgos	= 0xbabe;
+
+	xfrm_tmpl.family = AF_INET;
+	xfrm_tmpl.id.proto = IPPROTO_ESP;
+	if (rtattr_pack(&req.nh, sizeof(req), XFRMA_TMPL, &xfrm_tmpl, sizeof(xfrm_tmpl)))
+		goto out_close;
+
+	if (send(xfrm_sock, &req, req.nh.nlmsg_len, 0) < 0) {
+		pr_err("send()");
+		goto out_close;
+	}
+
+	if (recv(xfrm_sock, &req, sizeof(req), 0) < 0) {
+		pr_err("recv()");
+		goto out_close;
+	} else if (req.nh.nlmsg_type != NLMSG_ERROR) {
+		printk("expected NLMSG_ERROR, got %d", (int)req.nh.nlmsg_type);
+		goto out_close;
+	}
+
+	if (req.error) {
+		printk("NLMSG_ERROR: %d: %s", req.error, strerror(-req.error));
+		ret = req.error;
+		goto out_close;
+	}
+
+	if (recv(xfrm_listen, &req, sizeof(req), 0) < 0) {
+		pr_err("recv()");
+		goto out_close;
+	}
+
+	if (req.acq.aalgos != 0xfeed || req.acq.ealgos != 0xbaad
+			|| req.acq.calgos != 0xbabe) {
+		printk("xfrm_user_acquire has changed  %x %x %x",
+				req.acq.aalgos, req.acq.ealgos, req.acq.calgos);
+		goto out_close;
+	}
+
+	ret = KSFT_PASS;
+out_close:
+	close(xfrm_listen);
+	return ret;
+}
+
+static int xfrm_expire_state(int xfrm_sock, uint32_t *seq,
+		unsigned int nr, struct xfrm_desc *desc)
+{
+	struct {
+		struct nlmsghdr nh;
+		union {
+			struct xfrm_user_expire expire;
+			int error;
+		};
+	} req;
+	struct in_addr src, dst;
+	int xfrm_listen = -1, ret = KSFT_FAIL;
+	uint32_t seq_listen;
+
+	src = inet_makeaddr(INADDR_B, child_ip(nr));
+	dst = inet_makeaddr(INADDR_B, grchild_ip(nr));
+
+	if (xfrm_state_add(xfrm_sock, (*seq)++, gen_spi(src), src, dst, desc)) {
+		printk("Failed to add xfrm state");
+		return KSFT_FAIL;
+	}
+
+	if (netlink_sock_bind(&xfrm_listen, &seq_listen, NETLINK_XFRM, XFRMNLGRP_EXPIRE))
+		return KSFT_FAIL;
+
+	memset(&req, 0, sizeof(req));
+	req.nh.nlmsg_len	= NLMSG_LENGTH(sizeof(req.expire));
+	req.nh.nlmsg_type	= XFRM_MSG_EXPIRE;
+	req.nh.nlmsg_flags	= NLM_F_REQUEST | NLM_F_ACK;
+	req.nh.nlmsg_seq	= (*seq)++;
+
+	memcpy(&req.expire.state.id.daddr, &dst, sizeof(dst));
+	req.expire.state.id.spi		= gen_spi(src);
+	req.expire.state.id.proto	= desc->proto;
+	req.expire.state.family		= AF_INET;
+	req.expire.hard			= 0xff;
+
+	if (send(xfrm_sock, &req, req.nh.nlmsg_len, 0) < 0) {
+		pr_err("send()");
+		goto out_close;
+	}
+
+	if (recv(xfrm_sock, &req, sizeof(req), 0) < 0) {
+		pr_err("recv()");
+		goto out_close;
+	} else if (req.nh.nlmsg_type != NLMSG_ERROR) {
+		printk("expected NLMSG_ERROR, got %d", (int)req.nh.nlmsg_type);
+		goto out_close;
+	}
+
+	if (req.error) {
+		printk("NLMSG_ERROR: %d: %s", req.error, strerror(-req.error));
+		ret = req.error;
+		goto out_close;
+	}
+
+	if (recv(xfrm_listen, &req, sizeof(req), 0) < 0) {
+		pr_err("recv()");
+		goto out_close;
+	}
+
+	if (req.expire.hard != 0x1) {
+		printk("expire.hard is not set: %x", req.expire.hard);
+		goto out_close;
+	}
+
+	ret = KSFT_PASS;
+out_close:
+	close(xfrm_listen);
+	return ret;
+}
+
+static int xfrm_expire_policy(int xfrm_sock, uint32_t *seq,
+		unsigned int nr, struct xfrm_desc *desc)
+{
+	struct {
+		struct nlmsghdr nh;
+		union {
+			struct xfrm_user_polexpire expire;
+			int error;
+		};
+	} req;
+	struct in_addr src, dst, tunsrc, tundst;
+	int xfrm_listen = -1, ret = KSFT_FAIL;
+	uint32_t seq_listen;
+
+	src = inet_makeaddr(INADDR_B, child_ip(nr));
+	dst = inet_makeaddr(INADDR_B, grchild_ip(nr));
+	tunsrc = inet_makeaddr(INADDR_A, child_ip(nr));
+	tundst = inet_makeaddr(INADDR_A, grchild_ip(nr));
+
+	if (xfrm_policy_add(xfrm_sock, (*seq)++, gen_spi(src), src, dst,
+				XFRM_POLICY_OUT, tunsrc, tundst, desc->proto)) {
+		printk("Failed to add xfrm policy");
+		return KSFT_FAIL;
+	}
+
+	if (netlink_sock_bind(&xfrm_listen, &seq_listen, NETLINK_XFRM, XFRMNLGRP_EXPIRE))
+		return KSFT_FAIL;
+
+	memset(&req, 0, sizeof(req));
+	req.nh.nlmsg_len	= NLMSG_LENGTH(sizeof(req.expire));
+	req.nh.nlmsg_type	= XFRM_MSG_POLEXPIRE;
+	req.nh.nlmsg_flags	= NLM_F_REQUEST | NLM_F_ACK;
+	req.nh.nlmsg_seq	= (*seq)++;
+
+	/* Fill selector. */
+	memcpy(&req.expire.pol.sel.daddr, &dst, sizeof(tundst));
+	memcpy(&req.expire.pol.sel.saddr, &src, sizeof(tunsrc));
+	req.expire.pol.sel.family	= AF_INET;
+	req.expire.pol.sel.prefixlen_d	= PREFIX_LEN;
+	req.expire.pol.sel.prefixlen_s	= PREFIX_LEN;
+	req.expire.pol.dir		= XFRM_POLICY_OUT;
+	req.expire.hard			= 0xff;
+
+	if (send(xfrm_sock, &req, req.nh.nlmsg_len, 0) < 0) {
+		pr_err("send()");
+		goto out_close;
+	}
+
+	if (recv(xfrm_sock, &req, sizeof(req), 0) < 0) {
+		pr_err("recv()");
+		goto out_close;
+	} else if (req.nh.nlmsg_type != NLMSG_ERROR) {
+		printk("expected NLMSG_ERROR, got %d", (int)req.nh.nlmsg_type);
+		goto out_close;
+	}
+
+	if (req.error) {
+		printk("NLMSG_ERROR: %d: %s", req.error, strerror(-req.error));
+		ret = req.error;
+		goto out_close;
+	}
+
+	if (recv(xfrm_listen, &req, sizeof(req), 0) < 0) {
+		pr_err("recv()");
+		goto out_close;
+	}
+
+	if (req.expire.hard != 0x1) {
+		printk("expire.hard is not set: %x", req.expire.hard);
+		goto out_close;
+	}
+
+	ret = KSFT_PASS;
+out_close:
+	close(xfrm_listen);
+	return ret;
+}
+
+static int child_serv(int xfrm_sock, uint32_t *seq,
+		unsigned int nr, int cmd_fd, void *buf, struct xfrm_desc *desc)
+{
+	struct in_addr src, dst, tunsrc, tundst;
+	struct test_desc msg;
+	int ret = KSFT_FAIL;
+
+	src = inet_makeaddr(INADDR_B, child_ip(nr));
+	dst = inet_makeaddr(INADDR_B, grchild_ip(nr));
+	tunsrc = inet_makeaddr(INADDR_A, child_ip(nr));
+	tundst = inet_makeaddr(INADDR_A, grchild_ip(nr));
+
+	/* UDP pinging without xfrm */
+	if (do_ping(cmd_fd, buf, page_size, src, true, 0, 0, udp_ping_send)) {
+		printk("ping failed before setting xfrm");
+		return KSFT_FAIL;
+	}
+
+	memset(&msg, 0, sizeof(msg));
+	msg.type = MSG_XFRM_PREPARE;
+	memcpy(&msg.body.xfrm_desc, desc, sizeof(*desc));
+	write_msg(cmd_fd, &msg, 1);
+
+	if (xfrm_prepare(xfrm_sock, seq, src, dst, tunsrc, tundst, desc->proto)) {
+		printk("failed to prepare xfrm");
+		goto cleanup;
+	}
+
+	memset(&msg, 0, sizeof(msg));
+	msg.type = MSG_XFRM_ADD;
+	memcpy(&msg.body.xfrm_desc, desc, sizeof(*desc));
+	write_msg(cmd_fd, &msg, 1);
+	if (xfrm_set(xfrm_sock, seq, src, dst, tunsrc, tundst, desc)) {
+		printk("failed to set xfrm");
+		goto delete;
+	}
+
+	/* UDP pinging with xfrm tunnel */
+	if (do_ping(cmd_fd, buf, page_size, tunsrc,
+				true, 0, 0, udp_ping_send)) {
+		printk("ping failed for xfrm");
+		goto delete;
+	}
+
+	ret = KSFT_PASS;
+delete:
+	/* xfrm delete */
+	memset(&msg, 0, sizeof(msg));
+	msg.type = MSG_XFRM_DEL;
+	memcpy(&msg.body.xfrm_desc, desc, sizeof(*desc));
+	write_msg(cmd_fd, &msg, 1);
+
+	if (xfrm_delete(xfrm_sock, seq, src, dst, tunsrc, tundst, desc->proto)) {
+		printk("failed ping to remove xfrm");
+		ret = KSFT_FAIL;
+	}
+
+cleanup:
+	memset(&msg, 0, sizeof(msg));
+	msg.type = MSG_XFRM_CLEANUP;
+	memcpy(&msg.body.xfrm_desc, desc, sizeof(*desc));
+	write_msg(cmd_fd, &msg, 1);
+	if (xfrm_cleanup(xfrm_sock, seq, src, dst, tunsrc, tundst)) {
+		printk("failed ping to cleanup xfrm");
+		ret = KSFT_FAIL;
+	}
+	return ret;
+}
+
+static int child_f(unsigned int nr, int test_desc_fd, int cmd_fd, void *buf)
+{
+	struct xfrm_desc desc;
+	struct test_desc msg;
+	int xfrm_sock = -1;
+	uint32_t seq;
+
+	if (switch_ns(nsfd_childa))
+		exit(KSFT_FAIL);
+
+	if (netlink_sock(&xfrm_sock, &seq, NETLINK_XFRM)) {
+		printk("Failed to open xfrm netlink socket");
+		exit(KSFT_FAIL);
+	}
+
+	/* Check that seq sock is ready, just for sure. */
+	memset(&msg, 0, sizeof(msg));
+	msg.type = MSG_ACK;
+	write_msg(cmd_fd, &msg, 1);
+	read_msg(cmd_fd, &msg, 1);
+	if (msg.type != MSG_ACK) {
+		printk("Ack failed");
+		exit(KSFT_FAIL);
+	}
+
+	for (;;) {
+		ssize_t received = read(test_desc_fd, &desc, sizeof(desc));
+		int ret;
+
+		if (received == 0) /* EOF */
+			break;
+
+		if (received != sizeof(desc)) {
+			pr_err("read() returned %zd", received);
+			exit(KSFT_FAIL);
+		}
+
+		switch (desc.type) {
+		case CREATE_TUNNEL:
+			ret = child_serv(xfrm_sock, &seq, nr,
+					 cmd_fd, buf, &desc);
+			break;
+		case ALLOCATE_SPI:
+			ret = xfrm_state_allocspi(xfrm_sock, &seq,
+						  -1, desc.proto);
+			break;
+		case MONITOR_ACQUIRE:
+			ret = xfrm_monitor_acquire(xfrm_sock, &seq, nr);
+			break;
+		case EXPIRE_STATE:
+			ret = xfrm_expire_state(xfrm_sock, &seq, nr, &desc);
+			break;
+		case EXPIRE_POLICY:
+			ret = xfrm_expire_policy(xfrm_sock, &seq, nr, &desc);
+			break;
+		default:
+			printk("Unknown desc type %d", desc.type);
+			exit(KSFT_FAIL);
+		}
+		write_test_result(ret, &desc);
+	}
+
+	close(xfrm_sock);
+
+	msg.type = MSG_EXIT;
+	write_msg(cmd_fd, &msg, 1);
+	exit(KSFT_PASS);
+}
+
+static void grand_child_serv(unsigned int nr, int cmd_fd, void *buf,
+		struct test_desc *msg, int xfrm_sock, uint32_t *seq)
+{
+	struct in_addr src, dst, tunsrc, tundst;
+	bool tun_reply;
+	struct xfrm_desc *desc = &msg->body.xfrm_desc;
+
+	src = inet_makeaddr(INADDR_B, grchild_ip(nr));
+	dst = inet_makeaddr(INADDR_B, child_ip(nr));
+	tunsrc = inet_makeaddr(INADDR_A, grchild_ip(nr));
+	tundst = inet_makeaddr(INADDR_A, child_ip(nr));
+
+	switch (msg->type) {
+	case MSG_EXIT:
+		exit(KSFT_PASS);
+	case MSG_ACK:
+		write_msg(cmd_fd, msg, 1);
+		break;
+	case MSG_PING:
+		tun_reply = memcmp(&dst, &msg->body.ping.reply_ip, sizeof(in_addr_t));
+		/* UDP pinging without xfrm */
+		if (do_ping(cmd_fd, buf, page_size, tun_reply ? tunsrc : src,
+				false, msg->body.ping.port,
+				msg->body.ping.reply_ip, udp_ping_reply)) {
+			printk("ping failed before setting xfrm");
+		}
+		break;
+	case MSG_XFRM_PREPARE:
+		if (xfrm_prepare(xfrm_sock, seq, src, dst, tunsrc, tundst,
+					desc->proto)) {
+			xfrm_cleanup(xfrm_sock, seq, src, dst, tunsrc, tundst);
+			printk("failed to prepare xfrm");
+		}
+		break;
+	case MSG_XFRM_ADD:
+		if (xfrm_set(xfrm_sock, seq, src, dst, tunsrc, tundst, desc)) {
+			xfrm_cleanup(xfrm_sock, seq, src, dst, tunsrc, tundst);
+			printk("failed to set xfrm");
+		}
+		break;
+	case MSG_XFRM_DEL:
+		if (xfrm_delete(xfrm_sock, seq, src, dst, tunsrc, tundst,
+					desc->proto)) {
+			xfrm_cleanup(xfrm_sock, seq, src, dst, tunsrc, tundst);
+			printk("failed to remove xfrm");
+		}
+		break;
+	case MSG_XFRM_CLEANUP:
+		if (xfrm_cleanup(xfrm_sock, seq, src, dst, tunsrc, tundst)) {
+			printk("failed to cleanup xfrm");
+		}
+		break;
+	default:
+		printk("got unknown msg type %d", msg->type);
+	};
+}
+
+static int grand_child_f(unsigned int nr, int cmd_fd, void *buf)
+{
+	struct test_desc msg;
+	int xfrm_sock = -1;
+	uint32_t seq;
+
+	if (switch_ns(nsfd_childb))
+		exit(KSFT_FAIL);
+
+	if (netlink_sock(&xfrm_sock, &seq, NETLINK_XFRM)) {
+		printk("Failed to open xfrm netlink socket");
+		exit(KSFT_FAIL);
+	}
+
+	do {
+		read_msg(cmd_fd, &msg, 1);
+		grand_child_serv(nr, cmd_fd, buf, &msg, xfrm_sock, &seq);
+	} while (1);
+
+	close(xfrm_sock);
+	exit(KSFT_FAIL);
+}
+
+static int start_child(unsigned int nr, char *veth, int test_desc_fd[2])
+{
+	int cmd_sock[2];
+	void *data_map;
+	pid_t child;
+
+	if (init_child(nsfd_childa, veth, child_ip(nr), grchild_ip(nr)))
+		return -1;
+
+	if (init_child(nsfd_childb, veth, grchild_ip(nr), child_ip(nr)))
+		return -1;
+
+	child = fork();
+	if (child < 0) {
+		pr_err("fork()");
+		return -1;
+	} else if (child) {
+		/* in parent - selftest */
+		return switch_ns(nsfd_parent);
+	}
+
+	if (close(test_desc_fd[1])) {
+		pr_err("close()");
+		return -1;
+	}
+
+	/* child */
+	data_map = mmap(0, page_size, PROT_READ | PROT_WRITE,
+			MAP_SHARED | MAP_ANONYMOUS, -1, 0);
+	if (data_map == MAP_FAILED) {
+		pr_err("mmap()");
+		return -1;
+	}
+
+	randomize_buffer(data_map, page_size);
+
+	if (socketpair(PF_LOCAL, SOCK_SEQPACKET, 0, cmd_sock)) {
+		pr_err("socketpair()");
+		return -1;
+	}
+
+	child = fork();
+	if (child < 0) {
+		pr_err("fork()");
+		return -1;
+	} else if (child) {
+		if (close(cmd_sock[0])) {
+			pr_err("close()");
+			return -1;
+		}
+		return child_f(nr, test_desc_fd[0], cmd_sock[1], data_map);
+	}
+	if (close(cmd_sock[1])) {
+		pr_err("close()");
+		return -1;
+	}
+	return grand_child_f(nr, cmd_sock[0], data_map);
+}
+
+static void exit_usage(char **argv)
+{
+	printk("Usage: %s [nr_process]", argv[0]);
+	exit(KSFT_FAIL);
+}
+
+static int __write_desc(int test_desc_fd, struct xfrm_desc *desc)
+{
+	ssize_t ret;
+
+	ret = write(test_desc_fd, desc, sizeof(*desc));
+
+	if (ret == sizeof(*desc))
+		return 0;
+
+	pr_err("Writing test's desc failed %ld", ret);
+
+	return -1;
+}
+
+static int write_desc(int proto, int test_desc_fd,
+		char *a, char *e, char *c, char *ae)
+{
+	struct xfrm_desc desc = {};
+
+	desc.type = CREATE_TUNNEL;
+	desc.proto = proto;
+
+	if (a)
+		strncpy(desc.a_algo, a, ALGO_LEN - 1);
+	if (e)
+		strncpy(desc.e_algo, e, ALGO_LEN - 1);
+	if (c)
+		strncpy(desc.c_algo, c, ALGO_LEN - 1);
+	if (ae)
+		strncpy(desc.ae_algo, ae, ALGO_LEN - 1);
+
+	return __write_desc(test_desc_fd, &desc);
+}
+
+int proto_list[] = { IPPROTO_AH, IPPROTO_COMP, IPPROTO_ESP };
+char *ah_list[] = {
+	"digest_null", "hmac(md5)", "hmac(sha1)", "hmac(sha256)",
+	"hmac(sha384)", "hmac(sha512)", "hmac(rmd160)",
+	"xcbc(aes)", "cmac(aes)"
+};
+char *comp_list[] = {
+	"deflate",
+#if 0
+	/* No compression backend realization */
+	"lzs", "lzjh"
+#endif
+};
+char *e_list[] = {
+	"ecb(cipher_null)", "cbc(des)", "cbc(des3_ede)", "cbc(cast5)",
+	"cbc(blowfish)", "cbc(aes)", "cbc(serpent)", "cbc(camellia)",
+	"cbc(twofish)", "rfc3686(ctr(aes))"
+};
+char *ae_list[] = {
+#if 0
+	/* not implemented */
+	"rfc4106(gcm(aes))", "rfc4309(ccm(aes))", "rfc4543(gcm(aes))",
+	"rfc7539esp(chacha20,poly1305)"
+#endif
+};
+
+const unsigned int proto_plan = ARRAY_SIZE(ah_list) + ARRAY_SIZE(comp_list) \
+				+ (ARRAY_SIZE(ah_list) * ARRAY_SIZE(e_list)) \
+				+ ARRAY_SIZE(ae_list);
+
+static int write_proto_plan(int fd, int proto)
+{
+	unsigned int i;
+
+	switch (proto) {
+	case IPPROTO_AH:
+		for (i = 0; i < ARRAY_SIZE(ah_list); i++) {
+			if (write_desc(proto, fd, ah_list[i], 0, 0, 0))
+				return -1;
+		}
+		break;
+	case IPPROTO_COMP:
+		for (i = 0; i < ARRAY_SIZE(comp_list); i++) {
+			if (write_desc(proto, fd, 0, 0, comp_list[i], 0))
+				return -1;
+		}
+		break;
+	case IPPROTO_ESP:
+		for (i = 0; i < ARRAY_SIZE(ah_list); i++) {
+			int j;
+
+			for (j = 0; j < ARRAY_SIZE(e_list); j++) {
+				if (write_desc(proto, fd, ah_list[i],
+							e_list[j], 0, 0))
+					return -1;
+			}
+		}
+		for (i = 0; i < ARRAY_SIZE(ae_list); i++) {
+			if (write_desc(proto, fd, 0, 0, 0, ae_list[i]))
+				return -1;
+		}
+		break;
+	default:
+		printk("BUG: Specified unknown proto %d", proto);
+		return -1;
+	}
+
+	return 0;
+}
+
+/*
+ * Some structures in xfrm uapi header differ in size between
+ * 64-bit and 32-bit ABI:
+ *
+ *             32-bit UABI               |            64-bit UABI
+ *  -------------------------------------|-------------------------------------
+ *   sizeof(xfrm_usersa_info)     = 220  |  sizeof(xfrm_usersa_info)     = 224
+ *   sizeof(xfrm_userpolicy_info) = 164  |  sizeof(xfrm_userpolicy_info) = 168
+ *   sizeof(xfrm_userspi_info)    = 228  |  sizeof(xfrm_userspi_info)    = 232
+ *   sizeof(xfrm_user_acquire)    = 276  |  sizeof(xfrm_user_acquire)    = 280
+ *   sizeof(xfrm_user_expire)     = 224  |  sizeof(xfrm_user_expire)     = 232
+ *   sizeof(xfrm_user_polexpire)  = 168  |  sizeof(xfrm_user_polexpire)  = 176
+ *
+ * Check the affected by the UABI difference structures.
+ */
+const unsigned int compat_plan = 4;
+static int write_compat_struct_tests(int test_desc_fd)
+{
+	struct xfrm_desc desc = {};
+
+	desc.type = ALLOCATE_SPI;
+	desc.proto = IPPROTO_AH;
+	strncpy(desc.a_algo, ah_list[0], ALGO_LEN - 1);
+
+	if (__write_desc(test_desc_fd, &desc))
+		return -1;
+
+	desc.type = MONITOR_ACQUIRE;
+	if (__write_desc(test_desc_fd, &desc))
+		return -1;
+
+	desc.type = EXPIRE_STATE;
+	if (__write_desc(test_desc_fd, &desc))
+		return -1;
+
+	desc.type = EXPIRE_POLICY;
+	if (__write_desc(test_desc_fd, &desc))
+		return -1;
+
+	return 0;
+}
+
+static int write_test_plan(int test_desc_fd)
+{
+	unsigned int i;
+	pid_t child;
+
+	child = fork();
+	if (child < 0) {
+		pr_err("fork()");
+		return -1;
+	}
+	if (child) {
+		if (close(test_desc_fd))
+			printk("close(): %m");
+		return 0;
+	}
+
+	if (write_compat_struct_tests(test_desc_fd))
+		exit(KSFT_FAIL);
+
+	for (i = 0; i < ARRAY_SIZE(proto_list); i++) {
+		if (write_proto_plan(test_desc_fd, proto_list[i]))
+			exit(KSFT_FAIL);
+	}
+
+	exit(KSFT_PASS);
+}
+
+static int children_cleanup(void)
+{
+	unsigned ret = KSFT_PASS;
+
+	while (1) {
+		int status;
+		pid_t p = wait(&status);
+
+		if ((p < 0) && errno == ECHILD)
+			break;
+
+		if (p < 0) {
+			pr_err("wait()");
+			return KSFT_FAIL;
+		}
+
+		if (!WIFEXITED(status)) {
+			ret = KSFT_FAIL;
+			continue;
+		}
+
+		if (WEXITSTATUS(status) == KSFT_FAIL)
+			ret = KSFT_FAIL;
+	}
+
+	return ret;
+}
+
+typedef void (*print_res)(const char *, ...);
+
+static int check_results(void)
+{
+	struct test_result tr = {};
+	struct xfrm_desc *d = &tr.desc;
+	int ret = KSFT_PASS;
+
+	while (1) {
+		ssize_t received = read(results_fd[0], &tr, sizeof(tr));
+		print_res result;
+
+		if (received == 0) /* EOF */
+			break;
+
+		if (received != sizeof(tr)) {
+			pr_err("read() returned %zd", received);
+			return KSFT_FAIL;
+		}
+
+		switch (tr.res) {
+		case KSFT_PASS:
+			result = ksft_test_result_pass;
+			break;
+		case KSFT_FAIL:
+		default:
+			result = ksft_test_result_fail;
+			ret = KSFT_FAIL;
+		}
+
+		result(" %s: [%u, '%s', '%s', '%s', '%s', %u]\n",
+		       desc_name[d->type], (unsigned int)d->proto, d->a_algo,
+		       d->e_algo, d->c_algo, d->ae_algo, d->icv_len);
+	}
+
+	return ret;
+}
+
+int main(int argc, char **argv)
+{
+	unsigned int nr_process = 1;
+	int route_sock = -1, ret = KSFT_SKIP;
+	int test_desc_fd[2];
+	uint32_t route_seq;
+	unsigned int i;
+
+	if (argc > 2)
+		exit_usage(argv);
+
+	if (argc > 1) {
+		char *endptr;
+
+		errno = 0;
+		nr_process = strtol(argv[1], &endptr, 10);
+		if ((errno == ERANGE && (nr_process == LONG_MAX || nr_process == LONG_MIN))
+				|| (errno != 0 && nr_process == 0)
+				|| (endptr == argv[1]) || (*endptr != '\0')) {
+			printk("Failed to parse [nr_process]");
+			exit_usage(argv);
+		}
+
+		if (nr_process > MAX_PROCESSES || !nr_process) {
+			printk("nr_process should be between [1; %u]",
+					MAX_PROCESSES);
+			exit_usage(argv);
+		}
+	}
+
+	srand(time(NULL));
+	page_size = sysconf(_SC_PAGESIZE);
+	if (page_size < 1)
+		ksft_exit_skip("sysconf(): %m\n");
+
+	if (pipe2(test_desc_fd, O_DIRECT) < 0)
+		ksft_exit_skip("pipe(): %m\n");
+
+	if (pipe2(results_fd, O_DIRECT) < 0)
+		ksft_exit_skip("pipe(): %m\n");
+
+	if (init_namespaces())
+		ksft_exit_skip("Failed to create namespaces\n");
+
+	if (netlink_sock(&route_sock, &route_seq, NETLINK_ROUTE))
+		ksft_exit_skip("Failed to open netlink route socket\n");
+
+	for (i = 0; i < nr_process; i++) {
+		char veth[VETH_LEN];
+
+		snprintf(veth, VETH_LEN, VETH_FMT, i);
+
+		if (veth_add(route_sock, route_seq++, veth, nsfd_childa, veth, nsfd_childb)) {
+			close(route_sock);
+			ksft_exit_fail_msg("Failed to create veth device");
+		}
+
+		if (start_child(i, veth, test_desc_fd)) {
+			close(route_sock);
+			ksft_exit_fail_msg("Child %u failed to start", i);
+		}
+	}
+
+	if (close(route_sock) || close(test_desc_fd[0]) || close(results_fd[1]))
+		ksft_exit_fail_msg("close(): %m");
+
+	ksft_set_plan(proto_plan + compat_plan);
+
+	if (write_test_plan(test_desc_fd[1]))
+		ksft_exit_fail_msg("Failed to write test plan to pipe");
+
+	ret = check_results();
+
+	if (children_cleanup() == KSFT_FAIL)
+		exit(KSFT_FAIL);
+
+	exit(ret);
+}
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c
index a54966531a64..77bb62feb872 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c
@@ -54,6 +54,7 @@ static int pf = AF_INET;
 static int cfg_sndbuf;
 static int cfg_rcvbuf;
 static bool cfg_join;
+static bool cfg_remove;
 static int cfg_wait;
 
 static void die_usage(void)
@@ -271,6 +272,9 @@ static size_t do_rnd_write(const int fd, char *buf, const size_t len)
 	if (cfg_join && first && do_w > 100)
 		do_w = 100;
 
+	if (cfg_remove && do_w > 50)
+		do_w = 50;
+
 	bw = write(fd, buf, do_w);
 	if (bw < 0)
 		perror("write");
@@ -281,6 +285,9 @@ static size_t do_rnd_write(const int fd, char *buf, const size_t len)
 		first = false;
 	}
 
+	if (cfg_remove)
+		usleep(200000);
+
 	return bw;
 }
 
@@ -428,7 +435,7 @@ static int copyfd_io_poll(int infd, int peerfd, int outfd)
 	}
 
 	/* leave some time for late join/announce */
-	if (cfg_join)
+	if (cfg_join || cfg_remove)
 		usleep(cfg_wait);
 
 	close(peerfd);
@@ -686,7 +693,7 @@ static void maybe_close(int fd)
 {
 	unsigned int r = rand();
 
-	if (!cfg_join && (r & 1))
+	if (!(cfg_join || cfg_remove) && (r & 1))
 		close(fd);
 }
 
@@ -822,13 +829,18 @@ static void parse_opts(int argc, char **argv)
 {
 	int c;
 
-	while ((c = getopt(argc, argv, "6jlp:s:hut:m:S:R:w:")) != -1) {
+	while ((c = getopt(argc, argv, "6jrlp:s:hut:m:S:R:w:")) != -1) {
 		switch (c) {
 		case 'j':
 			cfg_join = true;
 			cfg_mode = CFG_MODE_POLL;
 			cfg_wait = 400000;
 			break;
+		case 'r':
+			cfg_remove = true;
+			cfg_mode = CFG_MODE_POLL;
+			cfg_wait = 400000;
+			break;
 		case 'l':
 			listen_mode = true;
 			break;
diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index c2943e4dfcfe..08f53d86dedc 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -8,6 +8,7 @@ cin=""
 cout=""
 ksft_skip=4
 timeout=30
+mptcp_connect=""
 capture=0
 
 TEST_COUNT=0
@@ -132,6 +133,8 @@ do_transfer()
 	cl_proto="$3"
 	srv_proto="$4"
 	connect_addr="$5"
+	rm_nr_ns1="$6"
+	rm_nr_ns2="$7"
 
 	port=$((10000+$TEST_COUNT))
 	TEST_COUNT=$((TEST_COUNT+1))
@@ -156,14 +159,44 @@ do_transfer()
 		sleep 1
 	fi
 
-	ip netns exec ${listener_ns} ./mptcp_connect -j -t $timeout -l -p $port -s ${srv_proto} 0.0.0.0 < "$sin" > "$sout" &
+	if [[ $rm_nr_ns1 -eq 0 && $rm_nr_ns2 -eq 0 ]]; then
+		mptcp_connect="./mptcp_connect -j"
+	else
+		mptcp_connect="./mptcp_connect -r"
+	fi
+
+	ip netns exec ${listener_ns} $mptcp_connect -t $timeout -l -p $port -s ${srv_proto} 0.0.0.0 < "$sin" > "$sout" &
 	spid=$!
 
 	sleep 1
 
-	ip netns exec ${connector_ns} ./mptcp_connect -j -t $timeout -p $port -s ${cl_proto} $connect_addr < "$cin" > "$cout" &
+	ip netns exec ${connector_ns} $mptcp_connect -t $timeout -p $port -s ${cl_proto} $connect_addr < "$cin" > "$cout" &
 	cpid=$!
 
+	if [ $rm_nr_ns1 -gt 0 ]; then
+		counter=1
+		sleep 1
+
+		while [ $counter -le $rm_nr_ns1 ]
+		do
+			ip netns exec ${listener_ns} ./pm_nl_ctl del $counter
+			sleep 1
+			let counter+=1
+		done
+	fi
+
+	if [ $rm_nr_ns2 -gt 0 ]; then
+		counter=1
+		sleep 1
+
+		while [ $counter -le $rm_nr_ns2 ]
+		do
+			ip netns exec ${connector_ns} ./pm_nl_ctl del $counter
+			sleep 1
+			let counter+=1
+		done
+	fi
+
 	wait $cpid
 	retc=$?
 	wait $spid
@@ -219,7 +252,24 @@ run_tests()
 	connect_addr="$3"
 	lret=0
 
-	do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP ${connect_addr}
+	do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP ${connect_addr} 0 0
+	lret=$?
+	if [ $lret -ne 0 ]; then
+		ret=$lret
+		return
+	fi
+}
+
+run_remove_tests()
+{
+	listener_ns="$1"
+	connector_ns="$2"
+	connect_addr="$3"
+	rm_nr_ns1="$4"
+	rm_nr_ns2="$5"
+	lret=0
+
+	do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP ${connect_addr} ${rm_nr_ns1} ${rm_nr_ns2}
 	lret=$?
 	if [ $lret -ne 0 ]; then
 		ret=$lret
@@ -276,6 +326,80 @@ chk_join_nr()
 	fi
 }
 
+chk_add_nr()
+{
+	local add_nr=$1
+	local echo_nr=$2
+	local count
+	local dump_stats
+
+	printf "%-39s %s" " " "add"
+	count=`ip netns exec $ns2 nstat -as | grep MPTcpExtAddAddr | awk '{print $2}'`
+	[ -z "$count" ] && count=0
+	if [ "$count" != "$add_nr" ]; then
+		echo "[fail] got $count ADD_ADDR[s] expected $add_nr"
+		ret=1
+		dump_stats=1
+	else
+		echo -n "[ ok ]"
+	fi
+
+	echo -n " - echo  "
+	count=`ip netns exec $ns1 nstat -as | grep MPTcpExtEchoAdd | awk '{print $2}'`
+	[ -z "$count" ] && count=0
+	if [ "$count" != "$echo_nr" ]; then
+		echo "[fail] got $count ADD_ADDR echo[s] expected $echo_nr"
+		ret=1
+		dump_stats=1
+	else
+		echo "[ ok ]"
+	fi
+
+	if [ "${dump_stats}" = 1 ]; then
+		echo Server ns stats
+		ip netns exec $ns1 nstat -as | grep MPTcp
+		echo Client ns stats
+		ip netns exec $ns2 nstat -as | grep MPTcp
+	fi
+}
+
+chk_rm_nr()
+{
+	local rm_addr_nr=$1
+	local rm_subflow_nr=$2
+	local count
+	local dump_stats
+
+	printf "%-39s %s" " " "rm "
+	count=`ip netns exec $ns1 nstat -as | grep MPTcpExtRmAddr | awk '{print $2}'`
+	[ -z "$count" ] && count=0
+	if [ "$count" != "$rm_addr_nr" ]; then
+		echo "[fail] got $count RM_ADDR[s] expected $rm_addr_nr"
+		ret=1
+		dump_stats=1
+	else
+		echo -n "[ ok ]"
+	fi
+
+	echo -n " - sf    "
+	count=`ip netns exec $ns2 nstat -as | grep MPTcpExtRmSubflow | awk '{print $2}'`
+	[ -z "$count" ] && count=0
+	if [ "$count" != "$rm_subflow_nr" ]; then
+		echo "[fail] got $count RM_SUBFLOW[s] expected $rm_subflow_nr"
+		ret=1
+		dump_stats=1
+	else
+		echo "[ ok ]"
+	fi
+
+	if [ "${dump_stats}" = 1 ]; then
+		echo Server ns stats
+		ip netns exec $ns1 nstat -as | grep MPTcp
+		echo Client ns stats
+		ip netns exec $ns2 nstat -as | grep MPTcp
+	fi
+}
+
 sin=$(mktemp)
 sout=$(mktemp)
 cin=$(mktemp)
@@ -332,6 +456,7 @@ reset
 ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal
 run_tests $ns1 $ns2 10.0.1.1
 chk_join_nr "unused signal address" 0 0 0
+chk_add_nr 1 1
 
 # accept and use add_addr
 reset
@@ -340,6 +465,7 @@ ip netns exec $ns2 ./pm_nl_ctl limits 1 1
 ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal
 run_tests $ns1 $ns2 10.0.1.1
 chk_join_nr "signal address" 1 1 1
+chk_add_nr 1 1
 
 # accept and use add_addr with an additional subflow
 # note: signal address in server ns and local addresses in client ns must
@@ -352,6 +478,7 @@ ip netns exec $ns2 ./pm_nl_ctl limits 1 2
 ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
 run_tests $ns1 $ns2 10.0.1.1
 chk_join_nr "subflow and signal" 2 2 2
+chk_add_nr 1 1
 
 # accept and use add_addr with additional subflows
 reset
@@ -362,6 +489,59 @@ ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
 ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags subflow
 run_tests $ns1 $ns2 10.0.1.1
 chk_join_nr "multiple subflows and signal" 3 3 3
+chk_add_nr 1 1
+
+# single subflow, remove
+reset
+ip netns exec $ns1 ./pm_nl_ctl limits 0 1
+ip netns exec $ns2 ./pm_nl_ctl limits 0 1
+ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
+run_remove_tests $ns1 $ns2 10.0.1.1 0 1
+chk_join_nr "remove single subflow" 1 1 1
+chk_rm_nr 1 1
+
+# multiple subflows, remove
+reset
+ip netns exec $ns1 ./pm_nl_ctl limits 0 2
+ip netns exec $ns2 ./pm_nl_ctl limits 0 2
+ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow
+ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
+run_remove_tests $ns1 $ns2 10.0.1.1 0 2
+chk_join_nr "remove multiple subflows" 2 2 2
+chk_rm_nr 2 2
+
+# single address, remove
+reset
+ip netns exec $ns1 ./pm_nl_ctl limits 0 1
+ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal
+ip netns exec $ns2 ./pm_nl_ctl limits 1 1
+run_remove_tests $ns1 $ns2 10.0.1.1 1 0
+chk_join_nr "remove single address" 1 1 1
+chk_add_nr 1 1
+chk_rm_nr 0 0
+
+# subflow and signal, remove
+reset
+ip netns exec $ns1 ./pm_nl_ctl limits 0 2
+ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal
+ip netns exec $ns2 ./pm_nl_ctl limits 1 2
+ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
+run_remove_tests $ns1 $ns2 10.0.1.1 1 1
+chk_join_nr "remove subflow and signal" 2 2 2
+chk_add_nr 1 1
+chk_rm_nr 1 1
+
+# subflows and signal, remove
+reset
+ip netns exec $ns1 ./pm_nl_ctl limits 0 3
+ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal
+ip netns exec $ns2 ./pm_nl_ctl limits 1 3
+ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
+ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags subflow
+run_remove_tests $ns1 $ns2 10.0.1.1 1 2
+chk_join_nr "remove subflows and signal" 3 3 3
+chk_add_nr 1 1
+chk_rm_nr 2 2
 
 # single subflow, syncookies
 reset_with_cookies
@@ -396,6 +576,7 @@ ip netns exec $ns2 ./pm_nl_ctl limits 1 1
 ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal
 run_tests $ns1 $ns2 10.0.1.1
 chk_join_nr "signal address with syn cookies" 1 1 1
+chk_add_nr 1 1
 
 # test cookie with subflow and signal
 reset_with_cookies
@@ -405,6 +586,7 @@ ip netns exec $ns2 ./pm_nl_ctl limits 1 2
 ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
 run_tests $ns1 $ns2 10.0.1.1
 chk_join_nr "subflow and signal w cookies" 2 2 2
+chk_add_nr 1 1
 
 # accept and use add_addr with additional subflows
 reset_with_cookies
@@ -415,5 +597,6 @@ ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
 ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags subflow
 run_tests $ns1 $ns2 10.0.1.1
 chk_join_nr "subflows and signal w. cookies" 3 3 3
+chk_add_nr 1 1
 
 exit $ret
diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh
index 7c38a909f8b8..8a2fe6d64bf2 100755
--- a/tools/testing/selftests/net/rtnetlink.sh
+++ b/tools/testing/selftests/net/rtnetlink.sh
@@ -1175,6 +1175,51 @@ kci_test_neigh_get()
 	echo "PASS: neigh get"
 }
 
+kci_test_bridge_parent_id()
+{
+	local ret=0
+	sysfsnet=/sys/bus/netdevsim/devices/netdevsim
+	probed=false
+
+	if [ ! -w /sys/bus/netdevsim/new_device ] ; then
+		modprobe -q netdevsim
+		check_err $?
+		if [ $ret -ne 0 ]; then
+			echo "SKIP: bridge_parent_id can't load netdevsim"
+			return $ksft_skip
+		fi
+		probed=true
+	fi
+
+	echo "10 1" > /sys/bus/netdevsim/new_device
+	while [ ! -d ${sysfsnet}10 ] ; do :; done
+	echo "20 1" > /sys/bus/netdevsim/new_device
+	while [ ! -d ${sysfsnet}20 ] ; do :; done
+	udevadm settle
+	dev10=`ls ${sysfsnet}10/net/`
+	dev20=`ls ${sysfsnet}20/net/`
+
+	ip link add name test-bond0 type bond mode 802.3ad
+	ip link set dev $dev10 master test-bond0
+	ip link set dev $dev20 master test-bond0
+	ip link add name test-br0 type bridge
+	ip link set dev test-bond0 master test-br0
+	check_err $?
+
+	# clean up any leftovers
+	ip link del dev test-br0
+	ip link del dev test-bond0
+	echo 20 > /sys/bus/netdevsim/del_device
+	echo 10 > /sys/bus/netdevsim/del_device
+	$probed && rmmod netdevsim
+
+	if [ $ret -ne 0 ]; then
+		echo "FAIL: bridge_parent_id"
+		return 1
+	fi
+	echo "PASS: bridge_parent_id"
+}
+
 kci_test_rtnl()
 {
 	local ret=0
@@ -1224,6 +1269,8 @@ kci_test_rtnl()
 	check_err $?
 	kci_test_neigh_get
 	check_err $?
+	kci_test_bridge_parent_id
+	check_err $?
 
 	kci_del_dummy
 	return $ret
diff --git a/tools/testing/selftests/powerpc/mm/prot_sao.c b/tools/testing/selftests/powerpc/mm/prot_sao.c
index e0cf8ebbf8cd..30b71b1d78d5 100644
--- a/tools/testing/selftests/powerpc/mm/prot_sao.c
+++ b/tools/testing/selftests/powerpc/mm/prot_sao.c
@@ -7,6 +7,7 @@
 #include <stdlib.h>
 #include <string.h>
 #include <sys/mman.h>
+#include <unistd.h>
 
 #include <asm/cputable.h>
 
@@ -18,9 +19,13 @@ int test_prot_sao(void)
 {
 	char *p;
 
-	/* SAO was introduced in 2.06 and removed in 3.1 */
+	/*
+	 * SAO was introduced in 2.06 and removed in 3.1. It's disabled in
+	 * guests/LPARs by default, so also skip if we are running in a guest.
+	 */
 	SKIP_IF(!have_hwcap(PPC_FEATURE_ARCH_2_06) ||
-		have_hwcap2(PPC_FEATURE2_ARCH_3_1));
+		have_hwcap2(PPC_FEATURE2_ARCH_3_1) ||
+		access("/proc/device-tree/rtas/ibm,hypertas-functions", F_OK) == 0);
 
 	/*
 	 * Ensure we can ask for PROT_SAO.
diff --git a/tools/testing/selftests/timers/Makefile b/tools/testing/selftests/timers/Makefile
index 7656c7ce79d9..0e73a16874c4 100644
--- a/tools/testing/selftests/timers/Makefile
+++ b/tools/testing/selftests/timers/Makefile
@@ -13,6 +13,7 @@ DESTRUCTIVE_TESTS = alarmtimer-suspend valid-adjtimex adjtick change_skew \
 
 TEST_GEN_PROGS_EXTENDED = $(DESTRUCTIVE_TESTS)
 
+TEST_FILES := settings
 
 include ../lib.mk
 
diff --git a/tools/testing/selftests/timers/settings b/tools/testing/selftests/timers/settings
new file mode 100644
index 000000000000..e7b9417537fb
--- /dev/null
+++ b/tools/testing/selftests/timers/settings
@@ -0,0 +1 @@
+timeout=0
diff --git a/tools/testing/selftests/vm/map_hugetlb.c b/tools/testing/selftests/vm/map_hugetlb.c
index 6af951900aa3..312889edb84a 100644
--- a/tools/testing/selftests/vm/map_hugetlb.c
+++ b/tools/testing/selftests/vm/map_hugetlb.c
@@ -83,7 +83,7 @@ int main(int argc, char **argv)
 	}
 
 	if (shift)
-		printf("%u kB hugepages\n", 1 << shift);
+		printf("%u kB hugepages\n", 1 << (shift - 10));
 	else
 		printf("Default size hugepages\n");
 	printf("Mapping %lu Mbytes\n", (unsigned long)length >> 20);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 67cd0b88a6b6..cf88233b819a 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -4332,7 +4332,7 @@ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 void kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
 			       struct kvm_io_device *dev)
 {
-	int i;
+	int i, j;
 	struct kvm_io_bus *new_bus, *bus;
 
 	bus = kvm_get_bus(kvm, bus_idx);
@@ -4349,17 +4349,20 @@ void kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
 
 	new_bus = kmalloc(struct_size(bus, range, bus->dev_count - 1),
 			  GFP_KERNEL_ACCOUNT);
-	if (!new_bus)  {
+	if (new_bus) {
+		memcpy(new_bus, bus, sizeof(*bus) + i * sizeof(struct kvm_io_range));
+		new_bus->dev_count--;
+		memcpy(new_bus->range + i, bus->range + i + 1,
+		       (new_bus->dev_count - i) * sizeof(struct kvm_io_range));
+	} else {
 		pr_err("kvm: failed to shrink bus, removing it completely\n");
-		goto broken;
+		for (j = 0; j < bus->dev_count; j++) {
+			if (j == i)
+				continue;
+			kvm_iodevice_destructor(bus->range[j].dev);
+		}
 	}
 
-	memcpy(new_bus, bus, sizeof(*bus) + i * sizeof(struct kvm_io_range));
-	new_bus->dev_count--;
-	memcpy(new_bus->range + i, bus->range + i + 1,
-	       (new_bus->dev_count - i) * sizeof(struct kvm_io_range));
-
-broken:
 	rcu_assign_pointer(kvm->buses[bus_idx], new_bus);
 	synchronize_srcu_expedited(&kvm->srcu);
 	kfree(bus);